Keynotes


Dr. Mahendra Gooroochurn

Faculty of Engineering, University of Mauritius

Dr. Mahendra Gooroochurn works as Senior Lecturer and is the Head of Department in the Mechanical & Production Engineering Department of the University of Mauritius. He is a certified Huawei AI Instructor and a Chartered Engineer registered with the Engineering Council of UK, an accredited green building design and construction professional registered with the USGBC, an Edge Expert registered with the International Finance Corporation (IFC), a WELL AP registered with International Well Building Institute (IWBI) and is a member with IET, IEEE and ASHRAE. He has research interests in developing intelligent and low-energy solutions for promoting sustainability in the built environment. He has been the Ellen McArthur Foundation Circular Economy Pioneer for Mauritius, the COP26/COP27 representative of Mauritius for the Association of Commonwealth Universities (ACU) Futures Climate Research Cohort and for the IVLP 2023 programme on energy crisis: working together for future generations.

Title: Developing AI-predictive models for supporting climate mitigation and adaptation solutions for the built environment

Abstract: The built environment has attracted high interest as a powerful lever to address the consequences of climate change, both from a mitigation and adaptation perspective, given that it encompasses several areas including energy, water, materials, transportation and human comfort and well-being. Several studies have shown the ill-preparedness of the existing building stock to predicted climate scenarios, meaning the indoor environment conditions is anticipated to degrade steadily as the effect of climate change worsens. As the world experiences extreme weather conditions such as heat waves, record summer temperatures and unprecedented high intensity short duration precipitation, adopting a passive building design paradigm centred on bioclimatic considerations to adapt to the local context is an unequivocal approach to achieve sustainable climate solutions. This presentation will give a brief overview of the circular economy framework developed by the Ellen McArthur Foundation and how it has been applied to develop the circular homes concept as a community climate engagement tool, which is used to illustrate its adaptation to the tropical context of Mauritius, and to show how AI predictive models can be used to modulate the performance of the underlying passive systems to achieve near optimum results with respect to the seasonal and non-seasonal changes in weather. Examples of passive systems designed from a Mechatronics perspective will be presented together with the AI design philosophy to provide directions for this active research area looking at improving the thermal comfort, energy and water performance of existing and new buildings using Industry 4.0.


Dr. Akihito Nakamura

University of Aizu, Japan

Dr. Akihitro Nakamura is currently a Professor in the School of Computer Science and Engineering, University of Aizu, JAPAN. He obtained his Ph.D degree in Computers and Systems Engineering from Tokyo Denki University, JAPAN, in 1994. From 1994 to 2015, he worked as a senior researcher at the National Institute of Advanced Industrial Science and Technology (AIST), JAPAN. His primary research interests are cybersecurity and distributed computing. He served as general chair for several international conferences, including IEEE Conference on Dependable and Secure Computing (DSC 2021), International Conference on Science of Cyber Security (SciSec 2022), ACM Asia Service Sciences and Software Engineering Conference (ASSE 2023), ACM International Artificial Intelligence and Blockchain Conference (AIBC 2023).

Title: A Heuristics and Machine Learning Hybrid Approach to Adaptive Cyberattack Detection

Abstract: Cybersecurity is more important now than ever and the damage has increased accordingly. One possible countermeasure is Intrusion Detection and Prevention System (IDPS) which enables detection of malicious activities in the network based on signature-matching and other detection methods. A signature is the recorded pattern of the specific attack. However, it occasionally misses malicious traffic or raises false alerts when the detection method is not carefully configured with the latest information. That is, it is prone to being false-positive or false-negative. This paper presents a highly accurate cyberattack detection method with automatic generation of tailored signatures and rapid response to emerging threats. We combine heuristics for known attacks and machine learning (ML) techniques to detect unforeseen attack patterns in traffic, i.e. a hybrid method. Rule-based judgment for heuristics and anomaly detection for ML are used, respectively. This study provides a novel approach to utilize ML method using a packet-to-image conversion technique. Network packet data are converted to images and image data are used for training and classification of attack patterns. By transforming the problem to anomaly detection in image data, the evaluation results revealed that the method has high accuracy

ACDSA


International Conference on Artificial Intelligence,
Computer, Data Sciences and Applications

Logo

Flag Counter

Contact

ECER Events
World Wide Commercial Building, No:72
Al Hilal, D Ring Road, Doha, Qatar
+974 72021173

copyright © acdsa.org