Search Results (59,520)

The search for viable alternative resources is essential for advancing sustainable development in the construction industry. A significant global concern is the substantial generation of industrial waste, particularly coal ash byproducts such as fly ash (FA) and coal bottom ash (CBA) from thermal power plants (TPPs). India ranks as the third-largest producer of coal ash globally and the second-largest in Asia, generating approximately 105 million metric tonnes annually. While TPP-derived wastes have been extensively studied in masonry mortars, the potential of CBA as a partial or complete replacement for natural fine aggregates (NFA) in high-strength mortar (HSM) remains significantly underexplored. This study investigates the fresh, mechanical, and microstructural properties of mortar incorporating CBA as a substitute for NFA, specifically up to a 100% replacement level Flow table tests revealed improved workability with increasing CBA content, which is attributed to its porous microstructure; however, significant bleeding was observed at higher replacement levels (≥75%). The dry density consistently decreased with the addition of CBA with a reduction of up to 19.27% at full replacement. Ultrasonic pulse velocity (UPV) values declined with higher levels of CBA but improved with curing age. The mortar incorporating up to 100% CBA retains appreciable mechanical properties despite a progressive reduction in compressive strength (C_S) with increasing CBA content. The observed compressive strengths for the different mixes were as follows: control mix (CM) at 36.72 MPa, mix with 25% CBA (CBA25) at 25.56 MPa, mix with 50% CBA (CBA50) at 19.69 MPa, mix with 75% CBA (CBA75) at 16 MPa, and mix with 100% CBA (CBA100) at 9.93 MPa. All mixes exceeded the minimum strength criteria, confirming their classification as HSMs at all replacement levels. These results highlight the potential of CBA as a sustainable alternative in construction materials, supporting efforts toward resource efficiency and environmental sustainability in the industry. Full article

This paper contains an analysis of methods for person classification based on signals from wearable IMU sensors during sports. While this problem has been investigated in prior work, existing approaches have not addressed it within the context of few-shot or minimal-data scenarios. A few-shot scenario is especially useful as the main use case for person identification in sports systems is to be integrated into personalised biofeedback systems in sports. Such systems should provide personalised feedback that helps athletes learn faster. When introducing a new user, it is impractical to expect them to first collect many recordings. We demonstrate that the problem can be solved with over 90% accuracy in both open-set and closed-set scenarios using established methods. However, the challenge arises when applying few-shot methods, which do not require retraining the model to recognise new people. Most few-shot methods perform poorly due to feature extractors that learn dataset-specific representations, limiting their generalizability. To overcome this, we propose a combination of an unsupervised feature extractor and a prototypical network. This approach achieves 91.8% accuracy in the five-shot closed-set setting and 81.5% accuracy in the open-set setting, with a 99.6% rejection rate for unknown athletes. Full article

This paper presents a dual-structured convolutional neural network (CNN) for image classification, which integrates two parallel branches: CNN-A with spatial attention and CNN-B with channel attention. The spatial attention module in CNN-A dynamically emphasizes discriminative regions by aggregating channel-wise information, while the channel attention mechanism in CNN-B adaptively recalibrates feature channel importance. The extracted features from both branches are fused through concatenation, enhancing the model’s representational capacity by capturing complementary spatial and channel-wise dependencies. Extensive experiments on a 12-class image dataset demonstrate the superiority of the proposed model over state-of-the-art methods, achieving 98.06% accuracy, 96.00% precision, and 98.01% F1-score. Despite a marginally longer training time, the model exhibits robust convergence and generalization, as evidenced by stable loss curves and high per-class recognition rates (>90%). The results validate the efficacy of dual attention mechanisms in improving feature discrimination for complex image classification tasks. Full article

Plants vary in number of chromosomes (ploidy levels), which can influence morphological traits, including the size and density of stomata cells. Although biologists can detect these differences under a microscope, the process is often time-consuming and tedious. This study aims to automate the classification of blackcurrant (Ribes nigrum L.) ploidy levels—diploid, triploid, and tetraploid—by leveraging deep learning techniques. Convolutional Neural Networks and Vision Transformers are employed to perform microscopic image classification across two distinct blackcurrant datasets. Initial experiments demonstrate that these models can effectively classify ploidy levels when trained and tested on subsets derived from the same dataset. However, the primary challenge lies in proposing a model capable of yielding satisfactory classification results across different datasets ensuring robustness and generalization, which is a critical step toward developing a universal ploidy classification system. In this research, a variety of experiments is performed including application of augmentation technique. Model efficacy is evaluated with standard metrics and its interpretability is ensured through Gradient-weighted Class Activation Mapping visualizations. Finally, future research directions are outlined with application of other advanced state-of-the-art machine learning methods to further refine ploidy level prediction in botanical studies. Full article

High-precision semantic segmentation of remote sensing imagery is crucial in geospatial analysis. It plays an immeasurable role in fields such as urban governance, environmental monitoring, and natural resource management. However, when confronted with complex objects (such as winding roads and dispersed buildings), existing semantic segmentation methods still suffer from inadequate target recognition capabilities and multi-scale representation issues. This paper proposes a neural network model, LMVMamba (LoRA Multi-scale Vision Mamba), for semantic segmentation of remote sensing images. This model integrates the advantages of convolutional neural networks (CNNs), Transformers, and state-space models (Mamba) with a multi-scale feature fusion strategy. It simultaneously captures global contextual information and fine-grained local features. Specifically, in the encoder stage, the ResT Transformer serves as the backbone network, employing a LoRA fine-tuning strategy to effectively enhance model accuracy by training only the introduced low-rank matrix pairs. The extracted features are then passed to the decoder, where a U-shaped Mamba decoder is designed. In this stage, a Multi-Scale Post-processing Block (MPB) is introduced, consisting of depthwise separable convolutions and residual concatenation. This block effectively extracts multi-scale features and enhances local detail extraction after the VSS block. Additionally, a Local Enhancement and Fusion Attention Module (LAS) is added at the end of each decoder block. LAS integrates the SimAM attention mechanism, further enhancing the model’s multi-scale feature fusion capability and local detail segmentation capability. Through extensive comparative experiments, it was found that LMVMamba achieves superior performance on the OpenEarthMap dataset (mIoU 52.3%, OA 69.8%, mF1: 68.0%) and LoveDA (mIoU 67.9%, OA 80.3%, mF1: 80.5%) datasets. Ablation experiments validated the effectiveness of each module. The final results indicate that this model is highly suitable for high-precision land-cover classification tasks in remote sensing imagery. LMVMamba provides an effective solution for precise semantic segmentation of high-resolution remote sensing imagery. Full article

Modern energy systems are undergoing a profound transformation characterized by the active replacement of conventional fossil-fuel-based power plants with renewable energy sources. This transition aims to reduce the carbon emissions associated with electricity generation while enhancing the economic performance of electric power market players. However, alongside these benefits come several challenges, including reduced overall inertia within energy systems, heightened stochastic variability in grid operation regimes, and stricter demands on the rapid response capabilities and adaptability of emergency controls. This paper presents a novel methodology for selecting effective control laws for low-inertia energy systems, ensuring their dynamic stability during post-emergency operational conditions. The proposed approach integrates advanced techniques, including feature selection via decision tree algorithms, classification using Random Forest models, and result visualization through the Mean Shift clustering method applied to a two-dimensional representation derived from the t-distributed Stochastic Neighbor Embedding technique. A modified version of the IEEE39 benchmark model served as the testbed for numerical experiments, achieving a classification accuracy of 98.3%, accompanied by a control law synthesis delay of just 0.047 milliseconds. In conclusion, this work summarizes the key findings and outlines potential enhancements to refine the presented methodology further. Full article

Background: The miniaturization of ureterorenoscopes increasingly enables atraumatic primary ureteroscopy, without ureteral dilation or presenting. This study aims to evaluate the feasibility and safety of primary ureteroscopy using the HU30M (6.3 Fr, HugeMed, Shenzhen HugeMed Medical Technical Development Co., Ltd., China), the smallest currently available ureteroscope Methods: We analyzed consecutive patients in whom primary ureteroscopy using the HU30M was performed or attempted, using prospectively collected in-hospital and 30-day follow-up data for retrospective evaluation. The primary outcome was the success rate of primary ostial intubation. Secondary outcomes included the stone-free rate (SFR) in patients with urolithiasis, incidence of in-hospital complications (Clavien–Dindo classification) and 30-day emergency readmission. Additionally, we conducted a propensity score-matched comparative analysis of the HU30M versus a contemporary 7.5 Fr digital single-use ureteroscope (PUSEN PU3033AH, Zhuhai Pusen Medical Technology Co., Ltd., China). Results: Between January and April 2025, primary ureteroscopy using the HU30M was performed or attempted in 34 patients, including four bilateral procedures. Primary ureteroscopy was defined as ureteroscopic access without prior stenting or dilation. Indications were diagnostic evaluation in 15 patients (44%), uretreroscopic stone treatment in 10 patients (29%) and endoscopic combined intrarenal surgery (ECIRS) in 9 patients (27%). Successful primary ostial intubation was achieved in 36 of 38 renal units (95%). Among urolithiasis cases, SFR was 17/19 (90%) in-hospital complications were limited to postoperative fever in two patients (6%) and no procedure-related 30-day emergency readmission occurred. In matched analyses, HU30M demonstrated significantly shorter operative times compared with the 7.5 Fr ureteroscope, while postoperative hemoglobin drop, inflammatory parameters and renal function were comparable. Conclusions: Primary ureteroscopy with HU30M is feasible and safe across diverse indications, achieving high success of atraumatic ostial access. Comparative analyses suggest procedural efficiency advantages and overall safety comparable to the current digital single-use ureteroscope standard. Full article

Artificial intelligence (AI) is an important tool for improving agricultural tasks. In particular, object detection methods based on convolutional neural networks (CNNs) enable the detection and classification of objects directly in the field. Combined with unmanned aerial vehicles (UAVs, drones), these methods allow efficient crop monitoring. The primary challenge is to develop models that are both accurate and feasible under real-world conditions. This study addresses this challenge by evaluating marigold flower detection using three groups of CNN detectors: canonical models, including YOLOv2, Faster R-CNN, and SSD with their original backbones; modified versions of these detectors using DarkNet-53; and modern architectures, including YOLOv11, YOLOv12, and the RT-DETR. The dataset consisted of 392 images from marigold fields, which were manually labeled and augmented to a total of 940 images. The results showed that YOLOv2 with DarkNet-53 achieved the best performance, with 98.8% mean average precision (mAP) and 97.9% F1-score (F1). SSD and Faster R-CNN also improved, reaching 63.1% and 52.8%, respectively. Modern models obtained strong results: YOLOv11 and YOLOv12 reached 96–97%, and RT-DETR 93.5%. The modification of YOLOv2 allowed this classical detector to compete directly with, and even surpass, recent models. Precision–recall (PR) curves, F1-scores, and complexity analysis confirmed the trade-offs between accuracy and efficiency. These findings demonstrate that while modern detectors are efficient baselines, classical models with updated backbones can still deliver state-of-the-art results for UAV-based crop monitoring. Full article

Feature selection is essential for enhancing classification accuracy, reducing overfitting, and improving interpretability in high-dimensional datasets. Evolutionary Feature Selection (EFS) methods employ a threshold parameter $\theta$ to decide feature inclusion, yet the widely used static setting $\theta =0.5$ may not yield optimal results. This paper presents the first large-scale, systematic evaluation of threshold adaptation mechanisms in wrapper-based EFS across a diverse number of benchmark datasets. We examine deterministic, adaptive, and self-adaptive threshold parameter control under a unified framework, which can be used in an arbitrary bio-inspired algorithm. Extensive experiments and statistical analyses of classification accuracy, feature subset size, and convergence properties demonstrate that adaptive mechanisms outperform the static threshold parameter control significantly. In particular, they not only provide superior tradeoffs between accuracy and subset size but also surpass the state-of-the-art feature selection methods on multiple benchmarks. Our findings highlight the critical role of threshold adaptation in EFS and establish practical guidelines for its effective application. Full article

Currently, the customs inspection of wood-boring pests in timber still primarily relies on manual visual inspection, which involves observing insect holes on the timber surface and splitting the timber for confirmation. However, this method has significant drawbacks such as long detection time, high labor cost, and accuracy relying on human experience, making it difficult to meet the practical needs of efficient and intelligent customs quarantine. To address this issue, this paper develops a rapid identification system based on the peristaltic signals of wood-boring pests through the PyQt framework. The system employs a deep learning model with multi-attention mechanisms, namely the Residual Denoising Vision Network (RDVNet). Firstly, a LabVIEW-based hardware–software system is used to collect pest peristaltic signals in an environment free of vibration interference. Subsequently, the original signals are clipped, converted to audio format, and mixed with external noise. Then signal features are extracted through three cepstral feature extraction methods Mel-Frequency Cepstral Coefficients (MFCC), Power-Normalized Cepstral Coefficients (PNCC), and RelAtive SpecTrAl-Perceptual Linear Prediction (RASTA-PLP) and input into the model. In the experimental stage, this paper compares the denoising module of RDVNet (de-RDVNet) with four classic denoising models under five noise intensity conditions. Finally, it evaluates the performance of RDVNet and four other noise reduction classification models in classification tasks. The results show that PNCC has the most comprehensive feature extraction capability. When PNCC is used as the model input, de-RDVNet achieves an average peak signal-to-noise ratio (PSNR) of 29.8 and a Structural Similarity Index Measure (SSIM) of 0.820 in denoising experiments, both being the best among the comparative models. In classification experiments, RDVNet has an average F1 score of 0.878 and an accuracy of 92.8%, demonstrating the most excellent performance. Overall, the application of this system in customs timber quarantine can effectively improve detection efficiency and reduce labor costs and has significant practical value and promotion prospects. Full article

This paper presents an automatic system for the classification of musical instruments from audio recordings. The project leverages deep learning (DL) techniques to achieve its objective, exploring three different classification approaches based on distinct input representations. The first method involves the extraction of Mel-Frequency Cepstral Coefficients (MFCCs) from the audio files, which are then fed into a two-dimensional convolutional neural network (Conv2D). The second approach makes use of mel-spectrogram images as input to a similar Conv2D architecture. The third approach employs conventional machine learning (ML) classifiers, including Logistic Regression, K-Nearest Neighbors, and Random Forest, trained on MFCC-derived feature vectors. To gain insight into the behavior of the DL model, explainability techniques were applied to the Conv2D model using mel-spectrograms, allowing for a better understanding of how the network interprets relevant features for classification. Additionally, t-distributed stochastic neighbor embedding (t-SNE) was employed on the MFCC vectors to visualize how instrument classes are organized in the feature space. One of the main challenges encountered was the class imbalance within the dataset, which was addressed by assigning class-specific weights during training. The results, in terms of classification accuracy, were very satisfactory across all approaches, with the convolutional models and Random Forest achieving around 97–98%, and Logistic Regression yielding slightly lower performance. In conclusion, the proposed methods proved effective for the selected dataset, and future work may focus on further improving class balance techniques. Full article

Spatial reasoning ability plays a critical role in predicting academic outcomes, particularly in STEM (science, technology, engineering, and mathematics) education. According to the Cattell–Horn–Carroll (CHC) theory of human intelligence, spatial reasoning is a general ability including various specific attributes. However, most spatial assessments focus on testing one specific spatial attribute or a limited set (e.g., visualization, rotation, etc.), rather than general spatial ability. To address this limitation, we created a mixed spatial test that includes mental rotation, object assembly, and isometric perception subtests to evaluate both general spatial ability and specific attributes. To understand the complex relationship between general spatial ability and mastery of specific attributes, we used a higher-order linear logistic model (HO-LLM), which is designed to simultaneously estimate high-order ability and sub-attributes. Additionally, this study compares four spatial ability classification frameworks using each to construct Q-matrices that define the relationships between test items and spatial reasoning attributes within the HO-LLM framework. Our findings indicate that HO-LLMs improve model fit and show distinct patterns of attribute mastery, highlighting which spatial attributes contribute most to general spatial ability. The results suggest that higher-order LLMs can offer a deeper and more interpretable assessment of spatial ability and support tailored training by identifying areas of strength and weakness in individual learners. Full article

In our study, we examine how the temporal window shift—the step between consecutive analysis windows—affects EEG-based cognitive fatigue detection while keeping the window length fixed. Using a reference workload dataset and a pipeline that includes preprocessing and feature extraction, we vary the shift to control segment overlap and, consequently, the number and independence of training samples. We evaluate six machine-learning models (decision tree, random forest, SVM, kNN, MLP, and a transformer). Across the models, smaller shifts generally increase accuracy and F1 score, consistent with the larger sample count; however, they also reduce sample independence and can inflate performance if evaluation splits are not sufficiently stringent. Class-wise analyses reveal persistent confusion for the moderate-fatigue class, the severity of which depends on the chosen shift. We discuss the methodological trade-offs, provide practical recommendations for choosing and reporting shift parameters, and argue that temporal segmentation decisions should be treated as first-class design choices in EEG classification. Our findings highlight the need for transparent reporting of window length, shift/overlap, and subject-wise evaluation protocols to ensure reliable and reproducible results in cognitive fatigue detection. Our conclusions pertain to subject-wise generalization on the STEW dataset; cross-dataset validation is an important next step. Full article

Background/Objectives: Breast cancer (BC) is the most commonly diagnosed cancer in women and the leading cause of cancer-related deaths globally. Molecular subtyping is crucial for prognosis and treatment planning, with immunohistochemistry (IHC) being the most commonly used method. However, IHC has limitations, including observer variability, a lack of standardization, and a lack of reproducibility. Gene expression profiling is considered the ground truth for molecular subtyping; unfortunately, this is expensive and inaccessible to many institutions. This study investigates the potential of an artificial intelligence (AI) model to predict BC molecular subtypes directly from hematoxylin and eosin (H&E)-stained whole-slide images (WSIs). Methods: A pretrained deep learning framework based on multiple-instance learning (MIL) was validated on the Stavanger Breast Cancer (SBC) dataset, consisting of 538 BC cases. Three classification tasks were assessed, including two-class [triple negative BC (TNBC) vs. non-TNBC], three-class (luminal vs. HER2-positive vs. TNBC), and four-class (luminal A vs. luminal B vs. HER2-positive vs. TNBC) groups. Performance metrics were used for the evaluation of the AI model. Results: The AI model demonstrated strong performance in distinguishing TNBC from non-TNBC (AUC = 0.823, accuracy = 0.833, F1-score = 0.824). However, performance declined with an increasing number of classes. Conclusions: The study highlights the potential of AI in BC molecular subtyping from H&E WSIs, offering an easily applicable and standardized method to IHC. Future improvements should focus on optimizing multi-class classification and validating AI-based methods against gene expression analyses for enhanced clinical applicability. Full article

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