Best Paper Award
| Mercy Mulwa |
| Affiliation |
Jomo Kenyatta University of Agriculture and Technology (JKUAT) |
| Country |
Kenya |
| Scopus ID |
58922109600 |
| Documents |
1 |
| Citations |
1 |
| h-index |
16 |
| Subject Area |
Computer Science |
| Event |
International Research Excellence and Best Paper Awards |
Mercy Mulwa
Mercy Mulwa of Jomo Kenyatta University of Agriculture and Technology (JKUAT), Kenya is recognized with the Best Paper Award for research excellence in the field of Computer Science. The recognized research, titled “GMM-LIME explainable machine learning model for interpreting sensor-based human gait,” focuses on explainable machine learning techniques for interpreting sensor-based human gait data and improving the transparency and understanding of machine learning models.
Abstract
This article recognizes Mercy Mulwa for research excellence in Computer Science and for the paper titled “GMM-LIME explainable machine learning model for interpreting sensor-based human gait.” The research focuses on the application of explainable machine learning to sensor-based human gait analysis. By combining a Gaussian Mixture Model (GMM) approach with Local Interpretable Model-agnostic Explanations (LIME), the work addresses the need for greater interpretability in machine learning systems that analyze human movement data. The research contributes to the growing field of explainable artificial intelligence, machine learning interpretation, sensor-based computing, and human gait analysis.
Keywords
Explainable Machine Learning, GMM-LIME, Gaussian Mixture Model, LIME, Human Gait Analysis, Sensor-Based Gait Recognition, Explainable Artificial Intelligence, Machine Learning Interpretability, Sensor Data, Computer Science.
Introduction
Machine learning has become increasingly important for analyzing complex sensor data and identifying meaningful patterns in human movement. Human gait analysis is an important area of research because gait characteristics can provide valuable information for applications involving movement recognition, activity analysis, intelligent sensing, and human-centered computing.
The awarded paper, “GMM-LIME explainable machine learning model for interpreting sensor-based human gait,” addresses the challenge of understanding how machine learning models interpret sensor-based gait information. The integration of explainability techniques provides a pathway toward making machine learning predictions more understandable to researchers, practitioners, and end users.
Research Profile
Mercy Mulwa is affiliated with Jomo Kenyatta University of Agriculture and Technology (JKUAT), Kenya, and works within the broad field of Computer Science. The provided academic information identifies the researcher with Scopus Author ID 58922109600. The supplied profile information records 1 document, 1 citation, and an h-index of 16.
Research Contributions
The research makes a contribution to explainable artificial intelligence and sensor-based machine learning by focusing on the interpretation of human gait data. The use of GMM-LIME provides an explainability-oriented framework for examining machine learning behavior and identifying patterns that may influence model outputs.
Research Impact
The research has relevance to several areas of modern computing, including explainable AI, machine learning, sensor analytics, gait recognition, human activity analysis, and intelligent systems. Explainable models can help researchers better understand complex relationships within sensor-generated data and support the development of more transparent computational systems.
Award Suitability
The Best Paper Award recognizes research that demonstrates academic relevance, methodological value, originality, and contribution to its field. Mercy Mulwa’s research aligns with these objectives through its focus on GMM-LIME explainable machine learning for interpreting sensor-based human gait.
Conclusion
Mercy Mulwa represents research excellence in the field of Computer Science through the recognized paper “GMM-LIME explainable machine learning model for interpreting sensor-based human gait.” The research addresses an important intersection between sensor-based computing, human gait analysis, machine learning, and explainable artificial intelligence.
External Links
References
- Scopus Author Profile: Mercy Mulwa, Author ID 58922109600.
Scopus.https://www.scopus.com/pages/authors/58922109600
- Bet Paper Awards.
https://bestpaperawards.com/