Communication without words

Technological innovations to assess and include the human dimension in the building-performance loop: A review

Statistical analysis and control of dynamic systems

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.

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

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.

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

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.

Power Demand Forecasting Using Meteorological Data and Human Congestion Information

We consider the problem of short-term electricity demand forecasting in a small-scale area. Electric power usage depends heavily on irregular daily events. Event information must be incorporated into the forecasting model to obtain high forecast accuracy. The electricity fluctuation due to daily events is considered to be a basis function of time period in a regression model. We present several basis functions that extract the characteristics of the event effect. When the basis function cannot be specified, we employ the fused lasso for automatic construction of the basis function. With the fused lasso, some coefficients of neighboring time periods take exactly the same values, leading to stable basis function estimation and enhancement of interpretation. Our proposed method is applied to the electricity demand data of a research facility in Japan. The results show that our proposed model yields better forecast accuracy than a model that omits event information; our proposed method resulted in roughly 12% and 20% improvements in mean absolute percentage error and root mean squared error, respectively.

https://www.mdpi.com/1996-1073/13/21/5839/pdf

Event effects estimation on electricity demand forecasting

The electroencephalogram (EEG) is necessary for the diagnosis of epilepsy. To make a diagnosis of epilepsy exactly, a full EEG recording for a long stretch of time is needed. The observation for a long record is a big burden for a doctor. To reduce this burden, a computer aid is important. This paper presented classifications of EEG patterns using the ensemble TPunit NNs for the diagnosis of epilepsy. The classification accuracy rates of the proposed classifiers were found to be higher than that of stand alone neural network. In addition, the classification accuracy was higher than previous study. The ensemble of the TPUnit neural networks is highly effective in classification problem.

/pdf/eeg-signals-classification-by-using-an-ensemble-tpunit-392hvk6n6z.pdf

EEG Signals Classification by Using an Ensemble TPUnit Neural Networks for the Diagnosis of Epilepsy

Digital signage often uses a large display with the camera placed on the outer frame and set with a wide angle to capture the face of the viewer. In some cases the viewer’s iris is obstructed due to the gaze position of the viewer. In this study, we present an appearance-based gaze estimation method that can be used for digital signage even when the iris is not fully visible. The proposed approach uses the angle of the head and the image of the eye area as features for a neural network machine learning algorithm. Our subject experiments confirm that we achieve accurate focus-point gaze estimation.

/pdf/appearance-based-gaze-estimation-for-digital-signage-43kxn0z6i7.pdf

Appearance-Based Gaze Estimation for Digital Signage Considering Head Pose

This paper presents a telepresence system for a ride, such as on a roller coaster, using a motion platform that can provide a seated user with the sensation of inertial force. Most conventional studies using a motion platform with a few degrees of freedom have not generated an inertial force when a ride accelerates, because a motion platform cannot simulate the same motion of a real roller coaster. We propose a new telepresence system that can provide a user with an inertial force sensation using a motion platform with a few degrees of freedom and an immersive display. In our research, the inertial force sensation is generated by acceleration of gravity produced by inclining the motion platform. The inclination of the seated user is estimated from an image sequence captured using an omnidirectional camera placed on an actual running roller coaster. In our experiments, the inertial force sensation is realized using a motion platform and an immersive display.

/pdf/poster-mr-telepresence-system-with-inertial-force-sensation-3rin6zx5cd.pdf

Maiya Hori

Papers

Power Demand Forecasting Using Meteorological Data and Human Congestion Information

Event effects estimation on electricity demand forecasting

EEG Signals Classification by Using an Ensemble TPUnit Neural Networks for the Diagnosis of Epilepsy

Appearance-Based Gaze Estimation for Digital Signage Considering Head Pose

Poster: MR telepresence system with inertial force sensation using a motion platform and an immersive display