Human activity recognition from environmental background sounds for wireless sensor networks (特集 知識情報化社会を支えるシステム技術)
スポンサーリンク
概要
- 論文の詳細を見る
Sound feature extraction Mel Frequency Cepstral Coefficients (MFCC) and Vector Quantization (VQ) classification Linde-Buzo-Gray algorithm (LBG) algorithms are applied for recognizing the background sounds in the human daily activities. Applying these algorithms to twenty typical daily activity sounds, average recognition accuracy of 93.8% can be achieved. In these algorithms, how three parameters (i.e., Mel filters number, frame-to-frame overlap and LBG codebook cluster number) affect systems calculation burden and accuracy is also investigated. By adjusting these three parameters to an optimized combination, the multiplication and addition calculation burden can be reduced by 87.0% and 87.1% individually while maintaining the systems average accuracy rate at 92.5%. This is promising for future integration with other sensor (s) to fulfill daily activity recognition by using power aware Wireless Sensor Networks (WSN) systems.
- 2010-04-01
著者
-
ZHAN Yi
Keio University, Dept. of Electronics and Electrical Engineering
-
NISHIMURA Jun
Keio University, Dept. of Electronics and Electrical Engineering
-
KURODA Tadahiro
Keio University, Dept. of Electronics and Electrical Engineering
-
Zhan Yi
Keio University Dept. Of Electronics And Electrical Engineering
-
Kuroda Tadahiro
Keio Univ.
-
Kuroda Tadahiro
Keio University Dept. Of Electronics And Electrical Engineering
-
Nishimura Jun
Keio University Dept. Of Electronics And Electrical Engineering
-
Nishimura Jun
Keio Univ. Dept. Of Electronics And Electrical Engineering
関連論文
- Human activity recognition from environmental background sounds for wireless sensor networks (特集 知識情報化社会を支えるシステム技術)
- Non-contact 10% efficient 36mW power delivery using on-chip inductor in 0.18-μm CMOS (電子部品・材料)
- Chip-to-Chip Power Delivery by Inductive Coupling with Ripple Canceling Scheme
- Human activity recognition from environmental background sounds for wireless sensor networks (特集 知識情報化社会を支えるシステム技術)
- Digital Rosetta Stone : A Sealed Permanent Memory with Inductive-Coupling Power and Data Link
- A 9-bit 100-MS/s 1.46-mW Tri-Level SAR ADC in 65nm CMOS
- Measurement of Inductive Coupling in Wireless Superconnect
- Split Capacitor DAC Mismatch Calibration in Successive Approximation ADC
- 18-GHz Clock Distribution Using a Coupled VCO Array(Analog and Communications,Low-Power, High-Speed LSIs and Related Technologies)
- Analysis of Inductive Coupling and Design of Rectifier Circuit for Inter-Chip Wireless Power Link
- Constant Magnetic Field Scaling in Inductive-Coupling Data Link
- Daisy Chain Transmitter for Power Reduction in Inductive-Coupling CMOS Link(Analog and Communications,Low-Power, High-Speed LSIs and Related Technologies)
- Constant Magnetic Field Scaling in Inductive-Coupling Data Link
- 60% Power Reduction in Inductive-Coupling Inter-Chip Link by Current-Sensing Technique
- A 1.2 Gbps Non-contact 3D-Stacked Inter-Chip Data Communications Technology (Interface and Interconnect Techniques, VLSI Design Technology in the Sub-100nm Era)
- System LSI : Challenges and Opportunities (System LSIs and Microprocessors, VLSI Design Technology in the Sub-100nm Era)
- A 4-Gbps Quasi-Millimeter-Wave Transmitter in 65nm CMOS and a Fast Carrier and Symbol Timing Recovery Scheme
- Special Section on Low-Power, High-Speed LSIs and Related Technologies
- A 9-bit 100-MS/s 1.46-mW Tri-Level SAR ADC in 65nm CMOS
- A Dynamic Offset Control Technique for Comparator Design in Scaled CMOS Technology
- A 60-GHz Injection-Locked Frequency Divider Using Multi-Order LC Oscillator Topology for Wide Locking Range
- A 9-bit 100MS/s SAR ADC with Digitally Assisted Background Calibration
- Human action recognition using wireless wearable in-ear microphone (特集 医療・ヘルスケアにおける工学技術の新展開)
- A 9-bit 100MS/s SAR ADC with Digitally Assisted Background Calibration
- Transmission Line Coupler Design and Mixer-Based Receiver for Dicode Partial Response Communications
- A 4-10bit, 0.4-1V Power Supply, Power Scalable Asynchronous SAR-ADC in 40nm-CMOS with Wide Supply Voltage Range SAR Controller
- An Adaptive DAC Settling Waiting Time Optimized Ultra Low Voltage Asynchronous SAR ADC in 40nm CMOS
- Symbol-Rate Clock Recovery for Integrating DFE Receivers