In case of verifying an application operating on a mobile device such as a smartphone, the position, operation, and communication situation of the person are greatly related to the performance of the application. To verify such applications, we have installed applications on their own smartphone and verified by collecting data. In this case, the number of devices that can be used for verification and the density of people become uncertain. Furthermore, conditions of occurrence of bugs and deterioration of performance could only be estimated from collected logs and data. Also, when trying to reproduce the situation, it is difficult to faithfully reproduce the communication situation and the operation history, and it was also difficult in terms of reproducibility. It is possible to set the communication status, the position and operation of a person by a simulator, and by using the result as an input of an application, it becomes possible to set the number and the density with an arbitrary value and reproduce the occurrence situation of the bug and the performance deterioration Can be easily performed. In this paper, we propose a framework that enables generation and reproduction of flexible situations of verification by linking emulator of simulator and application.

In this paper, we propose a system configuration that reduces processing time to realize real-time evacuation simulation of urban flood damage and discuss feasibility of immediate processing from prototype system. The purpose of our research is to develop a system to estimate the effectivity of urban flood damage and countermeasure by using this flood prediction result. In general, in the calculation processing, the calculation amount increases as the target area becomes wider. Processing time often takes several hours to several tens of hours for calculation, therefore immediate processing on the assumption value of flooding depth and human flow against flooding has difficulty. Therefore this paper considers the possibility of real-time evacuation simulation from the viewpoint of processing performance. We develop a prototype system of simulation for flood evacuation in order to enable immediate processing. The system shows some requirements for stable operation and the feasibility of real-time evacuation simulation.

This study attempts to simulate people flow before and after the flooding in the West Japan heavy rain on July 2018, using a mobile GPS (global positioning system) data. We focus on Mabi-Cho, Kurashiki-City, which is one of the most damaged area on the flood disaster. A Monte Carlo simulation approach is introduced to generate micro-scale people's evacuation flows from spatially sparse GPS information. The result shows that GPS data effectively simulate people flow after flooding even if the simulation approach is very simple, and how people flow changed before and after the disaster.

In this paper, LSTM-based neural network is applied to indoor localization using mobile BLE tag's signal strength collected by multiple scanners. Stability of signal strength is a critical factor of wireless indoor localization for higher accuracy. While traditional methods like trilateration and fingerprinting suffer from noise and packet loss, deep learning based methods perform well. We focus on large-scale exhibition where wireless signal gets unstable due to many people. Proposed neural network consists of fully connected layers for noise removal and LSTM layers for time-series feature extraction. The network takes the time-series of signal strength as input and outputs the estimated location. In the evaluation, the number of layers is changed to find the optimal structure. As a result, the best configuration achieved the error of 2.44m at 75 percentile for the data of a large-scale exhibition in Tokyo.

We propose an integrated framework for sensing, recognizing and utilizing of subjective time as context. Various studies on experimental psychology have showed several factors which affects subjective time. Those factors should be partially captured by ubiquitous sensors such as smartphones and wearable devices, therefore, we tackle to create common and individual model for subjective time based on the sensor data. We report our first prototype implementation for the framework based on AWARE framework with adding experience sampling method for subjective time recognition. In addition, we discuss potential applications which leveraging advantages of subjective time as context.

This paper proposes an accurate estimation method of walking speed using deep learning for smartphone-based Pedestrian Dead Reckoning (PDR).PDR requires to estimate speed and direction of pedestrians accurately using accelerometer and gyroscope.To improve the accuracy of PDR, existing works focused to improve the key factors of speed estimation (i.e., stride and/or step estimation) by adapting deep learning.On the contrary, our research proposes to adapt deep learning more directly to estimate walking speed from sensor data of smartphone. We evaluate the accuracy of proposed method by comparing with conventional PDR method. As a result, we confirmed that proposed method can estimate the speed more accurately.

There are many methods for indoor positioning. These methods are divided into the relative localization and absolute localization. In the relative localization, one widely used method is Pedestrian Dead Reckoning (PDR). Relative localization estimates the moving distance, orientation, and height of the pedestrian. However, relative localization has a problem caused by an accumulated error: the longer the path, the worse the accuracy of relative localization. There is another problem in the existing evaluating metrics: they compare only the actual location and the estimated location of the destination. Relative localization also has this evaluation problem. We propose PIEM: Path Independent Evaluation Metric for Relative Localization. PIEM is a path independent evaluation metric, considering the complexity of the path; distance, orientation, and height. Then we evaluate these three factors of relative localization in addition to the position. Our proposed method showed more consistent results for the complexity of the path than the existing methods of relative localization evaluation.

Techniques for obtaining customers' behavior (dwell time, count, and flow) in a shopping mall or large exhibit are highly sought-after by organizers or shop owners. Additionally, ways of effectively directing customers from cyber space such as the Web or smartphone apps to physical retail stores are also in high demand. "Online to Offline (O2O) Marketing" has recently been attracting attention to make these a reality. However, the know-how accumulated through "O2O Marketing" is not shared widely as it can be sensitive for business and customer's privacy. In this paper, we provide the knowledge obtained through the demonstration experiments held by the "O2O Digital Marketing Study Group" organized by NPO Lisra at a large underground shopping mall in Nagoya. 250 BLE tags and 12 Wi-Fi scanners were installed in this mall. We also organized a "coupon campaign" to increase the number of participants. We were able to effectively collect visiting customer count measurements via Wi-Fi scanners irrespective of the anonymization of BSSID, as our results showed similar trends collected by optical human detectors inherently installed at the venue. This paper provides preliminary insight into understanding the behaviors of retail shoppers and we believe this is a firm starting point for this area.