Deepa Beeta Thiyam

Dr. Deepa Beeta Thiyam


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 August 2024 in Traitement du Signal
Verified
Journal Article
Open access
SRShelishiyah R
Shelishiyah R
DTDeepa Beeta Thiyam
Deepa Beeta Thiyam

21 September 2023 in International Journal on Recent and Innovation Trends in Computing and Communication
Verified
Journal Article
Open access
PDF file
SRShelishiyah R
Shelishiyah R
DTDeepa Beeta Thiyam
Deepa Beeta Thiyam
JMJehosheba Margaret M
Jehosheba Margaret M
The Brain-Computer Interface (BCI) technologies have excellent clinical and non-clinical uses. Among the most popular imaging methods adopted in BCI technologies is electroencephalography (EEG). But EEG signals are typically quite complicated, so analyzing them necessitates a significant amount of effort. With the help of machine learning (ML), this research investigates the feasibility of a BCI platform based on the motor imagery (MI) concept. The steps of pre-processing, feature extraction and classification are the underpinning of any conventional ML model. To train such a model, however, a large amount of data is needed. To address this gap, this work introduces a new mayfly-optimized multiclass weighted random forest (MFO-MWRF) technique that uses retrieved features as input to mitigate the need for this supplementary data. In this study, we gather a dataset of hybrid EEG and fNIRS motor imagery that can be pre-processed using a Wiener filter (WF) to filter out noisier signals without affecting the high-quality images. The characteristics are extracted using the discrete wavelet transform (DWT). The research results indicate that the proposed approach achieves the best performance compared to existing approaches for classifying motor movement images.

7 November 2025 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
SGSudarsun G
Sudarsun G
GNGlen Nitish
Glen Nitish
DFDANIEL FORD
DANIEL FORD
DTDeepa Beeta Thiyam
Deepa Beeta Thiyam
SRShelishiyah Raymond
Shelishiyah Raymond
In pharmaceutical and biomedical industries, manual handling of dangerous chemicals is a leading cause of hazardous exposure to chemicals, toxic burning, and chemical contamination. To counteract these risks, we proposed a gesture-controlled bionic hand system to mimic human finger movements for safe and contactless chemical handling. This innovation system uses an ESP32 microcontroller to decode the hand gestures that are detected by the system using computer vision via an integrated camera. A PWM servo driver converts these movements to motor commands such that accurate movements of the fingers can be achieved. Teflon and other corrosion-proof materials are utilized in the 3D printing of the bionic hand in order to withstand corrosive conditions. This new, low-cost, and non-surgical approach replaces the EMG sensors, gives real-time control, and enhances industrial and laboratory process safety. The project is a major milestone in the application of robotics and AI for automation and risk reduction in dangerous environments.

25 November 2024 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
BPBidheyak Pokharel
Bidheyak Pokharel
DTDeepa Beeta Thiyam
Deepa Beeta Thiyam
SDSachin Devkota
Sachin Devkota
DSDevanand Kumar Sah
Devanand Kumar Sah
In the context of developing countries, medical instruments are imported from foreign countries. To overcome this challenge, herein the design of an oxygen analyzer using ultrasonic flow sensor technology and a microcontroller while promoting local innovation and reducing dependency on imported equipment is presented. Moreover, this design aims to enhance patient care by ensuring accurate oxygen concentration and flow rate measurements on ventilators and oxygen concentrators. The data measured using the proposed system have been validated by comparison with data obtained using standard oxygen analyzer equipment like the VT-900 Gas Flow Analyzer from Fluke Biomedical and the Ultra Max oxygen analyzer. Measurements were conducted on hospital ventilators, with oxygen concentration (FiO2) being set to range from 21% to 100%, with increments of 5%, and the flow rate was set to range from 1 L/m to 10 L/m. The results show an error value of 2.1% for oxygen concentration measurements and a value of 0.6 L/m for flow rate measurements. Based on our analysis, it can be concluded that the proposed system works well. Additionally, it offers portability, affordability, and user-friendliness, overcoming the limitations of existing options. This project seeks to contribute to the healthcare infrastructure in developing countries like Nepal, India, Bangladesh, etc., by providing a domestically produced solution for oxygen analysis.

26 November 2024 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
SRShelishiyah R
Shelishiyah R
DTDeepa Beeta Thiyam
Deepa Beeta Thiyam
LALekha Chandhini Anipakala
Lekha Chandhini Anipakala
The state-of-art Hybrid Brain–Computer Interface (BCI) has shown improved classification of mental states either by combining different modalities or by choosing a combination of BCI activation tasks. Among these, the classification of motor imagery/execution tasks of contralateral and ipsilateral data of the upper arm is challenging due to its spatial adjacency and retention of these spatial features. The proposed work uses a Hybrid BCI dataset acquired using EEG and fNIRS for upper limb movement (right hand/left hand, right arm/left arm). The electrode positioning is along the motor cortex, and previous deep learning studies have shown that good accuracy can be obtained without any channel selection. Hence, the current study applies a combination of deep learning methods to the data, which were halved into two without using channel selection algorithms. The model was evaluated for both sets of channels using F1-score, precision, and recall with an accuracy of 89%. This investigation shows that all the channels of the studied dataset contained inter-related spatial information. Also, the problem of long-term EEG/fNIRS recording can be addressed using this study if the total number of channels can be used in two halves by switching the channels after the minimum efficient time of recording.