جست‌وجوی استاد و پژوهشگر

• Data Mining
• Machine Learning
• Computer Vision
• +۵ مورد دیگر

Dr. Bin Liang is a Senior Lecturer at the University of Technology Sydney (UTS), working within the Faculty of Engineering and Information Technology and the Data Science Institute. He joined UTS in December 2018 as a Lecturer and was promoted to Senior Lecturer in July 2022, following his postdoctoral fellowship at Data61 (CSIRO). PhD in Computer Vision, Pattern Recognition, and Machine Learning from Charles Sturt University, Australia (2012-2015) Masters in Computer Science from Taiyuan University of Technology, China (2009-2012) BEng in Computer Science from Taiyuan University of Technology, China (2005-2009) Dr. Liang's research spans data mining, machine learning, computer vision, pattern recognition, and survival analysis, with a strong focus on practical applications in critical infrastructure. His work develops sophisticated machine learning frameworks for anomaly detection, failure prediction, and optimization in water infrastructure, flood mapping, and real estate appraisal. He has pioneered approaches that integrate graph neural networks with temporal analysis for pipe failure prediction and has made significant contributions to water quality optimization through data-driven methods. His research consistently bridges theoretical advancements with practical implementation in industry settings. His recent publications demonstrate a clear trajectory toward increasingly sophisticated models that capture complex temporal and spatial relationships in infrastructure data. There's a notable emphasis on multimodal learning approaches and domain generalization techniques that enhance model robustness across diverse application scenarios. His work on anomaly detection frameworks like MLAD shows innovation in grouping sensors by temporal characteristics for more accurate monitoring. 2022 – AWA R&D Excellence Award (NSW) 2022 – UTS Medal for Research Impact 2022 – Finalist for 2021-22 AWA Young Water Professional of the Year Award (NSW) 2020 – Finalist for the Best Paper Award of the ICARCV 2020 2019 – Industrial & Primary Industries Merit at the Victorian iAwards 2018 – Australian Museum Eureka Prize for Excellence in Data Science Dr. Liang actively supervises Masters Research and PhD students, focusing on data science applications for infrastructure management. His research has been supported through industry partnerships with water utilities and other infrastructure organizations, translating academic research into practical solutions that reduce water loss, improve infrastructure reliability, and enhance environmental sustainability. His work on pipe failure prediction and leak detection has directly contributed to operational improvements in water distribution networks. As a core member of the Data Science Institute at UTS, Dr. Liang collaborates with interdisciplinary teams working on data-driven solutions for urban infrastructure challenges. His research group focuses on developing scalable machine learning models that can be deployed in real-world settings, often working directly with industry partners to validate and implement their approaches. This industry-academia collaboration ensures that his research remains grounded in practical challenges while pushing the boundaries of data science methodology.

• Bayesian Statistics
• Approximate Bayesian Computation
• Statistical Modeling
• +۶ مورد دیگر

Christopher Drovandi is a Professor at Queensland University of Technology and a Chief Investigator in the Australian Research Council Centre of Excellence for Mathematical and Statistical Frontiers (ACEMS). His research spans statistical methodology development and applications across diverse fields including ecology, biomedicine, and environmental science. Dr. Drovandi's primary research interests focus on advancing Bayesian statistical methods, particularly in the areas of: Approximate Bayesian Computation (ABC) and likelihood-free inference Synthetic likelihood methods Sequential Monte Carlo algorithms Bayesian experimental design Statistical computing for complex models His recent work demonstrates a strong emphasis on addressing model misspecification in Bayesian inference, developing robust computational methods for intractable likelihoods, and applying advanced statistical techniques to solve real-world problems in ecology, biomedicine, and environmental science. Drovandi has made significant contributions to both the theoretical foundations and practical applications of modern Bayesian statistics. Dr. Drovandi has received research funding through multiple Australian Research Council grants and collaborates extensively with researchers across disciplines. His work has been published in top-tier statistical and interdisciplinary journals including the Journal of the American Statistical Association, Bayesian Analysis, and PLOS Computational Biology.