Search Results (177)

Background/Objectives: People suffering from mental illnesses are more likely to experience adverse social and health outcomes. Various interventions have been shown to help people with mental illness achieve better results in terms of symptom reduction, functional status, and quality of life. Psychiatric rehabilitation interventions integrate evidence-based practices, promising approaches, and emerging methods that can be effectively implemented to enhance health outcomes in this population. This study aims to examine whether the rehabilitative treatment provided to a group of patients with mental illness leads to improvements in health outcomes and psychiatric symptomatology. Methods: This study employed a retrospective quasi-experimental design. Data were collected between 2023 and 2025 within the Partial Hospitalization Program of the Psychiatry and Mental Health Service of Soria (Spain). The sample consisted of 58 participants who received rehabilitative treatment in this setting. Data were collected at the time of patients’ admission and at discharge. Gender, age, psychiatric diagnosis according to ICD-10, and the average length of stay in the rehabilitation program were assessed. The questionnaires administered were psychometrically validated scales related to heteroaggressiveness, perceived quality of life, global functioning, attitudes toward medication, and the risk of suicide. Results: A significant improvement was observed in the Global Assessment of Functioning (GAF) Scale (t = −7.1, p < 0.001), with mean scores increasing from 42.17 at admission to 69.13 at discharge. Additionally, reductions in suicidal risk and hetero-aggressive behavior were noted, alongside improvements in quality of life and treatment adherence. Conclusions: The findings highlight the effectiveness of implementing activities and programs focused on psychiatric rehabilitation processes to promote positive health outcomes. Future research directions and practical implications are discussed to support the continued development and optimization of psychiatric rehabilitation programs. Full article

Background/Objectives: Essential amino acids’ (EAAs) biological effects depend on both gastrointestinal stability and intestinal bioavailability. A commercially available EAA blend has previously shown to be highly bioaccessible and able to inhibit the DPP-IV enzyme both directly and at a cellular level following simulated digestion in vitro. In light with this consideration, the present study aimed to evaluate the intestinal in vitro bioavailability of GAF subjected to INFOGEST digestion (iGAF) and to investigate the metabolic effects of its bioavailable fraction on muscle cells using an integrated Caco-2/C2C12 co-culture model. Methods: Differentiated Caco-2 cell lines were treated with iGAF, and amino acid transport was quantified by ion-exchange chromatography. The basolateral fraction containing bioavailable EAAs was used to treat differentiated C2C12 myotubes for 24 h. Western blot analyses were performed to assess the activation of anabolic and metabolic pathways, including mTOR, Akt, GSK3, AMPK and GLUT-4. Results: More than 50% of each EAA present in iGAF crossed the Caco-2 monolayer, with BCAAs and phenylalanine particularly enriched in the basolateral fraction. Exposure of C2C12 myotubes to the bioavailable iGAF stimulated mTORC1 activation and increased the phosphorylation of Akt and GSK3, indicating an enhanced anabolic response. At a cellular level, iGAF also elevated the p-AMPK/AMPK ratio, suggesting activation of energy-sensing pathways. Moreover, GLUT4 protein levels and glucose uptake were significantly increased. Conclusions: The study focuses exclusively on a cellular model, and results suggested that iGAF is highly bioavailable in vitro and that its absorbed fraction activates key anabolic and metabolic pathways of skeletal muscle cells, enhancing both protein synthesis signaling and glucose utilization in vitro. Full article

To address the limitations of existing fault diagnosis methods for excitation dry-type transformers, such as inadequate utilization of multi-axis vibration data, low recognition accuracy under complex operational conditions, and limited computational efficiency, this paper presents a lightweight fault diagnosis approach based on the fusion of multi-channel vibration signals and visual features. Initially, a multi-physics field coupling simulation model of the excitation dry-type transformer is developed. Vibration data collected from field-installed three-axis sensors are combined to generate typical fault samples, including normal operation, winding looseness, core looseness, and winding eccentricity. Due to the high dimensionality of vibration signals, the Symmetrized Dot Pattern (ISDP) method is extended to aggregate and map time- and frequency-domain information from the x-, y-, and z-axes into a two-dimensional feature map. To optimize the inter-class separability and intra-class consistency of the map, Particle Swarm Optimization (PSO) is employed to adaptively adjust the angle gain factor (η) and time delay coefficient (t). Keypoint descriptors are then extracted from the map using the Oriented FAST and Rotated BRIEF (ORB) feature extraction operator, which improves computational efficiency while maintaining sensitivity to local details. Finally, an efficient fault classification model is constructed using an Adaptive Boosting Support Vector Machine (Adaboost-SVM) to achieve robust fault mode recognition across multiple operating conditions. Experimental results demonstrate that the proposed method achieves a fault diagnosis accuracy of 94.00%, outperforming signal-to-image techniques such as Gramian Angular Field (GAF), Recurrence Plot (RP), and Markov Transition Field (MTF), as well as deep learning models based on Convolutional Neural Networks (CNN) in both training and testing time. Additionally, the method exhibits superior stability and robustness in repeated trials. This approach is well-suited for online monitoring and rapid diagnosis in resource-constrained environments, offering significant engineering value in enhancing the operational safety and reliability of excitation dry-type transformers. Full article

Traffic accidents on highway are often characterized by high destructiveness and severe casualties. Predicting accident severity and understanding its causes are crucial for enhancing highway safety. To address the issues of limited prediction accuracy and poor interpretability of traditional machine learning and deep learning methods at the current stage, this study proposes an accident severity prediction model based on a hybrid architecture of MobileNetV3 and a Transformer. The model first encodes numerical accident-related variables into two-dimensional images using the Gramian Angular Field (GAF) method. Local spatial features are then extracted via the depthwise separable convolution modules of MobileNetV3, and long-range temporal dependencies are captured through the Transformer encoder, which outputs the final prediction. The proposed model is compared with Convolutional Neural Networks (CNNs), Long Short-Term Memory networks (LSTMs), MobileNetV3, a Transformer, and LSTM–Transformer architectures in terms of prediction performance. Results show that the MobileNetV3–Transformer model achieves the highest accuracy of 0.9549. Finally, the DeepSHAP interpretability algorithm is introduced to reveal the systemic influence and contribution of significant factors to accident severity. The results indicate that vehicle age, special road conditions, speed limits, and lighting conditions are closely related to the severity of highway accidents. This study provides a reliable theoretical basis for early warning of highway accidents and refines control measures to further enhance highway safety. Full article

In recent decades, data collection technologies have evolved to facilitate the monitoring and improvement of numerous activities and processes in everyday human life. Their evolution is propelled by the advancement of artificial intelligence (AI), which aims to emulate human intelligence in the execution of related tasks. The remarkable success of deep learning (DL) and computer vision (CV) on image data prompted researchers to consider its application to time series and multivariate data. In this context, time series imaging has been identified as the research field for the transformation of time series data (a one-dimensional data format) into images (a two-dimensional data format). These data can be the variables or features of a system or phenomenon under consideration. State-of-the-art techniques for time series imaging include recurrence plot (RP), Gramian angular field (GAF), and Markov transition field (MTF). This paper proposes a novel, robust, and simple technique of time series imaging using Grayscale Fingerprint Features Field Imaging (G3FI). This novel technique is distinguished by the low resolution of the resulting image and the simplicity of the transformation procedure. The efficacy of the novel and state-of-the-art techniques for enhancing the performance of CNN-based classification models on time series datasets is thoroughly examined and compared. Full article

Background: Stereotactic radiotherapy (SRT) is a promising treatment option for patients with multiple brain metastases (BMs). Using one isocenter instead of a separate isocenter for each BM can reduce the treatment time. This work compares the calculated dose in the treatment planning system with the measured dose using film dosimetry of single-isocenter multi-target (SIMT) SRT for multiple BM. Methods: Fifty patients with 4 to 18 BMs (median = 6, in total 356 BMs) were treated with a single-isocenter non-coplanar LINAC-based treatment with six VMAT arcs. Treatment was performed using RayStation and Elekta Versa HD with Agility multileaf collimator, including a 6D robotic couch. Patient-specific QA measurements were performed with an in-house developed phantom using three layers of GafChromic EBT3 film. Film measurements were analyzed in DoseLab using global gamma with 3% and 1 mm distance-to-agreement criteria. Additionally, secondary dose calculations in Mobius3D were performed with similar gamma criteria. Results: The mean total Paddick conformity index and gradient index were 0.7 ± 0.10 and 5.2 ± 1.9, respectively. Monitor units used were 6321 ± 2510, and mean irradiation time was 600 ± 90 s. The mean global gamma passing rate for all measured films was 94.5 ± 4.6% with 3% and 1 mm criteria, while that of the dose calculations in Mobius3D was 98.2 ± 1.2% with the same criteria. A dependence of gamma passing rates of film measurements on the total PTV volume was observed, whereas such dependence was minimal for Mobius3D. Conclusions: The results demonstrate good agreement between the TPS, film measurements, and independent dose calculations, supporting the dosimetric accuracy of single-isocenter multi-target SRT for treating multiple BMs. Full article

Timely and effective identification of the tool wear condition is crucial for ensuring the machining quality of CNC machine tools. In most industrial scenarios, the cost of sample collection is high, so only a small number of samples are available for model training, making it difficult for the existing tool wear condition monitoring (TCM) methods based on deep learning to achieve high performance. To address this problem, this paper proposes a TCM method based on the improved symmetric dot pattern (SDP) enhanced ResNet18. Firstly, the time series sample data is converted into grayscale matrices through SDP, the correlation coefficient between the grayscale matrices is calculated, and the optimal parameter combination of SDP is determined according to the objective of minimizing the correlation coefficient. Then, the cutting force signal is converted into a lobe diagram of the optimized SDP to enrich the sample feature information. Next, the SDP lobe diagram is input into ResNet18 for few-shot learning. The results of a series of TCM experiments demonstrate that the proposed method is significantly superior to the STFT and GAF based methods. Full article

Reliable operation of proton exchange membrane fuel cells (PEMFCs) is crucial for their widespread commercialization, and accurate fault diagnosis is the key to ensuring their long-term stable operation. However, traditional fault diagnosis methods not only lack sufficient interpretability, making it difficult for users to trust their diagnostic decisions, but also one-dimensional (1D) feature extraction methods highly rely on manual experience to design and extract features, which are easily affected by noise. This paper proposes a new interpretable fault diagnosis algorithm that integrates Gramian angular field (GAF) transform, convolutional neural network (CNN), and gradient-weighted class activation mapping (Grad-CAM) for enhanced fault diagnosis and analysis of proton exchange membrane fuel cells. The algorithm is systematically validated using experimental data to classify three critical health states: normal operation, membrane drying, and hydrogen leakage. The method first converts the 1D sensor signal into a two-dimensional GAF image to capture the temporal dependency and converts the diagnostic problem into an image recognition task. Then, the customized CNN architecture extracts hierarchical spatiotemporal features for fault classification, while Grad-CAM provides visual explanations by highlighting the most influential regions in the input signal. The results show that the diagnostic accuracy of the proposed model reaches 99.8%, which is 4.18%, 9.43% and 2.46% higher than other baseline models (SVM, LSTM, and CNN), respectively. Furthermore, the explainability analysis using Grad-CAM effectively mitigates the “black box” problem by generating visual heatmaps that pinpoint the key feature regions the model relies on to distinguish different health states. This validates the model’s decision-making rationality and significantly enhances the transparency and trustworthiness of the diagnostic process. Full article

The phosphodiesterase 1 genes PDE1A, PDE1B, and PDE1C encode calcium-regulated cyclic nucleotide phosphodiesterases that mediate the interplay between calcium and cyclic nucleotide signaling in the brain, heart, and vasculature. While an inhibitory domain and a calmodulin-binding domain have been identified in PDE1, the mechanism of regulation is not understood. In this study, we investigated the regulatory mechanism through a series of experiments. The experimental data, supported by AlphaFold structure predictions, consistently point to the following model of PDE1 regulation: In the absence of calcium, the inhibitory domain of PDE1 binds to and blocks the catalytic site via molecular interactions that closely resemble those observed in autoinhibited PDE4. Upon calcium/calmodulin binding to PDE1’s calmodulin-binding domain, steric constraints prevent the inhibitory domain from reaching the catalytic site, thereby activating PDE1. Understanding this mode of PDE1 regulation may open new avenues for pharmacological intervention. Moreover, it establishes PDE1 and PDE4 as a second mechanistic class of phosphodiesterase regulation in addition to the GAF-domain-mediated regulation known to control the activity of several other PDEs. Full article

This paper presents a resilient and energy-efficient framework for jamming mitigation in cluster-based wireless sensor networks (WSNs), addressing a critical vulnerability in hostile or interference-prone environments. The proposed approa ch integrates dynamic cluster reorganization, adaptive MAC-layer behavior, and multipath routing strategies to restore communication capabilities and sustain network functionality under jamming conditions. The framework is evaluated across heterogeneous topologies using Zigbee and Bluetooth Low Energy (BLE); both stacks were validated in a physical testbed with matched jammer and traffic conditions, while simulation was used solely to tune parameters and support sensitivity analyses. Results demonstrate significant improvements in Packet Delivery Ratio, end-to-end delay, energy consumption, and retransmission rate, with BLE showing particularly high resilience when combined with the mitigation mechanism. Furthermore, a comparative analysis of routing protocols including AODV, GAF, and LEACH reveals that hierarchical protocols achieve superior performance when integrated with the proposed method. This framework has broader applicability in mission-critical IoT domains, including environmental monitoring, industrial automation, and healthcare systems. The findings confirm that the framework offers a scalable and protocol-agnostic defense mechanism, with potential applicability in mission-critical and interference-sensitive IoT deployments. Full article

Tool wear is a major challenge in sheet-metal forming, as it directly affects product quality and process stability. Reliable monitoring of tool-wear conditions is therefore essential, yet it remains challenging due to limited data availability and uncertainties in manufacturing conditions. To this end, this study evaluates different strategies for developing robust machine learning models under data scarcity for fluctuating manufacturing conditions: a 1D-CNN using time-series data (baseline model), a 1D-CNN with signal fusion of force and acceleration signals, and a 2D-CNN based on Gramian Angular Field (GAF) transformation. Experiments are conducted using inline data from a blanking process with varying material thicknesses and varying availability of training data. The results show that the fusion model achieved the highest improvement (up to 93.2% with the least training data) compared to the baseline model (78.3%). While the average accuracy of the 2D-CNN was comparable to that of the baseline model, its performance was more consistent, with a reduced standard deviation of 5.4% compared to 9.2%. The findings underscore the benefits of sensor fusion and structured signal representation in enhancing classification robustness. Full article

Background/Objectives: Autism Spectrum Disorder (ASD) presents complex developmental challenges that require coordinated, individualized interventions. This study aimed to evaluate the effectiveness of a transdisciplinary, family-centered approach in improving clinical and functional outcomes in children and adolescents with ASD. Methods: A longitudinal study was conducted with 53 participants aged 2 to 16 years, all with confirmed ASD diagnoses. Assessments were performed at baseline, 6 months, and 12 months. Participants received personalized, evidence-based interventions provided by a multidisciplinary team working within a transdisciplinary model. Therapies were delivered individually and in groups, with flexible intervention phases tailored to each participant’s evolving needs. Outcomes were measured using the Clinical Global Impression (CGI), Global Assessment of Functioning (GAF), and the Aberrant Behavior Checklist (ABC). Results: Clinical and functional improvements were observed over the 12-month period. Most participants reached high functional levels by the end of the study. Caregivers reported notable reductions in support needs, while therapist ratings confirmed more moderate improvements. Decreases in behavioral challenges, sensory difficulties, and sleep disturbances were observed, alongside gains in adaptability and functional play. Greater family involvement was associated with more favorable outcomes. Conclusions: A transdisciplinary, family-centered intervention model was beneficial in supporting developmental progress in children and adolescents with ASD. The findings highlight the importance of flexible, team-based care and emphasize the critical role of family engagement in achieving positive long-term outcomes. Full article

The protection, safety and security (PSS) of complex objectives have become managerial subjects for aspects such as guarantee, growth and development. These aspects are marked by intrinsic and extrinsic factors. The present paper approaches the analysis of the current state in the PSS field through a case study with reference to the situation of small modular reactor (SMR) investments, which officially entered the application agenda for the first time in Romania and in the European Union (EU). The main object of the research aims at the perception scale of integrated PSS, using the method of interviewing decision-makers and researching the factorial structure of the centrality items of PSS activities in SMRs. The central view of this article is to conceptually delimit integrated PSS, their operationalization to complex objectives, and, respectively, their management in the context of research on the analysis and development directions registered nationally and internationally in the field. Derived from this approach, we defined secondary objectives as follows: to highlight the achievements in the field that contribute to ensuring the functioning of complex industrial objectives; to characterize energy demands in the context of the increasing phenomenon of globalization, technological transfer and knowledge; and to establish the framework for evaluating integrated PSS that have a preventive, safe and feasible contribution in the new economy. Full article

The detection of damage in wind turbine blades is critical for ensuring their operational efficiency and longevity. This study presents a novel method for wind turbine blade damage detection, utilizing Gramian Angular Field (GAF) transformations of vibration signals in combination with Convolutional Neural Networks (CNNs). The GAF method enables the transformation of vibration signals, which are captured using a triaxial accelerometer, into angular representations that preserve temporal dependencies and reveal distinctive texture patterns that can be associated with structural damage. This transformation facilitates the capability of CNNs to identify complex features correlated with crack severity in wind turbine blades, thereby enhancing the precision and effectiveness of turbine fault diagnosis. The GAF-CNN model achieved a notable classification accuracy over 99.9%, demonstrating its robustness and potential for automated damage detection. Unlike traditional methods, which rely on expert interpretation and are sensitive to noise, the proposed system offers a more efficient and precise tool for damage monitoring. The findings suggest that this method can significantly enhance wind turbine condition monitoring systems, offering reduced dependency on manual inspections and improving early detection capabilities. Full article

To address the limitations of traditional fault diagnosis methods for rotating machinery, which heavily rely on single-dimensional vibration data and fail to fully exploit the deep features of time-series data, this study proposes an innovative diagnostic model that integrates Gramian Angular Field-Parallel Convolutional Neural Network (GAF-PCNN) with Gated Recurrent Units (GRU). Specifically, one-dimensional vibration signals are first transformed into Gramian angular and difference fields as image representations using Gramian Angular Field (GAF). These two types of images are then input into parallel-configured PCNN modules for feature learning. The features extracted by the two CNN branches are weighted and fused to construct a combined feature sequence. This sequence is subsequently fed into the GRU network to capture temporal dependencies and perform deep feature extraction. In this process, an integrated self-attention mechanism is applied to dynamically select key features. The proposed method is validated using two publicly available datasets, including comparative and noise interference experiments. The results demonstrate that the proposed model excels in diagnostic accuracy, model generalization, and robustness against noise interference. Full article