Malika Doshanova
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Malika Doshanova has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Gulshaxarxon Ruziyeva
Tashkent State University of Economics
1 shared publication - Mirzayeva Nilufar
Department of Artificial Intelligence, Tashkent State University of Economics, Tashkent, Uzbekistan
1 shared publication - Rashida Pirova
Department of Applied Mathematics, Karshi State University, Karshi, Uzbekistan
1 shared publication
Latest Publications
- Open Access
- 8 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1021-1027
Research into methods for determining driver drowsiness
This paper discusses the expansion of the capabilities of vehicle driver drowsiness detection based on surveillance camera signals. To this end, features associated with driver blinking and yawning are extracted in experiments. Based on this dataset, a feature selection method is developed to detect driver state. The results obtained will help in the future to develop reliable driver drowsiness monitoring systems to prevent fatigue-related accidents. Modern driver fatigue monitoring systems that analyze driving performance to collect driver state information are also discussed. Such systems are capable of detecting drowsiness signs by evaluating steering behavior and warning the driver when drowsiness reaches a critical level. However, such systems do not have access to direct driver state data.
- 8 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1021-1027
Open AccessResearch into methods for determining driver drowsiness
This paper discusses the expansion of the capabilities of vehicle driver drowsiness detection based on surveillance camera signals. To this end, features associated with driver blinking and yawning are extracted in experiments. Based on this dataset, a feature selection method is developed to detect driver state. The results obtained will help in the future to develop reliable driver drowsiness monitoring systems to prevent fatigue-related accidents. Modern driver fatigue monitoring systems that analyze driving performance to collect driver state information are also discussed. Such systems are capable of detecting drowsiness signs by evaluating steering behavior and warning the driver when drowsiness reaches a critical level. However, such systems do not have access to direct driver state data.