Kenta Cho

Human Activity Recognizer for Mobile Devices with Multiple Sensors

This paper presents a novel human activity recognizer used to estimate a users activities with sensors on a widespread consumer mobile device. Our recognizer can estimate a users means of migration by using a combination of an acceleration sensor and a GPS. We evaluate the accuracy rate of the estimation with cellular phones carried freely and the result is 90.6 percent even in the case of intermittent working mode for lower power consumption.

Mobile Agents and Logic Programming

In many mobile agent systems, it is normal for mobile agents to be uninformed about the environment of a computer until they actually arrive at the computer. If the environment of computers is updated frequently, it is even more difficult to execute actions as expected. This paper introduces a new procedure for mobile agents that work in such dynamic world. The new procedure smoothly integrates planning, action execution, knowledge updates, and plan modifications.

A new HTN planning framework for agents in dynamic environments

In a dynamic environment, even if an agent makes a plan to obtain a goal, the environment might change while the agent is executing the plan. In that case, the plan, which was initially valid when it was made, might later become invalid. Furthermore, in the process of replanning, it is necessary to take into account the side effects of actions already executed . To solve this problem, we have previously presented an agent life cycle that interleaves HTN planning, action execution, knowledge updates, and plan modification. In that agent life cycle, the plans are always kept valid according to the most recent knowledge and situation. However, it deals with only total-order plans. This paper extends the agent life cycle so that the agent can handle partial-order plans.

Speculative Computation and Action Execution in Multi-Agent Systems

In some multi-agent systems, when an agent cannot retrieve information from another agent, the agent makes an assumption and tentatively performs the computation. When the agent comes across a mistake in the preliminary assumption, the computation is modified. This kind of speculative computation is effective when the assumption is correct. However, once the agent executes an action, it is impossible to modify the computation in these systems. This paper shows how to integrate speculative computation and action execution through logic programming.

picoPlangent: an intelligent mobile agent system for ubiquitous computing

This paper describes an intelligent mobile agent named picoPlangent that we developed for use with portable devices. picoPlangent is designed with a component-based architecture. The agent functions are implemented by a set of small components, and the arrangement of these components can be easily changed within the limits of the available resources of each portable device. Agent actions are described into the goal tree that realizes the flexible actions of the agent on portable devices. The picoPlangent architecture is simple and easy to implement on various devices. We implemented picoPlangent using J2SE on PCs, GCC on PDAs (Palm devices) and J2ME on cellular phones (iAppli/ezPlus).

Interoperability for mobile agents by incarnation agents

Many different kinds of mobile agent platforms have been developed. However, migration to a different type of mobile agent platform is actually impossible. As a solution to this problem, we propose an interoperability concept using incarnation agents. This concept realizes logical mobility between different kinds of agent platforms. The incarnation agent extracts an agents procedures and status, compiles them into an agent platform-independent format, and then re-compiles them to the target agent platform format, thus enabling the process to continue. The incarnation agent also has autonomy for interoperability. It manages complex migration for interoperability so that the agents procedures can be described in a simple mobile model. Moreover, the incarnation agent modifies the agents procedures so that they are applicable to the facilities of the target agent platform. Feasibility experiments using interoperability middleware have been conducted as a basis for realizing incarnation agents.

Advice Extraction from Web for Providing Prior Information Concerning Outdoor Activities

Conventional context-aware recommendation systems do not provide information before user action, although they provide information considering users’ ongoing activity. However, users want to know prior information such as how to go to their destination or get necessary items when they plan to do outdoor activities such as climbing and sightseeing. It takes time to collect the prior information since it is not so easy to appropriately find them. This paper proposes a method for extracting prior advices from the web. The method first identifies whether a given sentence is an advice or not. Then the method identifies whether the sentence is a prior advice or not if the sentence is identified as advice. In this paper, we will show availability of the proposed method through our experimentation. We also developed a system for providing prior information using the proposed method.

BDI Model-Based Crowd Simulation

We present a new approach for crowd simulation in which a BDI (Belief-Desire-Intention) model is introduced that makes it possible for a character in a simulated environment to work adaptively. Our approach allows the character to realize realistic behavior by adapting its action with the sensed information in a changing environment. We implemented a demo system simulating the BDI model-based NPCs that extinguishes a forest fire with a 3D game engine, Source Engine. We measured the performance to evaluate the scalability and the bottleneck of the system.

Annotating knowledge work lifelog: term extraction from sensor and operation history

We present a system that supports review of a knowledge work lifelog as an activity history. Since knowledge workers often review their own activity histories, gathering each users activities on his/her terminal as a lifelog is a promising approach. However, readability of the stored lifelog is a large problem of lifelog-based application. We propose a term extraction method to add annotation labels to the stored lifelog for supporting knowledge workers, exploiting text data acquired from desktop activities. Our prototype system monitors a users desktop activities after combining raw events, and then extracts possible annotation labels with LDA and C-value techniques from documents and text data in sensor events. In this paper, we introduce a lifelogging module and a lifelog annotation method based on term extraction techniques. According to an empirical evaluation for three weeks, we found that the current method is useful for one-week review.

An online human activity recognizer for mobile phones with accelerometer

We propose a novel human activity recognizer for an application for mobile phones. Since such applications should not consume too much electric power, our method should have not only high accuracy but also low electric power consumption by using just a single three-axis accelerometer. In feature extraction with the wavelet transform, we employ the Haar mother wavelet that allows low computational complexity. In addition, we reduce dimensions of features by using the singular value decomposition. In spite of the complexity reduction, we discriminate a users status into walking, running, standing still and being in a moving train with an accuracy of over 90%.