FCSIT Researchers at the Jelinek Summer Workshop on Speech and Language Technology 2023, France The annual Jelinek Summer Workshop on Speech and Language Technology (JSALT) 2023, organized by John Hopkins University’s Center for Language and Speech Processing, currently running on its 30th edition in France this year, saw a team of four researchers from the Faculty of Computer Science and Information Technology, UNIMAS, as part its international team of participants chosen from a highly-competitive selection process. The UNIMAS team, consisting of Dr Sarah Flora Samson Juan, Dr Suhaila Saee, Mohd Zulhafiz Rahim and Muhammad Abdullah Yusof, spent 6 weeks from 26 June to 4 August in the city of Le Mans in northwestern France to undergo this intensive research program, working closely with experts and fellow specialists in the field of speech and natural language processing to tackle the field’s challenges that have not yet been thoroughly investigated. At JSALT2023 the UNIMAS team worked on the topic of explainability for diarization, focusing on Sarawak Malaysia language data. The Sarawak Malay language is considered an under resourced language, in which a language has limited amount of linguistic data, resources, and tools. Diarization is a the process of partitioning an audio stream ...

By Unit Penjenamaan, FSKTM

By employing an agent-based model, researchers can analyze crowd behavior and improve evacuation procedures in educational environments.

Safety during emergencies is of paramount importance, this is particularly true especially in densely populated educational environments.

Understanding and predicting individual behaviour during such instances can greatly increase the effectiveness of evacuation procedures. Traditionally, live drills and physical experiments have been the go-to methods for this purpose.

However, these practices can be time-consuming, expensive, and incapable of capturing the full breadth of possible human behaviours.

At the Faculty of Computer Science and Information Technology (FCSIT) at UNIMAS, researchers led by Hamizan Sharbini are turning to agent-based models—a type of computer simulation—as a solution.

These simulations mirror the behaviour of individuals within a crowd, functioning like a 2D particle agents where each agent can react independently and make its own decisions.

In the face of an emergency, such as a fire alarm ringing, swift and safe evacuation of all occupants is vital. In these simulations, the agents represent the students who must understand the evacuation protocol for such emergencies during the learning process.

The agent-based model considers a variety of factors that ...