다중 이벤트 센서 기반 스마트 홈에서 사람 행동 분류를 위한 효율적 의사결정평면 생성기법
Efficient Hyperplane Generation Techniques for Human Activity Classification in Multiple-Event Sensors Based Smart Home
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In this paper, we propose an efficient hyperplane generation technique to classify human activity from combination of events and sequence information obtained from multiple-event sensors. By generating hyperplane efficiently, our machine learning algorithm classify with less memory and run time than the LSVM (Linear Support Vector Machine) for embedded system. Because the fact that light weight and high speed algorithm is one of the most critical issue in the IoT, the study can be applied to smart home to predict human activity and provide related services. Our approach is based on reducing numbers of hyperplanes and utilizing robust string comparing algorithm. The proposed method results in reduction of memory consumption compared to the conventional ML (Machine Learning) algorithms; 252 times to LSVM and 34,033 times to LSTM (Long Short-Term Memory), although accuracy is decreased slightly. Thus our method showed outstanding performance on accuracy per hyperplane; 240 times to LSVM and 30,520 times to LSTM. The binarized image is then divided into groups, where each groups are converted to binary number, in order to reduce the number of comparison done in runtime process. The binary numbers are then converted to string. The test data is evaluated by converting to string and measuring similarity between hyperplanes using Levenshtein algorithm, which is a robust dynamic string comparing algorithm. This technique reduces runtime and enables the proposed algorithm to become 27% faster than LSVM, and 90% faster than LSTM.
Abstract
In this paper, we propose an efficient hyperplane generation technique to classify human activity from combination of events and sequence information obtained from multiple-event sensors. By generating hyperplane efficiently, our machine learning algorithm classify with less memory and run time than the LSVM (Linear Support Vector Machine) for embedded system. Because the fact that light weight and high speed algorithm is one of the most critical issue in the IoT, the study can be applied to smart home to predict human activity and provide related services. Our approach is based on reducing numbers of hyperplanes and utilizing robust string comparing algorithm. The proposed method results in reduction of memory consumption compared to the conventional ML (Machine Learning) algorithms; 252 times to LSVM and 34,033 times to LSTM (Long Short-Term Memory), although accuracy is decreased slightly. Thus our method showed outstanding performance on accuracy per hyperplane; 240 times to LSVM and 30,520 times to LSTM. The binarized image is then divided into groups, where each groups are converted to binary number, in order to reduce the number of comparison done in runtime process. The binary numbers are then converted to string. The test data is evaluated by converting to string and measuring similarity between hyperplanes using Levenshtein algorithm, which is a robust dynamic string comparing algorithm. This technique reduces runtime and enables the proposed algorithm to become 27% faster than LSVM, and 90% faster than LSTM.
참고문헌 (13)
- P. Casale, "Human Activity Recognition from Accelerometer Data Using a Wearable Device", Proceedings of Pattern Recognition and Image Analysis, pp.289~296 (2011)
- T. Fujimoto, "Wearable Human Activity Recognition by Electrocardiograph and Accelerometer", Proceedings of 2013 IEEE 43rd International Symposium on Multiple-Valued Logic, pp.12~17 (2013)
- 신수연, "다중모드 센서와 LSTM 기반의 딥 러닝을 이용한 인간의 행동인식 시스템", 대한기계학회논문집 A, 42(2), pp.111~121 (2018), 대한기계학회
- O. Ann, "Human Activity Recognition: A Review", Proceedings of 4th IEEE International Conference on Control System, Computing and Engineering, pp.389~393 (2015)
- S. Ke, "A Review on Video-Based Human Activity Recognition", Computers, 2(2), pp.88~131 (2013)
- M. Chan, "A Review of Smart Homes—Present State and Future Challenges", Journal of Computer Methods and Programs in Biomedicine, 91(1), pp.55~81 (2008)
- Y. Tsividis, "Event-Driven Data Acquisition and Digital Signal Processing-A Tutorial", Journal of IEEE Transactions on Circuits and Systems, 57(8), pp.577~581 (2010)
- A. Konak, "New Event-driven Sampling Techniques for Network Reliability Estimation", Proceedings of the 2004 Winter Simulation Conference, 1, pp.231~ (2004)
- N. Persson, "Event Based Sampling with Application to Spectral Estimation" (2002), Division of Control & Communication, Department of Electrical Engineering, Linköpings universitet
- B. Karg, "Towards Low-energy, Low-cost and High-performance IoT-based Operation of Interconnected Systems", Proceedings of 2018 IEEE 4th World Forum on Internet of Things (WF-IoT), pp.706~711 (2018)
- 정정은, "통계적 특징 기반 SVM을 이용한 야간 전방 차량 검출 기법", 대한임베디드공학회논문지, 7(4), pp.163~172 (2012), 대한임베디드공학회
- 박태희, "동시 발생 행렬의 특성함수 모멘트를 이용한 접합 영상 검출", 대한임베디드공학회논문지, 10(5), pp.265~272 (2015), 대한임베디드공학회[DOI]
- R. E. Bellman, "Applied Dynamic Programming" (2015), Princeton Legacy Library, Princeton University Press