Electronics

Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

VIT Unitversity

School of Electronics Engineering

Chennai Campus

Fulltext

International Journal of Computer Aided Engineering and Technology

Hybrid Algorithm for Twin Image Removal in Optical Scanning Holography

Chronic obstructive pulmonary disease (COPD) is a group of lung disease like emphysema, chronic bronchitis, asthma and some kinds of bronchiectasis. This group of diseases are expected to be one of the major causes of morbidility and the third case of mortality by 2020. If the disease is identified in the early stage itself the survival rate will be increased. In this paper a novel method is proposed to classify the disease COPD in chest X-ray images. Prior to classification essential features are to be extracted. In this regards, some structural features include number of ribs in the chest X-ray, heart shape, diaphragm shape and distance between ribs of the given X-ray image are extracted by means of various image processing techniques. Based on the above said features the input image is classified as normal or COPD with various classifiers include MLC, LDA, neural network, genetic algorithm. The maximum classification accuracy achieved is 97.9%. This work not only ends up with the classification of COPD images, it also enables the medicos to identify the heart disease cardiomegaly. Copyright © 2020 Inderscience Enterprises Ltd.

World University root node

Feature extraction and classification of COPD chest X-ray images

The passive optical network (PON) technology has been drastically improved in recent years. In spite of using the optical technology, the utilization of the entire bandwidth is a very challenging task. The main categories of PON are the Ethernet passive optical network (EPON) and gigabit passive optical network (GPON). These two networks use the dynamic bandwidth allocation (DBA) algorithm to attain the maximum usage of bandwidth, which is provided in the network dynamically according to the need of the customers with the support of the service level agreement (SLA). This paper will provide a clear review about the DBA algorithm of both technologies as well as the comparison. © 2020, JOURNAL OF ELECTRONIC SCIENCE AND TECHNOLOGY. All Rights Reserved

Journal of Electronic Science and Technology

Review on Dynamic Bandwidth Allocation of GPON and EPON

In this modern era, where there is a great shift in momentum towards AI and data science, data-driven approach has substantiated to have diverse talents. This type of approach specifically in the field of wireless communication has proven to be highly efficient in modelling an end to end wireless communication channel with a completely unknown channel state information (CSI). Though there has been some work done in this direction they are not focusing on high dimension data like audio and image. Further with the tremendous growth in multimedia technologies and with higher resolution data being transmitted, there is an increasing need for bandwidth. Hence in this paper, we propose a novel idea where a Conditional Generative Adversarial Network is used to represent the channel effects of an end to end wireless communication channel which adapts to different noise levels with having the memory of the channel state information (CSI). Further to address this issue with bandwidth, Variational Adversarial Network is used where the input data is encoded into a condensed latent space and impacted with noise which is then passed through a Generative Adversarial Network which would be able to extract the original information. This reduces a lot of bandwidth and thereby increasing the overall data rate. To strengthen our proposal, we provide a comparative analysis with our conditional GAN and with extensive experiment results with both quantitative and qualitative analysis on images and voice signals. © 2020 IEEE.

2020 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2020 - Proceedings

Deep Generative Model based Channel Agnostic Communication System for Efficient Data Transmission

In the applications of Wireless Sensor Network, sensor nodes broadcast the data towards the destination. Localization is considered as the most important and interesting area in WSN as identifying the location of sensor nodes is needful for many situations. The proposed work, points on discovering the sensor node location and promotes cross layer effective routing path searching for the reliable data transmission in the network. The proposed work consists of three main phases. The initial phase includes the cross-layer link establishment. The second phase includes, identifying the fuzziness of wireless sensors. It tracks the location of sensor nodes and analyzes the behaviour. This can be done with the algorithm namely; Fuzziness based Contiguous nodes Refining Algorithm. Since the characteristics of nodes may vary often, the algorithm finds the unsuitable communication node in the routing path and removes it. Source node controls the activities of the intermediate nodes in the routing path. After identifying and removing the unsuitable nodes, in final phase, an effective routing path is established by using the scheme called Efficient Fuzziness based Contiguous node refining with cross-layer routing Scheme (EFCRS) is proposed. This selects the routing nodes from starting node to ending node with the lesser energy usage. At last, destination node acquires the enhanced throughput and reduced consumption of energy. It also obtains minimum packet latency. Simulation is carried out and found it, achieves better performance than existing algorithms in comparing metrics end to end delay, overhead, connectivity ratio, throughput and energy consumption. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.

Peer-to-Peer Networking and Applications

An efficient fuzziness based contiguous node refining scheme with cross-layer routing path in WSN

The demand for larger bandwidth to carry high capacity data in optical networks is increasing. Thus, it is expected to replace all digital logic with optical logic soon. Privacy and data security are also of utmost importance in all-optical networks. Generally, all-optical encryption has been carried out using (i) highly nonlinear fiber (HNLF) and (ii) Semiconductor Optical Amplifier (SOA) with interferometric structures. However, the former is limited by the requirement of a lengthy fiber and the latter one with more number of nonlinear components. In this work, an all-optical encryption process using nonlinear effects and four-wave mixing (FWM) in SOA without interferometric structure is presented for different number systems. The basic idea of the proposed system is to use delay operations which are carried out by duo binary modulation units whereas the encryption using single SOA is possible by FWM nonlinear effect. This combination of novel design for different number systems is optimized through SOA structural parameters, pump and probe signal power, and wavelength. Through optimization, the performance improvement is assured by a good extinction ratio of 11.5 dB for the active region length of less than 200 μm. Compared to the existing techniques, the quality factor is 2.28 times and 1.52 times better than HNLF and SOA-MZI, respectively. © 2020 Walter de Gruyter GmbH, Berlin/Boston 2020.

Journal of Optical Communications

Performance analysis and parameter optimization of all-optical encryption using the FWM effect in semiconductor optical amplifier

In this paper, we have proposed a blocking probability-based admission control technique for QoS provisioning on in WDM networks, for this, we estimate the blocking probability for an arriving connection request. The probability that there is at least one free wavelength at the specified book-ahead time that remains idle for the whole connection duration. Next to this an admission control scheme used in each group for deterministic QoS provisioning. The admission control scheme has its root from network calculus which can derive deterministic bounds on throughput and delay rather than statistical averages. Along with the delay metric, the blocking probability is also considered as the main constraints for admission control. The scheme allocates the aggregate token bucket for each class of traffic based on its bandwidth share. © 2020 Inderscience Enterprises Ltd.

International Journal of Operational Research

Blocking probability-based admission control technique for QoS provisioning in WDM networks

Breast cancer is a major concern among women that causes high risk of death. Early diagnosis of such cancer becomes challenging due to alterations in the color of the histopathological breast images. This study uses a publicly available dataset of breast cancer histopathology images. This paper introduces a dual stage normalization approach, to address the color variation problem of biopsy specimen collectively caused by incompatible staining in biopsy process and bizarre imaging quality. The dual stage normalization proposed here consists of a stain normalization unit and a light normalization unit. This system addresses the variations of both imaging and staining of specimen that are caused by a microscopic imaging setup. Later on, eight features have been extracted from the normalized images and used for the classification of breast cancer (benign and malignant). The overall accuracy of the back propagation algorithm (BPA) classifier is obtained as 81.8%. After comparison with other classifier accuracies, BPA classifier is found to be acceptable. Recall and precision values are approximately 89% and 90%, respectively, which is acceptable. The saturation-weighted hue statistics produces balanced and uniform color hues for stain normalization. This statistic is powerful against variations in model parameters and unsusceptible to image subjects and achromatic colors. This normalization technique retains all histological data with an enhanced performance. © 2020, © 2020 IETE.

IETE Journal of Research

Dual Stage Normalization Approach Towards Classification of Breast Cancer

Background: Sleep apnea is the most pervasive sleep disorder as its severity causes even life-threatening health issues. The present study aimed to evaluate the self-administered questionnaire for assessing obstructive sleep apnea (OSA). Methods: The qualitative analysis compared and validated the Berlin (BQ), STOP-BANG (SBQ) and OSA50 questionnaires for sleep apnea assessment. In this preliminary study, we proposed four systematic analyses: gender, age group, smoking habit and working hour. One hundred and ninety participants were completed the screening test, where 52% of men and 48% of women with the mean age of 27 ± 10. Results: In the present study, the results summarized that the male, young age adults, smoking person and long working hour's participants seem to be high prevalence of OSA. The statistical parameters such as sensitivity, specificity, positive predictive values (PPV) and negative predictive values (NPV) of BQ, SBQ and OSA50 questionnaires has been calculated. The OSA50 had the highest sensitivity (93%) when compared to BQ and SBQ having the sensitivity (91%). Significant difference (p < 0.05) in specificity was found in OSA50 (93%) when compared to the specificity of BQ and SBQ (90%). The PPV and NPV of BQ and SBQ questionnaires were 24% and 77% respectively. The OSA50 achieved 65% and 98%of PPV and NPV respectively. Conclusions: The study concluded that OSA50 questionnaire seems to be better validated OSA screening tool that can be used in resource-poor primary healthcare settings. © 2020 Elsevier Ltd

Obesity Medicine

Screening of obstructive sleep apnea in an urban population in south India

Seizures are one of the serious neuropsychiatric disorders that affect 50 million people across the world, and 80% of them live in the developing countries like India. In such kind of critical care, delays in the diagnosis of neurological conditions can have a significant impact on patients with seizure. To address this treatment gap, we propose an early identificationof pre-ictal period of seizure and brain lobes for seizure detection by using electroencephalogram (EEG) biomarkers. Five subjects were voluntarily involved in this study. The raw EEG signals were filtered and decomposed using wavelet techniques and the features such as relative delta energy, relative theta energy, total beta energy, heart rate, and neuronal activity were extracted for analysis. The results showed that the relative theta activity and the neuronal activity are found to be the better features in early predicting of period of pre-ictal seizures, as both the features can be seen with significant differences among the three different time periods in all the electrode positions, which are taken into consideration. It is also evident that the occipital lobe is better in indicating the pre-ictal period earlier, as the observed data shows expected outcome from the electrode positions O1 and O2 (occipital lobe). On national level, this study will enable the primary health centres to fulfil its dream of providing basic medical facilities to serve huge sections of population with seizure. © Published under licence by IOP Publishing Ltd.