Title: LISTEN Project: Situation-Awareness based on the Analysis of Speech and Environmental Sounds
Khan Muhammad (S’16–M’18, SM’22) received his Ph.D. in Digital Contents from Sejong University, Republic of Korea in February 2019. He was an Assistant Professor in the Department of Software, Sejong University, from March 2019 to February 2022. He is currently the Director of the Visual Analytics for Knowledge Laboratory (VIS2KNOW Lab) and an Assistant Professor (Tenure-Track) with the Department of Applied AI, School of Convergence, College of Computing and Informatics, Sungkyunkwan University, Seoul, Republic of Korea. His research interests include intelligent video surveillance, information security, video summarization, and smart cities. He has registered 10 patents and contributed 220+ papers in peer-reviewed journals and conference proceedings in his research areas. His contributions have received 15250+ citations to date, with an H-index of 67. He is an Associate Editor/Editorial Board Member for more than 14 journals. He is among the most highly cited researchers in 2021 and 2022 according to the Web of Science (Clarivate).
The conference talk will introduce the LISTEN Project, an innovative initiative employing speech and environmental sound analysis to enhance situation awareness, particularly in fraud detection for security transformation. It will outline the project’s background and explore its key modules: Gender Recognition, Age Prediction, and Speech Emotion Recognition, showcasing their role in decoding nuanced auditory information for holistic context understanding. The talk will emphasize the fusion of module outputs through reasoning techniques, spotlighting LISTEN’s comprehensive approach and its capacity to comprehend the interplay between speech and environmental sounds. Ultimately, the presentation will underscore LISTEN’s pivotal role in advancing situational awareness through cutting-edge technology, offering attendees insights into its diverse applications and significance in tackling contemporary security challenges.
Prof. Farman Ali
Title: Transportation Sentiment Analysis using Fuzzy Ontology and Machine Learning
Farman Ali is currently working as an Assistant Professor in the Department of Software, Sejong University, South Korea. He received his B.S. degree in computer science from the University of Peshawar, Pakistan, in 2011, an M.S. degree in computer science from Gyeongsang National University, South Korea, in 2015, and a Ph.D. degree in information and communication engineering from Inha University, South Korea, in 2018. He worked as a Post-Doctoral Fellow at the UWB Wireless Communications Research Center, Inha University, from September 2018 to August 2019. He has registered over 4 patents and published more than 90 research articles in reputable international conferences and journals. His research interests include sentiment analysis, Intelligent transportation system, data science, text mining, recommendation system, healthcare monitoring system, ontology, fuzzy logic, and type-2 fuzzy logic, artificial intelligence, and deep learning. He serves as an Associate Editor for international journals, including CSSE-Computer Systems Science and Engineering, and Frontiers in Big Data.
Traffic congestion is rapidly increasing in urban areas, particularly in mega cities. Intelligent Transportation Systems (ITSs) use sensors to capture information and then utilize it to address this problem. In addition, people are using sensors-based transport applications to predict traffic flow. Unfortunately, these sensor-based devices are expensive and need maintenance and replacement. In addition, these devices are not suitable enough in terms of monitoring an entire transportation system and delivering emergency services when needed. Social networks can play an important role in providing a new approach to collect information regarding mobility and transportation services. To study this information, sentiment analysis can make decent observation to support ITS for examining traffic control and management systems. However, the text of social networks is unstructured, and it is the biggest challenging task for sentiment analysis to extract accurate knowledge from it. In addition, topic modeling and word representation are other problems in sentiment analysis. In this talk, I will overview this research area and present a novel mechanism to tackle some of the aforementioned challenges with the goal of improving the performance of transportation sentiment analysis using both the fuzzy ontology and machine learning techniques. Finally, future directions in this area will be discussed.