Search

Human-centirc artificial intelligence: Frontier research and building industry capability Chin-Teng Lin, Distinguished Professor from the University of Technology Sydney, Human-centric AI Centre, AAII, explores human-centric AI, focusing on frontier research & building industry capability. Distinguished Professor Chin-Teng Lin is a pioneer, inventor and world leader in computational intelligence and co-founder of the GrapheneX-UTS Human-centric AI Centre (HAI) at the University of Technology Sydney, Australia. For the past three decades, he has significantly advanced artificial intelligence (AI), brain-computer interfaces and human-AI teaming across theory, methodology and applications. Here, he provides an overview of his frontier research in combining human intelligence with AI to enable humans to make better decisions in complex, stressful situations and what it takes to translate research into tangible products and services. He also highlights the importance of ethical considerations when teaming humans with robots.

The long short-term memory (LSTM) network underpins many achievements and breakthroughs especially in natural language processing fields. Essentially, it is endowed with certain memory capabilities to boost its performance. Currently, the volume and speed of big data generation are increasing exponentially, and such data require efficient models to acquire memory augmented knowledge. In this paper, we propose a memory augmented convolutional neural network (MACNN) with utilizing self-organizing maps (SOM) as the memory module. First, we depict the potential challenge about just applying solely a convolutional neural network (CNN) so as to highlight the advantage of augmenting SOM memory for better network generalization. Then, we dissert a corresponding network architecture incorporating memory to instantiate the distributed knowledge representation machanism, which tactically combines both SOM and CNN. Each component of the input vector is connected with a neuron in a two-dimensional lattice. Finally, we test the proposed network on various datasets and the experimental results reveal that MACNN can achieve competitive performance, especially for bioimages datasets. Meanwhile, we further illustrate the learned representations to interpret the SOM behavior and to comprehend the achieved results, which indicates that the proposed memory-incorporating model can exhibit the better performance.

Vehicle accidents are the primary cause of fatalities worldwide. Most often, experiencing fatigue on the road leads to operator errors and behavioral lapses. Thus, there is a need to predict the cognitive state of drivers, particularly their fatigue level. Electroencephalography (EEG) has been demonstrated to be effective for monitoring changes in the human brain state and behavior. Thirty-seven subjects participated in this driving experiment and performed a perform lane-keeping task in a visual-reality environment. Three domains, namely, frequency, temporal, and 2-D spatial information, of the EEG channel location were comprehensively considered. A 4-D convolutional neural-network (4-D CNN) algorithm was then proposed to associate all information from the EEG signals and the changes in the human state and behavioral performance. A 4-D CNN achieves superior forecasting performance over 2-D CNN, 3-D CNN, and shallow networks. The results showed a 3.82% improvement in the root mean-square error, a 3.45% improvement in the error rate, and a 11.98% improvement in the correlation coefficient with 4-D CNN compared with 3-D CNN. The 4-D CNN algorithm extracts the significant theta and alpha activations in the frontal and posterior cingulate cortices under distinct fatigue levels. This work contributes to enhancing our understanding of deep learning methods in the analysis of EEG signals. We even envision that deep learning might serve as a bridge between translation neuroscience and further real-world applications.

The automatic feature-extraction capability of deep neural networks (DNNs) endows them with the potential for analyzing complicated electroencephalogram (EEG) data captured from brain functionality research. This article investigates the potential coherent correspondence between the region of interest (ROI) for DNNs to explore, and the ROI for conventional neurophysiological-oriented methods to work with, as exemplified in the case of a working memory study. The attention mechanism induced by global average pooling (GAP) is applied to a public EEG data set of a working memory test to unveil these coherent ROIs via a classification problem. The results show the potential alignment of the ROIs from different discipline methods, and consequently asserts the confidence and promise of utilizing DNNs for EEG data analysis.

Multitasking has become omnipresent in daily activities and increased brain connectivity under high workload conditions has been reported. Moreover, the effect of fatigue on neural activity has been shown in participants performing cognitive tasks, but the effect of fatigue on different cognitive workload conditions is unclear. In this article, we investigated the effect of fatigue on changes in effective connectivity (EC) across the brain network under distinctive workload conditions. There were 133 electroencephalography (EEG) data sets collected from 16 participants over a five-month study, in which high-risk, reduced, and normal states of real-world fatigue were identified through a daily sampling system. The participants were required to perform a lane-keeping task (LKT) with/without multimodal dynamic attention-shifting (DAS) tasks. The results show that the EC magnitude is positively correlated with the increased workload in normal and reduced states. However, low EC was discovered in the high-risk state under high workload conditions. To the best of our knowledge, this investigation is the first EEG-based longitudinal study of real-world fatigue under multitasking conditions. These results could be beneficial for real-life applications, and adaptive models are essential for monitoring important brain patterns under varying workload demands and fatigue states.