Project Title : Cupture

Sanctioned Year : 2025

Amount : 3,32,500

Funding/Sanction agency : Rajiv Gandhi Entrepreneurship Program (RGEP)

Status : Ongoing

Principal Investigators : Dr. Mohana Lakshmi J

Project Title : Startup Tumkuru

Sanctioned Year : 2025

Amount : 3,32,500

Funding/Sanction agency : Rajiv Gandhi Entrepreneurship Program (RGEP)

Status : Ongoing

Principal Investigators : Dr. Mohana Lakshmi J

Project Title : Smart area nut plucking machine with remote control and sensor based ripe nut detection

Sanctioned Year : 2024

Amount : 2,00,000

Funding/Sanction agency : New Age Innovation Network 2.0 Department of Electronics, IT, BT, S&T – Government of Karnataka

Status : Ongoing

Principal Investigators : Dr. Mohana Lakshmi J

Project Title : Scootlite

Sanctioned Year : 2024

Amount : 1,00,000

Funding/Sanction agency : New Age Innovation Network 2.0 Department of Electronics, IT, BT, S&T – Government of Karnataka

Status : Ongoing

Principal Investigators : Dr. Mohana Lakshmi J

Project Title : Multi-functional Borewell Rescue Robot for Enhanced Child Safety

Sanctioned Year : 2024

Amount : 3,00,000

Funding/Sanction agency : New Age Innovation Network 2.0 Department of Electronics, IT, BT, S&T – Government of Karnataka

Status : Ongoing

Principal Investigators : Mr. Kiran Kumar Naik

Student Name : B. Pooja

Title of the Paper : Design of a Battery Charge Controller Through MPPT Based Solar Photovoltaic System

Research Description : IEEE Fourth International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT), PES College of Engineering, Mandya ISBN: 978-1-6654-5635-7

Faculty Coordinator : S. Rajanna, N. L. Varaprasad, M. Ramesh, G.R. Sowmya, S.R.

Reference Link: https://ieeexplore.ieee.org/document/10060581

Student Name : R.K. Dhavala

Title of the Paper : Case study on demand side management-based cost optimized battery integrated hybrid renewable energy system for remote rural electrification

Research Description : Energy Storage, Wiley, September, 2022

Faculty Coordinator : H.N. Suresh, S. Rajanna, M. Ramesh

Reference Link: https://onlinelibrary.wiley.com/doi/abs/10.1002/est2.410

Student Name : R.K. Dhavala

Title of the Paper : Effects of different batteries and dispatch strategies on performance of standalone PV/WT/DG/battery system: A case study

Research Description : Energy Storage, Wiley, November, 2021, pp 1-19, Vol. 4, Issue 2, DOI: https://doi.org/10.1002/est2.306 ISSN: 2578-4862

Faculty Coordinator : H.N. Suresh, S. Rajanna, M. Ramesh

Reference Link: https://onlinelibrary.wiley.com/doi/abs/10.1002/est2.306

Student Name : N. Sushma

Title of the Paper : Experimental investigation on wireless integrated smart system for energy and water resource management in Indian smart cities

Research Description : In the realm of India's smart cities, precise meter readings are essential for effectively managing domestic energy and water systems. Nevertheless, meter reading employing conventional techniques prove to be both costly and time-consuming, especially considering the vast user base and deficit of everyday consumption analysis. To cope with this challenge, the proposed solution introduces a novel unified wireless smart metering system for measuring energy and water usage. This prototype harnesses the smart, advanced metering technology to manage energy and water resources. The presence of data and remote control capabilities in smart distribution transformers offers distribution operators the chance to optimize system operation and control. The innovative system proposed utilizes smart metering technology and incorporates a distribution system self-healing mechanism against power outages, revolutionizing the way utilities manage water and energy consumption. The system not only offers real-time consumption statistics to the utility provider but also provides the flexibility to remotely control the system's turn-on and turn-off functions. The system effectively captures real-time data, transmits it via LoRa to Telegram application. The system automatically re-establishes remote connections in the event of disconnections caused by emergency conditions or non-payment of the bill, once the relevant issue has been resolved. Additionally, the system promptly notifies authorities on overload, over-temperature, and instances of electricity theft. The system proficiently generates bills based on the consumed data and seamlessly transmits the consumed units to the authorities. The innovative system proposed has proven its ability to communicate effectively, yielding results that align with the given circumstances.

Faculty Coordinator : H.N. Suresh, Mohana Lakshmi J

Reference Link: https://www.sciencedirect.com/science/article/pii/S2590123024009423

Student Name : N. Sushma

Title of the Paper : A unified metering system deployed for water and energy monitoring in smart city

Research Description : In the context of smart cities in India, accurate meter readings are crucial for managing household water and energy systems efficiently. However, traditional meter reading methods are costly and time-consuming due to the large number of users and the lack of daily usage analysis leading to customer dissatisfaction. The proposed solution to tackle this matter involves implementing an integrated wireless smart energy and water metering system that utilizes smart metering technology. This system can potentially revolutionize how utilities handle energy and water management. The integrated system is designed to replace the mechanical water meters and conventional digital energy meters, whose primary function is to accurately record meter readings for payment purposes, for automatic meter readings that do not require frequent trips to the location where the meters are installed. This article proposes a smart, integrated wireless metering system to revolutionize customer engagement and energy and water utility management. This technology enables the transmission of precise and secure data on water and energy consumption in real-time by employing Low Power Wide Area Networks (LPWAN) technology, known for its low power consumption, cost-effectiveness, long-range coverage, and efficient penetration. The system has a water flow sensor and PZEM-004T for real-time water and energy consumption readings. The interoperable features in the integrated water flow and energy meter are achieved through trial-and-error methods. The trials led to experimental findings that enabled successful communication between the energy and water flow meters and recorded accurate readings. The device provides the utility provider with real-time consumption statistics and the flexibility to turn on and off the system remotely. The system also helps the users by giving them real-time consumption data and preventing overloading situations.

Faculty Coordinator : H. N. Suresh, Mohana Lakshmi J

Reference Link: https://ieeexplore.ieee.org/document/10196447

Student Name : Poornima H G; Bindushree S N; Raksha A; Lateshkumar S N

Title of the Paper : Simulation Based Hybrid Solar and Wind Energy System for Standalone Application

Research Description : Growing concerns about environmental sustainability and energy security have led to a substantial global acceleration in the use of renewable energy sources in recent years. The unpredictable nature of renewable energy sources makes it difficult to produce total electric demand from an individual source. It is fortunate to be able to meet load demand with Hybrid Renewable Energy Systems (HRES). This system is reliable, cost effective, efficient and environmentally acceptable energy supply. The integration of solar and wind energy sources with battery storage results in optimal energy production and reliable power supply. Sizing Hybrid Renewable Energy Systems (HRES) as efficiently as possible while considering local solar and wind energy sources into account is the goal of the present study. The proposed system is considered for the partial electric load of Malnad College of Engineering, Hassan Karnataka. The optimal size, Total Net Present Cost (TNPC), and Cost of Energy (COE) of the proposed model is estimated using HOMER Pro software. Further, the mathematical models of solar & wind energy systems are compared using MATLAB Simulink.

Faculty Coordinator : Rajanna S.; Ramesh M

Reference Link: https://ieeexplore.ieee.org/document/10652580

Student Name : M. Sudharshan

Title of the Paper : Performance Analysis of Rabbit Algorithm with Gaussian Process Classifier for Detection of Adenocarcinoma from Lung Cancer Histopathological Images

Research Description : Lung and colon cancers are among the most common and fatal tumors. In 2022, 4.27 million people were diagnosed with lung and colon cancer, and more than 2.74 million died worldwide. Parts of the lungs affected by cancer are located utilizing image processing techniques such as noise reduction, feature extraction, damaged region identification, and possibly a comparison to a medical history of lung cancer. The primary goal of this study is to employ Rabbit Algorithm with Gaussian process classifier to detect and classify cancer using histopathology images of lung. The LC25000 collection contains 25,000 histopathological images from the human lung and colon, including both malignant and normal scans. Classifier performance parameters like Accuracy, Error rates, F1 score, Sensitivity, Specificity, Critical Success Index (CSI) and Youden’s Index (YI) are used to assess how well a classifier can distinguish between classes. Results indicate that an accuracy rate of 91.67% in detecting Adenocarcinoma can be achieved using the Rabbit Algorithm which is also characterized by the Gaussian Process Classifier.

Faculty Coordinator : Gowri Shankar Manivannan

Reference Link: https://ieeexplore.ieee.org/document/10922062

Student Name : K. R. Chethana, A. Firdose and N. Adithya

Title of the Paper : Performance Analysis of Local Binary Pattern Features with Eagle Optimization Algorithm based CNN Classifier for Breast Cancer Detection from Ultrasound Images

Research Description : Breast cancer detection at early stages is very much needed as it is one of the most prevalent cancer related death causing cancers among females. This paper poses an automated breast cancer detection based on analyzing ultrasound images using modern deep learning and optimization algorithms. We implement Local Binary Pattern feature extraction in addition to the Cuckoo Search Algorithm and Eagle Optimization Algorithm based CNN to improve the accuracy of the classification. The Eagle Optimization Algorithm on CNN classifier 97.89% results higher than the Cuckoo Search Algorithm on CNN classifier 95.46%. These results highlight the importance of good feature extraction and selection in enhancing the diagnosis.

Faculty Coordinator : Gowri Shankar Manivannan, S. Rajanna

Reference Link: https://ieeexplore.ieee.org/document/10921764

Student Name : A. R. Sinchana, S. Fathima, T. M. Sonika and D. P. Priya

Title of the Paper : Performance Analysis of LSTM Classification Model from GLCM with Lion Optimization Algorithm Features for Melanoma Identification from Skin Cancer Images

Research Description : Melanoma skin cancer is one of the most dangerous types of skin cancers that if not diagnosed and treated in the early stages can lead to death. This paper examines the detection of melanoma through GLCM feature extraction for the identification of patterns. We conduct a performance analysis on LOA based LSTM classifier and MSA based LSTM classifier. The accuracy of the LOA based classifier which is 97.49% is more than the accuracy of MSA based classifier which is 95.89% with a less error margin of 2.55%. These results illustrate the promise that the latest machine learning approaches have in the promotion of early detection of malignant melanoma, which is essential to improve health care delivery to patients.

Faculty Coordinator : Gowri Shankar Manivannan, K. B. Kaveri

Reference Link: https://ieeexplore.ieee.org/document/10921952

Student Name : Prathima H. V, Keerthana C. P, Lekhana. G. B.

Title of the Paper : Mitigating Mismatch and Wiring Losses Through Static PV Array Reconfiguration

Research Description : Partial shading in photovoltaic (PV) arrays results in considerable mismatch losses, diminished power output, and the potential for hotspot development. To alleviate these adverse effects, various static physical reconfiguration techniques are employed to improve energy yield and facilitate shade dispersion. In this study, the conventional Total-Cross-Tied (TCT) configuration, along with two static reconfiguration strategies namely Column-Based Reconfiguration and Array-Level Reconfiguration are examined under a range of shading scenarios, including L-shape, Long-wide, Random, and Right Top Corner (RTC) patterns. The proposed methods are modelled and analyzed within the MATLAB/Simulink framework, integrating realistic wiring specifications and accounting for resistive losses. For performance assessment, irradiance levels of 1000 W/m2 (unshaded), 700 W/m2, 500 W/m2,200 W/m2, and 100 W/m2 (shaded) were employed to simulate various shading conditions. Simulation results reveal that both static reconfiguration approaches enhance shade dispersion and improve current uniformity compared to the conventional TCT arrangement, with Method 2 (Array-Level Reconfiguration) demonstrating superior shading tolerance at the expense of higher wiring resistance. The study highlights the trade-off between wiring complexity and mismatch reduction, offering insights into the practical implementation of shade-resilient PV array configurations.

Faculty Coordinator : M. Ramesh

Reference Link: https://ieeexplore.ieee.org/document/11307505

Student Name : Sinchana K P; Tejaswini S; Chandan H S; Ankesh N

Title of the Paper : An Efficient Capsule Network Model Performance Analysis from Fast Fourier Transform Features for Prediction of Stator Winding Temperature in Permanent Magnet Synchronous Motor

Research Description : An electric motor's temperature estimation is one of the critical factors governing operational efficiency, overheating prevention, and maximizing motor life. The utility of such accurate predictions will eventually lead to a priori detection of a fault, thereby improving system reliability. This study recommends a deep learning-based approach to PMSM temperature prediction. Missing data preprocessing is done by the KNN imputer and autoencoder. FFT is applied to extract the significant features in the frequency domain. Finally, these extracted features are used for training and testing of both CNN-LSTM and Capsule Network models. Results indicate that the Capsule Network surpasses the CNN-LSTM by achieving a reduced MSE of 0.0239 and a better R2 score of 0.8823 in their performance on PMSM temperature prediction.

Faculty Coordinator : Gowri Shankar Manivannan

Reference Link: https://ieeexplore.ieee.org/document/11053102

Student Name : Thanmayi H S; Thejaswini D D; Nadiya Huda Khanum; Kishore B Hassan

Title of the Paper : Fourier Transform Temporal Features based Hybrid GRU-TCN Algorithm Performance Analysis for Prediction of Multi-Region Electricity Energy Consumption

Research Description : Energy Consumption forecasting is an important part of proper management and sustainability for the grid. Deep learning models are currently being employed as strong energy demand predictors. Here, Simple Imputer is used to fill in missing data, and LOF is used to remove the outliers in this work. The temporal features extracted by the Fourier Transform are then fed to models LightGBM and GRU+TCN for evaluation. Experimental results show that the GRU+TCN model outperformed the PJMW region with the lowest MSE of 0.0173 and R2 of 0.9699, revealing more accurate prediction capability.

Faculty Coordinator : Gowri Shankar Manivannan; Ranjan N A

Reference Link: https://ieeexplore.ieee.org/document/11052996

Student Name : Chinmayee R G, Tharesh D R, Shreyas C and Ruthik J K

Title of the Paper : Unified Approach to Detection of Induction Motor Faults from Vibration Signals using Hilbert Transform based Autoencoder Features and Hybrid Efficient Machine Learning Algorithms

Research Description : Since vibration signals are sensitive to changes, they are regularly used to assess the condition of rotating electrical machines. These signals include vital data that makes it possible to find mechanical problems and identify unusual behaviors. Revealing important patterns from information in vibration data is now greatly assisted by machine learning. Once faults have been prepared and processed properly, ML systems are able to identify both the type and severity of each fault. Three-phase induction motor vibration signals are very important for fault diagnosis to ensure reliable operation and minimize downtime. In this study, vibration signals are collected and pre-processed by the Hilbert Transform to eliminate noise and outliers. The pre-processed signals are fed to an Autoencoder for feature extraction and subsequent classification by effective learning algorithms. Among the models under study, the proposed Hybrid RF-GMM model provided the highest classification accuracy of 95.91%, outperforming RF (92.28%) and GMM (88.18%), reflecting its excellence in fault detection.

Faculty Coordinator : Gowri Shankar Manivannan

Reference Link: https://ieeexplore.ieee.org/document/11136571

Student Name : Dhyana Tejas Shukla C R

Title of the Paper : Deep Residual Networks Based Classification of Ovarian Cancer from Histopathological Images Using Bio-Inspired Metaheuristic Optimization Algorithm

Research Description : Ovarian cancer is one of the deadliest gynecological malignancies and is commonly discovered in the later stages because the symptoms are vague and early detection methods are not very effective. Early and precise detection is very important to improve patient outcomes. In this work, an artificial intelligence framework is developed for classifying histopathological images into the four main subtypes of ovarian cancer such as Clear Cell, Endometrioid, Mucinous, Serous Carcinoma, and non-cancerous samples. The model uses a fuzzy Gabor filter to enhance the original image, followed by superpixel-based segmentation and feature extraction by using t-SNE. The reduction of dimensionality into a low-dimension space is subsequently enhanced by applying the Firefly Algorithm, and the classification process is carried out by implementing four ResNet variants, namely ResNet18, ResNet50, ResNet101, and ResNet152. Among them, ResNet152 showed the highest performance with a classification accuracy of 95.68% for serous carcinoma. The findings validate the performance of the proposed pipeline for precise analysis of ovarian cancer subtypes, indicating its potential to provide faster diagnoses with greater trustworthiness to pathologists.

Faculty Coordinator : Gowri Shankar Manivannan

Reference Link: https://ieeexplore.ieee.org/document/11211200

Student Name : M. Goutham; Rashmi M.H; Ayesha Zameer

Title of the Paper : Multifunctional Borewell Rescue Robot for Enhanced Child Safety

Research Description : Borewell accidents involving children are a recurring and tragic issue in many regions. Existing rescue methods are often slow, labor-intensive, and risky. This project proposes a multifunctional borewell rescue robot designed to improve child safety through rapid and efficient intervention. The robot is capable of descending into narrow borewells, locating the trapped child using real-time video and sensor data, and performing rescue operations with precision. Equipped with lightweight servo motors, airbags, and a robust control system, it allows for both autonomous and manual operation. The system ensures constant communication with rescue teams and enhances safety through advanced navigation and manipulation mechanisms. Tested in both simulated and controlled environments, the robot has shown significant potential in reducing response times and improving the success rate of borewell rescues. This innovation aims to revolutionize emergency rescue operations and save young lives with greater reliability and efficiency.

Faculty Coordinator : Mohana Lakshmi J

Reference Link: https://ieeexplore.ieee.org/document/11158883

Student Name : N Kotesha; B K Punith Gowda

Title of the Paper : Development of Automated Harvest Machine for Precision Farming of Areca Nut

Research Description : This article provides a comprehensive review and proposes a system design that integrates machine learning with an automated harvesting machine for areca nut classification and collection. Utilizing image processing techniques, the system employs machine learning algorithms to classify areca nuts as ripe, unripe, or rotten based on features such as color, texture, and shape. An IoT-enabled automated mechanism facilitates the selective harvesting of mature nuts, improving efficiency compared to traditional methods. This approach aims to enhance productivity in areca nut farming by automating and optimizing the harvesting process. The article discusses both existing solutions and a system currently being deployed.

Faculty Coordinator : Mohana Lakshmi J

Reference Link: https://ieeexplore.ieee.org/document/11158830

Student Name : Thejaswini T

Title of the Paper : Cuckoo Search Algorithm Features based Multi Kernel Support Vector Machine Performance Analysis for Detection of Battery Anomaly from Lithium-Ion Battery

Research Description : An important factor in assuring system reliability and safety is the detection of anomalies in lithium-ion battery voltage in a timely manner using machine learning techniques. In this study, the NASA battery voltage dataset is first preprocessed with a One-Class SVM to remove the outliers. Following this, the Cuckoo Search algorithm was used in feature extraction to select the most informative parameters for classification. Then, the extracted features are evaluated using Support Vector Machine classifiers through Linear, RBF, and Polynomial kernels. Among them, the RBF kernel achieved the highest classification accuracy of 96.87% and MSE at 0.0741, thus effectively performing anomaly detection in the battery voltage profiles.

Faculty Coordinator : Gowri Shankar Manivannan; Rajanna S

Reference Link: https://ieeexplore.ieee.org/document/11081291

Student Name : Pavan Kumar P K; Prajwal M D

Title of the Paper : Development of AI Powered Model for Oralcancer Detection

Research Description : Oral cancer detection, a critical health challenge due to late-stage diagnoses, has seen significant advancements through the integration of both hardware and software technologies. The system, designed for the early detection of oral cancer, combines innovative hardware, such as robotic arms for assistive feeding, cost-effective control systems for industrial robotics using Raspberry Pi, and Io T - enabled devices for remote oral examinations, with advanced software solutions. These hardware systems utilize lightweight structures, motorized joints, stepper motors and precise motion control to enhance functionality in healthcare and industrial environments. For early detection, Machine Learning (ML) and Deep Learning (DL) techniques, including Convolutional Neural Networks (CNNs) and transfer learning models like VGG19 and InceptionNetV3, Res-Net and Dense-Net, have been employed to analyse medical images. Image processing methods such as GLCM, wavelet transforms, and CNN-based feature extraction improve classification accuracy, while optimization techniques like Fuzzy Particle Swarm Optimization (FPSO) and Artificial Bee Colony (ABC) enhance performance. The integration of these systems achieves high sensitivity, specificity, and precision, making them effective in early oral cancer detection. By combining advanced diagnostic technologies, the system offers a comprehensive approach that improves early diagnosis, enhances patient outcomes, and complements traditional methods.

Faculty Coordinator : Mohana Lakshmi J

Reference Link: https://ieeexplore.ieee.org/document/11159023

Title : MoU with Department of E & E Engineering, Adichunchanagiri Institute of Technology, Chikkamagaluru

Description : Department of Electrical & Electronics Engineering, Malnad College of Engineering, Hassan signed MoU with Department of E & E Engineering, Adichunchanagiri Institute of Technology, Chikkamagaluru on 24th May 2022. The purpose of MOU is to promote interest in the teaching and research activities of the respective institution.

Reference Files:

Title : DEBESON ENTERPRISES

Description : Department of Electrical & Electronics Engineering, Malnad College of Engineering, has signed a MoU with Debeson Enterprises, Tumkur on 9th of January 2025. MCE and Debeson Enterprises have jointly agreed to work together to offer Industry Oriented Training Program to MCE Students.

Reference Files: