Background: Regulation of temperature is clinically important in the care of neonates because it has a significant impact on prognosis. Although probes that make contact with the skin are widely used to monitor temperature and provide spot central and peripheral temperature information, they do not provide details of the temperature distribution around the body. Although it is possible to obtain detailed temperature distributions using multiple probes, this is not clinically practical. Thermographic techniques have been reported for measurement of temperature distribution in infants. However, as these methods require manual selection of the regions of interest (ROIs), they are not suitable for introduction into clinical settings in hospitals. Here, we describe a method for segmentation of thermal images that enables continuous quantitative contactless monitoring of the temperature distribution over the whole body of neonates. Methods: The semantic segmentation method, U-Net, was applied to thermal images of infants. The optimal combination of Weight Normalization, Group Normalization, and Flexible Rectified Linear Unit (FReLU) was evaluated. U-Net Generative Adversarial Network (U-Net GAN) was applied to thermal images, and a Self-Attention (SA) module was finally applied to U-Net GAN (U-Net GAN + SA) to improve precision. The semantic segmentation performance of these methods was evaluated. Results: The optimal semantic segmentation performance was obtained with application of FReLU and Group Normalization to U-Net, showing accuracy of 92.9% and Mean Intersection over Union (mIoU) of 64.5%. U-Net GAN improved the performance, yielding accuracy of 93.3% and mIoU of 66.9%, and U-Net GAN + SA showed further improvement with accuracy of 93.5% and mIoU of 70.4%. Conclusions: FReLU and Group Normalization are appropriate semantic segmentation methods for application to neonatal thermal images. U-Net GAN and U-Net GAN + SA significantly improved the mIoU of segmentation.

Japan was hit by typhoon Hagibis, which came with torrential rains submerging almost eight-thousand buildings. For fast alleviation of and recovery from flood damage, a quick, broad, and accurate assessment of the damage situation is required. Image analysis provides a much more feasible alternative than on-site sensors due to their installation and maintenance costs. Nevertheless, most state-of-art research relies on only ground-level images that are inevitably limited in their field of vision. This paper presents a water level detection system based on aerial drone-based image recognition. The system applies the R-CNN learning model together with a novel labeling method on the reference objects, including houses and cars. The proposed system tackles the challenges of the limited and wild data set of flood images from the top view with data augmentation and transfer-learning overlaying Mask R-CNN for the object recognition model. Additionally, the VGG16 network is employed for water level detection purposes. We evaluated the proposed system on realistic images captured at disaster time. Preliminary results show that the system can achieve a detection accuracy of submerged objects of 73.42% with as low as only 21.43 cm error in estimating the water level.

Robust and accurate indoor localization has been the goal of several research efforts over the past decade. Toward achieving this goal, WiFi fingerprinting-based indoor localization systems have been proposed. However, fingerprinting involves significant effort—especially when done at high density—and needs to be repeated with any change in the deployment area. While a number of recent systems have been introduced to reduce the calibration effort, these still trade overhead with accuracy. This article presents LiPhi++ , an accurate system for enabling fingerprinting-based indoor localization systems without the associated data collection overhead. This is achieved by leveraging the sensing capability of transportable laser range scanners to automatically label WiFi scans, which can subsequently be used to build (and maintain) a fingerprint database. As part of its design, LiPhi++ leverages this database to train a deep long short-term memory network utilizing the signal strength history from the detected access points. LiPhi++ also has provisions for handling practical deployment issues, including the noisy wireless environment, heterogeneous devices, among others. Evaluation of LiPhi++ using Android phones in two realistic testbeds shows that it can match the performance of manual fingerprinting techniques under the same deployment conditions without the overhead associated with the traditional fingerprinting process. In addition, LiPhi++ improves upon the median localization accuracy obtained from crowdsourcing-based and fingerprinting-based systems by 284% and 418%, respectively, when tested with data collected a few months later.

Unfortunately, many persons are injured or killed during disasters. The problems of paper triage tags, which are widely used at disaster scenes, include an inability to show the current priorities of casualties and a failure to collect the physiological conditions of the casualties. To save lives, this paper proposes an electronic triage system that consists of two types of electronic triage tags and an electronic triage server. The electronic triage tag continuously monitors the vital signs of casualties and transmits them to the electronic triage server, and the electronic triage system shows the current priorities of the casualties. Experimental results show that our proposed electronic triage system can save more lives than paper triage tags.

In this paper, we propose an efficient data exchange method for acquiring local traffic information where we use inter-vehicle ad-hoc communication with queries. In the proposed approach, each vehicle disseminates traffic information of its neighborhood and relays it within a few square kilometers. Traffic information of distant areas can be obtained by issuing queries and propagating them using inter-vehicle ad-hoc communication. This makes the time necessary for acquiring neighboring traffic information rather short, nevertheless we can still keep acquisition time of distant traffic information reasonable. The proposed data dissemination protocol CRCP has an autonomous packet collision avoidance mechanism by sensing data dissemination from neighboring vehicles. In this paper, we use VPSQ over CRCP as diseminated data selection. We have evaluated the performance of our proposed approach in a simulator, using realistic traffic models obtained from Toyota Central R&D Lab., Inc. Simulation results reveal the usefulness of the proposed approach.