Search Results (65,649)

Reinforcement learning (RL) has been shown to be effective in path planning. However, it usually requires exploring a sufficient number of state–action pairs, some of which may be unsafe when deployed in practical obstacle environments. To this end, this paper proposes an end-to-end planning method based model-free RL framework with optimization, which can achieve better learning performance with a safety guarantee. Firstly, for second-order drone systems, a differentiable high-order control barrier function (HOCBF) is introduced to ensure the output of the planning algorithm falls in a safe range. Then, a safety layer based on the HOCBF is proposed, which projects RL actions into a feasible solution set to guarantee safe exploration. Finally, we conducted a simulation for drone obstacle avoidance and validated the proposed method in the simulation environment. The experimental results demonstrate a significant enhancement over the baseline approach. Specifically, the proposed method achieved a substantial reduction in the average cumulative number of collisions per drone during training compared to the baseline. Additionally, in the testing phase, the proposed method realized a 43% improvement in the task success rate relative to the MADDPG. Full article

Background: Managing metabolism for optimal training, performance, and recovery in medium-to-high-level endurance runners involves enhancing energy systems through strategic nutrient intake. Optimal carbohydrate intake before, during, and after endurance running can enhance glycogen stores and maintain optimal blood glucose levels, influencing various physiological responses and adaptations, including transitory post-endurance inflammation. This randomized trial investigates the impact of a high-dose 2:1 maltodextrin–fructose supplementation to medium-to-high-level endurance runners immediately before, during, and after a 15 km run at 90% VO_2max intensity on post-exercise inflammatory stress. Methods: We evaluated inflammatory biomarkers and lipidomic profiles before the endurance tests and up to 24 h after. We focused on the effects of high-dose 2:1 maltodextrin–fructose supplementation on white blood cell count, neutrophil number, IL-6, cortisol, and CRP levels, as well as polyunsaturated fatty acids, ω-3 index, and AA/EPA ratio. Results: This supplementation significantly reduced inflammatory markers and metabolic stress. Additionally, it may enhance the post-activity increase in blood ω-3 fatty acid levels and reduce the increase in ω-6 levels, resulting in a lower trend of AA/EPA ratio at 24 h in the treated arm. Conclusions: Adequate carbohydrate supplementation may acutely mitigate inflammation during a one-hour endurance activity of moderate-to-high intensity. These effects could be beneficial for athletes engaging in frequent, high-intensity activities. Full article

The authenticity of classical Arabic poetry has long been challenged by claims that some part of the pre-Islamic poetic heritage should not be attributed to this era. According to these assertions, some of this legacy was produced after the advent of Islam and ascribed, for different reasons, to pre-Islamic poets. As pre-Islamic poets were illiterate, medieval Arabic literature devotees relied on Bedouin oral transmission when writing down and collecting the poems about two centuries later. This process left the identity of the real poets who composed these poems and the period in which they worked unresolved. In this work, we seek to answer the questions of how and to what extent we can identify the period in which classical Arabic poetry was composed, where we exploit modern-day automatic text processing techniques for this aim. We consider a dataset of Arabic poetry collected from the diwans (‘collections of poems’) of thirteen Arabic poets that corresponds to two main eras: the pre-ʿAbbāsid era (covering the period between the 6th and the 8th centuries CE) and the ʿAbbāsid era (starting in the year 750 CE). Some poems in each diwan are considered ‘original’; i.e., poems that are attributed to a certain poet with high confidence. The diwans also include, however, an additional section of poems that are attributed to a poet with reservations, meaning that these poems might have been composed by another poet and/or in another period. We trained a set of machine learning algorithms (classifiers) in order to explore the potential of machine learning techniques to automatically identify the period in which a poem had been written. In the training phase, we represent each poem using various types of features (characteristics) designed to capture lexical, topical, and stylistic aspects of this poetry. By training and assessing automatic models of period prediction using the ’original’ poetry, we obtained highly encouraging results, measuring between 0.73–0.90 in terms of F1 for the various periods. Moreover, we observe that the stylistic features, which pertain to elements that characterize Arabic poetry, as well as the other feature types, are all indicative of the period in which the poem had been written. We applied the resulting prediction models to poems for which the authorship period is under dispute (‘attributed’) and got interesting results, suggesting that some of the poems may belong to different eras—an issue to be further examined by Arabic poetry researchers. The resulting prediction models may be applied to poems for which the authorship period is under dispute. We demonstrate this research direction, presenting some interesting anecdotal results. Full article

The use of a pretrained image classification model (trained on cats and dogs, for example) as a perceptual loss function for hyperspectral super-resolution and pansharpening tasks is surprisingly effective. However, RGB-based networks do not take full advantage of the spectral information in hyperspectral data. This inspired the creation of HyperKon, a dedicated hyperspectral Convolutional Neural Network backbone built with self-supervised contrastive representation learning. HyperKon uniquely leverages the high spectral continuity, range, and resolution of hyperspectral data through a spectral attention mechanism. We also perform a thorough ablation study on different kinds of layers, showing their performance in understanding hyperspectral layers. Notably, HyperKon achieves a remarkable 98% Top-1 retrieval accuracy and surpasses traditional RGB-trained backbones in both pansharpening and image classification tasks. These results highlight the potential of hyperspectral-native backbones and herald a paradigm shift in hyperspectral image analysis. Full article

Although deep learning (DL) algorithms have been proved to be effective in diverse research domains, their application in developing models for tabular data remains limited. Models trained on tabular data demonstrate higher efficacy using traditional machine learning models than DL models, which are largely attributed to the size and structure of tabular datasets and the specific application contexts in which they are utilized. Thus, the primary objective of this paper is to propose a method to use the supremacy of Stacked Bidirectional LSTM (Long Short-Term Memory) deep learning algorithms in pattern discovery incorporating tabular data with customized 3D tensor modeling in feeding neural networks. Our findings are empirically validated using six diverse, publicly available datasets each varying in size and learning objectives. This paper proves that the proposed model based on time-sequence DL algorithms, which were generally described as inadequate when dealing with tabular data, yields satisfactory results and competes effectively with other algorithms specifically designed for tabular data. An additional benefit of this approach is its ability to preserve simplicity while ensuring fast model training also with large datasets. Even with extremely small datasets, models can be applied to achieve exceptional predictive results and fully utilize their capacity. Full article

The key point in the process of agent-based management in e-service for malware detection (according to accuracy criteria) is a decision-making process. To determine the optimal e-service for malware detection, two concepts were investigated: Fuzzy Logic (FL) and Probabilistic Neural Networks (PNN). In this study, three evolutionary variants of fuzzy partitioning, including regular, hierarchical fuzzy partitioning, and k-means, were used to automatically process the design of the fuzzy partition. Also, this study demonstrates the application of a feature selection method to reduce the dimensionality of the data by removing irrelevant features to create fuzzy logic in a dataset. The behaviors of malware are analyzed by fuzzifying relevant features for pattern recognition. The Apriori algorithm was applied to the fuzzified features to find the fuzzy-based rules, and these rules were used for predicting the output of malware detection e-services. Probabilistic neural networks were also used to find the ideal agent-based model for numerous classification problems. The numerical results show that the agent-based management performances trained with the clustering method achieve an accuracy of 100% with the PNN-MCD model. This is followed by the FL model, which classifies on the basis of linguistic variables and achieves an average accuracy of 82%. Full article

Zoo enclosure design, and housing and husbandry protocols, will always be a compromise between what a species has evolved to do and what is possible to offer in a human-created environment. For some species, behaviours that are commonly performed in the wild may be constrained by husbandry practices that are used for ease or aesthetics or are accepted conventions. As zoos place more emphasis on positive animal welfare states, zoo enclosures should be scrutinised to check that what is provided, in terms of useful space, appropriate replication of habitat features, and maximal potential for natural behaviour performance, is relevant to the species and individuals being housed. For some species, zoos need to grapple with tough questions where the answer may not seem immediately obvious to ensure they are continuously improving standards of care, opportunities for the performance of species-typical behaviours, and advancing the attainment of positive welfare states. Determining the importance of flight, for example, and what this behaviour adds to the quality of life of a zoo-housed bird, is an important question that needs addressing to truly advance aviculture and how we determine bird welfare. This paper provides questions that should be answered and poses measures of what flight means to a bird, to provide evidence for the development and evolution of zoo bird housing. If we can devise some way of asking the animals in our care what they need, we can more firmly support decisions made that surround enclosure design, and housing decisions. Ultimately, this means gathering evidence on whether birds like to fly (e.g., from birds in training or demonstration activities) by applying mixed methods approaches of behavioural analysis, data on wild ecology, qualitative behavioural assessment, and cognitive bias testing to develop a robust suite of tools to address avian welfare considerations. Avian welfare scientists should attempt to define what meaningful flight is (i.e., flight that truly suggests a bird is flying) in order to support guidelines on aviary dimensions, space allowance, and welfare outputs from birds in both flighted and flight-restricted populations, and to determine what is most appropriate for an individual species. Changing the term “best practice” husbandry guidelines to “better practice” husbandry guidelines would instil the importance of regular review and reassessment of housing and management suitability for a species to ensure such care regimes remain appropriate. With an increasingly welfare-savvy public visiting zoos, it is essential that we seek more evidence to support and justify how birds are kept and ultimately use such evidence to enact changes to practices that are shown to infringe on avian welfare. Full article

Introduction and Objective: The aim of this study was to evaluate the coronary arteries in patients undergoing thoracic CT angiography for congenital heart disease, to determine the frequency of detection of coronary artery anomalies in congenital heart diseases, and to determine which type of anomaly is more common in which disease. Materials and Methods: In our investigation, a 128-detector multidetector computed tomography machine was used to perform thorax CT angiography. The acquisition parameters were set to 80–100 kVp based on the patient’s age and mAs that the device automatically determined based on the patient’s weight. During the examination, an intravenous (IV) nonionic contrast material dose of 1–1.5 mL/kg was employed. An automated injector was used to inject contrast material at a rate of 1.5–2 mL/s. In the axial plane, 2.5 mm sections were extracted, and they were rebuilt with 0.625 mm section thickness. Results: Between October 2022 and May 2024, 132 patients who were diagnosed with congenital heart disease by echocardiography and underwent Thorax CT angiography in our department were retrospectively evaluated. Of the evaluated patients, 32 were excluded with exclusion criteria such as patients being younger than 3 months, older than 18 years, insufficient contrast enhancement in imaging and contrast-enhanced imaging, thin vascular structure, and motion and contrast artifacts; the remaining 100 patients were included in this study. The age range of these patients was 3 months to 18 years (mean age 4.4 years). Conclusion: In congenital heart diseases, attention to the coronary arteries on thoracic CT angiography examination in the presence of possible coronary anomalies may provide useful information. Full article

Hydrodynamic models are often used to obtain insights into potential dike breaches, because dike breaches can have severe consequences. However, their high computational cost makes them unsuitable for real-time flood forecasting. Machine learning models are a promising alternative, as they offer reasonable accuracy at a significant reduction in computation time. In this study, we explore the effectiveness of a Long Short-Term Memory (LSTM) neural network in fast flood modelling for a dike breach in the Netherlands, using training data from a 1D–2D hydrodynamic model. The LSTM uses the outflow hydrograph of the dike breach as input and produces water depths on all grid cells in the hinterland for all time steps as output. The results show that the LSTM accurately reflects the behaviour of overland flow: from fast rising and high water depths near the breach to slowly rising and lower water depths further away. The water depth prediction is very accurate (MAE = 0.045 m, RMSE = 0.13 m), and the inundation extent closely matches that of the hydrodynamic model throughout the flood event (Critical Success Index = 94%). We conclude that machine learning techniques are suitable for fast modelling of the complex dynamics of dike breach floods. Full article

Autonomous decision-making is a hallmark of intelligent mobile robots and an essential element of autonomous navigation. The challenge is to enable mobile robots to complete autonomous navigation tasks in environments with mapless or low-precision maps, relying solely on low-precision sensors. To address this, we have proposed an innovative autonomous navigation algorithm called PEEMEF-DARC. This algorithm consists of three parts: Double Actors Regularized Critics (DARC), a priority-based excellence experience data collection mechanism, and a multi-source experience fusion strategy mechanism. The algorithm is capable of performing autonomous navigation tasks in unmapped and unknown environments without maps or prior knowledge. This algorithm enables autonomous navigation in unmapped and unknown environments without the need for maps or prior knowledge. Our enhanced algorithm improves the agent’s exploration capabilities and utilizes regularization to mitigate the overestimation of state-action values. Additionally, the priority-based excellence experience data collection module and the multi-source experience fusion strategy module significantly reduce training time. Experimental results demonstrate that the proposed method excels in navigating the unmapped and unknown, achieving effective navigation without relying on maps or precise localization. Full article

Oral cancer, also known as oral squamous cell carcinoma (OSCC), is one of the most prevalent types of cancer and caused 177,757 deaths worldwide in 2020, as reported by the World Health Organization. Early detection and identification of OSCC are highly correlated with survival rates. Therefore, this study presents an automatic image-processing-based machine learning approach for OSCC detection. Histopathological images were used to compute deep features using various pretrained models. Based on the classification performance, the best features (ResNet-101 and EfficientNet-b0) were merged using the canonical correlation feature fusion approach, resulting in an enhanced classification performance. Additionally, the binary-improved Haris Hawks optimization (b-IHHO) algorithm was used to eliminate redundant features and further enhance the classification performance, leading to a high classification rate of 97.78% for OSCC. The b-IHHO trained the k-nearest neighbors model with an average feature vector size of only 899. A comparison with other wrapper-based feature selection approaches showed that the b-IHHO results were statistically more stable, reliable, and significant (p < 0.01). Moreover, comparisons with those other state-of-the-art (SOTA) approaches indicated that the b-IHHO model offered better results, suggesting that the proposed framework may be applicable in clinical settings to aid doctors in OSCC detection. Full article

In this paper, the dataset is collected from the fluidic muscle datasheet. This dataset is then used to train models predicting the pressure, force, and contraction length of the fluidic muscle, as three separate outputs. This modeling is performed with four algorithms—extreme gradient boosted trees (XGB), ElasticNet (ENet), support vector regressor (SVR), and multilayer perceptron (MLP) artificial neural network. Each of the four models of fluidic muscles (5-100N, 10-100N, 20-200N, 40-400N) is modeled separately: First, for a later comparison. Then, the combined dataset consisting of data from all the listed datasets is used for training. The results show that it is possible to achieve quality regression performance with the listed algorithms, especially with the general model, which performs better than individual models. Still, room for improvement exists, due to the high variance of the results across validation sets, possibly caused by non-normal data distributions. Full article

Objectives: The adolescent development period is critical for rugby league athletes, given the physical growth, neuromuscular adaptation, and skill acquisition that occurs. Secondary schools play an important role in the development of adolescent rugby league players; however, players may be selected into rugby league academies and development programs outside of school, as well as participating in additional sports. In turn, the training loads these young athletes accrue and the implications of these loads are currently unknown. Our aim was to quantify the training loads and concomitant changes in physical qualities of schoolboy and adolescent rugby league players during mesocycles within the pre-season and in-season phases. Design: This is a prospective experimental study. Methods: Twenty-one schoolboy rugby league players (16.2 ± 1.3 years) were monitored across separate 4-week mesocycles in the pre-season and in-season. Session frequency, duration, and the session rating of perceived exertion (sRPE) load were reported for all examples of training and match participation in the school rugby league program, as well as club and representative teams for any sport and personal strength and conditioning. Various physical qualities were assessed before and after each 4-week mesocycle. Results: The sRPE load that accumulated across the 4-week mesocycles was higher in the pre-season than the in-season (8260 ± 2021 arbitrary units [AU] vs. 6148 ± 980 AU, p < 0.001), with non-significant differences in accumulated session frequency and duration between phases. Session frequency, duration, and sRPE load differed (p < 0.05) between some weeks in an inconsistent manner during the pre-season and in-season mesocycles. Regarding physical qualities, improvements (p < 0.05) in the 10 m sprint test, Multistage Fitness Test, medicine ball throw, and 1-repetition maximum back squat and bench press performances were evident across the pre-season mesocycle, with declines (p < 0.05) in the 505-Agility Test, L-run Test, and 1-repetition maximum back squat performances across the in-season mesocycle. Conclusions: These novel training load data show schoolboy rugby league players experience considerable demands that may be suitable in developing several physical qualities during the pre-season but detrimental to maintaining such qualities across the in-season. Full article

On many maps, relief shading is one of the most significant graphical elements. Modern relief shading techniques include neural networks. To generate such shading automatically at an arbitrary scale, one needs to consider how the resolution of the input digital elevation model (DEM) relates to the neural network process and the maps used for training. Currently, there is no clear guidance on which DEM resolution to use to generate relief shading at specific scales. To address this gap, we trained the U-Net models on swisstopo manual relief shadings of Switzerland at four different scales and using four different resolutions of SwissALTI3D DEM. An interactive web application designed for this study allows users to outline a random area and compare histograms of varying brightness between predictions and manual relief shadings. The results showed that DEM resolution and output scale influence the appearance of the relief shading, with an overall scale/resolution ratio. We present guidelines for generating relief shading with neural networks for arbitrary areas and scales. Full article

The advancement of urban rail transit is increasingly confronted with environmental challenges related to vibration and noise. To investigate the critical issues surrounding vibration propagation and the generation of structure-borne noise, a two-story frame building was selected for on-site measurements of both vibration and its induced structure-borne noise. The collected data were analyzed in both the time and frequency domains to explore the correlation between these phenomena, leading to the proposal of a hybrid prediction method for structural noise that was subsequently compared with measured results. The findings indicate that the excitation of structure-borne noise produces significant waveforms within sound signals. The characteristic frequency of the structure-borne noise is 25–80 Hz, as well as that of the train-induced vibration. Furthermore, there exists a positive correlation between structural vibration and structure-borne noise, whereby increased levels of vibration correspond to more pronounced structure-borne noise; additionally, indoor distribution patterns of structure-borne noise are non-uniform, with corner wall areas exhibiting greater intensity than central room locations. Finally, a hybrid prediction methodology that is both semi-analytical and semi-empirical is introduced. The approach derives dynamic response predictions of the structure through analytical solutions, subsequently estimating the secondary noise within the building’s interior using a newly formulated empirical equation to facilitate rapid predictions regarding indoor building vibrations and structure-borne noises induced by subway train operations. Full article