Electromyogram-Based Classification of Hand and Finger Gestures Using Artificial Neural Networks

Wearable e-health system, are frequently used for monitoring biomedical signals. These devices need to have advanced and applicable methods of feature selection and classifications for real time applications. Electromyogram (EMG) signal records the movement of the human muscle. EMG signal processing techniques aim to achieve the actual signal and among others, detect the state of signals related to positive and negative emotional expression. In our study, the data collected is from the facial muscle activity that is produced by the emotion of the facial expressions. The key challenge is in finding an accurate classification method of the measured signals. This paper investigates the promising techniques for the detection and classification of EMG signal using machine-learning theory. Here, we demonstrated Support Vector Machine (SVM) is an optimal method for classification of facial surface Electromyogram (sEMG) signal associated to pain dataset. The test results and the methods are able to analyze the patterns recognition of facial EMG signal classification. The result and the findings 99% accuracy with SVM method adds value on the classification algorithms of our EMG signal acquisitions platform.

The electromyogram (EMG) signal has been used as the command input to myoelectric prostheses. A common control scheme is based on classifying the EMG signals from multiple electrodes into one of several distinct classes of user intent/function. In this work, we investigated the use of EMG whitening as a preprocessing step to EMG pattern recognition. Whitening is known to decorrelate the EMG signal, with improved performance shown in the related applications of EMG amplitude estimation and EMG-torque processing. We reanalyzed the EMG signals recorded from 10 electrodes placed circumferentially around the forearm of 10 intact subjects and 5 amputees. The coefficient of variation of two time-domain features--mean absolute value and signal length--was significantly reduced after whitening. Pre-whitened classification models using these features, along with autoregressive power spectrum coefficients, added approximately five percentage points to their classification accuracy. Improvement was best using smaller window durations (<100 ms).

In recent years, there has been extensive interest in the revelation of different technologies for artificial neural network (ANN) application in various classification of biomedical signals. Several publications have focused on diverse applications of ANN techniques for biomedical signals classification, detection, and processing. This review work gives an overview on the multilayer perceptron (MLP) technique of ANN and how this technology is useful for the classification of EMG signal. This paper will be interesting for those researchers who are studying the classification EMG signal for tremor detection in Parkinson’s disease. Many researchers have worked and also working on Parkinson’s disease tremor by using EMG signal and classifying its feature using ANN. Among those various techniques, MLP technique is highlighted in this work for the classification of EMG signal. The core center of this paper is to review the evolution and research works related to the topic mentioned above.

Industrial robots are widely used in critical tasks such as assembly, welding, and material handling as core components of modern manufacturing systems. For the reliable operation of these systems, early and accurate detection of execution failures is crucial. In this study, a comprehensive comparison of machine learning and deep learning methods is conducted for the classification of robot execution failures using data acquired from force-torque sensors. Three different feature engineering approaches are proposed. The first is a Baseline approach that includes 90 raw time-series features. The second is the Domain-6 approach, which consists of 6 basic statistical features per sensor (36 in total). The third is the Domain-12 approach, which comprises 12 comprehensive statistical features per sensor (72 in total). The domain features include the mean, standard deviation, minimum, maximum, range, slope, median, skewness, kurtosis, RMS, energy, and IQR. In total, ten classification algorithms are evaluated, including eight machine learning methods and two deep learning models: Support Vector Machines (SVM), Random Forest (RF), k-Nearest Neighbors (KNN), Artificial Neural Network (ANN), Naive Bayes (NB), Decision Trees (DT), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM-LGBM), as well as a One-Dimensional Convolutional Neural Network (CNN-1D) and Long Short-Term Memory (LSTM). For traditional machine learning algorithms, 5 × 5 nested cross-validation is used, whereas for deep learning models, 5-fold cross-validation with a 20% validation split is employed. To ensure statistical reliability, all experiments are repeated over 30 independent runs. The experimental results demonstrate that feature engineering has a decisive impact on classification performance. In addition, regardless of the feature set, the highest accuracy (93.85% ± 0.90) is achieved by the Naive Bayes classifier using the Baseline features. The Domain-12 feature set provides consistent improvements across many algorithms, with substantial performance gains. The results are reported using accuracy, precision, recall, and F1-score metrics and are supported by confusion matrices. Finally, permutation feature importance analysis indicates that the skewness features of the Fx and Fy sensors are the most critical variables for failure detection. Overall, these findings show that time-domain statistical features offer an effective approach for robot failure classification.

In the study of detection of an epileptic seizure using Electroencephalogram (EEG), pattern recognition has been recognized as a valued tool. In this pattern recognition study, the first time the authors have attempted to use time domain (TD) features such as waveform length (WL), number of zero-crossings (ZC) and number of slope sign changes (SSC) derived directly from filtered EEG data and from discrete wavelet transform (DWT) of filtered EEG data for the detection of an epileptic seizure. Further, the authors attempted to study the performance of other time domain features such as mean absolute value (MAV), standard deviation (SD), average power (AVP), which had been attempted by other researchers. The performance of the TD features is studied using naive Bayes (NB) and support vector machines (SVM) classifiers for the university of Bonn database with fourteen different combinations of set E with set A to D. The proposed scheme was also compared with other existing scheme in the literature. The implementation results showed that the proposed scheme could attain the highest accuracy of 100% for normal eyes open and epileptic data set with direct as well as DWT based TD features. For other data sets, the highest accuracy is obtained with DWT based TD features using SVM. However, no significant difference in the classification of 14 data sets with TD features filtered EEG data and from DWT of filtered EEG data.

Surface electromyogram (sEMG) signals are widely used to control the myoelectric prosthetic arm for amputees. In this study, the authors investigated the usefulness of discrete wavelet transform (DWT) features from multiple levels of approximation and detail coefficients obtained from sEMG signals. DWT is used for de-noising as well as feature extraction in this study and further tested using Support Vector Machine (SVM) classifier and Artificial Neural Network (ANN) Classifier. The performance of SVM classifier is compared with ANN classifier. The classification accuracy of SVM classifiers was found better as compared to ANN in term of speed and robustness. In the first section of paper the authors presented the introduction related to the study. The experimental set-up for recording surface EMG signal is presented in section 2. In section 3 the experimental results are depicted and in section 4 the results are concluded.

Air pollution in Macau has become a serious problem following the Pearl River Delta’s (PRD) rapid industrialization that began in the 1990s. With this in mind, Macau needs an air quality forecast system that accurately predicts pollutant concentration during the occurrence of pollution episodes to warn the public ahead of time. Five different state-of-the-art machine learning (ML) algorithms were applied to create predictive models to forecast PM2.5, PM10, and CO concentrations for the next 24 and 48 h, which included artificial neural networks (ANN), random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and multiple linear regression (MLR), to determine the best ML algorithms for the respective pollutants and time scale. The diurnal measurements of air quality data in Macau from 2016 to 2021 were obtained for this work. The 2020 and 2021 datasets were used for model testing, while the four-year data before 2020 and 2021 were used to build and train the ML models. Results show that the ANN, RF, XGBoost, SVM, and MLR models were able to provide good performance in building up a 24-h forecast with a higher coefficient of determination (R2) and lower root mean square error (RMSE), mean absolute error (MAE), and biases (BIAS). Meanwhile, all the ML models in the 48-h forecasting performance were satisfactory enough to be accepted as a two-day continuous forecast even if the R2 value was lower than the 24-h forecast. The 48-h forecasting model could be further improved by proper feature selection based on the 24-h dataset, using the Shapley Additive Explanations (SHAP) value test and the adjusted R2 value of the 48-h forecasting model. In conclusion, the above five ML algorithms were able to successfully forecast the 24 and 48 h of pollutant concentration in Macau, with the RF and SVM models performing the best in the prediction of PM2.5 and PM10, and CO in both 24 and 48-h forecasts.

Surface electromyography (EMG) is widely used in hand gesture recognition for human-computer interface (HCI). This paper presents a finger gesture recognition scheme at two level of plane pressing force through the fusion of wrist EMG and accelerometers (ACC). The classification algorithm is evaluated on eight healthy subjects for identifying five finger gestures at two plane pressing force level. Experimental results show that frequency domain (improved discrete Fourier, iDFT) feature is better than time domain (TD) feature for wrist EMG classification. Moreover, it indicates that the fusion of EMG and ACC achieved improved recognition performance (85.77%) for finger gestures at two level of plane pressing force when compared to that obtained using EMG (80.65%) or ACC (56.86%) solely.

An alternative approach for soil characterization is proposed, using digital images and machine learning. The present work investigated the Red, Green, and Blue (RGB) pattern with Artificial Neural Network (ANN) and Random Forest (RF) in the classification of Oxisol and Inceptisol collected in South Brazil. Furthermore, we also built ANN, RF, Partial Least Squares (PLS), and Support Vector Machine (SVM) models from digital images to quantify Total Carbon (TC) content in soil samples. Preliminary evaluations considered the hypothesis that alternative methods of classification and quantification of soil properties might provide results comparable to traditional methods. The TC content of 91 soil samples, 40 from Oxisol and 51 from Inceptisol were determined by dry combustion. ANN and RF as machine learning algorithms were applied to classify the two kinds of soils. The classification quality was assessed by the percentage of correctly classified instances. The results suggest using digital images and machine learning algorithms as a new methodology to soil classification. The best machine learning method was RF which can be used to classify soil types by the RGB channel colors of the soil images. The use of digital images and RF is a clean (eco-friendly), rapid, and affordable strategy analysis for TC quantification in soils. Therefore, the proposed methods represent an advancement in soil classification, such as the determination of the TC content of soils.

Wearable device is becoming more and more popular, the emergence of wearable equipment, is widely used in daily life, medical, industrial and scientific research and so on. But most of the wearable equipment still needs people's actual operation, which will bring a lot of inconvenience. For example, when people's hands are not available, they can't be operated. Now, many sensors are embedded in off-the-shelf smartwatch, which make it possible to detect different finger gestures by using these sensors. Past research mostly concentrates on identifying gross hand gestures, which usually need the help of other additional hardware that is expensive and discomfort. In this work we utilize muscle activity data getting from integrated motion sensors (accelerometer, linear accelerometer and gyroscope) nested in smartwatch to recognize tiny finger gestures. We extract features within a 1 second sliding window. We test classification effect of different classifiers and different sensors. In the result, we can recognize 5 unremarkable finger gestures well and identify specific finger gestures with a high accuracy. The result can be applied on current popular smartwatches interaction. Also our result will lay the foundation for related research in finger gestures recognition field.

Characterization of Electromyogram (EMG) signals is important for identifying neuromuscular diseases. Although various techniques were implemented for classification, none of them were implemented in the complexity domain. In this study, characterization of EMG signals recorded from healthy, neuropathic and myopathic subjects has been performed in complexity domain based on Multiscale Entropy (MSE) method. To do this, the multiscale entropy method has been applied to an EMG database publicly available in PhysioNet. The complexity profile curves obtained with the MSE approach have shown promising classification among healthy subject, neuropathic and myopathic patients in terms of complexity. One way ANOVA test has shown statistically significant differences (p<0.01) among these three classes. Moreover, Support Vector Machine (SVM) has demonstrated a classification accuracy of 86.1% for characterizing EMG signals of neuromuscular disorders. Furthermore, myopathic and neuropathic patients have been recognized with 66.7% sensitivity at 95.8% specificity and 100% sensitivity at 100% specificity respectively.

This systematic review summarizes the application of artificial intelligence (AI) in classifying upper-limb motion using Electroencephalogram (EEG) and Electromyogram (EMG) signals, focusing on the field's progression from Traditional Machine Learning (TML) to Deep Learning (DL) architectures. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a search of PubMed, IEEEXplore, and Web of Science yielded 301 eligible studies published up to June 2025. The results indicate a change from classical classifiers like Linear Discriminant Analysis (LDA) and Support Vector Machines (SVMs) toward DL approaches. While Convolutional Neural Networks (CNNs) remain the most frequently implemented, emerging architectures, including Long Short-Term Memory (LSTM) networks and Transformers, have demonstrated remarkable performance. Despite the rise of DL, classical models remain highly relevant due to their robustness and efficiency. This review also identifies a heavy reliance on EEG-only modalities (60%), with only 7% of studies utilizing hybrid EEG-EMG systems, representing a potential missed opportunity for signal fusion.

GIS-based mineral prospectivity mapping using machine learning methods: A case study from Tongling ore district, eastern China

Background and Objectives: Partial nephrectomy (PN) is the preferred option for treating localized cT1 renal cell carcinoma (RCC), as it preserves renal function in most patients and offers non-inferior oncological outcomes compared to radical nephrectomy. In this study, we aimed to construct a predictive model for estimating the glomerular filtration rate (GFR) at one year after PN in patients with RCC, using various machine learning techniques. Methods: Retrospective data were collected from two academic centers, covering surgeries performed between 2010 and 2022. GFR was estimated using the Chronic Kidney Disease Epidemiology Collaboration 2021 (CKD-EPI) formula. Univariable linear regression (LR) was used to identify significant clinical predictors of 1-year postoperative GFR, followed by multivariable LR. The dataset was split into training and testing cohorts in a 70:30 ratio. Internal validation was performed on the test cohort, and various machine learning methods, including artificial neural networks (ANNs), support vector machines (SVMs), random forests (RFs), and XGBoost, were compared. Results: Among 615 patients treated with PN, 415 had complete follow-up GFR data and were included in the analysis. Only 8.7% of patients experienced significant GFR loss (>30% decrease) at 1 year. Multivariable LR identified baseline GFR (Estimate: 0.76, p < 0.001), tumor diameter on imaging (Estimate: -1.65, p = 0.005), and Charlson Comorbidity Index (Estimate: -1.95, p < 0.001) as independent predictors of 1-year GFR (R2 = 0.67). A 10-fold cross-validation of the multivariable model yielded an R2 of 0.68. In the testing cohort, ANN, SVM, RF, and XGBoost did not outperform the LR model, with R2 values of 0.68, 0.66, 0.64, and 0.55, respectively. Conclusions: Preoperative factors, including baseline GFR, tumor size on imaging, and Charlson Comorbidity Index, are effective predictors of GFR at 1 year following PN. Our study demonstrates that a conventional LR model based on preoperative variables provides acceptable accuracy for predicting GFR after PN and is not inferior to more complex machine learning techniques.

Hand gesture recognition is a relevant study topic for a reason that sometimes we may not be in position to communicate verbally. There is need to design Hand gesture recognition systems in order to help people adopt to nonverbal communication mainly sign language. However, there is no clue to understand the meaning of gesture through the computers directly. So this calls for definitions that generalize models in a computer. That is why the machine-learning approaches are implemented in recognition systems. There are generally two types of hand gestures recognition systems which researches have concentrated on. These include static and dynamic Hand gesture recognition systems. However, in building Hand gesture recognition systems, various machine learning approaches have been used. For implementing the proposed system, MS Kinect depth sensor was used as a hardware. The Kinect depth sensor is composed of an infrared camera. This is an advantage to the systems that are designed basing on the depth sensing because factors like color, clothing and background have less effect on the performance. So Kinect based depth sensor systems have a high accuracy and performance making them relevant and applicable in our daily lives. In this paper, we propose a static hand gesture recognition system in real time using two machine learning methods namely Support Vector Machine and Artificial Neural Networks. We use of the newly launched Microsoft Kinect sensor for image extraction. The sensor helps us to extract the hand images. We implement the system on a Matlab platform for reasons that Matlab is widely used by researchers in different fields and that can handle complex computations. In the training of the model, we collect a hundred depth-based Histogram of Oriented Gradient features per alphabet from the hand gesture images which we trained, tested and validated using Artificial Neural Networks (ANN) and Support Vector Machine (SVM). From this dataset, we can generate the generalized gesture model for each alphabet image. For the proposed system, the classification with ANN proves a higher performance then SVM.