MERLIN C D

@citchennai.edu.in

Assistant Professor, Department of Computer Science and Engineering
Chenai Institute of Technology

MERLIN C D


                  Download Compact PDF  
https://researchid.co/merlincd

RESEARCH, TEACHING, or OTHER INTERESTS

Electrical and Electronic Engineering, Biomedical Engineering, Artificial Intelligence, Computer Vision and Pattern Recognition
8

Scopus Publications

8

Scholar Citations

1

Scholar h-index

Scopus Publications

  • Sensing an Activated Mobile Phone by using Transmitted Signals
    M Yogapriya, Merlin C D, Kavitha Rani S
    2025 International Conference on Data Science Agents and Artificial Intelligence Icdsaai 2025, 2025
    The changes that have taken place over the centuries have led to the better development of science and technology, but have also aroused many scammers. Some examples of technologies that have evolved in recent years include: there is online transactions, internet banking, sports and other entertainment. Especially in education during the pandemic (COVID-19). In this situation, the use of mobile phones was compulsory. After the pandemic, students continued to attend school, college, and resume real life, but kept their mobile phones in the facility. For example, students in a classroom or examination room may seek to communicate informally with those outside the hall for whatever purpose. Mobile phone activity is identified by the presence of a transmitted signal. It is based on radio frequency (RF) principles. Developing and implementing a mobile phone detector is part of our project. This portable gadget will identify a cell phone that is also in silent mode (an active cell phone). This detector is designed to detect within a radius of 1.5 meters
  • Design of an Home Automation System with Voice Controlled Application using Arduino
    Merlin C D, Darwin A, Gowtham M, Danushkodi R
    2025 International Conference on Data Science Agents and Artificial Intelligence Icdsaai 2025, 2025
    Nowadays home automation forms one of the major applications around the globe, all of us likes to setup a home automation but its complex circuit becomes a barrier in setting up it. Home automation involves putting motion or voice control on household appliances. In this paper we discuss about developing of home automation process by using Arduino to decrease the burden of the users and make it easier to interact with home appliances. The focus of the current study is speech-controlled home automation, which enables household appliances like lights, fans, and doors to be operated by voice. To achieve this, Arduino with Bluetooth module have been used as hardware components which controls the state of the electronic gadgets (ON/OFF). The commands are made to pass with the help of MIT application. This research makes home automation simple and affordable to everyone
  • Advanced Biometric Iris Authentication System Leveraging Deep Learning Techniques
    Breesha R, Menaka M, Merlin C D, Ramya D, Sakthisri R, Thirisha M
    2025 International Conference on Data Science and Business Systems Icdsbs 2025, 2025
    This paper provides an advanced biometric iris authentication system using deep learning, particularly Convolutional Neural Networks (CNNs), in order to enhance the performance as well as efficiency of iris-based biometrics. The proposed system overcomes a few of the shortcomings of traditional methods of iris authentication, such as susceptibility to spoofing and reduced accuracy when lighting conditions change. A very large dataset of iris images was preprocessed to minimize variations, ensuring the best possible accuracy in recognition of iris patterns. The system outperformed the state-of-the-art systems in terms of False Acceptance Rate (FAR) and False Rejection Rate (FRR). Furthermore, high-level spoofing detection capabilities were added, significantly lowering vulnerability to attacks using fake iris images. One of the significant contributions of this work is creating a particular CNN architecture for iris recognition and a novel preprocessing pipeline for more improved feature extraction. Results show that the proposed deep learning-based approach outperforms the already existing systems, so it is a promising solution for secure and privacy-preserving human identification in real-world applications. This research will serve as a seed to future studies in fine-tuning deep learning models applied to different security domains in biometric systems.
  • Detection Of Diabetic Retinopathy Using Deep Learning
    R Breesha, C D Merlin, S Jalaja, R Keerthana, S A Abinaya, A Durga Devi
    2025 8th International Conference on Circuit Power and Computing Technologies Iccpct 2025, 2025
    One of the main causes of visual loss is diabetic retinopathy (DR) affecting millions globally, especially those with diabetes Early identification and action are essential to avoiding severe complications, but traditional diagnostic methods rely on manual examination, which is time consuming and resourceintensive. A deep learning- based approach for automated DR detection is presented in this paper using a combination of U-Net for retinal image segmentation and Convolution Neural Networks (CNN) for classification. The U-Net architecture is employed to segment vital retinal characteristics like lesions and blood vessels while the CNN model classifies images into two categories: proliferative and non-proliferative DR. The proposed system aims to improve diagnostic efficiency by offering an automated, accurate, and salable solution for DR detection, particularly in resource constrained settings. The method was evaluated using key performance metrics, demonstrating its potential for enhancing early diagnosis and treatment of diabetic retinopathy
  • Cryptocurrency Forecasting: Predicting Dogecoin Prices with Machine Learning
    M Menaka, C D Merlin, Breesha, R Sham, C Vinoth Kumar, S Sabarishankar
    2025 8th International Conference on Circuit Power and Computing Technologies Iccpct 2025, 2025
    Xephyr, the meme cryptocurrency, based on time, has grown in prominence and trade activity. Due to the market volatility and other factors it is still difficult to predict the prices of bitcoin. In this paper, we employ a machine learning model to forecast the future price trends of Dogecoin after analyzing the historical data. The method used in this study involves the application of different machine learning techniques including Linear Regression, Random Forest Regressor, and Long Short-Term Memory (LSTM) networks which are implemented using Python for data preprocessing, visualization and predictive modelling. The results indicate that deep learning has a potential in the cryptocurrency pricing and forecasting since LSTM models outperforms the conventional models in pricing.
  • Dementia Detection in MRI Using CNN Classifier
    C D Merlin, R Breesha, P S Divya, M Madhan, J. Godson, V Abhunoejith
    2025 8th International Conference on Circuit Power and Computing Technologies Iccpct 2025, 2025
    It is essential to emphasise the importance of detecting dementia as early as possible, as this cognitive disorder exhibits signs that increasingly limit the patient. Consequently, early detection aids in improving patient management and controlling disease progression. With the assistance of modern medical imaging techniques, particularly MRI, studying the structural and functional changes in the brain associated with dementia has become feasible. In this work, we focus on the classification of MRI images. We aim to explore the potential of a broad data set of magnetic resonance imaging regarding brain scans to identify markers of cognitive decline, which are often subtle and not easily recognised by clinicians. We expand the range of deep learning applications by implementing algorithms within the medical domain, specifically in tasks involving MRI images. These algorithms are believed to effectively distinguish normal ageing traits from the morphological changes associated with dementia. CNNs enable preferred feature representation in dense layers, minimising the memory consumption typically required for fully connected neural networks. Consequently, CNNs are widely and successfully employed for various applications involving images. Thus, the cognitive impairment of such patients can be diagnosed automatically without the need for labour-intensive and time-consuming preprocessing or manual feature engineering.
  • Classification of Lesions in Brain MR Images using Probabilistic Neural Network Classifier
    C D Merlin, V C Subash Bala, G Ranjith Kumar, R Surya
    2024 International Conference on Electrical Electronics and Computing Technologies Iceect 2024, 2024
    Classification of medical image forms one of the most important process in computer aided diagnosis and medical image applications. Classification of lesions in Brain MRI classification forms a complicated task due to its high complex and resolution in medical imaging. The proposed work consists of a novel classification method using Probabilistic Neural Network (PNN) classifier. The Neural Network (NN) training is done in all the layers of the network. The classification results identifies whether the given image is Normal or Benign or Malignant. PNN classifier is used for its fast speed on training and its simple structure. Finally the classified image is bounded so that the exact region which is detected will be identified.
  • Human behavioural identification in different aspects using neural network
    Merlin C D, V. R. Ravi, Parthiban M, Yashwanth Raj A, Mohanasundaram M, Sathish A
    Proceedings of International Conference on Circuit Power and Computing Technologies Iccpct 2024, 2024
    Examining a person’s facial expressions is a common technique for understanding their emotions, but training a computer to perform the same task is a difficult challenge. Numerous algorithms and methods are available to analyze human emotions conveyed through facial expressions. This study compares various approaches to recognizing emotions on human faces, incorporating multiple perspectives on emotion detection and utilizing the "Viola-Jones Face Detection" method to identify faces. Emotion classification can be accomplished using different classifiers, with features extracted through methods such as "Zernike moments," "DCT transform," or "LBP." Another method for identifying facial emotions is through Convolutional Neural Networks (CNN), which involves two stages. The first stage isolates the facial component vector, while the second stage removes the image’s background. With computer vision technology, it is now feasible to detect emotions by examining human faces using various algorithms and methods.

RECENT SCHOLAR PUBLICATIONS

  • Machine Learning Models for Early Diagnosis of Huntingtons Disease Using Gene Expression Data
    CD Merlin, TJ Nagalakshmi
    2025 IEEE 9th International Conference on Information and Communication … , 2025
    2025
    Citations: 1
  • Dementia Detection in MRI Using CNN Classifier
    CD Merlin, R Breesha, PS Divya, M Madhan, J Godson, V Abhunoejith
    2025 8th International Conference on Circuit, Power & Computing Technologies … , 2025
    2025
  • Detection Of Diabetic Retinopathy Using Deep Learning
    R Breesha, CD Merlin, S Jalaja, R Keerthana, SA Abinaya, AD Devi
    2025 8th International Conference on Circuit, Power & Computing Technologies … , 2025
    2025
  • Cryptocurrency Forecasting: Predicting Dogecoin Prices with Machine Learning
    M Menaka, CD Merlin, R Sham, CV Kumar, S Sabarishankar
    2025 8th International Conference on Circuit, Power & Computing Technologies … , 2025
    2025
    Citations: 1
  • Advanced Biometric Iris Authentication System Leveraging Deep Learning Techniques
    R Breesha, M Menaka, CD Merlin, D Ramya, R Sakthisri, M Thirisha
    2025 International Conference on Data Science and Business Systems (ICDSBS), 1-7 , 2025
    2025
  • Sensing an Activated Mobile Phone by using Transmitted Signals
    M Yogapriya, CD Merlin
    2025 International Conference on Data Science, Agents & Artificial … , 2025
    2025
  • Design of an Home Automation System with Voice Controlled Application using Arduino
    CD Merlin, A Darwin, M Gowtham, R Danushkodi
    2025 International Conference on Data Science, Agents & Artificial … , 2025
    2025
  • Classification of Lesions in Brain MR Images using Probabilistic Neural Network Classifier
    CD Merlin, VCS Bala, GR Kumar, R Surya
    2024 International Conference on Electrical Electronics and Computing … , 2024
    2024
    Citations: 1
  • Human behavioural identification in different aspects using neural network
    CD Merlin, VR Ravi, M Parthiban, M Mohanasundaram, A Sathish
    2024 7th International Conference on Circuit Power and Computing … , 2024
    2024
    Citations: 1
  • Detection and Classification of Diabetic Retinopathy using Deep Learning
    N Duraichi, S Jalaja, CD Merlin, SM Jasmine, RN Kamali, K Manoj
    Cardiometry, 808-813 , 2023
    2023
    Citations: 4

MOST CITED SCHOLAR PUBLICATIONS

  • Detection and Classification of Diabetic Retinopathy using Deep Learning
    N Duraichi, S Jalaja, CD Merlin, SM Jasmine, RN Kamali, K Manoj
    Cardiometry, 808-813 , 2023
    2023
    Citations: 4
  • Machine Learning Models for Early Diagnosis of Huntingtons Disease Using Gene Expression Data
    CD Merlin, TJ Nagalakshmi
    2025 IEEE 9th International Conference on Information and Communication … , 2025
    2025
    Citations: 1
  • Cryptocurrency Forecasting: Predicting Dogecoin Prices with Machine Learning
    M Menaka, CD Merlin, R Sham, CV Kumar, S Sabarishankar
    2025 8th International Conference on Circuit, Power & Computing Technologies … , 2025
    2025
    Citations: 1
  • Classification of Lesions in Brain MR Images using Probabilistic Neural Network Classifier
    CD Merlin, VCS Bala, GR Kumar, R Surya
    2024 International Conference on Electrical Electronics and Computing … , 2024
    2024
    Citations: 1
  • Human behavioural identification in different aspects using neural network
    CD Merlin, VR Ravi, M Parthiban, M Mohanasundaram, A Sathish
    2024 7th International Conference on Circuit Power and Computing … , 2024
    2024
    Citations: 1
  • Dementia Detection in MRI Using CNN Classifier
    CD Merlin, R Breesha, PS Divya, M Madhan, J Godson, V Abhunoejith
    2025 8th International Conference on Circuit, Power & Computing Technologies … , 2025
    2025
  • Detection Of Diabetic Retinopathy Using Deep Learning
    R Breesha, CD Merlin, S Jalaja, R Keerthana, SA Abinaya, AD Devi
    2025 8th International Conference on Circuit, Power & Computing Technologies … , 2025
    2025
  • Advanced Biometric Iris Authentication System Leveraging Deep Learning Techniques
    R Breesha, M Menaka, CD Merlin, D Ramya, R Sakthisri, M Thirisha
    2025 International Conference on Data Science and Business Systems (ICDSBS), 1-7 , 2025
    2025
  • Sensing an Activated Mobile Phone by using Transmitted Signals
    M Yogapriya, CD Merlin
    2025 International Conference on Data Science, Agents & Artificial … , 2025
    2025
  • Design of an Home Automation System with Voice Controlled Application using Arduino
    CD Merlin, A Darwin, M Gowtham, R Danushkodi
    2025 International Conference on Data Science, Agents & Artificial … , 2025
    2025