Though DBS is suiting well to Parkinson`s still its current version being modified now and often as suggested by the neuroscientists. The technique has gained an effectual management surgical therapy concerned to PD, explicitly whilst growing idea as an effectual method to alleviate Parkinson’s disease and other movement disorders. The present ver.1 indirect DBS is an open loop based and its parameters are changeable manually and there is no provision to adjust automatically or online based on Parkinson diseased behavior and performance. Hence, supervised classification of patient behavior is a major and significant step towards the design of next generation DBS systems which are adaptive closed loop based. The work in this study demonstrates a supervised classification machine learning (CML, i.e., multiple kernel learning M-K-L) method to distinguish such cognitive behavioral tasks by using the subthalamic nuclei (STN) biomarkers, i.e., biomedical data of microelectrode recording (MER) bio signals (or local field potential LFP). We applied the time domain and frequency domain representation spectrograms of the raw data acquired from right and left hemisphere brain`s STNs as the feature vectors. Following the feature extractions, we combined those features via support vector machines (SVMs) with complex multifaceted root learning, i.e., C-M-L or multi kernel learning (M-K-L) formulation. The C-M-L based classification techniques were applied to a class and categorize different tasks such as switch (push-pull button), movement of jaws, vocalizations, plus movement of arm due to the tremor. Our experiments show that the l - n o r m C-M-L/M-K-L radically smash distinct kernel SVM-based classifiers in classifying behavioral tasks of five subjects even using signals acquired with a low sampling rate of 10 Hz. This leads to a lower computational cost.
In recent trends, Cognitive Radio Sensor Networks (CRSNs) are investigated in‐depth and getting momentum in all types of applications. CRSN can make use of the underutilized frequency spectrum in a suitable manner. Due to the above‐mentioned advantage, the scholars have initiated to study of the domain of cognitive radio routing. Network congestion produces transmission delays and packet loss, as well as time and energy wasted on recovery. In order to fulfill the energy efficiency and network lifetime in CRSN, Congestion Centric Multi‐Objective Reptile Search Algorithm (CC‐MORSA)‐based Clustering and Routing are used. The main objective of proposed CC‐MORSA is to improve the lifetime by minimizing the distance among the designated Cluster Head nodes which creates the fitness function by multiple objectives like energy, distance, and load. This technique is appropriate for common sensor nodes in coordinated communications infrastructure and large networks. The simulation results are analyzed through MATALB in terms of remaining energy (999.5 J), average delay (0.36 s), Packet Delivery Ratio (99.8%), Energy Consumption (24.1 J), Throughput (0.98 Mbps), routing overhead (0.54), and Packet Loss Rate (0.2%). From the outcomes, it shows that the presented CC‐MORSA outperformed conventional Stability‐Aware Cluster‐based Routing and Drop Factor‐Based Energy Efficient Routing technique.
In Brain Computer Interface (BCI), achieving a reliable motor-imagery classification is a challenging task. The set of discriminative and relevant feature vectors plays a crucial role in classification. In this article, an enhanced optimization technique is implemented for selecting active feature vectors to enhance motor-imagery classification using Electroencephalography (EEG) signals. After collecting the input EEG signals from BCI competition III-4a and IV-2a databases, the 6th-order butter-worth filter is employed for eliminating base-line wander noise from the raw EEG signals. Further, the Variational Mode Decomposition technique is applied for separating the important signal components from the composite EEG signals, and then, the Higher Order Statistic, kurtosis, skewness, standard deviation, and entropy are utilized for feature extraction. The high-dimensional feature values are given to the Enhanced Grasshopper Optimization Algorithm for optimum feature selection, which are given to the Extreme Learning Machines (ELM) classifier for motor-imagery classification. Finally, in the resulting section, the optimized ELM model achieved 99.48% and 99.12% of accuracy on the BCI competition III-4a and IV-2a databases, where the achieved results are maximum compared to the traditional deep learning models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.