The increasing application of Artificial Intelligence (AI) in health and medicine has attracted a great deal of research interest in recent decades. This study aims to provide a global and historical picture of research concerning AI in health and medicine. A total of 27,451 papers that were published between 1977 and 2018 (84.6% were dated 2008–2018) were retrieved from the Web of Science platform. The descriptive analysis examined the publication volume, and authors and countries collaboration. A global network of authors’ keywords and content analysis of related scientific literature highlighted major techniques, including Robotic, Machine learning, Artificial neural network, Artificial intelligence, Natural language process, and their most frequent applications in Clinical Prediction and Treatment. The number of cancer-related publications was the highest, followed by Heart Diseases and Stroke, Vision impairment, Alzheimer’s, and Depression. Moreover, the shortage in the research of AI application to some high burden diseases suggests future directions in AI research. This study offers a first and comprehensive picture of the global efforts directed towards this increasingly important and prolific field of research and suggests the development of global and national protocols and regulations on the justification and adaptation of medical AI products.

No abstract

This work proposes deep network models and learning algorithms for unsupervised and supervised binary hashing. Our novel network design constrains one hidden layer to directly output the binary codes. This addresses a challenging issue in some previous works: optimizing non-smooth objective functions due to binarization. Moreover, we incorporate independence and balance properties in the direct and strict forms in the learning. Furthermore, we include similarity preserving property in our objective function. Our resulting optimization with these binary, independence, and balance constraints is difficult to solve. We propose to attack it with alternating optimization and careful relaxation. Experimental results on three benchmark datasets show that our proposed methods compare favorably with the state of the art.

Abstract-While much of multiview video coding focuses on the rate-distortion performance of compressing all frames of all views for storage or non-interactive video delivery over networks, we address the problem of designing a frame structure to enable interactive multiview streaming, where clients can interactively switch views during video playback. Thus, as a client is playing back successive frames (in time) for a given view, it can send a request to the server to switch to a different view while continuing uninterrupted temporal playback. Noting that standard tools for random access (i.e., I-frame insertion) can be bandwidth-inefficient for this application, we propose a redundant representation of I-, P-, and "merge" frames, where each original picture can be encoded into multiple versions, appropriately trading off expected transmission rate with storage, to facilitate view switching. We first present ad hoc frame structures with good performance when the view-switching probabilities are either very large or very small. We then present optimization algorithms that generate more general frame structures with better overall performance for the general case. We show in our experiments that we can generate redundant frame structures offering a range of tradeoff points between transmission and storage, e.g., outperforming simple I-frame insertion structures by up to 45% in terms of bandwidth efficiency at twice the storage cost.Index Terms-Media interaction, multiview video coding, video streaming.

We investigate coding tools for interactive multiview streaming (IMVS), where clients interactively request desired views for successive video frames, and in response the server sends the appropriate pre-compressed video data to the clients. Solution based on using only I-frames to support view switching would incur high transmission cost, while for that based on using only P-frames to encode every possible traversal, although it can minimize transmission cost, prohibitive server's storage may be required. Therefore, efficient solutions for IMVS need to consider the trade-off between transmission and storage cost. In this paper, we study the potential use of distributed source coding (DSC) in IMVS. Specifically, we propose two DSC constructions that could achieve good transmission-storage trade-offs. Central to these constructions is a method that can efficiently encode the least significant bits (LSB) of a frame to be decoded, leading to competitive storage and transmission requirements. Experiment results demonstrate these constructions compare favorably to existing tools, and could be valuable for interactive multiview streaming.

No abstract

We have directly observed the Anderson localized wave functions in three dimensions in a new class of photonic band gap systems. Such systems are networks made of one-dimensional waveguides. By adopting a simple scattering geometry in a unit cell, we are able to obtain large photonic band gaps. In the presence of defects or randomness, we have systematically studied the structures of transmission and the localized wave functions inside a gap. The effects due to absorption are investigated. Excellent quantitative agreements between theory and experiments have been obtained. [S0031-9007(98) PACS numbers: 41.20.Jb In the past decade, the localization of classical waves in random media has been under intensive studies [1]. Unlike electrons, the localization of classical waves is purely a result of multiple scatterings in a random environment and free from the complications arising from interaction effects. However, due to the Rayleigh scattering at low frequencies, it is more difficult to localize classical waves than to localize electrons. In 3D, waves can be localized only in certain windows in the intermediate frequency range with a minimum dielectric contrast [2]. It has been suggested that waves are more easily localized inside a gap or pseudogap of a photonic band gap (PBG) material [3]. The PBG material in its own right is of great interest and has important implications in both fundamental science and technological applications [4]. The localization of electromagnetic waves has been observed in 1D and 2D PBG materials [5,6]. For 3D systems, efforts have been focused only on wave localization in random media. The effects arising from wave localization have been reported in microwave experiments [7]. Nevertheless, a direct interpretation of localization was complicated by the presence of large absorption. Very recently, direct evidence of light localization has been reported in strong scattering media of semiconductor powders based on the size dependence of the transmission coefficient [8]. These important developments lead us to question if one can directly observe Anderson localized wave functions in 3D. For this purpose, like earlier investigations in 2D [6], we need to investigate the strongly localized states inside the gap of a PBG system, where the localization length is short. In addition, a direct measurement of the 3D wave function should be allowed in such systems.To meet these two requirements, we propose a new class of PBG systems here. Such systems are networks connected by segments of 1D waveguides [9]. There are two important advantages in such systems. First, strong scattering can be easily introduced in a unit cell to produce large full gaps in any dimension. Thus, unlike usual PBG systems, our systems do not require a material with a large dielectric constant. Second, the wave function at each node is physically accessible so that 3D localized wave functions can be probed.In our study, the coaxial cable was adopted as the 1D waveguide. The 3D network considered was in a diamond structure...

No abstract