This paper attempts to present a new approach of forecasting the WiMAX traffic by exploiting Artificial
Neural Networks (ANN). To develop the model, actual data is gathered from the LibyaMax network that spans the duration of 180 days in total. Traffic data is separated into three cases based on the base stations involved (A, B and AB). The model implements traffic prediction by emphasizing on the maximum and minimum number of online user whereby two different learning algorithms are tested upon. to find the optimal one. Overall, the experimentation shows promising results of which the most severe error of prediction is not more than 0.0014. This indicates the feasibility of making accurate forecasting of both daily and weekly traffic of the WiMAX network based solely on the maximum and minimum number of users online.
This document introduces a new evaluation scheme and optimization algorithms for universal mobile telecommunications system (UMTS) radio networks that goes beyond traditional snapshot models. The key aspects are:
1) It generalizes interference coupling matrices from user snapshots to average load and introduces an analytical scaling scheme to emulate load control, allowing for fast approximate analysis of network capacity without time-consuming simulations.
2) It presents two novel radio network optimization algorithms - an efficient local search procedure and a mixed integer program that aims to optimize the coupling matrix by designing it.
3) Computational experiments show that optimizing antenna tilts with the new approaches outperforms traditional snapshot models for realistic planning scenarios.
Recent many works have concentrated on
dynamically turning on/off some base stations (BSs) in order to
improve energy efficiency in radio access networks (RANs). In
this survey, we broaden the research over BS switching
operations, which should competition up with traffic load
variations. The proposed method formulate the traffic variations
as a Markov decision process which should differ from dynamic
traffic loads which are still quite challenging to precisely forecast.
A reinforcement learning framework based BS switching
operation scheme was designed in order to minimize the energy
consumption of RANs. Furthermore a transfer actor-critic
algorithm (TACT) is used to speed up the ongoing learning
process, which utilizes the transferred learning expertise in
historical periods or neighboring regions. The proposed TACT
algorithm performs jumpstart and validates the feasibility of
significant energy efficiency increment.
IMPROVED PROPAGATION MODELS FOR LTE PATH LOSS PREDICTION IN URBAN & SUBURBAN ...ijwmn
To maximize the benefits of LTE cellular networks, careful and proper planning is needed. This requires the use of accurate propagation models to quantify the path loss required for base station deployment. Deployed LTE networks in Ghana can barely meet the desired 100Mbps throughput leading to customer dissatisfaction. Network operators rely on transmission planning tools designed for generalized environments that come with already embedded propagation models suited to other environments. A challenge therefore to Ghanaian transmission Network planners will be choosing an accurate and precise propagation model that best suits the Ghanaian environment. Given this, extensive LTE path loss measurements at 800MHz and 2600MHz were taken in selected urban and suburban environments in Ghana and compared with 6 commonly used propagation models. Improved versions of the Ericson, SUI, and ECC-33 developed in this study predict more precisely the path loss in Ghanaian environments compared with commonly used propagation models.
ITA: The Improved Throttled Algorithm of Load Balancing on Cloud ComputingIJCNCJournal
Cloud computing makes the information technology industry boom. It is a great solution for businesses who want to save costs while ensuring the quality of service. One of the key issues that make cloud computing successful is the load balancing technique used in the load balancer to minimize time costs and optimize costs economically. This paper proposes an algorithm to enhance the processing time of tasks so that it can help improve the load balancing capacity on cloud computing. This algorithm, named as Improved Throttled Algorithm (ITA), is an improvement of Throttled Algorithm. The paper uses the Cloud Analyst tool to simulate. The selected algorithms are used to compare: Equally Load, Round Robin, Throttled and TMA. The simulation results show that the proposed algorithm ITA has improved the processing time of tasks, time spent processing requests and reduced the cost of Datacenters compared to the selected popular algorithms as above. The improvement of ITA is because of selecting virtual machines in an index table that is available but in order of priority. It helps response times and processing times remain stable, limits the idling resources, and cloud costs are minimized compared to selected algorithms.
A Data Collection Scheme with Multi-Agent Based Approach for VSNSIRJET Journal
This document discusses a proposed multi-agent based approach for data collection in vehicular sensor networks (VSNs). VSNs consist of sensor nodes in vehicles and roadside units that collect and share data. It is challenging to manage these dynamic networks. The document reviews single mobile agent approaches and proposes deploying multiple mobile agents to more efficiently collect sensor readings across urban areas. This three-layer network architecture uses mobile agents to achieve higher network coverage and reduce energy and delay issues compared to previous approaches.
Campus realities: forecasting user bandwidth utilization using Monte Carlo si...IJECEIAES
This document describes a study that used Monte Carlo simulation to forecast user bandwidth utilization in a campus network. The study collected traffic data from a test campus network setup over 30 days. It analyzed the data to determine bandwidth usage patterns and categorized usage. It then used the data to develop a Monte Carlo simulation model that generated random numbers based on the actual usage data probability distribution. This allowed the model to forecast bandwidth utilization for different days, helping network planners understand demands and design network upgrades accordingly. The model and results help campus networks better plan for high and normal traffic loads to deliver content.
Impact of Packet Inter-arrival Time Features for Online Peer-to-Peer (P2P) Cl...IJECEIAES
Identification of bandwidth-heavy Internet traffic is important for network administrators to throttle high-bandwidth application traffic. Flow features based classification have been previously proposed as promising method to identify Internet traffic based on packet statistical features. The selection of statistical features plays an important role for accurate and timely classification. In this work, we investigate the impact of packet inter-arrival time feature for online P2P classification in terms of accuracy, Kappa statistic and time. Simulations were conducted using available traces from University of Brescia, University of Aalborg and University of Cambridge. Experimental results show that the inclusion of inter-arrival time (IAT) as an online feature increases simulation time and decreases classification accuracy and Kappa statistic.
A novel character segmentation reconstruction approach for license plate reco...Journal Papers
The document discusses a novel approach for license plate recognition that involves character segmentation through partial reconstruction and complete reconstruction for recognition. It aims to develop a system that can handle multiple adverse factors like low resolution, blurring, complex backgrounds, etc. that affect license plate images. The proposed approach uses characteristics of stroke width in the Laplacian and gradient domain to segment character components with incomplete shapes. It then studies the angular information and aspect ratios of character components to further segment characters. Finally, it uses the same stroke width properties to reconstruct the complete shape of each character for improved recognition rates. Experimental results on several benchmark and real-world databases demonstrate the effectiveness of the proposed technique.
A Multipath Connection Model for Traffic MatricesIJERA Editor
Peer-to-Peer (P2P) applications have witnessed an increasing popularity in recent years, which brings new challenges to network management and traffic engineering (TE). As basic input information, P2P traffic matrices are of significant importance for TE. Because of the excessively high cost of direct measurement. In this paper,A multipath connection model for traffic matrices in operational networks. Media files can share the peer to peer, the localization ratio of peer to peer traffic. This evaluates its performance using traffic traces collected from both the real peer to peer video-on-demand and file-sharing applications. The estimation of the general traffic matrices (TM) then used for sending the media file without traffic. Share the media file, source to destination traffic is not occur. So it give high performance and short time process.
Effective Access Point Selection for improving Throughput in Wireless LANEswar Publications
In recent years, WLANs are widely deployed everywhere due to the low-cost and easy installation. Selecting the best access point is the major research problem. The stations in the network should get associate with the suitable access points that results in higher throughput. In IEEE 802.11 wireless networks, the simple association strategy is to get associate to the AP with the strongest RSSI value, which may cause load imbalance and may eventually leads to traffic overhead. Access point selection is still a critical problem.So, a new metric or combination of metrics has to be derived that facilitates the effective selection of an AP to achieve better throughput.
Energy Optimized Link Selection Algorithm for Mobile Cloud ComputingEswar Publications
Mobile cloud computing is the revolutionary distributed computing research area which consists of three different domains: cloud computing, wireless networks and mobile computing targeting to improve the task computational capabilities of the mobile devices in order to minimize the energy consumption. Heavy computations can be offloaded to the cloud to decrease energy consumption for the mobile device. In some mobile cloud applications, it has been more energy inefficient to use the cloud compared to the conventional computing conducted in the local device. Despite mobile cloud computing being a reliable idea, still faces several
problems for mobile phones such as storage, short battery life and so on. One of the most important concerns for mobile devices is low energy consumption. Different network links has different bandwidths to uplink and downlink task as well as data transmission from mobile to cloud or vice-versa. In this paper, a novel optimal link selection algorithm is proposed to minimize the mobile energy. In the first phase, all available networks are
scanned and then signal strength is calculated. All the calculated signals along with network locations are given
input to the optimal link selection algorithm. After the execution of link selection algorithm, an optimal network link is selected.
This document discusses load balancing in 5G networks through offloading traffic between LTE and Wi-Fi networks. It describes the COHERENT architectural framework, which uses network graphs and two main control components - the Central Controller and Coordinator (C3) and Real-Time Controller (RTC) - to manage resource allocation and control tasks like traffic steering and load balancing across heterogeneous networks. Specifically, it focuses on a load balancing use case where traffic is offloaded from overloaded LTE networks to Wi-Fi networks to improve resource utilization and system performance.
"Performance Analysis of In-Network Caching in Content-Centric Advanced Meter...Khaled Ben Driss
"Performance Analysis of In-Network Caching in Content-Centric Advanced Metering Infrastructure" The International Journal of Advanced Computer Science and Applications(IJACSA), Volume 7 Issue 11, 2016.
The document discusses the feasibility of implementing a smart grid in Papua New Guinea using broadband powerline communications. It notes that the existing power grid infrastructure is aging and deteriorating, reducing reliability and efficiency. A smart grid could help address issues like blackouts and lack of automatic fault detection. It presents simulations of digital modulation techniques over powerline channels to evaluate techniques like OFDM and spread spectrum modulation for transmitting data. Bit error rate, signal-to-noise ratio, and other metrics are used to analyze performance over the powerline medium and determine the viability of powerline communications for a smart grid network.
Bit Error Rate Analysis in Multicast Multiple Input Multiple Output Systemsrahulmonikasharma
At the present time whole information and communication technology industry contributes to the global carbon emission. With the aim of reducing the carbon footprint and the operating cost of wireless networks, overall energy reduction is required in the region of two to three orders of magnitude. Meanwhile, significant increase of the network spectrum efficiency is needed to cope with the exponentially increasing traffic loads. Due to this factors spatial modulation (SM) has recently established itself as promising transmission concept which belongs to single-radio frequency large scale multiple input multiple output (MIMO) wireless system. Spatial modulation MIMO takes advantage of whole antenna array at the transmitter, while using limited number of radio frequency chains. The multiple input multiple output multiplies capacity by transmitting different signals over multiple antennas and orthogonal frequency division multiplexing (OFDM), which divides a radio channel into many closely spaced sub channels to provide more reliable communication at high speeds. The system calculate the bit error rate (BER) for multicast multiple input multiple output system with the spatial modulation (SM) and study the effect of signal to noise ratio on bit error rate. MATLAB software is use to simulate system. The simulation results show that bit error rate decreases as signal to noise ratio increases. System reaches zero bit error rate for the value of signal to noise ratio greater than 18dB. System has provided less bit error rate for large signal to noise ratio which improves system performance.
This document summarizes a study on the performance of LTE networks. The researchers conducted passive and active measurements on a commercial LTE network with over 300,000 users to analyze network characteristics and resource utilization. They found that while LTE provides higher bandwidth than 3G, TCP flows often underutilize available bandwidth due to factors like limited receive windows. On average, flows used only 52% of available bandwidth, lengthening transfers and wasting energy. The researchers developed techniques to estimate bandwidth and identify inefficient application behaviors to recommend protocol and design improvements.
This document summarizes a research paper that proposes an energy-efficient topology control algorithm for cooperative ad hoc networks. It begins by introducing cooperative communication (CC) which allows nodes to cooperatively transmit signals to extend transmission range and reduce power. Previous topology control research with CC focused only on connectivity and power, ignoring energy efficiency of paths. The paper studies a new problem of energy-efficient topology control with CC (ETCC) to obtain a topology with minimum total energy consumption while ensuring energy-efficient paths. It proposes selecting optimal relay nodes for CC networks to reduce overall power usage. A greedy algorithm is presented to construct a cooperative energy spanner topology where least energy paths are guaranteed while maintaining a connected network under the CC model.
Forecasting is essential for capital budgeting and involves analyzing past data to establish future expectations. Quantitative forecasting uses statistical techniques like regression analysis to model relationships between variables in historical data and project them into the future. Qualitative forecasting relies more on expert judgment through techniques like the Delphi method. The document provides examples of quantitative forecasting using simple, multiple, and time series regression analysis in Excel to model sales data and generate sales forecasts.
Artificial neural networks are computer programs that can recognize patterns in data and produce models to represent that data. They are inspired by the human brain in how knowledge is acquired through learning and stored in the connections between neurons. Neural networks learn by adjusting the strengths of connections between neurons based on examples provided during training. They are able to model and learn both linear and nonlinear relationships in data.
This document discusses a traffic analysis project on Gomti Nagar in Lucknow, India with respect to pedestrian facilities. It provides background on traffic studies and their purpose in evaluating transportation systems. It also outlines different types of traffic counts and analysis methods, including manual counts, cordon counts, screen line counts, intersection counts, and pedestrian counts. The document describes the project timeline and concludes that future transportation investments in the area must be strategically coordinated with land use plans to maximize benefits.
In this study, we have to project the airline travel for the next 12 months .The dataset used here is SASHELP.AIR which is Airline data and contains two variables – DATE and AIR( labeled as International Airline Travel).It contains the data from JAN 1949 to DEC 1960.
This document describes a special project on using an artificial neural network (ANN) for load flow studies of the MSU-IIT electrical system. The objectives are to model the power system as a 5-bus system, evaluate bus voltages using a power flow program under different loads, train an ANN using the power flow results, and validate the ANN's accuracy by comparing its results to the power flow program. The document reviews literature on load flow studies, numerical methods, ANNs, and discusses how ANNs could provide faster and more accurate solutions to complex load flow problems compared to numerical methods.
This document discusses a presentation on a traffic volume study. It outlines the objectives, scope, methodology, data collection, and purposes of conducting a traffic volume study. The study aims to count vehicle volumes, types, and flows over time to help with transportation planning, design, and management. Methodologies include manual counting methods using hand counters or video review as well as automatic methods using sensors to detect vehicle presence and classify types.
This document contains information from a traffic study conducted at Shahid Tajuddin Ahmed Avenue in Dhaka, Bangladesh. A group of 6 students conducted manual traffic counts over two 15-minute periods in both directions at the location. They classified over 2000 vehicles and calculated passenger car equivalents, directional distribution, hourly flow rates, and average daily traffic. Their analysis found the directional split to be 54% from Shatrasta to the flyover and 46% from the flyover to Shatrasta. Peak hourly flows were around 2000 passenger car units in each direction. This traffic study provides data to understand volume, composition, and flow patterns at this location.
The document discusses a traffic volume study conducted at Russell Square in Dhaka. It defines key terms like average daily traffic (ADT) and level of service (LOS). Data was collected manually over three hours and analyzed to find a service flow rate of 1,131 passenger car units per hour, indicating an LOS of D. The average daily traffic was calculated as 16,080 passenger cars with an annual average of 22,432. Traffic movement was found to be nearly equal in both directions.
Applications of Artificial Neural Networks in Civil EngineeringPramey Zode
An artificial brain-like network based on certain mathematical algorithms developed using a numerical computing environment is called as an ‘Artificial Neural Network (ANN)’. Many civil engineering problems which need understanding of physical processes are found to be time consuming and inaccurate to evaluate using conventional approaches. In this regard, many ANNs have been seen as a reliable and practical alternative to solve such problems. Literature review reveals that ANNs have already being used in solving numerous civil engineering problems. This study explains some cases where ANNs have been used and its future scope is also discussed.
P REDICTION F OR S HORT -T ERM T RAFFIC F LOW B ASED O N O PTIMIZED W...ijcsit
Short term traffic forecasting has been a very impo
rtant consideration in many areas of transportation
research for more than 3 decades. Short-term traffi
c forecasting based on data driven methods is one o
f the
most dynamic and developing research arenas with en
ormous published literature. In order to improve
forecasting model accuracy of wavelet neural networ
k, an adaptive particle swarm optimization algorith
m
based on cloud theory was proposed, not only to hel
p improve search performance, but also speed up
individual optimizing ability. And the inertia weig
ht adaptively changes depending on X-conditional cl
oud
generator which has the stable tendency and randomn
ess property .Then the adaptive particle swarm
optimization algorithm based on cloud theory was us
ed to optimize the weights and thresholds of wavele
t
BP neural network, Instead of traditional gradient
descent method . At last, wavelet BP neural network
was
trained to search for the optimal solution. Based o
n above theory, an improved wavelet neural network
model based on modified particle swarm optimization
algorithm was proposed and the availability of the
modified prediction method was proved by predicting
the time series of real traffic flow. At last, the
computer simulations have shown that the nonlinear
fitting and accuracy of the modified prediction
methods are better than other prediction methods.
This document discusses two projects involving narrow pavement widening conducted by the San Angelo District. The first project details an in-house method developed using a road widener attachment and conveyor system to widen roads by 2-3 feet at a cost of $2000 and production rate of 0.5 miles per day. The second project discusses the widening of RM 336 from 18-20 feet to 21 feet using a Roadtec milling machine to remove material and widen the road. The RM 336 project cost $145,000 per mile to complete.
This presentation discusses pavement construction issues, and the use of interlayers in pavement widening. Prepared by Katie Strain and Michael Samueloff of TENCATE. Please remember to cite this research if the information you find here is used.
Artificial neural networks are a form of artificial intelligence inspired by biological neural networks. They are composed of interconnected processing units that can learn patterns from data through training. Neural networks are well-suited for tasks like pattern recognition, classification, and prediction. They learn by example without being explicitly programmed, similarly to how the human brain learns.
- The document introduces artificial neural networks, which aim to mimic the structure and functions of the human brain.
- It describes the basic components of artificial neurons and how they are modeled after biological neurons. It also explains different types of neural network architectures.
- The document discusses supervised and unsupervised learning in neural networks. It provides details on the backpropagation algorithm, a commonly used method for training multilayer feedforward neural networks using gradient descent.
This document summarizes previous literature on traffic analysis and congestion modeling in mobile networks. It reviews works that have evaluated network performance at different elements like the BTS, BSC and MSC. However, none addressed congestion at all three basic elements (BTS, BSC, MSC) to characterize end-to-end connections, or used busy hour traffic data to adequately dimension network elements. The document also identifies gaps in the existing research, such as not establishing the statistical causes of congestion or using sufficient data. It proposes to analyze traffic at the access and core networks using live network data over two years to help dimension elements and identify congestion causes to develop an accurate congestion prediction model.
Probability Density Functions of the Packet Length for Computer Networks With...IJCNCJournal
The research on Internet traffic classification and identification, with application on prevention of attacks
and intrusions, increased considerably in the past years. Strategies based on statistical characteristics of
the Internet traffic, that use parameters such as packet length (size) and inter-arrival time and their
probability density functions, are popular. This paper presents a new statistical modeling for packet length,
which shows that it can be modeled using a probability density function that involves a normal or a beta
distribution, according to the traffic generated by the users. The proposed functions has parameters that
depend on the type of traffic and can be used as part of an Internet traffic classification and identification
strategy. The models can be used to compare, simulate and estimate the computer network traffic, as well
as to generate synthetic traffic and estimate the packets processing capacity of Internet routers
IRJET- An Incentive Framework for Cellular Traffic OffloadingIRJET Journal
This document proposes an incentive framework to motivate cellular users to offload traffic through other intermittent networks like Delay Tolerant Networks (DTNs) and WiFi hotspots. The framework uses a reverse auction where users bid on how long they are willing to delay downloading data in exchange for discounts on their cellular plan. The goal is to minimize costs for the cellular provider while meeting traffic offloading targets. Models are developed to predict how much traffic individual users could offload based on their data access and mobility patterns for DTNs, and mobility and nearby WiFi availability for WiFi offloading. The proposed incentive framework aims to maximize offloading by prioritizing users with high delay tolerance and offloading potential.
The International Journal of Engineering & Science is aimed at providing a platform for researchers, engineers, scientists, or educators to publish their original research results, to exchange new ideas, to disseminate information in innovative designs, engineering experiences and technological skills. It is also the Journal's objective to promote engineering and technology education. All papers submitted to the Journal will be blind peer-reviewed. Only original articles will be published.
The papers for publication in The International Journal of Engineering& Science are selected through rigorous peer reviews to ensure originality, timeliness, relevance, and readability.
A Survey on the Common Network Traffic Sources ModelsCSCJournals
Selecting the appropriate traffic model can lead to the successful design of networks. The more accurate is the traffic model the better is the system quantified in terms of its performance Successful design lead to enhancement the overall performance of the whole of network .in literature there is innumerous traffic models proposed for understanding and analyzing the traffic characteristics of networks. Consequently, the study of traffic models to understand the features of the models and identify eventually the best traffic model, for a concerned environment has become a crucial and lucrative task. Good traffic modeling is also a basic requirement for accurate capacity planning. This paper provides an overview of some of the widely used network traffic models, highlighting the core features of the model and traffic characteristics they capture best. Finally we found that the N_BURST traffic model can capture the traffic characteristics of most types of networks, under every possible circumstance rather than any type of traffic model.
This document reviews the Security and QoS Aware Dynamic Clustering (SQADC) Routing protocol for cognitive radio networks (CRNs). It first discusses existing routing protocols for CRNs and identifies gaps, including that most focus on improving quality of service but few address security issues. It then outlines the objectives of designing a new routing protocol to achieve a tradeoff between QoS performance and security performance for CRNs. The proposed SQADC protocol will use dynamic clustering based on ant colony optimization for cluster head selection and re-clustering to optimize spectrum allocation and quality of service while introducing a lightweight trust-based mechanism for detecting malicious nodes.
Bit Error Rate Analysis in WiMAX Communication at Vehicular Speeds using mod...IJMER
At high vehicular speeds, rapid changes in surrounding environments, cause severe fading at
the receiver, resulting a drastic fall in throughput and unless any proactive measure is taken to combat
this problem, throughput becomes insufficient to support many applications, particularly those with
multimedia contents. Bit Error Rate (BER) estimation is an integral part of any proactive measure and
recent studies suggest that Nakagami-m model performs better for modelling channel fading in wireless
communications at high vehicular speeds. No work has been reported in literature that estimates BER
at high vehicular speeds in WiMAX communication using Nakagami-m model. In this thesis, we develop
and present an analytical model to estimate BER in WiMAX at vehicular speeds using Nakagami-m
fading model. The proposed model is adaptive and can be used with resource management schemes
designed for fixed, nomadic, and mobile WiMAX communications.
PERFORMANCE ANALYSIS OF MOBILE DATA OFFLOADING IN HETEROGENEOUS NETWORKSnexgentechnology
GET IEEE BIG DATA,JAVA ,DOTNET,ANDROID ,NS2,MATLAB,EMBEDED AT LOW COST WITH BEST QUALITY PLEASE CONTACT BELOW NUMBER
FOR MORE INFORMATION PLEASE FIND THE BELOW DETAILS:
Nexgen Technology
No :66,4th cross,Venkata nagar,
Near SBI ATM,
Puducherry.
Email Id: praveen@nexgenproject.com
Mobile: 9791938249
Telephone: 0413-2211159
www.nexgenproject.com
Residual balanced attention network for real-time traffic scene semantic segm...IJECEIAES
Intelligent transportation systems (ITS) are among the most focused research in this century. Actually, autonomous driving provides very advanced tasks in terms of road safety monitoring which include identifying dangers on the road and protecting pedestrians. In the last few years, deep learning (DL) approaches and especially convolutional neural networks (CNNs) have been extensively used to solve ITS problems such as traffic scene semantic segmentation and traffic signs classification. Semantic segmentation is an important task that has been addressed in computer vision (CV). Indeed, traffic scene semantic segmentation using CNNs requires high precision with few computational resources to perceive and segment the scene in real-time. However, we often find related work focusing only on one aspect, the precision, or the number of computational parameters. In this regard, we propose RBANet, a robust and lightweight CNN which uses a new proposed balanced attention module, and a new proposed residual module. Afterward, we have simulated our proposed RBANet using three loss functions to get the best combination using only 0.74M parameters. The RBANet has been evaluated on CamVid, the most used dataset in semantic segmentation, and it has performed well in terms of parameters’ requirements and precision compared to related work.
8 of the Must-Read Network & Data Communication Articles Published this weeke...IJCNCJournal
Beamforming for millimetre-wave (mmWave) frequencies has been studied for many years. It is considered as an important enabling technology for communications in these high-frequency ranges and it received a lot of attention in the research community. The special characteristics of the mmWave band made the beamforming problem a challenging one because it depends on many environmental and operational factors. These challenges made any model-based architecture fit only special applications, working scenarios, and specific environment geometry. All these reasons increased the need for more general machine learning based beamforming systems that can work in different environments and conditions. This increased the need for an extended adjustable dataset that can serve as a tool for any machine learning technique to build an efficient beamforming architecture. Deep MIMO dataset has been used in many architectures and designs and has proved its benefits and flexibility to fit in many cases. In this paper, we study the extension of collaborative beamforming that includes many cooperating base stations by studying the impact of User Equipment (UE) speed ranges on the beamforming performance, optimizing the parameters of the neural network architecture of the beamforming design, and suggesting the optimal design that gives the best performance for as a small dataset as possible. Suggested architecture can achieve the same performance achieved before with up to 33% reduction in the dataset size used to train the system which provides a huge reduction in the data collection and processing time.
Traffic Lights Control System for Indian Cities using WSN and Fuzzy ControlIRJET Journal
This document proposes a traffic light control system for Indian cities that uses a wireless sensor network (WSN) and fuzzy control. Sensors would monitor traffic in real-time and transmit data to a centralized control system. Multiple fuzzy logic controllers, one for each traffic light phase, would work in parallel to dynamically manage both the phase timing and green light times. This approach aims to reduce vehicle wait times under heavy traffic by combining the advantages of WSNs and parallel fuzzy controllers that can manage phases individually. A simulation showed this multi-controller approach outperformed single-controller methods.
Enhancement of Single Moving Average Time Series Model Using Rough k-Means fo...IJERA Editor
This document proposes combining rough k-means clustering with a single moving average time series model to improve network traffic prediction. The document first discusses related work on network traffic prediction using various time series models. It then describes using a single moving average model to initially predict network packet loads, and enhancing this prediction by incorporating clusters identified through rough k-means analysis of the network data. The proposed integrated model is evaluated on real network traffic data and shown to improve prediction accuracy over the conventional single moving average model alone.
Target Response Electrical usage Profile Clustering using Big DataIRJET Journal
This document discusses using clustering algorithms to analyze large datasets from smart meters to identify patterns in electricity usage. It proposes a new method for clustering micro-clusters that uses a density graph to explicitly represent the density of data points between micro-clusters. This allows the micro-clusters to be re-clustered into a smaller number of final clusters. The algorithm involves constructing a minimum spanning tree from the density graph, partitioning it into trees representing clusters, and selecting representative features from each micro-cluster. This clustering-based feature subset selection aims to improve the efficiency and accuracy of load profiling and short-term load forecasting using big data from smart meters.
Performance Analysis of Data Traffic Offload Scheme on Long Term Evolution (L...TELKOMNIKA JOURNAL
One of new mobile technology is being developed by 3GPP is Long Term Evolution (LTE). LTE
usually used by user because provide high data rate. Many traffic sending over LTE, makes several users
didn’t get good Quality of Service (QoS). Traffic diversion is needed to increasing QoS value. It can be
done with offloading data method from LTE to Wi-Fi network. This paper using 802.11ah standard to
evaluate Wi-Fi network. IEEE 802.11ah have 1000 meters coverage area and efficiency energy
mechanism, which is proposed for M2M in 5G techonology. Some research has proven that traffic
diversion with offloading can increasing network performance. The contribution of this paper is to evaluate
the impact of traffic offload between LTE and IEEE 802.11ah standard. This paper propose two scenarios
using increment number of user and increment mobility speed of user to evaluate throughput and delay
value before and after the offload process. The simulation will simulate using Network Simulator-3. We can
conclude that network performance after offloading is better for every scenario. For increment number of
user scenario, throughput value increasing 29.08%, and delay decreasing 8.12%. Scenario with increment
mobility speed of user obtain throughput value increasing 37,57%, and delay value decreasing 27.228%.
IRJET- Smart Railway System using Trip Chaining MethodIRJET Journal
This document proposes a smart railway system using trip chaining and big data analysis of passenger information from smart cards. The system would collect data like passenger name, age, travel time, source and destination stations from smart cards. It would then use k-means clustering to group passengers by age and travel patterns. A naïve bayes classifier would predict passenger counts at each station. This analysis of passenger data could help the railway department improve infrastructure and services based on demand.
The prediction of mobile data traffic based on the ARIMA model and disruptive...TELKOMNIKA JOURNAL
Disruptive technologies, which are caused by the cellular evolution including
the Internet of Things (IoT), have significantly contributed data traffic to the mobile
telecommunication network in the era of Industry 4.0. These technologies cause
erroneous predictions prompting mobile operators to upgrade their network, which
leads to revenue loss. Besides, the inaccuracy of network prediction also creates
a bottleneck problem that affects the performance of the telecommunication network,
especially on the mobile backhaul. We propose a new technique to predict more
accurate data traffic. This research used a univariate Autoregressive Integrated Moving
Average (ARIMA) model combined with a new disruptive formula. Another model,
called a disruptive formula, uses a judgmental approach based on four variables:
Political, Economic, Social, Technological (PEST), cost, time to market, and market
share. The disruptive formula amplifies the ARIMA calculation as a new combination
formula from the judgmental and statistical approach. The results show that
the disruptive formula combined with the ARIMA model has a low error in mobile
data forecasting compared to the conventional ARIMA. The conventional ARIMA
shows the average mobile data traffic to be 49.19 Mb/s and 156.93 Mb/s for the 3G and
4G, respectively; whereas the ARIMA with disruptive formula shows more optimized
traffic, reaching 56.72 Mb/s and 199.73 Mb/s. The higher values in the ARIMA with
disruptive formula are closest to the prediction of the mobile data forecast. This result
suggests that the combination of statistical and computational approach provide more
accurate prediction method for the mobile backhaul networks.
A Survey on Data Aggregation Cluster based Technique in Wireless Sensor Netwo...IRJET Journal
This document summarizes a survey on using cluster-based data aggregation techniques in wireless sensor networks for railway track monitoring. It discusses how WSNs can be used to automatically monitor tracks and reduce human inspection needs. It reviews different data aggregation approaches that combine data to reduce redundancy and transmission costs. In particular, it examines the Low Energy Adaptive Clustering Hierarchy (LEACH) protocol, which forms clusters to perform in-network data processing and transmit aggregated data to sinks. Using this clustering approach can achieve high accuracy, reduce energy consumption, and prolong the lifetime of WSNs for railway track condition monitoring.
Bandwidth allocation mechanisms in the next mobile generation: A practical Ap...iosrjce
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
1) The document proposes an algorithm for bandwidth management in integrated LTE and WLAN networks. It aims to increase bandwidth availability in lower data rate networks like WLAN to reduce congestion in high data rate networks like LTE.
2) A simulation tool was developed in MATLAB to simulate the proposed algorithm. It uses Poisson distribution for traffic generation and uniform distribution for mobile location. Parameters like number of users, traffic type, user class, and bandwidth are considered.
3) Simulation results show that the new algorithm improves bandwidth availability in WLAN and reduces congestion in the LTE network. This ensures quality of service but may introduce high signaling load due to frequent handovers between networks.
Call Admission Control (CAC) with Load Balancing Approach for the WLAN NetworksIJARIIT
The cell migrations take place between the different network operators, and require the significant information exchange between the operators to handle the migratory users. The new user registration requires the pre-shared information from the user’s equipment, which signifies the user recognition before registering the new user over the network. In this thesis, the proposed model has been aimed at the development of the new call admission control mechanism with the sub-channel assignment. The very basic utilization of the proposed model is to increase the number of the users over the given cell units, which is realized by using the sub-channel assignment to the users of the network. The proposed model is aimed at solving the issue by assigning the dual sub channels over the single communication channel. Also the proposed model is aimed at handling the minimum resource users by incorporating the load balancing approach over the given network segment. The load balancing approach shares the load of the overloaded cell with the cell with lowest resource utilization. The proposed model performance has been evaluated in the various scenarios and over all of the BTS nodes. The proposed model results have been obtained in the form of the resource utilization, network load, transmission delay, consumed bandwidth and data loss. The proposed model has shown the efficiency obtained by using the proposed call admission control (CAC) along with the new load balancing mechanism. The proposed model has shown the robustness of the proposed model in handling the cell overloading factors.
Similar to FORECASTING THE WIMAX TRAFFIC VIA MODIFIED ARTIFICIAL NEURAL NETWORK MODELS (20)
UiPath Community Day Kraków: Devs4Devs ConferenceUiPathCommunity
We are honored to launch and host this event for our UiPath Polish Community, with the help of our partners - Proservartner!
We certainly hope we have managed to spike your interest in the subjects to be presented and the incredible networking opportunities at hand, too!
Check out our proposed agenda below 👇👇
08:30 ☕ Welcome coffee (30')
09:00 Opening note/ Intro to UiPath Community (10')
Cristina Vidu, Global Manager, Marketing Community @UiPath
Dawid Kot, Digital Transformation Lead @Proservartner
09:10 Cloud migration - Proservartner & DOVISTA case study (30')
Marcin Drozdowski, Automation CoE Manager @DOVISTA
Pawel Kamiński, RPA developer @DOVISTA
Mikolaj Zielinski, UiPath MVP, Senior Solutions Engineer @Proservartner
09:40 From bottlenecks to breakthroughs: Citizen Development in action (25')
Pawel Poplawski, Director, Improvement and Automation @McCormick & Company
Michał Cieślak, Senior Manager, Automation Programs @McCormick & Company
10:05 Next-level bots: API integration in UiPath Studio (30')
Mikolaj Zielinski, UiPath MVP, Senior Solutions Engineer @Proservartner
10:35 ☕ Coffee Break (15')
10:50 Document Understanding with my RPA Companion (45')
Ewa Gruszka, Enterprise Sales Specialist, AI & ML @UiPath
11:35 Power up your Robots: GenAI and GPT in REFramework (45')
Krzysztof Karaszewski, Global RPA Product Manager
12:20 🍕 Lunch Break (1hr)
13:20 From Concept to Quality: UiPath Test Suite for AI-powered Knowledge Bots (30')
Kamil Miśko, UiPath MVP, Senior RPA Developer @Zurich Insurance
13:50 Communications Mining - focus on AI capabilities (30')
Thomasz Wierzbicki, Business Analyst @Office Samurai
14:20 Polish MVP panel: Insights on MVP award achievements and career profiling
Implementations of Fused Deposition Modeling in real worldEmerging Tech
The presentation showcases the diverse real-world applications of Fused Deposition Modeling (FDM) across multiple industries:
1. **Manufacturing**: FDM is utilized in manufacturing for rapid prototyping, creating custom tools and fixtures, and producing functional end-use parts. Companies leverage its cost-effectiveness and flexibility to streamline production processes.
2. **Medical**: In the medical field, FDM is used to create patient-specific anatomical models, surgical guides, and prosthetics. Its ability to produce precise and biocompatible parts supports advancements in personalized healthcare solutions.
3. **Education**: FDM plays a crucial role in education by enabling students to learn about design and engineering through hands-on 3D printing projects. It promotes innovation and practical skill development in STEM disciplines.
4. **Science**: Researchers use FDM to prototype equipment for scientific experiments, build custom laboratory tools, and create models for visualization and testing purposes. It facilitates rapid iteration and customization in scientific endeavors.
5. **Automotive**: Automotive manufacturers employ FDM for prototyping vehicle components, tooling for assembly lines, and customized parts. It speeds up the design validation process and enhances efficiency in automotive engineering.
6. **Consumer Electronics**: FDM is utilized in consumer electronics for designing and prototyping product enclosures, casings, and internal components. It enables rapid iteration and customization to meet evolving consumer demands.
7. **Robotics**: Robotics engineers leverage FDM to prototype robot parts, create lightweight and durable components, and customize robot designs for specific applications. It supports innovation and optimization in robotic systems.
8. **Aerospace**: In aerospace, FDM is used to manufacture lightweight parts, complex geometries, and prototypes of aircraft components. It contributes to cost reduction, faster production cycles, and weight savings in aerospace engineering.
9. **Architecture**: Architects utilize FDM for creating detailed architectural models, prototypes of building components, and intricate designs. It aids in visualizing concepts, testing structural integrity, and communicating design ideas effectively.
Each industry example demonstrates how FDM enhances innovation, accelerates product development, and addresses specific challenges through advanced manufacturing capabilities.
MYIR Product Brochure - A Global Provider of Embedded SOMs & SolutionsLinda Zhang
This brochure gives introduction of MYIR Electronics company and MYIR's products and services.
MYIR Electronics Limited (MYIR for short), established in 2011, is a global provider of embedded System-On-Modules (SOMs) and
comprehensive solutions based on various architectures such as ARM, FPGA, RISC-V, and AI. We cater to customers' needs for large-scale production, offering customized design, industry-specific application solutions, and one-stop OEM services.
MYIR, recognized as a national high-tech enterprise, is also listed among the "Specialized
and Special new" Enterprises in Shenzhen, China. Our core belief is that "Our success stems from our customers' success" and embraces the philosophy
of "Make Your Idea Real, then My Idea Realizing!"
Are you interested in dipping your toes in the cloud native observability waters, but as an engineer you are not sure where to get started with tracing problems through your microservices and application landscapes on Kubernetes? Then this is the session for you, where we take you on your first steps in an active open-source project that offers a buffet of languages, challenges, and opportunities for getting started with telemetry data.
The project is called openTelemetry, but before diving into the specifics, we’ll start with de-mystifying key concepts and terms such as observability, telemetry, instrumentation, cardinality, percentile to lay a foundation. After understanding the nuts and bolts of observability and distributed traces, we’ll explore the openTelemetry community; its Special Interest Groups (SIGs), repositories, and how to become not only an end-user, but possibly a contributor.We will wrap up with an overview of the components in this project, such as the Collector, the OpenTelemetry protocol (OTLP), its APIs, and its SDKs.
Attendees will leave with an understanding of key observability concepts, become grounded in distributed tracing terminology, be aware of the components of openTelemetry, and know how to take their first steps to an open-source contribution!
Key Takeaways: Open source, vendor neutral instrumentation is an exciting new reality as the industry standardizes on openTelemetry for observability. OpenTelemetry is on a mission to enable effective observability by making high-quality, portable telemetry ubiquitous. The world of observability and monitoring today has a steep learning curve and in order to achieve ubiquity, the project would benefit from growing our contributor community.
Coordinate Systems in FME 101 - Webinar SlidesSafe Software
If you’ve ever had to analyze a map or GPS data, chances are you’ve encountered and even worked with coordinate systems. As historical data continually updates through GPS, understanding coordinate systems is increasingly crucial. However, not everyone knows why they exist or how to effectively use them for data-driven insights.
During this webinar, you’ll learn exactly what coordinate systems are and how you can use FME to maintain and transform your data’s coordinate systems in an easy-to-digest way, accurately representing the geographical space that it exists within. During this webinar, you will have the chance to:
- Enhance Your Understanding: Gain a clear overview of what coordinate systems are and their value
- Learn Practical Applications: Why we need datams and projections, plus units between coordinate systems
- Maximize with FME: Understand how FME handles coordinate systems, including a brief summary of the 3 main reprojectors
- Custom Coordinate Systems: Learn how to work with FME and coordinate systems beyond what is natively supported
- Look Ahead: Gain insights into where FME is headed with coordinate systems in the future
Don’t miss the opportunity to improve the value you receive from your coordinate system data, ultimately allowing you to streamline your data analysis and maximize your time. See you there!
Data Protection in a Connected World: Sovereignty and Cyber Securityanupriti
Delve into the critical intersection of data sovereignty and cyber security in this presentation. Explore unconventional cyber threat vectors and strategies to safeguard data integrity and sovereignty in an increasingly interconnected world. Gain insights into emerging threats and proactive defense measures essential for modern digital ecosystems.
Interaction Latency: Square's User-Centric Mobile Performance MetricScyllaDB
Mobile performance metrics often take inspiration from the backend world and measure resource usage (CPU usage, memory usage, etc) and workload durations (how long a piece of code takes to run).
However, mobile apps are used by humans and the app performance directly impacts their experience, so we should primarily track user-centric mobile performance metrics. Following the lead of tech giants, the mobile industry at large is now adopting the tracking of app launch time and smoothness (jank during motion).
At Square, our customers spend most of their time in the app long after it's launched, and they don't scroll much, so app launch time and smoothness aren't critical metrics. What should we track instead?
This talk will introduce you to Interaction Latency, a user-centric mobile performance metric inspired from the Web Vital metric Interaction to Next Paint"" (web.dev/inp). We'll go over why apps need to track this, how to properly implement its tracking (it's tricky!), how to aggregate this metric and what thresholds you should target.
INDIAN AIR FORCE FIGHTER PLANES LIST.pdfjackson110191
These fighter aircraft have uses outside of traditional combat situations. They are essential in defending India's territorial integrity, averting dangers, and delivering aid to those in need during natural calamities. Additionally, the IAF improves its interoperability and fortifies international military alliances by working together and conducting joint exercises with other air forces.
Details of description part II: Describing images in practice - Tech Forum 2024BookNet Canada
This presentation explores the practical application of image description techniques. Familiar guidelines will be demonstrated in practice, and descriptions will be developed “live”! If you have learned a lot about the theory of image description techniques but want to feel more confident putting them into practice, this is the presentation for you. There will be useful, actionable information for everyone, whether you are working with authors, colleagues, alone, or leveraging AI as a collaborator.
Link to presentation recording and transcript: https://bnctechforum.ca/sessions/details-of-description-part-ii-describing-images-in-practice/
Presented by BookNet Canada on June 25, 2024, with support from the Department of Canadian Heritage.
Fluttercon 2024: Showing that you care about security - OpenSSF Scorecards fo...Chris Swan
Have you noticed the OpenSSF Scorecard badges on the official Dart and Flutter repos? It's Google's way of showing that they care about security. Practices such as pinning dependencies, branch protection, required reviews, continuous integration tests etc. are measured to provide a score and accompanying badge.
You can do the same for your projects, and this presentation will show you how, with an emphasis on the unique challenges that come up when working with Dart and Flutter.
The session will provide a walkthrough of the steps involved in securing a first repository, and then what it takes to repeat that process across an organization with multiple repos. It will also look at the ongoing maintenance involved once scorecards have been implemented, and how aspects of that maintenance can be better automated to minimize toil.
Transcript: Details of description part II: Describing images in practice - T...BookNet Canada
This presentation explores the practical application of image description techniques. Familiar guidelines will be demonstrated in practice, and descriptions will be developed “live”! If you have learned a lot about the theory of image description techniques but want to feel more confident putting them into practice, this is the presentation for you. There will be useful, actionable information for everyone, whether you are working with authors, colleagues, alone, or leveraging AI as a collaborator.
Link to presentation recording and slides: https://bnctechforum.ca/sessions/details-of-description-part-ii-describing-images-in-practice/
Presented by BookNet Canada on June 25, 2024, with support from the Department of Canadian Heritage.
Are you interested in learning about creating an attractive website? Here it is! Take part in the challenge that will broaden your knowledge about creating cool websites! Don't miss this opportunity, only in "Redesign Challenge"!
Blockchain and Cyber Defense Strategies in new genre timesanupriti
Explore robust defense strategies at the intersection of blockchain technology and cybersecurity. This presentation delves into proactive measures and innovative approaches to safeguarding blockchain networks against evolving cyber threats. Discover how secure blockchain implementations can enhance resilience, protect data integrity, and ensure trust in digital transactions. Gain insights into cutting-edge security protocols and best practices essential for mitigating risks in the blockchain ecosystem.
What's Next Web Development Trends to Watch.pdfSeasiaInfotech2
Explore the latest advancements and upcoming innovations in web development with our guide to the trends shaping the future of digital experiences. Read our article today for more information.
GDG Cloud Southlake #34: Neatsun Ziv: Automating AppsecJames Anderson
The lecture titled "Automating AppSec" delves into the critical challenges associated with manual application security (AppSec) processes and outlines strategic approaches for incorporating automation to enhance efficiency, accuracy, and scalability. The lecture is structured to highlight the inherent difficulties in traditional AppSec practices, emphasizing the labor-intensive triage of issues, the complexity of identifying responsible owners for security flaws, and the challenges of implementing security checks within CI/CD pipelines. Furthermore, it provides actionable insights on automating these processes to not only mitigate these pains but also to enable a more proactive and scalable security posture within development cycles.
The Pains of Manual AppSec:
This section will explore the time-consuming and error-prone nature of manually triaging security issues, including the difficulty of prioritizing vulnerabilities based on their actual risk to the organization. It will also discuss the challenges in determining ownership for remediation tasks, a process often complicated by cross-functional teams and microservices architectures. Additionally, the inefficiencies of manual checks within CI/CD gates will be examined, highlighting how they can delay deployments and introduce security risks.
Automating CI/CD Gates:
Here, the focus shifts to the automation of security within the CI/CD pipelines. The lecture will cover methods to seamlessly integrate security tools that automatically scan for vulnerabilities as part of the build process, thereby ensuring that security is a core component of the development lifecycle. Strategies for configuring automated gates that can block or flag builds based on the severity of detected issues will be discussed, ensuring that only secure code progresses through the pipeline.
Triaging Issues with Automation:
This segment addresses how automation can be leveraged to intelligently triage and prioritize security issues. It will cover technologies and methodologies for automatically assessing the context and potential impact of vulnerabilities, facilitating quicker and more accurate decision-making. The use of automated alerting and reporting mechanisms to ensure the right stakeholders are informed in a timely manner will also be discussed.
Identifying Ownership Automatically:
Automating the process of identifying who owns the responsibility for fixing specific security issues is critical for efficient remediation. This part of the lecture will explore tools and practices for mapping vulnerabilities to code owners, leveraging version control and project management tools.
Three Tips to Scale the Shift Left Program:
Finally, the lecture will offer three practical tips for organizations looking to scale their Shift Left security programs. These will include recommendations on fostering a security culture within development teams, employing DevSecOps principles to integrate security throughout the development
Navigating Post-Quantum Blockchain: Resilient Cryptography in Quantum Threatsanupriti
In the rapidly evolving landscape of blockchain technology, the advent of quantum computing poses unprecedented challenges to traditional cryptographic methods. As quantum computing capabilities advance, the vulnerabilities of current cryptographic standards become increasingly apparent.
This presentation, "Navigating Post-Quantum Blockchain: Resilient Cryptography in Quantum Threats," explores the intersection of blockchain technology and quantum computing. It delves into the urgent need for resilient cryptographic solutions that can withstand the computational power of quantum adversaries.
Key topics covered include:
An overview of quantum computing and its implications for blockchain security.
Current cryptographic standards and their vulnerabilities in the face of quantum threats.
Emerging post-quantum cryptographic algorithms and their applicability to blockchain systems.
Case studies and real-world implications of quantum-resistant blockchain implementations.
Strategies for integrating post-quantum cryptography into existing blockchain frameworks.
Join us as we navigate the complexities of securing blockchain networks in a quantum-enabled future. Gain insights into the latest advancements and best practices for safeguarding data integrity and privacy in the era of quantum threats.
AI_dev Europe 2024 - From OpenAI to Opensource AIRaphaël Semeteys
Navigating Between Commercial Ownership and Collaborative Openness
This presentation explores the evolution of generative AI, highlighting the trajectories of various models such as GPT-4, and examining the dynamics between commercial interests and the ethics of open collaboration. We offer an in-depth analysis of the levels of openness of different language models, assessing various components and aspects, and exploring how the (de)centralization of computing power and technology could shape the future of AI research and development. Additionally, we explore concrete examples like LLaMA and its descendants, as well as other open and collaborative projects, which illustrate the diversity and creativity in the field, while navigating the complex waters of intellectual property and licensing.
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2024/07/intels-approach-to-operationalizing-ai-in-the-manufacturing-sector-a-presentation-from-intel/
Tara Thimmanaik, AI Systems and Solutions Architect at Intel, presents the “Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” tutorial at the May 2024 Embedded Vision Summit.
AI at the edge is powering a revolution in industrial IoT, from real-time processing and analytics that drive greater efficiency and learning to predictive maintenance. Intel is focused on developing tools and assets to help domain experts operationalize AI-based solutions in their fields of expertise.
In this talk, Thimmanaik explains how Intel’s software platforms simplify labor-intensive data upload, labeling, training, model optimization and retraining tasks. She shows how domain experts can quickly build vision models for a wide range of processes—detecting defective parts on a production line, reducing downtime on the factory floor, automating inventory management and other digitization and automation projects. And she introduces Intel-provided edge computing assets that empower faster localized insights and decisions, improving labor productivity through easy-to-use AI tools that democratize AI.
“Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” a Pres...
FORECASTING THE WIMAX TRAFFIC VIA MODIFIED ARTIFICIAL NEURAL NETWORK MODELS
1. International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 5, No. 5, September 2014
FORECASTING THE WIMAX TRAFFIC VIA
MODIFIED ARTIFICIAL NEURAL NETWORK
MODELS
Daw Abdulsalam Ali Daw1*, Kamaruzzaman Bin Seman1, Madihah Bint Mohd
Saudi2
1* Corresponding author: Daw Abdulsalam Ali Daw
Faculty of science and Technology, University Sains Islam Malaysia
Malaysia
ABSTRACT
This paper attempts to present a new approach of forecasting the WiMAX traffic by exploiting Artificial
Neural Networks (ANN). To develop the model, actual data is gathered from the LibyaMax network that
spans the duration of 180 days in total. Traffic data is separated into three cases based on the base stations
involved (A, B and AB). The model implements traffic prediction by emphasizing on the maximum and
minimum number of online user whereby two different learning algorithms are tested upon. to find the
optimal one. Overall, the experimentation shows promising results of which the most severe error of
prediction is not more than 0.0014. This indicates the feasibility of making accurate forecasting of both
daily and weekly traffic of the WiMAX network based solely on the maximum and minimum number of
users online.
KEYWORDS
WIMAX traffic, ANN model, Forecasting System
1. INTRODUCTION
Being able to predict the traffic of a particular WiMAX network is rather crucial in analyzing its
performance. It bears various applications in reality. For instance, to enable better network
management and admission. Furthermore, traffic forecasting plays a vital role in ensuring that the
quality of service is maintained at the necessary level. In this respect, it is an obligatory process
that must be adhered upon. Prediction works closely with decision making in network design. By
predicting the impact of changing a certain part of the network architecture, more effective
decision can be made regarding the best viable structure in a particular situation. As such, it is
critical to capture the behavior of traffic accurately. To this end, many models have been
proposed and revised for the purpose of simulating and understanding the inherent dynamics of a
network. The main idea of traffic prediction is to forecast the possible future traffic by analyzing
a series of recorded traffic in the past. Traffic data that is gathered through time must be tested
rigorously to validate its usefulness in developing the predictive model. Other factors such as the
actual prediction phase, prediction malfunction and computational cost must also be taken into
serious consideration in constructing a versatile forecasting model.
DOI : 10.5121/ijaia.2014.5503 33
2. International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 5, No. 5, September 2014
One of the most challenging issues to be addressed in data mining research is the exploration of
time series data [1]. Several prediction methods are considered in deriving the most appropriate
summary and conclusion. Based on commonality, the procedure of these methods in time series is
assumed to be linear. However, they can also be non-linear[2] of which linear approaches will no
longer apply. Now, if the approach is developed on the basis of Box-Jenkins method, then it
would be advisable to construct the time series model in a sequence of steps, before discovering
the ideal model. A series of alternative models can also be found by using structural state space
methods, which allows the estimation of stationary, trend, seasonal and cyclical data. Compared
to other methods, they capture the summation of separate components to enable analysis.
Among all the available models, Artificial Neural Network (ANN) displays an affinity to give
superior results [3][4][5]. Compared with ARIMA or fractional ARIMA predictors [6], the
performance of ANN is rather balanced when contrated with its computational intricacy. This
research accentuates the impact of using ANN in traffic forecasting for WiMAX network
whereby the advantage [7] is properly demonstrated in comparison with standard rule-based
systems. Apart from that, others [8][9][10] have also recommended the use of Time Delayed
Neural Network (TDNN). However, this particular approach will not be included here.
To generate the traffic, an integration of the entire network system is required. This includes the
traffic source [11] as well as the prediction technique that provides future energy prices,
specifically one day earlier. Here, Wavelet Transform offers a highly beneficial pre-processing
approach for forecasting data that can enhance the performance of prediction strategies as a
whole. The proposed forecasting model in this research deviates from the decomposition of time
series in the wavelet domain [12].
Instead, it employs ANN in the transform domain by exploiting the Alcatel-Lucent study [13]. In
addition, the impact of different ANN configurations on prediction performance will also be
examined in the end.
The following section narrates the forecasting structure as well as the theoretical consideration
with regard to data collection. A brief explanation on ANN and its theory are also included, along
with its configuration and implementation. In section three, the result and the discussion are
presented. Finally, the conclusion and future work are covered in the last section.
34
2. METHODOLOGY
A. Data Collection
Data for this research is gathered from the WiMAX traffic of Tripoli, the capital city of Libya. It
is required in the construction of the ANN based model for the WiMAX traffic forecasting
analysis. The data consist of two collection of scenarios. The first collection (Figure 1(a,b),
2(a,b), 3(a,b)) entails the daily data during the 180 days. On the other hand, the second collection
(Figure 4(a,b), 5(a,b), 6(a,b)) covers the weekly data within the 180 days duration. Each
collection includes the maximum and minimum number of user-A, user-B and user-AB as well as
their WiMAX traffic of MIMO-A, MIMO-B and MIMO-AB.
3. International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 5, No. 5, September 2014
Now, for the daily traffic, the maximum number of online users is generally between 25 to 80
people. On the contrary, the minimum number of online users is between 20 to 75 people. In
terms of traffic, MIMO-A user shows a range of traffic between 2e8 and 10e8 byte. MIMO-B
user however, shows a degree of traffic between 0.5e8 to 5.5e8 byte.
35
Figure 1(a). Daily data input Max number online of user-A,
Figure 1(b). Daily data Output Min number online user A and traffic of MIMO-user A
4. International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 5, No. 5, September 2014
36
Figure 2 (a). Daily data input Max number online of user-B,
Figure 3 (a). Daily data input Max number online of user-AB,
5. International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 5, No. 5, September 2014
37
Figure 3(b). Daily data Output Min number online user A and traffic of MIMO-user AB.
For the weekly traffic, the maximum number of online users is between 40 to 70 people while the
minimum number lies between 33 and 66 people. The range of traffic for weekly use is
approximately between 2.4e8 to 8.1e8 byte for MIMO-A user and 2.0e8 to 4.3e8 byte for MIMO-B
user. This indicates that the former user displays a higher level of weekly traffic as compared to
the latter.
Figure 4 (a). Weekly data input Max number online of user-A,
6. International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 5, No. 5, September 2014
38
Figure 4 (b). Weekly data Output Min number online user A and traffic of MIMO-user A
Figure 5 (a). Weekly data input Max number online of user-B,
Figure 5 (b). Weekly data Output Min number online user A and traffic of MIMO-user B.
7. International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 5, No. 5, September 2014
39
Figure 6 (a). Weekly data input Max number online of user-AB,
Figure 6 (b). Weekly data Output Min number online user A and traffic of MIMO-user AB.
B. ANN based Implementation of WIMAX Traffic Forecasting
To previse the WiMAX traffic using the ANN model, the multilayered feed forward perceptron is
exploited. Three sub-models are designed for this purpose whereby each involves network
architecture with input and output layers, as well as the hidden layers in between. The structure of
the hidden layer is shown in Figure 7. The data for the input layer consists of the maximum and
minimum number of online users. However, data for the output layer involves the traffic of
MIMO-A, MIMO-B and MIMO-AB. As such, three configuration patterns or models of training
are employed. Each configuration works on two time frames, which are daily and weekly. To
explain the idea in more detail, consider the following:
• Case (1): WIMAX traffic of MIMO-A users
Here, the effort of estimating the WiMAX Traffic comes from MIMO-A users. This is
done using the daily and weekly recorded data, which include the maximum and the
8. International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 5, No. 5, September 2014
minimum number of online users only. Thus, the traffic from MIMO-A users of daily and
weekly data are given as:
40
( , ) Daily ( A) A user (Max ) user (Min ) T = f X X (1a)
( , ) Weekly ( A) A user (Max ) user (Min ) T = f X X (1b)
• Case (2): WIMAX traffic of MIMO-B users
The prediction of daily and weekly traffic for MIMO-B user are attained only by
considering the maximum and the minimum number of its online users. In effect, so the
traffic from MIMO-B users for both time frames, daily and weekly, are :
( , ) Daily (B) B user (Max ) user (Min ) T = f X X (2a)
( , ) Weekly (B) B user (Max ) user (Min ) T = f X X (2b)
• Case (3): WIMAX traffic of MIMO-AB users
For the final scenario, both aforementioned cases are combined. The prediction of WiMAX
traffic for MIMO-AB users from the aspect of daily and weekly, are derived by utilizing the
daily and weekly data recorded :
( , ) Daily ( AB) AB user (Max ) user (Min) T = f X X (3a)
( , ) Weekly ( AB) AB user (Max) user (Min) T = f X X (3b)
Here, Daily ( A , B , AB ) T represents the daily WiMAX traffic from MIMO-A, MIMO-B and MIMO-AB
users (byte) respectively while Weekly ( A , B , AB ) T corresponds to the weekly traffic. ( ) user (Max) X ,
( ) user (Min) X represent the maximum and the minimum number of online (Max-online) and (Min-online)
respectively, A B AB f , , is the function model depend on the architecture of the neural
network as indicated in Figure 7
Figure 7. General ANN configuration patterns
9. International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 5, No. 5, September 2014
The usage of all the models enables the estimation of traffic in terms of the traffic flow index
(output). This provides a prediction on the traffic flow index of the WiMAX network on a daily
and weekly basis. Daily and weekly prediction differ from the aspect of overall duration whereby
the former is more interested on the short term analysis of the traffic whereby the latter gives a
somewhat mid term portrayal of traffic as a whole. Working together, both predictions can assist
the process of analyzing the network traffic more accurately.
41
Training Process
To perform the training, the back propagation method is employed whereby neurons are trained
and adjusted according to the error, with the synaptic weights appropriately modified. The output
of the approach depends on the variability of the input. Essentially, the algorithm is supervised
and iterated for multilayer feed forward nets, specifically tailored with nonlinear sigmoidal
threshold units, defined by the following equation:
1
( ) x e
f x −
(1 +
)
=
(4)
The characteristic of the problem is reflected in the set of input-output vectors within the
modeling stage where 2/3 of the entire data is used as training data. Output is gathered and then
compared with the one from the training set. The difference detected between the experimental
and desired output will then be utilized to modify the connection weights. Computationally, this
is done to minimize error, such that it will reach a stipulated level of tolerance.
At the accepted tolerance level, the connection weights are maintained and used to make decision.
The training halts when the mean average error between the measured output and desired output
remains unchanged after a number of trials. Consequently, the output attained by this procedure
will then be contrasted against the targeted value. This is achieved by measuring the error
function, which is defined by the average of square difference between the output of each neuron
in the output layer and the actual desired output.
This process is conducted on both of the datasets – training and testing. For the training, the
parameters are set according to the ones below:
Epochs of training : 10e4
Training goal : 10-3
Momentum constant : 0.92
Number of neurons : [20 10 1].
The maximum time of training, however, is not set at a particular value because it depends on the
learning algorithm. Consistency of the model is achieved by normalizing the input and output
data within the range of (0, 1). They are returned to the original values after the simulated is
completed by employing the following formula:
Min
x x
( ) max
/
Min
x x
x
−
−
=
(5)
10. International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 5, No. 5, September 2014
Here, ( x ) denotes the inputs/outputs of the network and the normalized version is written as
( / x ). Normalized values are determined by the maximum and minimum value of the input and
output. To note, the value of normalized input or output is 1 when the input or output is max x ,
and the value of normalized input or output is 0 when the input or output is Min x .
In designing the ANN, the activation function employs the sigmoid function. On the other hand,
the “Tansig” transfer function is used in the hidden layer while the “Purelin” transfer function is
deployed in the output layer. The “Tansig” transfer function is:
42
1
1
2
tan ( ) ( 2 )
−
+
=
− x e
sig x
(6)
ANN Models Error Analysis (The Proposed)
To train, validate and test the feed-forward back-propagation neural network, the data gathered
from LibyaMax network is used. Later, it is employed to estimate the WIMAX traffic such that
the accuracy can be ascertained in the end. This is crucial in verifying the performance of the
prediction model whereby the predicted value generated by the model is compared with the actual
data obtained. The stability of the model can then be found by evaluating the difference via the
calculation of the statistical error, or more specifically, the mean square error (MSE) that exploits
the following formula:
2
MSE = −
1
( )
1
M E
N
i
X X
N
=
(7)
N number of input-output pairs
XM desired value
XE estimated value
Further statistical analysis will give rise to a parameter known as the model efficiency (Meff) for
the ANN prediction results. It is defined as:
MSE
1 ( )
Var
M eff
= −
(8)
Discriminating the best model from the rest can be done by observing the extent of errors that
occurred. Statistically speaking, the model having the lowest error (MSE) is deemed as the best
one.
3. RESULT AND DISCUSSIONS
There are two set of results to be discussed in this particular section. The first set is the daily
WiMAX traffic for the Tripoli city and the second one is the weekly WiMAX traffic. For the
ANN model, three types of learning algorithms are implemented. They are (a) TrainLM and (b)
TrainSCG. The predictive performance of the model is then measured by examining the error
(MSE) and Model efficiency (Eff) indicators. Details of the discussion is covered below :
11. International Journal of Artificial Intelligence Applications (IJAIA), Vol. 5, No. 5, September 2014
43
C. Modeling results: daily WiMAX traffic of MIMO-A users
The result of the experimentation for the daily WiMAX traffic of MIMO-A users is summarized
in Table I while the graphical description is given in Figure 8. Overall, the results show
remarkable accuracy when plotted against the measured data.
Table I Cross-Validation Report Of Ann Modeling Results Of Wimax Traffic Of Mimo-User A
[20 10 1]
( , ) Daily ( A) A user (Max ) user (Min ) T = f X X
Training Testing
Algorithms
MSE Meff R MSE
TrainLM 0.000099 0.9464 0.97271 0.0010
TrainSCG
0.001033 0.9447 0.97166 0.0010
From Table I, the average efficiency of the model can be calculated, which is found to be 0.9456.
Among the learning algorithms, TrainLM shows the best performance with a competitive error or
MSE (0.0010) and highest efficiency (0.9464). The worst performance is exhibited by TrainSCG
with similar MSE (0.0010) and lowest efficiency (0.9447).
Figure 8. Results of modeling the daily Wimax traffic of MIMO-A users with (a) trainLM
12. International Journal of Artificial Intelligence Applications (IJAIA), Vol. 5, No. 5, September 2014
44
Figure 8. Results of modeling the daily Wimax traffic of MIMO-A users with (b) trainSCG
D. Modeling results: daily WIMAX traffic of MIMO-B users
The experimental result for the daily WiMAX traffic of MIMO-B users is given in Table II. Its
corresponding graphical depiction is shown in Figure 9.
Table Ii Cross-Validation Report Of Ann Modeling Results Of Daily Wimax Traffic Of Mimo-User B
[20 10 1]
( , ) Daily (B) B user (Max ) user (Min ) T = f X X
Training Testing
Algorithms
MSE Meff R MSE
TrainLM 0.0009974 0.9473 0.97316 0.0010
TrainSCG
0.001027 0.9407 0.89443 0.0038
Again, it is discovered here that the best learning algorithm is trainLM with the lowest error MSE
(0.0010) and highest efficiency (0.9473). TrainSCG consistently shows the worst performance
with the highest MSE (0.0038) and lowest efficiency (0.9407).
The performance of TrainLM in forecasting the daily WiMAX
traffic of MIMO-A users suggests the suitability of this particular learning algorithm in handling
traffic data that is specific to this context. The limitation of ANN however, is its inability to
explain why certain algorithm is better than another.
13. International Journal of Artificial Intelligence Applications (IJAIA), Vol. 5, No. 5, September 2014
45
Figure 9. Results of modeling the daily Wimax traffic of MIMO-B users with (a) trainLM
Figure 9. Results of modeling the daily Wimax traffic of MIMO-B users with (b) trainSCG
E. Modeling results: daily WIMAX traffic of MIMO-AB users
Figure 9 exhibits the result of modeling the WiMAX traffic for MIMO-AB users. Here, the
graphical comparison for the prediction data against the actual data is plotted accordingly. It can
be seen that there is a great fit between the two. This implies the high accuracy of the model in
forecasting the WiMAX traffic data.
14. International Journal of Artificial Intelligence Applications (IJAIA), Vol. 5, No. 5, September 2014
Table Iii Cross-Validation Report Of Ann Modeling Results Of Daily Wimax Traffic Of Mimo-Users Ab
46
[20 10 1]
( , ) Daily ( AB) AB user (Max ) user (Min) T = f X X
Training Testing
Algorithms
MSE Meff R MSE
TrainLM 0.0009982 0.9998 0.96057 0.0014
TrainSCG
0.001538 0.9638 0.91877 0.0056
The performance of two algorithms is compared and overall, TrainLM is superior among them.
TrainLM shows the highest efficiency (0.9998) and lowest MSE (0.0014). On the other hand, the
most inferior learning algorithm is TrainSCG with the highest MSE (0.0056) and lowest
efficiency (0.9638). Here, it can be seen that the MSE of TrainSCG is very severe when
compared to TrainLM. To understand the extent of severity, it is useful to note that the degree of
error displayed by TrainSCG is four times as much as the one exhibited by TrainLM.
Figure 10. Results of modeling the dailyWimax traffic of MIMO-AB users with (a) trainLM
15. International Journal of Artificial Intelligence Applications (IJAIA), Vol. 5, No. 5, September 2014
47
Figure 10. Results of modeling the dailyWimax traffic of MIMO-AB users with (b) trainSCG
F. Modeling results: weekly WiMAX traffic of MIMO-A users
From the weekly results of the MIMO-A users, it is quite apparent that TrainLM exhibits the best
performance for the traffic forecasting with the lowest MSE (0.0007) and highest efficiency
(0.95529). The performance of TrainSCG is comparatively worst, with a highest MSE (0.0010)
and lowest efficiency (0.95404). The difference of efficiency level between the two algorithms is
quite marginal however, with a value of 0.00125.
Cross-Validation Report Of Ann Modeling Results Of Weekly Wimax Traffic Of Mimo-Users A
[20 10 1]
( , ) Weekly ( A) A user (Max ) user (Min ) T = f X X
Training Testing
Algorithms
MSE Meff R MSE
TrainLM 0.00097138 0.95529 0.97112 0.0007
TrainSCG
0.0099844 0.95404 0.97589 0.0010
16. International Journal of Artificial Intelligence Applications (IJAIA), Vol. 5, No. 5, September 2014
48
Figure 11. Results of modeling the weekly Wimax traffic of MIMO-A users with (a) trainLM
Figure 11. Results of modeling the weekly Wimax traffic of MIMO-A users with (b) trainSCG
G. Modeling results: weekly WiMAX traffic of MIMO-B users
For the results of the weekly traffic of MIMO-B users, the performance of both learning
algorithms TrainLM and TrainSCG is similar in term of error with the same MSE (0.0010).
However, TrainLM still outperforms TrainSCG in term of efficiency whereby the former
achieves 0.95422 while the latter only manages an efficiency of 0.92209. Here, the difference of
efficiency is more significant when compared to the MIMO-A users. This indicates that the traffic
behavior of MIMO-B users in training is more consistent when contrasted with MIMO-A users.
17. International Journal of Artificial Intelligence Applications (IJAIA), Vol. 5, No. 5, September 2014
49
Cross-Validation Report Of Ann Modeling Results Of Weekly Wimax Traffic Of Mimo-Users A
[20 10 1]
( , ) Weekly (B) B user (Max ) user (Min ) T = f X X
Training Testing
Algorithms
MSE Meff R MSE
TrainLM 0.00099665 0.95422 0.96067 0.0010
TrainSCG
0.009993 0.92209 0.96617 0.0010
Figure 12. Results of modeling the weekly Wimax traffic of MIMO-B users with (a) trainLM
Figure 12. Results of modeling the weekly Wimax traffic of MIMO-B users with (b) trainSCG
18. International Journal of Artificial Intelligence Applications (IJAIA), Vol. 5, No. 5, September 2014
50
H. Modeling results: weekly WiMAX traffic of MIMO-AB users
Examining the results of the weekly MIMO-AB users, it is discovered that both learning
algorithms show similar propensity in term of MSE (0.0010). However, the performance of
TrainLM in term of efficiency (0.95422) is still better when contrasted against TrainSCG, which
shows a significantly lower efficiency (0.92209). Overall, this implies that the weekly traffic of
MIMO-AB users can be predicted more accurately with TrainLM instead of TrainSCG.
Cross-Validation Report Of Ann Modeling Results Of Weekly Wimax Traffic Of Mimo-Users Ab
[20 10 1]
( , ) Weekly ( AB) AB user (Max) user (Min) T = f X X
Training Testing
Algorithms
MSE Meff R MSE
TrainLM 0.00099665 0.95422 0.96067 0.0010
TrainSCG
0.009993 0.92209 0.96617 0.0010
Figure 13. Results of modeling the weekly Wimax traffic of MIMO-AB users with (a) trainLM
19. International Journal of Artificial Intelligence Applications (IJAIA), Vol. 5, No. 5, September 2014
51
Figure 13. Results of modeling the weekly Wimax traffic of MIMO-AB users with (b) trainSCG
4. CONCLUSION
Forecasting the WiMAX traffic via the ANN model is a feasible approach in making prediction
of the daily and weekly performance of the WiMAX network. It is possible to ascertain the traffic
only by utilizing the maximum and minimum number of user online. Two algorithms, namely
TrainLM and TrainSCG, are tested to determine the best model of forecasting. It is found that
TrainLM, which invariably offers the lowest error and highest efficiency, shows the best
performance.
5. ACKNOWLEDGMENT
The authors thank LibyaMax network (WiMAX technology) motorized by Libya Telecom and
Technology for providing us the WiMAX traffic data and for helpful discussions around WiMAX
network. We also thank staff of Faculty of Science and Technology, University Sains Islam
Malaysia for their help and support.
REFERENCES
[1] Yang, Q. X. Wu, (2006) “10 challenging problems in data mining research”, International Journal
of Information Technology Decision Making 5(04): 597-604.
[2] Zhang, G., B. Eddy Patuwo M. Y Hu, (1998) “ Forecasting with artificial neural networks: The
state of the art”, International journal of forecasting 14(1): 35-62.
[3] Adya, M., J. S. Armstrong, F. Collopy M. Kennedy, (2000) “ An application of rule-based
forecasting to a situation lacking domain knowledge”, International Journal of Forecasting 16(4):
477-484.
[4] Mitra, S. A. Mitra, (2006) “ Modeling exchange rates using wavelet decomposed genetic neural
networks”, Statistical Methodology 3(2): 103-124.
20. International Journal of Artificial Intelligence Applications (IJAIA), Vol. 5, No. 5, September 2014
[5] Ibarra-Berastegi, G., A. Elias, R. Arias A. Barona, (2007) “ Artificial Neural Networks vs Linear
Regression in a Fluid Mechanics and Chemical Modelling Problem: Elimination of Hydrogen
Sulphide in a Lab-Scale Biofilter”, Computer Systems and Applications, 2007. AICCSA'07.
IEEE/ACS International Conference on, hlm. 584-587.
[6] Feng, H. Y. Shu, (2005) “ Study on network traffic prediction techniques”, Wireless
Communications, Networking and Mobile Computing, 2005. Proceedings. 2005 International
Conference on, hlm. 1041-1044.
[7] Tan, C. N., (1993) “ Incorporating artificial neural networks into a rule-based financial trading
system”, Artificial Neural Networks and Expert Systems, 1993. Proceedings., First New Zealand
International Two-Stream Conference on, hlm. 292-293.
[8] Taskaya-Temizel, T. M. C. Casey, (2005) “ Configuration of neural networks for the analysis of
seasonal time series. Dlm. (pnyt.). Ed”, Pattern Recognition and Data Mining hlm. 297-304.
Springer.
[9] Clouse, D. S., C. L. Giles, B. G. Horne G. W. Cottrell (1997) “ Time-delay neural networks:
Representation and induction of finite-state machines”,Neural Networks, IEEE Transactions on 8(5):
1065-1070.
[10] Zhang, G. P. M. Qi, (2005) “ Neural network forecasting for seasonal and trend time series.
52
European journal of operational research 160(2): 501-514.
[11] Daw, D. A. A. K. B., (2013 ) “Seman A Gateway To Wimax Profiling Services In Libya”,
International Journal of Engineering Research and Development. vol. 7, PP. 63-68.
[12] Railean, I., C. Stolojescu, S. Moga P. Lenca, (2010) “ Wimax traffic forecasting based on neural
networks in wavelet domain”, Research Challenges in Information Science (RCIS), 2010 Fourth
International Conference on, hlm. 443-452.
[13] I. Firoiu, C. Stolojescu, A. Isar, (2009) Forecasting of WiMAX BS Traffic: Observations and Initial
Models, Alcatel Lucent technical report.