3. Real-Time Recognition of Bangla Sign Language
Characters: A Computer Vision-Based Approach
Using Convolutional Neural Network
Publication: 2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE),
Publication date: 2021/12/22
Publisher: IEEE
​
Contribution: Sign Language is the elementary communication media for Deaf & Mute (D&M) people. On the other hand, it seems too tenacious for the general people to understand this language. In order to tear out this communication barrier, a real-time automated translator is essential. Through this research, a computer vision-based approach has been developed for the recognition of Bangla Sign Language (BdSL) characters. In this work, a deep learning-based recognition model has been developed. Adaptive thresholding has been integrated with 2D Convolutional Neural Network (CNN) to construct this model. The proposed model has been trained to build this real-time automated translator through our own created dataset (dataset containing 3600 different images for 36 distinct characters). The proposed model has been trained and tested with 2880 (80%) training images and 720 (20%) testing images respectively. Thirty-six unique characters of Bangla Sign Language can be recognized through this model with significant accuracy. The model delivers a validation accuracy of 99.72% and a validation loss of 0.73%. A significant result has been achieved for the recognition and translation of Bangla Sign Language characters with this dataset over other existing Bangla Sign Language Recognition models.
Availability: Access Link
Research Manuscript
​1. A comprehensive review of available battery datasets, RUL prediction approaches, and advanced battery management.
Authorship: First Author
Publication: IEEE Access Journal,
Rank: Q1
Publication date: 2021/6/14
Publisher: IEEE
​
Contribution: This review paper is mainly focused on three parts. The first one is battery data acquisitions with commercially and freely available Li-ion battery data set information. The second is the estimation of the state of the battery with the battery management system. And third is battery RUL estimation. Various RUL prognostic methods applied for Li-ion batteries are classified, discussed, and reviewed based on their essential performance parameters. Information on commercially and publicly available data sets of many battery models under various conditions is also reviewed. Various battery states are reviewed considering advanced battery management systems. To that end, a comparative study of Li-ion battery RUL prediction is provided together with the investigation of various RUL prediction algorithms and mathematical modeling.
​
Google Scholar Citations: 121.
​
Availability: Access Link
2. Driving Range Prediction of Electric Vehicles: A Machine Learning Approach.
Authorship: First Author
Publication: 2021 5th International Conference on Electrical Engineering and Information Communication Technology (ICEEICT),
Publication date: 2021/12/14
Publisher: IEEE
​
Contribution: Due to the immense progress of green energy technology, the popularity of electric vehicles (EVs) is increasing day by day. The rapid transition from an internal combustion engine-based vehicle to a battery-driven vehicle creates another issue which is the limited storage capacity of batteries. Researchers are working hard to improve the storage capacity of batteries through the use of advanced materials. Meanwhile, the accurate prediction of the driving range of EVs has become a topic of interest for researchers. In this paper, multiple regression machine learning algorithms are used to predict the electric vehicle range. Among the models, Multiple Linear Regression (MLR) gives the best R squared value of 0.973 and the lowest RMSE value of 39.67 in predicting the EV range. The result is compared with other machine learning models.
​
Google Scholar Citations: 4
​
Availability: Access Link
4. Electric Vehicle Driving Range Prediction: A deep Learning approach.
Authorship: First Author
Publication: Submitted to Journal of Energy Storage.
Publisher: Elsivier.
​
Contribution: The popularity of Electric vehicles (EVs) has increased rapidly as a result of their environmental impact, energy independence, sustainability, and environmental impact. However, the swift shift from traditional internal combustion engine vehicles to battery-powered ones brings forth a challenge the restricted storage capacity of batteries. To address this limitation, researchers are actively exploring innovative materials to enhance battery storage capabilities. Simultaneously, accurately predicting the driving range of EVs has emerged as a crucial area of interest for researchers. In this study, various deep-learning algorithms have been employed to forecast the electric vehicle range. Notably, the Neural Network (NN) model, featuring two hidden layers and utilizing the RMSProp optimizer delivers the most favorable results, achieving a Root Mean Squared Error (RMSE) of 9.32, Mean Absolute Error (MAE) of 6.81, and an impressive R2 score of 0.99. It is worth noting that employing the same NN architecture with the Adam optimizer yields a comparable R2 score but exhibits a slightly different performance, with an RMSE of 9.77 and an MAE of 8.10. The obtained results are meticulously compared with those
from various other machine learning and deep learning models in this paper.
5. Comprehensive Analysis of Soft-Robotics and Underwater Applications: Limitations, Current Challenges, and Future Perspectives.
Authorship: First Author
Contribution: In the field of Robotics, Soft Robotics has become a trending field due to its flexibility in comparison to rigid body Robotics. The application of underwater soft robotics gives more degree of freedom (DOF) to Marin environment exploration, navigation, and research. In this manuscript, a comprehensive analysis of Soft Robotics has been conducted in the realm of underwater robotics.
