Masamichi Shimosaka

Hierarchical recognition of daily human actions based on Continuous Hidden Markov Models

This paper presents a recognition method of human daily-life action. The method utilizes hierarchical structure of actions and describes it as a tree. We model the actions by using Continuous Hidden Markov Models which gives an output of time-series feature vectors extracted by feature extraction filter based on human knowledge. In this method, recognition starts from the root, it then competes the likelihoods of child-nodes, chooses the maximum one as recognition result of the level, and goes to deeper level. The advantages of hierarchical recognition are: 1) recognition of various levels of abstraction, 2) simplification of low-level models, 3) response to novel data by decreasing degree of details. Experimental result shows that the method is able to recognize some basic human actions.

Steered crowdsensing: incentive design towards quality-oriented place-centric crowdsensing

Crowdsensing technologies are rapidly evolving and are expected to be utilized on commercial applications such as location-based services. Crowdsensing collects sensory data from daily activities of users without burdening users, and the data size is expected to grow into a population scale. However, quality of service is difficult to ensure for commercial use. Incentive design in crowdsensing with monetary rewards or gamifications is, therefore, attracting attention for motivating participants to collect data to increase data quantity. In contrast, we propose Steered Crowdsensing, which controls the incentives of users by using the game elements on location-based services for directly improving the quality of service rather than data size. For a feasibility study of steered crowdsensing, we deployed a crowdsensing system focusing on application scenarios of building processes on wireless indoor localization systems. In the results, steered crowdsensing realized deployments faster than non-steered crowdsensing while having half as many data.

Hand shape classification with a wrist contour sensor: development of a prototype device

In this paper, we describe a novel sensor device which recognizes hand shapes using wrist contours. Although hand shapes can express various meanings with small gestures, utilization of hand shapes as an interface is rare in domestic use. That is because a concise recognition method has not been established. To recognize hand shapes anywhere with no stress on the user, we developed a wearable wrist contour sensor device and a recognition system. In the system, features, such as sum of gaps, were extracted from wrist contours. We conducted a classification test of eight hand shapes, and realized approximately 70% classification rate.

Grasping by caging: A promising tool to deal with uncertainty

This paper presents a novel approach to deal with uncertainty in grasping. The basic idea is to initiate a caging manipulation state and then shrink fingers into immobilization to perform a practical grasping. Thanks to flexibility from caging, this procedure is intrinsically safe and gains tolerance towards uncertainty. Besides, we demonstrate that the minimum caging is immobilization and consequently propose using three or four fingers to manipulate planar convex objects in a grasping-by-caging way. Experimental results with physical simulation show the robustness and efficacy of our approach. We expect its leading benefits in saving finger number, conquering low-friction materials and especially, dealing with pose/shape uncertainty.

Anomaly detection algorithm based on life pattern extraction from accumulated pyroelectric sensor data

This paper describes an algorithm of behavior labeling and anomaly detection for elder people living alone. In order to grasp the personpsilas life pattern, we set some pyroelectric sensors in the house and measure the personpsilas movement data all the time. From those sequential data, we extract two kinds of information, time and duration, and calculate two-dimensional probabilistic density function of them. Using this function, we try to classify behavior labels and detect anomaly. Here, we assume two kinds of anomaly, ldquothe rare behaviorsrdquo and ldquothe changes of life patternrdquo. The algorithm is confirmed to work on real behavior data through the experiment on about 400 days data.

Typical Behavior Patterns Extraction and Anomaly Detection Algorithm Based on Accumulated Home Sensor Data

In this paper, we propose a method consists of two components, behavior patterns extraction and anomaly detection algorithm in daily life. To begin with, sensor data are accumulated in a room environment and behavior description labels are assigned for each data segment using HMM(hidden Markov model) and k-means method. An HMM is composed every day based on sensor data segments of the day. The behavior description label at each time segment is determined by likelihood of the segment computed using the HMM. In anomaly detection step, typical behavior sequences are acquired using probabilistic density of behavior occurrence and behavior successive time. Each probabilistic density is composed based on accumulating labeled- data using sequential discounting Laplace estimation and sequential discounting expectation and maximization algorithms. When a new datum comes, if typical behavior data change largely, the data is detected as anomaly. The proposed method is verified by a long-time activity detection sensor data taken at a house of elderly person.

Forecasting urban dynamics with mobility logs by bilinear Poisson regression

Understanding people flow in a city (urban dynamics) is of great importance in urban planning, emergency management, and commercial activity. With the spread of smart devices, many studies on urban dynamics modeling with mobility logs have been conducted. It is predictive analysis, not analysis of the past, that enables various applications contributing to a more prosperous society. To deal with the non-linear effects on urban dynamics from external factors, such as day of the week, national holiday, or weather, we propose a low-rank bilinear Poisson regression model, for a novel and flexible representation of urban dynamics predictive analysis. The results obtained from an experiment with one years worth of mobility records suggest the high prediction accuracy of the proposed model. We also introduce the following applications: regional event detection via irregularities, visualization of urban dynamics corresponding to urban demographics, and extraction of urban demographics of unknown point of interests.

A new “grasping by caging” solution by using eigen-shapes and space mapping

“Grasping by caging” has been considered as a powerful tool to deal with uncertainty. In this paper, we continue to explore into “grasping by caging” and propose a new solution by using eigen-shapes and space mapping. For one thing, eigen-shapes fix dexterous hands into a series of finger formations and help to reduce dimensionality and computational complexity. For the other, space mapping builds a mapping between rasterized grids in 2-D Work space (W space) and rasterized voxels in 3-D Configuration space (C space) and helps to rapidly reconstruct C space so that we can efficiently measure the robustness of caging and find an optimal caging configuration for grasping. Our algorithm can work rapidly and squeezingly cage any 2-D shapes, including objects with either convex boundaries, concave boundaries, 1-order or high-order boundaries and even objects with inner holes. We implement the algorithm with MATLAB and carry out experiments with WEBOTS simulation to test its robustness to uncertainties. The results show that our algorithm can work well with various object shapes and can be robust to noisy control and noisy perception. It is promising in the power grasping tasks of dexterous hands.

A unified framework for modeling and predicting going-out behavior

Living in society, to go out is almost inevitable for healthy life. There is increasing attention to it in many fields, including pervasive computing, medical science, etc. There are various factors affecting the daily going-out behavior such as the day of the week, the condition of ones health, and weather. We assume that a person has ones own rhythm or patterns of going out as a result of the factors. In this paper, we propose a non-parametric clustering method to extract ones rhythm of the daily going-out behavior and a prediction method of ones future presence using the extracted models. We collect time histories of going out/coming home (6 subjects, total 827 days). Experimental results show that our method copes with the complexity of patterns and flexibly adapts to unknown observation.

Robust Action Recognition and Segmentation with Multi-Task Conditional Random Fields

In this paper, we propose a robust recognition and segmentation method for daily actions with a novel multi-task sequence labeling algorithm called multi-task conditional random field (MT-CRF). Multi-Task sequence labeling is a task of assigning input sequence to sequence of multi-labels that consist of one or multiple symbols in single frame. Multi-Task sequence labeling is essential for action recognition, since motions can be often classified into multi-labels, e.g. he is folding arms while sitting. The MT-CRFs: extensions of conditional random fields (CRFs), incorporate jointly interaction between action labels as well as Markov property of actions, to improve the performance of the joint accuracy: the accuracy for whole labels at specific time. The MT-CRFs offer several advantages over the generative dynamic Bayesian networks (DBNs), which are often utilized as multi-task sequence labelers. First, the MT-CRFs allow relaxing the strong assumption of conditional independence of observed motion, which is used in DBNs. Second, the MT-CRFs exploit the power of non-Markovian discriminative classification frameworks instead of generative models in DBNs. With deep insight of the problem Multi-Task sequence labeling, the inference process of the classifier gains more efficiency than the previous Markov random fields that tackle multi-task sequence labeling. The experimental results show that classifiers with MT-CRFs have better performance than cascaded classifiers with a couple of CRFs.