1) The document discusses VLSI architecture and implementation for 3D neural network based image compression. It proposes developing new hardware architectures optimized for area, power, and speed for implementing 3D neural networks for image compression.
2) A block diagram is presented showing the overall process of image acquisition, preprocessing, compression using a 3D neural network, and encoding for transmission.
3) The proposed 3D neural network architecture uses multiple hidden layers with lower dimensions than the input and output layers to perform the compression and decompression transformations between the image pixels and hidden layer representations.
Optimization of image compression and ciphering based on EZW techniquesTELKOMNIKA JOURNAL
This paper presents the design and optimization of image compression and ciphering depend on optimized embedded zero tree of wavelet (EZW) techniques. Nowadays, the compression and ciphering of image have become particularly important in a protected image storage and communication. The challenge is put in application for both compression and encryption where the parameters of images such as quality and size are critical in secure image transmission. A new technique for secure image storage and transmission is proposed in this work. The compression is achieved by remodel the EZW scheme combine with discrete cosine transform (DCT). Encrypted the XOR ten bits by initial threshold of EZW with random bits produced from linear-feedback shift register (LFSR). The obtained result shows that the suggested techniques provide acceptable compression ratio, reduced the computational time for both compression and encryption, immunity against the statistical and the frequency attacks.
Image Compression and Reconstruction Using Artificial Neural NetworkIRJET Journal
1) The document presents a neural network based method for image compression and reconstruction. An artificial neural network is used to compress image data for storage or transmission and then restore the image when desired.
2) The neural network accepts image data as input, compresses it by generating an internal representation, and then decompresses the data to reconstruct the original image.
3) The performance of the neural network method for image compression and reconstruction is evaluated using standard test images. Results show that it achieves high compression ratios and low distortion while maintaining its ability to generalize and is robust.
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
Image Captioning Generator using Deep Machine Learningijtsrd
Technologys scope has evolved into one of the most powerful tools for human development in a variety of fields.AI and machine learning have become one of the most powerful tools for completing tasks quickly and accurately without the need for human intervention. This project demonstrates how deep machine learning can be used to create a caption or a sentence for a given picture. This can be used for visually impaired persons, as well as automobiles for self identification, and for various applications to verify quickly and easily. The Convolutional Neural Network CNN is used to describe the alphabet, and the Long Short Term Memory LSTM is used to organize the right meaningful sentences in this model. The flicker 8k and flicker 30k datasets were used to train this. Sreejith S P | Vijayakumar A "Image Captioning Generator using Deep Machine Learning" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-4 , June 2021, URL: https://www.ijtsrd.compapers/ijtsrd42344.pdf Paper URL: https://www.ijtsrd.comcomputer-science/artificial-intelligence/42344/image-captioning-generator-using-deep-machine-learning/sreejith-s-p
Key Management Schemes for Secure Communication in Heterogeneous Sensor NetworksIDES Editor
Hierarchical Sensor Network organization is
widely used to achieve energy efficiency in Wireless Sensor
Networks(WSN). To achieve security in hierarchical WSN,
it is important to be able to encrypt the messages sent
between sensor nodes and its cluster head. The key
management task is challenging due to resource constrained
nature of WSN. In this paper we are proposing two key
management schemes for hierarchical networks which
handles various events like node addition, node compromise
and key refresh at regular intervals. The Tree-Based
Scheme ensures in-network processing by maintaining some
additional intermediate keys. Whereas the CRT-Based
Scheme performs the key management with minimum
communication and storage at each node.
This document discusses an enhanced technique for secure and reliable watermarking using Modified Haar Wavelet Transform (MFHWT). The proposed technique embeds a watermark into an original image using discrete wavelet transform (DWT) and wavelet packet transform (WPT) according to the size of the watermark. MFHWT is a memory efficient, fast, and simple transform. The watermarking process involves embedding and extraction processes. Various watermarking techniques in different transform domains are discussed, including DWT and WPT. The proposed algorithm uses MFHWT for decomposition and reconstruction. Image quality is measured using metrics like MSE and PSNR, with higher PSNR indicating better quality. The technique achieves robustness
A new study of dss based on neural network and data miningAttaporn Ninsuwan
This document proposes using neural networks and data mining to support intelligent decision support systems (IDSS). It discusses how neural networks can help with knowledge learning, problem solving abilities, and real-time processing. Data mining can be used for analysis, clustering, and concept description. The paper then presents a framework for an IDSS combining neural networks, data mining, reasoning, and natural language processing. It provides an example application to evaluate using marsh gas instead of oil and natural gas in China.
Secured Data Transmission Using Video Steganographic SchemeIJERA Editor
Steganography is the art of hiding information in ways that avert the revealing of hiding messages. Video Steganography is focused on spatial and transform domain. Spatial domain algorithm directly embedded information in the cover image with no visual changes. This kind of algorithms has the advantage in Steganography capacity, but the disadvantage is weak robustness. Transform domain algorithm is embedding the secret information in the transform space. This kind of algorithms has the advantage of good stability, but the disadvantage of small capacity. These kinds of algorithms are vulnerable to steganalysis. This paper proposes a new Compressed Video Steganographic scheme. The data is hidden in the horizontal and the vertical components of the motion vectors. The PSNR value is calculated so that the quality of the video after the data hiding is evaluated.
A novel steganographic technique based on lsb dct approach by Mohit GoelMohit Goel
The document summarizes a research paper presented at the National Conference on Emerging Trends in Information and Computing Technologies. The paper proposes a novel steganographic technique that embeds data by altering the least significant bit of low frequency discrete cosine transform coefficients of image blocks. Experimental results showed the technique has a better peak signal-to-noise ratio value and higher data capacity compared to other techniques like least significant bit, modulus arithmetic, and SSB4-DCT embedding. It also maintains satisfactory security as the secret message cannot be extracted without knowing the decoding algorithm.
This document summarizes a research paper that proposes a new technique for data embedding and extraction in high resolution AVI videos. The technique encrypts a secret message before embedding it by alternately changing the LSB and LSB+3 bits of alternate bytes in the cover video file. An index is also created for the secret information and placed in a video frame to aid extraction. This technique aims to provide higher security, capacity and robustness compared to typical data embedding methods. The paper discusses related work on digital steganography techniques and the proposed video steganography algorithm in more detail.
Efficient And Improved Video Steganography using DCT and Neural NetworkIJSRD
As per the demand of modern communication it is important to establish secret communication which is obtain by seganography .Video Steganography is the technique of hiding some covert message inside a video. The addition of this information to the video is not recognizable through the human eye as modify of a pixel color is negligible. In the proposed method Discrete Cosine Transform (DCT) and neural network is used. Input image is divided into blocks and is processed to generate quantization matrix of cover and stego images by using Discrete Cosine Transform (DCT).And using neural network performance of this method can be further improved. The neural network is trained and on the basis of training and segmentation done, neural network provide efficient positions where data can be merge. The performance and efficiency is measured by PSNR and MSE value.
Self Attested Images for Secured Transactions using Superior SOMIDES Editor
Separate digital signals are usually used as the
digital watermarks. But this paper proposes rebuffed
untrained minute values of vital image as a digital watermark,
since no host image is needed to hide the vital image for its
safety. The vital images can be transformed with the self
attestation. Superior Self Organized Maps is used to derive
self signature from the vital image. This analysis work
constructs framework with Superior Self Organizing Maps
(SSOM) against Counter Propagation Network for watermark
generation and detection. The required features like
robustness, imperceptibility and security was analyzed to prove
that which neural network is appropriate for mining watermark
from the host image. SSOM network is proved as an efficient
neural trainer for the proposed watermarking technique. The
paper presents one more contribution to the watermarking
area.
A ROBUST CHAOTIC AND FAST WALSH TRANSFORM ENCRYPTION FOR GRAY SCALE BIOMEDICA...sipij
In this work, a new scheme of image encryption based on chaos and Fast Walsh Transform (FWT) has been proposed.
We used two chaotic logistic maps and combined chaotic encryption methods to the two-dimensional FWT of images.
The encryption process involves two steps: firstly, chaotic sequences generated by the chaotic logistic maps are used to
permute and mask the intermediate results or array of FWT, the next step consist in changing the chaotic sequences or
the initial conditions of chaotic logistic maps among two intermediate results of the same row or column. Changing the
encryption key several times on the same row or column makes the cipher more robust against any attack. We tested
our algorithms on many biomedical images. We also used images from data bases to compare our algorithm to those
in literature. It comes out from statistical analysis and key sensitivity tests that our proposed image encryption schemeprovides an efficient and secure way for real-time encryption and transmission biomedical images.
The document discusses hiding confidential text data within an encrypted image using reversible data hiding techniques. It begins by introducing the concepts of reversible data hiding and meaningful image encryption. The proposed method first encrypts an original image using AES to create a pre-encrypted image. It then applies discrete wavelet transform to the pre-encrypted image to transform it into a visually meaningful encrypted image. Finally, reversible data hiding is used to hide confidential text data within the meaningful encrypted image while still allowing lossless retrieval of both the image and hidden data. The method aims to provide effective data protection with low computational cost.
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...ijscai
Object detection and recognition are important problems in computer vision and pattern recognition
domain. Human beings are able to detect and classify objects effortlessly but replication of this ability on
computer based systems has proved to be a non-trivial task. In particular, despite significant research
efforts focused on meta-heuristic object detection and recognition, robust and reliable object recognition
systems in real time remain elusive. Here we present a survey of one particular approach that has proved
very promising for invariant feature recognition and which is a key initial stage of multi-stage network
architecture methods for the high level task of object recognition.
This document summarizes an article from the International Journal of Advanced Research in Computer Engineering & Technology about developing an artificial neural network based clustering method for atmospheric conditions prediction in Indian cities. The method uses Adaptive Resonance Theory (ART) neural networks to form clusters of cities based on their monthly atmospheric condition data (temperature, pressure, humidity). ART networks can self-organize to create stable clusters while learning new patterns. The authors apply city data to an ART network to create clusters representing associations between cities with similar atmospheric conditions. This allows predicting conditions in one city based on patterns from another in the same cluster. The ART-based clustering method shows cities grouped in the same cluster have comparable monthly atmospheric conditions.
1) The document discusses a GSM based power meter reading and control system that uses GSM technology to remotely read electricity meters and control home appliances.
2) Current manual meter reading is time-consuming and prone to errors. The proposed system sends daily meter readings via SMS to both users and the electricity department to generate accurate bills.
3) It also allows remote control of appliances to reduce unnecessary power consumption and save energy by monitoring power usage and controlling loads that exceed predefined limits.
This paper proposes a wide dynamic range CMOS sensor with gating capabilities for use in night vision and multiple applications. The sensor can detect objects within 15 meters in day or night conditions with centimeter accuracy. It integrates high functionality pixels to extract distance and reflectivity information. This data is modulated into an active optical signal during light propagation, allowing each pixel to act as an individual stopwatch. The system is directly interfaced with vehicle controls to automatically apply the brakes if an object is detected within 10 meters, improving safety. Potential applications include biomedical, industrial, surveillance and more.
This document summarizes a research paper on changing data rates during handoffs in GSM-ATM networks. It discusses:
1) Wireless ATM networks which combine ATM's support for multimedia services with mobility support for mobile devices. This poses challenges like mobility management and ensuring quality of service during handoffs.
2) Handoff is the process of transferring a mobile terminal's connections from one access point to another during movement. It involves initiation, establishing a new connection, and data flow control to maintain quality of service.
3) The document reviews different handoff types in wireless ATM networks and various handoff protocol approaches like full connection re-routing, route augmentation, and partial connection re-routing
This document discusses the development and management of an information security lifecycle based on standards. It begins by discussing the importance of information security for organizations and describes the key components of information security. It then discusses adopting a standards-based approach to security policy using the British Standard 7799 as a guideline. This involves assessing network assets and risks, designing a security policy, deploying security measures, and ongoing management and support through monitoring and education. The lifecycle approach helps ensure security is addressed systematically from the start of a project through ongoing management.
This document summarizes a research paper on tracking multiple targets using the mean shift algorithm. It begins by stating that multi-target tracking is challenging due to factors like noise, clutter, occlusions, and sudden changes in velocity. The mean shift algorithm is then introduced as a kernel-based tracking method that works by iteratively shifting target locations to their mean shifts. Targets are represented using histograms within elliptical regions. The Bhattacharyya coefficient is used to measure similarity between target models and candidates. Experimental results on a video sequence show the algorithm can accurately track targets under small displacements but performance degrades for large displacements, fast motion, or occlusions. In conclusion, the mean shift algorithm provides a simple method for multi
This document presents a proposed approach called ICCC (Information Correctness to the Customers in Cloud Data Storage) to provide customers with proof of the correctness of their data stored in the cloud. The ICCC approach aims to minimize storage and computation costs for both customers and cloud storage providers. It involves the customer pre-processing their file by generating and encrypting metadata about random bits of each data block before uploading the file. This metadata is appended to the file. To verify correctness, the customer challenges the cloud storage provider by specifying a data block and bit, and the provider must return the correct metadata bit. This allows verification with minimal access to the entire file and low overhead for both parties.
1. The document describes an application of the unscented Kalman filter (UKF) for state estimation in sonar signal processing.
2. It provides background on linear and nonlinear state estimation techniques, including the Kalman filter, extended Kalman filter, unscented Kalman filter, and particle filter.
3. As an example, it models target tracking using bearing-only measurements, where the target is assumed to move at constant course and velocity. The UKF is used to estimate the target state parameters in the presence of measurement noise.
This document summarizes the current state of middleware and operating systems used in wireless sensor networks (WSNs). It discusses the need for middleware to facilitate application development on resource-constrained sensor nodes. It categorizes existing middleware approaches and describes desirable middleware characteristics. It also discusses sensor node hardware, including different sensor platforms and their properties. Challenges in designing operating systems for WSNs given limitations in memory, power, and other resources are outlined. Finally, desirable features for sensor node operating systems are presented.
An optimized discrete wavelet transform compression technique for image trans...IJECEIAES
Transferring images in a wireless multimedia sensor network (WMSN) knows a fast development in both research and fields of application. Nevertheless, this area of research faces many problems such as the low quality of the received images after their decompression, the limited number of reconstructed images at the base station, and the high-energy consumption used in the process of compression and decompression. In order to fix these problems, we proposed a compression method based on the classic discrete wavelet transform (DWT). Our method applies the wavelet compression technique multiple times on the same image. As a result, we found that the number of received images is higher than using the classic DWT. In addition, the quality of the received images is much higher compared to the standard DWT. Finally, the energy consumption is lower when we use our technique. Therefore, we can say that our proposed compression technique is more adapted to the WMSN environment.
International Journal of Computational Engineering Research(IJCER)ijceronline
The document discusses image compression using artificial neural networks. It begins with an introduction to image compression and the need for it. Then it reviews various existing neural network approaches for image compression, including backpropagation networks, hierarchical networks, multilayer feedforward networks, and radial basis function networks. It proposes a new approach using a multilayer perceptron with a modified Levenberg-Marquardt training algorithm to improve compression performance. Authentication and protection would be incorporated by exploiting the one-to-one mapping and one-way properties of neural networks. The proposed system is described as compressing images using neural networks trained with a modified LM algorithm to achieve high compression ratios while maintaining image quality.
Video Encryption and Decryption with Authentication using Artificial Neural N...IOSR Journals
Abstract :Multimedia data security is becoming important with the continuous increase of digital
communications on internet. With the rapid development of various multimedia technologies, more and more
multimedia data are generated and transmitted in the medical, commercial, and military fields, which may
include some sensitive information which should not be accessed by or can only be partially exposed to the
general users. . The encryption algorithms developed to secure text data are not suitable for multimedia
application because of the large data size and real time constraint. Therefore, there is a great demand for
secured data storage and transmission techniques. Information security has traditionally been ensured with
data encryption and authentication techniques. The secrecy of communication is maintained by secret key
exchange. In effect the strength of the algorithm depends solely on the length of the key. The presented work
aims at secure video transmission using randomness in encryption algorithm, thereby creating more confusion
to obtain the original data. The security of the original cipher has been enhanced by addition of impurities to
misguide the cryptanalyst. Since the encryption process is one way function, the artificial neural networks are
best suited for this purpose as they possess features like high security, no distortion and its ability to perform for
non linear input-output characteristics, In the presented work the need for key exchange is also eliminated,
which is otherwise a perquisite for most of the algorithms used today. The proposed work finds its application in
medical imaging systems, military image database communication and confidential video conferencing, and
similar such application. The results are obtained through the use of MATLAB 7.14.0
Keywords: Artificial Neural networks, Back propagation algorithm, video encryption and decryption, cipher
and decipher
Devanagari Digit and Character Recognition Using Convolutional Neural NetworkIRJET Journal
This document describes a system for recognizing handwritten Devanagari digits and characters using a convolutional neural network (CNN). The system is designed to overcome challenges from variations in handwriting styles. It involves preprocessing the dataset, extracting features, training a CNN model on training images, and using the trained model to classify testing and real-time input images and output the recognized character or digit. An experiment using a Kaggle dataset of 92,000 Devanagari character and digit images achieved recognition of user-drawn input on an interface using the trained CNN model.
A Survey on Image Processing using CNN in Deep LearningIRJET Journal
This document discusses the use of convolutional neural networks (CNNs) for image processing tasks. It provides an overview of CNNs and their application in image classification. The document then reviews several papers that have applied CNNs to tasks like image classification, object detection, and image segmentation. Some key advantages of CNNs discussed are their ability to directly take images as input without needing separate preprocessing steps. However, challenges include overfitting when training data is limited and complex images can confuse networks. The document concludes that CNN performance improves with more network layers and training data. CNNs are widely used for computer vision tasks due to their strong image feature extraction capabilities.
Implementing Neural Networks Using VLSI for Image Processing (compression)IJERA Editor
Biological systems process the analog signals such as image and sound efficiently. To process the information the way biological systems do we make use of ANN. (Artificial Neural Networks) The focus of this paper is to review the implementation of the neural network architecture using analog components like Gilbert cell multiplier, differential amplifier for neuron activation function and tan sigmoid function circuit using MOS transistor. The neural architecture is trained using Back propagation algorithm for compressing the image. This paper surveys the methods of implementing the neural network using VLSI .Different CMOS technologies are used for implementing the circuits for arithmetic operations (i.e. 180nm, 45nm, 32nm).And the MOS transistors are working in sub threshold region. In this paper a review is made on how the VLSI architecture is used to implement neural networks and trained for compressing the image.
Iaetsd implementation of chaotic algorithm for secure imageIaetsd Iaetsd
This document proposes a system for secure image transcoding using chaotic algorithm encryption. The system encrypts images using a chaotic key-based algorithm (CKBA) before transcoding. It involves applying the discrete cosine transform, CKBA encryption, quantization, and entropy encoding like Huffman coding. A transcoder block then converts the data to a lower bit rate format while maintaining security. At the receiver, the inverse processes are applied to reconstruct the image. The system aims to provide efficient content delivery with end-to-end security for multimedia applications like mobile web browsing.
IRJET- Fire Detector using Deep Neural NetworkIRJET Journal
This document summarizes a research paper that proposes using a deep neural network for real-time fire detection from CCTV surveillance videos. Specifically, it uses the SqueezeNet architecture, which requires fewer parameters and memory than other networks. The proposed system analyzes frames from surveillance videos and compares images to a trained dataset of fire and non-fire images using SqueezeNet. If a fire is detected, an alert message is immediately sent to the fire station. The system aims to provide early detection of fires from existing CCTV infrastructure to reduce accidents.
The document provides an introduction to image encryption using AES key expansion. It discusses how traditional encryption techniques are not well-suited for encrypting large multimedia files like images due to their size and characteristics. The objective of the study is to develop an image encryption system that is computationally secure, fast enough for real-time use, and widely acceptable. It reviews related works in image encryption and discusses limitations of only using a 128-bit AES key. The document is organized into chapters covering cryptography fundamentals, image cryptosystems, AES algorithm details, an example of AES key expansion, and experimental analysis.
Machine learning based augmented reality for improved learning application th...IJECEIAES
Detection of objects and their location in an image are important elements of current research in computer vision. In May 2020, Meta released its state-ofthe-art object-detection model based on a transformer architecture called detection transformer (DETR). There are several object-detection models such as region-based convolutional neural network (R-CNN), you only look once (YOLO) and single shot detectors (SSD), but none have used a transformer to accomplish this task. These models mentioned earlier, use all sorts of hyperparameters and layers. However, the advantages of using a transformer pattern make the architecture simple and easy to implement. In this paper, we determine the name of a chemical experiment through two steps: firstly, by building a DETR model, trained on a customized dataset, and then integrate it into an augmented reality mobile application. By detecting the objects used during the realization of an experiment, we can predict the name of the experiment using a multi-class classification approach. The combination of various computer vision techniques with augmented reality is indeed promising and offers a better user experience.
DEEP LEARNING BASED BRAIN STROKE DETECTIONIRJET Journal
This document discusses using deep learning and convolutional neural networks to detect brain strokes in CT scan images. It proposes a CNN model with four layers - convolution, pooling, flatten, and fully connected layers - to classify brain CT images as normal or showing signs of stroke. The CNN model was trained on brain CT images and able to accurately diagnose hemorrhages in the brain and detect strokes. This early detection of strokes using deep learning could help reduce death rates by enabling faster treatment.
Development of 3D convolutional neural network to recognize human activities ...journalBEEI
This document describes the development of a 3D convolutional neural network (CNN) model to recognize human activities using moderate computation capabilities. The model is trained on the KTH dataset, which contains activities like walking, running, jogging, handwaving, handclapping, and boxing. The proposed model uses 3D CNN layers and max pooling layers to extract both spatial and temporal features from video frames. Testing achieved an accuracy of 93.33% for activity recognition. The number of model parameters and operations are also calculated to show the model can perform human activity recognition with reasonable computational requirements suitable for devices with moderate capabilities.
Image compression and reconstruction using a new approach by artificial neura...Hưng Đặng
This document describes a neural network approach to image compression and reconstruction. It discusses using a backpropagation neural network with three layers (input, hidden, output) to compress an image by representing it with fewer hidden units than input units, then reconstructing the image from the hidden unit values. It also covers preprocessing steps like converting images to YCbCr color space, downsampling chrominance, normalizing pixel values, and segmenting images into blocks for the neural network. The neural network weights are initially randomized and then trained using backpropagation to learn the image compression.
Image compression and reconstruction using a new approach by artificial neura...Hưng Đặng
This document describes a neural network approach to image compression and reconstruction. It discusses using a backpropagation neural network with three layers (input, hidden, output) to compress an image by representing it with fewer hidden units than input units, then reconstructing the image from the hidden unit values. It also covers preprocessing steps like converting images to YCbCr color space, downsampling chrominance, normalizing pixel values, and segmenting images into blocks for the neural network. The neural network weights are initially randomized and then trained using backpropagation to learn the image compression.
Fast and Secure Transmission of Image by using Byte Rotation Algorithm in Net...IRJET Journal
This document proposes a new secure image transmission method using byte rotation algorithm that improves encryption speed and security. The key steps are:
1. The input image is divided into four blocks which are shuffled using byte rotation.
2. A cover image is used to embed the shuffled secret image blocks for transmission.
3. At the receiver, byte rotation is applied again to extract the original secret image blocks from the embedded image.
Experimental results show the proposed method recovers images with high PSNR quality scores while increasing encryption speed over other algorithms like AES. This provides a more secure and fast way to transmit encrypted images over networks.
This document summarizes a research paper that proposes a new image encryption method using magnitude and phase manipulation with crossover and mutation approaches. The proposed method encrypts images in the frequency domain. It performs crossover operations to swap real and complex parts of frequency components. It also applies a mutation operation using NOT logic. This makes the encrypted image sensitive to key changes and difficult to decrypt without the key. The method is evaluated on different types of images and is shown to encrypt images with 84-98% efficiency depending on the image content. The authors conclude the method provides an efficient encryption scheme and future work could further improve encryption of images containing easily recognizable objects.
Thesis on Image compression by Manish MystManish Myst
The document discusses using neural networks for image compression. It describes how previous neural network methods divided images into blocks and achieved limited compression. The proposed method applies edge detection, thresholding, and thinning to images first to reduce their size. It then uses a single-hidden layer feedforward neural network with an adaptive number of hidden neurons based on the image's distinct gray levels. The network is trained to compress the preprocessed image block and reconstruct the original image at the receiving end. This adaptive approach aims to achieve higher compression ratios than previous neural network methods.
From Pixels to Understanding: Deep Learning's Impact on Image Classification ...IRJET Journal
This document discusses how deep learning has significantly improved image classification and recognition abilities compared to traditional machine learning methods. It provides an overview of different deep learning network structures used for these tasks, including deep belief networks, convolutional neural networks, and recurrent neural networks. Deep learning algorithms are able to extract abstract feature representations from unlabeled image data using multi-layer neural networks, leading to more accurate image categorization than earlier approaches.
Ijri ece-01-01 joint data hiding and compression based on saliency and smvqIjripublishers Ijri
Global interconnect planning becomes a challenge as semiconductor technology continuously scales. Because of the increasing wire resistance and higher capacitive coupling in smaller features, the delay of global interconnects becomes large compared with the delay of a logic gate, introducing a huge performance gap that needs to be resolved A novel equalized global link architecture and driver– receiver co design flow are proposed for high-speed and low-energy on-chip communication by utilizing a continuous-time linear equalizer (CTLE). The proposed global link is analyzed using a linear system method, and the formula of CTLE eye opening is derived to provide high-level design guidelines and insights.
Compared with the separate driver–receiver design flow, over 50% energy reduction is observed.
SELECTIVE ENCRYPTION OF IMAGE BY NUMBER MAZE TECHNIQUEijcisjournal
Due to enormous increase in the usage of computers and mobiles, today’s world is currently flooded with
huge volumes of data. This paper is primarily focused on multimedia data and how it can be protected
from unwanted attacks. Sharing of multimedia data is easy and very efficient, it has been a customary
practice to share multimedia data but there is no proper encryption technique to encrypt multimedia data.
Sharing of multimedia data over unprotected networks using DCT algorithm and then applying selective
encryption-based algorithm has never been adequately studied. This paper introduces a new selective
encryption-based security system which will transfer data with protection even in unauthenticated network.
Selective encryption-based security system will also minimize time during encryption process which there
by achieves efficiency. The data in the image is transmitted over a network is discriminated using DCT
transform and then it will be selectively encrypted using Number Puzzle technique, and thus provides
security from unauthorized access. This paper discusses about numeric puzzle-based encryption technique
and how it can achieve security and integrity for multimedia data over traditional encryption technique.
Electrically small antennas: The art of miniaturizationEditor IJARCET
We are living in the technological era, were we preferred to have the portable devices rather than unmovable devices. We are isolating our self rom the wires and we are becoming the habitual of wireless world what makes the device portable? I guess physical dimensions (mechanical) of that particular device, but along with this the electrical dimension is of the device is also of great importance. Reducing the physical dimension of the antenna would result in the small antenna but not electrically small antenna. We have different definition for the electrically small antenna but the one which is most appropriate is, where k is the wave number and is equal to and a is the radius of the imaginary sphere circumscribing the maximum dimension of the antenna. As the present day electronic devices progress to diminish in size, technocrats have become increasingly concentrated on electrically small antenna (ESA) designs to reduce the size of the antenna in the overall electronics system. Researchers in many fields, including RF and Microwave, biomedical technology and national intelligence, can benefit from electrically small antennas as long as the performance of the designed ESA meets the system requirement.
This document provides a comparative study of two-way finite automata and Turing machines. Some key points:
- Two-way finite automata are similar to read-only Turing machines in that they have a finite tape that can be read in both directions, but cannot write to the tape.
- Turing machines have an infinite tape that can be read from and written to, allowing them to recognize recursively enumerable languages.
- Both models are examined in their ability to accept the regular language L={anbm|m,n>0}.
- The time complexity of a two-way finite automaton for this language is O(n2) due to making two passes over the
This document analyzes and compares the performance of the AODV and DSDV routing protocols in a vehicular ad hoc network (VANET) simulation. Simulations were conducted using NS-2, SUMO, and MOVE simulators for a grid map scenario with varying numbers of nodes. The results show that AODV performed better than DSDV in terms of throughput and packet delivery fraction, while DSDV had lower end-to-end delays. However, neither protocol was found to be fully suitable for the highly dynamic VANET environment. The document concludes that further work is needed to develop improved routing protocols optimized for VANETs.
This document discusses the digital circuit layout problem and approaches to solving it using graph partitioning techniques. It begins by introducing the digital circuit layout problem and how it has become more complex with increasing circuit sizes. It then discusses how the problem can be decomposed into subproblems using graph partitioning to assign geometric coordinates to circuit components. The document reviews several traditional approaches to solve the problem, such as the Kernighan-Lin algorithm, and discusses their limitations for larger circuit sizes. It also discusses more recent approaches using evolutionary algorithms and concludes by analyzing the contributions of various approaches.
This document summarizes various data mining techniques that have been used for intrusion detection systems. It first describes the architecture of a data mining-based IDS, including sensors to collect data, detectors to evaluate the data using detection models, a data warehouse for storage, and a model generator. It then discusses supervised and unsupervised learning approaches that have been applied, including neural networks, support vector machines, K-means clustering, and self-organizing maps. Finally, it reviews several related works applying these techniques and compares their results, finding that combinations of approaches can improve detection rates while reducing false alarms.
This document provides an overview of speech recognition systems and recent progress in the field. It discusses different types of speech recognition including isolated word, connected word, continuous speech, and spontaneous speech. Various techniques used in speech recognition are also summarized, such as simulated evolutionary computation, artificial neural networks, fuzzy logic, Kalman filters, and Hidden Markov Models. The document reviews several papers published between 2004-2012 that studied speech recognition methods including using dynamic spectral subband centroids, Kalman filters, biomimetic computing techniques, noise estimation, and modulation filtering. It concludes that Hidden Markov Models combined with MFCC features provide good recognition results for large vocabulary, speaker-independent, continuous speech recognition.
This document discusses integrating two assembly lines, Line A and Line B, based on lean line design concepts to reduce space and operators. It analyzes the current state of the lines using tools like takt time analysis and MTM/UAS studies. Improvements are identified to eliminate waste, including methods improvements, workplace rearrangement, ergonomic changes, and outsourcing. Paper kaizen is conducted and work elements are retimed. The goal is to integrate the lines to better utilize space and manpower while meeting manufacturing standards.
This document summarizes research on the exposure of microwaves from cellular networks. It describes how microwaves interact with biological systems and discusses measurement techniques and safety standards regarding microwave exposure. While some studies have alleged health hazards from microwaves, independent reviews by health organizations have found no evidence that exposure to microwaves below international safety limits causes harm. The document concludes that with precautions like limiting exposure time and using phones with lower SAR ratings, microwaves from cell phones pose minimal health risks.
This document summarizes a research paper that examines the effect of feature reduction in sentiment analysis of online reviews. It uses principle component analysis to reduce the number of features (product attributes) from a dataset of 500 camera reviews labeled as positive or negative. Two models are developed - one using the original set of 95 product attributes, and one using the reduced set. Support vector machines and naive Bayes classifiers are applied to both models and their performance is evaluated to determine if classification accuracy can be maintained while using fewer features. The results show it is possible to achieve similar accuracy levels with less features, improving computational efficiency.
This document provides a review of multispectral palm image fusion techniques. It begins with an introduction to biometrics and palm print identification. Different palm print images capture different spectral information about the palm. The document then reviews several pixel-level fusion methods for combining multispectral palm images, finding that Curvelet transform performs best at preserving discriminative patterns. It also discusses hardware for capturing multispectral palm images and the process of region of interest extraction and localization. Common fusion methods like wavelet transform and Curvelet transform are also summarized.
This document describes a vehicle theft detection system that uses radio frequency identification (RFID) technology. The system involves embedding an RFID chip in each vehicle that continuously transmits a unique identification signal. When a vehicle is stolen, the owner reports it to the police, who upload the vehicle's information to a central database. Police vehicles are equipped with RFID receivers. If a stolen vehicle passes within range of a receiver, the receiver detects the vehicle's ID signal and displays its details on a tablet. This allows police to quickly identify and recover stolen vehicles. The system aims to make it difficult for thieves to hide a vehicle's identity and allows vehicles to be tracked globally wherever the detection system is implemented.
This document discusses and compares two techniques for image denoising using wavelet transforms: Dual-Tree Complex DWT and Double-Density Dual-Tree Complex DWT. Both techniques decompose an image corrupted by noise using filter banks, apply thresholding to the wavelet coefficients, and reconstruct the image. The Double-Density Dual-Tree Complex DWT yields better denoising results than the Dual-Tree Complex DWT as it produces more directional wavelets and is less sensitive to shifts and noise variance. Experimental results on test images demonstrate that the Double-Density method achieves higher peak signal-to-noise ratios, especially at higher noise levels.
This document compares the k-means and grid density clustering algorithms. It summarizes that grid density clustering determines dense grids based on the densities of neighboring grids, and is able to handle different shaped clusters in multi-density environments. The grid density algorithm does not require distance computation and is not dependent on the number of clusters being known in advance like k-means. The document concludes that grid density clustering is better than k-means clustering as it can handle noise and outliers, find arbitrary shaped clusters, and has lower time complexity.
This document proposes a method for detecting, localizing, and extracting text from videos with complex backgrounds. It involves three main steps:
1. Text detection uses corner metric and Laplacian filtering techniques independently to detect text regions. Corner metric identifies regions with high curvature, while Laplacian filtering highlights intensity discontinuities. The results are combined through multiplication to reduce noise.
2. Text localization then determines the accurate boundaries of detected text strings.
3. Text binarization filters background pixels to extract text pixels for recognition. Thresholding techniques are used to convert localized text regions to binary images.
The method exploits different text properties to detect text using corner metric and Laplacian filtering. Combining the results improves
This document describes the design and implementation of a low power 16-bit arithmetic logic unit (ALU) using clock gating techniques. A variable block length carry skip adder is used in the arithmetic unit to reduce power consumption and improve performance. The ALU uses a clock gating circuit to selectively clock only the active arithmetic or logic unit, reducing dynamic power dissipation from unnecessary clock charging/discharging. The ALU was simulated in VHDL and synthesized for a Xilinx Spartan 3E FPGA, achieving a maximum frequency of 65.19MHz at 1.98mW power dissipation, demonstrating improved performance over a conventional ALU design.
This document describes using particle swarm optimization (PSO) and genetic algorithms (GA) to tune the parameters of a proportional-integral-derivative (PID) controller for an automatic voltage regulator (AVR) system. PSO and GA are used to minimize the objective function by adjusting the PID parameters to achieve optimal step response with minimal overshoot, settling time, and rise time. The results show that PSO provides high-quality solutions within a shorter calculation time than other stochastic methods.
This document discusses implementing trust negotiations in multisession transactions. It proposes a framework that supports voluntary and unexpected interruptions, allowing negotiating parties to complete negotiations despite temporary unavailability of resources. The Trust-x protocol addresses issues related to validity, temporary loss of data, and extended unavailability of one negotiator. It allows a peer to suspend an ongoing negotiation and resume it with another authenticated peer. Negotiation portions and intermediate states can be safely and privately passed among peers to guarantee stability for continued suspended negotiations. An ontology is also proposed to provide formal specification of concepts and relationships, which is essential in complex web service environments for sharing credential information needed to establish trust.
This document discusses and compares various nature-inspired optimization algorithms for resolving the mixed pixel problem in remote sensing imagery, including Biogeography-Based Optimization (BBO), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO). It provides an overview of each algorithm, explaining key concepts like migration and mutation in BBO. The document aims to prove that BBO is the best algorithm for resolving the mixed pixel problem by comparing it to other evolutionary algorithms. It also includes figures illustrating concepts like the species model and habitat in BBO.
This document discusses principal component analysis (PCA) for face recognition. It begins with an introduction to face recognition and PCA. PCA works by calculating eigenvectors from a set of face images, which represent the principal components that account for the most variance in the image data. These eigenvectors are called "eigenfaces" and can be used to reconstruct the face images. The document then discusses how the system is implemented, including preparing a face database, normalizing the training images, calculating the eigenfaces/principal components, projecting the face images into this reduced space, and recognizing faces by calculating distances between projected test images and training images.
This document summarizes research on using wireless sensor networks to detect mobile targets. It discusses two optimization problems: 1) maximizing the exposure of the least exposed path within a sensor budget, and 2) minimizing sensor installation costs while ensuring all paths have exposure above a threshold. It proposes using tabu search heuristics to provide near-optimal solutions. The research also addresses extending the models to consider wireless connectivity, heterogeneous sensors, and intrusion detection using a game theory approach. Experimental results show the proposed mobile replica detection scheme can rapidly detect replicas with no false positives or negatives.
Demystifying Neural Networks And Building Cybersecurity ApplicationsPriyanka Aash
In today's rapidly evolving technological landscape, Artificial Neural Networks (ANNs) have emerged as a cornerstone of artificial intelligence, revolutionizing various fields including cybersecurity. Inspired by the intricacies of the human brain, ANNs have a rich history and a complex structure that enables them to learn and make decisions. This blog aims to unravel the mysteries of neural networks, explore their mathematical foundations, and demonstrate their practical applications, particularly in building robust malware detection systems using Convolutional Neural Networks (CNNs).
Improving Learning Content Efficiency with Reusable Learning ContentEnterprise Knowledge
Enterprise Knowledge’s Emily Crockett, Content Engineering Consultant, presented “Improve Learning Content Efficiency with Reusable Learning Content” at the Learning Ideas conference on June 13th, 2024.
This presentation explored the basics of reusable learning content, including the types of reuse and the key benefits of reuse such as improved content maintenance efficiency, reduced organizational risk, and scalable differentiated instruction & personalization. After this primer on reuse, Crockett laid out the basic steps to start building reusable learning content alongside a real-life example and the technology stack needed to support dynamic content. Key objectives included:
- Be able to explain the difference between reusable learning content and duplicate content
- Explore how a well-designed learning content model can reduce duplicate content and improve your team’s efficiency
- Identify key tasks and steps in creating a learning content model
The History of Embeddings & Multimodal EmbeddingsZilliz
Frank Liu will walk through the history of embeddings and how we got to the cool embedding models used today. He'll end with a demo on how multimodal RAG is used.
Connector Corner: Leveraging Snowflake Integration for Smarter Decision MakingDianaGray10
The power of Snowflake analytics enables CRM systems to improve operational efficiency, while gaining deeper insights into closed/won opportunities.
In this webinar, learn how infusing Snowflake into your CRM can quickly provide analysis for sales wins by region, product, customer segmentation, customer lifecycle—and more!
Using prebuilt connectors, we’ll show how workflows using Snowflake, Salesforce, and Zendesk tickets can significantly impact future sales.
Cracking AI Black Box - Strategies for Customer-centric Enterprise ExcellenceQuentin Reul
The democratization of Generative AI is ushering in a new era of innovation for enterprises. Discover how you can harness this powerful technology to deliver unparalleled customer value and securing a formidable competitive advantage in today's competitive market. In this session, you will learn how to:
- Identify high-impact customer needs with precision
- Harness the power of large language models to address specific customer needs effectively
- Implement AI responsibly to build trust and foster strong customer relationships
Whether you're at the early stages of your AI journey or looking to optimize existing initiatives, this session will provide you with actionable insights and strategies needed to leverage AI as a powerful catalyst for customer-driven enterprise success.
"Hands-on development experience using wasm Blazor", Furdak Vladyslav.pptxFwdays
I will share my personal experience of full-time development on wasm Blazor
What difficulties our team faced: life hacks with Blazor app routing, whether it is necessary to write JavaScript, which technology stack and architectural patterns we chose
What conclusions we made and what mistakes we committed
Redefining Cybersecurity with AI CapabilitiesPriyanka Aash
In this comprehensive overview of Cisco's latest innovations in cybersecurity, the focus is squarely on resilience and adaptation in the face of evolving threats. The discussion covers the imperative of tackling Mal information, the increasing sophistication of insider attacks, and the expanding attack surfaces in a hybrid work environment. Emphasizing a shift towards integrated platforms over fragmented tools, Cisco introduces its Security Cloud, designed to provide end-to-end visibility and robust protection across user interactions, cloud environments, and breaches. AI emerges as a pivotal tool, from enhancing user experiences to predicting and defending against cyber threats. The blog underscores Cisco's commitment to simplifying security stacks while ensuring efficacy and economic feasibility, making a compelling case for their platform approach in safeguarding digital landscapes.
Keynote : AI & Future Of Offensive SecurityPriyanka Aash
In the presentation, the focus is on the transformative impact of artificial intelligence (AI) in cybersecurity, particularly in the context of malware generation and adversarial attacks. AI promises to revolutionize the field by enabling scalable solutions to historically challenging problems such as continuous threat simulation, autonomous attack path generation, and the creation of sophisticated attack payloads. The discussions underscore how AI-powered tools like AI-based penetration testing can outpace traditional methods, enhancing security posture by efficiently identifying and mitigating vulnerabilities across complex attack surfaces. The use of AI in red teaming further amplifies these capabilities, allowing organizations to validate security controls effectively against diverse adversarial scenarios. These advancements not only streamline testing processes but also bolster defense strategies, ensuring readiness against evolving cyber threats.
kk vathada _digital transformation frameworks_2024.pdfKIRAN KV
I'm excited to share my latest presentation on digital transformation frameworks from industry leaders like PwC, Cognizant, Gartner, McKinsey, Capgemini, MIT, and DXO. These frameworks are crucial for driving innovation and success in today's digital age. Whether you're a consultant, director, or head of digital transformation, these insights are tailored to help you lead your organization to new heights.
🔍 Featured Frameworks:
PwC's Framework: Grounded in Industry 4.0 with a focus on data and analytics, and digitizing product and service offerings.
Cognizant's Framework: Enhancing customer experience, incorporating new pricing models, and leveraging customer insights.
Gartner's Framework: Emphasizing shared understanding, leadership, and support teams for digital excellence.
McKinsey's 4D Framework: Discover, Design, Deliver, and De-risk to navigate digital change effectively.
Capgemini's Framework: Focus on customer experience, operational excellence, and business model innovation.
MIT’s Framework: Customer experience, operational processes, business models, digital capabilities, and leadership culture.
DXO's Framework: Business model innovation, digital customer experience, and digital organization & process transformation.
Garbage In, Garbage Out: Why poor data curation is killing your AI models (an...Zilliz
Enterprises have traditionally prioritized data quantity, assuming more is better for AI performance. However, a new reality is setting in: high-quality data, not just volume, is the key. This shift exposes a critical gap – many organizations struggle to understand their existing data and lack effective curation strategies and tools. This talk dives into these data challenges and explores the methods of automating data curation.
Discovery Series - Zero to Hero - Task Mining Session 1DianaGray10
This session is focused on providing you with an introduction to task mining. We will go over different types of task mining and provide you with a real-world demo on each type of task mining in detail.
How UiPath Discovery Suite supports identification of Agentic Process Automat...DianaGray10
📚 Understand the basics of the newly persona-based LLM-powered Agentic Process Automation and discover how existing UiPath Discovery Suite products like Communication Mining, Process Mining, and Task Mining can be leveraged to identify APA candidates.
Topics Covered:
💡 Idea Behind APA: Explore the innovative concept of Agentic Process Automation and its significance in modern workflows.
🔄 How APA is Different from RPA: Learn the key differences between Agentic Process Automation and Robotic Process Automation.
🚀 Discover the Advantages of APA: Uncover the unique benefits of implementing APA in your organization.
🔍 Identifying APA Candidates with UiPath Discovery Products: See how UiPath's Communication Mining, Process Mining, and Task Mining tools can help pinpoint potential APA candidates.
🔮 Discussion on Expected Future Impacts: Engage in a discussion on the potential future impacts of APA on various industries and business processes.
Enhance your knowledge on the forefront of automation technology and stay ahead with Agentic Process Automation. 🧠💼✨
Speakers:
Arun Kumar Asokan, Delivery Director (US) @ qBotica and UiPath MVP
Naveen Chatlapalli, Solution Architect @ Ashling Partners and UiPath MVP
BLOCKCHAIN TECHNOLOGY - Advantages and DisadvantagesSAI KAILASH R
Explore the advantages and disadvantages of blockchain technology in this comprehensive SlideShare presentation. Blockchain, the backbone of cryptocurrencies like Bitcoin, is revolutionizing various industries by offering enhanced security, transparency, and efficiency. However, it also comes with challenges such as scalability issues and energy consumption. This presentation provides an in-depth analysis of the key benefits and drawbacks of blockchain, helping you understand its potential impact on the future of technology and business.
Latest Tech Trends Series 2024 By EY IndiaEYIndia1
Stay ahead of the curve with our comprehensive Tech Trends Series! Explore the latest technology trends shaping the world today, from the 2024 Tech Trends report and top emerging technologies to their impact on business technology trends. This series delves into the most significant technological advancements, giving you insights into both established and emerging tech trends that will revolutionize various industries.
Top 12 AI Technology Trends For 2024.pdfMarrie Morris
Technology has become an irreplaceable component of our daily lives. The role of AI in technology revolutionizes our lives for the betterment of the future. In this article, we will learn about the top 12 AI technology trends for 2024.
This PDF delves into the aspects of information security from a forensic perspective, focusing on privacy leaks. It provides insights into the methods and tools used in forensic investigations to uncover and mitigate privacy breaches in mobile and cloud environments.