Search Results (2,611)

Unmanned aerial vehicles (UAVs) often face significant challenges in trajectory tracking within complex dynamic environments, where uncertainties, external disturbances, and nonlinear dynamics hinder accurate and stable control. To address this issue, a bio-inspired deep reinforcement learning (DRL) algorithm is proposed, integrating behavior cloning (BC) and long short-term memory (LSTM) networks. This method can achieve autonomous learning of high-precision control policy without establishing an accurate system dynamics model. Motivated by the memory and prediction functions of biological neural systems, an LSTM module is embedded into the policy network of the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. This structure captures temporal state patterns more effectively, enhancing adaptability to trajectory variations and resilience to delays or disturbances. Compared to memoryless networks, the LSTM-based design better replicates biological time-series processing, improving tracking stability and accuracy. In addition, behavior cloning is employed to pre-train the DRL policy using expert demonstrations, mimicking the way animals learn from observation. This biomimetic plausible initialization accelerates convergence by reducing inefficient early-stage exploration. By combining offline imitation with online learning, the TD3-LSTM-BC framework balances expert guidance and adaptive optimization, analogous to innate and experience-based learning in nature. Simulation experimental results confirm the superior robustness and tracking accuracy of the proposed method, demonstrating its potential as a control solution for autonomous UAVs. Full article

This study presents a systematic review of the literature on teaching techniques that enhance student motivation and academic performance across basic, secondary, and higher education levels. The review is grounded in the distinction between intrinsic and extrinsic motivation, highlighting their decisive roles in engagement and achievement. The analysis focuses on active learning methodologies such as project-based learning, collaborative learning, gamification, and flipped classrooms. It identifies the mechanisms by which each approach fosters students’ interest, sense of competence, and persistence. Four international databases were consulted, and studies published between 2000 and 2024 reporting quantitative measures of motivation and/or performance were selected. Five investigations met all eligibility criteria and were assessed for methodological quality. The results indicate moderate motivational effects, especially when interventions last at least eight weeks, provide frequent feedback, and place students at the center of authentic problem-solving. Greater gains were also observed in STEM disciplines and in contexts that encourage peer collaboration. Based on these findings, practical recommendations are proposed for educators: structure interdisciplinary projects, incorporate playful elements in the initial stages of formal education, combine autonomous work with small-group discussions, and use data analysis tools to deliver personalized feedback. The study concludes that adopting diverse, student-centered pedagogical practices enhances motivation and academic achievement, leading to deeper and more lasting learning outcomes. Full article

The integrity of subsea oil and gas pipelines is essential for offshore safety and environmental protection. Conventional leak detection approaches, such as manual inspection and indirect sensing, are often costly, time-consuming, and prone to subjectivity, motivating the development of automated methods. In this study, we present a deep learning-based framework for detecting underwater leaks using images acquired in controlled experiments designed to reproduce representative conditions of subsea monitoring. The dataset was generated by simulating both gas and liquid leaks in a water tank environment, under scenarios that mimic challenges observed during Remotely Operated Vehicle (ROV) inspections along the Brazilian coast. It was further complemented with artificially generated synthetic images (Stable Diffusion) and publicly available subsea imagery. Multiple Convolutional Neural Network (CNN) architectures, including VGG16, ResNet50, InceptionV3, DenseNet121, InceptionResNetV2, EfficientNetB0, and a lightweight custom CNN, were trained with transfer learning and evaluated on validation and blind test sets. The best-performing models achieved stable performance during training and validation, with macro F1-scores above 0.80, and demonstrated improved generalization compared to traditional baselines such as VGG16. In blind testing, InceptionV3 achieved the most balanced performance across the three classes when trained with synthetic data and augmentation. The study demonstrates the feasibility of applying CNNs for vision-based leak detection in complex underwater environments. A key contribution is the release of a novel experimentally generated dataset, which supports reproducibility and establishes a benchmark for advancing automated subsea inspection methods. Full article

Background/Objectives: Recent state-of-the-art advances in deep learning have significantly improved diagnostic accuracy in medical imaging, particularly in chest radiograph (CXR) analysis. Motivated by these developments, a comprehensive comparison was conducted to investigate how architectural choices affect performance of 14 deep learning models across Convolutional Neural Networks (CNNs), Transformer-based models, and Mamba-based State Space Models. Methods: These models were trained and evaluated under identical conditions on the NIH ChestX-ray14 dataset, a large-scale and widely used benchmark comprising 112,120 labeled CXR images with 14 thoracic disease categories. Results: It was found that recent hybrid architectures—particularly ConvFormer, CaFormer, and EfficientNet—deliver superior performance in both common and rare pathologies. ConvFormer achieved the highest mean AUROC of 0.841 when averaged across all 14 thoracic disease classes, closely followed by EfficientNet and CaFormer. Notably, AUROC scores of 0.94 for hernia, 0.91 for cardiomegaly, and 0.88 for edema and effusion were achieved by the proposed models, surpassing previously reported benchmarks. Conclusions: These results not only highlight the continued strength of CNNs but also demonstrate the growing potential of Transformer-based architectures in medical image analysis. This work contributes to the literature by providing a unified, state-of-the-art benchmarking of diverse deep learning models, offering valuable guidance for researchers and practitioners developing clinically robust AI systems for radiology. Full article

The growing demand for sustainable and multifunctional construction materials, particularly those capable of addressing durability and energy challenges, has motivated the development of conductive and photothermally active geopolymers. This study investigated the use of an Fe-rich spinel aggregate (FSA) as a high-density filler in geopolymers composed of ground granulated blast furnace slag and bauxite residue, with a fixed addition of 1 wt% graphite (binder-based) to enhance electrical conductivity. The effects of different FSA replacement percentages (0–100%) on compressive strength, electrical conductivity, photothermal efficiency, and chemical resistance were evaluated. An increase in the FSA content translated to an increase in the final compressive strength, with 100% FSA replacement achieving the highest value of 45.5 ± 2.5 MPa at 28 days. As the FSA content increased, the electrical resistivity decreased to as low as 42 Ω·m at 100% replacement. Under simulated solar flux conditions (1 kW/m²), photothermal analysis revealed that the 100% FSA mixtures exhibited the highest surface temperature increase of 9.8 °C after 300 s, indicating their superior thermal responsiveness. Furthermore, acid immersion in 10% HCl for 28 days showed mass gain in all geopolymers, with the highest gain observed at 50% FSA (+11.51%). Similarly, the strength increased after acid exposure up to a 75% FSA content. These findings highlight the multifunctional potential of FSA-enhanced geopolymers for high-mechanical-performance, electrically conductive, photothermally active, and chemically durable materials as multifunctional construction materials. Full article

This paper presents the design and evaluation of a sound-driven robot quiz system that enhances fairness and engagement in educational human–robot interaction (HRI). The system integrates a real-time sound-based first-responder detection mechanism with gamified multimodal feedback, including verbal cues, music, gestures, points, and badges. Motivational design followed the Octalysis framework, and the system was evaluated using validated scales from the Technology Acceptance Model (TAM), the Intrinsic Motivation Inventory (IMI), and the Godspeed Questionnaire. An experimental study was conducted with 32 university students comparing the proposed multimodal system combined with sound-driven first quiz responder detection to a sequential turn-taking quiz response with a verbal-only feedback system as a baseline. Results revealed significantly higher scores for the experimental group across perceived usefulness (M = 4.32 vs. 3.05, d = 2.14), perceived ease of use (M = 4.03 vs. 3.17, d = 1.43), behavioral intention (M = 4.24 vs. 3.28, d = 1.62), and motivation (M = 4.48 vs. 3.39, d = 3.11). The sound-based first-responder detection system achieved 97.5% accuracy and was perceived as fair and intuitive. These findings highlight the impact of fairness, motivational feedback, and multimodal interaction on learner engagement. The proposed system offers a scalable model for designing inclusive and engaging educational robots that promote active participation through meaningful and enjoyable interactions. Full article

The increasing popularity of long-distance running in urban areas reflects a convergence of personal health goals and sustainable urban living practices. However, understanding the psychological drivers behind such behaviors remains essential for designing effective health promotion strategies. This study investigated the motivations of 155 participants of the Poznan Marathon and Half Marathon using the validated Polish version of the Motivations of Marathoners Scale (MOMS). Data were collected via an online survey and analyzed using descriptive statistics, t-tests, ANOVA, and MANOVA to assess differences across gender, education, place of residence, and BMI. The highest-rated motivations were personal goal achievement and health orientation, aligning with the values of sustainable urban living. The least important were recognition and affiliation. Women reported significantly higher motivations related to health and weight control, while men showed a greater tendency toward competition. Education level and place of residence did not significantly affect motivational profiles. BMI was positively correlated only with weight-related motives. The findings highlight the importance of tailoring physical activity promotion to demographic differences, particularly gender and BMI. Supporting long-distance running through inclusive, personalized strategies may enhance its role in fostering healthier and more sustainable urban communities. Full article

In the Ultra-High-Definition (UHD) domain, blind image quality assessment remains challenging due to the high dimensionality of UHD images, which exceeds the input capacity of deep learning networks. Motivated by the visual discrepancies observed between high- and low-quality images after down-sampling and Super-Resolution (SR) reconstruction, we propose a SUper-Resolved Pseudo References In Dual-branch Embedding (SURPRIDE) framework tailored for UHD image quality prediction. SURPRIDE employs one branch to capture intrinsic quality features from the original patch input and the other to encode comparative perceptual cues from the SR-reconstructed pseudo-reference. The fusion of the complementary representation, guided by a novel hybrid loss function, enhances the network’s ability to model both absolute and relational quality cues. Key components of the framework are optimized through extensive ablation studies. Experimental results demonstrate that the SURPRIDE framework achieves competitive performance on two UHD benchmarks (AIM 2024 Challenge, PLCC = 0.7755, SRCC = 0.8133, on the testing set; HRIQ, PLCC = 0.882, SRCC = 0.873). Meanwhile, its effectiveness is verified on high- and standard-definition image datasets across diverse resolutions. Future work may explore positional encoding, advanced representation learning, and adaptive multi-branch fusion to align model predictions with human perceptual judgment in real-world scenarios. Full article

Sexual behavior is a complex process in which the brain plays an active role. In the male rat, stimuli from the female are perceived through sensory receptors related to olfaction, hearing, vision, and the perigenital area, priming the individual for a sexual response. This process culminates with ejaculation and the deposition of semen into the uterine tract with the aim of achieving fertilization. The brain plays a fundamental role in both generating motivation and executing male sexual behavior. Meanwhile, the spinal cord, through the autonomic nervous system and the pelvic ganglion, transmits information to the reproductive organs, including the testes. Currently, there is extensive evidence demonstrating the involvement of various brain structures in the regulation of sexual behavior, as well as specific regions of the spinal cord involved in the control of ejaculation. For instance, the medial preoptic area (MPOA) has been shown to regulate the secretion of pituitary hormones, which in turn modulate the function of reproductive organs. Among these, testosterone production is particularly notable, as this hormone not only directly affects reproductive organs but also exerts a modulatory role on brain nuclei responsible for sexual behavior. Although there is a reciprocal regulation between the nervous and endocrine systems, it is important to note that the execution of sexual behavior also impacts peripheral structures, such as the major pelvic ganglion (MPG) and the testis, preparing the organism for reproduction. The purpose of this mini-review is to provide an overview of the main brain nuclei involved in the regulation of sexual behavior, as well as the spinal cord regions implicated in reproduction. Finally, we discuss how these structures may alter their function in the context of neurodegenerative diseases, aiming to introduce readers to this field of study. Full article

This study investigates the use of artificial neural networks (ANNs) and deep neural networks (DNNs) for estimating photovoltaic (PV) energy output, with a particular focus on hyperparameter tuning. Supervised regression for photovoltaic (PV) direct current power prediction was conducted using only sensor-based inputs (PanelTemp, Irradiance, AmbientTemp, Humidity), together with physically motivated-derived features (ΔT, IrradianceEff, IrradianceSq, Irradiance × ΔT). Samples acquired under very low irradiance (<50 W m⁻²) were excluded. Predictors were standardized with training-set statistics (z-score), and the target variable was modeled in log space to stabilize variance. A shallow artificial neural network (ANN; single hidden layer, widths {4–32}) was compared with deeper multilayer perceptrons (DNN; stacks {16 8}, {32 16}, {64 32}, {128 64}, {128 64 32}). Hyperparameters were selected with a grid search using validation mean squared error in log space with early stopping; Bayesian optimization was additionally applied to the ANN. Final models were retrained and evaluated on a held-out test set after inverse transformation to watts. Test performance was obtained as MSE, RMSE, MAE, R², and MAPE for the ANN and DNN. Hence, superiority in absolute/squared error and explained variance was exhibited by the ANN, whereas lower relative error was achieved by the DNN with a marginal MAE advantage. Ablation studies showed that moderate depth can be beneficial (e.g., two-layer variants), and a simple bootstrap ensemble improved robustness. In summary, the ANN demonstrated superior performance in terms of absolute-error accuracy, whereas the DNN exhibited better consistency with relative-error accuracy. Full article

An unsupervised anomaly-detection framework is proposed and field validated for thrust-bearing monitoring in the impulse turbine of a shoreline oscillating water-column (OWC) wave energy converter (WEC) off Jeju Island, Korea. Operational monitoring is constrained by nonstationary sea states, scarce fault labels, and low-rate supervisory logging at 20 Hz. To address these conditions, a 24 h period of normal operation was median-filtered to suppress outliers, and six physically motivated time-domain features were computed from triaxial vibration at 10 s intervals: absolute mean; standard deviation (STD); root mean square (RMS); skewness; shape factor (SF); and crest factor (CF, peak divided by RMS). A feature-based autoencoder was trained to reconstruct the feature vectors, and reconstruction error was evaluated with an adaptive threshold derived from the moving mean and moving standard deviation to accommodate baseline drift. Performance was assessed on a 2 h test segment that includes a 40 min simulated fault window created by doubling the triaxial vibration amplitudes prior to preprocessing and feature extraction. The detector achieved accuracy of 0.99, precision of 1.00, recall of 0.98, and F1 score of 0.99, with no false positives and five false negatives. These results indicate dependable detection at low sampling rates with modest computational cost. The chosen feature set provides physical interpretability under the 20 Hz constraint, and denoising stabilizes indicators against marine transients, supporting applicability in operational settings. Limitations associated with simulated faults are acknowledged. Future work will incorporate long-term field observations with verified fault progressions, cross-site validation, and integration with digital-twin-enabled maintenance. Full article

In spite of the ever-growing body of research in achievement goal profiles and their contribution to performance, the research on young children is quite limited. This study examined achievement goal profiles related to mathematics and literacy performance among third-grade students (N = 185, M = 8.73 years; 98 girls), using Latent Profile Analysis. Four distinct profiles emerged—Mastery-Oriented, Approach-Oriented, High Multiple-Goals, and Moderate Multiple-Goals—that were highly similar across math and literacy (contingency coefficient = 0.59). Schoolchildren endorsing the Approach-Oriented profile demonstrated higher achievement compared to those with High Multiple-Goals or Moderate Multiple-Goals profiles, which involved more avoidance goals and were less adaptive (with up to 8% of variance explained by profile). Gender differences were observed: girls were more likely to endorse profiles combining multiple goals, whereas boys more often endorsed mastery or approach profiles. These results highlight early inter-individual differences in motivational development, observable in both mathematics and literacy. Promoting adaptive goal profiles in early education may enhance academic engagement and help reduce emerging motivational disparities. Full article

Internal waves (IWs) play a crucial role in the transport of energy and matter within the ocean while also posing significant risks to marine engineering, navigation, and underwater communication systems. Consequently, effective segmentation methods are essential for mitigating their adverse impacts and minimizing associated hazards. A promising strategy involves applying remote sensing image segmentation techniques to accurately identify IWs, thereby enabling predictions of their propagation velocity and direction. However, current IWs segmentation models struggle to balance computational efficiency and segmentation accuracy, often resulting in either excessive computational costs or inadequate performance. Motivated by recent developments in the Mamba2 architecture, this paper introduces the state-space model meets linear attention (SMLA), a novel segmentation framework specifically designed for IWs. The proposed hybrid architecture effectively integrates three key components: a feature-aware serialization (FAS) block to efficiently convert spatial features into sequences; a state-space model with linear attention (SSM-LA) block that synergizes a state-space model with linear attention for comprehensive feature extraction; and a decoder driven by hierarchical fusion and upsampling, which performs channel alignment and scale unification across multi-level features to ensure high-fidelity spatial detail recovery. Experiments conducted on a dataset of 484 synthetic-aperture radar (SAR) images containing IWs from the South China Sea achieved a mean Intersection over Union (MIoU) of 74.3%, surpassing competing methods evaluated on the same dataset. These results demonstrate the superior effectiveness of SMLA in extracting features of IWs from SAR imagery. Full article

The increasing number of intelligent connected vehicles (ICVs) is leading to a growing scarcity of spectrum resources for the Internet of Vehicles (IoV), which has created an urgent need for the use of full-duplex non-orthogonal multiple access (FD-NOMA) techniques in vehicle-to-everything (V2X) communications. Meanwhile, for the flexibility of autonomous aerial vehicles (AAVs), V2X communications assisted by AAVs are regarded as a potential solution to achieve reliable communication between ICVs. However, if the integration of FD-NOMA and AAVs can satisfy the requirements of V2X communications, then quickly and accurately analyzing the total achievable rate becomes a challenge. Motivated by the above, an accurate analytical expression for the total achievable rate over Rician fading channels is proposed to evaluate the transmission performance of NOMA-enhanced AAV-assisted IoV with imperfect channel state information (CSI). Then, we derive an approximate expression with the truncated error, based on which the closed-form expression for the approximate error is theoretically provided. Finally, the simulation results demonstrate the accuracy of the obtained approximate results, where the maximum approximate error does not exceed 0.5%. Moreover, the use of the FD-NOMA technique in AAV-assisted IoV can significantly improve the total achievable rate compared to existing work. Furthermore, the influence of key network parameters (e.g., the speed and Rician factor) on achievable rate is thoroughly discussed. Full article

Currently, teaching programming in primary and secondary schools is already standard practice in many countries. Although teaching methods and tools vary, the goal remains the same: to teach students how to program, i.e., to create appropriate algorithms for solving various tasks. In our research, we focused on the influence of personal interest and career orientation as motivation for better performance in programming and algorithm design. The main objective of the research was to determine the influence of student motivation, personal preferences, and career orientation tests on programming results. The secondary objective of the research was to verify in the practical part whether elementary school students (eighth and ninth grade) are able to program an industrial machine that they will encounter at secondary vocational schools. A structured questionnaire and an unconventional device, the PLC Logo from Siemens, were used as testing tools. Research has shown that students who have the prerequisites for studying at a technical secondary school achieve better results in programming than students who do not have these prerequisites. Full article