Inspirit AI Projects Catalog

This study explores the use of artificial intelligence (AI) for fault prediction in electric vehicles (EVs) to reduce unexpected breakdowns and improve reliability. Using sensor, driving, and diagnostic data from 2020–2024, the research found that tree-based models, particularly Decision Tree and Random Forest, achieved over 90% predictive accuracy, demonstrating AI’s potential to enable proactive maintenance and enhance user confidence in EV technology.

Unplanned breakdowns in electric vehicles (EVs) pose challenges such as costly repairs, unexpected downtime, and reduced user confidence. To address this issue, this research investigates whether artificial intelligence (AI) can perform fault prediction and improve EV reliability. Using the EV Sensors, Driving Pattern & Diagnostics dataset (2020–2024), which contains information on battery performance, motor readings, driving behaviors, and diagnostic trouble codes (DTCs), we tested four machine learning models: Random Forest, Decision Tree, Support Vector Regression (SVR), and Linear Regression. Results showed that the Decision Tree and Random Forest models outperformed the others, achieving over 90% predictive accuracy compared to less than 70% for SVR and Linear Regression. These findings indicate that tree-based model approaches are effective in capturing nonlinear patterns between sensor data and breakdown events. Overall, this study highlights the potential of AI to provide early warnings of EV failures, enable proactive maintenance strategies, and strengthen consumer trust in EV technology.

Explore More!

Allez Go: AI Fencing Referee

Technology in fencing is generally an underdeveloped field and automated referees present potentially significant benefits to the sport. Automated referees will offer a more consistent call compared to a group of human referees with slightly different interpretations of the fencing rules.

Jason M.

Mentored by Anna Orosz

DeepSolar Bangladesh: A Novel Convolutional Neural Network (CNN) Architecture for the Detection of Solar Panels from Low Resolution Satellite Imagery in Developing Countries

Due to its environmental benefits and decreasing costs, the supply of solar energy is growing at an accelerating pace globally. However, the decentralised nature of solar makes it difficult to keep track of the different photovoltaic (PV) systems deployed across a country. There is a critical need for highly accurate, comprehensive national databases of solar systems, which would allow policymakers, researchers, and the government to study socioeconomic trends in solar deployment. Manual surveys have shown to be inaccurate. The 2018 DeepSolar study by Yang et. al developed a deep-learning framework and national solar deployment database for the US using high-quality satellite imagery, which proved to be a much more efficient and accurate approach. However, satellite imagery in developing countries such as Bangladesh is of much lower resolution and quality, and performed poorly with the original DeepSolar model by Yang et. al. Our study highlights the implementation of a novel convolutional neural network (CNN) in detecting solar panels through low resolution Google Static Maps API satellite imagery data.

Khondoker F.

Mentored by Barbie Duckworth

Using Machine Learning to Detect Parkinson’s Disease Through Drawing Data

This research explores the use of machine learning models, particularly logistic regression, on patients' spiral and wave drawings as an accessible and cost-effective method to improve Parkinson's disease diagnosis, achieving an accuracy of 91%, precision of 92%, and recall of 89%.

Katie Y.

Mentored by Sriram Hathwar

About Inspirit AI

Home Team Impact

Programs

Live Online Learn More Apply Now

Join Our Mailing List

Stay up to date with all things Inspirit AI!

Terms and conditions | Refund policy | Privacy policy

Research Paper