venkatesan ramachandran
@karunya.edu
Associate Professor, Department of Computer Science and Engineering
Karunya Institute of Technology and Sciences
Scopus Publications
Scopus Publications
V. D. Ambeth Kumar, Sowmya Surapaneni, D. Pavitra, R. Venkatesan, Marwan Omar, and A. K. Bashir
World Scientific Pub Co Pte Ltd
In the colloquy concerning human rights, equality, and human health, mental illness and therapy regarding mental health have been condoned. Mental disorder is a behavioral motif that catalyzes the significant anguish or affliction of personal functioning. The symptoms of a mental disorder may be tenacious, degenerative, or transpire as a single episode. Brain sickness is often interpreted as a combination of how a person thinks, perceives, contemplates and reacts. This may be analogous to a specific region or workings of the brain frequently in a social context. Anxiety disorders, psychotic disorders, personality disorders, mood disorders, eating disorders, and many more are examples of mental disorders, while complications include social problems, suicides, and cognitive impairment. These days, mental disorders are quotidian worldwide, and clinically consequential levels of derangement rise adversely. The purpose of this paper is to aid in prognosis of the type of mental disorder by analyzing the brainwaves such as Alpha ([Formula: see text]), Beta ([Formula: see text]), Gamma ([Formula: see text]), Theta ([Formula: see text]), Delta ([Formula: see text]) with the help of big data analysis and the Internet of Medical Things (IoMT). IoMT helps in gathering the required data and data transmission, while big data analysis helps in predicting the type of disorder.
R. Venkatesan, T. Jemima Jebaseeli, K. Ramalakshmi, and P. B. Hemanthkumar
AIP Publishing
Jeffrey Philip Biju, K Ramalakshmi, R Venkatesan, G Naveen Sundar, Golden Nancy, and Manoshika Catherine J
IEEE
Potatoes, a globally recognized vegetable, are integral to agriculture worldwide. However, potato leaf diseases pose significant threats to potato yields. In this paper, we propose a methodology utilizing image processing techniques to identify and classify these diseases promptly, minimizing financial losses for farmers. Leveraging machine learning, particularly Convolutional Neural Networks (CNN), our model accurately detects potato leaf diseases from images. We meticulously engineer each step, from data preprocessing to model evaluation, utilizing TensorFlow and Keras. Through dataset visualization, partitioning, and augmentation, we prepare our model for robust training. The CNN architecture, chosen for its superior image classification capabilities, demonstrates remarkable accuracy in distinguishing between healthy and diseased potato leaves. Our methodology showcases the potential of technology to revolutionize agriculture by enabling early disease detection and efficient crop management.
Deniel Sampson J, K Ramalakshmi, R Venkatesan, G Naveen Sundar, Golden Nancy, and Prince Nickson
IEEE
The simulation focused on assessing the vulnerabilities and potential impacts of cyberattacks within the healthcare sector, specifically in a hospital environment. Various attack scenarios, including ransomware, distributed denial-of-service (DDoS) attacks, and unauthorized access to patient records, were simulated to gauge the extent of potential damage. The cybersecurity team successfully identified weak points and devised strategies to mitigate these risks. To enhance detection and response capabilities, a machine learning-based mechanism was implemented, leveraging algorithms like support vector machines, random forest, and deep learning models. This mechanism analyzes real-time network traffic data, identifying deviations from normal behavior such as unusual data transfer patterns, unauthorized access attempts, or abnormal system behaviors. Trained on labeled datasets, these algorithms classify network traffic into normal or potentially malicious activities. The system's continuous learning capabilities enable it to adapt and improve detection as new attack patterns emerge. Overall, the simulation, coupled with the advanced detection mechanism, empowers the cybersecurity team to proactively safeguard patient data, ensure uninterrupted healthcare services, and fortify critical infrastructure against evolving cyber threats, thereby enhancing their understanding of vulnerabilities and bolstering incident response capabilities.
Darwin Raj A, K Ramalakshmi, R Venkatesan, G Naveen Sundar, Golden Nancy, and S Shirly
IEEE
Nowadays, the global challenge of ensuring food security for a growing population necessitates innovative solutions in agriculture. The convergence of Internet of Things (IoT) and Artificial Intelligence (AI) technologies presents a promising avenue for addressing key issues such as crop disease management and resource optimization. In that project proposes a holistic approach to smart agriculture by integrating IoT-based sensor systems for real-time monitoring of key agricultural parameters with AI-powered disease detection and severity estimation techniques. Leveraging advanced sensor technologies, including soil moisture, float level, pH, and humidity sensors, the proposed system collects real-time data from agricultural lands and transmits it to a cloud-based platform. Additionally, a deep learning-based Convolutional Neural Network (CNN) model is employed to detect and classify crop diseases from images captured in the field. The system further estimates disease severity by analyzing affected and unaffected leaf regions, enabling targeted treatment with appropriate pesticide concentrations. By combining IoT sensor data with AI-driven disease management. The integrated system offers a comprehensive solution for precision agriculture. Through early disease detection, optimized resource usage, and timely intervention, the proposed system aims to enhance crop yield, minimize wastage, and contribute towards global food security goals.
Venkatesan R, Brijit Benny, Shirley C P, and Berin Jeba Jingle I
IEEE
As the virtual and real worlds continue to collide, digital twins may become important tools for finding solutions to some of the most serious challenges facing the sustainability movement. These challenges include making effective use of resources, adjusting to the effects of climate change, and ensuring that everyone has access to a high quality of life. The first steps have been taken on the road to making widespread use of digital twins. It is imperative that their connectedness should be secured if their potential is to be fully utilized. This presents a number of challenging situations. The digital transition may make it possible to achieve several of the United Nations' sustainable development objectives. Data and technology should assist the user to make appropriate judgements that are better suited to their circumstances. It’s feasible that the computer model can see into the future and predict the user about the consequence. This may be used to make predictions about the future, analyze the present, and analyze how a decision will play out in the future. These features may have an effect on a number of different sectors including commerce. The use of dynamic modelling may be beneficial for improving efficiency in the management of supply chains, transportation, and crowds.
K R Aagaash, K Ramalakshmi, R Venkatesan, G Naveen Sundar, Golden Nancy, and S Shirly
IEEE
An integrated system for spraying pesticides and fertilizers on plants, coupled with machine learning capabilities for disease prediction, revolutionizes crop management, transforming crop management. This innovative solution administers precise doses of nutrients and pesticides to optimize crop health autonomously. Leveraging CNN algorithms and image processing, it predicts diseases proactively, mitigating risks. By integrating machine learning into traditional practices, it enhances efficiency and sustainability in terrace farming, tailoring care to each crop’s needs. Continuous monitoring allows real-time adjustment of spraying, responding to changing conditions. The system learns from extensive plant image datasets to recognize disease patterns, empowering preemptive action. This proactive approach minimizes crop losses, promotes sustainability, and improves yields in terrace farming.
Anagha Dileep, K Ramalakshmi, R Venkatesan, G Naveen Sundar, Golden Nancy, and S Shirly
IEEE
This study presents a detailed analysis and framework utilizing machine learning techniques to understand the occurrences of crimes against women in India. The key methodologies include data preprocessing, feature selection, and model selection whichwould enhance the accuracy of the models. Various supervised learning algorithms such as logistic regression, naive Bayes, stochastic gradient descent, K-nearest neighbor, decision tree, random forest, and extreme gradient booster have been used and compared to understand which algorithm would be the most capable. The findings and approach discussed in this study can be used to mitigate the risks, enhance victim support systems, and strengthen preventive measures to reduce crimes against women. This study would also contribute to combating gender-based violence and foster a safer and more inclusive environment for women in India.
Vaibhav Daniel, K Ramalakshmi, R Venkatesan, G Naveen Sundar, Golden Nancy, and S Shirly
IEEE
This research study offers a novel use of Internet of Things technology to enhance and modify the growth environment for various bonsai trees, suggesting ways to maximize these plants’ growth circumstances and provide a more flexible care schedule. The use of Internet of Things devices to automate and simplify the maintenance plan, ensuring that bonsai trees receive specialized care. These mechanical interventions are necessary because of the unique requirements of bonsai trees, which differ from regular indoor or outdoor plants. Certain factors that might significantly impact a bonsai’s development, including as mugginess, temperature, and light, must be carefully considered during their development. This study highlights the potential of IoT innovation in managing the complexities and outlines the unique problems involved in maintaining optimal conditions for bonsai trees. The proposed method aims to ease the process of cultivation for Bonsai enthusiasts by providing real-time observation and adjustments, promoting a more active and convenient means of developing these unique specimen of trees. The study’s focus on automation advances the field of intelligent and adaptable agricultural methods by positioning IoT as a driving force in agriculture and highlighting the useful advantages for Bonsai maintenance.
R. R., , , , , Sindhu. P., G. Naveen Sundar, and R. Venkatesan
ASPG Publishing LLC
Smart grids, pivotal in modern energy distribution, confront a mounting cybersecurity threat landscape due to their increased connectivity. This study introduces a novel hybrid deep learning approach designed for robust intrusion detection, addressing the imperative to fortify the security of these critical infrastructures. Renamed as Intrusion Detection for Smart Grid Using a Hybrid Deep Learning Approach, the study amalgamates Conv1D for spatial feature extraction, MaxPooling1D for dimensionality reduction, and GRU for modeling temporal dependencies. The research leverages the Edge-IIoTset Cyber Security Dataset, encompassing diverse layers of emerging technologies within smart grids and facilitating a nuanced understanding of intrusion patterns. Over 10 types of IoT devices and 14 attack categories contribute to the dataset's richness, enhancing the model's training and evaluation. The proposed hybrid model's architecture is detailed, emphasizing the synergy of convolutional and recurrent neural networks in addressing complex intrusion scenarios. This research not only contributes to the evolving field of intrusion detection in smart grids but also sets the stage for creating adaptive security systems. The convergence of a hybrid deep learning approach with a comprehensive cyber security dataset marks a significant stride towards fortifying smart grids against evolving cybersecurity threats. The proposed model achieves 98.20 percentage.
R Golden Nancy, R Venkatesan, G Naveen Sundar, and T Jemima Jebaseeli
Scalable Computing: Practice and Experience
The investigation describes an inventive use of digital twin technology and LSTM-based machine learning models for real-time patient lung disease monitoring and nutrition planning. The suggested application uses various patient healthcare data, treatment processes, dietary habits, and real-time sensor information to construct digital twins, which are virtual reproductions of specific patients. The LSTM model is trained on this large dataset to predict patient health improvements and dietary needs. For each patient’s digital twin, the program provides personalized treatment plans and nutritional advice, enabling proactive interventions and optimizing patient care. Using performance measures, the trained LSTM model achieves high scores for accuracy (92%), precision (89%), recall (93%), and F1 score (91%), proving its usefulness in generating credible health predictions. Patient feedback on the program shows that patients (98.8%) agree on the accuracy and importance of health feedback, as well as the convenience of access to health information (95.4%). The application’s response rate study reveals an average response rate of 85.87%, assuring prompt feedback. To secure patient information, the study emphasizes data privacy and security, adopting multilayered authentication and data encryption. The outcomes of this study demonstrate the application’s potential to revolutionize patient-centered healthcare by providing data-driven, personalized solutions to patients and healthcare professionals.
Rahul R, R. Venkatesan, and T. Jemima Jebaseeli
IEEE
The evolution of smart farming through the integration of Internet of Things (IoT) technology has ushered in a new era of precision agriculture, offering increased efficiency, sustainability, and productivity. However, this technological advancement also brings forth a critical concern: the security of the data collected and transmitted by IoT devices in agricultural settings. In response to this concern, this research presents a comprehensive security implementation tailored for IoT-based smart farming systems. At its core, the system focuses on two key aspects: data authentication and secure transmission. To achieve these objectives, the Ascon encryption algorithm, known for its lightweight design and robust security features has been proposed. The implementation utilizes Raspberry Pi devices, powered by the Adafruit CircuitPython library, to collect real-time sensor data from various agricultural sources. This data encompasses a wide range of vital parameters, including temperature, humidity, soil moisture, and livestock health. The Ascon algorithm is employed for device authentication, ensuring that only authorized devices gain access to the IoT network. The crux of the research lies in securing the data from its point of origin to its final destinations. The collected sensor data undergoes encryption using the ASCON algorithm before transmission. This encryption guarantees the confidentiality and integrity of the data, making it immune to interception or tampering during transit. AskSensors cloud platform acts as the secure repository for this encrypted data, while mobile integration provides users with real-time access to critical agricultural insights. This research represents a vital stride in addressing the pressing security challenges that accompany 10T-based smart farming. By combining the robust authentication capabilities of the Ascon algorithm with the secure data transmission to AskSensors, establish a trust framework essential for the widespread adoption of IoT technologies in agriculture. This implementation not only safeguards valuable agricultural data but also contributes to the long-term sustainability and success of modern farming practices.
M. Mythily, Beaulah David, R. Venkatesan, and Iwin Thanakumar Joseph
IOS Press
Emerging daily, new devices and software-driven advancements pose challenges in software development, including errors, bugs, and evolving requirements. This leads to delays in delivery. Ensuring software security within the Software Development Life Cycle (SDLC) is crucial. To address this, the research focuses on incorporating security aspects early in the SDLC through model transformation. Platform-independent models with security attributes like Integrity, Privacy, Security Audit, non-repudiation, and authentication are generated. A template-based source code generator is utilized to create the structure of the source model. The Secure Business Process Model (SBPM) encompasses Unified Modeling Language (UML) artifacts, such as analysis level classes and sequence diagrams, enriched with security attributes derived from the activity model. Security requirements are linked to elements extracted from the source model, and structural codes with security-enabled members are produced. Automation in software development is inevitable, though not complete, as it plays a vital role in addressing these challenges and improving the security of software applications.
Samson Arun Raj, Venkatesan Ramachandran, G. Naveen Sundar, and Subramaniam Nachiyappan
Akademia Baru Publishing
Smart devices, terminals, energy grids, houses, users, and companies united under one roof have recently grown into smart cities using various technical tools and ways to communicate, process, and exchange information. Urbanization plays a significant part in developing smart cities among the many application services that smart cities offer. Many users/consumers who live in rural areas commute daily to urban areas for jobs, school, and other purposes. There are not many people there, therefore building comprehensive smart city services would be a waste of time, money, and resources. However, there is a chance that urbanisation may create a small-scale industry for development and a beneficial energy grid for those living in rural areas. A completely functional energy grid is also challenging to build; one must comprehend and determine the parameters before manufacturing. To examine the incoming energy rate from rural areas connected to the primary smart city energy grid, this article presents an efficient Mobile Energy Distribution Substation (M-EDS). Every home's energy inflow rate is assessed, and resources are distributed following the queueing criteria the M-EDS has examined. Two categories—dynamic energy and fixed energy—are used to measure the rate of incoming energy. The suggested mobile energy distribution substation's performance is examined considering these two evaluations, and its benefits and drawbacks are highlighted.
Suja Alphonse, Ramachandran Venkatesan, and Theena Jemima Jebaseeli
MDPI
Ramachandran Venkatesan, Sundarsingh Shirly, Mariappan Selvarathi, and Theena Jemima Jebaseeli
MDPI
S. Shirly, R. Venkatesan, D. Jasmine David, and T. Jemima Jebaseeli
Frontier Scientific Publishing Pte Ltd
<p>Low back pain occurs because of the degeneration in Intervertebral Disc (IVD) namely: Disc Desiccation, Disc Bulge, and Disc Herniation, etc. To detect disc degeneration, a doctor often physically evaluates the Magnetic Resonance Imaging (MRI), which takes time and is dependent on the doctor’s expertise and training. Degeneration diagnosis that is automated can ease some of the doctor’s workload. On 378 IVDs for 63 patients, the proposed method is trained, tested, and assessed. According to the performance evaluation, the proposed Local Sub-Rhombus Binary Relationship (LS-RBRP) and Random Forrest (RF) classifier approach gives an overall accuracy of 90.2%. The proposed approach also produces a higher sensitivity, specificity, precision, and F-score of 80.8%, 90.3%, 90.4%, and 84.5%, respectively, when diagnosing the normal IVD, disc desiccation, and disc bulge in the lumbar MRI.</p>
Antony Taurshia, , , , Jaspher Willsie Kathrine, and Venkatesan Venkatesan
American Scientific Publishing Group
Smart applications came into existence with technological advancements like Software Defined Networks (SDN), Cloud computing, Network Function Virtualization (NFV), and the Internet of Things (IoT). Internet of Vehicles (IoV) is a highly dynamic application with limited tolerance to latency since a small delay can lead to drastic disasters. For efficient network and vehicle management clusters are formed in IoV. Secure key management is unavoidable to secure communication between the vehicles in the cluster. In this article, a sustainable cluster key management approach is proposed to handle the dynamic and latency-sensitive nature of IoV. Security analysis proves that the proposed approach holds secrecy in group key management. The proposed approach reduces the communication complexity to a single broadcast for re-keying. The analysis proves that the computation and storage complexity is also minimal, hence proving that the scheme is sustainable with limited resource usage and efficient for usage in latency-sensitive IoV environments.
C. S. Manigandaa, , , , , , V. D. Ambeth Kumar, G. Ragunath, R. Venkatesan, and N. Senthil Kumar
American Scientific Publishing Group
Medical diagnosis and prognosis are challenging tasks due to subjectivity and inherent uncertainty in medical images. Inconsistencies in expert opinions can result in incorrect diagnoses. Neutrosophic theory, a mathematical framework that deals with imprecise or incomplete data, has shown promise in addressing the challenges posed by medical image processing. A neutrosophic theory approach is explored in this paper for de-noising and segmenting medical images. Neutrosophic theory has been utilized to represent the different degrees of truth in each piece of information, resulting in better performance in de-noising and segmentation tasks. Neutosophic theory presents a promising avenue for future investigation in medical image processing as shown in this study.
S. .., , , , , V. D. Ambeth .., R. Venkatesan, and S. Malathi
American Scientific Publishing Group
In computer vision, multi-label classification (MLC) is especially important for medical picture analysis. We use MLC to classify diverse stages of diabetic retinopathy (DR) using colour fundus pictures of varying brightness and contrast. As a result, ophthalmologists can now identify the early warning symptoms of DR and the varying stages of DR, allowing them to begin therapy sooner and prevent further difficulties. Using the outlier-based shallow regularization fuzzy clustering approach (OSR-FCA), for classification we present a deep learning method in this paper's picture segmentation task. The fundamental feature of the proposed system is the ability to identify and analyse different degenerative changes in the retina that occur alongside the progression of DR without requiring the patient to undergo costly diagnostic procedures like dye injections. Photographs are first resized, converted to grayscale, cleaned of noise, and the contrast increased by the use of histogram equalization adopting the CLAHE method. The clipping limit of CLAHE is optimized by the help of the rat optimization algorithm, which is applied throughout the histogram process. In addition, a Gaussian metric regularization to the objective function in OSR-FCA is a great way to enhance clustering approaches that use fuzzy membership with sparseness which is based on neutrosophic set. This research proposes a new approach called Relevance Mapping on Multi-Class Label (RMMCL) for locating and viewing regions of interest (ROI) inside a segmented picture. These representations give better explanations for the predictions of the DL model founded on a convolutional neural network-(CNN). The validation of two ML datasets showed the projected model outperformed the existing models by achieving an average correctness of 97.27 percent over five stages of the IDRID dataset.
M. Sangeetha, R.Manjula Devi, Hemalatha Gunasekaran, R. Venkatesan, K. Ramalakshmi, and P. Murugesan
IEEE
The incorporation of deep learning and image processing techniques has rendered the early identification of lung cancer critical and simple. There are an astounding five million deaths annually caused by lung cancer which makes it one of the leading killers of both sexes worldwide. In the case of lung illnesses, the data gleaned from a computed tomography (CT) scan might be quite helpful. The primary aims of this research are to (1) identify cancerous lung nodules in the input lung image and (2) rank the severity of the cancer present in each nodule. In order to detect lung cancer utilizing non-small cell lung cancer imaging, histological pictures of the lungs as well as CT scan data are acquired. The adenocarcinoma images, the big cell carcinoma images, the squamous cell carcinoma images, and the normal lung tissue images are the four subsets that are contained inside these two primary types of data. The quality of the obtained lung image can be improved by inspecting each individual pixel using the multilayer brightness-preserving technique, which also helps to remove unwanted background noise. Noise-reduced lung CT scans and lung cancer histopathological scans are used to separate the damaged area using an improved deep neural network with layer-based network segmentation