The paper introduces TimeHUT, a new method for learning time-series representations using hierarchical uniformity-tolerance balancing of contrastive representations. TimeHUT employs a hierarchical setup to learn both instance-wise and temporal information, along with a temperature scheduler to balance uniformity and tolerance. The method was evaluated on UCR, UAE, Yahoo, and KPI datasets, demonstrating superior performance in classification tasks and competitive results in anomaly detection.
This paper explores the use of deep learning for anomaly detection in sports facilities, with the goal of optimizing energy management. The researchers propose a method using Deep Feedforward Neural Networks (DFNN) and threshold estimation techniques to identify anomalies and reduce false alarms. They tested their approach on an aquatic center dataset at Qatar University, achieving 94.33% accuracy and 92.92% F1-score. Why it matters: The research demonstrates the potential of AI to improve energy efficiency and operational effectiveness in sports facilities within the GCC region.
Salem AlMarri, the first Emirati Ph.D. graduate from MBZUAI, developed a video anomaly detection (VAD) system for his thesis. The VAD system can detect subtle anomalies in video, such as suspicious interactions, to help police prevent crimes and save lives. AlMarri's work was carried out under the guidance of Karthik Nandakumar, Affiliated Associate Professor of Computer Vision at MBZUAI. Why it matters: This research showcases the potential of AI in enhancing public safety and security in the UAE, demonstrating practical applications of computer vision in law enforcement.
MBZUAI Associate Professor Mohammad Yaqub is focused on translating AI research into real-world healthcare solutions. His previous work includes the development of SanNav, an AI-based fetal anomaly detection system that became an FDA-approved product used by GE Healthcare and used on his own wife during pregnancy. Yaqub joined MBZUAI to help build a new model of AI research and education with a focus on interdisciplinary collaboration and industry partnerships. Why it matters: This highlights the UAE's growing focus on AI in healthcare and MBZUAI's role in bridging the gap between research and practical applications in the medical field.
MBZUAI Ph.D. graduate Hilal Mohammad Hilal AlQuabeh researched methods to improve the efficiency of machine learning algorithms, specifically focusing on pairwise learning and multi-instance learning. Pairwise learning teaches AI to make decisions by comparing options in pairs, useful for ranking and anomaly detection. Multi-instance learning involves learning from sets of data points, applicable in areas like drug discovery. Why it matters: Optimizing AI for low-resource environments expands its accessibility and applicability in critical sectors like healthcare and remote area operations.
A team of MBZUAI students won the Pioneers 4.0 Hackathon by developing an AI-based predictive maintenance solution using sensor data. The solution uses data preprocessing techniques and the Prophet model to identify anomalies in manufacturing, leading to energy savings and preventing sensor outages. The hackathon, organized by MoIAT and EDGE, involved 15 students from UAE universities. Why it matters: This highlights the practical application of AI skills being cultivated at UAE universities and their potential to address industrial challenges in line with the UAE's 4IR strategy.
An all-female team including two MBZUAI master's students won the WomenHackAI competition, presented by Siemens Female Data Science Network. The team developed an anomaly detector for financial time-series datasets, achieving 99% performance. The solution involved building models to analyze historical data and a GUI for real-time data upload and anomaly flagging. Why it matters: The recognition of MBZUAI students in an international competition highlights the growing talent pool in AI within the UAE and the university's role in fostering innovation.