Doctor Honoris Causa, Obuda University, Budapest
Founding Director, KEDRI and Professor Emeritus of Knowledge Engineering
Auckland University of Technology, Auckland, New Zealand
Visiting Professor IICT Bulgarian Academy of Sciences, Sofia, BG
Brain-inspired AI for multimodal and explainable modelling to predict individual health and welfare outcomes in a digital environment
The medical and health domains are now overwhelmed by the existence of multimodal data, such as genetic, neuroimaging, clinical, cognitive, ethnical, behavioural and many other, some of them collected as large longitudinal cohorts. The new trends in health, such as digital health and hospitals-with-no-walls, require new techniques to deal with this multimodal data at a personalised level and to explain their diagnosis or prognosis outcome. The talk presents a brain-inspired AI approach for predictive and explainable modelling of multimodal data to predict individual health and welfare outcomes. The models are based on brain inspired spiking neural neuronal network architectures (BI-SNN) that include other machine learning methods [1,2,3,4]. The inspiration comes from the brain, which can deal with multimodal sensory, emotional and other information at different and connected time scales. The talk discusses how multiple modalities of data can be integrated for a better outcome prediction and a better explainability of the models, showing the “hidden” dynamic interaction between the used modalities of data related to an individual. Referenced applications are in the areas of cognitive decline, dementia, psychosis, mental health. This approach could potentially lead to the creation of principally new “conscious” decision support systems [5], where systems take into account holistically many aspects of an individual health across different factors and time scales and also their consequences and relation to the environment and other individuals.
[1] N.Kasabov, NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data, Neural Networks, vol. 52, pp. 62-76, 2014.
[2] NeuCube: https://kedri.aut.ac.nz/neucube
[3] N.Kasabov, Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence, Springer, 2019, https://www.springer.com/gp/book/9783662577134 .
[4] Knowledgeengineering: https://www.knowlegeengineering.ai
[5] Conscium: https://www.conscium.com
Professor Nikola K Kasabov is a Life Fellow of IEEE, Fellow of the Royal Society of New Zealand, Fellow of the INNS College of Fellows, DVF of the Royal Academy of Engineering UK. He has Doctor Honoris Causa from Obuda University, Budapest. He is the Founding Director KEDRI and Professor Emeritus at the School of Engineering, Computing and Mathematical Sciences at Auckland University of Technology, New Zealand. He is also Visiting Professor at IICT Bulgarian Academy of Sciences and Dalian University, China. Kasabov is the Science Leader of a Data Science Project between New Zealand and Singapore (2020-2024). He is the Director of Knowledgeengineering.ai and member of the advisory board of Conscium.com. Kasabov is Past President of the Asia Pacific Neural Network Society (APNNS) and the International Neural Network Society (INNS). He has been a chair and a member of several technical committees of IEEE Computational Intelligence Society and Distinguished Lecturer of IEEE (2012-2014). He is Editor of Springer Handbook of Bio-Neuroinformatics, EiC of Springer Series of Bio-and Neuro-systems and co-EiC of the Springer journal Evolving Systems. He is Associate Editor of several other journals. Kasabov holds MSc in computer engineering and PhD in mathematics from TU Sofia, Bulgaria. His main research interests are in the areas of neural networks, intelligent information systems, soft computing, bioinformatics, neuroinformatics. He has published more than 700 publications, highly cited internationally. He has extensive academic experience at various academic and research organisations in Europe and Asia, including: TU Sofia Bulgaria; University of Essex UK; University of Otago, NZ; Shanghai Jiao Tong University and CASIA Beijing; ETH/University of Zurich. Kasabov has received a number of awards, among them: INNS Ada Lovelace Meritorious Service Award; NN journal Best Paper Award for 2016; APNNA ‘Outstanding Achievements Award’; INNS Gabor Award for ‘Outstanding contributions to engineering applications of neural networks’; EU Marie Curie Fellowship; Bayer Science Innovation Award; APNNA Excellent Service Award; RSNZ Science and Technology Medal; 2015 AUT NZ Medal; Medal “Bacho Kiro” and Honorary Citizen of Pavlikeni, Bulgaria; Honorary Member of the Bulgarian-, the Greek- and the Scottish Societies for Computer Science. More information of Prof. Kasabov can be found in: https://academics.aut.ac.nz/nkasabov .
Al-Khawarzmi Distinguished Professor, Electrical and Computer Engineering
King Abdullah University of Science and Technology
Saudi Arabia.
Towards connecting the remaining 3 billion
The transformative influence of Internet and Communication Technology (ICT) has reshaped society, touching every aspect from the economy to healthcare. As the widespread deployment of 5G continues, there is an on-going focus on the inception of the sixth generation (6G) of wireless communication systems (WCSs). Anticipated to shape the future of connectivity in the 2030s, 6G aims to deliver unparalleled communication services to meet the demands of hyper-connectivity.
While densely populated urban areas have traditionally been the primary beneficiaries of WCS advancements, the vision for 6G transcends city limits. Aligned with the United Nations’ sustainability goals for 2030, an important aspect of 6G endeavors to democratize the benefits of ICT, fostering global connectivity sustainably. This talk delves into this particular envisioned landscape of 6G, providing insights into the future of wireless communication and guiding research efforts towards sustainable, inclusive, and high-speed connectivity solutions for the future. Central to this discussion are two emerging technologies: Free Space Optics (FSO) and Non-Terrestrial Networks (NTN). These innovative solutions hold the promise of extending high-speed connectivity beyond urban hubs to underserved regions, fostering digital inclusivity and contributing to the development of remote areas. Through this exploration, we aim to convey the potential of 6G and its role in shaping a connected, sustainable future for all.
Mohamed-Slim Alouini was born in Tunis, Tunisia. He received the Ph.D. degree in Electrical Engineering from the California Institute of Technology (Caltech) in 1998. He served as a faculty member at the University of Minnesota then in the Texas A&M University at Qatar before joining in 2009 the King Abdullah University of Science and Technology (KAUST) where he is now the Al-Khawarizmi Distinguished Professor of Electrical and Computer Engineering and Holder of the UNESCO Chair on Education to Connect the Unconnected. Prof. Alouini is a Fellow of the IEEE and OPTICA (Formerly the Optical Society of America (OSA)). He is currently particularly interested in addressing the technical challenges associated with the uneven distribution, access to, and use of information and communication technologies in rural, low-income, disaster, and/or hard-to-reach areas.
Chairman, Department of Computer Science and Engineeering
University of Dhaka,
Bangladesh
Cross-Regional Online Food Delivery: Opportunities and Challenges
Online food delivery (OFD) represents a rapidly evolving e-business application that leverages cloud computing data centers, playing a crucial role in meeting the demands of urban lifestyles. With diverse order fulfillment features and increasing expectations for service quality, the task of effectively assigning riders for timely long-distance, cross-regional deliveries presents a significant engineering challenge. Previous studies often relied on traditional rider allocation methods that failed to account for varying capacities, or they utilized non-intelligent systems that did not adequately address fluctuating order demands and service delays. In this study, we introduce a robust Mixed Integer Linear Programming (MILP) optimization framework designed to minimize the total service time and delivery cost for cross-regional orders. This framework divides a large OFD area into multiple regions and utilizes both transfer vehicles and riders to optimize deliveries. To enhance the predictive accuracy of our model, we incorporate advanced machine learning techniques. Specifically, we employ the Long Short-Term Memory (LSTM) model to forecast regional order demands accurately, reflecting the dynamic nature of the marketplace. Additionally, Extreme Gradient Boosting (XGBoost) is tailored to dynamically predict travel times from restaurants to customer locations, facilitating more precise scheduling and resource allocation within the MILP framework. These machine-learning techniques significantly bolster the MILP framework by providing detailed, accurate predictions that improve decision-making processes and adaptability to real-time conditions. Acknowledging the complexity of this optimization problem, we further enhance our approach by integrating a meta-heuristic algorithm, Adaptive Large Neighbor Search (ALNS), which efficiently assigns orders to the appropriate transfer vehicles and riders within polynomial time. Our Cross Regional Online Food Delivery (XROFD) system is meticulously designed to optimize both customer satisfaction and rider incentives.
Dr. Md. Abdur Razzaque is a Professor and Chairman of the Department of Computer Science and Engineering at University of Dhaka. He received his BS in Applied Physics and Electronics and MS in Computer Science from the University of Dhaka, Bangladesh in 1997 and 1999, respectively. He obtained a PhD in Computer Engineering from Kyung Hee University, South Korea in August, 2009. He worked for Green University of Bangladesh as Pro Vice Chancellor, Dean of Faculty of Science and Engineering and Chairperson, Dept. of CSE during 2016-2021. He was a research professor, College of Electronics and Information, Kyung Hee University, South Korea during 2010-2011. He worked as a visiting professor in Stratford University, Virginia, USA in 2017. He is the director of Green Networking Research Group (http://cse.du.ac.bd/gnr) of the Dept. of CSE, DU. He has been promoting Outcome Based Education for Science and Engineering Faculties of leading universities of the country. He was the principal investigator of some national and international research projects funded by the Government of Bangladesh and the Information Society Innovation Fund (ISIF) Asia. His research interest is in the area of modeling, analysis, and optimization of wireless networking protocols and architectures, Mobile Crowdsourcing, Sensor Data Clouds, the Internet of Things, Edge Computing, etc. He has published 180+ research papers in peer-reviewed international conferences and journals. He is an Associate Editor of IEEE Access, editorial board member of the Journal of Networks and Applications (JNCA, Elsevier), and International Journal of Distributed Sensor Networks, General Chair of STI 2024-2019, TPC Chair of ICIET 2019-2018, TPC member of IEEE HPCC, ICOIN, SCALCOM, SKIMA, ICIEV, ADM, NSysS, ICACCI, etc. He is a senior member of IEEE, member of IEEE Communications Society, IEEE Computer Society, Internet Society (ISOC), Pacific Telecommunications Council (PTC), and KIPS. He chaired 2020 and 2021 Executive Committees for the IEEE Computer Society Bangladesh Chapter.
Graduate School of Life Science and Systems Engineering
Kyushu Institute of Technology,
Japan
How to Apply Activity Recognition and Care Forecasting Services in Elderly Care Domain?
In this talk, the challenges of human activity recognition and its application to elderly care / hospital domains are discussed. We firstly review the demand in elderly care and hospital domains including the productivity of care workers. Then we introduce several approaches to forecast the future and utilize them for improving productivity. We use various sensor data, video data, and care / medical records and integrate them. We also introduce several techniques to improve machine learning in such a domain, including enhancing the algorithm using large language models. Finally, we introduce the deployment challenges cooperating with a startup company.
Sozo Inoue is a full professor in National Kyushu Institute of Technology, Japan, and the Chief Technical Officer of AUTOCARE LLC. His research interests include human activity recognition with smart phones, and healthcare application of web/pervasive/ubiquitous systems. Currently he is working on applications of activity recognition and health forecasting for nursing care and medicine to hospitals and more than 50 nursing facilities using smartphones and IoT. Inoue has a Ph.D of Engineering from Kyushu University in 2003. After completion of his degree, he was appointed as an assistant professor in the Faculty of Information Science and Electrical Engineering at the Kyushu University, Japan. He then moved to the Research Department at the Kyushu University Library in 2006. Since 2009, he has been appointed as an associate professor in the Faculty of Engineering at Kyushu Institute of Technology, Japan, and moved to Graduate School of Life Science and Systems Engineering at Kyushu Institute of Technology in 2018, and appointed as a full professor from 2020 and a head of Care XDX Center in Kyushu Institute of Technology from 2022. Meanwhile, he was a guest professor in Kyushu University, a visiting professor at Karlsruhe Institute of Technology, Germany, in 2014, a special researcher at Institute of Systems, Information Technologies and Nanotechnologies (ISIT) during 2015-2016, and a guest professor at University of Los Andes in Colombia in 2019. He was a technical advisor of Team AIBOD Co. Ltd during 2017-2019, and a guest researcher at RIKEN Center for Advanced Intelligence Project (AIP) during 2017-2019. He was a director during 2020-2021 and is a senior member of the Information Processing Society of Japan (IPSJ), a member of the IEEE Computer Society, the ACM, the Institute of Electronics, Information and Communication Engineers (IEICE), the Japan Society for Fuzzy Theory and Intelligent Informatics, the Japan Association for Medical Informatics (JAMI), and the Database Society of Japan (DBSJ).
AI and Digital Health Technology, AI and Cyber Futures Institute,
Rural Health Research Institute,
Charles Sturt University,
Australia
Ai-Empowered Portable And Wearable Devices For Digital Health Care
Advancements in Artificial Intelligence (AI) are revolutionising digital health, offering unprecedented opportunities for automated, real-time monitoring, early diagnosis, and management of various health conditions.[1] However, there is a need for robust and explainable algorithms to integrate AI with portable and wearable devices to promptly, accurately, and automatically analyse data collected from these tools, make decisions, and generate reports [2]
Our research focuses on developing novel AI-enabled portable and wearable devices specifically designed for real-time monitoring and diagnosis of chronic conditions. These devices leverage advanced machine learning algorithms and sensor technologies based on the ECG, EMG, and EEG technologies to continuously collect and analyse health data, providing personalised insights and timely interventions. [3-8] We are also developing novel, robust, and explainable machine/deep-learning algorithms and software tools for analysing multimodal data (e.g., image, EEG, ECG, multi-omics) to identify accurate markers that could be used for diagnosing and predicting disease conditions. [9-11] These innovative methods and tools harness the power of AI to provide continuous health monitoring and early detection of potential health issues.
Our AI-driven portable devices and software tools can analyse and measure genetic, multi-omics, and physiological data such as heart rate, blood pressure, glucose levels, and physical activity. These devices can detect and track vital signs, anomalies, and predict health events such as falls, sleep apnoea, cardiovascular conditions, mental health, and remote patient monitoring. [3-10] Our developed decision support system can detect subtle changes and patterns in the data that may indicate the onset of health issues, providing timely alerts and recommendations to users and healthcare providers for informed decision-making.
The findings of our studies demonstrate that our developed methodologies, software systems, and AI-enabled portable and wearable devices have the potential to transform digital health by providing continuous, personalised healthcare solutions, ultimately improving patient care and health outcomes. This work underscores the importance of interdisciplinary collaboration in advancing the development of next-generation digital health technologies.
[1] Zhang, A., Xing, L., Zou, J., & Wu, J. C. (2022). Shifting machine learning for healthcare from development to deployment and from models to data. Nature Biomedical Engineering, 6(12), 1330-1345.
[2] Acosta, J. N., Falcone, G. J., Rajpurkar, P., & Topol, E. J. (2022). Multimodal biomedical AI. Nature Medicine, 28(9), 1773-1784.
[3] Anik, I. A., Kamal, A. H. M., Kabir, M. A., Uddin, S., & Moni, M. A. (2024). A Robust Deep-Learning Model to Detect Major Depressive Disorder Utilising EEG Signals. IEEE Transactions on Artificial Intelligence.
[4] Sutradhar, A., Al Rafi, M., Ghosh, P., Shamrat, F. J. M., Moniruzzaman, M., Ahmed, K., ... & Moni, M. A. (2023). An Intelligent Thyroid Diagnosis System Utilising Multiple Ensemble and Explainable Algorithms with Medical Supported Attributes. IEEE Transactions on Artificial Intelligence.
[5] Rumi, R. B., Paul, A. K., Alyami, S. A., & Moni, M. A. (2023). Multi-Disease Detection Using a Prism-Based Surface Plasmon Resonance Sensor: A TMM and FEM Approach. IEEE Transactions on NanoBioscience.
[6] Islam, M. S., Hasan, K. F., Sultana, S., Uddin, S., Quinn, J. M., & Moni, M. A. (2023). HARDC: A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention based dual structured RNN with dilated CNN. Neural Networks, 162, 271-287.
[7] Mim, T. R., Amatullah, M., Afreen, S., Yousuf, M. A., Uddin, S., Alyami, S. A., ... & Moni, M. A. (2023). GRU-INC: An inception-attention based approach using GRU for human activity recognition. Expert Systems with Applications, 216, 119419.
[8] Khatun, M. A., Yousuf, M. A., Ahmed, S., Uddin, M. Z., Alyami, S. A., Al-Ashhab, S., ... & Moni, M. A. (2022). Deep CNN-LSTM with self-attention model for human activity recognition using wearable sensor. IEEE Journal of Translational Engineering in Health and Medicine, 10, 1-16.
[9] Faruqui, N., Yousuf, M. A., Whaiduzzaman, M., Azad, A. K. M., Barros, A., & Moni, M. A. (2021). LungNet: A hybrid deep-CNN model for lung cancer diagnosis using CT and wearable sensor-based medical IoT data. Computers in Biology and Medicine, 139, 104961.
[10] Mashrur, F. R., Islam, M. S., Saha, D. K., Islam, S. R., & Moni, M. A. (2021). SCNN: Scalogram-based convolutional neural network to detect obstructive sleep apnea using single-lead electrocardiogram signals. Computers in Biology and Medicine, 134, 104532.
[11] Hossain, M. A., Islam, S. M. S., Quinn, J. M., Huq, F., & Moni, M. A. (2019). Machine learning and bioinformatics models to identify gene expression patterns of ovarian cancer associated with disease progression and mortality. Journal of biomedical informatics, 100, 103313.
Dr. Mohammad Ali Moni is a worldwide recognised leader in AI and Digital Health and one of the top 1% of highly cited researchers. He earned his PhD in Machine Learning and Data Science from Cambridge University, UK. Dr Moni is the Program Lead and Director of the Centre for AI & Digital Health Technology at Charles Sturt University. He is also a group leader and head of the AI & Digital Health Technology lab at the University of Queensland, Australia. Dr. Moni has received numerous prestigious fellowships and awards, including the USyd Vice-Chancellor Fellowship, UoW Distinguish Engineering technology fellowship, UQ academic awards, Ridley Ken Devis award, and Commonwealth Awards, and has held academic roles at top universities such as Cambridge, Oxford, UNSW and Sydney.
Dr. Moni is renowned for his groundbreaking contributions to AI and Digital Health Data Science, with over 300 peer-reviewed publications and more than 26,000 citations. His leadership in research programs, particularly in AI-driven health data applications, AI-enabled portable device development, and bioinformatics, has had a significant impact. He has managed large projects on big health datasets, developing machine learning and deep-learning models, and developing AI-empowered wear-able sensors for disease diagnostics and prediction, especially for complex and chronic diseases.
©Designed and Developed by NSTU