원문정보
초록
영어
Smart home technologies have become, in the last few years, a very active topic of research. However, many scientists working in this field do not possess smart home infrastructures allowing them to conduct satisfactory experiments in a concrete environment with real data. To address this issue, this paper presents a new flexible 3D smart home infrastructure simulator, which is developed in Java specifically to help researchers working in the field of activity recognition. A set of pre-recorded scenarios, made with data extracted from clinical trials, will be included with the simulator in order to give a common foundation to test activity recognition algorithms. The goal is to release the SIMACT simulator with a visual scenario editor as an open source component that will benefit the whole smart home research community.
목차
1. Introduction
2. SIMACT: a 3D Smart Home Simulator
2.1. User Interface
2.2. Options and Parameters
2.3. Software Architecture
2.2. Technologies for Implementation
3. Parameterization in Text Format
3.1. Dynamic Objects Loading
3.2. XML based Script Creation and Edition
4. Visual Script Editor
4.1. Script Design
4.2. Action Definition
5. Experiment, Trials and Scenarios
5.1. Designing an Experiment Meeting Research Needs
5.2. Experimental Approach for Gathering Useful Data
5.3. Phase 1: Experiment with 20 Normal Subjects
5.4. Phase 2: Experiment with 20 Alzheimer’s Patients
5.5. Open Source Database coming with SIMACT
5.6. Testing a Recognition Algorithm with SIMACT
6. Related Works
6.1. CAST Simulation Toolkit
6.5. ViSi from A. Lazovik & al.
6.5. Park’s Simulator: CASS
6.5. ISS System from H. Nguyen & al.
6.5. Smart House Simulation Tool by Krzyska
7. Conclusion and Perspective
Acknowledgements
References