Search

In this paper; denoising; feature extraction and classification are proposed based on Wavelet Packet Transform(WPT) of Surface Electromyogram signal (sEMG) using Fine Gaussian SVM. sEMG signal was acquired from nine healthy subjects. And then; pre-processing was carried out using MyoResearch XP Software. Further; denoising was improvised using Discrete Wavelet Packet Transform (DWPT). Mother wavelet Daubechies (db 7) at level 4 (Shannon Entropy function) with global threshold (soft) value 1.007 was used for Time-Frequency Domain(TFD) feature extraction so that the possibility of Mean Square Error(MSE) should be minimum. Using Fine Gaussian SVM; an average accuracy of 92.8% and overall MSE of 7.2% was achieved. Five-fold cross valediction methods were performed in this study. The main advantages of this approach are low training time (approximately 2 seconds) and fast speed of response. Using this classification approach; controlling the external robotic device can be achieved in a smooth manner.

This paper presents the design and development of a Graphical User Interface (GUI) for real time monitoring and analysis of vital human body parameters such as surface body temperature, blood pressure, heart rate, ECG and Spirometry. The objective of the proposed work is to display the body temperature, blood pressure, heart rate, ECG and oxygen consumption of the human body in real time. Vernier Surface Temperature Sensor, Vernier Blood Pressure Sensor, Vernier Hand Grip Heart Rate Monitor, Vernier ECG Sensor and Vernier Spirometer, provided by National Instruments are employed for measuring the body temperature, Blood Pressure, Heart Rate, ECG and oxygen consumption respectively. The sensors are interfaced with the computer using NI ELVIS prototype board. The output of the sensors is processed using LabVIEW software and is displayed on the computer screen. The resultant output from the sensors displays the condition of the human body by means of an indicator using LabVIEW. It is green when the output is within healthy conditions and is red when it goes beyond the normal range or limits. The body temperature sensor is calibrated using standard clinical thermometer and the blood pressure sensor is also calibrated using standard sphygmomanometer. The ECG sensor and Spirometer is calibrated using Patient's Clinical Reports. When compared to existing systems, it was found that the developed GUI measures all the five parameters accurately.

Surface Electromyography (sEMG) signal plays an important role in various engineering application to make partially disabled person's life as smooth as normal. In this work, few selected time domain and time scale features were used as an input to linear Support Vector Machine (SVM) Classifier. Timescale feature was extracted using Wavelet Packet Transform (WPT). WPT are also used for noise reduction and compression of unnecessary disturbance. Impelling employment of SVM in classification needed the appropriate selection of a kernel function. Total Training Data was 303 observations acquired from eight healthy subjects, which were used to train the linear SVM classifier 114 data for extension and 189 data for flexion. Out of 114, 105 extension data were truly classified and only nine extension data were falsely classified. Out of 189 flexion data, 171 were truly classified and only eighteen were falsely classified. The simulation results show 91.1% classification accuracy for elbow movement which can be used to control any bidirectional robotic vehicle.