Maiya Hori

Bio: Maiya Hori is an academic researcher from Kyushu University. The author has contributed to research in topics: Facial expression & Rendering (computer graphics). The author has an hindex of 4, co-authored 35 publications receiving 81 citations. Previous affiliations of Maiya Hori include Nara Institute of Science and Technology & Tottori University.

Real-Time Learning Analytics Dashboard for Students in Online Classes

Abstract: In recent years, online classes have been increasingly conducted in various situations. However, in these classes, especially non-face-to-face and large-scale ones, it is more difficult for teachers and students to understand the status of the class during a lecture. To address this issue, we propose a real-time learning analytics dashboard that provides summarized information on teachers’ instruction and students’ learning activities during lectures. In this article, we introduce the real-time learning analytics dashboard and report its effectiveness through experiments in an online class at our university.

Generation of Facial Expression Emphasized with Cartoon Techniques Using a Cellular-Phone-Type Teleoperated Robot with a Mobile Projector

Abstract: We propose a method for generating facial expressions emphasized with cartoon techniques using a cellular-phone-type teleoperated android with a mobile projector. Elfoid is designed to transmit the speaker’s presence to their communication partner using a camera and microphone, and has a soft exterior that provides the look and feel of human skin. To transmit the speaker’s presence, Elfoid sends not only the voice of the speaker but also emotional information captured by the camera and microphone. Elfoid cannot, however, display facial expressions because of its compactness and a lack of sufficiently small actuator motors. In this research, facial expressions are generated using Elfoid’s head-mounted mobile projector to overcome the problem. Additionally, facial expressions are emphasized using cartoon techniques: movements around the mouth and eyes are emphasized, the silhouette of the face and shapes of the eyes are varied by projection effects, and color stimuli that induce a particular emotion are added. In an experiment, representative face expressions are generated with Elfoid and emotions conveyed to users are investigated by subjective evaluation.

A mixed reality telepresence system with limited DOF motion base and immersive display

Abstract: This paper describes a mixed reality (MR) telepresence system for a ride to provide users with a highly realistic sensation. To make a realistic scene in a virtual environment, it is necessary to combine visual information with a reproduction of the forces which a user experiences in the real environment. This paper proposes an MR telepresence system that presents a realistic image and an inertial force sensation using an immersive display and a motion base with limited degrees of freedom. In our approach, the realistic image is acquired with an omnidirectional camera and the inertial force is generated virtually by a combination of the acceleration of gravity and a video effect. In experiments, a prototype system has been proven to produce a highly realistic sensation in various environments.

Correlation between Coulomb stress imparted by the 2011 Tohoku-Oki earthquake and seismicity rate change in Kanto, Japan

Abstract: We show that the seismicity rate increase in the Kanto region around Tokyo following the 2011 Tohoku-Oki earthquake (M w9.0) was well correlated with the static increases in the Coulomb failure function ( ∆CFF) transferred from the Tohoku-Oki earthquake sequence. Because earthquakes in the Kanto region exhibit various focal mechanisms, the receiver faults for the ∆CFF were assumed to be reliable focal mechanism solutions of ̃3,000 earthquakes compiled from three networks (F-net, JMA network, and MeSO-net). The histograms of ∆CFF showed that more events in the postseismic period had positive ∆CFF values than those in the preseismic period (2008 April 1 2011 March 10). Among the 928 receiver faults showing the significant ∆CFF with absolute values≥ 0.1 bars in the preseismic period, 717 receiver faults (77.3 %) indicated positive ∆CFF. On the contrary, 1,334 (88.2 %) out of 1,513 receiver faults indicated positive ∆CFF in the postseismic period. We confirmed that the result is similar for the longer preseismic period, between 1997 October 1 and 2011 March 10. To test the significance of the difference in the distribution of ∆CFF between preseismic and postseismic periods, we used a Monte Carlo method with bootstrap resampling. As a result, the ratio of positive ∆CFF randomly resampled from∆CFF values in the preseismic period never exceeded 83.1%, even after 10,000 iterations. This supports the findings of Toda & Stein [2013]; however, our calculation is more reliable than theirs because we used a much larger number of focal mechanisms compiled from the three networks. It also proves that the static stress changes transferred from the Tohoku-Oki earthquake sequence are responsible for the changes in the seismicity rate in the Kanto region. Earthquakes of focal mechanisms with positive ∆CFF values drastically increased, while those with negative ∆CFFs showed no obvious changes except for immediately after the mainshock. This fault-dependent seismicity rate change strongly supports the contribution of the Coulomb stress transferred from the Tohoku-Oki sequence to the seismicity rate change in the Kanto region. Immediately following the mainshock, earthquakes of all types of focal mechanisms were activated, but the increased seismicity rate of earthquakes with negative ∆CFFs returned to the background level within a few months. This suggests that there might be other contributing factors to the seismicity rate change such as dynamic stress triggering or pore-fluid pressure changes.

Sample Efficient Home Power Anomaly Detection in Real Time Using Semi-Supervised Learning

Abstract: Anomaly detection in home power monitoring can be categorized into two main types: detection of electrical theft, leakage, or nontechnical loss and monitoring anomalies in the daily activities of residents. Focusing on the application and practicality of anomaly detection, we propose sample efficient home power anomaly detection (SEPAD) with improved monitoring performance in terms of electricity usage as well as changes in the daily living activities of residents via provision of detailed feedback. SEPAD consists of two classifiers: an appliance pattern matching classifier (APMC) and an energy consumption habit classifier (ECHC). The APMC uses a single-source separation framework based on a semi-supervised support vector machine (semi-SVM) model. This semi-supervised learning method requires only a small amount of labeled data to achieve high accuracy in near real time and is a sample efficient detection method. The hidden Markov model (HMM)-based ECHC improves the rationality of SEPAD by providing anomaly detection functionality with respect to the daily activities of householders, especially the elderly and residents in developing areas. When SEPAD detects the appearance of an unknown pattern or known patterns contrary to the household’s electricity usage habits, it triggers an alarm. SEPAD was applied to monitor power consumption data from Mkalama, a rural area in Tanzania with 52 households containing nearly 150 occupants connected to a solar powered off-grid network. The results of the practical test demonstrate the high accuracy and practicality of the proposed method.