Search Results (672)

With the growing application of soft robot technology in complex, dynamic environments, the limitations of traditional rigid robots have become increasingly prominent, urgently demanding novel soft actuation technologies. Dielectric elastomer actuators (DEAs) have gradually emerged as a research focus in soft robotics due to their high energy density, rapid response, low noise, and excellent compliance. This paper systematically reviews the research progress of DEA-based soft robots over the past decade. Using classification and comparative analysis, DEAs are categorized into four basic types according to their initial shape—planar, saddle-shaped, cylindrical, and conical—with detailed elaboration on their working principles, structural features, and typical applications. Furthermore, from two major application scenarios (underwater and terrestrial), this paper analyzes the adaptability of various DEAs in robot design and corresponding optimization strategies and summarizes their performance and research challenges in bionic propulsion, multi-modal motion, and environmental adaptability. Finally, it provides the prospective future research directions of DEAs in material development, structural design, intelligent control, and system integration, providing theoretical support and technical references for their wide application in fields such as medical treatment, detection, and human–robot interaction. Full article

Post-traumatic lymphedema (PTL) is a chronic and often under-recognized sequela of soft tissue trauma, leading to persistent swelling, functional impairment, and increased risk of infection. While lymphedema is traditionally associated with oncologic interventions, growing evidence highlights the significant burden of PTL in trauma patients. This review provides a comprehensive analysis of the current understanding of PTL, including epidemiology, risk factors, pathophysiology, diagnostic modalities, and treatment strategies. PTL often occurs after high-impact musculoskeletal injuries (such as open fractures with significant soft tissue loss) or burns (especially if deep or circumferential). This risk is increased if injury occurs at critical areas of increased lymphatic density (such as anteromedial leg, medial knee, medial thigh, medial elbow, or medial arm). Advances in imaging techniques, including indocyanine green lymphography and magnetic resonance lymphangiography, have improved early detection and classification of PTL. Management approaches range from conservative therapies, such as complete decongestive therapy (CDT), to surgical interventions, including lymphaticovenous anastomosis (LVA), vascularized lymph node transfer (VLNT), and vascularized lymph vessel transfer (VLVT)/lymph-interpositional-flap transfer (LIFT). We report on our experience with two patients. At our center, we diagnose and stage PTL with ICG lymphography and trial CDT for 6 months. If there is no significant improvement, we recommend LVA. If there is insufficient improvement after 12 months, we recommend LIFT/repeat LVA/VLNT. We also treat open fractures with significant soft tissue defects with LIFT, as prophylaxis against PTL. PTL remains an underdiagnosed condition, necessitating increased awareness and intervention to prevent long-term disability. Full article

This paper introduces a modified soft margin optimal hyperplane (MSMOH) algorithm, which enhances the linear separating properties of support vector machines (SVMs) by placing higher penalties on large misclassification errors. This approach improves margin symmetry in both balanced and asymmetric data distributions. The research is divided into two main stages. The first stage evaluates MSMOH for synthetic data classification and its application in heart disease diagnosis. In a cross-validation setting with unknown data, MSMOH demonstrated superior average performance compared to the standard soft margin optimal hyperplane (SMOH). Performance metrics confirmed that MSMOH maximizes the margin and reduces the number of support vectors (SVs), thus improving classification performance, generalization, and computational efficiency. The second stage applies MSMOH as a novel synthesis algorithm to design a neural associative memory (NAM) based on a recurrent neural network (RNN). This NAM is used for fault diagnosis in fossil electric power plants. By promoting more symmetric decision boundaries, MSMOH increases the accurate convergence of 1024 possible input elements. The results show that MSMOH effectively designs the NAM, leading to better performance than other synthesis algorithms like perceptron, optimal hyperplane (OH), and SMOH. Specifically, MSMOH achieved the highest number of converged input elements $\left(1019\right)$ and the smallest number of elements converging to spurious memories $\left(5\right)$. Full article

This study explores the application of Mid-Infrared (MIR) and Near-Infrared (NIR) spectroscopy combined with various multivariate calibration techniques to detect the presence of cannabis in tobacco samples and tobacco in herbal smoking products. Both MIR and NIR spectra were recorded for self-prepared samples, followed by data exploration using Principal Component Analysis (PCA) and Hierarchical Clustering Analysis (HCA), and the calculation of binary classification models with Soft Independent Modelling of Class Analogy (SIMCA) and Partial Least Squares-Discriminant Analysis (PLS-DA). PCA demonstrated a clear differentiation between tobacco samples containing and not containing cannabis. On the other hand, based on PCA, only NIR was able to distinguish herbal smoking products adulterated and not adulterated with tobacco. HCA further clarified these results by revealing distinct clusters within the data. Modelling results indicated that MIR and NIR spectroscopy, particularly when paired with preprocessing techniques like Standard Normal Variate (SNV) and autoscaling, demonstrated high classification accuracy in SIMCA and PLS-DA, achieving correct classification rates of 90% to 100% for external test sets. Comparison of MIR and NIR revealed that NIR spectroscopy resulted in slightly more accurate models for the screening of tobacco samples for cannabis and herbal smoking products for tobacco. The developed approach could be useful for the initial screening of tobacco samples for cannabis, e.g., in a night life setting by law enforcement, but also for inspectors visiting shops selling tobacco and/or herbal smoking products. Full article

Background: Diabetes-related foot diseases represent a global health problem because of the associated complications, the risk of amputation, and the economic burden on health systems. Negative pressure wound therapy (NPWT) is a technique that uses sub-atmospheric pressure to help promote wound healing by reducing the inflammatory exudate while keeping the wound moist, inhibiting bacterial growth, and promoting the formation of granulation tissue. Objective: This study aimed to assess the effectiveness of NPWT in preventing major amputation in diabetic patients with complicated foot or lower limb infections and to contextualize the results through a review of the existing literature. Materials and methods: We conducted a retrospective study at the First Surgical Department of “Dr. I. Cantacuzino” Clinical Hospital in Bucharest, Romania, over a 15-year period, including 30 consecutive adult patients with diabetes and soft tissue foot or lower limb infections treated with NPWT. Patients with non-diabetic ulcers, incomplete medical data, or aged under 18 were excluded. All patients underwent initial surgical debridement, minor amputation, or drainage procedures, followed by the application of NPWT using a standard protocol. Dressings were changed every 2–4 days for a total of 7–10 days. Antibiotic therapy was adapted according to the culture results. The primary outcome was limb preservation, defined as avoidance of major amputation. Secondary outcomes included in-hospital mortality and wound status at discharge. Results: NPWT was associated with a favorable outcome in 24 patients (80%), defined by wound granulation or healing without the need for major amputation. Five patients (16.6%) underwent major amputation because of failure of the primary lesion treatment, and one patient died. No statistically significant association was observed between the outcomes and standard classification scores (WIFI, IWGDF, and TPI). A comprehensive literature review helped to integrate these findings into the existing pool of knowledge. Conclusions: NPWT may support limb preservation in selected diabetic foot cases. While the retrospective design and the small sample size of the study limit generalizability, these results reinforce the need for further controlled studies to evaluate NPWT in real-life clinical settings. The correct use of NPWT combined with etiological treatment may offer a maximum chance to avoid major amputation in patients with diabetes-related foot diseases. Full article

The garment manufacturing industry, being labor-intensive, has long faced challenges in automating the sewing process due to the flexibility and deformability of fabrics. This study proposes a novel strategy for automated sewing by integrating soft fingers and machine vision technology. Firstly, leveraging the flexibility and adjustability of soft fingers, combined with the motion characteristics of the sewing machine, a sewing model was established to achieve coordinated operation between the soft fingers and the sewing machine. Experimental results indicate that the fabric feeding speed and waiting time of the soft fingers are significantly correlated with the sewing speed and stitch density of the sewing machine, but not with the fabric properties. Secondly, machine vision technology was employed to inspect the quality of the sewn fabrics, achieving a classification accuracy of 97.84%. This study not only provides theoretical and technical support for the intelligent upgrading of the garment manufacturing industry but also lays the foundation for the automation of complex sewing processes such as quilting. Future research will further optimize the system’s performance and expand its applications in more complex sewing tasks. Full article

Objectives: The aim of the study was to gauge the clinical usefulness of the Derkay scale in assessing the severity of voice dysfunction in patients with recurrent respiratory papillomatosis (RRP). Material and Methods: The study included 29 patients (8 women and 21 men) with a mean age of 40.2 years. To subjectively assess each patient’s voice, the Polish version of the Voice Handicap Index questionnaire was used. Acoustic parameters were calculated using the Multidimensional Voice Program, which included mean fundamental frequency (F0), frequency changes (% Jitter), amplitude changes (% Shimmer), noise-to-harmonic ratios (NHRs), and the soft phonation Index (SPI). The stage of RRP was assessed using the Derkay scale, together with the anatomical location of the lesion (from laryngeal endoscopy) and the impact RRP had on the general condition of the patient. Results: In women, Derkay clinical and total scores showed significant, positive, and strong correlations with almost all VHI-30 subscales (rho = 0.73–0.76). In men, the correlations were weaker (rho = 0.38–0.55) but were strong between the Derkay total score and F0 and total score and Jitter (rho = 0.63–0.65). Patients with human papilloma virus HPV-6 had significantly higher soft phonation index values (M = 11.97) compared to patients with HPV-11 (M = 6.91, U = 34.0; p = 0.019). Conclusions: The Derkay classification system correlates well with objective acoustic frequency measures and patient-reported voice outcomes. The system may be helpful in identifying patients at increased risk of voice dysfunction. It could be used to guide decisions about voice assessment and rehabilitation. Full article

Background/Objective: Understanding the training effect in high-level running is important for performance optimization and injury prevention. This includes awareness of how different running surface types (e.g., hard versus soft) may modify biomechanics. Recent studies have demonstrated that deep learning algorithms, such as convolutional neural networks (CNNs), can accurately classify human activity collected via body-worn sensors. To date, no study has assessed optimal signal type, sensor location, and model architecture to classify running surfaces. This study aimed to determine which combination of signal type, sensor location, and CNN architecture would yield the highest accuracy in classifying grass and asphalt surfaces using inertial measurement unit (IMU) sensors. Methods: Running data were collected from forty participants (27.4 years + 7.8 SD, 10.5 ± 7.3 SD years of running) with a full-body IMU system (head, sternum, pelvis, upper legs, lower legs, feet, and arms) on grass and asphalt outdoor surfaces. Performance (accuracy) for signal type (acceleration and angular velocity), sensor configuration (full body, lower body, pelvis, and feet), and CNN model architecture was tested for this specific task. Moreover, the effect of preprocessing steps (separating into running cycles and amplitude normalization) and two different data splitting protocols (leave-n-subject-out and subject-dependent split) was evaluated. Results: In general, acceleration signals improved classification results compared to angular velocity (3.8%). Moreover, the foot sensor configuration had the best performance-to-number of sensor ratio (95.5% accuracy). Finally, separating trials into gait cycles and not normalizing the raw signals improved accuracy by approximately 28%. Conclusion: This analysis sheds light on the important parameters to consider when developing machine learning classifiers in the human activity recognition field. A surface classification tool could provide useful quantitative feedback to athletes and coaches in terms of running technique effort on varied terrain surfaces, improve training personalization, prevent injuries, and improve performance. Full article

Background: Mixed martial arts (MMA) is becoming increasingly popular and is developing dynamically in terms of training methods and number of participants involved, while weightlifting, powerlifting, and other kinds of strength disciplines are well established. In this study, the aim was to compare the body composition, as an anthropometric effect of training in MMA fighters and strength athletes, and then analyze and find reasoning for observed differences. Methods: Thirty-four young healthy male participants (body weight 84.9 ± 10.2 kg, body height 182.0 ± 6.8 cm, BMI 25.8 ± 2.51 kg/m², tier 2/3 in McKay’s sports level classification) represented two groups: MMA (n = 17) and powerlifting athletes (STR, n = 17). The measured anthropometric characteristics were skeletal muscle mass (SMM), percentage of body fat (PBF), body fat mass (FM) and visceral fat mass (VFM). Phase angle (º) was measured as an indicator of tissue quality and we performed detailed investigations of soft fat-free tissue mass (SLM) and of fat mass in body parts separately in each lower and upper limb and trunk. Results: The groups did not differ in terms of body weight, height, BMI, SMM, PBF, FM, VFM, SLM in upper limbs and trunk, FM in the body parts, or the phase angle (all p > 0.05). The statistically significant differences were only observed in the SLM of both lower limbs (greater in STR, p < 0.05) but, after statistical correction with the Holm’s method, these parameters also did not show statistically significant differences despite high effect sizes. Conclusions: The MMA athletes do not differ significantly from strength training athletes in measured anthropometric parameters despite distinct differences in training methodology. The reasons for these observations need future research, combining anthropometric measurements with training and competing load monitoring. Full article

Background and Objectives: Sarcopenia is a progressive loss of skeletal muscle mass and function in elderly adults, posing a significant risk of frailty, falls, and morbidity. The current study designs and evaluates SarcoNet, a novel artificial neural network (ANN)-based classification framework developed in order to classify Sarcopenic from non-Sarcopenic subjects using a comprehensive real-time dataset. Methods: This pilot study involved 30 subjects, who were divided into Sarcopenic and non-Sarcopenic groups based on physician assessment. The collected dataset consists of thirty-one clinical parameters like skeletal muscle mass, which is collected using various equipment such as Body Composition Analyser, along with ten kinetic features which are derived from video-based gait analysis of joint angles obtained during walking on three terrain types such as slope, steps, and parallel path. The performance of the designed ANN-based SarcoNet was benchmarked against the traditional machine learning classifiers utilised including Support Vector Machine (SVM), k-Nearest Neighbours (k-NN), and Random Forest (RF), as well as hard and soft voting ensemble classifiers. Results: SarcoNet achieved the highest overall classification accuracy of about 94%, with a specificity and precision of about 100%, an F1-score of about 92.4%, and an AUC of 0.94, outperforming all other models. The incorporation of lower-limb joint kinetics such as knee flexion, extension, ankle plantarflexion and dorsiflexion significantly enhanced predictive capability of the model and thus reflecting the functional deterioration characteristic of muscles in Sarcopenia. Conclusions: SarcoNet provides a promising AI-driven solution in Sarcopenia diagnosis, especially in low-resource healthcare settings. Future work will focus on improving the dataset, validating the model across diverse populations, and incorporating explainable AI to improve clinical adoption. Full article

We propose a speed-adaptive robot accurate path-tracking framework based on the soft actor–critic (SAC) and Stanley methods (STANLY_ASAC). First, the Lidar–Inertial Odometry Simultaneous Localization and Mapping (LIO-SLAM) method is used to map the environment and the LIO-localization framework is adopted to achieve real-time positioning and output the robot pose at 100 Hz. Next, the Rapidly exploring Random Tree (RRT) algorithm is employed for global path planning. On this basis, we integrate an improved A* algorithm for local obstacle avoidance and apply a gradient descent smoothing algorithm to generate a reference path that satisfies the robot’s kinematic constraints. Secondly, a network classification model based on U-Net is used to classify common road surfaces and generate classification results that significantly compensate for tracking accuracy errors caused by incorrect road surface coefficients. Next, we leverage the powerful learning capability of adaptive SAC (ASAC) to adaptively adjust the vehicle’s acceleration and lateral deviation gain according to the road and vehicle states. Vehicle acceleration is used to generate the real-time tracking speed, and the lateral deviation gain is used to calculate the front wheel angle via the Stanley tracking algorithm. Finally, we deploy the algorithm on a mobile robot and test its path-tracking performance in different scenarios. The results show that the proposed path-tracking algorithm can accurately follow the generated path. Full article

Phyllodes tumors are rare fibroepithelial neoplasms of the breast, and their malignant forms present significant diagnostic and therapeutic challenges. This review summarizes current knowledge across the benign-to-malignant spectrum, focusing on diagnostic approaches, histopathological classification, molecular alterations, and treatment strategies. While recent molecular studies have revealed recurrent genetic mutations, their clinical implications remain under investigation. Surgical excision remains the cornerstone of treatment, and systemic therapies are generally adapted from soft tissue sarcoma protocols. Future efforts should focus on improving diagnostic accuracy, identifying molecular targets for therapy, and fostering international collaboration to advance clinical research in this rare tumor type. Full article

Effective waste management is important for reducing environmental harm, improving recycling operations, and building urban sustainability. However, accurate waste classification remains a critical challenge, as many deep learning models struggle with diverse waste types. In this study, classification accuracy is enhanced using transfer learning, ensemble techniques, and custom architectures. Eleven pre-trained convolutional neural networks, including ResNet-50, EfficientNet variants, and DenseNet-201, were fine-tuned to extract meaningful patterns from waste images. To further improve model performance, ensemble strategies such as weighted averaging, soft voting, and stacking were implemented, resulting in a hybrid model combining ResNet-50, EfficientNetV2-M, and DenseNet-201, which outperformed individual models. In the proposed system, two specialized architectures were developed: EcoMobileNet, an optimized MobileNetV3 Large-based model incorporating Squeeze-and-Excitation blocks for efficient mobile deployment, and EcoDenseNet, a DenseNet-201 variant enhanced with Mish activation for improved feature extraction. The evaluation was conducted on a dataset comprising 4691 images across 10 waste categories, sourced from publicly available repositories. The implementation of EcoMobileNet achieved a test accuracy of 98.08%, while EcoDenseNet reached an accuracy of 97.86%. The hybrid model also attained 98.08% accuracy. Furthermore, the ensemble stacking approach yielded the highest test accuracy of 98.29%, demonstrating its effectiveness in classifying heterogeneous waste types. By leveraging deep learning, the proposed system contributes to the development of scalable, sustainable, and automated waste-sorting solutions, thereby optimizing recycling processes and minimizing environmental impact. Full article

Deploying deep learning (DL) models in real-world environments remains a major challenge, particularly under resource-constrained conditions where achieving both high accuracy and compact architectures is essential. While effective, Conventional pruning methods often suffer from high computational overhead, accuracy degradation, or disruption of the end-to-end training process, limiting their practicality for embedded and real-time applications. We present Dynamic Attention-Guided Pruning (DAGP), a Dynamic Attention-Guided Soft Channel Pruning framework that overcomes these limitations by embedding learnable, differentiable pruning masks directly within convolutional neural networks (CNNs). These masks act as implicit attention mechanisms, adaptively suppressing non-informative channels during training. A progressively scheduled L1 regularization, activated after a warm-up phase, enables gradual sparsity while preserving early learning capacity. Unlike prior methods, DAGP is retraining-free, introduces minimal architectural overhead, and supports optional hard pruning for deployment efficiency. Joint optimization of classification and sparsity objectives ensures stable convergence and task-adaptive channel selection. Experiments on CIFAR-10 (VGG16, ResNet56) and PlantVillage (custom CNN) achieve up to 98.82% FLOPs reduction with accuracy gains over baselines. Real-world validation on an enhanced PlantDoc dataset for agricultural monitoring achieves 60 ms inference with only 2.00 MB RAM on a Raspberry Pi 4, confirming efficiency under field conditions. These results illustrate DAGP’s potential to scale beyond agriculture to diverse edge-intelligent systems requiring lightweight, accurate, and deployable models. Full article

Breast cancer is a widespread disease involving abnormal (uncontrolled) growth of breast tissue cells along with the formation of a tumor and metastasis. Breast cancer cases occur mostly among women. Early detection and regular screening have significantly improved survival rates. This research classifies breast cancer and non-breast cancer cases using machine learning algorithms based on the Breast Cancer Coimbra dataset by optimizing the classifier performance and feature selection methodology. In addition, this research identifies the influential features responsible for BC classification by using diverse counterfactual explanations. The Rotation Forest classifier algorithm is used to classify breast cancer and non-breast cancer cases. The hyperparameters of this algorithm are optimized using the Optuna optimizer. Three wrapper-based feature selection techniques (Sequential Forward Selection, Sequential Backward Selection, and Exhaustive Feature Selection) are used to select the most relevant features. An ensemble environment is also created using the best feature subsets of these methods, incorporating both soft and hard voting strategies. Experimental results show that the hard voting strategy achieves an accuracy of 85.71%, F1-score of 83.87%, precision of 92.85%, and recall of 76.47%. In contrast, the soft voting strategy obtains an accuracy of 80.00%, F1-score of 77.42%, precision of 85.71%, and recall of 70.59%. These findings demonstrate that hard voting achieves noticeably better performance. The misclassification outcomes of both strategies are explored using Diverse Counterfactual Explanations, revealing that BMI and Glucose values are most influential in predicting correct classes, whereas the HOMA, Adiponectin, and Resistin values have little influence. Full article