ObjectiveThe suicide rate in South Korea was the second highest among the Organization for Economic Cooperation and Development countries in 2017. The purpose of this study is to understand the characteristics of people who died by suicide in Korea from 2013–2017 and to better prevent suicide. MethodsThis study was performed by the Korea Psychological Autopsy Center (KPAC), an affiliate of the Korea Ministry of Health and Welfare. According to the Korea National Statistical Office, the number of suicide victims nationwide was estimated to reach about 70,000 from 2013 to 2017. Comprehensive suicide records from all 254 police stations in South Korea were evaluated by 32 investigators who completed a 14-day didactic training program. Then, we evaluated the characteristics of suicide victims in association with disease data from the National Health Insurance Database (NHID), which is anonymously linked to personal information of suicide victims. ResultsThirty-one of 254 police stations in the Seoul metropolitan area were analyzed by August 10, 2018. Findings showed that the characteristics of suicide victims differed according to the nature of the region. ConclusionOur results suggest that different strategies and methods are needed to prevent suicide by regional groups.

It seems as though progressively more people are in the race to upload content, data, and information online; and hospitals haven’t neglected this trend either. Hospitals are now at the forefront for multi-site medical data sharing to provide ground-breaking advancements in the way health records are shared and patients are diagnosed. Sharing of medical data is essential in modern medical research. Yet, as with all data sharing technology, the challenge is to balance improved treatment with protecting patient’s personal information. This paper provides a novel split learning algorithm coined the term, “multi-site split learning”, which enables a secure transfer of medical data between multiple hospitals without fear of exposing personal data contained in patient records. It also explores the effects of varying the number of end-systems and the ratio of data-imbalance on the deep learning performance. A guideline for the most optimal configuration of split learning that ensures privacy of patient data whilst achieving performance is empirically given. We argue the benefits of our multi-site split learning algorithm, especially regarding the privacy preserving factor, using CT scans of COVID-19 patients, X-ray bone scans, and cholesterol level medical data.

Machine learning requires a large volume of sample data, especially when it is used in highaccuracy medical applications. However, patient records are one of the most sensitive private information that is not usually shared among institutes. This paper presents spatio-temporal split learning, a distributed deep neural network framework, which is a turning point in allowing collaboration among privacysensitive organizations. Our spatio-temporal split learning presents how distributed machine learning can be efficiently conducted with minimal privacy concerns. The proposed split learning consists of a number of clients and a centralized server. Each client has only has one hidden layer, which acts as the privacypreserving layer, and the centralized server comprises the other hidden layers and the output layer. Since the centralized server does not need to access the training data and trains the deep neural network with parameters received from the privacy-preserving layer, privacy of original data is guaranteed. We have coined the term, spatio-temporal split learning, as multiple clients are spatially distributed to cover diverse datasets from different participants, and we can temporally split the learning process, detaching the privacy preserving layer from the rest of the learning process to minimize privacy breaches. This paper shows how we can analyze the medical data whilst ensuring privacy using our proposed multi-site spatio-temporal split learning algorithm on Coronavirus Disease-19 (COVID-19) chest Computed Tomography (CT) scans, MUsculoskeletal RAdiographs (MURA) X-ray images, and cholesterol levels.INDEX TERMS Split learning, deep learning, deep neural network, privacy preserving, data protection

Monocular depth estimation is very challenging because clues to the exact depth are incomplete in a single RGB image. To overcome the limitation, deep neural networks rely on various visual hints such as size, shade, and texture extracted from RGB information. However, we observe that if such hints are overly exploited, the network can be biased on RGB information without considering the comprehensive view. We propose a novel depth estimation model named RElative Depth Transformer (RED-T) that uses relative depth as guidance in self-attention. Specifically, the model assigns high attention weights to pixels of close depth and low attention weights to pixels of distant depth. As a result, the features of similar depth can become more likely to each other and thus less prone to misused visual hints. We show that the proposed model achieves competitive results in monocular depth estimation benchmarks and is less biased to RGB information. In addition, we propose a novel monocular depth estimation benchmark that limits the observable depth range during training in order to evaluate the robustness of the model for unseen depths.

Experience sharing among multiple users in virtual reality (VR) is one of the key applications in next generation wireless systems. In this VR application, one object can be reproduced as a virtual object based on recorded/captured multiple real-time images from multiple observation points. At this time, VR applications require a lot of bandwidth to provide seamless services to users in wireless links, and thus, a certain level of data rates should be maintained. As the number of users increases, the server allocates more data rates to users on top of the limited bandwidth in wireless networks. At this time, users who utilize the VR streaming services will suffer from a lower quality, due to the limited bandwidth. This paper reports the measurement study and also analyzes the fluctuations in terms of the data rates as the number of users increases while sharing point cloud information in real-time authorized reality environments over IEEE 802.11ac wireless networks. Moreover, it measures and analyzes fluctuations in terms of frames-per-second and Jitters, which are practical quality reduction indicators.