Classification of Different Shoulder Girdle Motions for Prosthesis Control Using a Time-Domain Feature Extraction Technique

Abstract

Abstract—The upper limb amputation exerts a significant burden on the amputee, limiting their ability to perform everyday activities, and degrading their quality of life. Amputee patients’ quality of life can be improved if they have natural control over their prosthetic hands. Among the biological signals, most commonly used to predict upper limb motor intentions, surface electromyography (sEMG), and axial acceleration sensor signals are essential components of shoulder-level upper limb prosthetic hand control systems. In this work, a pattern recognition system is proposed to create a plan for categorizing high-level upper limb prostheses in seven various types of shoulder girdle motions. Thus, combining seven feature groups, which are root mean square, four-order autoregressive, wavelength, slope sign change, zero crossing (ZC), mean absolute value, and cardinality. In this article, the time-domain features were first extracted from the EMG and acceleration signals. Then, the spectral regression (SR) and principal component analysis dimensionality reduction methods are employed to identify the most salient features, which are then passed to the linear discriminant analysis (LDA) classifier. EMG and axial acceleration signal datasets from six intact-limbed and four amputee participants exhibited an average classification error of 15.68 % based on SR dimensionality reduction using the LDA classifier.

An optimal method for diagnosing heart disease using combination of grasshopper evalutionary algorithm and support vector machines

“…The search procedure in this algorithm is split into two phases: exploration and exploitation. While during exploitation they prefer to move locally, search agents are pushed to move quickly during exploration [ 49 , 50 ]. Along with target search, locusts intuitively carry out these two tasks.…”

Presenting a New Approach for Clustering Optimization in Wireless Sensor Networks using Fuzzy Cuckoo Search Algorithm

“…It is feasible to produce random values that satisfy the first two requirements since the current nodes are dispersed randomly throughout the environment using various techniques. Making up positive random values and dividing them all by their sum is one of the easiest methods [31,32]. Values between zero and one are generated using this straightforward method, and their sum equals one.…”

“…For wireless sensor network clustering, a novel optimization strategy based on the cuckoo algorithm and multi-objective genetic algorithm is thus described in this study. The research in [19] used near-optimal routing based on the cuckoo optimization algorithm to transmit data between nodes in order to choose cluster nodes from a multi-objective genetic algorithm based on reducing intracluster distances and reducing energy consumption in cluster member nodes. The results of the implementation demonstrate that the suggested method has improved over previous methods in terms of energy consumption, efficiency, delivery rate, and packet transmission delay.…”

“…The number of steps on the path is indicated in the fourth entry. The three levels of definition for this entry are the number of little steps, the number of average steps, and the number of large steps [19], [47], [50]. Its membership function is also displayed in Fig.…”

“…The fuzzy system output makes use of the composite Gaussian function. In reality, this function combines two Gaussian functions with varying values of σ and c on the left and right sides [32] in order for c1<c2 and σ1<σ2. The path's optimality is determined by the outputs from CWR to CBR.…”