Journal of Medical Signals and Sensors
Volume:13 Issue: 1, Jan -Mar 2023

The first step in developing new drugs is to find binding sites for a protein structure that can be used as a starting point to design new antagonists and inhibitors. The methods relying on convolutional neural network for the prediction of binding sites have attracted much attention. This study focuses on the use of optimized neural network for three‑dimensional (3D) non‑Euclidean data.

A graph, which is made from 3D protein structure, is fed to the proposed GU‑Net model based on graph convolutional operation. The features of each atom are considered as attributes of each node. The results of the proposed GU‑Net are compared with a classifier based on random forest (RF). A new data exhibition is used as the input of RF classifier.

The performance of our model is also examined through extensive experiments on various datasets from other sources. GU‑Net could predict the more number of pockets with accurate shape than RF.

This study will enable future works on a better modeling of protein structures that will enhance knowledge of proteomics and offer deeper insight into drug design process.

Alcohol addiction contributes to disorders in brain`s normal patterns. Analysis of electroencephalogram (EEG) signal helps to diagnose and classify alcoholic and normal EEG signal.

One-second EEG signal was applied to classify alcoholic and normal EEG signal. To determine discriminative feature and EEG channel between the alcoholic and normal EEG signal, different frequency and non-frequency features of EEG signal, including power of EEG signal, permutation entropy (PE), approximate entropy (ApEn), katz fractal dimension (katz FD) and Petrosion fractal dimension (Petrosion FD) were extracted from alcoholic and normal EEG signal. Statistical analysis and Davis-Bouldin criterion (DB) were utilized to specify and select most discriminative feature and EEG channel between the alcoholic and normal EEG signal.

Results of statistical analysis and DB criterion showed that the Katz FD in FP2 channel showed the best discrimination between the alcoholic and normal EEG signal. The Katz FD in FP2 channel showed the accuracies of 98.77% and 98.5% by two classifiers with 10-fold cross validation.

This method helps to diagnose alcoholic and normal EEG signal with the minimum number of feature and channel, which provides low computational complexity. This is helpful to faster and more accurate classification of normal and alcoholic subjects.

In this paper, the method of designing a noninvasive device for eliminating hand tremors in Parkinson’s patients is presented. The designed device measures the tremors of the patient’s hand and implements the tremor control accordingly. Since Parkinson’s disease reduces patients’ abilities to perform daily activities, this device is designed as an electronic spoon. The inertial measurement units are used to measure hand tremors.

The signals got from motion sensors are passed through Butterworth’s second order low pass filters to attenuate signals amplitude at frequencies higher than the human hand’s natural frequency. The signals are sent to a proposed Proportional Integral (PI) fuzzy controller as a set point signal, and appropriate control signals are applied to two actuators installed orthogonal. Besides motion sensors, a microcontroller is installed inside the spoon handle that implements a PI fuzzy controller and provides control signals for two high speed servo motors installed perpendicularly.

As such, the spoon can minimize the tremor effect. In this system, no damper or mass is added to the hand, and the patients are not required to wear an orthosis. The contribution of this paper is twofold. First, we use sensor data fusion to increase measurement accuracy. In this paper, we use accelerometer and gyroscope sensors. Second, we proposed a robust PI fuzzy controller to compensate for the uncertainties and reduce the tremor.

The test results show that the hand tremor of Parkinson’s patients during eating is reduced up to 75% using this method.

This study was conducted to compare the response between the results of experimental data and the results achieved by the NARX neural network model to predict the electromyogram (EMG) signal on the biceps muscle in nonlinear stimulation conditions as a new stimulation model.

This model is applied to design the controllers based on functional electrical stimulation (FES). To this end, the study was conducted in five stages, including skin preparation, placement of recording and stimulation electrodes, along with the position of the person to apply the stimulation signal and recording EMG, stimulation and recording of single‑channel EMG signal, signal preprocessing, and training and validation of the NARX neural network. The electrical stimulation applied in this study is based on a chaotic equation derived from the Rossler equation and on the musculocutaneous nerve, and the response to this stimulation, i.e., the EMG signal, is from the biceps muscle as a single channel. The NARX neural network was trained, along with the stimulation signal and the response of each stimulation for 100 recorded signals from 10 individuals, and then validated and retested for trained data and new data after processing and synchronizing both signals.

The results indicate that the Rossler equation can create nonlinear and unpredictable conditions for the muscle, and we also can predict the EMG signal with the NARX neural network as a predictive model.

The proposed model appears to be a good method to predict control models based on FES and to diagnose some diseases.

Laryngeal damages after chemoradiation therapy (RT) in nonlaryngeal head‑and‑neck cancers (HNCs) can cause voice disorders and finally reduce the patient’s quality of life (QOL). The aim of this study was to evaluate voice and predict laryngeal damages using statistical binary logistic regression (BLR) models in patients with nonlaryngeal HNCs.

This cross‑section experimental study was performed on seventy patients (46 males, 24 females) with an average age of 50.43 ± 16.54 years, with nonlaryngeal HNCs and eighty individuals with assumed normal voices. Subjective and objective voice assessment was carried out in three stages including before, at the end, and 6 months after treatment. Eventually, the Enter method of the BLR was used to measure the odds ratio of independent variables.

In objective evaluation, the acoustic parameters except for F0 increased significantly (P < 0.001) at the end treatment stage and decreased 6 months after treatment. The same trend can be seen in the subjective evaluations, whereas none of the values returned to pretreatment levels. Statistical models of BLR showed that chemotherapy (P < 0.05), mean laryngeal dose (P < 0.05), V50 Gy (P = 0.002), and gender (P = 0.008) had the greatest effect on incidence laryngeal damages. The model based on acoustic analysis had the highest percentage accuracy of 84.3%, sensitivity of 87.2%, and the area under the curve of 0.927.

Voice evaluation and the use of BLR models to determine important factors were the optimum methods to reduce laryngeal damages and maintain the patient’s QOL.

Physical fitness refers to the ability of the body to perform tasks or do one of the physical activities well without being tired quickly. The objective of this research is to develop a physical fitness instrument for measuring oneself heart rate, grip strength, and reaction time that could develop a model for a self‑check‑up on physical fitness which helps to plan the improvement for health which is called the “FIBER‑FIT” model.

The physical fitness measuring instrument is composed of three modules; (1) heart rate meter module using a green light emitting diode and a photosensor, (2) grip strength meter module using a load cell transducer, and (3) reaction time meter module using a computer graphical function. All modules are controlled by computer programming, LabVIEW. The program could measure the physical fitness parameters in real‑time and display the results in graphs, values on a computer monitor. The data could be recorded on cloud storage and could be retrieved for viewing and analyzing from anywhere via the internet.

Getting the “FIBER‑FIT” model, a physical fitness measuring instrument to evaluate and analyze the results in real time. Overall performance test results were comparable to the standard commonly used instruments. The satisfaction survey scores from the participants were 33.33% and 66.67% for the highest level and the high level, respectively.

The Cloud “FIBER‑FIT” model is recommended for physical fitness applications for health improvement.

Social stress affects brain function. Trier social stress test (TSST) is a standard test to assess it. The study aimed to analyze the electroencephalographic (EEG) recording during and after TSST in healthy subjects. The EEG signals of 44 healthy men participating in the study were recorded in the control condition, during and after TSST and after 30 min of recovery. Salivary cortisol (SC) and the Emotional Visual Analog Scale (EVAS) score were measured in the control condition, after TSST, and after the recovery period. The false discovery rate correction was used to control the false positive of significance in EEG. In the comparison control condition, the SC and EVAS levels significantly increased after TSST. The relative Delta band frequency significantly increased during TSST. On the other hand, the Beta bands and, in less amount, the Theta and Gamma 1 (30–40 Hz) oscillations decreased, especially in the frontal region. The nonlinear features such as, approximate and spectral entropy, Katz fractal dimension behaved like Beta band oscillation. All changes returned to baseline after TSST except the increase of Katz in the F3 channel after the recovery period. Thus, stress on EEG increased low frequency (1–4 Hz), decreased high frequency (13–40 Hz), and complexity indices during TSST.

Type 2 diabetes mellitus (T2DM) is associated with decreased muscle force generation. The disturbed force generation process in T2DM could be attributed to either or both agonist and antagonist muscles activation. The present study aims to assess the effects of T2DM on the interaction of antagonist and agonist muscles in the knee joint.

The peak torque, root mean square (RMS) of the SEMG signals, the ratio of torque/RMS, and the interaction of antagonists and agonist muscles were compared between healthy and T2DM patients. Surface ElectroMyoGraphy (SEMG) of knee flexor and extensor muscles were recorded during concentric contraction with an isokinetic dynamometer at 60°/s in 13 T2DM and 12 healthy subjects. The independent sample t‑tests were used to compare diabetic and healthy subjects. The significance level was set at 0.05.

The antagonist/agonist interaction during maximal extension (P = 0.010) and flexion (P = 0.022) torques of the knee joint showed significantly lower activation of antagonist muscles in T2DM patients than in healthy subjects. Lower knee flexion (41.3%) and extension torques (49.1%) and RMS of agonist and antagonist muscles were observed in T2DM. The torque/RMS ratio (P > 0.05) showed no significant differences in T2DM and healthy subjects.

The reduced maximal knee flexor and extensor torques in T2DM are accompanied with the decreased myoelectric activity of corresponding muscles. The related mechanism could be attributed to lower values of antagonist/agonist interaction, which may point out some neural compensatory processes to preserve the functional capacity of the neuromuscular system in T2DM.