Electromyography (EMG) signal is one of the extensively utilised biological signals for predicting human motor intention, which is an essential element in human-robot collaboration platforms. Studies on motion intention prediction from EMG signals have often been concentrated on either classification and regression models of muscle activity. In this study, we leverage the information from the EMG signals, to detect the subject’s intentions in generating motion commands for a robot-assisted upper limb rehabilitation platform. The EMG signals are recorded from ten healthy subjects’ biceps muscle, and the movements of the upper limb evaluated are voluntary elbow flexion and extension along the sagittal plane. The signals are filtered through a fifth-order Butterworth filter. A number of features were extracted from the filtered signals namely waveform length (WL), mean absolute value (MAV), root mean square (RMS), standard deviation (SD), minimum (MIN) and maximum (MAX). Several different classifiers viz. Linear Discriminant Analysis (LDA), Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM) and k-Nearest Neighbour (k-NN) were investigated on its efficacy to accurately classify the pre-intention and intention classes based on the significant features identified (MIN and MAX) via Extremely Randomised Tree feature selection technique. It was observed from the present investigation that the DT classifier yielded an excellent classification with a classification accuracy of 100%, 99% and 99% on training, testing and validation dataset, respectively based on the identified features. The findings of the present investigation are non-trivial towards facilitating the rehabilitation phase of patients based on their actual capability and hence, would eventually yield a more active participation from them.
Stroke is amongst the leading causes of deprivation of one's ability in carrying out activities of daily living. It has been reported from literature that, the functional recovery of stroke patients are rather poor, unless frequent rehabilitative therapy is assumed on the affected limb. Recent trends of rehabilitation therapy have also shifted towards allowing more participation of the patient in the therapy session rather than simple passive treatments as it has been demonstrated to be non-trivial in promoting neural plasticity to expedite motor recovery process. Therefore, the employment of rehabilitation robotics is seen as a means of mitigating the limitations of conventional rehabilitation therapy. It enables unique methods for promoting patient engagement by providing patients assistance only as needed basis. This paper attempts on reviewing assist-as-needed control strategy applied on upper-limb robotic rehabilitation devices.
In this paper, a fuzzy inference system has been developed for automatic tea making process. The system takes five inputs and gives two output which determines the grade of black tea and milk tea. Specifically, the proposed system considers five important characteristics of hot tea beverage such as water temperature, sugar, milk, brewing time and tea leaves quantity for grading the standard of the drink according to the consumer's requirement. Both black tea and milk tea can be rated with a grade based on the human expert judgment which is according to the taste and aroma of the tea. This automatic tea making system can let the users choose their preferred type of tea without figuring out the complicated process to making a cup of hot tea beverage.