This paper focuses on room access management based on the received signal strength indicator (RSSI) at two different points using two monitoring devices from smartphones. A server with a wireless LAN access point (AP) continuously sends an echo request packet to every smartphone connected to the AP, and the RSSI of the echo reply packet from the smartphones is monitored by two monitoring devices at two different points. The RSSI characteristics are that the RSSI becomes higher as the user approaches the monitoring devices and lower as the move away from them. Applying machine learning using the RSSI characteristics, we estimate the room access information of users concerning entering, staying in, or leaving the room. The proposed method does not require any special application software and user operations. Because the RSSI is monitored at two different points, our proposed method can handle various user behaviors. As a result, our proposed method achieves a high estimation accuracy of 94.44%.

抄録全体を表示

This paper evaluates the bluetooth low energy (BLE) positioning systems using the sparse-training data through the comparison experiments. The sparse-training data is extracted from the database including enough data for realizing the highly accurate and precise positioning. First, we define the sparse-training data, i.e., the data collection time and the number of smartphones, directions, beacons, and reference points, on BLE positioning systems. Next, the positioning performance evaluation experiments are conducted in two indoor environments, that is, an indoor corridor as a one-dimensionally spread environment and a hall as a twodimensionally spread environment. The algorithms for comparison are the conventional fingerprint algorithm and the hybrid algorithm (the authors already proposed, and combined the proximity algorithm and the fingerprint algorithm). Based on the results, we confirm that the hybrid algorithm performs well in many cases even when using sparse-training data. Consequently, the robustness of the hybrid algorithm, that the authors already proposed for the sparse-training data, is shown.

抄録全体を表示

During the period from sowing and planting to harvesting, outdoor crops are directly affected by the natural environment, including wind, rain, frost, and sunlight. Under such circumstances, vegetables change their growth conditions, shape, and flexibility daily. We aimed to develop an agricultural work-support robot that automates monitoring, cultivation, disease detection, and treatment. In recent years, many researchers and venture companies have developed agricultural harvesting robots. In this study, instead of focusing on intensive harvesting operations, we focused on daily farm operations from the beginning of cultivation to immediately before harvest. Therefore, gripping and cutting are considered basic functions that are common to several routine agricultural tasks. To find the assumed objects from a camera image with a low computational load, this study focuses on branch points to detect and identify even if the stems, lateral branches, and axillary buds are swaying in the wind. A branch point is a characteristic part close to the working position, even when the wind blows. Therefore, we propose a method to detect the assumed branch points simultaneously and divide each branch point into the main stem, lateral branch, and axillary bud. The effectiveness of this method is demonstrated through experimental evaluations using three types of vegetables, regardless of whether their stems are swaying.

抄録全体を表示

Active learning has been gradually focused on in recent years and introduced in various education fields because it gives better learning experience and outcomes than conventional lecture style approach. In this active learning, the quality of interaction between students, teacher and students is critically important because it decides the outcomes. Therefore, it is necessary to evaluate the interaction properly at real time and improve it. In this study, we measured and analyzed the body movement of students in group work using the sensors on smartphone. Also, we evaluated the outcomes and subjective communication quality of group work. By analyzing these three relations, there are positive correlations between the amount of body movement and the outcomes, also the evaluation of communication of group work. These results show that it is possible to evaluate the learning activity of students at real time in group work by using smartphones.

抄録全体を表示

近年の冬期歩行者転倒事故の増加により，冬期歩行空間の転倒危険度を把握することの重要性は増しつつある．一方で，冬期歩行空間の転倒危険度を定量的，リアルタイムかつ広域にわたり簡便に評価する手法は確立されていない．本研究では上記課題を解決するために，スマートフォン搭載加速度センサにより歩行挙動を計測し転倒の危険性を定量的に示す指標（歩行安定度）を求める手法を開発した．また，様々な路面状態下で被験者実験を行い，歩行安定度と路面状態およびスリップ発生状況の関係について検証した． 検証の結果，歩行安定度は路面状態の悪化およびスリップ発生回数の増加に伴い低下し，この傾向は被験者の年齢や性別などの属性によらず現れたことから本手法による冬期歩行空間の転倒危険度を定量的に評価できる可能性があることが示された．

抄録全体を表示

With the increasing spread of smartphones and wearable devices equipped with various sensors, human activities, biometric information, and surrounding situations can be recognized. The process of human activity recognition must construct a model that has learned annotated sensor data, i.e., ground truth, labels, or answer activity, in advance. Therefore, a large and diverse set of annotated data is required to improve and evaluate model performance. It is difficult to judge a user's situation even after observing acceleration data; thus, it is necessary to annotate the collected acceleration data. In this paper, we propose a method to estimate user and device situations from the user's response to a notification generated by a device, e.g., a smartphone. The user and device situations are estimated from the user's response time to the notification and the device's acceleration values. An estimation result with high confidence is given to the sensor data as an annotation. Increasing the frequency of notifications, response to the notifications can be used as a sensor. We assume that acceleration values are affected by a user and device situation when the device notifications are taken instantly after its generation. The system pursues a high precision of estimation by selecting input acceleration data based on the interaction to the notification so that the estimations can be used as annotations. Through an evaluation experiment, for seven types of annotation classes, an average precision of 0.769 and 0.963 for user-independent experiments and user-dependent experiments were achieved, respectively. We also tested the proposed method in a natural environment, where 25 correct annotations were given for 45 responses to notifications, no annotations were given for 19 responses, and only one incorrect notification was observed.

抄録全体を表示