Dear Colleagues,

While “Artificial Intelligence” (AI) becomes the mainstream of application techniques breakthrough, its impacts to our future life is unprecedented. AI becomes increasingly important for understanding complex data and offering intelligent processing to foster innovative business applications, self-driving cars, voice recognition, drug design, and new medical applications in the future. Recently, new technologies with explainable AI, such as federated learning, meta-learning, active learning, multi-task learning, inductive graph learning, transfer learning, and ensemble learning, have emerged and attracted considerable interests from both academic and industrial communities. Meanwhile, the rising prominence of AI has dramatically transformed a variety of domains. For intelligent wireless networks, due to privacy constraints and limited communication resources, distributed multi-agent reinforcement learning and federated learning are employed to solve complex convex and nonconvex optimization problems and collaboratively learn shared prediction models for user clustering, resource management, and interference alignment. For smart automatic driving, robust deep learning models that are capable to avoid adversarial examples are developed to analyze world state representations and behavior models, as well as forecast and control the car trajectory according to various sensors (e.g., cameras, HD maps, inertial measurement units, wheel encoders, LiDAR).

Moreover, for immersive VR and AR, Generative Adversarial Networks (GANs) have been widely adopted to address scene segmentation, depth estimation, realistic 3D modeling, image fusion, whereas effective gaze estimation and prediction algorithms are designed to reduce the computation time for immersive view rendering. For health and digitized education, AI is also the cornerstone to infer indicators of disease activities for early detection of emerging outbreaks, and to facilitate knowledge tracing for online courses. To support the above applications, domain-specific software and hardware co-design in DNN accelerators is crucial to boost the performance and energy efficiency for various computation and memory-intensive tasks, making these models usable on smaller devices at the edge of the Internet. Researchers and practitioners are jointly devoting efforts to develop solutions for related problems using various AI methods. Therefore, this special issue aims to bring together recent advances in AI for various domains to share new findings among the community and bridge the gaps between research and practice.

The topics of interest include, but are not limited to:

• Artificial Intelligence Learning Theory and Statistics
• AI for Healthcare and Bioinformatics
• Artificial Intelligence on Education
• AIoT Applications
• AR/VR and Human Computer Interaction
• Autonomous Driving
• Algorithms and Computation Theory
• Big Data
• Image Processing, Computer Graphics, and Multimedia Technologies
• Intelligent Network
• Intelligent Manufacturing
• Web Intelligence and Social Network
• Cyber security
• Computer Architecture, Embedded Systems, SoC, and VLSI/EDA to support AI
• Parallel, Distributed, and Cloud/Edge Computing for AI

Dr. Pau-Choo Chung
Dr. Gary G. Yen
Dr. De-Nian Yang
Dr. Meng-Hsun Tsai
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• artificial intelligence
• autonomous driving
• cyber security
• e-health and bioinformatics
• human computer interaction
• intelligent manufacturing
• Internet of Things
• web intelligence