The recent COVID-19 pandemic has made it extremely important to avoid crowded environments. In light of this, we are developing a congestion measurement system utilizing IoT technology, in which the congestion state of a given location is estimated by counting the number of WiFi Probe Request messages and BLE exposure notification messages sent from smartphones and laptops. Our congestion measurement system, however, suffers from an unstable measurement problem because the number of WiFi and BLE messages is highly dependent on the environment in which our system is deployed. This paper presents a congestion measurement system employing an automatic parameter adjuster that accurately estimates the number of people in various target locations. The parameters are automatically adjusted based on the seating capacity and area size of the target environment, as well as information gathered from a sensor which is designed to collect and analyze WiFi and BLE messages collected in a university cafeteria.

日本各地において，「居心地が良く歩きたくなるまちなか」を目指した街路運用の検討が進んでいる．本来は車を締め出し歩行者専用空間にすることが理想だが，反対の声も強く実現しにくいのが現状である．よって，車を締め出さずとも歩きやすい街路空間を形成する必要がある．そこで，本研究では，現存する商業地区内街路のうち歩車混合空間に着目し，すれ違い時の回避行動において歩車間に発生している相互作用を明らかにすることを目的とする．歩車混合空間にてビデオを撮影し，両者の1/30秒ごとの座標から回避行動に至るまでの位置関係や速度，車種などを記録した．それらのデータを分析した結果，歩車は互いの回避行動の様子を見ながら最低限必要な側方距離を確保することが明らかとなった．

The analysis of the movement of people in a shopping area with the aim of improving marketing is an important research topic. Many conventional methods are dependent on the density of people in the area, which is easily estimated by counting the people entering or exiting the area. However, a high density does not always mean an increase in activity, as certain people are simply passing the area at a given time. The primary goal of this study was to introduce a set of indicators for measuring the bustle of the area, which we call "Nigiwai," from pedestrian movement by using an analogy from classical kinematics. Such indicators can be used to measure the impact of promotional events and to optimize the design of the area. Our novel indicators were evaluated with simulated pedestrian scenarios and were demonstrated to distinguish shopping scenarios from those in which people move around without shopping successfully, even when the latter scenarios had much higher densities. The indicators were computed solely from the pedestrian trajectory, which can easily be obtained from ordinary sensors using deep learning-based techniques. As a demonstration with real data, we applied our method to a video of a street and provided a visualization of the indicators.

Due to the spread of COVID-19, we are desired to avoid crowded places including public transportation. Kyushu University has the largest campus in Japan, called "Ito campus", and the population there is about 20,000 in which 23% of students and 46% of staff use a bus for reaching the campus. The lectures in the first half of 2020 have been conducted online, but we plan to resume face-to-face lectures gradually. At that time, we expect the bus stops and buses to be crowded, especially during rush hour. In this paper, we introduce a system, called Itocon, to visualize the human congestion of bus stops around the campus. Itocon aggregates the sensing data from various sensors deployed around the target bus stops, and calculate and visualize the congestion degrees in real-time. Itocon is developed as a web application to avoid requesting the application install. We hope all the people who use a bus change their moving time based on the congestion information for avoiding human crowds. We explain the details and the future prospects of Itocon.

Background The efficacy of vision screening for adults has not been well established. The present study aimed to investigate the prevalence of vision-threatening ocular diseases, including glaucoma, among subjects who participated in specific health checkups in Japan. Methods This cross-sectional study included 1360 individuals who underwent comprehensive ophthalmic examinations at 16 ophthalmology clinics located in three municipalities. We surveyed the study participants using a questionnaire. The participants also underwent visual acuity and refraction tests, intraocular pressure tests, slit-lamp microscopy, fundus examinations, fundus photography, optical coherence tomography, and static perimetry. Results The mean age of the subjects was 63.7 ± 8.7 years (range, 40–74 years). Among the 1360 participants, 168 (12.4%) were diagnosed with glaucoma and 33 (2.4%) with preperimetric glaucoma. Cataracts were seen in 741 participants (54.5%), and 77 (5.7%) were diagnosed with clinically significant cataracts. Retinal diseases included macular degeneration (1.2%), diabetic retinopathy (1.0%), chorioretinal atrophy (0.5%), macular epiretinal membrane (2.9%), branch retinal vein occlusion (0.7%), and others (2.0%). Regarding the type of glaucoma, 93.5% of participants with glaucoma were diagnosed with open-angle glaucoma in a broad sense (81.0% with normal-tension glaucoma and 12.5% with primary open-angle glaucoma). Multivariate analysis showed that male sex, age, systemic comorbidities, and myopia were significant risk factors for open-angle glaucoma. Conclusion Many adults with ocular diseases were screened by ophthalmic checkups. The addition of simultaneous ophthalmic checkups to specific health checkups could be an effective measure for the prevention of visual impairment in the older population.

Our objective is to achieve a city where everyone can move safely and comfortably by developing and implementing ICT-based mobile support system at the actual transport hub. Our system uses cameras installed at the transport hub to detect people who have difficulty moving, and notifies this information to the transportation staff in real time to help them move more smoothly. This system makes it possible to aggregate and provide information on places that is useful for COVID-19 measures, such as measuring the congestion of places and the social distances of the people who gather there.

This paper tackles the problem of discovering subtle fall risks using skeleton clustering by multi-robot monitoring. We aim to identify whether a gait has fall risks and obtain useful information in inspecting fall risks. We employ clustering of walking postures and propose a similarity of two datasets with respect to the clusters. When a gait has fall risks, the similarity between the gait which is being observed and a normal gait which was monitored in advance exhibits a low value. In subtle fall risk discovery, unsafe skeletons, postures in which fall risks appear slightly as instabilities, are similar to safe skeletons and this fact causes the difficulty in clustering. To circumvent this difficulty, we propose two instability features, the horizontal deviation of the upper and lower bodies and the curvature of the back, which are sensitive to instabilities and a data preprocessing method which increases the ability to discriminate safe and unsafe skeletons. To evaluate our method, we prepare seven kinds of gait datasets of four persons. To identify whether a gait has fall risks, the first and second experiments use normal gait datasets of the same person and another person, respectively. The third experiments consider that how many skeletons are necessary to identify whether a gait has fall risks and then we inspect the obtained clusters. In clustering more than 500 skeletons, the combination of the proposed features and our preprocessing method discriminates gaits with fall risks and without fall risks and gathers unsafe skeletons into a few clusters.

This paper proposes new system that generates 3D models of cattle from their multiple depth-maps for estimating their BCS (body condition scores). Various works of the agriculture are almost tedious and the use of advanced ICT is possible to improve such works. Currently, the authors have been studying such an ICT agriculture research whose targets are beef cattle. The goal of this study is to capture 3D shape information of cattle accurately for the estimation of their BCS. BCS are important data for checking whether cattle grow appropriately. However, it is very difficult to capture such information even using a commercial 3D scanner because cattle are animals and always moving. Then, the authors propose the use of multiple depth-maps of a cow simultaneously captured by multiple Kinect sensors at a different viewpoint to generate its 3D model. The problems in this case are the calibration of Kinect sensors and the synchronization of their depth-maps capturing. This paper describes how the authors solve these problems, and it shows several results of actually obtained 3D models of cattle using the proposed system.

This paper proposes prediction methods for people flows and anomalies in people flows on a university campus. The proposed methods are based on deep learning frameworks. By predicting the statistics of people flow conditions on a university campus, it becomes possible to create applications that predict future crowded places and the time when congestion will disappear. Our prediction methods will be useful for developing applications for solving problems in cities.

In this paper, a new compact deep neural network (DNN) architecture based on lifting complex wavelets is proposed. The proposed DNN architecture (LcwtNet) is composed of multiple layers in addition to a CNN architecture. Complex wavelet and lifting wavelet layers are introduced as the lower layers of LcwtNet, which can reduce the number of parameters while maintaining high performance similar to that of CNN models. In simulations, the effectiveness of LcwtNet is demonstrated by several test results using the MNIST dataset.

This paper presents 3D model generation of black cattle using multiple RGB cameras for their BCS. The use of advanced ICT has a certain possibility to improve various agricultural activities. The authors have such a project whose targets are beef cattle. The goal of the project is to capture 3D shape information of black cattle for the estimation of their body condition scores (BCS). Cattle are always moving because they are animals. Therefore, it is very difficult to capture their body shape information even using a commercial 3D scanner. Another reason is that the color of beef cattle is almost black and then a commercial 3D scanner like a laser range finder cannot be used. So, as the first trial, the authors used multiple RGB cameras to capture RGB images of a cow, generated manually its silhouette images, and employed Shape-from-Silhouette(SfS) method to generate its 3D model. The authors took multiple RGB camera images of cows in a natural environment and generated their 3D models. From the generated 3D models of cows, it can be found that it is possible to estimate the weight of each cow correctly if its accurate silhouette images are generated manually. Here, the problem is how the accurate silhouette images can be obtained automatically in a natural environment. From several experiments, the authors conclude it is impossible. Therefore, the authors propose the use of new method based on multicolor attributed voxels instead of SfS method. This paper clarifies the availability of the new method by showing several experimental results.

Understanding the states or emotions of learners at a lecture is expected to be useful for improving lecture quality. In our work, we tried to recognize two activities of learners by using their brain wave data to estimate their states. While existing analyses of brain wave data for activity recognition used standard bands such as α and β as features, we used other bands with higher and lower frequencies to compensate for the coarseness of simple electroencephalographs. We conducted experiments on recognizing two activities performed by six subjects with brain wave data captured by a simple electroencephalograph. We applied a support vector machine to 8-dimensional vectors corresponding to eight bands of the brain wave data. The results show that using the eight bands yielded higher accuracy compared than that obtained with the standard features based on at most four bands.

Recently, with the development of graphics devices and the widely use of 3D geometrical sensors, the quantity of multimedia data including 3D model data has become increasing. Therefore, the technological needs for searching those data to create multimedia contents are expanding. In this paper, the authors propose a 3D model data retrieval system using KAZE image feature that accepts 2D images as queries for the search. The paper explains a system overview and the details of its functionalities. It also shows experimental results. From the results, the proposed system as a 3D model search system that accepts a 3D model as a query indicates better performance than D2 method which is one of the popular 3D model search methods although it indicates not so good performance when accepts 2D images as the query.

In this paper, we propose a method for forecasting power demand using meteorological data and human congestion information. In an energy management system (EMS), accurate power demand forecasts reduce the cost on the demand side and stabilize the power supply on the supply side. Although previously observed power consumption and meteorological data are conventionally used for forecasting power demand, it is difficult to estimate power demand in cases that are greatly affected by the behavior of people. Power consumption may vary according to the behavior of just one person, depending on the size of the community. In this study, the power demands of multiple buildings on the campus of a university are estimated accurately by analyzing heterogeneous data obtained with various sensors. Experiments show that using meteorological data and human congestion improves results. Consequently, we confirm that a cyber physical system can play an important role in the construction of an EMS.

This paper presents 3D model generation of cattle by shape-from-silhouette method for ICT agriculture. The use of advanced ICT has any possibility to improve various agricultural activities. The authors have such a project whose targets are beef cattle. The goal of the project is to capture 3D shape information of cattle for the estimation of their body condition scores (BCS). Cattle do not stop moving because they are animals. Therefore, it is very difficult to capture their body shape information even using a commercial 3D scanner. Another reason is that the color of beef cattle is almost black and then a commercial 3D scanner like a laser range finder cannot be used. The authors use multiple RGB cameras to capture silhouette images of a cow and employ shape-from-silhouette method to generate its 3D model. Actually, the authors have taken multiple RGB camera images of cows and generated their 3D models. And then, it can be found that the generated 3D models' volumes of cows have positive correlation with their weights. This result says that the estimation of cows' weights is possible from multiple RGB camera images of them.

Understanding the states of learners at a lecture is expected to be useful for improving the quality of the lecture. This paper is trying to recognize the activities of learners by their brain wave data for estimating the states. In analyses on brain wave data, generally, some particular bands such as $$\alpha $$ and $$\beta $$ are considered as the features. The authors considered other bands of higher and lower frequencies to compensate for the coarseness of simple electroencephalographs. They conducted an experiment of recognizing two activities of five subjects with the brain wave data captured by a simple electroencephalograph. They applied support vector machine to 8-dimensional vectors which correspond to eight bands on the brain wave data. The results show that considering multiple bands yielded high accuracy compared with the usual features.

Understanding the states of learners at a lecture is useful for improving the quality of the lecture. A video camera with an infrared sensor Kinect has been widely studied and proved to be useful for some kinds of activity recognition. However, learners in a lecture usually do not act with large moving. This paper evaluates Kinect for use of activity recognition of learners. The authors considered four activities for detecting states of a learner, and collected the data with the activities by a Kinect. They applied K-nearest neighbor algorithm to the collected data and obtained the accuracy 0.936 of the activity recognition. The result shows that Kinect is applicable also to the activity recognition of learners in a lecture.