In this work, a total of 322 tests were taken on young volunteers by performing 10 different falls, 6 different Activities of Daily Living (ADL) and 7 Dynamic Gait Index (DGI) tests using a custom-designed Wireless Ga...In this work, a total of 322 tests were taken on young volunteers by performing 10 different falls, 6 different Activities of Daily Living (ADL) and 7 Dynamic Gait Index (DGI) tests using a custom-designed Wireless Gait Analysis Sensor (WGAS). In order to perform automatic fall detection, we used Back Propagation Artificial Neural Network (BP-ANN) and Support Vector Machine (SVM) based on the 6 features extracted from the raw data. The WGAS, which includes a tri-axial accelerometer, 2 gyroscopes, and a MSP430 microcontroller, is worn by the subjects at either T4 (at back) or as a belt-clip in front of the waist during the various tests. The raw data is wirelessly transmitted from the WGAS to a near-by PC for real-time fall classification. The BP ANN is optimized by varying the training, testing and validation data sets and training the network with different learning schemes. SVM is optimized by using three different kernels and selecting the kernel for best classification rate. The overall accuracy of BP ANN is obtained as 98.20% with LM and RPROP training from the T4 data, while from the data taken at the belt, we achieved 98.70% with LM and SCG learning. The overall accuracy using SVM was 98.80% and 98.71% with RBF kernel from the T4 and belt position data, respectively.展开更多
This paper presents a low-power CMOS analog front-end (AFE) IC designed with a selectable on-chip dual AC/DC- coupled paths for bio-sensor applications. The DC-coupled path can be selected to sense a biosignal with us...This paper presents a low-power CMOS analog front-end (AFE) IC designed with a selectable on-chip dual AC/DC- coupled paths for bio-sensor applications. The DC-coupled path can be selected to sense a biosignal with useful DC information, and the AC-coupled path can be selected for sensing the AC content of the biosignal by attenuating the unwanted DC component. The AFE IC includes a DC-coupled instrumentation amplifier (INA), two variable-gain 1st-order low pass filters (LPF) with tunable cut-off frequencies, a fixed gain 2nd-order Sallen-Key high-pass filter (HPF) with tunable cut-off frequencies, a buffer and an 8-bit differential successive approximation register (SAR) ADC. The entire AFE channel is designed and fabricated in a proprietary 0.35-μm CMOS technology. Excluding an external buffer needed to properly drive the ADC, the measured AFE IC consumes only 2.37 μA/channel with an input referred noise of ~40 μVrms in [1 Hz, 1 kHz], and successfully displays proper ECG (electrocardiogram) and electrogram (EGM) waveforms for QRS peaks detection. We expect that the low-power dual-path design of this AFE IC can enable it to periodically record both the AC and the DC signals for proper sensing and calibration for various bio-sensing applications.展开更多
文摘In this work, a total of 322 tests were taken on young volunteers by performing 10 different falls, 6 different Activities of Daily Living (ADL) and 7 Dynamic Gait Index (DGI) tests using a custom-designed Wireless Gait Analysis Sensor (WGAS). In order to perform automatic fall detection, we used Back Propagation Artificial Neural Network (BP-ANN) and Support Vector Machine (SVM) based on the 6 features extracted from the raw data. The WGAS, which includes a tri-axial accelerometer, 2 gyroscopes, and a MSP430 microcontroller, is worn by the subjects at either T4 (at back) or as a belt-clip in front of the waist during the various tests. The raw data is wirelessly transmitted from the WGAS to a near-by PC for real-time fall classification. The BP ANN is optimized by varying the training, testing and validation data sets and training the network with different learning schemes. SVM is optimized by using three different kernels and selecting the kernel for best classification rate. The overall accuracy of BP ANN is obtained as 98.20% with LM and RPROP training from the T4 data, while from the data taken at the belt, we achieved 98.70% with LM and SCG learning. The overall accuracy using SVM was 98.80% and 98.71% with RBF kernel from the T4 and belt position data, respectively.
文摘This paper presents a low-power CMOS analog front-end (AFE) IC designed with a selectable on-chip dual AC/DC- coupled paths for bio-sensor applications. The DC-coupled path can be selected to sense a biosignal with useful DC information, and the AC-coupled path can be selected for sensing the AC content of the biosignal by attenuating the unwanted DC component. The AFE IC includes a DC-coupled instrumentation amplifier (INA), two variable-gain 1st-order low pass filters (LPF) with tunable cut-off frequencies, a fixed gain 2nd-order Sallen-Key high-pass filter (HPF) with tunable cut-off frequencies, a buffer and an 8-bit differential successive approximation register (SAR) ADC. The entire AFE channel is designed and fabricated in a proprietary 0.35-μm CMOS technology. Excluding an external buffer needed to properly drive the ADC, the measured AFE IC consumes only 2.37 μA/channel with an input referred noise of ~40 μVrms in [1 Hz, 1 kHz], and successfully displays proper ECG (electrocardiogram) and electrogram (EGM) waveforms for QRS peaks detection. We expect that the low-power dual-path design of this AFE IC can enable it to periodically record both the AC and the DC signals for proper sensing and calibration for various bio-sensing applications.
