Search Results (3,583)

Deep learning, a subfield of artificial intelligence that uses neural networks with multiple layers, is rapidly changing healthcare. Its ability to analyze large datasets and extract relevant information makes it a powerful tool for improving diagnosis, treatment, and disease management. The integration of DL with pressure mats—which are devices that use pressure sensors to continuously and non-invasively monitor the interaction between patients and the contact surface—is a promising application. These pressure platforms generate data that can be very useful for detecting postural anomalies. In this paper we will discuss the application of deep learning algorithms in the analysis of pressure data for the detection of postural asymmetries in 139 patients aged 3 to 20 years. We investigated several main tasks: patient classification, hemibody segmentation, recognition of specific body parts, and generation of automated clinical reports. For this purpose, convolutional neural networks in their classification and regression modalities, the object detection algorithm YOLOv8, and the open language model LLaMa3 were used. Our results demonstrated high accuracy in all tasks: classification achieved 100% accuracy; hemibody division obtained an MAE of approximately 7; and object detection had an average accuracy of 70%. These results demonstrate the potential of this approach for monitoring postural and motor disabilities. By enabling personalized patient care, our methodology contributes to improved clinical outcomes and healthcare delivery. To our best knowledge, this is the first study that combines pressure images with multiple deep learning algorithms for the detection and assessment of postural disorders and motor disabilities in this group of patients. Full article

Pancreatic cystic lesions (PCLs) represent a spectrum of non-neoplasms and neoplasms with varying malignant potential, posing significant challenges in diagnosis and management. While some PCLs are precursors to pancreatic cancer, others remain benign, necessitating accurate differentiation for optimal patient care. Conventional approaches to PCL management rely heavily on radiographic imaging, and endoscopic ultrasound (EUS) guided fine-needle aspiration (FNA), coupled with clinical and biochemical data. However, the observer-dependent nature of image interpretation and the complex morphology of PCLs can lead to diagnostic uncertainty and variability in patient management strategies. This review critically evaluates current PCL diagnosis and surveillance practices, showing features of the different lesions and highlighting the potential limitations of conventional methods. We then explore the potential of artificial intelligence (AI) to transform PCL management. AI-driven strategies, including deep learning algorithms for automated pancreas and lesion segmentation, and radiomics for analyzing heterogeneity, can improve diagnostic accuracy and risk stratification. These advanced techniques can provide more objective and reproducible assessments, aiding clinicians in decision-making regarding follow-up intervals and surgical interventions. Early results suggest that AI-driven methods can significantly improve patient outcomes by enabling earlier detection of high-risk lesions and reducing unnecessary procedures for benign cysts. Finally, this review emphasizes that AI-driven approaches could potentially reshape the landscape of PCL management, ultimately leading to improved pancreatic cancer prevention. Full article

Background: To validate the automated quantification of cardiac chamber volumes and myocardial mass on non-contrast chest CT using cardiac MR (CMR) as a reference. Methods: We retrospectively included 53 consecutive patients who received non-contrast chest CT and CMR within three weeks. A deep learning model created cardiac segmentations on axial soft-tissue reconstructions from CT, covering all four cardiac chambers and the left ventricular myocardium. Segmentations on CMR cine short-axis and long-axis images served as a reference. Standard estimates of diagnostic accuracy were calculated for ventricular volumes at end-diastole and end-systole (LVEDV, LVESV, RVEDV, RVESV), left ventricular mass (LVM), and atrial volumes (LA, RA) at ventricular end-diastole. A qualitative assessment noted segmentation issues. Results: The deep learning model generated CT measurements for 52 of the 53 patients (98%). Based on CMR measurements, the average LVEDV was 166 ± 64 mL, RVEDV was 144 ± 51 mL, and LVM was 115 ± 39 g. The CT measurements correlated well with CMR measurements for LVEDV, LVESV, and LVM (r = 0.85, r = 0.84, and r = 0.91; all p < 0.001) and RVEDV and RVESV (r = 0.82 and r = 0.84; both p < 0.001), and moderately well with LA and RA (r = 0.77 and r = 0.67; both p < 0.001). Absolute agreements likewise favored LVEDV, LVESV, and LVM. ECG-gating did not relevantly influence the results. The CT results correctly identified 7/15 LV and 1/1 RV as dilated (one and six false positives, respectively). Major qualitative issues were found in three cases (6%). Conclusions: Automated cardiac chamber volume and myocardial mass quantification on non-contrast chest CT produced viable measurements in this retrospective sample. Relevance Statement: An automated cardiac assessment on non-contrast chest CT provides quantitative morphological data on the heart, enabling a preliminary organ evaluation that aids in incidentally identifying at-risk patients who may benefit from a more targeted diagnostic workup. Full article

An increasing number of automation technologies for dairy cattle farming, including automatic milking, feeding, manure removal and bedding, are now commercially available. The effects of these technologies on individual aspects of animal welfare have already been explored to some extent. However, as of now, there are no studies that analyze the impact of increasing farm automation through various combinations of these technologies. The objective of this study was to examine potential correlations between welfare indicators from the Welfare Quality^® Assessment protocol and dairy farms with varying degrees of automation. To achieve this, 32 trial farms in Northern and Central Germany were categorized into varying automation levels using a newly developed classification system. The Welfare Quality^® Assessment protocol was used to conduct welfare assessments on all participating farms. Using analysis of variance (ANOVA), overall welfare scores and individual measures from the protocol were compared across farms with differing automation levels. No significant differences were observed in overall welfare scores, suggesting that the impact of automation does not exceed other farm-related factors influencing animal wellbeing, such as housing environment or management methods. However, significant effects of milking, feeding, and bedding systems on the appropriate behavior of cattle were observed. Higher levels of automation had a positive impact on the human–animal relationship and led to positive emotional states. Moreover, farms with higher automation levels had significantly lower scores for the prevalence of severe lameness and dirtiness of lower legs. It could be concluded that a higher degree of automation could help to improve animal welfare on dairy farms. Full article

This study presents a detailed analysis of the stability of weigh-in-motion sensors used at vehicle weighing stations. The objective of this research was a long-term assessment of reading variability, with a particular focus on the sensors’ application in automated measurement stations. These investigations constitute a critical component of modern traffic management systems and vehicle overload control. The analysis covered the period from 2022 to 2024, incorporating data from vehicles participating in regular traffic as well as dedicated control runs using vehicles with known wheel and axle load distributions. The study also considered changes in road surface conditions, particularly rut depth, and their variations over the examined period. The findings revealed that, despite the lack of station calibration over the three-year period, the observed parameters exhibited only minor changes. These results confirm the high stability of the applied measurement system and its ability to maintain measurement accuracy over extended operational periods, which is essential for its practical application in real-world traffic conditions. Full article

Lung ultrasound is an increasingly utilized non-invasive imaging modality for assessing lung condition but interpreting it can be challenging and depends on the operator’s experience. To address these challenges, this work proposes an approach that combines artificial intelligence (AI) with feature-based signal processing algorithms. We introduce a specialized deep learning model designed and trained to facilitate the analysis and interpretation of lung ultrasound images by automating the detection and location of pulmonary features, including the pleura, A-lines, B-lines, and consolidations. Employing Convolutional Neural Networks (CNNs) trained on a semi-automatically annotated dataset, the model delineates these pulmonary patterns with the objective of enhancing diagnostic precision. Real-time post-processing algorithms further refine prediction accuracy by reducing false-positives and false-negatives, augmenting interpretational clarity and obtaining a final processing rate of up to 20 frames per second with accuracy levels of 89% for consolidation, 92% for B-lines, 66% for A-lines, and 92% for detecting normal lungs compared with an expert opinion. Full article

Image velocimetry has become an effective method of mapping flow conditions in rivers, but this analysis is typically performed in a post-processing mode after data collection is complete. In this study, we evaluated the potential to infer flow velocities in approximately real time as thermal images are being acquired from an uncrewed aircraft system (UAS). The sensitivity of thermal image velocimetry to environmental conditions was quantified by conducting 20 flights over four days and assessing the accuracy of image-derived velocity estimates via comparison to direct field measurements made with an acoustic Doppler current profiler (ADCP). This analysis indicated that velocity mapping was most reliable when the air was cooler than the water. We also introduced a workflow for River Velocity Measurement in Approximately Real Time (RiVMART) that involved transferring brief image sequences from the UAS to a ground station as distinct data packets. The resulting velocity fields were as accurate as those generated via post-processing. A new particle image velocimetry (PIV) algorithm based on staggered image sequences increased the number of image pairs available for a given image sequence duration and slightly improved accuracy relative to a standard PIV implementation. Direct, automated geo-referencing of image-derived velocity vectors based on information on the position and orientation of the UAS acquired during flight led to poor alignment with vectors that were geo-referenced manually by selecting ground control points from an orthophoto. This initial proof-of-concept investigation suggests that our workflow could enable highly efficient characterization of flow fields in rivers and might help support applications that require rapid response to changing conditions. Full article

Numerous studies address the estimation of energy consumption at intermodal terminals, with a primary focus on existing facilities. However, a significant research gap lies in the lack of reliable methods and tools for the ex ante estimation of energy consumption in transshipment systems. Such tools are essential for assessing the energy demand and intensity of intermodal terminals during the design phase. This gap presents a challenge for intermodal terminal designers, power grid operators, and other stakeholders, particularly in an era of growing energy needs. The authors of this paper identified this issue in the context of a real business case while planning potential intermodal terminal locations along new railway lines. The need became apparent when power grid designers requested energy consumption forecasts for the proposed terminals, highlighting the necessity to formulate and mathematically solve this problem. To address this challenge, a three-stage model was developed based on a pre-designed intermodal terminal. Stage I focused on establishing the fundamental assumptions for intermodal terminal operations. Key parameters influencing energy intensity were identified, such as the size of the transshipment yard, the types of loading operations, the number of containers handled, and the selection of handling equipment. These parameters formed the foundation for further analysis and modeling. Stage II focused on determining the optimal number of machines required to handle a given throughput. This included determining the specific parameters of the equipment, such as speed, span, and efficiency coefficients, as well as ensuring compliance with installation constraints dictated by the terminal layout. Stage III focused on estimating the energy consumption of both individual handling cycles and the total consumption of all handling equipment installed at the terminal. This required obtaining detailed information about the operational parameters of the handling equipment, which directly influence energy consumption. Using these parameters and the equations outlined in Stage III, the energy consumption for a single loading cycle was calculated for each type of handling equipment. Based on the total number of loading operations and model constraints, the total energy consumption of the terminal was estimated for various workload scenarios. In this phase of the study, numerous test calculations were performed. The analysis of testing parameters and the specified terminal layout revealed that energy consumption per cycle varies by equipment type: rail-mounted gantry cranes consume between 5.23 and 8.62 kWh, rubber-tired gantry cranes consume between 3.86 and 7.5 kWh, and automated guided vehicles consume approximately 0.8 kWh per cycle. All handling equipment, based on the adopted assumptions, will consume between 2200 and 13,470 kWh per day. Based on the testing results, a methodology was developed to aid intermodal terminal designers in estimating energy consumption based on variations in input parameters. The results closely align with those reported in the global literature, demonstrating that the methodology proposed in this article provides an accurate approach for estimating energy consumption at intermodal terminals. This method is also suited for use in ex ante cost–benefit analysis. A sensitivity analysis revealed the key variables and parameters that have the greatest impact on unit energy consumption per handling cycle. These included the transshipment yard’s dimensions, the mass of the equipment and cargo, and the nominal specifications of machinery engines. This research is significant for present-day economies heavily reliant on electricity, particularly during the energy transition phase, where efficient management of energy resources and infrastructure is essential. In the case of Poland, where this analysis was conducted, the energy transition involves not only switching handling equipment from combustion to electric power but, more importantly, decarbonizing the energy system. This study is the first to provide a methodology fully based on the design parameters of a planned intermodal terminal, validated with empirical data, enabling the calculation of future energy consumption directly from terminal technical designs. It also fills a critical research gap by enabling ex ante comparisons of energy intensity across transport chains, an area previously constrained by the lack of reliable tools for estimating energy consumption within transshipment terminals. Full article

Camera traps offer enormous new opportunities in ecological studies, but current automated image analysis methods often lack the contextual richness needed to support impactful conservation outcomes. Integrating vision–language models into these workflows could address this gap by providing enhanced contextual understanding and enabling advanced queries across temporal and spatial dimensions. Here, we present an integrated approach that combines deep learning-based vision and language models to improve ecological reporting using data from camera traps. We introduce a two-stage system: YOLOv10-X to localise and classify species (mammals and birds) within images and a Phi-3.5-vision-instruct model to read YOLOv10-X bounding box labels to identify species, overcoming its limitation with hard-to-classify objects in images. Additionally, Phi-3.5 detects broader variables, such as vegetation type and time of day, providing rich ecological and environmental context to YOLO’s species detection output. When combined, this output is processed by the model’s natural language system to answer complex queries, and retrieval-augmented generation (RAG) is employed to enrich responses with external information, like species weight and IUCN status (information that cannot be obtained through direct visual analysis). Combined, this information is used to automatically generate structured reports, providing biodiversity stakeholders with deeper insights into, for example, species abundance, distribution, animal behaviour, and habitat selection. Our approach delivers contextually rich narratives that aid in wildlife management decisions. By providing contextually rich insights, our approach not only reduces manual effort but also supports timely decision making in conservation, potentially shifting efforts from reactive to proactive. Full article

Monitoring the body condition of dairy cows is essential for ensuring their health and productivity, but traditional BCS methods—relying on visual or tactile assessments by skilled personnel—are subjective, labor-intensive, and impractical for large-scale farms. To overcome these limitations, we present BCS-YOLO, a lightweight and automated BCS framework built on YOLOv8, which enables consistent, accurate scoring under complex conditions with minimal computational resources. BCS-YOLO integrates the Star-EMA module and the Star Shared Lightweight Detection Head (SSLDH) to enhance the detection accuracy and reduce model complexity. The Star-EMA module employs multi-scale attention mechanisms that balance spatial and semantic features, optimizing feature representation for cow hindquarters in cluttered farm environments. SSLDH further simplifies the detection head, making BCS-YOLO viable for deployment in resource-limited scenarios. Additionally, channel-based knowledge distillation generates soft probability maps focusing on key body regions, facilitating effective knowledge transfer and enhancing performance. The results on a public cow image dataset show that BCS-YOLO reduces the model size by 33% and improves the mean average precision (mAP) by 9.4%. These advances make BCS-YOLO a robust, non-invasive tool for consistent and accurate BCS in large-scale farming, supporting sustainable livestock management, reducing labor costs, enhancing animal welfare, and boosting productivity. Full article

Determining the maturity of cocoa pods early is not just about guaranteeing harvest quality and optimizing yield. It is also about efficient resource management. Rapid identification of the stage of maturity helps avoid losses linked to a premature or late harvest, improving productivity. Early determination of cocoa pod maturity ensures both the quality and quantity of the harvest, as immature or overripe pods cannot produce premium cocoa beans. Our innovative research harnesses artificial intelligence and computer vision technologies to revolutionize the cocoa industry, offering precise and advanced tools for accurately assessing cocoa pod maturity. Providing an objective and rapid assessment enables farmers to make informed decisions about the optimal time to harvest, helping to maximize the yield of their plantations. Furthermore, by automating this process, these technologies reduce the margins for human error and improve the management of agricultural resources. With this in mind, our study proposes to exploit a computer vision method based on the GLCM (gray level co-occurrence matrix) algorithm to extract the characteristics of images in the RGB (red, green, blue) and LAB (luminance, axis between red and green, axis between yellow and blue) color spaces. This approach allows for in-depth image analysis, which is essential for capturing the nuances of cocoa pod maturity. Next, we apply classification algorithms to identify the best performers. These algorithms are then combined via stacking and voting techniques, allowing our model to be optimized by taking advantage of the strengths of each method, thus guaranteeing more robust and precise results. The results demonstrated that the combination of algorithms produced superior performance, especially in the LAB color space, where voting scored 98.49% and stacking 98.71%. In comparison, in the RGB color space, voting scored 96.59% and stacking 97.06%. These results surpass those generally reported in the literature, showing the increased effectiveness of combined approaches in improving the accuracy of classification models. This highlights the importance of exploring ensemble techniques to maximize performance in complex contexts such as cocoa pod maturity classification. Full article

In response to the critical demand for innovative solutions to tackle plastic pollution, this research presents a low-cost, fully automated plastic injection molding system designed to convert waste into sustainable products. Constructed entirely from repurposed materials, the apparatus focuses on processing high-density polyethylene (HDPE) efficiently without hydraulic components, thereby enhancing eco-friendliness and accessibility. Performance evaluations identified an optimal molding temperature of 200 °C, yielding consistent products with a minimal weight deviation of 4.17%. The key operational parameters included a motor speed of 525 RPM, a gear ratio of 1:30, and an inverter frequency of 105 Hz. Further tests showed that processing temperatures of 210 °C and 220 °C, with injection times of 15 to 35 s, yielded optimal surface finish and complete filling. The surface finish, assessed through image intensity variation, had a low coefficient of variation (≤5%), while computer vision evaluation confirmed the full filling of all specimens in this range. A laser-based overflow detection system has minimized material waste, proving effective in small-scale, community recycling. This study underscores the potential of low-cost automated systems to advance the practices of circular economies and enhance localized plastic waste management. Future research will focus on automation, temperature precision, material adaptability, and emissions management. Full article

Background: Temporal lobe epilepsy (TLE) is the most common form of drug-resistant epilepsy, often associated with hippocampal sclerosis (HS), which involves selective neuronal loss in the Cornu Ammonis subregion 1 CA1 and CA4 regions of the hippocampus. Granule cells show migration and mossy fiber sprouting, though the mechanisms remain unclear. Microglia play a role in neurogenesis and synaptic modulation, suggesting they may contribute to epilepsy. This study examines the role of microglia and axonal guidance molecules in neuronal reorganization in TLE. Methods: Nineteen hippocampal samples from patients with TLE undergoing epilepsy surgery were analyzed. Microglial activity (M1/M2-like microglia) and neuronal guidance molecules were assessed using microscopy and semi-automated techniques. Gene expression was evaluated using the nCounter Expression Profiling method. Results: Neuronal cell loss was correlated with decreased activity of the M1 microglial phenotype. In the CA2 region, neuronal preservation was linked to increased mossy fiber sprouting and microglial presence. Neuronal markers such as Deleted in Colorectal Cancer (DCC) and Synaptopodin were reduced in areas of cell death, while Netrin-1 was elevated in the granule cell layer, potentially influencing mossy fiber sprouting. The nCounter analysis revealed downregulation of genes involved in neuronal activity (e.g., NPAS4, BCL-2, GRIA1) and upregulation of IκB, indicating reduced neuroinflammation. Conclusions: This study suggests reduced neuroinflammation in areas of neuronal loss, while regions with preserved neurons showed mossy fiber sprouting associated with microglia, Netrin-1, and DCC. Full article

Electric power material warehouses are critical to optimizing power grid supply chains and reducing carbon emissions, aiding the power sector’s decarbonization and climate goals. Nevertheless, to our knowledge, there are no comprehensive assessments of the life cycle carbon emissions associated with storage warehouses, so the emission reduction potential of the ever-increasing number of automated technologies is still unknown. This study presents an extensive life cycle carbon footprint assessment model tailored for electric power material warehouses, and it encompasses both traditional and automated frameworks. Utilizing a process-based life cycle assessment (LCA) methodology, carbon emissions across five distinct stages are examined: storage buildings and facilities, loading and unloading, transportation, packaging, and information management systems. For this purpose, warehouses in Jiangsu Province, China, are employed as a case study. The results show that automating warehouses can achieve a reduction in total carbon emissions of 42.85% compared with traditional warehouses, with total life cycle emissions of 39,531.26 tCO₂, and the transportation stage is identified as the predominant contributor. This research not only offers actionable recommendations for strategies, including renewable energy integration, intelligent control systems, and standardized packaging protocols, but also establishes a framework for future investigations of refining carbon accounting methodologies—particularly in underexplored domains such as packaging. Full article

As fully automated vehicles (FAVs) advance towards SAE Level 5 automation, the role of in-vehicle intelligent agents (IVIAs) in shaping passenger experience becomes critical. Even at SAE Level 5 automation, effective communication between the vehicle and the passenger will remain crucial to ensure a sense of safety, trust, and engagement. This study explores how different types and combinations of information provided by IVIAs influence user experience, acceptance, and trust. A sample of 25 participants was recruited for the study, which experienced a fully automated ride in a driving simulator, interacting with Iris, an IVIA designed for voice-only communication. The study utilized both qualitative and quantitative methods to assess participants’ perceptions. Findings indicate that critical and vehicle-status-related information had the highest positive impact on trust and acceptance, while personalized information, though valued, raised privacy concerns. Participants showed high engagement with non-driving-related activities, reflecting a high level of trust in the FAV’s performance. Interaction with the anthropomorphic IVIA was generally well received, but concerns about system transparency and information overload were noted. The study concludes that IVIAs play a crucial role in fostering passenger trust in FAVs, with implications for future design enhancements that emphasize emotional intelligence, personalization, and transparency. These findings contribute to the ongoing development of IVIAs and the broader adoption of automated driving technologies. Full article