This paper presents a smart battery management system for portable devices using deep learning techniques to enhance battery life. The research employs machine learning models built in Python using Scikit-learn and TensorFlow to estimate State of Charge (SoC), State of Health (SoH), and Remaining Useful Life (RUL) with high accuracy. Evaluation using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared metrics showed significant improvements over traditional Battery Management System methods.
@article{kone2024smartbattery,title={Smart Battery Management System for Portable Devices to Enhance Battery Life Based on Machine Learning},author={Kone, Sambou},journal={International Journal of Innovative Research in Technology},volume={10},number={11},year={2024},month=apr,publisher={IJIRT},doi={10.64643/IJIRTV10I11-163173-459},issn={2349-6002},url={https://doi.org/10.64643/IJIRTV10I11-163173-459},}
Minor Project
Cotton Wool Detection for Diabetic Retinopathy
Sambou Kone and others
Minor Project Research at ECE Department, Jain University, Apr 2024
A computer vision project focused on detecting cotton wool spots in retinal images for early detection of diabetic retinopathy, a major cause of vision loss in diabetic patients. The project employs image processing and machine learning techniques to identify and classify cotton wool spots in fundus images.
@article{kone2024cottonwool,title={Cotton Wool Detection for Diabetic Retinopathy},author={Kone, Sambou and others},year={2024},month=apr,journal={Minor Project Research at ECE Department, Jain University},institution={Jain University, Bangalore},supervisor={Chethan, G. S.},}
Presentation on the future of Electronics and Communication Engineering in the year 2030, focusing on emerging technologies, trends, and their implications for the field.
@inproceedings{kone2023ece2030,title={Electronics And Communication Engineering - 2030},author={Kone, Sambou},year={2023},month=mar,event={Jain University's ECE Department Avalanche Club, Bangalore},}
2019-2020
Master Thesis
Human Voice Recognition System Based on Feed Forward Neural Networks for Platforms
Sambou Kone
National School of Engineering ENI ABT, Bamako, Mali, Mar 2019-2020
Implementation of human voice recognition system using Python, PyTorch, and TensorFlow with feed-forward neural networks trained on MFCC and FBANK features extracted using NumPy and Librosa. The system’s performance was assessed through accuracy, F1-score, and Equal Error Rate (EER), demonstrating significant improvements over traditional voice recognition methods.
@mastersthesis{kone2019voicerecognition,title={Human Voice Recognition System Based on Feed Forward Neural Networks for Platforms},author={Kone, Sambou},year={2019-2020},school={National School of Engineering ENI ABT, Bamako, Mali},supervisor={Sidibe, Abdoulaye},}
