LOARA 1 2 3 4 4 1 2 2 DSL DSL LOARA Designing and evaluation of LOARA, a Domain-Specific Language for Activity Recognition Applications Kotaro Ichino, 1 Kenji Hisazumi, 2 Sozo Inoue, 3 Tsuneo Nakanishi 4 and Akira Fukuda 4 Developmental issues in activity recognition applications is shown below. 1)Knowledge is necessary for developing two field, platform and pattern recognitions. Therefore, advanced knowledge and skills are necessary. 2)Only means to improve the recognition accuracy is tuning of the parameter. It takes long time to the system development. To solve these problems, we propose introduce the domain-specific development into the activity recognition application development. In the domain-specific development, the application is developed by using DSL Domain-Specific Language, that is the language for a specific domain. In this paper, we present results of the design of LOARA that is DSL for activity recognition, and show evaluations. 1. GPS 1) 2 1 2 2 1 2) GPL General Purpose Language DSL Domain-Specific Language DSL DSL 1 Graduate School of Information Science and Electrical Engineering, Kyushu University 2 LSI System LSI Research Center, Kyushu University 3 Graduate School of Engineering, Kyushu Institute of Technology 4 Faculty of Information Science and Electrical Engineering, Kyushu University 1 c 2010 Information Processing Society of Japan
DSL DSL 2 3 DSL 4 DSL 5 DSL 6 2. DSL 2.1 DSL 2) DSL DSL DSL GPL C Java Visser DSL 3) DSL GPL DSL DSL yacc RDBMS SQL HTML CSS Make DSL DSL 4) Software Factories Flow 5) DSL LOSA 6) GPL DSL 500% 4) DSL 2.2 7) 3 3 14Hz 9 SVM Support Vector Machine 8) 2 ewatch 9) 50Hz 6 C4.5 k 10) 3 3 10Hz FFT 2 c 2010 Information Processing Society of Japan
3. DSL DSL DSL 2)11)6) 1 DSL 2 3 DSL DSL 3.1 DSL DSL DSL DSL DSL 3.2 FODA Feature Oriented Domain Analysis 12) 12)13) FODA 12) 3.3 DSL DSL DSL 3 DSL DSL DSL DSL DSL DSL 4. DSL DSL LOARA Language Of Activity Recognition Application 4.1 LOARA 2 LOARA DSL DSL 3 c 2010 Information Processing Society of Japan
1 (a) (b) 4.2 LOARA 2 4.2 DP 4.2 2 2 FORM Feature Oriented Reuse Method 13) 2 DSL 4.3 DSL 2 DSL SensorDeviceClass FeatureQuantityClass Algorithm- Class ContextGroupClass 4 DSL LOARA DSL 3 DSL 4 c 2010 Information Processing Society of Japan
3 LOARA DSL 1 Acceleration X Acceleration Y Acceleration Z GPS Humidity Light Pressure Temperature SensorDeviceType X Y Z GPS 2 FormulaType Average Differential FourierTransform Integration RawData StandardDeviation Variance Vector 2 4.3.1 SensorDeviceClass SensorDeviceClass DSL 3 A Name Type SensorDeviceType 1 SamplingRate Hz SensorDeviceClass 1 FeatureQuantityClass 4.3.2 FeatureQuantityClass FeatureQuantityClass DSL 3 B Name Type FormulaType 2 WindowSize SlideWindowSize FeatureQuantityClass 1 SensorDeviceClass 1 Feature- QuantityClass AlgorithmClass 5 c 2010 Information Processing Society of Japan
3 C4 5 DPMatching EuclideanDistance HMM MAP MLLR SVM TemplateMatching Algorithm Type C4.5 DP MAP MLLR 4 PlatformType iphone ipodtouch iphone 14) ipod touch 15) MICAz MICAz(MPR2600J/MTS400) 16) 4.3.3 AlgorithmClass AlgorithmClass DSL 3 C Name Type AlgorithmType 3 Size AlgorithmClass 1 FeatureQuantityClass 1 ContextGroupClass 4.3.4 ContextGroupClass ContextGroupClass DSL 3 D Name Description Context Context Context Name Description Description ContextGroupClass 1 AlgorithmClass 4.3.5 4 Name Description Platform PlatformType 4 4.4 DSL DSL LOSA Language Of wireless Sensor network Application 6) LOARA LOSA DSL LOARA DSL LOARA DSL LOSA 5. LOARA 5.1 LOARA DSL LOARA Microsoft DSL Tools 17) LOARA 4 4000 4 A DSL 4 B Drag&Drop DSL 4 C DSL 4 D DSL 5 5.2 LOARA 4 8 12 LOARA 10 LOARA 6 c 2010 Information Processing Society of Japan
5 LOARA LOARA 3.0 4.5 2.5 4.6 2.5 4.5 2.5 5.0 2.5 5.0 2.0 4.4 4.0 3.0 4.1 2.8 3.3 2.3 2.8 3.4 3.1 3.9 2.8 4.0 4 LOARA 5 5 5 3 1 GPL LOARA 5 LOARA LOARA LOARA LOARA 7 c 2010 Information Processing Society of Japan
LOARA LOARA LOARA DSL LOARA 6. LOARA LOARA LOARA DSL 4 DSL LOARA Microsoft DSL Tools 12 LOARA LOARA DSL IT (21013038) 1) HASC: Human Activity Sensing Consortium, http://hasc.jp/. 2) Cook, S., Jones, G., Kent, S. and Wills, A. C.: Domain Specific Development with Visual Studio DSL Tools (Microsoft.Net Development), Addison Wesley (2007). 3) Visser, E.: WebDSL: A case study in domain-specific language engineering, Generative and Transformational Techniques in Software Engineering (GTTSE 2007), Lecture Notes in Computer Science. Springer, Vol.5235, pp.291 373 (2008). 4) Bhanot, V., Paniscotti, D., Roman, A. and Trask, B.: Using domain-specific modeling to develop software defined radio components and applications, Proc. of the 5th OOPSLA Workshop on Domain-Specific Modeling (DSM 05), San Diego, California, USA (2005). 5) Naumowicz, T., Schröter, B. and Schiller, J.: Prototyping a software factory for wireless sensor networks, Proc. of the 7th ACM Conference on Embedded Networked Sensor Systems, ACM, pp.369 370 (2009). 6) DICOMO2009 pp.1578 1587 (2009). 7) Song, S., Jang, J. and Park, S.: An Efficient Method for Activity Recognition of the Elderly Using Tilt Signals of Tri-axial Acceleration Sensor, Lecture Notes in Computer Science, Vol.5120, pp.99 104 (2008). 8) Maurer, U., Smailagic, A., Siewiorek, D. and Deisher, M.: Activity recognition and monitoring using multiple sensors on different body positions, Proc. of the Workshop on Wearable and Implantable Body Sensor Networks (BSN 2006), Vol.5847, pp.113 116 (2006). 9) Maurer, U., Rowe, A., Smailagic, A. and Siewiorek, D.: ewatch: a wearable sensor and notification platform, Body Sensor Networks Workshop, submitted, Citeseer, pp.142 145 (2006). 10) 3 No.54, pp.15 22 (2006). 11) Mernik, M., Heering, J. and Sloane, A.: When and how to develop domain-specific languages, ACM Computing Surveys (CSUR), Vol.37, No.4, pp.316 344 (2005). 12) Kang, K., Cohen, S., Hess, J., Novak, W. and Peterson, A.: Feature-oriented domain analysis (FODA) feasibility study, Technical Report SEI/CMU-90TR-21, Software Engineering Institute, Carnegie Mellon University (1990). 13) Kang, K., Kim, S., Lee, J., Kim, K., Shin, E. and Huh, M.: FORM: A feature-oriented reuse method with domain-specific reference architectures, Annals of Software Engineering, Vol.5, No.1, pp.143 168 (1998). 14) iphone: http://www.apple.com/iphone/. 15) ipod touch: http://www.apple.com/ipodtouch/. 16) Crossbow: http://www.xbow.com/. 17) Microsoft: Microsoft Domain-Specific Language Tools, http://www.domainspecificdevelopment.com/. 8 c 2010 Information Processing Society of Japan