Dr.P.Kalpana Devi

@veltech.edu.in

Associate Professor and Electronics and Communication Engineering
Veltech rangarajan Dr. sagunthala R & D institute of science and technology

Dr.P.Kalpana Devi


            Download Compact PDF  
https://researchid.co/kalpanand77
36

Scopus Publications

Scopus Publications

  • Octa multibit upset correction in SRAM memories using interleaved MPC code
    T. V. Sindhu, P. Kalpana Devi
    International Journal of Information Technology Singapore, 2025
  • Dense wavelength division multiplexing scheme based on effective distributed inline light fiber Raman amplifier configuration
    Govindaraj Ramkumar, Perumal Kalpana Devi, Vinodhini Shankar, Sivaraman Pandarinathan, Rajinikanth Eshwar, Binu Sukumar, Omar Karem Omran
    Journal of Optical Communications, 2025
    This paper demonstrated the dense wavelength division multiplexing scheme based on effective distributed inline light fiber Raman amplifier configuration. Various forward/backward and bidirectional pumping power configurations are studied versus fiber reach. Output light signal power is demonstrated against fiber reach without Raman amplification technique. Output light signal power in the forward Raman amplification scheme is clarified with pumping power of both 500 mW and 700 mW in various fiber channel configurations. As well as output light signal power in the backward Raman amplification scheme with pumping power of both 500 mW and 700 mW in various fiber channel configurations. Amplification Raman gain parameter coefficient is demonstrated with various values of pumping power pump based on various fiber channel configurations. Backward amplification net parameter gain is studied for different single mode/true wave/freelight fibers channel configuration at different both pumping power values and fiber reach. As well as the forward amplification net parameter gain is clarified for different single mode/true wave/freelight fibers channel configuration at different both pumping power values and fiber reach.
  • A deep learning approach for brain tumour classification and detection in MRI images using YOLOv7
    Ramya Nimmagadda, P. Kalpana Devi
    Frontiers in Oncology, 2025
    The medical imaging field has grown tremendously due to the latest digital imaging and artificial intelligence (AI) advancements. These advancements have improved tumour classification accuracy, time, cost efficiency, etc. Radiologists utilize an MRI scan due to its exceptional capacity to identify even the most minor alterations in brain activity. This research uses YOLOv7, a Deep Learning (DL) model, to classify and detect brain tumours and to conduct a detailed analysis of the frequently used structures for tumour identification. The study uses a brain MRI dataset from Roboflow with 2870 labelled pictures divided into four types of tumours. Our brain tumour dataset has four distinct classes: pituitary, gliomas, meningiomas, and no tumours. This preprocessed sample was used to assess the performance of deep learning models on identifying and classifying brain tumours. Throughout the preprocessing stage, aspect ratio normalization and resizing algorithms are applied to improve tumour localization for bounding box-based detection. YOLOv7 performs admirably, with a recall score of 0.813 and a box detection accuracy of 0.837. Remarkably, the mAP value for the 0.5 IoU threshold is 0.879. During box identification within the extended IoU spectrum of 0.5 for a to 0.95, the mAP value was 0.442.
  • FPGA Based Enhanced Spectrum Sensing Using Matched Filter Detection in Cognitive Radio Systems
    Kalpana Devi P, Priya P A, J Josphine Pon Gloria
    Conference Proceedings 4th IEEE International Conference on Technology Engineering Management for Societal Impact Using Marketing Enterpreneurship and Talent Temsmet 2025, 2025
    Cognitive radio (CR) is a promising technology that enables unlicensed secondary users (SUs) to make effective use of idle frequency bands licensed to primary users (PUs). Spectrum sensing is a crucial component in CR systems, enabling the detection of the availability of PUs and preventing interference. The matched filter (MF) is a popular spectrum sensing technique in CR systems because of its optimal detection performance in additive noise. The process of the MF technique is to correlate the received signal with the complex conjugate of a known reference signal, which ensures the signal-to-noise ratio (SNR) at the output is maximized if the received signal is the same as the reference signal. This paper provides a comprehensive analysis of the MF technique, such as its mathematical model, merits, and demerits. The performance of the MF technique is also compared with other spectrum sensing approaches, and its implementation issues in VHDL code in an FPGA are outlined. The simulation shows that the MF technique provides better detection performance, particularly for the detection of weak or intermittent signals, which makes the technique a good option for CR systems. Accurate knowledge of the reference signal, timing and frequency offset compensation, and computational complexity, however, should be carefully evaluated in the implementation of the MF technique in an FPGA-based CR system. Further research can also be explored to improve the performance of the MF technique and remedy its limitations in real-world CR implementations.
  • Machine Learning Based Smart Aquaponics System with Integrated Fish and Plant Monitoring
    S. Sivasankari, S.G. Rahul, Logeswari Panneerselvam, Talari Sofiya Rheema, Chavala Jahnavi, P. Kalpana Devi
    Proceedings International Conference on Next Generation Communication and Information Processing Incip 2025, 2025
    This study intends to create an intelligent aquaponics system that uses Internet of Things technology to change farming methods. Combining hydroponics and aquaculture, aquaponics provides a sustainable response to issues including degraded soil, scarce water supplies, and inefficient use of resources in conventional farming. In aquaponics, plants and fish mutually benefit without soil, using inert media like pebbles or lava rocks. The developed system enables real-time monitoring and control of environmental parameters such as Total Dissolved Solids, pH, Temperature, and dissolved oxygen. Data from these sensors are processed using machine learning algorithms such as Isolation Forest for anomaly detection. This algorithm identifies deviations in water quality parameters, such as unexpected TDS or pH spikes, signalling potential issues that could disrupt the ecosystem. Early detection allows immediate corrective actions such as adjusting water flow or activating filtration systems to maintain optimal conditions for fish health and plant growth. Leveraging Linear Regression models, the system forecasts soil moisture and temperature based on historical data trends. These predictions facilitate preemptive adjustments in irrigation schedules and nutrient supplementation, ensuring optimal growing conditions for robust plant development. This automation enhances operational efficiency, reducing the need for human intervention and ensuring stable ecosystem conditions.
  • A Machine Learning-Based Smart Aquaponics Framework for Sustainable Basil Cultivation
    Rahul S G, Avinaash Arjun V, Kalpana Devi P, T M Amirthalakshmi, Logeswari Panneerselvam, Talari Sofiya Rheema
    5th IEEE International Conference on Innovations in Power and Advanced Computing Technologies I Pact 2025, 2025
    This paper presents a smart aquaponics system for cultivating Ocimum Basilicum (basil), integrating the Internet of Things (IoT), machine learning and automation to enhance sustainable agriculture. The system continuously monitors key environmental parameters; pH, Total Dissolved Solids (TDS), temperature, water level, and soil moisture using an ESP32-based sensor network. An Isolation Forest algorithm, trained on historical sensor data, detects anomalies with 96.2% accuracy, enabling proactive intervention. A Proportional Integral and Derivative (PID) control loop automates water circulation and fish feeding based on real-time feedback. Visual crop monitoring is enabled through an ESP32-CAM integrated with a Telegram bot, while a Streamlit dashboard offers live data visualization. Real-time SMS alerts via Twilio inform users of critical changes, ensuring system reliability. Experimental deployment demonstrated reduced manual intervention, optimal resource usage, and increased system responsiveness with an average alert latency of 2.1 seconds. The proposed system supports scalable, efficient, and resilient food production systems.
  • Sensor Data Modelling for Anomaly Detection in Aquatic Environments
    Rahul S G, Kalpana Devi P, N Kirn Kumar, Priscilla Dinkar Moyya, T M Amirthalakshmi, Avinaash Arjun V
    Proceedings of International Conference on Modern Sustainable Systems Cmss 2025, 2025
    Monitoring essential water parameters like pH, pond temperature, and dissolved oxygen is crucial for ensuring the production of high-quality aquariums. Machine learning techniques are under development to predict the periodic fluctuations of these factors, aiding fish cultivators in data-driven decision-making processes. Advanced real-time data collection, storage, and remote monitoring technologies facilitate the development of highly precise machine learning models. However, fish growers sometimes do not have access to sophisticated monitoring equipment and must instead use handheld tools for manual assessments. The analysis of data is limited in quantity and frequency due to the constraints of manual assessment methods. This study investigates the application of machine learning models like artificial neural networks, random forests, and multivariate linear regression to analyze water quality metrics in aquaculture systems with limited data. The study presents a modeling approach for estimating unobserved variables based on observed measurements and making predictions with limited training data in two scenarios. Our findings demonstrate accurate prediction of dissolved oxygen, pond temperature, pH, ammonia, and ammonium using random forest algorithms, even with water quality data measured only twice a day. Moreover, integrating these predictive models into a mobile device-accessible information system enables their implementation on smartphones, ensuring feasibility and cost-effectiveness.
  • Automated Aquaponics System with AI-Based Plant Health Monitoring for Ocimum Basilicum
    Rahul S G, Avinaash Arjun V, Kalpana Devi P, T M Amirthalakshmi, Logeswari Panneerselvam, Talari Sofiya Rheema
    2025 International Conference on Next Generation Computing Systems Intelligent System for Sustainable Development Icngcs 2025 Conference Proceedings, 2025
    This study intends to improve sustainable agricultural practices by creating a cutting-edge smart aquaponics system that integrates real-time monitoring, Artificial Intelligence (AI) and the Internet of Things (IoT). The system offers real-time monitoring of vital environmental parameters, such as Total Dissolved Solids (TDS), pH, temperature, water level, water contact, air gap and soil moisture, using an ESP32-CAM module and multiple Internet of Things sensors. This information is gathered by the Micro Python-based ESP32 microcontroller and transmitted to the ThingsBoard Cloud through secure HTTP requests that use JWT authentication. Early identification of possible risks using machine learning algorithms like Isolation Forest, which identify anomalies in variables like pH, TDS and moisture content, enables proactive fertilizer and irrigation management adjustments. Additionally, a Telegram bot was developed to incorporate an ESP32-CAM module for remote visual monitoring in real time. This allows users to receive system updates and real-time photos of plant growth directly on their mobile devices. Fish feeding, water flow and aeration are all automated with the help of the microcontroller's built-in PID control algorithm, guaranteeing ideal environmental conditions with little assistance from humans. Real-time data retrieved from the ThingsBoard dashboard is interactively visualized using a web-based demo application created with Streamlit. Based on Twilio, it offers automated SMS warnings for critical situations, live charting and anomaly detection. This smart aquaponics system greatly improves efficiency, scalability and sustainability by combining IoT, AI-driven anomaly detection, camera monitoring and automated control.
  • High bandwidth profile based on fiber bragg grating dispersion compensation systems for high bit rate optical communications with long distance links
    Perumal Kalpana Devi, Thankaraj Helan Vidhya, Madhubalan Selvaraju, Bhuvaneswari Balasubramanian, Suvitha Sundar, Jayanthi Anvar, Govindaraj Ramkumar, Shaik Hasane Ahammad, Ahmed Nabih Zaki Rashed, A. H. M. Iftekharul Ferdous, Md. Amzad Hossain
    Journal of Optics India, 2024
  • Advanced Terahertz Waveguide Biosensing: Blood Component Detection with a Pentagonal Cladding and Decagonal Core Fiber Design
    A. H. M. Iftekharul Ferdous, Sakhawat Hossain, Perumal Kalpana Devi, Aranganathan Anandan, Benjir Newaz Sathi, Khalid Sifulla Noor, Md.Sabbir Hossain, Kayab Khandakar, Ahmed Nabih Zaki Rashed, Mahmoud M. A. Eid
    Brazilian Journal of Physics, 2024
  • Fabrication Model Design and Analysis of Flexible Polarization Surface Polariton Resonance with a Dual-Wing Antenna Structure Platform for Diverse Multiband Characteristics in the Measurement Environment
    R. Thandaiah Prabu, M. Benisha, P. Kalpana Devi, R. Harikrishnan, T. Gomathi, Kandrapu Rajesh Kumar, T. D. Subha, Ahmed Nabih Zaki Rashed, Shaik Hasane Ahammad, M. Suman, Md. Amzad Hossain
    Plasmonics, 2024
  • Unlocking insights of oil derivatives with terahertz spectrum analysis: the hybrid refractive index rectangular core photonic crystal fiber perspective sensing
    A. H. M. Iftekharul Ferdous, Sheikh Zannat E. Noor, P. Kalpana Devi, K. R. Kavitha, G. Anitha, T. Jayakumar, Khalid Sifulla Noor, Rosni Sayed, Md. Ariful Islam, Ahmed Nabih Zaki Rashed, Shaik Hasane Ahammad
    Journal of Optics India, 2024
  • OPTIMIZED DEEP LEARNING FRAMEWORK FOR BRAIN TUMOR DETECTION AND CLASSIFICATION USING HYBRID VISUAL GEOMETRY GROUP-16 WITH REDUCED WEIGHTS VIA BUTTERFLY OPTIMIZATION
    Journal of Theoretical and Applied Information Technology, 2024
  • High efficiency coupling fibers with different types of photo detectors for the management of noise multiplication and efficient bandwidth
    Ramachandran Thandaiah Prabu, Chandran Ramesh Kumar, Perumal Kalpana Devi, Soman Shibu, Ata Kishore Kumar, Benisha Maria Xavier, Fawzya Kamel Mahmmoud
    Journal of Optical Communications, 2024
  • Efficient employment of Yb doped multi-mode fiber amplifiers based pumped laser with advanced light sources in high speed modulated optical communication systems
    Mani Tamilselvi, Ata Kishore Kumar, Dhanalakshmi Ganapathy, Perumal Kalpana Devi, Thandaiah Prabu Ramachandran, Ahmed Ali Zahran, Vasimalla Yesudasu
    Journal of Optical Communications, 2024
  • High speed broadband light spatial laser system with hybrid linear/parabolic/measured indexed multimode optical fibers performance signature
    Ramachandran Thandaiah Prabu, Suvitha Sundar, Merlin Livingston Louis Mary, Arunya Revathi Arumugam, Perumal Kalpana Devi, Thankamony Devakhi Subha, Karem Tarek Anwer
    Journal of Optical Communications, 2024
  • BUFIT: FINE-GRAINED DYNAMIC BURST FAULT INJECTION TOOL FOR EMBEDDED FIELD PROGRAMMABLE GATE ARRAY TESTING
    SINDHU THAZHATHETHIL VELAYAUDHAN, KALPANA DEVI
    Revue Roumaine Des Sciences Techniques Serie Electrotechnique Et Energetique, 2024
  • A Review of Burst Error-Correction Codes with Parallel Decoding
    T. V. Sindhu, P. Kalpana Devi
    Lecture Notes in Electrical Engineering, 2024
  • Robust Learning Principle Design to Detect Diabetic Retinopathy Disease in Early Stages with Skilled Feature Extraction Policy
    D. Sasirekha, Devi P. Kalpana, W. Nancy, K. Valarmathi, G. Anitha
    Deep Learning in Biomedical Signal and Medical Imaging, 2024
  • IOT-Smart Monitoring of Pet Housing
    Yi-Chih Tung, Yi-Hung Lien, Li-Wei Liu, M. David Honesty B, P. Kalpana Devi
    2024 International Conference on Wireless Communications Signal Processing and Networking Wispnet 2024, 2024
  • GDVM: A Deep Learning Assisted Fetal Health Prediction System Using Gradient Distance Vector Model
    G. Ramkumar, M Swarna, Madhini M, P Kalpana Devi, Pallavi Giri, Ala'a Al Sherideh
    2024 IEEE 2nd International Conference on Emerging Trends in Engineering and Medical Sciences Icetems 2024, 2024
  • Smart IoT-based water treatment with a Supervisory Control and Data Acquisition (SCADA) system process
    Dwarakanath B., Kalpana Devi P., Ranjith Kumar A, Ahmed Sayed M. Metwally, Ghulam Abbas Ashraf, Bheema Lingaiah Thamineni
    Water Reuse, 2023
  • Automatic Trash Monitoring System
    Kalpana Devi P, Mukesh Narayana Gadde, Prativa Oli, Meghana Somineni
    Proceedings of the 8th International Conference on Communication and Electronics Systems Icces 2023, 2023
  • Automatic Modulation Classification using Software Defined Radio System
    P Kalapana Devi, N Nitish Kumar, M Sai Varun, S Sai Ganesh
    3rd International Conference on Innovative Mechanisms for Industry Applications Icimia 2023 Proceedings, 2023
  • Design of Intelligent Home Security Handling System based on Face Recognition and IoT Assisted Technology
    P. Nirmala, Lakshmi S, J. Megala, P.Kalpana Devi, Venkatramanan C B, F. Antony Xavier Bronson
    2023 IEEE International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2023, 2023
  • Design and Development of the Efficient RF Energy Harvesting System
    P. Kalpana Devi, T. Yuvaraj
    Lecture Notes in Networks and Systems, 2022
  • An OAuth-Based Authentication System for IoT Networks Using LabVIEW
    P. Kalpana Devi, M. Manasa, S. Naga Chandra Prakash, B. Vittal Teja
    Lecture Notes on Data Engineering and Communications Technologies, 2022
  • An Secure and Low Energy Consumption based Intelligent Street Light Managing System using LoRa Network
    P. Kalpana Devi, D. Arulanantham, C. Kalaivanan, N. Gomathi, J.R. Arunkumar, G. Ramkumar
    6th International Conference on Electronics Communication and Aerospace Technology Iceca 2022 Proceedings, 2022
  • Experimental Analysis Using USRP for Novel Wavelet-Based Spectrum Sensing for 2.2 GHZ Band Communication Using LabVIEW
    Kalpana Devi Perumal, E. D. Kanmani Ruby, M. Dhivya, G. Aloy Anuja Mary, V. Kavitha, Umamahesawari Kandasamy
    Journal of Nanomaterials, 2022
  • Design of reconfigurable integrated patch antenna in ISM band for IoT applications
    P.Kalpana Devi, M. Sujatha, J.Arun Prasath
    2020 7th International Conference on Smart Structures and Systems Icsss 2020, 2020
  • Design of frequency reconfigurable antenna for SDR application
    P.Kalapna Devi, Aparna Shekar, Abhishek, Tarun
    2020 7th International Conference on Smart Structures and Systems Icsss 2020, 2020
  • Linguistic Effects Based Novel Filter for Hearing Aid to Deliver Natural Sound and Speech Clarity in Universal Environment
    Perumal Kalpana Devi, Raghuvel Subramanian Bhuvaneswaran
    Wireless Personal Communications, 2017
  • A novel frequency range reconfigurable filter for hearing aid to deliver natural sound and speech clarity in universal environment
    Perumal Kalpana Devi, Raghuvel Subramaniyam Bhuvaneswaran
    Journal of Computational and Theoretical Nanoscience, 2016
  • Improved non uniform transmultiplexers for channelization
    P. Kalpana Devi, R. S. Bhuvaneswaran
    Indian Journal of Science and Technology, 2015
  • FPGA implementation of coefficient decimated polyphase filter bank structure for multistandard communication receiver
    Journal of Theoretical and Applied Information Technology, 2014
  • Flexible reconfigurable filter architecture for SDR receiver
    P. Kalpana Devi, R. S. Bhuvaneswaran
    2013 IEEE 11th Malaysia International Conference on Communications Micc 2013, 2013