Motion Analysis Method Research Articles

A hybrid harmonic polynomial cell and STF strip theory method for marine hydrodynamics and ship motion analysis

ABSTRACT This paper presents a hybrid method that combines the Harmonic Polynomial Cell (HPC) method and STF strip theory to solve marine hydrodynamics and ship motion problems. The efficient and precise HPC method is extended to three-dimensional ship hydrodynamics using STF strip theory. A new single-node hybridisation condition is introduced to enhance the stability of hydrodynamic predictions. To improve computational accuracy for complex hull shapes, automatic structured grid generation and mesh refinement techniques are applied. The hybrid HPC-STF method is then used to solve 3D ship radiation and diffraction problems in regular waves with forward speed. The method’s performance is validated through comparisons of hydrodynamic coefficients, wave forces, and motion response amplitude operators (RAOs) against experimental data and results from other numerical methods. The findings demonstrate that this hybrid approach provides accurate and effective solutions for ship hydrodynamics, making it a valuable tool for analysing marine structures and motions.

The use of deep learning in intelligent athlete motion recognition: Integrating biological mechanisms

This work explores the effective application of deep learning for recognizing athletes’ movements, aiming to enhance precision in competitive sports. Traditional motion analysis methods primarily rely on manual observation, which can introduce subjective bias and limit accuracy. To address these limitations, we propose an automated method based on deep learning for recognizing and classifying athletes’ technical movements while evaluating their performance. A hybrid model, combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks, is utilized to extract key frames from video data. The CNN is responsible for feature extraction, capturing the intricate details of movement, while the LSTM captures the temporal sequence characteristics, providing context to the actions. To further strengthen our approach, we delve into the biological mechanisms underlying athletic movements. Understanding the biomechanics of motion—such as joint angles, muscle activation patterns, and energy expenditure—can enhance the accuracy of deep learning models. By integrating these biological insights into our model, we improve the recognition process, allowing for a more nuanced understanding of how movements impact performance. Through experiments, we demonstrate that the model achieves high accuracy across multiple benchmark datasets (UCF-101, HMDB-51, Kinetics-400, and Sports-1M), with a particularly high accuracy of 93.5% on the UCF-101 dataset. These results indicate that the proposed method is both accurate and reliable, making it suitable for athlete training and competition analysis. The findings of this research have significant implications for sports science, training evaluation, and injury prevention. By providing coaches and athletes with precise feedback based on deep learning analysis, we can facilitate targeted training interventions that enhance performance while reducing injury risks. This work aims to offer a powerful tool for athletes, coaches, and researchers, contributing to the advancement of competitive sports through a deeper understanding of movement dynamics and their biological underpinnings.

Reliability and Validity of the Articulation Motion Assessment System Using a Rotary Encoder

This study aimed to validate the effectiveness of the Articulation Motion Assessment System (AMAS), a joint kinematic evaluation system, for clinical applications. AMAS enables synchronised measurement using neurophysiological indicators, overcoming laboratory setting limitations. We compared AMAS-based ankle joint kinematic evaluations, particularly the sagittal and frontal plane angles, with two-dimensional (2D) motion analysis to determine the validity and reliability of AMAS. Both AMAS and 2D motion analysis reliably detected significant differences in angles within the sagittal and frontal planes. Correlation analysis revealed a significant moderate-to-strong correlation between the AMAS and the conventional method of 2D motion analysis, proving the measurement validity of the AMAS (ρ = 0.53–0.77 for sagittal plane angles; ρ = 0.46–0.72 for frontal plane angles). The average root mean squared error (RMSE) was significantly lower in AMAS (10.90 ± 2.93° for sagittal plane angles; 13.44 ± 1.09° for frontal plane angles) than in the inertial sensor-based three-dimensional (3D) motion analysis. Reliability analysis revealed high reliability of measurements (intraclass correlation coefficients (ICC) ≥ 0.76). However, the Bland–Altman analysis identified a slightly lower fixed bias, which was observed as a characteristic of each measurement system. The AMAS accurately detects ankle joint angles without being constrained by measurement environment limitations. Synchronised measurements using neurophysiological indicators potentially contribute to understanding ankle joint control mechanisms and developing rehabilitation strategies.

A remote motion analysis of mass casualty incident simulations

BackgroundRegular training for mass casualty incidents at physical simulation events is vital for emergency services. The preparation and execution of these simulations consume huge amounts of time, personnel, and money. It is therefore important to gather as much information as possible from each simulation while minimizing any influence on the participants, so as to keep the simulation as realistic as possible. In this paper, an analysis of GPS-based remote motion measurements of participants in a mass casualty incident simulation is presented. A combination of different evaluation methods is used to analyze the data. This could reduce the potential bias of the measurement methods.MethodsMovement patterns of participants of mass casualty incident simulations, measured by GPS loggers, were analyzed. The timeline of the simulation was segmented into event sections, based on movement patterns of participants entering or leaving defined areas. Movement patterns of participants working closely together were correlated to analyze their cooperation. Written logs created by observers on the ground were used to reconstruct the events of the simulation, to provide a comparative reference to validate the motion analysis.ResultsRecorded motion patterns of the participants were found to be qualitatively related to observer logs and triage allocations, allowing a partial reconstruction of the behavior of the participants during the simulation. By analyzing the times the simulation patients left the site of events some possible misjudgments in the triage decisions were indicated.ConclusionsAnalysis of movement patterns from GPS loggers and comparison with observations made on the ground showed that accurate information about the events during the simulation can be automatically delivered. Although the records of observers on the ground are vital to assess details, delegation of the automated analysis of individual and group motion could perhaps allow observers to concentrate on more specific tasks. The partially automated motion analysis methods presented should simplify the process of analyzing mass casualty incident simulations.

Cross-sectional Effects of Isolated Meniscal Tears on In Vivo Biomechanics of the Knee: A Systematic Review of Motion Analysis Studies

Objectives: To systematically review the effects of meniscal tears on in vivo knee biomechanics, with a focus on kinematic and kinetic outcome measures. Methods: Databases were queried for level I-IV studies that met the following criteria: in vivo studies of gait or motion analysis, cohorts with isolated meniscal pathology, and kinematics and/or kinetics outcome measures. Demographic data, methods of motion analysis, tasks performed, and kinematics and kinetics outcomes were extracted. Standardized mean differences with a random-effects model were calculated to compare cohorts with meniscal tears and healthy controls when outcomes were homogeneous. Results: Thirteen studies were eligible, with a pooled sample of 176 medial meniscal and 74 lateral meniscal tears. Eleven studies assessed gait biomechanics. There was considerable variability in reported outcomes and motion capture methods. Meta-analysis revealed statistically significant decreases in peak knee flexion angle, range of adduction-abduction, and internal-external rotation (p < 0.05) for the pooled sample of lateral meniscus tears. In terms of kinetics, although qualitative evidence in individual studies suggested alterations (e.g., decreased total support moment of the injured limb), quantitative analysis failed to demonstrate significant differences in peak knee flexion moment and peak knee adduction moment (p ≥ 0.05). Conclusion: Lateral meniscus tears significantly impact in vivo knee kinematics across all three planes of motion. No significant differences were observed in the kinetics of medial meniscus tears, and the evidence for their impact on kinematics remains conflicting. Our findings suggest that analyzing more demanding functional tasks may be necessary to detect the biomechanical changes caused by meniscal tears.

The use of accelerometers to assess upper limb function in patients with obstetric brachial plexus palsy

For half a century, the Mallet Scale (MS) has been utilized to assess upper limb function in patients with obstetric brachial plexus palsy (OBPP). However, the correct use of the MS requires trained personnel and the MS does not measure compensatory movements. For this reason, new methods are needed to compensate for these weaknesses. This study introduces an innovative method for objective functional motion analysis using accelerometers to measure upper limb movements in thirty patients with obstetric brachial plexus lesions. Five triaxial accelerometers were positioned on the chest and each upper limb. They recorded acceleration signals during repetitive everyday tasks: hand-to-mouth (HM), hand-to-neck (HN), and hand-to-spine (HS). From these signals, 54 features were extracted and subjected to linear correlation tests to identify 5 suitable features. An algorithm was then developed to categorize patients into five groups and compute an individual movement performance score (iMPScore) assessing the patient’s upper extremity function. By using the iMPScore more than 75% of all participants have been classified correctly with respect to their MS category. Identification of MS I category patients in general and assessing upper extremity function of MS I to III in HS tasks were most challenging. We conclude that the introduced approach is a valuable tool for gauging movement limitation of upper limbs in patients with obstetric brachial plexus palsy. Compared to other clinically established methods, it becomes possible to record and even quantify the extent of compensatory movements. In this way, an objective, user- and patient-friendly method is offered, which supports significantly physicians and therapists in their evaluation of OBPP.

MODELS OF REMOTE IDENTIFICATION OF PARAMETERS OF DYNAMIC OBJECTS USING DETECTION TRANSFORMERS AND OPTICAL FLOW

The tasks of remote identification of parameters of dynamic objects are important for various fields, including computer vision, robotics, autonomous vehicles, video surveillance systems, and many others. Traditional methods of solving these problems face the problems of insufficient accuracy and efficiency of determining dynamic parameters in conditions of rapidly changing environments and complex dynamic scenarios. Modern methods of identifying parameters of dynamic objects using technologies of detection transformers and optical flow are considered. Transformer detection is one of the newest approaches in computer vision that uses transformer architecture for object detection tasks. This transformer integrates the object detection and boundary detection processes into a single end-to-end model, which greatly improves the accuracy and speed of processing. The use of transformers allows the model to effectively process information from the entire image at the same time, which contributes to better recognition of objects even in difficult conditions. Optical flow is a motion analysis method that determines the speed and direction of pixel movement between successive video frames. This method allows obtaining detailed information about the dynamics of the scene, which is critical for accurate tracking and identification of parameters of moving objects. The integration of detection transformers and optical flow is proposed to increase the accuracy of identification of parameters of dynamic objects. The combination of these two methods allows you to use the advantages of both approaches: high accuracy of object detection and detailed information about their movement. The conducted experiments show that the proposed model significantly outperforms traditional methods both in the accuracy of determining the parameters of objects and in the speed of data processing. The key results of the study indicate that the integration of detection transformers and optical flow provides reliable and fast determination of parameters of moving objects in real time, which can be applied in various practical scenarios. The conducted research also showed the potential for further improvement of data processing methods and their application in complex dynamic environments. The obtained results open new perspectives for the development of intelligent monitoring and control systems capable of adapting to rapidly changing environmental conditions, increasing the efficiency and safety of their work.

Effective Motion Self-Learning Genre Using 360° Virtual Reality Content on Mobile Device: A Study Based on Taichi Training Platform.

Online fitness training, with its affordability and flexibility, offers a convenient way for individuals to engage in regular workouts that promote physical and mental health. Yet, learning fitness motions in this way presents various challenges and may not always be as effective as in-person training. To address the practical demands of motion learning, we conducted a systematic survey and accordingly proposed a four-stage self-learning genre that integrates immersive virtual reality (VR) environments with motion skill learning theories, strategies, and expert experience. Herein, we merged progressive structures and multi-level visual cues to enhance instruction, and proposed a fine-grained motion analysis method to provide adaptive correction feedback during training. Utilizing a Taichi training platform with the genre embedded, we systematically validated the effectiveness of the genre, and examined the potential impact of VR content presentation form on motion learning among different age groups, as well as their preferences and focus on VR fitness training genre design. Results from the quantitative analysis, qualitative evaluation, and case study showed that the 360° video-based VR content brought more positive motion learning performance and user experiences than the fully-simulated VR used in many previous studies. The proposed genre demonstrated outstandingly performance, experience, and usability, with each stage and design playing an effective role. Moreover, we offer several design considerations for VR fitness systems targeting diverse age groups, providing beneficial insights for VR development in the sports and health-related fields.

Transformative skeletal motion analysis: optimization of exercise training and injury prevention through graph neural networks.

Exercise is pivotal for maintaining physical health in contemporary society. However, improper postures and movements during exercise can result in sports injuries, underscoring the significance of skeletal motion analysis. This research aims to leverage advanced technologies such as Transformer, Graph Neural Networks (GNNs), and Generative Adversarial Networks (GANs) to optimize sports training and mitigate the risk of injuries. The study begins by employing a Transformer network to model skeletal motion sequences, facilitating the capture of global correlation information. Subsequently, a Graph Neural Network is utilized to delve into local motion features, enabling a deeper understanding of joint relationships. To enhance the model's robustness and adaptability, a Generative Adversarial Network is introduced, utilizing adversarial training to generate more realistic and diverse motion sequences. In the experimental phase, skeletal motion datasets from various cohorts, including professional athletes and fitness enthusiasts, are utilized for validation. Comparative analysis against traditional methods demonstrates significant enhancements in specificity, accuracy, recall, and F1-score. Notably, specificity increases by ~5%, accuracy reaches around 90%, recall improves to around 91%, and the F1-score exceeds 89%. The proposed skeletal motion analysis method, leveraging Transformer and Graph Neural Networks, proves successful in optimizing exercise training and preventing injuries. By effectively amalgamating global and local information and integrating Generative Adversarial Networks, the method excels in capturing motion features and enhancing precision and adaptability. Future research endeavors will focus on further advancing this methodology to provide more robust technological support for healthy exercise practices.

A Crowd Movement Analysis Method Based on Radar Particle Flow.

Crowd movement analysis (CMA) is a key technology in the field of public safety. This technology provides reference for identifying potential hazards in public places by analyzing crowd aggregation and dispersion behavior. Traditional video processing techniques are susceptible to factors such as environmental lighting and depth of field when analyzing crowd movements, so cannot accurately locate the source of events. Radar, on the other hand, offers all-weather distance and angle measurements, effectively compensating for the shortcomings of video surveillance. This paper proposes a crowd motion analysis method based on radar particle flow (RPF). Firstly, radar particle flow is extracted from adjacent frames of millimeter-wave radar point sets by utilizing the optical flow method. Then, a new concept of micro-source is defined to describe whether any two RPF vectors originated from or reach the same location. Finally, in each local area, the internal micro-sources are counted to form a local diffusion potential, which characterizes the movement state of the crowd. The proposed algorithm is validated in real scenarios. By analyzing and processing radar data on aggregation, dispersion, and normal movements, the algorithm is able to effectively identify these movements with an accuracy rate of no less than 88%.

Research on the electromyography-based pattern recognition for inter-limb coordination in human crawling motion.

Aiming to provide a feasible crawling motion analysis method for clinical application, this study introduced electromyography (EMG)-based motion intention recognition technology into the pattern recognition of inter-limb coordination during human crawling for the first time. Eight inter-limb coordination modes (ILCMs) were defined. Ten adult participants were recruited, and each participant performed hands-knees crawling at low, medium, and fast speeds in self-selected ILCMs and the eight predefined ILCMs, respectively. EMG signals for pattern recognition were collected from 30 limbs and trunk muscles, and pressure signals for crawling cycle segmentation were collected from the left palm. The pattern recognition experiments were conducted in participant-specific, multi-participant, and participant-independent ways, respectively, adopting three different classifiers, including bidirectional long short-term memory (BiLSTM) network, support vector machine (SVM), and k-nearest neighbor (KNN). The experimental results show that EMG-based pattern recognition schemes could classify the eight ILCMs with high recognition rates, thereby confirming the feasibility of providing an EMG-based crawling motion analysis method for clinical doctors. Furthermore, based on the classification results of self-selected ILCMs at different speeds and the statistical results of stance duration, swing duration, and the duty factors of stance phase, the possible reasons why humans chose various ILCMs at different crawling speeds were discussed. The research results have potential application value for evaluating crawling function, understanding abnormal crawling control mechanisms, and designing rehabilitation robots.

Dynamic Muscle Function Parameters in Indian Children and Adolescents with Type 1 Diabetes Mellitus: A Case-Control Study.

Recent evidence reveals that type 1 diabetes mellitus (T1DM) impairs muscle function (MF) in adolescents. However, despite its importance in physical well-being, data on dynamic MF in Indian children and adolescents (C and Y) with T1DM are scarce. We assessed MF using Jumping Mechanography (JM, a measurement method for motion analysis and assessment of muscle power and force). (1) To assess dynamic MF by JM in C and Y with T1DM as compared to healthy controls (2) To determine predictors of MF in children with T1DM. A cross-sectional observational study on 266 children (133 - T1DM duration >1 year with no known comorbidities + 133 age and gender-matched healthy controls) aged 6-19 years. Anthropometry, body composition, and MF (maximum relative power Pmax/mass, maximum relative force Fmax/BW by JM) were recorded. The lean mass index (LMI) was calculated as lean mass (kg)/height (m2). HbA1c was assessed in T1DM. Independent sample t-test and linear regression were performed. MF parameters (Pmax/mass 33.5 ± 7.2 vs 38.0 ± 8.6 W/kg and Fmax/BW 10.5 ± 2.9 vs 11.4 ± 4.1 N/kg, P < 0.05) were significantly lower in T1DM group vs controls. Positive association of body mass index and LMI with both MF parameters and negative association of insulin requirement and HbA1c with Fmax was observed in T1DM. Predictors of MF identified were MMI (Pmax/mass:b = 1.6,95%CI = 0.6-2.6; Fmax/BW:b =2.0,95%CI = 1.6-2.4) and HbA1c (Pmax/mass:b = -2.1,95%CI = -4.5--0.5; Fmax/BW:b = -1.1,95%CI = -2.0--0.2) (P < 0.05). C and Y with T1DM exhibits compromised muscle function. Poor glycaemic control increases the risk of having decreased MF, irrespective of diabetes duration and may contribute to sarcopenia in adulthood.

Kinematic Analysis and Research on the "Push Shot" Action of Table Football

In order to reveal the kinematic characteristics of the "push shot" technique in table football, this article analyzes and studies the kinematics of the "push shot" technique in table football using the three-dimensional motion analysis method, conducts experimental measurements of the push shot technique in table football players, and analyzes and studies its kinematic parameters. When completing the entire table football technical movement, the upper limbs need to rotate and cooperate with the vertical axis and coronal axis of the torso, ultimately forming a wrist compression movement to the fingers and wrists. When athletes complete technical movements, whether it is dribbling or shooting, the flexibility of their wrists is extremely high. Therefore, during practice, it is necessary to strengthen the training of the wrist and small muscle groups of the fingers, and pay attention to the practice of instant force application. Both the joints of the upper and lower limbs are very important. Therefore, during athlete training, it is necessary to strengthen the strength of the body's joints.

USING SHAPE MODELlING TECHNIQUES FOR MARKERLESS MOTION ANALYSIS

For many years, marker-based systems have been used for motion analysis. However, the emergence of new technologies, such as 4D scanners provide exciting new opportunities for motion analysis. In 4D scanners, the subjects are measured as a dense mesh, which enables the use of shape analysis techniques. In this talk, we will explore how the combination of the rising new motion analysis methods and shape modelling may change the way we think about movement and its analysis.

Concurrent Validity of Motion Parameters Measured With an RGB-D Camera-Based Markerless 3D Motion Tracking Method in Children and Young Adults.

Low-cost, portable RGB-D cameras with integrated motion tracking functionality enable easy-to-use 3D motion analysis without requiring expensive facilities and specialized personnel. However, the accuracy of existing systems is insufficient for most clinical applications, particularly when applied to children. In previous work, we developed an RGB-D camera-based motion tracking method and showed that it accurately captures body joint positions of children and young adults in 3D. In this study, the validity and accuracy of clinically relevant motion parameters that were computed from kinematics of our motion tracking method are evaluated in children and young adults. Twenty-three typically developing children and healthy young adults (5-29 years, 110-189 cm) performed five movement tasks while being recorded simultaneously with a marker-based Vicon system and an Azure Kinect RGB-D camera. Motion parameters were computed from the extracted kinematics of both methods: time series measurements, i.e., measurements over time, peak measurements, i.e., measurements at a single time instant, and movement smoothness. The agreement of these parameter values was evaluated using Pearson's correlation coefficients r for time series data, and mean absolute error (MAE) and Bland-Altman plots with limits of agreement for peak measurements and smoothness. Time series measurements showed strong to excellent correlations (r-values between 0.8 and 1.0), MAE for angles ranged from 1.5 to 5 degrees and for smoothness parameters (SPARC) from 0.02-0.09, while MAE for distance-related parameters ranged from 9 to 15 mm. Extracted motion parameters are valid and accurate for various movement tasks in children and young adults, demonstrating the suitability of our tracking method for clinical motion analysis. The low-cost portable hardware in combination with our tracking method enables motion analysis outside of specialized facilities while providing measurements that are close to those of the clinical gold-standard.

Dance movement error correction based on decision tree algorithm

Abstract In an environment where action recognition technology is widely used, dance action recognition technology has also received extensive attention. Due to the complexity of dance movements, there will be a large number of errors in dance movement recognition. Therefore, this paper uses the decision tree algorithm to optimize dance movement recognition. In this paper, the general framework of dance movement recognition is first constructed, and the human body features are extracted and calculated by using the Laban motion analysis method for the changes in the joints of dance movements. Then, use the decision tree algorithm to classify and identify the dance movements, and use it to optimize the self-obscuring motion information repair algorithm to solve the problem of dance movement occlusion and error, and complete the construction of the dance movement recognition model based on CNN network. Empirical analysis shows that the model method's Top-1 and Top-5 accuracy are both 84.7% and 89.32%, respectively. The average probability of incorrect recognition, error recognition, and correct recognition of the optimized dance action recognition in this paper is 8.84%, 3.78 and 87.38 respectively. The average recognition correctness is improved by 12.02%, which indicates that the effect of recognition of the optimized model of dance action masking and error correction in this paper is excellent. It has achieved a better construction in the field of dance action error correction.

Comparison of Various Devices Used in the Evaluation of Vertical Jump Height

This study aimed to compare force plate, motion analysis, and mobile application methods for calculating vertical jump height. Twenty-nine male college students (age: 22.4 ± 1.0 years; height: 178.1 ± 6.2cm; body weight: 71.2 ± 8.0 kg) voluntarily participated in the study. Two countermovement jumps (CMJ) with 1-minute intervals on a force platform (BERTEC 4060-10) were performed. The countermovement jump performances were captured using an iPhone 11 (Apple Inc., USA). The experimental setup involved using three high-speed cameras, specifically the My Jump 2 and SIMI Motion 7.5. Obtained results from hip displacement (HD) data with motion analysis system showed that participants had significantly lower vertical jump height calculated from motion capture (p = 0.01; -8.3 ± 3.86, 95%CI; MyJump2-SIMI_HD = 1.24/3.30). It was also found that calculations from left and right foot displacement were higher than My Jump 2 results (95%CI; MyJump2-SIMI_RF = 0.66/2.93) and 95%CI (MyJump2-SIMI_LF) = (-0.63/2.65). In contrast, force plate calculations, known as the gold standard in the literature, were very similar to My Jump (95%CI; MyJumpII-FP) = (2.38/4.01). The findings indicate that the My Jump 2, used for assessing vertical jump height, may be a reliable alternative for determining vertical jump height instead of setting up gold standard methods. Individuals' athletic performance abilities and birth, gender, and sports preferences should be considered. Finally, when coaches or sports scientists intend to measure CMJ, My Jump 2 application can be recommended as a laboratory application as well as a practical and valid measurement method, especially for field applications.

Bearing‐only motion analysis of target based on low‐quality bearing‐time recordings map

AbstractAccurate bearing‐time recordings play a crucial role in hydroacoustic target motion analysis and situation estimation. The target bearing estimated by vector hydrophone in the interference environment suffers from poor display and low signal‐to‐noise ratio. To solve this problem, a two‐stage bearing‐only motion analysis method is proposed. Firstly, the bearing peak information and bearing dispersion are extracted for each sampling moment of the bearing‐time recording. Custom constraint regions and adaptive parameters are then set based on this information. The order truncate average algorithm is improved to enhance the quality of the low‐quality bearing‐time recording map. Secondly, a bearing‐only target motion model is established based on the bearing‐time recording distribution features, and a bearing‐time recording trust interval is constructed. Then a modified pseudo‐linear estimation algorithm is proposed to solve the target motion situation information, including target abeam time, target abeam bearing, target course, velocity‐to‐initial‐distance ratio, and so forth. Finally, by comparing the solved values of the sea trial data with the automatic identification system calculation results, the enhancement effect of the target bearing‐time recording map is significant and the solving error of the target motion elements meets the needs of engineering applications.

Electromyography based hand movement classification and feature extraction using machine learning algorithms

The categorization of hand gestures holds significant importance in controlling orthotic and prosthetic devices, enabling human-machine interaction, and facilitating telerehabilitation applications. For many years, methods of motion analysis based on image processing techniques have been employed to detect hand motions. However, recent research has focused on utilizing muscle contraction for detecting hand movements. Specifically, there has been an increase in studies that classify hand movements using surface electromyography (sEMG) data from the muscles of the hand and arm. In our study, we estimated the open (extension of the fingers) and closed (flexion of the fingers) positions of the hand by analyzing EMG data obtained from 4 volunteer participants' Extensor digitorum and Flexor carpi radialis muscles. In order to accurately discriminate EMG signals, various statistical measures such as variance, standard deviation, root mean square, average energy, minimum and maximum features were utilized. The dataset containing these additional features was then subjected to classification algorithms including Support Vector Machines (SVM), K Nearest Neighbour (KNN), Decision Tree (DT), and Gaussian Naive Bayes (GNB) for the purpose of classifying hand positions into open or closed states. Among the tested algorithms, SVM achieved the highest success rate with a maximum accuracy of 73.1%, while KNN yielded the lowest success rate at a minimum accuracy of 55.9%. To further enhance prediction accuracy in future studies, it is suggested that data from a larger set of muscles be collected.

Real-time eye blink detection using general cameras: a facial landmarks approach

Eyes are essential in Human-Computer Interaction (HCI) as they provide valuable insights into a person's thoughts and intentions. However, current eye movement analysis methods require specialized equipment or high-quality videos, making them less accessible and usable. This paper proposes a real-time eye blink detection algorithm that uses standard cameras, making it widely applicable and convenient. The approach achieves accurate and efficient eye blink detection by leveraging the Eye Aspect Ratio (EAR) algorithm and facial landmarks technique. This paper developed a Python application and conducted tests using a laptop webcam to validate the performance and practicality of the algorithm across various settings. The algorithm's effectiveness depends on carefully tuning parameters such as threshold and frame rate. The results demonstrate the algorithm's potential in real-time eye blink detection, with potential applications in drowsiness detection during driving, prevention of Computer Vision Syndrome, and assistance for individuals with disabilities. By enabling eye blink detection using commonly available cameras, the algorithm paves the way for integrating eye movement analysis into everyday devices and systems, enhancing user experience and enabling more natural interactions. Further refinement and optimization of this approach hold promise for a wide range of applications in HCI, healthcare, and beyond, opening up new possibilities for research and innovation.