venkatesan ramachandran

Associate Professor, Department of Computer Science and Engineering
Karunya Institute of Technology and Sciences


Scopus Publications

Scopus Publications

  • IoT based automatic temperature monitoring and adjustment system for the organic farm
    R. Venkatesan, T. Jemima Jebaseeli, K. Ramalakshmi, and P. B. Hemanthkumar

    AIP Publishing

    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.

  • Smart Farming with Improved Security using Ascon Encryption and Authentication
    Rahul R, R. Venkatesan, and T. Jemima Jebaseeli

    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.

  • An Internet of Medical Things-Based Mental Disorder Prediction System Using EEG Sensor and Big Data Mining
    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.

  • Model transformation and code generation using a secure business process model
    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.

  • A Queueing Model-Based Experimental Analysis of Mobile-Energy Distribution Stations (M-Eds) for Smart City Urbanization
    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.

  • Opinion on Student’s Educational Performance and Sleeping Patterns Using Data Analytics Technique

  • A Methodical Review of Iridology-Based Computer-Aided Organ Status Assessment Techniques
    Suja Alphonse, Ramachandran Venkatesan, and Theena Jemima Jebaseeli


  • Human Emotion Detection Using DeepFace and Artificial Intelligence †
    Ramachandran Venkatesan, Sundarsingh Shirly, Mariappan Selvarathi, and Theena Jemima Jebaseeli


  • Pest Management System for Food Crops using Deep Learning Techniques

  • Automated spinal MRI-based diagnostics of disc bulge and desiccating using LS-RBRP with RF
    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>

  • Software Defined Network aided cluster key management system for secure fusion multicast communication in Internet of Vehicles
    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.

  • De-Noising and Segmentation of Medical Images using Neutrophilic Sets
    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.

  • Relevance Mapping based CNN model with OSR-FCA Technique for Multi-label DR Classification
    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.

  • Deep Residual Learning for Lung Cancer Nodules Detection and Classification
    M. Sangeetha, R.Manjula Devi, Hemalatha Gunasekaran, R. Venkatesan, K. Ramalakshmi, and P. Murugesan

    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

  • Plant Classification based on Grey Wolf Optimizer based Support Vector Machine (GOS) Algorithm
    P. Keerthika, R.Manjula Devi, S.J. Suji Prasad, R. Venkatesan, Hemalatha Gunasekaran, and K. Sudha

    Leaves are the primary identifying feature of trees and other plants. Many of these plants are used in the pharmaceutical industry as industrial crops. Growing automation in industries including commerce and medicine has made accurate leaf identification crucial. Leaves are typically classified according to morphological or genetic characteristics. As a result of their numerous physical differences, however, it is becoming increasingly difficult to categorize the diverse leaf cultivars that exist. Several evolutionary shifts over the past several decades have resulted in an increase in the number of variants of a certain leaf type. To manually sift and identify these leaves is a laborious process. A novel hybrid GOS algorithm is proposed in this study for detecting leaves based on their shape, color, and texture. Three types of leaves (apple, cucumber, and mango) are used as examples, and features for each are extracted using Image Processing techniques, before being optimized with the Grey Wolf Optimizer and finally classified with the SVM (Support Vector Machine) classifier algorithm. Experimental results show that the proposed GOS work improves upon the SVM classifier, with a classification accuracy of 96.83 percent.

  • An efficient and secure data sharing scheme for cloud data using hash based quadraplet wavelet permuted cryptography approach
    Selvam Lakshmanan, Braveen Manimozhi, and Venkatesan Ramachandran

    Ensuring the reliable and secure data transmission in cloud systems is very essential and demanding task in the recent decades. For that purpose, various security frameworks have been deployed in the existing works, which are mainly focusing the improving the privacy and confidentiality of cloud data against the unauthenticated users. Yet, it facing the major problems of inefficient accessing, increased time consumption, computational complexity, storage complexity, and memory utilization rate. Hence, this research work intends to develop an advanced and efficient cryptography model, named as, hash based quadraplet wavelet permuted cryptography (HQWPC) for the secured cloud data storage and retrieval operations. Here, the bilinear mapping and group hash function generation processes are performed to generate the keys used for cryptographic operations. Also, the zig‐zag scanning, wavelet coefficients extraction, and permutation processes are accomplished for data encryption. Consequently, the inverse of these operations is performed while decrypting the data. In addition to that, an integrated signature control policy authentication mechanism is employed for validating the authenticity of the cloud data users. This kind of signature verification process could efficiently increase the security level of cloud data. For validating the performance of the proposed security framework, various evaluation metrics have been utilized during analysis. Then, the obtained results are compared with the recent state‐of‐the‐art models for proving the efficiency of the proposed technique over the other techniques.

  • Post-quantum confidential transaction protocols
    R. Manjula Devi, P. Keerthika, P. Suresh, R. Venkatesan, M. Sangeetha, C. Sagana, and K. Devendran


  • Unsupervised Lumbar IVD Localization and Segmentation using GFMM and Boundary Refined Region Growing Techniques
    Shirly S, Golden Nancy R, Venkatesan R, Jemima Jebaseeli T, and Ramalakshmi K

    Seventh Sense Research Group Journals

  • Traffic Aware Channel Assignment for Dynamic Wireless Mesh Networks

  • Weight Aware Channel Assignment with Node Stability in Wireless Mesh Networks

  • A Mathematical Queuing Model Analysis Using Secure Data Authentication Framework for Modern Healthcare Applications
    A. Samson Arun Raj, R. Venkatesan, S. Malathi, V. D. Ambeth Kumar, E. Thenmozhi, Anbarasu Dhandapani, M. Ashok Kumar, and B. Chitra

    Hindawi Limited
    Healthcare application is one of the most promising developments to provide on-time demand services to the end users, vehicles, and other Road Side Units (RSUs) in the urban environment. In recent years, several application interfaces have been developed to connect, communicate, and share the required services from one source to another. However, the urban environment holds a complex entity of both homogenous and heterogeneous devices to which the communication/sensing range between the devices leads to connectivity breakage, lack of needed service in time, and other environmental constraints. Also, security plays a vital role in allowing everyone in the urban area to access/request services according to their needs. Again, this leads to a massive breakthrough in providing reliable service to authentic users or a catastrophic failure of service denial involving unauthorized user access. This paper proposes a novel topological architecture, Secure Authentication Relay-based Urban Network (S-ARUN), designed for healthcare and other smart city applications for registered transportation stakeholders. The registered stakeholders hold a built-in data security framework with three subsystems connected to the S-ARUN topology: (1) authentication subsystem: the stakeholder must identify themselves to the source responder as part of the authentication subsystem before transmitting the actual data service request; (2) connectivity subsystem: to periodically check the connection state of stakeholders as they travel along with the road pattern; and (3) service subsystem: each source responder will keep a separate queue for collecting data service requests, processing them quickly, and sending the results to the appropriate stakeholder. The Kerberos authentication method is used in working with S-ARUN’s model to connect the stakeholders securely and legitimately. The performance of the proposed S-ARUN is assessed, and the performance metric toward key generation and other data security-related metrics is tested with existing schemes.

  • Introduction to ARM processors its types and Overview to Cortex M series with deep explanation of each of the processors in this Family
    Hemanthkumar P B, Shreekar Reddy Anireddy, Josh F T, and Venkatesan R

    ARM Cortex M series or family consists of 10 processors till date. In this paper, first we are going to discuss about ARM processors, how it can be classified, what these processors are meant for and how to select your right processor, followed by a basic idea about each of the processors in the M series. Along with the basic idea, we are going to share features of each of the processors, the available configuration options, works that were published on each of the processors with what was their idea on that particular processor and with the flow you will notice there will be some comparisons for the features and also configuration options available between the processors, at last there is a table that briefly gives the available configuration options with its features on each of the processor in this family.

  • A mathematical model for cost budget optimization in the early stage of house construction budget analysis
    S. Malathi, Ankit Kumar, R. Venkatesan, Naveen Sundar, A. S. Athigiri Arulalan, V. D. Ambeth Kumar, R. Priya, Shilpa Sharma, and Linesh Raja

    Informa UK Limited
    Abstract House building is a desire for many individuals these days. If we create our own structure via our own efforts, we may save money to a certain amount, but this is not feasible for everyone, particularly for families with two employees. Because the employee’s family cannot devote their entire attention to all areas of the building as and when necessary, they naturally present material contracts and negotiate with the builders. The length and cost of a prefabricated construction project are converted into quantifiable cost data during the early stages of the project using an earned value analysis technique, which is then used to determine the project’s implementation cost. A mathematical model of the pre-cost budget for prefabricated buildings is built based on the project parameters. By comparing the improved neural network algorithm’s cost budget performance in the early stages of an assembly construction project to that of the original mathematical model, it was determined that the improved neural network algorithm’s cost budget performance was superior, and the cost budget performance was improved. Methodology: first plan the preparation of the house construction, then determine whether the location is urban or rural, then calculate the square footage and floor division for their convenience, as well as check quantity take off, evaluate the primary materials for house construction, and paint the entire house, as well as fix rooms doors, windows, and window grilles. Following the selection of floor laying stones, the budget will be computed. Result and conclusion: I concluded that home building estimation is beneficial for newly constructed individuals, and then this project thoroughly taught how to calculate the house construction budget and how to implement it within our budget.

  • Prediction of COVID'19 through multiple organ analysis using iot devices and machine learning techniques
    Jemima Jebaseeli T, Jasmine David D, and Venkatesan R

    Seventh Sense Research Group Journals
    COVID-19 is a recently found coronavirus that tends to cause serious infections. It falls under the stage of mild to moderate does not require hospitalization. If the patient's immune system is strong, they can recover on their own with proper nutrition and treatment. This disease has an impact on the human hormone system. A computer-aided diagnosis is needed to predict COVID-19. The blood volume must be determined in order to predict the disease's severity level. The blood vessels or capillaries provide oxygen to the Red Blood Cells (RBCs), and the RBCs, in turn, provide oxygen to the internal organs. The wall and lining of the alveolus and capillaries are damaged and thickened by COVID-19. The oxygen transfer by RBCs becomes extremely difficult as the wall thickens. The body has trouble breathing as a result of this condition. This is the most common cause of respiratory problems in COVID-19 patients. Respiratory issues cause problems on the retina, triggering haemorrhages. It also has an impact on the human digestive tract and taste buds. This has been confirmed in medical studies. As a result, of diagnosis, the proposed IoT-based method needs microscopic blood smear images, CT images of the digestive tract, X-ray images of the chest, and fundus images of the eye. Hence, machine learning techniques have been used to process these images and yield more accurate results in diagnosis. © 2021 Seventh Sense Research Group®