Toshiki Iso

Gait analyzer based on a cell phone with a single three-axis accelerometer

We propose a fuss-free gait analyzer based on a single three-axis accelerometer mounted on a cell phone for health care and presence services. It is not necessary for users not to wear sensors on any part of their bodies; all they need to do is to carry the cell phone. Our algorithm has two main functions; one is to extract feature vectors by analyzing sensor data in detail using wavelet packet decomposition. The other is to flexibly cluster personal gaits by combining a self-organizing algorithm with Bayesian theory. Not only does the three-axis accelerometer realize low cost personal devices, but we can track aging or situation changes through on-line learning. A prototype that implements the algorithm is constructed. Experiments on the prototype show that the algorithm can identify gaits such as walking, running, going up/down stairs, and walking fast with an accuracy of about 80%.

Statistical approaches for personal feature extraction from pressure array sensors

We propose two statistical probability approaches to extract personal feature from the users grip force data. One approach is based on grip force changes predicted by the Kalman filter, the other is based on distributions of grip force changes by Jensen-Shannon(JS) divergence. Personal feature is the customary behavior that repeatedly appears without the user being aware of it. The personal feature is used for not only user-authentication, but also user-special commands. We mount pressure array sensors on a mobile phone and show that our proposals can extract personal feature from the users grip force data with 10[%] error in FAR-FRR by the Kalman filter approach and the accuracy of 100[%] by the JS divergence approach.

Ubiquitous discovery service platform for mobile applications via a cell phone

We propose a service infrastructure for richer ubiquitous services that assume access via a cell phone. We call it UDSP (ubiquitous discovery service platform). It can associate a variety of IDs in the real world with a variety of services on the communication network. It can also provide appropriate services for cell phone users. Furthermore, since it supports conventional IDs and service systems, it is easy for service providers to implement service control. In order to realize the above features, the UDSP is composed of four major components: multi-ID capture, UOI (universal object identifier) administration, BIND information (attribution information about objects and services) and basic service portal. We describe these components in the UDSP architecture and show a ubiquitous service system based on the UDSP.

Human face classification for security system

We propose a method for classifying faces that uses only simple image processing. The method can rapidly judge whether the person detected by a monitor camera is masked or not. Our algorithm has two stages. The first stage detects the facial pattern by template matching with a new similarity assessment. The second stage judges whether the face is masked or not by using optimal features in the spatial frequency domain. Indeed, experiments show that our algorithm can form an effective security system.

Screen Unlocking Method using Behavioral Characteristics when Taking Mobile Phone from Pocket

In this paper, we propose a screen unlocking system using an accelerometer and pressure sensor arrays mounted on a mobile phone as casual identification. The proposed system focuses on the users behavioral characteristics when taking their mobile phone from their pocket and the pressure distribution when gripping the mobile phone during this motion. In the evaluation experiment, 12 out of 30 taking-out actions succeed to unlock the mobile phone screen, and our system achieved 0.43 FAR after 18 templates had been trained.

Mobile phone user authentication with grip gestures using pressure sensors

Purpose – User authentication is generally used to protect personal information such as phone numbers, photos and account information stored in a mobile device by limiting the user to a specific person, e.g. the owner of the device. Authentication methods with password, PIN, face recognition and fingerprint identification have been widely used; however, these methods have problems of difficulty in one-handed operation, vulnerability to shoulder hacking and illegal access using fingerprint with either super glue or facial portrait. From viewpoints of usability and safety, strong and uncomplicated method is required. Design/methodology/approach – In this paper, a user authentication method is proposed based on grip gestures using pressure sensors mounted on the lateral and back sides of a mobile phone. Grip gesture is an operation of grasping a mobile phone, which is assumed to be done instead of conventional unlock procedure. Grip gesture can be performed with one hand. Moreover, it is hard to imitate grip...

Mobile Phone User Authentication with Grip Gestures using Pressure Sensors

Authentication methods with password, PIN, face recognition, and fingerprint identification have widely been used, however these methods have problems of difficulty in one-handed operation, vulnerability to shoulder hacking, and illegal access using fingerprint with super glue or facial portrait. Prom viewpoint of usability and safety, strong and uncomplicated method is required. We propose a user authentication method based on grip gestures using pressure sensors mounted on the lateral and back of a mobile phone. Grip gesture is an operation of grasping a mobile phone, which is assumed to be done instead of conventional unlock procedure. Grip gesture can be performed with one hand. Moreover, it is hard to imitate grip gestures since finger movements and grip force during a grip gesture are hardly seen by the others. We experimentally investigated the feature values of grip force and evaluated our proposed method from viewpoint of error rate.

Personal feature extraction via grip force sensors mounted on a mobile phone: authenticating the user during key-operation

We propose an algorithm for authenticating the user of a mobile phone from the outputs of pressure sensors during key-operations such as button-pushes. While not intended to replace password identification, it does help in providing the service which is suitable for a user without any his/her specific action. For example, during users entering key strokes. if a service cloud can recognize user-authentication by analyzing key strokes, then, it can find the optimal services based on the user preference. Our algorithm is based on a statistic probabilistic model based approach; it calculates the probability distribution of the temporal differential values of pressure by Kalman filtering. The captured sensory data is compared to predicted sensory data based on the probability distribution to judge whether the person making the key-operation is the registered owner or not. We implement the proposed system and subject it to feasibility experiments with 10 subjects; its user-authentication accuracy is quite good with a FAR-FRR error rate of only 10[%].

Sensing of Feeling and "Kansei". A Neural Network Approach for Classifying Eye Shape by Features Obtained from the Subjective Evaluation Standard.

A neural net approach is proposed to classify the eye shape with the respect to the three dominant features obtained from the subjective evaluation standard. The neural network is composed of eighteen physical features of the eye used as input data and the three features in the subjective tests used as output data. From the experiments, it can be concluded that these features combined can best represent various subjective impressions of human eyes. It can also be shown that unknown data can be classified by using k-neighbor interpolation training, where neighboring data are chosen based on the criterion of absolute standard of learning data.