Dr.V VIJAYA KISHORE

Scopus Publications

Multi-valued logic circuit designs using GNRFETs: A review
Pasupuleti Naga Sudhakar and V. Vijaya Kishore
AIP Publishing

Shaping perspectives: Navigating augmented reality and virtual reality in modern mobile computing environments

On the use of UDWT and fuzzy sets for medical image fusion
T. Tirupal, Y. Pandurangaiah, Ajay Roy, V. Vijaya Kishore, and Anand Nayyar
Springer Science and Business Media LLC

Trickle timer modification for RPL in Internet of things
Spoorthi P. Shetty, Mangala Shetty, Vijaya Kishore, and Pushparaj Shetty
Springer Science and Business Media LLC

Automated Blood Cell Identification, Counting, and Sub type classification using Deep Learning
V. Vijaya Kishore, V. Kalpana, and R. Nagendra
IEEE
Accurate identification and quantification of blood cells, such as platelets, white blood cells (WBCs), and red blood cells (RBCs), are of the utmost importance in medical diagnostics. Conventional approaches depend on manual procedures or automated analyzers; nevertheless, recent progressions in deep learning present more efficient substitutes. This study introduces a holistic methodology for blood cell analysis through the utilization of sophisticated neural network-based structures. These structures are designed to identify, quantify, and classify blood cells according to their subtypes. The BCCD dataset is utilized to enhance precision and surmount challenges such as overlapping cells and low resolution through the implementation of various preprocessing techniques. Blood cell identification by our research was accomplished with an exceptional 90% precision by employing Convolutional Neural Networks (CNN) utilizing the MXNet architecture. Moreover, the accuracy achieved by the VGG16 architecture integrated with Keras in the sub-classification of WBCs was 85%.The results of the experiment demonstrate the efficacy of the proposed methodology, indicating a positive potential for strengthening diagnostic accuracy and efficiency in clinical practice, ultimately improving patient care standards.

A Robust Design of Fault Nodes Identification and Recovery Model Over Wireless Sensor Network
Vijaya Vardan Reddy S P, V. Vijaya Kishore, S. Diwakaran, Sujatha. V, and T. Jayakumar
IEEE
From environmental monitoring to industrial automation, wireless sensor networks (WSNs) are essential in many different applications. However, the reliability and robustness of WSNs are often compromised by faults such as node failures, communication disruptions, and data packet losses. This paper presents a comprehensive approach to fault management in WSNs, encompassing fault detection, localization, and recovery strategies. In the fault detection phase, machine learning techniques, including the utilization of the MobileNet model, are employed to classify normal and faulty behavior based on sensor data. Statistical analysis methods, such as hypothesis testing, complement machine learning approaches to detect anomalies in sensor readings. A hybrid approach combining machine learning with rule-based systems enhances fault detection accuracy. Subsequently, fault localization techniques leverage network topology analysis and localization algorithms to identify the location of faulty nodes within the network. By analyzing the connectivity between nodes and potential communication paths, vulnerable areas are pinpointed, facilitating efficient fault localization efforts. In the fault recovery phase, dynamic reconfiguration algorithms dynamically adjust network routing and data aggregation strategies in response to detected faults. Redundancy mechanisms, dynamic reconfiguration, and load balancing techniques are deployed to mitigate the impact of node failures and ensure uninterrupted data flow.

CAD Tool for Prediction of Knee Osteoarthritis (KOA)
V.Vijaya Kishore, Uday Bhaskar Dosapati, E Deekshith, Karthik Boyapati, Surya Pranay, and V Kalpana
IEEE
Knee Osteoarthritis (KOA) stands as a prevalent chronic joint condition, impacting individuals globally, especially the elderly. The imperative for timely detection and intervention in curbing OA progression and mitigating associated discomfort cannot be overstated. This paper introduces innovative predictive analytics tool, amalgamating state of the art machine learning and medical imaging methods in anticipating onset and progression of Knee OA. A Flask-based website hosts the model, integrating the MobileNetV2 neural network renowned for its superior accuracy. Radiographic data and clinical parameters undergo meticulous analysis, offering healthcare providers preemptive insights for early interventions and personalized treatment strategies. The system aspires to revolutionize Knee OA management, heralding an era of proactive healthcare that enhances individual well-being and mobility. The discussion on the importance of predicting Knee OA underscores the critical role of early intervention, resource optimization, and advancements in treatment modalities. This predictive assessment holds transformative potential for healthcare, fostering not only healthier but also more resilient communities. The paper meticulously details the methodology employed, the resultant findings, and their broader implications, making a significant contribution to the ongoing discourse on proactive healthcare solutions for musculoskeletal conditions.

Interpretation of KOA by KL Grading System using Deep Learning
V. Vijaya Kishore, V. Kalpana, and Uday Bhaskar Dosapati
IEEE
Knee osteoarthritis poses a significant global health challenge, often diagnosed using conventional radiographic grading systems such as the Kellgren-Lawrence scale, which primarily rely on X-ray images and may result in delayed diagnosis. Recent efforts to improve diagnostic accuracy and efficiency have turned to deep learning methods, particularly convolutional neural networks (CNN). In this study, we examined eight adaptive neural network models that utilize CNN for knee osteoarthritis detection. These models were trained and validated on a substantial dataset of knee $\\mathbf{X}$-rays and underwent thorough evaluation to assess their capability in classifying knee osteoarthritis severity. Our results demonstrate that the top-performing model achieved an impressive accuracy of 98.73 %, outperforming its counterparts. This research highlights the potential of deep learning models, specifically CNN, in enhancing the precision and speed of knee osteoarthritis diagnosis.

Computational Intelligence and Blockchain in Distributed Applications: Benefits and Challenges
Satyam, V. Vijaya Kishore, K. Neelima, and N. Ashok Kumar
CRC Press

Advancements in Machine Learning and Data Mining Techniques for Collision Prediction and Hazard Detection in Internet of Vehicles
Ajay Manchala and V Vijaya Kishore
University of Garmian
The Internet of Vehicles (IoV) has transfigured transportation with connected vehicles, smart infrastructure, and self-driving cars. Road collisions and accidents are still a problem for road safety. This review of the literature discusses the prediction of IoV accidents and collisions as well as the detection of hazards using data mining, deep learning, and machine learning techniques. It describes the most recent developments to these methods and how they enhanced IoV safety. The article starts off by going over data collection, data quality, and the ever-changing nature of IoV traffic scenarios. What follows is a detailed breakdown of the ML, DL, and DM methods used in IoV safety applications. Convolutional neural networks, artificial neural networks, recurrent neural networks, support vector machines, and decision trees. As examples of real-world applications and case studies, intelligent accident prediction models, driver attention forecasting, traffic congestion forecasting, spatiotemporal analysis in autonomous vehicles, scene-graph embedding, and V2P collision risk alerts are discussed. The goal of this review is to give readers a comprehensive overview of the cutting-edge methods enhancing IoV accident prediction, collision avoidance, and hazard detection.

A power/energy-efficient, process-variation-resilient multiplier using graphene nanoribbon technology and ternary logic
Pasupuleti Naga Sudhakar and V. Vijaya Kishore
Elsevier BV

Evaluating the efficacy of deep learning models for knee osteoarthritis prediction based on Kellgren-Lawrence grading system
Vijaya Kishore V, V. Kalpana, and G Hemanth Kumar
Elsevier BV

Big Data and Different Subspace Clustering Approaches: From social media promotion to genome mapping
Vijaya Kishore Veparala and Vattikunta Kalpana
Salud, Ciencia y Tecnologia
En la era actual de las tecnologías de la información, la información es el factor más importante para determinar cómo progresarán los distintos paradigmas. Esta información debe extraerse de un enorme tesoro informático. El aumento de la cantidad de datos analizados e interpretados es consecuencia directa de la proliferación de plataformas de procesamiento más potentes, el incremento del espacio de almacenamiento disponible y la transición hacia el uso de plataformas electrónicas. En este trabajo se describe un estudio exhaustivo de Big Data, sus características y el papel que desempeña el algoritmo de clustering Subspace. La contribución más importante que hace este trabajo es que lee muchas investigaciones anteriores y luego hace una presentación exhaustiva sobre las diferentes formas en que otros autores han clasificado los métodos de clustering subespacial. Además, se han proporcionado, con una breve explicación, algoritmos significativos que pueden servir de referencia para cualquier desarrollo futuro.

Enhanced Fusion Approach to Diagnose ILD and Improve Patient Outcomes
Kalpana V, Vijaya Kishore V., and G. Hemanth Kumar
IEEE
Interstitial lung disorders (ILDs) are a group of ailments marked by lung fibrosis (scarring). The four primary groups of ILDs are Nodule, Idiopathic Pulmonary Fibrosis (IPF), Sarcoidosis, and Honeycomb. Detecting these ILDs at an early stage can be facilitated by employing image enhancement methods based on wavelet transform and IHS transform-based techniques. Wavelet transforms, a mathematical method, can capture alterations in edges and textures at different scales in photographs. The IHS method, a commonly used sharpening technique, involves converting a color image from the RGB space to the IHS space through various transformations. By applying image enhancement techniques and evaluating them using parameters such as Peak Signal to Noise ratio (PSNR), Structural Similarity Index Method (SSIM), Mean Square Error (MSE) across different pulmonary image modalities, more accurate extraction of abnormalities can be achieved. The SVM classifier utilizes extracted features from enhanced images to classify the disease, leading to improved prognosis, prevention of severe conditions, and early diagnosis of ILDs.

DFIR-Net: Convolutional Neural Networks with Deep Learning for Content-based Image Retrieval
V. Vijaya Kishore, V. Kalpana, and B. Hari Krishna
IEEE
Content based image retrieval (CBIR) is essentially responsible for many applications including search engines, digital libraries, cloud management systems. However, the conventional approaches are failed to provide the maximum retrieval performance. As a result, the central topic of discussion in this paper is the application of a deep learning convolutional neural network to the CBIR system (DLCNN). Here, DLCNN model is used to extract the seismic features from database and act as deep feature-based image retrieval network (DFIR-Net). Further, principal component analysis (PCA) is used to select the best features, which also reduce the dimension reduction. Finally, Euclidean distance is used to measure similarity between test and trained features, which results the similar images as retrieved images. The simulation results showed that the proposed method outperformed state-of-the-art CBIR systems in terms of retrieval efficiency.

Modified Support Vector Machine to Improve Diabetic Disease Prediction
V Vijaya Kishore, V Kalpana, and M Jayalakshmi
IEEE
Data mining has become increasingly important in recent years for the capacity of the medical industry to anticipate illness outbreaks. The process of selecting, analyzing, and modelling massive amounts of dossier information with the goal of locating previously unknown connections or alliances that are significant to information researchers is known as “data mining.” Data mining is a technique. Diabetes is a condition that is induced by having an abnormally high amount of glucose fixation in the blood. Several different computational understanding systems that use various classifications to forecast and identify diabetes were explained. The choice of dependable classifiers unquestionably contributes to an increase in the precision and proficiency of the system. In this article, a technique is proposed that identifies data by utilizing an SVM classifier that has been altered. Within the scope of this investigation, we developed a computational model with the goal of improving diabetes forecasting.

COVID-Net: COVID-19 detection and classification from Chest X-rays using DCNN
V. Kalpana, V. Vijaya Kishore, and B. Hari Krishna
Institution of Engineering and Technology

KNEE OSTEOARTHRITIS PREDICTION DRIVEN BY DEEP LEARNING AND THE KELLGREN-LAWRENCE GRADING
V. Vijaya Kishore, Shilpa Sreya Batthala, Jithendra Varma Chamarthi, Chalambu Achyutasai, and B Subrahmanyam
Faculty of Engineering, University of Kragujevac

Smart RFID: Experimental Evaluation of Secured Students Attendance Handling System Using RFID
Sruthy R, S. Kavitha, N. Darwin, Anita Titus, V. Vijaya Kishore, and Dharshini. B. S
IEEE
While old techniques are time-consuming and inefficient, recent years have seen a rise in the importance of student attendance as a reflection of academic accomplishments and the effectiveness provided to any university. Recently, however, a variety of automated identifying technologies, such as Radio Frequency Identification (RFID), have gained popularity (RFID). Many studies and applications being developed to make the most of this technology, which raises certain ethical questions. RFID, or radio-frequency identification, is a wireless technology used for the purpose of identifying and monitoring an object by the transfer of data from an electronic tag, termed an RFID tag or label, via radio waves to an RFID reader. In this project, an RFID-based system has been developed to provide an attendance monitoring system. In addition to streamlining the process as a whole, automated attendance management software will also produce a well-structured and analyzed report of the pattern of student attendance and time management, which may aid in the allocation and use of human resources. In this study, RFID was used to the task of tracking student attendance, allowing teachers and administrators to more efficiently record in-person classroom statistics that may be used to determine how students should be graded and inform other administrative choices.

Design of Three-valued Logic Based Adder and Multiplier Circuits using Pseudo N-type CNTFETs
K. Maheswari, M. L. Ravi Chandra, D. Srinivasulu Reddy, and V. Vijaya Kishore
FOREX Publication
This work presents a novel technique to develop the three-valued logic (TVL) circuit schematics for very large-scale integration (VLSI) applications. The TVL is better alternative technology over the two-valued logic because it provides decreased interconnect connections, fast computation speed and decreases the chip complexity. The TVL based complicated designs such as half-adder and multiplier circuits are designed utilizing the Pseudo N-type carbon nanotube field effect transistors (CNTFETs). The proposed TVL half adder multiplier schematics are developed in HSPICE tool. Additionally, the delay and circuit area for the half- adder and multiplier circuits are investigated and compared to the complementary circuits. The memory usage and CPU time for the proposed circuits are also analyzed. It is observed that the proposed circuit designs show the improved performance up to 43.03% on an average over the complementary designs.

MRI and SPECT Brain Image Analysis Using Image Fusion
V. Kalpana, V. Vijaya Kishore, and R. V. S. Satyanarayana
Springer Nature Singapore

GUI-CAD tool for segmentation and classification of abnormalities in lung CT image
V. Vijaya Kishore and R.V.S. Satyanarayana
IGI Global
A vital necessity for clinical determination and treatment is an opportunity to prepare a procedure that is universally adaptable. Computer aided diagnosis (CAD) of various medical conditions has seen a tremendous growth in recent years. The frameworks combined with expanding capacity, the coliseum of CAD is touching new spaces. The goal of proposed work is to build an easy to understand multifunctional GUI Device for CAD that performs intelligent preparing of lung CT images. Functions implemented are to achieve region of interest (ROI) segmentation for nodule detection. The nodule extraction from ROI is implemented by morphological operations, reducing the complexity and making the system suitable for real-time applications. In addition, an interactive 3D viewer and performance measure tool that quantifies and measures the nodules is integrated. The results are validated through clinical expert. This serves as a foundation to determine, the decision of treatment and the prospect of recovery.

Preface
IOP Publishing
The 2021 International Conference on Power Electronics and Power Transmission (ICPEPT 2021) was held on October 15-17, 2021 in Xi’an, China. ICPEPT 2021 is to bring together innovative academics and industrial experts in the field of Power Electronics and Power Transmission to a common forum. The primary goal of the conference is to promote research and developmental activities in Power Electronics and Power Transmission and another goal is to promote scientific information interchange between researchers, developers, engineers, students, and practitioners working all around the world. The conference will be held every year to make it an ideal platform for people to share views and experiences in Power Electronics and Power Transmission and related areas. The conference model was divided into two sessions, including oral presentations and keynote speeches. In the first part, some scholars, whose submissions were selected as the excellent papers, were given 15 minutes to perform their oral presentations one by one. Then in the second part, keynote speakers were each allocated 30-45 minutes to hold their speeches. More than 100 participants attended the meeting. There were over 20 experts and scholars in the area of Power Electronics and Power Transmission representing different famous universities and institutes around the globe to form Conference Committees. In the keynote presentation part, we invited three professors as our keynote speakers. The first keynote speakers, Assoc. Prof. Jinsong Tao, from School of Electrical Engineering and Automation, Wuhan University, China was invited to present his talk Operation Mode Analysis and Coordinated Control Strategy Research of Multi-terminal Network with DC Microgrid. Assoc. Prof. Sohrab MIRSAEIDI, from Beijing Jiaotong University, China was our second keynote speakers. He presented a talk: Improvement of Capacitor-Commutated-Converter-Based and Fault-Current-Limiting-Based Commutation Failure Prevention Approaches in HVDC Transmission Networks. In this talk, the structure of an improved Controllable Commutation Failure Inhibitor (CCFI) is presented which obviates the main drawbacks of the existing capacitor-commutated-converter-based and fault-current-limiting-based strategies. Assoc. Prof. ANWAR ALI, from Zhejiang Sci-Tech University, China as our finale keynote speakers. He delivered a speech: Design and Development of a Small Satellite Subsystems-AraMiS-C1. We are glad to share with you that we received lots of submissions from the conference and we selected a bunch of high-quality papers and compiled them into the proceedings after rigorously reviewed them. These papers feature following topics but are not limited to: 1. Power Electronic Technology. 2. Electric Power System. All the papers have been through rigorous review and process to meet the requirements of International publication standard. We are really grateful to the International/National advisory committee, keynote speakers, session chairs, organizing committee members, student volunteers and administrative assistance of the management section of University, including accounts section, digital media and publication house. Also, we are thankful to all the authors for contributing a large number of papers in the conference, because of which the conference became a story of success. It was the quality of their presentations and their passion to communicate with the other participants that really make this conference series a great success. The Committee of ICPEPT 2021 List of Committee members are available in this pdf.

Investigation of GPS-TEC Inconsistency and Correlation with SSN, Solar Flux (F<inf>10.7</inf>cm) and Ap-index during Low and High Solar Activity Periods (2008 and 2014) over Indian Equatorial Low Latitude Region
K.C.T. Swamy, V. Vijaya Kishore, S. Towseef Ahmed, and M A Farida
IEEE
The ionosphere Total Electron Content (TEC) measurement using Global Positioning System (GPS) technology (GPS-TEC) is carried out over the equatorial low latitudes of Indian region viz; Bangalore $\\left(13.0^{0}\\mathrm{~N}, 77.5^{0}\\mathrm{E}\\right)$, Hyderabad $\\left(17.5^{0} \\mathrm{~N}, 78.5^{0} \\mathrm{E}\\right)$, Bhopal $\\left(23.0^{0} \\mathrm{~N}, 77.2^{0} \\mathrm{E}\\right)$, Delhi $\\left(28.7^{0} \\mathrm{~N}, 77.2^{0} \\mathrm{E}\\right)$, Ahmedabad $\\left(23.0^{0} \\mathrm{~N}, 72.5^{0} \\mathrm{E}\\right)$ and Guwahati $\\left(26.0^{0} \\mathrm{~N}, 92.0^{0} \\mathrm{E}\\right)$ for low solar activity (LSA i.e., 2008) and high solar activity (HSA i.e., 2014) periods of solar cycle 24. The measured GPS-TEC were analysed to report diurnal, day to day and monthly variation with equatorial low latitude, solar activity and geomagnetic conditions. Moreover, GPS-TEC variation is investigated to find the correlation with Sun Spot Number (SSN), Solar Flux (F10.7 cm) and Ap-index. From the results, it is found that the TEC is enhanced during HSA (2014) compared to LSA. However, depletion is observed during pre-sunrise hours (4:00 hrs. to 6:00 hrs.) particularly in spring and autumn equinox periods of HSA (2014). Also, found that the equatorial ionization anomaly (EIA) crest which is occurred over Bhopal region during LSA (2008) is shifted to the higher latitudes (i.e. Delhi region) during HSA period (2014). Further, it is observed that Ap-index and F10.7 cm have the better correlation with GPS-TEC compared to SSN for both LSA (2008) and HSA (2014) periods. Additionally, it is also observed that the increased solar activity has negative impact on correlation between GPS-TEC and Ap-index and F10.7 cm.

Effect of Noise on Segmentation Evaluation Parameters
V. Vijaya Kishore and V. Kalpana
Springer Singapore
Lung cancer is the killing disease that maximum vertexes due to drugs, smoking chewing of tobacco. The affliction of this disease is 14% than any other neoplasm, curtailing the functioning and existence of the diseased by 14 years. The overall relative survival rate is less than 18%. Early diagnosis of lung abnormality is a key challenge to improve the survival rates. Identification of malignant nodules from the medical image is a critical task as the image may contain noise during the processing that can be unseen and also having similar intensities of unwanted tissue thickening. This may debase the image standard and lead to wrong predictions. To process and reconstruct a medical image noise is to be eliminated. To exactly diagnose the disease, image is to be properly segmented from the other regions as to identify the lesions. Accuracy of ROI identification depends on the selection of segmentation operators. In this paper the performance of reconstruction is evaluated by using morphological operations and segmentation filters in noisy environment. The analysis is done between the original extracted ROI and noise image based on the evaluation parameters, Global Consistency Error (GCE) and Variation of Information (VOI). The best suitable operator can be used to obtain the ROI which can help for early diagnosis of the disease so as to control the cancer incidence and mortality rates.

Dr.V VIJAYA KISHORE

RESEARCH INTERESTS

Scopus Publications

RECENT SCHOLAR PUBLICATIONS

Publications