PCA-based muscle selection for interventional manipulation recognition

Background: Surface electromyography (sEMG) of periocular muscles is a non-invasive technique used to assess eyelid dynamics and facial neuromuscular function, with applications in ophthalmology, neurology, and rehabilitation. Despite its clinical and research potential, substantial methodological variability-particularly in electrode placement, acquisition parameters, and signal processing-has limited reproducibility and hindered broader clinical translation. A comprehensive synthesis of existing methodologies was therefore needed to support future standardization. Objectives: The review aimed to systematically map current periocular sEMG methodologies, identify sources of methodological heterogeneity, organize findings into structured methodological domains, and develop a conceptual framework along with a minimum reporting set to promote transparency, reproducibility, and comparability across studies. Eligibility Criteria: Studies were eligible if they investigated surface electromyography of periocular muscles and reported methodological details related to electrode placement, signal acquisition, processing, or analysis. Randomized controlled trials, observational studies, and pilot investigations were included. No restrictions were placed on publication year. Sources of Evidence: Comprehensive searches were conducted in PubMed, Embase, and Web of Science from database inception through November 2025. Grey literature sources were also examined to enhance coverage and reduce publication bias. Charting Methods: Two reviewers independently screened records and extracted data. Extracted information was organized into predefined methodological domains. A thematic synthesis approach was used to identify recurring methodological patterns, and findings were integrated into a structured conceptual framework. Results: Sixteen studies published between 2002 and 2025 met the inclusion criteria, encompassing randomized trials, observational studies, and pilot investigations. Considerable heterogeneity was identified across studies in electrode characteristics, placement strategies, reference configurations, sampling frequencies, and normalization procedures. Three recurring methodological domains emerged: instrumentation and acquisition, analytical and normalization approaches, and clinical or experimental applications. Based on these domains, the authors developed a conceptual methodological framework and proposed a minimum reporting set intended to improve methodologyical transparency and support reproducibility and multicenter comparability. Conclusions: Periocular sEMG represents a promising yet methodologically fragmented field. This scoping review provides the first comprehensive synthesis of periocular sEMG practices and establishes an evidence-based platform for standardized acquisition, processing, and reporting. Adoption of the proposed framework may strengthen reproducibility, facilitate multicenter collaboration, and accelerate integration into clinical and research settings.

The incidence and mortality rate of the primary liver cancer are very high and its postoperative metastasis and recurrence have become important factors to the prognosis of patients. Circulating tumor cells (CTC), as a new tumor marker, play important roles in the early diagnosis and individualized treatment. This paper presents an effective method to distinguish liver cancer based on the cellular scattering spectrum, which is a non-fluorescence technique based on the fiber confocal microscopic spectrometer. Combining the principal component analysis (PCA) with back propagation (BP) neural network were utilized to establish an automatic recognition model for backscatter spectrum of the liver cancer cells from blood cell. PCA was applied to reduce the dimension of the scattering spectral data which obtained by the fiber confocal microscopic spectrometer. After dimensionality reduction by PCA, a neural network pattern recognition model with 2 input layer nodes, 11 hidden layer nodes, 3 output nodes was established. We trained the network with 66 samples and also tested it. Results showed that the recognition rate of the three types of cells is more than 90%, the relative standard deviation is only 2.36%. The experimental results showed that the fiber confocal microscopic spectrometer combining with the algorithm of PCA and BP neural network can automatically identify the liver cancer cell from the blood cells. This will provide a better tool for investigating the metastasis of liver cancers in vivo, the biology metabolic characteristics of liver cancers and drug transportation. Additionally, it is obviously referential in practical application.

Surface EMG of proximal leg muscles in neuromuscular patients and in healthy controls. Relations to force and fatigue

Palmprint recognition system has been one promising biometric system used in Presence System. There are some methods to recognize the individual palmprint as well as to extract its feature. In this research, two recognition methods are compared, i.e., backpropagation neural network and similarity measure using Euclidean distance. While, for feature extraction, we implemented Principal Components Analysis (PCA) method. From the research, it can be concluded that from test results, the best recognition using backpropogation neural networks is 93.33% which is reached when parameters used are: 100 principal components, 1 hidden layer, and 75 neurons. While, implementation of similarity measure using Euclidean distance, the best recognition rate is 96.67% which is reached when 75 principal components are used. When considering the time consumed in recognition, the Euclidean distance gives the better result, i.e. 17.09 seconds, while using backpropagation neural network with 75 neurons, time consumed is 425 seconds. Therefore, from this research, recognition implementation combining both PCA and Euclidean distance are more suggested rather than using combination of PCA and backpropagation neural network.

In order to improve the efficiency and accuracy of thermal and moisture comfort prediction of underwear, a new prediction model is designed by using principal component analysis method to reduce the dimension of related variables and eliminate the multi-collinearity relationship between variables, and then inputting the converted variables into genetic algorithm (GA) and BP neural network. In order to avoid the problems of slow convergence speed and easy falling into local minimum of Back Propagation (BP) neural network, this paper adopted GA to optimize the weights and thresholds of BP neural network, and utilized MATLAB software to program, and established the prediction models of BP neural network and GA–BP neural network. To verify the superiority of the model, the predicted result of GA–BP, PCA–BP and BP are compared with GA–BP neural network. The results show that PCA could improve the accuracy and adaptability of GA–BP neural network for thermal and moisture comfort prediction. PCA–GA–BP model is obviously superior to GA–BP, PCA–BP, BP, SVM and K-means prediction models, which could accurately predict thermal and moisture comfort of underwear. The model has better accuracy prediction and simpler structure.

The aim of this randomized controlled crossover study was to investigate the effect of a bout of unaccustomed eccentric exercise (ECC) followed by a consecutive bout of the same intensity on local muscle blood flow, amplitude, and frequency of the electromyographic (EMG) signal from the exercised tibialis anterior muscle. Sixteen healthy male participants (age, 25.7 (0.6) years; body mass index 24.8 (1) kg·m(-2) participated in this study. Two identical bouts of high-intensity ECC were performed on the tibialis anterior muscle 7 days apart. Control sessions involving no exercise were performed 4 weeks either before or after the exercise sessions. Changes in local total blood flow [ΔtHb], EMG root mean square, and median power frequency were recorded during isometric maximum voluntary contraction of ankle dorsiflexion. Measurements were performed before, immediately after, and the day after both ECCs (ECC1 and ECC2). The participants rested quietly in a chair in the control session. Eccentric exercise 1 led to a significant decrease in [ΔtHb] on the day after (p ≤ 0.05), whereas ECC2 did not. Median power frequency decreased significantly in ECC2 compared with ECC1 (p < 0.01). Root mean square was unchanged in all the instants. The present study showed that adaptation is depicted in the local muscle blood flow and the frequency contents of the EMG after an unaccustomed ECC inducing muscle soreness. These alterations provide a potential mechanism for a rapid adaptation, which decreases susceptibility of the muscle to develop further soreness in the subsequent ECC bout.

To evaluate the developmental and functional outcome of condylar fractures in children and adolescents after conservative treatment. Eight children and adolescents with unilateral condylar fracture, aged 5-13 were included. A removable occlusal splint, the thickness of which was determined according to the age, the developmental stage of the dentition, the level of the fracture and the degree of dislocation, worn for 1-3 months, and the patients were asked to perform functional exercises. The patients were followed up by clinical observation, panoramic radiograph, temporomandibular joint(TMJ ) cone beam computed tomography(CBCT), and surface electromyography(sEMG) of masticatory muscles (superficial masseter, anterior temporalis, and anterior digastric muscles). Ramus height and body length of mandible were measured on panoramic radiograph. The patients were asked to return for follow-up visits at 1, 3, and 6 months after treatment, and then once a year. The patients underwent clinical examination at each follow-up visit, and radiological examinations at 6 months and then annually. All the patients showed clinically satisfactory results. CBCT showed smooth and continuous cortex. Panoramic X-ray revealed that the ramus height was shorter in the fractured side than in the contralateral side, while body length was longer. The mean asymmetry index(AI,x±s) for ramus height and body length were (3.29±2.68)% and (4.01 ± 2.54)%. sEMG showed either hypertension or hypotension in the masticatory muscles of the fractured side and asymmetries were obvious. The mean AI for sEMG activity of the anterior temporalis, masseter, and anterior digastric muscle were masseter: (15.0 ± 16.9)%; anterior temporalis: (21.5 ± 15.9)%; anterior digastric muscles: (11.9 ± 10.7)%. Conservative treatment of condylar fracture in children and adolescents had clinically satisfactory results, while mandibular development was slightly interrupted. Asymmetries of EMG activities of masticatory muscles were obvious. EMG could objectively reveal the functional recovery of condylar fracture in children.

This prospective cohort study investigates the prediction of a voluntary cough using surface electromyography (EMG) of intercostal and diaphragm muscles, to develop control algorithms for an EMG-controlled artificial larynx. The Ear Institute, London. Electromyography onset compared to voluntary cough exhalation onset and to 100ms (to give the artificial larynx the time to close the bioengineered vocal cords) before voluntary cough exhalation onset, in twelve healthy participants. In the 189 EMG of intercostal muscle-detected voluntary coughs, 172 coughs (91% CI 70-112) were detected before onset of cough exhalation and 128 coughs (67.6% CI 33.7-101.7) 100ms before onset of cough exhalation. In the 158 EMG of diaphragm muscle-detected voluntary coughs, 149 coughs (94.3% CI 76.3-112.3) were detected before onset of cough exhalation and 102 coughs (64.6% CI 26.6-102.6) 100ms before onset of cough exhalation. More coughs were detected before onset of cough exhalation when combining EMG activity of intercostal and diaphragm muscles and comparing this to intercostal muscle activity alone (183 coughs [96.8% CI 83.8-109.8] vs 172 coughs, P=.0294). When comparing the mentioned combination to diaphragm muscle activity alone, the higher percentage of detected coughs before cough exhalation onset was not found to be significant (183 coughs vs 149 coughs, P=.295). In addition, more coughs were detected 100ms before onset of cough exhalation with the mentioned combination of EMG activity and comparing this to intercostal muscles alone (149 coughs [78.8% CI 48.8-108.8] vs 128 coughs, P=.0198) and to diaphragm muscles alone (149 coughs vs 102 coughs, P=.0038). Most voluntary coughs can be predicted based on combined EMG signals of intercostal and diaphragm muscles, and therefore, these two muscle groups will be useful in controlling the bioengineered vocal cords within the artificial larynx during a voluntary cough.

Objective: To develop a standardized paediatric protocol for acquiring simultaneous chest wall kinematics and surface electromyography (EMG) of chest wall muscles during maximum performance and speech tasks. Patients and Methods: Eighteen healthy participants included: (a) a younger age group (n = 6; ages 4.0-6.5 years), (b) an older age group (n = 6; ages 7.0-10.5 years), and (c) an adult group (n = 8; ages 21-33 years). A child (age 10 years) with spastic-type cerebral palsy (CP) served as a ‘proof of protocol feasibility'. Chest wall kinematics and surface EMGs (intercostals, rectus abdominus, external oblique, latissimus dorsi, and erector spinae) were acquired during maximum performance and speech tasks. Results: Successful calibration of the EMG signal and reliable detection of muscle activation onset, offset, and amplitude relative to vital capacity and percent maximum voluntary contraction in children were demonstrated. Kinematic and surface EMG measurements were sensitive to non-speech and speech tasks, age, and neurological status (i.e. CP). Conclusion: The simultaneous measurement of kinematics and EMG of the chest wall muscle groups provides a more comprehensive description of speech breathing in children. This protocol can be used for the observation and interpretation of clinical outcomes seen in children with motor speech disorders following treatments that focus on increasing overall respiratory and vocal effort.

Carbon emission is a significant indicator to balance regional development and environmental pollution. Currently, to achieve the global goal of carbon neutrality, many countries had formulated relevant policies to control carbon emissions in the future. It is of great importance to solve the problem of mid-term and long-term prediction of regional carbon emissions. To improve the prediction accuracy and lower the calculation cost, this paper uses the Principal Component Analysis (PCA) method to reasonably screen the driving factors of carbon emission prediction. It combines the Back Propagation (BP) neural network and Genetic Algorithm (GA) to construct the Genetic Algorithm - Back Propagation neural network (GA-BP) model for mid-term and long-term prediction. Based on historical statistics and official policy indicators, the prediction of carbon emissions in Jiangsu Province of China from 2025 to 2050 is carried out. By comparing the prediction results of the Multiple Linear Regression (MLR) model and the classic BP model, the improved GA-BP model based on Principal Component Analysis Stochastic Impacts by Regression on Population, Affluence, and Technology (PCA-STIRPAT) is significantly better than other methods in the mid-term and long-term prediction of regional carbon emissions, with a maximum relative error of 0.76% and a high prediction accuracy. This result can provide a reasonable basis for relevant parties to make decisions on controlling carbon emissions.

Carbon fiber reinforced plastic (CFRP) structures are vulnerable to low-speed impacts, which will lead to almost invisible impact damage. Therefore, the timely localization of impact is of great significance to damage detection and maintenance of the structure. In this article, a low velocity impact supervisory and testing system based on fiber Bragg grating (FBG) sensors was built up for CFRP laminates to obtain the low velocity impact strain sensitivity model. Meanwhile, genetic algorithm was applied to optimize the configuration of the FBG sensing network. The eigenvectors of the impact signals were extracted by applying fast Fourier transform (FFT) transform and principal component analysis (PCA) technology used as the input of the back propagation (BP) neural network model, while the corresponding impact coordinates were used as the output, to train the model. After training, the impact position prediction model based on BP neural network was obtained, thereby achieving the impact localization for CFRP laminates successfully with an average localization error of 2.1 cm.

In this paper, we present an approach to recognizing characters in surface mount technology (SMT) product. The recognition rate of SMT product character is not very good, because of unexpected noise in SMT the product character image. An improved SMT product character recognition method is proposed which can improve the recognition rate. At first, the character image is changed into a gray image. Some appropriate image processing algorithms are used to eliminate the noise. Then, single character image is obtained after character segmentation and character normalization. Finally, a three-layer back propagation (BP) neural network module is constructed. In order to improve the convergence rate of the network and avoid oscillation and divergence, the BP algorithm with momentum item is used. As a result, the SMT product character recognition system is developed, and its implementation method and steps are introduced with practical examples. Experimental results indicate that the proposed character recognition can obtain satisfactory character-recognition rate and the recognition rate reached over by 98.6%.

Prediction model of end-point phosphorus content in BOF steelmaking process based on PCA and BP neural network

The management and disposal of waste is a severe social issue and an essential part of ecological sustainability. As an important component of the green, low-carbon, and recycling economic system, the identification and classification of recyclable waste is the premise of its reuse and energy conservation. The main issues at hand are to improve the classification accuracy and reliability of recyclable waste and to achieve automatic classification. The methods based on physical characteristics and image-based methods are inaccurate and unreliable. The current spectroscopy methods need to process the detected samples in advance, unsuitable for automatic detection. Based on material composition properties, the Laser-Induced Breakdown Spectroscopy (LIBS) technology is here proposed to accurately and reliably identify and classify recyclable waste into six categories at the level of consumer, such as paper, plastic, glass, metal, textile, and wood. The method is also used to subclassify the same category of waste for reuse at the level of a recycling factory. We subclassified metals into iron, stainless steel, copper, and aluminum and plastics into polyvinylchloride, polyoxymethylene, acrylonitrile-butadiene-styrene, polyamide, polyethylene, and polytetrafluoroethylene. The drop-dimension methods of LIBS spectra of waste were researched to eliminate noise and redundant information by principal component analysis (PCA) and linear discriminant analysis (LDA), respectively. Their clustering effects were analyzed to choose a suitable dimension. Combining the random forest (RF), back propagation neural network (BPNN), and convolutional neural network (CNN), we established and compared five classification models, PCA + RF, PCA + BPNN, LDA + RF, LDA + BPNN, and 1D-CNN. For the classification of six categories, the accuracies of proposed classification models are all more than 96%, and LDA(5D) + RF has 100% accuracy and optimal classification performance indices. For the subclassification of metals and plastics, PCA(8D) + RF has the highest classification accuracy of 98.77% and 99.52%, respectively.

Study of Emotion Recognition Based on Electrocardiogram and RBF neural network