Human gait activity recognition is an emerging field of motion analysis that can be applied in various application domains. One of the most attractive applications includes monitoring of gait disorder patients, tracking their disease progression and the modification/evaluation of drugs. This paper proposes a robust, wearable gait motion data acquisition system that allows either the classification of recorded gait data into desirable activities or the identification of common risk factors, thus enhancing the subject’s quality of life. Gait motion information was acquired using accelerometers and gyroscopes mounted on the lower limbs, where the sensors were exposed to inertial forces during gait. Additionally, leg muscle activity was measured using strain gauge sensors. As a matter of fact, we wanted to identify different gait activities within each gait recording by utilizing Machine Learning algorithms. In line with this, various Machine Learning methods were tested and compared to establish the best-performing algorithm for the classification of the recorded gait information. The combination of attention-based convolutional and recurrent neural networks algorithms outperformed the other tested algorithms and was individually tested further on the datasets of five subjects and delivered the following averaged results of classification: 98.9% accuracy, 96.8% precision, 97.8% sensitivity, 99.1% specificity and 97.3% F1-score. Moreover, the algorithm’s robustness was also verified with the successful detection of freezing gait episodes in a Parkinson’s disease patient. The results of this study indicate a feasible gait event classification method capable of complete algorithm personalization.

The study aimed to analyze whether the high compression of unique, tight-fitting sportswear influences the clothing physiology comfort of the athlete. Three specific sportswear with different compression were tested on four subjects while they were running on a treadmill with increasing intensity. The compression effect of the sportswear on the body of the test persons, the temperature distribution of the subjects, and the intensity of their perspiration during running were determined. The results indicate that the compression effect exerted by the garments significantly influences the clothing physiology comfort of the athlete; a higher compression load leads to more intense sweating and higher skin temperature.

Contemporary CAD systems enable 3D clothing simulation for the purpose of predicting the appearance and behavior of conventional and intelligent clothing in real conditions. The physical and mechanical properties of the fabric and the simulation parameters play an important role in this issue. The paper presents an analysis of the parameters of the polygonal computer model that affect fabric drape simulation. Experimental research on physical and mechanical properties were performed for nine fabrics. For this purpose, the values of the parameters for the tensile, bending, shear, and compression properties were determined at low loads, while the complex deformations were analyzed using Cusick drape meter devices. The fabric drape simulations were performed using the 2D/3D CAD system for a computer clothing design on a disk model, corresponding to real testing on the drape tester in order to allow a correlation analysis between the values of drape parameters of the simulated fabrics and the realistically measured values for each fabric. Each fabric was simulated as a polygonal model with a variable related to the side length of the polygon to analyze the influence of the polygon size, i.e., mesh density, on the model behavior in the simulation. Based on the simulated fabric drape shape, the values of the areas within the curves necessary to calculate the drape coefficients of the simulated fabrics were determined in the program for 3D modelling. The results were statistically processed and correlations between the values of the drape coefficients and the optimal parameters for simulating certain physical and mechanical properties of the fabric were determined. The results showed that the mesh density of the polygonal model is an important parameter for the simulation results.

The perfect interlacing of needle and bobbin thread in the stitch formation process and seam appearance depends first of all on correct pre‐tension of the tension regulator. Changes in the pre‐tension settings also have a direct influence on the tensile force during the sewing process. This contribution presents the influence of pre‐tension in a defined area on the tensile force in important phases of the stitch formation process. In addition the influence of the stitch velocity on tensile force was investigated. On the basis of statistic analysis it was ascertained in which pre‐tension area and stitch velocity the significant differences between tensile forces occurred.

This paper presents a real-time wearable system designed to assist Parkinson’s disease patients experiencing freezing of gait episodes. The system utilizes advanced machine learning models, including convolutional and recurrent neural networks, enhanced with past sample data preprocessing to achieve high accuracy, efficiency, and robustness. By continuously monitoring gait patterns, the system provides timely interventions, improving mobility and reducing the impact of freezing episodes. This paper explores the implementation of a CNN+RNN+PS machine learning model on a microcontroller-based device. The device operates at a real-time processing rate of 40 Hz and is deployed in practical settings to provide ‘on demand’ vibratory stimulation to patients. This paper examines the system’s ability to operate with minimal latency, achieving an average detection delay of just 261 milliseconds and a freezing of gait detection accuracy of 95.1%. While patients received on-demand stimulation, the system’s effectiveness was assessed by decreasing the average duration of freezing of gait episodes by 45%. These preliminarily results underscore the potential of personalized, real-time feedback systems in enhancing the quality of life and rehabilitation outcomes for patients with movement disorders.

A drawn PET filament sewing thread for the automotive industry was used for this research. This study concerned itself with the draw ratio’s influence regarding certain physical properties of the threads, the tensile properties during sewing and the mechanical properties after sewing in order to estimate the drawn thread’s sewing performance. An increase in the draw ratio caused a decrease in the linear density, and thread twist. In addition, the tenacity, elastic modulus and tension at the yield point were increased when drawing, whilst the breaking extension decreased. It was found that tensile fatigue and heat loading during the sewing process cause changes in the threads’ mechanical properties, depending on the draw ratio. The tenacity, elastic modulus and tension at the yield point had decreased after the sewing process, whilst the breaking extension decreased for those threads drawn at lower draw ratios, and increased for those drawn at higher draw ratios. The results show that those threads drawn at higher draw ratios displayed inappropriate sewing performance, resulting from inadequate elastic and surface characteristics.