Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Indonesian Journal of Information System International Journal of Informatics, Information System and Computer Engineering (INJIISCOM)
Kumar, Sathish
Unknown Affiliation
Computer Science & IT Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Mechanical Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Enhanced Wearable Strap for Feminine using IoT Kumar, Sathish; Nandhini, S; Sujitha, R
International Journal of Informatics, Information System and Computer Engineering (INJIISCOM) Vol. 3 No. 1 (2022): International Journal of Informatics, Information System and Computer Engineeri
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injiiscom.v3i1.7910

Abstract

Women are increasingly experiencing a slew of security difficulties while traveling alone at night, particularly in the IT industry. Despite the benefits of new technologies, the rate of crime against women continues to rise. Despite the fact that numerous security gadgets are available on the market, women are unaware of them and do not use them. We are going to develop a prototype design using IoT. The term "physical objects” that are outfitted with sensors, computing power, software, and other technologies that enable them to connect and exchange data with other devices and systems over the Internet or other communication networks are referred to as the Internet of Things. Our project's ultimate goal is to give protection to working women and children. The majority of crimes occur as a result of a person's lack of awareness. We plan to keep the person aware throughout by administering a VIBRATION. The device comprises components such as the Start button, Arduino UNO, Panic Button, GSM Neo 6 m, GPS, Pulse Sensor, Vibration Motor, 6V Transformer, and Touch Sensor. The current location is determined using GPRS and GSM Neo 6 m. In emergency cases, a Pulse Sensor detects the person's actual pulse rate. The person must use a Touch Sensor to stop the vibration. If the vibration does not stop within the specified time, it is assumed that the person is not in an active state. The Emergency alert is then sent to the predefined contacts stored on the Arduino board. The transformer with a voltage range of 6v supplies power to the entire device. The future scope of this project is we can collect datasets of all hospitals for emergency purpose, creating offline maps to locate the victim without internet connection. Then the device can also contain Mic and camera to live monitor the consequences
Enhancing Eye Health Diagnosis through Deep Transfer Learning: Unveiling Insights from Low Quality Fundus Images S. Pariselvam; Kumar, Sathish; M. Govindarajan; R. Keerthivasan; I. Srivathsan
Indonesian Journal of Information Systems Vol. 7 No. 2 (2025): February 2025
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v7i2.9103

Abstract

Due to the frequency of eye illnesses, effective and precise diagnostic instruments are required. This work suggests an approach that uses low quality fundus images with deep transfer learning more precisely, the EfficientNetB0 architecture to improve eye health diagnosis. We tackle the problem caused by the quality of fundus photographs that are commonly found in clinical settings, which frequently display noise and abnormalities. Our methodology consists of pretraining the EfficientNetB0 model on a sizable dataset of excellent fundus photos, followed by fine-tuning it on a dataset of poor fundus photos. By employing this transfer learning technique, the model enhances its diagnostic capabilities by learning to identify significant features from the low-quality images. We ran tests on a variety of datasets that included fundus photos of varying degrees of deterioration in order to assess our approach. As compared to conventional techniques, the results reveal a significant improvement in diagnostic accuracy, demonstrating the effectiveness of deep transfer learning for improving eye health diagnosis from difficult fundus images. With fused features from MobileNet and DenseNet-121 models, the ANN specifically achieved accuracies of 98.5% for cataracts, 99.1% for diabetic retinopathy, 99% for glaucoma, and 99.5% for normal conditions.
Enhancing Eye Health Diagnosis through Deep Transfer Learning: Unveiling Insights from Low Quality Fundus Images S. Pariselvam; Kumar, Sathish; M. Govindarajan; R. Keerthivasan; I. Srivathsan
Indonesian Journal of Information Systems Vol. 7 No. 2 (2025): February 2025
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v7i2.9103

Abstract

Due to the frequency of eye illnesses, effective and precise diagnostic instruments are required. This work suggests an approach that uses low quality fundus images with deep transfer learning more precisely, the EfficientNetB0 architecture to improve eye health diagnosis. We tackle the problem caused by the quality of fundus photographs that are commonly found in clinical settings, which frequently display noise and abnormalities. Our methodology consists of pretraining the EfficientNetB0 model on a sizable dataset of excellent fundus photos, followed by fine-tuning it on a dataset of poor fundus photos. By employing this transfer learning technique, the model enhances its diagnostic capabilities by learning to identify significant features from the low-quality images. We ran tests on a variety of datasets that included fundus photos of varying degrees of deterioration in order to assess our approach. As compared to conventional techniques, the results reveal a significant improvement in diagnostic accuracy, demonstrating the effectiveness of deep transfer learning for improving eye health diagnosis from difficult fundus images. With fused features from MobileNet and DenseNet-121 models, the ANN specifically achieved accuracies of 98.5% for cataracts, 99.1% for diabetic retinopathy, 99% for glaucoma, and 99.5% for normal conditions.
Co-Authors I. Srivathsan M. Govindarajan Nandhini, S R. Keerthivasan S. Pariselvam Sujitha, R