Best Paper Competition

Wai Yie Leong (INTI International University, Malaysia); Yuan Zhi LEONG and Wai San Leong (Schneider Electric Singapore Pte. Ltd., Singapore)

Electroencephalography (EEG) is a powerful tool for monitoring brain activity and understanding cognitive processes. In recent years, the integration of Artificial Intelligence (AI) techniques has revolutionized EEG signal extraction and analysis, enabling deeper insights into brain function and facilitating applications in various domains such as healthcare, neuroscience, and human-computer interaction. This paper provides a comprehensive technical review of AI methods for EEG extraction, processing, and analysis. It discusses the challenges and opportunities associated with EEG data, reviews state-of-the-art AI algorithms for EEG feature extraction and classification, and explores emerging trends and future directions in the field.

Mehbas F Nawal, Gayan Brahmanage and Henry Leung (University of Calgary, Canada)

In this paper, we propose a Simultaneous Localization and Mapping approach (RGB-PD SLAM, where PD stands for Predicted Depth) that uses scale-consistent depth predictions from a neural network to tackle scale ambiguities in monocular SLAM systems. We propose an additional loss term to constrain the neural network in producing more scale-consistent depth maps over a sequence of images in an unsupervised manner. However, as the network learns from unlabeled monocular images, the predictions still suffer from per-frame uncertainty. As a result, we introduce a novel optimization step using sparse bundle adjustment (SBA) in the SLAM framework to handle noises in the predictions.

Wai-Chi Fang (National Yang Ming Chiao Tung University, Taiwan)

Over the past decade, the significance and appli- cation of deep learning have surged, showcasing their ability to surpass domain experts in prediction accuracy within short time- frames. However, their computational efficiency relies on intricate algorithmic complexity, necessitating substantial resources. To address this, researchers have developed hardware platforms to accelerate these algorithms. This paper explores various approaches to enhance computational efficiency, including lever- aging parallel computing, optimizing data flow, employing loop tiling techniques, and implementing data quantization. Addition- ally, learnable adaptive quantization and neural network spar- sification analysis are proposed to further refine computational demands. The paper adopts a strategy incorporating optimal parallel computing, data flow optimization, and tiling techniques to design processing elements for AI accelerators. The efficacy of these techniques is validated through the implementation of Long-term Recurrent Convolutional Networks (LRCN) in Electroencephalography-based affective computing applications.

Jinlong Zhu, Keigo Sakurai, Ren Togo, Takahiro Ogawa and Miki Haseyama (Hokkaido University, Japan)

We present a novel approach for automatic multitrack music generation utilizing a Generative Adversarial Network (GAN) framework integrated with Transformer architecture. While previous research has successfully produced extended multitrack compositions, they often exhibit an unnatural quality. This is caused by unusual instrument performance, unconventional composition, and inconsistencies in scale and groove, all contributing to the feeling of absence of the human feeling in generated music. In our method, we incorporate a Transformer-based discriminator specifically designed to assess the human-like qualities of the generated music tracks. Experimental results have demonstrated the effectiveness of our approach.

Shu-Cheng Hsu (National Taiwan University of Science and Technology, Taiwan); Chih-Hao Chuang and Hong-Yi Chien (Feng Chia University, Taiwan); Chien-Yu Chen (National Taiwan University of Science and Technology, Taiwan); Ching-Chen Hsu (Holovision Inc, Taiwan)

The COVID-19 pandemic has accelerated digitization and emphasized non-contact measures, providing an opportunity for floating display technology in diverse applications. This study, utilizing dihedral corner reflector arrays (DCRA) and infrared sensing, achieved touchless floating display buttons, presenting new possibilities for digital operations and medical facilities.