S. Syed Rafiammal
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
S. Syed Rafiammal has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
A. Ambika
Department of Electronics and Communication Engineering M.I.E.T Engineering College, Anna University, Tiruchirappalli
2 shared publicationsC. Parnasree
Department of Electronics and Communication Engineering M.I.E.T Engineering College, Anna University, Tiruchirappalli
1 shared publicationC.Parnasree Chakraborty
B.S. Abdur Rahman Crescent Institute of Science & Technology
1 shared publicationD. N. Jamal
Department of Electronics and Communication Engineering, B.S. Abdur Rahman Crescent Institute of Science and Technology, India
1 shared publication- D. Najumnissa Jamal
B. S. Abdur Rahman Crescent Institute of Science and Technology
1 shared publication - Dewan Najumnissa Jamal
B. S. Abdur Rahman Crescent Institute of Science and Technology
1 shared publication
Latest Publications
- 23 September 2025
- Published by Inventive Research Organization in Journal of Artificial Intelligence and Capsule Networks
- Vol. 7 (3) , 271-283
Comparative Analysis of Supervised Learning Algorithms for Clinical Diagnosis Heart Attack Prediction
This paper involves comparative research of novel deep machine learning and machine learning networks for the prediction of heart disease symptoms. Heart disease is one of the leading causes of death worldwide, and its early discovery saves a person's life. The objective of the research was to create a method of predicting heart attacks from lifestyle and clinical data through machine learning. The Machine learning algorithms that will be employed for prediction are discovered by conducting experiments that test combination of ML algorithms such as Logistic Regression, Random Forest, Support Vector Machines, and Gradient Boosting in the study. Data sets are downloaded from public sources and are processed to completion with missing value management, feature scaling, and exploratory data analysis (EDA). Validation has been performed using accuracy, precision, recall, and F1-score. The Random Forest classifier performed with an accuracy of 89%. The paper also discusses constraints and how to follow up the work, such as using larger data sets and new deep learning algorithms.
- 23 September 2025
- Published by Inventive Research Organization in Journal of Artificial Intelligence and Capsule Networks
- Vol. 7 (3) , 271-283
Comparative Analysis of Supervised Learning Algorithms for Clinical Diagnosis Heart Attack Prediction
This paper involves comparative research of novel deep machine learning and machine learning networks for the prediction of heart disease symptoms. Heart disease is one of the leading causes of death worldwide, and its early discovery saves a person's life. The objective of the research was to create a method of predicting heart attacks from lifestyle and clinical data through machine learning. The Machine learning algorithms that will be employed for prediction are discovered by conducting experiments that test combination of ML algorithms such as Logistic Regression, Random Forest, Support Vector Machines, and Gradient Boosting in the study. Data sets are downloaded from public sources and are processed to completion with missing value management, feature scaling, and exploratory data analysis (EDA). Validation has been performed using accuracy, precision, recall, and F1-score. The Random Forest classifier performed with an accuracy of 89%. The paper also discusses constraints and how to follow up the work, such as using larger data sets and new deep learning algorithms.
- 18 July 2024
- Published by Inventive Research Organization in Journal of Soft Computing Paradigm
- Vol. 6 (3) , 227-238
Enhanced Motor Imagery Classification through Channel Selection and Machine Learning Algorithms for BCI Applications
Brain-Computer Interface (BCI) applications utilizing Electroencephalography (EEG) signals have garnered significant attention for their potential to facilitate through communication between the brain and external devices. EEG-based BCIs offer a non-invasive means to interpret neural activity, enabling a range of applications in healthcare, gaming, and cognitive neuroscience. This study explores motor imagery (MI) EEG signals classification, employing a variety of signal processing techniques as well as machine learning algorithms to increase accuracy and reliability. Using data from the BCI Competition IV dataset, the proposed methodology involves EEG band separation via Butterworth bandpass filters, channel selection through a wrapper method using K-nearest neighbors (KNN), and classification of motor imagery tasks. The study demonstrates a high classification accuracy of 98% across different motor imagery tasks, highlighting the effectiveness of the proposed approach. This method not only shows promise for BCI applications aimed at assisting individuals with motor disabilities but also for gaming and potential security applications such as user authentication. Future work will focus on further enhancing the model's accuracy and exploring its integration into diverse practical applications.
- 18 July 2024
- Published by Inventive Research Organization in Journal of Soft Computing Paradigm
- Vol. 6 (3) , 227-238
Enhanced Motor Imagery Classification through Channel Selection and Machine Learning Algorithms for BCI Applications
Brain-Computer Interface (BCI) applications utilizing Electroencephalography (EEG) signals have garnered significant attention for their potential to facilitate through communication between the brain and external devices. EEG-based BCIs offer a non-invasive means to interpret neural activity, enabling a range of applications in healthcare, gaming, and cognitive neuroscience. This study explores motor imagery (MI) EEG signals classification, employing a variety of signal processing techniques as well as machine learning algorithms to increase accuracy and reliability. Using data from the BCI Competition IV dataset, the proposed methodology involves EEG band separation via Butterworth bandpass filters, channel selection through a wrapper method using K-nearest neighbors (KNN), and classification of motor imagery tasks. The study demonstrates a high classification accuracy of 98% across different motor imagery tasks, highlighting the effectiveness of the proposed approach. This method not only shows promise for BCI applications aimed at assisting individuals with motor disabilities but also for gaming and potential security applications such as user authentication. Future work will focus on further enhancing the model's accuracy and exploring its integration into diverse practical applications.
- Open Access
- 7 February 2024
- Published by Springer Nature in Research Square
RETRACTED: Integrating Neural Networks and Traditional Models: A Hybrid Approach for Accurate Heart Disease Prediction
The authors have requested that this preprint be removed from Research Square.
- 7 February 2024
- Published by Springer Nature in Research Square
Open AccessRETRACTED: Integrating Neural Networks and Traditional Models: A Hybrid Approach for Accurate Heart Disease Prediction
The authors have requested that this preprint be removed from Research Square.
- Open Access
- 4 November 2023
- Published by Inventive Research Organization in Journal of Electronics and Informatics
- Vol. 5 (4) , 351-367
Analysis of Audio Filtering Algorithms for Noise Cancellation
Real-time signal noise reduction poses a significant challenge in communication systems. To combat intrusive background noise during portable device conversations, an active noise cancellation (ANC) is employed. ANC generates anti-noise signals using techniques such as Least Mean Square (LMS) and Normalized Least Mean Square (NLMS) algorithms, Recursive Least Squares (RLS) and modified Recursive Least Squares (M-RLS) for effective reduction of unwanted sound and enhancing the output signal quality. The study includes various real-time noise signals to create anti-noise responses, successfully negating corresponding noise in input signals, which include sine waves, live voices, and music. Through a dedicated micro-controller device and electronic network, an "Anti-noise" wave is introduced to achieve active noise control (ANC). This research identifies ANC module specifications and effectively transmits them through the ANC library, demonstrating the efficiency of the proposed noise reduction technique.
- 4 November 2023
- Published by Inventive Research Organization in Journal of Electronics and Informatics
- Vol. 5 (4) , 351-367
Open AccessAnalysis of Audio Filtering Algorithms for Noise Cancellation
Real-time signal noise reduction poses a significant challenge in communication systems. To combat intrusive background noise during portable device conversations, an active noise cancellation (ANC) is employed. ANC generates anti-noise signals using techniques such as Least Mean Square (LMS) and Normalized Least Mean Square (NLMS) algorithms, Recursive Least Squares (RLS) and modified Recursive Least Squares (M-RLS) for effective reduction of unwanted sound and enhancing the output signal quality. The study includes various real-time noise signals to create anti-noise responses, successfully negating corresponding noise in input signals, which include sine waves, live voices, and music. Through a dedicated micro-controller device and electronic network, an "Anti-noise" wave is introduced to achieve active noise control (ANC). This research identifies ANC module specifications and effectively transmits them through the ANC library, demonstrating the efficiency of the proposed noise reduction technique.
- 4 November 2023
- Published by Inventive Research Organization in IRO Journal on Sustainable Wireless Systems
- Vol. 5 (4) , 276-287
A Hardware Vehicle Security and Accident Notification System using the Haar Cascade Algorithm
Low-cost vehicle security and accident notification system is essential in this modern society as vehicle theft and accidents that occur are increasing daily. In this proposed system, hardware for vehicle security is implemented, with authentication, and accident notification. Authentication is achieved by face detection and recognition using an open CV. The defaulter information is forwarded to the authenticated mobile number of the person by whom the vehicle is owned, using the GSM module and a notification email. The face authentication module was developed using the discrete wavelet transform-based Haar cascade algorithm. In addition to the face authentication, accident notifications will be sent to family members of the vehicle owner. Micro electrical mechanical system sensor was utilized to detect accident incidents using the accelerometer concept.
- 4 November 2023
- Published by Inventive Research Organization in IRO Journal on Sustainable Wireless Systems
- Vol. 5 (4) , 276-287
A Hardware Vehicle Security and Accident Notification System using the Haar Cascade Algorithm
Low-cost vehicle security and accident notification system is essential in this modern society as vehicle theft and accidents that occur are increasing daily. In this proposed system, hardware for vehicle security is implemented, with authentication, and accident notification. Authentication is achieved by face detection and recognition using an open CV. The defaulter information is forwarded to the authenticated mobile number of the person by whom the vehicle is owned, using the GSM module and a notification email. The face authentication module was developed using the discrete wavelet transform-based Haar cascade algorithm. In addition to the face authentication, accident notifications will be sent to family members of the vehicle owner. Micro electrical mechanical system sensor was utilized to detect accident incidents using the accelerometer concept.
- Open Access
- 7 June 2020
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 10 (3) , 5803-5807
Reconfigurable Hardware Design for Automatic Epilepsy Seizure Detection using EEG Signals
Reconfigurable circuit designs for automatic seizure detection devices are essential to prevent epilepsy affected people from severe injuries and other health-related problems. In this proposed design, an automatic seizure detection algorithm based on the Linear binary Support Vector Machine learning algorithm (LSVM) is developed and implemented in a Field-Programmable Gate Array (FPGA). The experimental results showed that the mean detection accuracy is 86% and sensitivity is 97%. The resource utilization of the implemented design is less when compared to existing hardware implementations. The power consumption of the proposed design is 76mW at 100MHz. The experimental results assure that a physician can make use of this proposed design in detecting seizure events.
- 7 June 2020
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 10 (3) , 5803-5807
Open AccessReconfigurable Hardware Design for Automatic Epilepsy Seizure Detection using EEG Signals
Reconfigurable circuit designs for automatic seizure detection devices are essential to prevent epilepsy affected people from severe injuries and other health-related problems. In this proposed design, an automatic seizure detection algorithm based on the Linear binary Support Vector Machine learning algorithm (LSVM) is developed and implemented in a Field-Programmable Gate Array (FPGA). The experimental results showed that the mean detection accuracy is 86% and sensitivity is 97%. The resource utilization of the implemented design is less when compared to existing hardware implementations. The power consumption of the proposed design is 76mW at 100MHz. The experimental results assure that a physician can make use of this proposed design in detecting seizure events.