Sibu Philip Soman
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Sibu Philip Soman has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Kiliyanal Muhammedkunju Abubeker
Amal Jyothi College of Engineering (Autonomous)
2 shared publications - G Senthil Kumar
Sri Ramakrishna College of Arts and Science, India
1 shared publication G. Senthil Kumar
Nilgiri College of Arts and Science, Thaloor, India
1 shared publicationSherin Zafar
School of Engineering Sciences and Technology, Jamia Hamdard, New Delhi, India
1 shared publication- Suri Babu Nuthalapati
Farmioc
1 shared publication
Latest Publications
- 26 November 2024
- Published by IOP Publishing in Engineering Research Express
- Vol. 6 (4) , 045239
Internet of things assisted deep learning enabled driver drowsiness monitoring and alert system using CNN-LSTM framework
Driver fatigue has been generally viewed as a critical road safety factor and has been cited for contributing to a good percentage of traffic accidents. Developing systems to monitor and alert drowsy drivers is essential to reduce incidents. This research proposes a robust framework for driver drowsiness detection using a CNN-LSTM architecture developed by fusing facial landmark analysis with multiple aspect ratios. It uses, as key metrics in detecting drowsiness, the Eye Aspect Ratio (EAR), Pupil Circularity (PUC), the Mouth Aspect Ratio (MAR), and the Mouth over Eye Aspect Ratio (MOE). CNN-LSTM had been trained on YawDD, NITYMD, FL3D, and custom datasets. Data augmentation techniques such as flipping, scaling, shearing, rotation, brightness, and contrast adjustment are used to generalise under different illumination conditions and driver postures. The system is implemented on NVIDIA’s 128-core Jetson Nano GPU platform and does real-time processing of video frames captured by a CSI camera. It detects eye closure and yawning as symptoms of driver fatigue and immediately raises an alert through vibrations in the seatbelt and pre-recorded voice messages. The Internet connectivity allows remote monitoring via mobile applications, making it safer by ensuring that alerts reach the driver and passengers. This CNN-LSTM model has been carefully tested for various scenarios, including day and night conditions, proving its effectiveness. The proposed framework indicated excellent performance concerning accuracy (98%), precision (95%), recall (93%), F1 score (94%), and AUC (99%), thereby revealing its efficiency in practical scenarios. By incorporating EAR, MAR, PUC, and MOE for the early detection of drowsiness in this CNN-LSTM architecture, the system will be able to alert the driver ahead of time so that necessary precautions can be taken to avoid an accident. The proposed approach enhances the driver’s safety and is a scalable solution that adapts to different environments and populations.
- 26 November 2024
- Published by IOP Publishing in Engineering Research Express
- Vol. 6 (4) , 045239
Internet of things assisted deep learning enabled driver drowsiness monitoring and alert system using CNN-LSTM framework
Driver fatigue has been generally viewed as a critical road safety factor and has been cited for contributing to a good percentage of traffic accidents. Developing systems to monitor and alert drowsy drivers is essential to reduce incidents. This research proposes a robust framework for driver drowsiness detection using a CNN-LSTM architecture developed by fusing facial landmark analysis with multiple aspect ratios. It uses, as key metrics in detecting drowsiness, the Eye Aspect Ratio (EAR), Pupil Circularity (PUC), the Mouth Aspect Ratio (MAR), and the Mouth over Eye Aspect Ratio (MOE). CNN-LSTM had been trained on YawDD, NITYMD, FL3D, and custom datasets. Data augmentation techniques such as flipping, scaling, shearing, rotation, brightness, and contrast adjustment are used to generalise under different illumination conditions and driver postures. The system is implemented on NVIDIA’s 128-core Jetson Nano GPU platform and does real-time processing of video frames captured by a CSI camera. It detects eye closure and yawning as symptoms of driver fatigue and immediately raises an alert through vibrations in the seatbelt and pre-recorded voice messages. The Internet connectivity allows remote monitoring via mobile applications, making it safer by ensuring that alerts reach the driver and passengers. This CNN-LSTM model has been carefully tested for various scenarios, including day and night conditions, proving its effectiveness. The proposed framework indicated excellent performance concerning accuracy (98%), precision (95%), recall (93%), F1 score (94%), and AUC (99%), thereby revealing its efficiency in practical scenarios. By incorporating EAR, MAR, PUC, and MOE for the early detection of drowsiness in this CNN-LSTM architecture, the system will be able to alert the driver ahead of time so that necessary precautions can be taken to avoid an accident. The proposed approach enhances the driver’s safety and is a scalable solution that adapts to different environments and populations.
- 26 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 7 (7) , 1-4
Internet-of-Things-Assisted Artificial Intelligence-Enabled Drowsiness Detection Framework
Drowsiness, drunk driving, and fatigue are major causes of car accidents and consequent deaths nowadays. In this research, we introduced a real-time, Internet-of-Things (IoT) assisted, Computer Vision (CV) enabled framework for monitoring driver sleepiness based on Eye Aspect Ratio (EAR). When the EAR ratio drops below 0.2, a warning error is generated using a text-to-voice converter. The driver is alerted via seat belt vibrators; this data is sent to a cloud server. If the driver continues to sleep or fatigues for more than 2 seconds after the warning mechanism, the acceleration of the car might be lowered to prevent the accident. With the help of the NoIR Camera and Machine Learning (ML) model, images can now see well both during the day and at night without compromising the image quality. The efficacy of the developed model is confirmed by testing in multiple test scenarios using different subjects on a Raspberry Pi 4B Graphics Processing Unit (GPU) computer. As a result, the suggested technique has detected driver exhaustion and raised awareness, and prevented the accident rate.
- 26 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 7 (7) , 1-4
Internet-of-Things-Assisted Artificial Intelligence-Enabled Drowsiness Detection Framework
Drowsiness, drunk driving, and fatigue are major causes of car accidents and consequent deaths nowadays. In this research, we introduced a real-time, Internet-of-Things (IoT) assisted, Computer Vision (CV) enabled framework for monitoring driver sleepiness based on Eye Aspect Ratio (EAR). When the EAR ratio drops below 0.2, a warning error is generated using a text-to-voice converter. The driver is alerted via seat belt vibrators; this data is sent to a cloud server. If the driver continues to sleep or fatigues for more than 2 seconds after the warning mechanism, the acceleration of the car might be lowered to prevent the accident. With the help of the NoIR Camera and Machine Learning (ML) model, images can now see well both during the day and at night without compromising the image quality. The efficacy of the developed model is confirmed by testing in multiple test scenarios using different subjects on a Raspberry Pi 4B Graphics Processing Unit (GPU) computer. As a result, the suggested technique has detected driver exhaustion and raised awareness, and prevented the accident rate.