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.
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.
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.
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.
KAUST and the Saudi Electricity Company (SEC) collaborated to reduce non-technical losses in the Saudi power sector using machine learning. KAUST Visualization Core Lab (KVL) developed models using five years of SEC billing data from the Riyadh area to predict electricity usage and detect anomalous billing transactions. SEC estimates it could recover at least 73,000,000 SAR in lost revenue by correcting anomalies identified by KAUST models. Why it matters: This partnership demonstrates the potential of AI to address inefficiencies and fraud in critical infrastructure sectors in Saudi Arabia.
A new mini-batch strategy using aggregated relational data is proposed to fit the mixed membership stochastic blockmodel (MMSB) to large networks. The method uses nodal information and stochastic gradients of bipartite graphs for scalable inference. The approach was applied to a citation network with over two million nodes and 25 million edges, capturing explainable structure. Why it matters: This research enables more efficient community detection in massive networks, which is crucial for analyzing complex relationships in various domains, but this article has no clear connection to the Middle East.
This paper introduces DetectLLM-LRR and DetectLLM-NPR, two novel zero-shot methods for detecting machine-generated text using log rank information. Experiments across three datasets and seven language models demonstrate improvements of up to 3.9 AUROC points over state-of-the-art methods. The code and data for both methods are available on Github.