@kalasalingam.ac.in
Head-Incubation/ Associate Professor-ECE
kalasalingam Academy of Research and Education
Dr. J. Deny holds an impressive academic background and has made significant contributions in the field of electronics and communication engineering, particularly focusing on image processing, network security, and innovation techniques in entrepreneurship. Here's a concise summary of his educational and professional journey:Dr. J. Deny earned his Bachelor of Engineering (B.E.) degree in electronics and communication engineering from Anna University in 2010. In 2012, he obtained a Master of Technology (M.Tech.) degree in digital communication and networks from the Kalasalingam Academy of Research and Education.
Dr. Deny pursued his passion for research and completed his Ph.D. in the field of image processing and network security at the Bharath Institute of Higher Education and Research in 2017.Currently, he is engaged in a Post-Doctoral Fellowship program with a focus on Innovation and Entrepreneurship at the Kazimierz Pulaski University of Technology and Humanities in Radom, Poland
B.E.,M.., (PDF)
Computer Networks and Communications, Management of Technology and Innovation, Signal Processing, General Engineering
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
M Sakthimohan, J Deny, K Umapathi, and Hady H. Fayek
Informa UK Limited
E. Sangeetha and J. Deny
AIP Publishing
Kavitha Gopalun, Deny John Samuvel and Deny John Samuvel
University of Slavonski Brod, Mechanical Engineering Faculty in Slavonski Brod
: Non-orthogonal Multiple Access (NOMA) is the technique proposed for multiple accesses in the fifth-generation (5G) cellular network. In NOMA, different users are allocated different power levels and are served using the same time/frequency Resource Blocks (RBs). The main challenges in existing NOMA systems are the limited channel feedback and the difficulty of merging them with advanced adaptive coding and modulation schemes. The 5G system in NOMA aims to access low latency, efficiency in superior spectra, and balanced user fairness. NOMA allows multiple users with different power levels to share resources in radio frequency time. The existing Orthogonal Multiple Access (OMA) system produces high latency, high computational complexity, and throughput complexity in modifying wireless channels. To overcome these issues, this paper proposed optimising deep learning-based power domain NOMA of Long Short-Term Memory (LSTM) with particles Swarm optimisation (PSO) technique. This proposed work (LSTM-PSO) is deployed with a Cooperative network model. The advantage of LSTM-PSO in Cooperative Non-orthogonal Multiple Access (CNOMA) is that it provides high performance, better utilisation of downlink, efficiency in sharing of resources, enhancing the activity of users, capacity of the base station and improving quality of service, estimation of channel condition. LSTM-PSO got a higher accuracy rate of 92.05%, LSTM got 86.45%, PSO got 88.13%, and the accuracy rate of ANN and DNN was 83.76% and 84.70%.
N. Bhuvaneswary, J. Deny, and A. Lakshmi
IOS Press
Universal Verification Methodology (UVM) caters to an essential role in verifying the different categories of circuits ranging from small-scale chips to complex system-on-chip architectures. Constrained random simulations are an indispensable part of UVM and are often used for design verification. However, the effort and time spent manually updating and analyzing the design input constraints result in high time complexity, which typically impacts the coverage goal and fault verification ratio. To overcome this problem, this paper proposes a novel hybrid optimized verification framework that combines Reinforcement Learning (RL) and Deep Neural Networks (DNN) for automatically optimizing the input constraints, accelerating faster verification with a high coverage ratio. The proposed algorithm uses reinforcement learning to generate all possible vector sequences needed for testing the target devices and corresponding outputs of the target devices and potential design errors. Furthermore, the framework intends to use high-speed deep-feedforward neural networks to automate and optimize the constraints during runtime. The proposed framework was developed using Python interfaced with the TCL environment. Extensive experimentation was carried out using several circuits, including multi-core designs, and performance parameters such as coverage accuracy, speed, and computational complexity were calculated and analyzed. The experiment demonstrated the proposed framework remarkable results, showing its superior performance in faster coverage and fewer misclassification errors. Furthermore, the proposed framework is compared with existing verification frameworks and other classical learning models. Good results demonstrate that the proposed framework increases the 4.5x speed for verifying multi-core designs and the 99% accuracy of detection and coverage.
G. Kavitha and J. Deny
Walter de Gruyter GmbH
Abstract In the framework of next-generation communication systems, Non-Orthogonal Multiple Access (NOMA) has attracted considerable interest. The fundamental advantage is that it has greater spectrum utilization than its orthogonal equivalents. This proposed work integrates Single-Input Single-Output NOMA (SISO) with Coordinated Multi-Point (CoMP). It uses both systems based on Quadrature Phase-Shift Keying (QPSK). A power-tolerant NOMA reduces the system’s vulnerability to erroneous power allocation by adaptively modifying each user’s signal power. The transmitted data is used to modify the power in the Power-Adaptive NOMA (PANOMA). PANOMA helps improve the Bit Error ratio and also improves the computational complexity. The Bit Error Rate (BER) and the lower limit capacity efficiency across Rayleigh fading channels are determined in precise closure representations of more than two consumer situations to measure its capability. The proposed method PA-CoMP-NOMA improves the Bit Error ratio in both systems. It improves the average BER among all users. Compared to its orthogonal cousin, NOMA has higher spectral efficiency. Nevertheless, our proposed method retains this feature as well as superior BER performance, although its spectral effectiveness is lower than that of the classic sum-rate based power NOMA.
R. Raja Sudharsan, J. Deny, E. Muthukumaran, and R. Varatharajan
Springer Science and Business Media LLC
B Perumal, P Nagaraj, J Deny, V Rajesh, Kakarla Manoj Kumar, and Kuncha Mahendra Reddy
IEEE
Our surroundings are brimming with visual signals that are designed to aid human navigation. For instance, there are room numbers next to doors and building directories at the entrances. We will design a more reliable and useful system by creating robot wheelchair systems that can comprehend these cues. The designs and developments of our robot’s wheelchair systems, Wheel, as well as its vision-based navigation technologies, are discussed in this study. The robot wheelchair system builds maps of the environments it travels through using stereo vision; these maps can subsequently be annotated with the data gained from the sign. We also discussed the incorporation of an assistive robot arm that will help with opening doors and pushing the buttons on elevators. numerous parties have constructed and conducted an extensive study on mobile double-wheeled self-balancing robots for academic, recreational, and commercial objectives. The designs and assembly of a compact, autonomous, two-wheeled robot platform are described in this study. The robot is quick, has several onboard sensors that let it navigate through an unstructured environment, can jump over minor obstacles, and can communicate wirelessly over short and long distances. The up-boards single camera machined visions module, which aids the robots in recognizing impediments, is one of the features. This disclosure is intended to help other researchers working on related projects enhance the design of these devices.
E. Sangeetha and J. Deny
IEEE
Smart cities are a vision of the future, promising to enhance the quality of life for urban dwellers while promoting sustain ability and efficiency in city management. To achieve these goals, the integration of diverse data sources, real-time analysis, and responsive actuator control is essential. The InterSCity platform represents a pioneering solution in this domain, offering a dynamic and adaptable infrastructure for managing various urban services. This abstract provides an overview of how the InterSCity platform enables innovative actuator control within smart cities. This work aims to analyze, plan, develop and test cases of a new approach for the InterSCity performance module. In addition, this work proposed for the new performance service, implemented the proposed service, tested with real platform devices before and after the change, and analysis and discussion of the results are obtained.
B. Perumal, J Deny, T Aravinth, S Gowshigan, E Nambi, and V Rajendra Prasath
IEEE
In this study, we introduce a cutting-edge approach to advancing sustainable piscicultures through the integration of a multilingual environmental monitoring system. The primary focus is on optimizing the management of critical environmental parameters in fish farming, utilizing sensors for Total Dissolved Solids (TDS), pH, temperature, turbidity, and dissolved oxygen. Central to this innovative system is the Raspberry Pi, which serves as a hub for real-time data collection and control. The collected data is processed and securely stored in a dedicated database, ensuring the availability of historical records for analysis. A mobile application complements this system, offering remote access to sensor data, and the mobile app is designed to support multiple languages, fostering widespread adoption and knowledge exchange on a global scale. Overall, this research emphasizes the potential of technology in pisciculture farming. Numerous challenges were faced by the farmers, with increasing fish mortality rates attributed to water quality issues being a prominent concern. The pivotal role of water quality in fish growth necessitates constant monitoring of various parameters such as pH, salt levels, and water cloudiness. The amalgamation of hazardous water with normal water exacerbates these challenges, demanding vigilant surveillance. Furthermore, the existing issue is compounded by inadequate data visualization tools, hindering effective monitoring. Addressing these critical concerns is paramount for optimizing fish health and yield in pisciculture operations.
B. Perumal, V. Bargavram, M. Bala Atharsh, Manoranjan Kumar, Deny. J, and Rajesh V
IEEE
Agriculture, a cornerstone of the global economy, faces challenges meeting the growing demands of an expanding world population. Addressing the shortage of skilled labor, "Smart Agriculture Using Bio Sensors and AI" emerges as an innovative solution. This system, integrating AI and bio sensor technology, predicts optimal crops based on crucial soil parameters. Real-time data is collected and analyzed, generating precise crop recommendations. Beyond boosting yields, the technology mitigates climate effects, reduces reliance on manual labor, fosters sustainability, and fortifies food security. This project offers a data-driven, sustainable solution for agriculture, ensuring productivity and economic growth in a world marked by expanding populations.
E. Sangeetha and J. Deny
IEEE
This study focuses on addressing the communication protocols of the medium access control layer, known as MAC. Among the best-known protocols are the ALOHA protocols, in their pure and slotted version (S-ALOHA) and the carrier-sensing media access protocols known as CSMA (Carrier Sense Multiple Access) in its different versions; which have been the basis for the development of different communication standards. Currently, there are multiple versions of the classic protocols of this layer that have achieved and demonstrated an improvement to the performance presented in the base protocols, and new strategies are continuously proposed according to the technologies that emerge each year. In addition, its use continues to be valid for certain applications, being even necessary for the request of bandwidth channel resources for sending a high volume of information, as is the case of control channels and random access from cellular systems.
D. Manoj Kumar, Deny J, Nagaraj P, Kudithipudi Dhanveer, Vaddepally Punith Kumar, and R Arthi
IEEE
Diabetes is a chronic disease that occurs when the blood glucose levels in the human body exceed the normal range. If left untreated, diabetes can lead to various health complications. To prevent such complications, early detection and management of diabetes are crucial. In this study, a novel system is proposed that uses hyperparameter tuning in addition to various machine learning algorithms for early detection of diabetes. This article also tunes the hyperparameters of the algorithms to optimize their performance. The results indicate that the Support Vector Machine algorithm provides the best fit for predicting diabetes. Hyperparameter tuning further improves the performance of this algorithm. Our approach can be used as a decision support tool for healthcare professionals to identify high-risk patients early on and provide appropriate care and management. Our study highlights the potential of machine learning algorithms and hyperparameter tuning for developing accurate and reliable predictive models for diabetes in expecting mothers. These models can aid healthcare professionals in taking preventive measures to improve maternal and child health outcomes.
N. Senthil Madasamy, K. J. Eldho, T. Senthilnathan, and J. Deny
Informa UK Limited
J. Deny, Duggirala Lakshmi Sai Deepika, Vempa Lekhana, Gonuguntla Vandana, and Katta Gayathri Devi
IEEE
This research study presents the five-staged pipelining concept with automation in functionality verification of the MIPS processor driver module, which makes the process interlinked to organize the activity in a parallel manner. As the design complexity in RTL increases with the current advancement of VLSI technology, it creates an impact on the verification process and the techniques in approaching the solution for complexity. In the present scenario, efficient verification involving less time consumption and accuracy in working is required and essential. Therefore, UVM, a standardized verification methodology, was employed to verify the functionality of the test bench. The verification process faces several challenges, including complex processor architectures, the need for efficient verification techniques, and ensuring thorough coverage of all functional aspects. To address these challenges, recent techniques in constrained random verification and the utilization of UVM’s object-oriented programming (OOP) features are employed. This study aims to develop an efficient and comprehensive verification of the driver module for the Five-Stage Pipelined MIPS Processor using UVM. The driver module in the MIPS Processor facilitates the handling and coordination of input signals, ensuring proper communication and synchronization between various components. It plays a crucial role in driving the execution of instructions and managing the flow of data within the processor.
P. Shobana and J. Deny
IEEE
In this article, a new approach has been proposed to segment the skin lesion using Dermoscopic image. The hairs in the images are removed by Dull Razor's method with two iterations. Then the color artefacts in images are removed using standard color constancy methods such as color equalization and grey world method. Also, these two color corrected versions are blended using multiscale image fusion technique. Then the two color corrected versions and their fused version are given as input to a U-Net which is developed with three encoders. Then the feature maps obtained from the encoders are fused and concatenated with the decoder part to get the segmented skin lesion. This approach outperforms well compared with the existing works.
J. Deny, M Dinesh Ram., C Satheesh., B Suryakumar, and Omkar Rushikesh Mekala
IEEE
The research study intends to develop an Object-Oriented Programming (OOP)-based UVM testbench monitor module. According to the OOP model, the testbench is made up of various objects, each of which is intended to perform a specific job of the verification flow. A 10GE MAC Core architecture is being verified. Even though the design comes with a crude test case that provides for some simple logic checks, scaling and/or maintaining such a testbench would be very challenging. This paper aims to provide a clean verification environment output monitor module that is easy to understand, control, and grow due to the tight separation between the RTL domain & the verification domain. This method has demonstrated to be very beneficial when working with the verification of sophisticated digital systems, like those present in today’s applications.
J. Deny, P Rajalakshmi, and P Nagaraj
IEEE
This brief is focused on sweat glucose monitoring for diabetes patients. Diabetes is a continual disease or a set of metabolic ailments wherein someone suffers from an excessive level of glucose in the frame. The majority of people currently suffer from diabetes. Diabetes is a manageable illness. People with diabetes must test their blood regularly and take the appropriate insulin. Collecting blood from the body on regular basis can cause a variety of difficulties, including heart and kidney disorders, stroke, and blindness. There is currently no reliable approach for determining the likelihood of developing diabetes. As a result, the appropriate safeguards can be implemented. Sweat-based blood glucose monitoring relieves the pain of blood-based analysis. The conductivity of the skin is measured using a Sweat glucose sensor module. The glucose level is calculated using this data. This method of measuring glucose is believed to be comfortable, cost-effective, and simple to monitor.
J. Deny, Siva Kamisetty, Harsha Vardhan Reddy Thalakola, Jagadeesh Vallamreddy, and Vijay Kumar Uppari
IEEE
Text summarization is a process of reducing a large amount of text into shorter version while retaining the most important information. When applied to news articles, text summarization can be used to provide a brief overview of the article’s main points, saving readers time and allowing them to quickly determine if the article is of interest to them. The massive increase in the volume of news articles being published every day, it is becoming increasingly difficult for readers to keep up with the latest developments. Text summarization, is technique of producing a short overview of a longer text, can assist readers in quickly grasping the major ideas of an article to present a method for abstractive text summarization of news articles using recurrent neural networks and sentence scoring approaches. The results of this experiment shows that proposed approach outcomes the existing methods in terms of summarization quality and efficacy. This approach provides a promising direction for improving the efficiency and accuracy of text summarization for news articles.
M. Raja, J. Deny, Nagaraj P, and Muneeswaran V
IEEE
There are numerous ways to assist blind people as they will not be able to detect text in all fonts, numbers, or low-light situations. To address this, an innovative model has been designed to detect various fonts, numbers, and so on. A camera has also been embedded to identify and capture text from printed text. Further, the image will be analyzed with Tesseract-Optical Character Recognition. Finally, to implement it in real-time, the Text-to-speech software is used.
G Kavitha and J Deny
Auricle Technologies, Pvt., Ltd.
The next-generation wireless networks and communications such as 5G/6G offers various benefits such as low latency, high data rates, and improvement in user numbers with increased base station capacity and quality of service. These advantages are obtained from the increasing receiver complexity through the non-orthogonal multiple access (NOMA) of users. It is the promising radio access approach used to enhance next-generation wireless communications. Among the techniques of NOMA such as power and code domain, this paper concentrates on power domain NOMA. The user in the network for transmission is selected using a deep learning approach called deep neural network (DNN). This user selection results are the training data and the loss function is modified for the selection of users that could meet the constraint the selected user cannot be in both strong and weak groups. The user aggregation/user pairing among the sub-channels is performed through the exhaustive analysis using particle swarm optimization (PSO). The usage of DNN-PSO enables the transmitter and required minimum uplink and downlink transmitting power and guaranteed for Quality of Service of each user. The simulation and comprehensive statistical evaluation are performed with the comparative analysis of energy efficiency and maximum achievable rate with the given spectrum efficiency (SE) of PD-NOMA. The proposed model ensures reduced latency, increased throughput, less energy, achievable data rate, user fairness and increased reliability and quality of service.
J. Deny, P. Rajalakshmi, V. Muneeswaran, R. Raja Sudharsan, and P Nagaraj
IEEE
This brief is focused on the Artificial Pancreas method for glucose control by using Continuous glucose monitoring sensors. Diabetes medical care is generally supported by separate insulin infusions that are used for interval measurements. The designed controller in this paper is proportional-integral-derivative (PID). These findings were based on substantial disruptions to glucose levels, like exercise, a delay in the glucose sensor device, and nutrition mixed meal absorption during meals. It gives experimental results of Hypoglycemia and Hyperglycemia during normal blood glucose measurements and CGM Measurements and computing the blood glucose for both adolescent and adult people
T R Sangeeta and J Deny
IEEE
Today’s wireless communication technology mainly makes use of radio waves and microwaves. These electromagnetic waves are transmitted and received using antennas. Recently emerged free space optical communication technology uses light waves traveling in free space to transmit data signals. For this our bigger antennas are replaced by minute optical nanoantennas. A main problem faced in optical communication technology is insufficient electromagnetic spectrum initialization. Nanoantennas are capable of solving this problem to a certain extent. The concept of optical nanoantennas is still in the very first phase of evolution. Developments in nanotechnology have improved nanoantenna fabrication techniques. So, a theoretical study of nanoantennas is highly desirable. This review paper provides an insight into various aspects of nanoantennas. A comparison between different types of nanoantennas is also done.
N. Bhuvaneswary, J. Deny, and A. Lakshmi
IEEE
The Universal Verification Approach is a robust verification methodology for a wide range of design sizes and types. The term “universal” refers to the methodology's ability to check everything and everything in the universe - or at least everything in integrated circuits. Through analysis of UVM verification methodology, research is focused on verification reusability. The reuse of the component, platform, test cases, and sequences is reflected in this paper's reusability. Initially the paper discusses about the reusability of UVM platform and test case, followed by a look at a standard UVM verification platform. The I2C protocol is created based on reusable verification environment and the verification results are analyzed.
J. Deny, B. Perumal, P. Nagaraj, K. Alekhya, V. Maneesha, and S. Amarnath Reddy
IEEE
Nowadays, Arthritis is a common disease among older people that influences the joints. It creates ache and inflammation, making it tough to walk, run or live active. Estimating the quantity or thickness of cartilage on the knee is critical for figuring out arthritis. In this study, MRI scans of the knee had been analyzed. Before segmentation, the picture is preprocessed with B-Splines creation. After that, canny and log facet detectors are used to obtain the boundaries or sharp edges or high variations in the grey values in the image. The proposed method extracts the cartilage thickness which plays a key role in determining the Osteoarthritis. The variety of pixels among edges is used to calculate the thickness. The abnormality of arthritis is then decided primarily based relating to the thickness of cartilage. The Joint Space Width (JSW) acquired is contrasted with standard joint space width esteem, 5.7mm for male and 4.8 mm for female. From this, the osteoarthritic knee can be distinguished from typical knee. This is a brief and smooth method to assess arthritis by relying on the thickness (viscosity) of the cartilage.
P. Shobana and J. Deny
IEEE
In this paper, the color artifacts that typically occur in dermoscopy images are removed using the image fusion-based color correction method. Two color-corrected versions of the original image are blended using the weight-based image fusion techniques. The contrast of the skin lesion is also enhanced to distinguish the affected parts from the normal skin. The purpose of the work is to enhance the positive impact on the further detection of melanoma type of skin disease.