Digital camera needs fixed bit rate. In this paper image compression is done using slant transform exploiting the characteristics of Human Visual System (HVS). Normally JPEG compressors support variable bit error rate. The error rate range in this compressor is found to be around -50 to 50. The error rate is reduced to around -0.6 to 1 using fuzzy logic. The input parameters for fuzzy logic are obtained by encoding bit rate and bit error rate. By framing rules the adaptive gain in quantization matrix of compressor is adjusted so that a fixed bit rate is achieved at different quality factors.

Design and simulation of Constant bit rate compressor using fuzzy logic

The overall goal of the research is to improve the quality of biomedical image for telemedicine with minimum percentages of noise in the retrieved image and to take less computation time. The novelty of this technique lies in the implementation of spectral coding for biomedical images using neural networks in order to accomplish the above objectives. This work is in continuity of an ongoing research project aimed at developing a system for efficient image compression approach for telemedicine in Saudi Arabia. We compare the efficiency of this technique against existing image compression techniques, namely, JPEG2000, in terms of compression ratio, peak signal to noise ratio (PSNR), and computation time. To our knowledge, the research is the primary in providing a comparative study with other techniques used in the compression of biomedical images. This work explores and tests biomedical images such as X-rays, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET).

https://downloads.hindawi.com/journals/tswj/2014/757146.pdf

Minimize the Percentage of Noise in Biomedical Images Using Neural Networks

Compression plays a significant role in a data storage and a transmission. If we speak about a generall data compression, it has to be a lossless one. It means, we are able to recover the original data 1:1 from the compressed file. Multimedia data (images, video, sound...), are a special case. In this area, we can use something called a lossy compression. Our main goal is not to recover data 1:1, but only keep them visually similar. This article is about an image compression, so we will be interested only in image compression. For a human eye, it is not a huge difference, if we recover RGB color with values [150,140,138] instead of original [151,140,137]. The magnitude of a difference determines the loss rate of the compression. The bigger difference usually means a smaller file, but also worse image quality and noticable differences from the original image. We want to cover compression techniques mainly from the last decade. Many of them are variations of existing ones, only some of them uses new principes.

Image compression overview

To store an image, large quantities of digital data are required. Due to limited bandwidth, image must be compressed before transmission. However, image compression reduces the image fidelity, when an image is compressed at low bitrates. Hence, the compressed images suffer from block artifacts. To meet this, several compression schemes have been developed in image processing. This study presents an overview of compression techniques for image applications. It covers the lossy and lossless compression algorithm used for still image and other applications. The focus of this article is based on the overview of VLSI DCT architecture for image compression. Further, this new approach may provide better results.

Review Article: An Overview of Image Compression Techniques

The overall aim of the research is to compare the retrieved image with the original image with respect to the evaluation factors such as MAE, MSE, PSNR and RMSE which reflects the quality of biomedical image for telemedicine with minimum percentage of error at the recipient side. This paper presents spectral coding technique for biomedical images using neural networks in-order to accomplish the above objectives. This work is in continuity of ongoing research project aimed at developing a system for efficient image compression approach for telemedicine in Saudi Arabia. This work compares the efficiency of proposed technique against existing image compression techniques viz JPEG2000 and improved BPNN. To my knowledge, the research is the primary in providing a comparative study of evaluation factors with other techniques used in compression of biomedical images. This work is explored and tested on biomedical images such as X-rays, CT, MRI, PET etc.

A Case Study of Evaluation Factors for Biomedical Images Using Neural Networks

It is well known that the classic image compression techniques such as JPEG and MPEG have serious limitations at high compression rate; the decompressed image gets really fuzzy or indistinguishable. To overcome problems associated with conventional methods, artificial neural networks based method can be used. Genetic algorithm is a very powerful method for solving real life problems and this has been proven by applying to number of different applications. There is lots of interest to involve the GA with ANN for various reasons at various levels. Trapping in the local minima is one of the well-known problems of gradient decent based learning in ANN. The problem can be addressed using GA algorithm. But no work has been done to evaluate the performance of both learning methods from the image compression point of view. In this paper, we investigate the performance of ANN with GA in the application of image compression for obtaining optimal set of weights. Direct method of compression has been applied with neural network to get the additive advantage for security of compressed data. The experiments reveal that the standard BP with proper parameters provide good generalize capability for compression and is much faster compared to earlier work in the literature, based on cumulative distribution function. Further, the results obtained shows that general concept about GA, it performs better over gradient decent based learning, is not applicable for image compression.

https://thesai.org/Downloads/SpecialIssueNo1/Paper_4-Modeling%20of%20neural%20image%20compression%20using%20GA%20and%20BP%20a%20comparative%20approach.pdf

Modeling of neural image compression using GA and BP: a comparative approach

Device-to-device (D2D) communication has grown into notoriety as a critical component of the internet of things (IoT). One of the primary limitations of IoT devices is restricted battery source. D2D communication is the direct contact between the participating devices that improves the data rate and delivers the data quickly by consuming less battery. An energy-efficient communication method is required to enhance the communication lifetime of the network by reducing the node energy dissipation. The clustering-based D2D communication method is maximally acceptable to boom the durability of a network. The oscillating spider monkey optimization (OSMO) and oscillating particle swarm optimization (OPSO) algorithms are used in this study to improve the selection of cluster heads (CHs) and routing paths for D2D communication. The CHs and D2D communication paths are selected depending on the parameters such as energy consumption, distance, end-to-end delay, link quality and hop count. A simulation environment is designed to evaluate and test the performance of the OSMO-OPSO algorithm with existing D2D communication algorithms (such as the GAPSO-H algorithm, adaptive resource-aware split-learning (ARES), bio-inspired cluster-based routing scheme (Bi-CRS), and European society for medical oncology (ESMO) algorithm). The results proved that the proposed technique outperformed with respect to traditional routing strategies regarding latency, packet delivery, energy efficiency, and network lifetime.

/pdf/energy-efficient-device-to-device-communication-in-internet-3imn1d1u.pdf

Energy-efficient device-to-device communication in internet of things using hybrid optimization technique

Received Sep 22, 2022 Revised Mar 1, 2023 Accepted Mar 9, 2023 Device-to-device (D2D) communication has grown into notoriety as a critical component of the internet of things (IoT). One of the primary limitations of IoT devices is restricted battery source. D2D communication is the direct contact between the participating devices that improves the data rate and delivers the data quickly by consuming less battery. An energy-efficient communication method is required to enhance the communication lifetime of the network by reducing the node energy dissipation. The clustering-based D2D communication method is maximally acceptable to boom the durability of a network. The oscillating spider monkey optimization (OSMO) and oscillating particle swarm optimization (OPSO) algorithms are used in this study to improve the selection of cluster heads (CHs) and routing paths for D2D communication. The CHs and D2D communication paths are selected depending on the parameters such as energy consumption, distance, end-to-end delay, link quality and hop count. A simulation environment is designed to evaluate and test the performance of the OSMO-OPSO algorithm with existing D2D communication algorithms (such as the GAPSO-H algorithm, adaptive resource-aware splitlearning (ARES), bio-inspired cluster-based routing scheme (Bi-CRS), and European society for medical oncology (ESMO) algorithm). The results proved that the proposed technique outperformed with respect to traditional routing strategies regarding latency, packet delivery, energy efficiency, and network lifetime.

Vrinda Shivashetty

Papers

Modeling of neural image compression using GA and BP: a comparative approach

Energy-efficient device-to-device communication in internet of things using hybrid optimization technique

International Journal of Electrical and Computer Engineering (IJECE)