Search Results (18,728)

This study applied modified linear regression in machine learning (ML) to predict the direction of arrival (DoA) in cellular networks using field measurements and radiofrequency parameters. Models were developed from base station data, with preprocessing for pattern identification and formula adjustments to improve the accuracy across angle ranges. Machine learning, tested here as an additional method to traditional techniques, achieved a root mean square error (RMSE) of 3.63 to 17.93, demonstrating enhanced adaptability. While requiring substantial data and computational resources, this approach highlights machine learning’s potential as a valuable tool for DoA estimation in cellular networks. Full article

Remote sensing image retrieval (RSIR) plays a crucial role in remote sensing applications, focusing on retrieving a collection of items that closely match a specified query image. Due to the advantages of low storage cost and fast search speed, deep hashing has been one of the most active research problems in remote sensing image retrieval. However, remote sensing images contain many content-irrelevant backgrounds or noises, and they often lack the ability to capture essential fine-grained features. In addition, existing hash learning often relies on random sampling or semi-hard negative mining strategies to form training batches, which could be overwhelmed by some redundant pairs that slow down the model convergence and compromise the retrieval performance. To solve these problems effectively, a novel Deep Multi-similarity Hashing with Spatial-enhanced Learning, termed DMsH-SL, is proposed to learn compact yet discriminative binary descriptors for remote sensing image retrieval. Specifically, to suppress interfering information and accurately localize the target location, by introducing a spatial enhancement learning mechanism, the spatial group-enhanced hierarchical network is firstly designed to learn the spatial distribution of different semantic sub-features, capturing the noise-robust semantic embedding representation. Furthermore, to fully explore the similarity relationships of data points in the embedding space, the multi-similarity loss is proposed to construct informative and representative training batches, which is based on pairwise mining and weighting to compute the self-similarity and relative similarity of the image pairs, effectively mitigating the effects of redundant and unbalanced pairs. Experimental results on three benchmark datasets validate the superior performance of our approach. Full article

One of the critical challenges in mobile robotics is obstacle avoidance, ensuring safe navigation in dynamic environments. In this sense, this work presents a comparative study of two intelligent control approaches for mobile robot obstacle avoidance based on a fuzzy architecture. The first approach is a neuro-fuzzy interface that combines neural networks’ learning capabilities with fuzzy logic’s rule-based reasoning, offering a flexible and adaptable control strategy. The second is a classic Mamdani fuzzy system that relies on human-defined fuzzy rules, providing an intuitive approach to control. A key contribution of this work is the development of a fast comprehensive, model-based dataset for neural network training generated without the need for real sensor data. The results show the evaluation of these two systems’ performance, robustness, and computational efficiency using low-cost ultrasonic sensors on a Pioneer 3DX robot within the Coppelia Sim environment. Full article

Due to the impact of climate change, the importance of urban flood analysis is increasing. One of the biggest challenges in urban flood simulations is the complexity of storm sewer networks, which significantly affects both computational time and accuracy. This study aimed to analyze and evaluate the impact of sewer network simplification on the accuracy and computational performance of urban flood prediction by comparing different rainfall runoff methods. Using the hyper-connected solution for urban flood (HC-SURF) model, two rainfall runoff methods, the SWMM Runoff method and the Surface Runoff method, were compared. The sewer network simplification was applied based on manhole catchment areas ranging from 10 m² to 10,000 m². The analysis showed that the computation time could be reduced by up to 54.5% through simplification, though some accuracy loss may occur depending on the chosen runoff method. Overall, both methods produced excellent results in terms of mass balance, but the SWMM Runoff method minimized the reduction in analytical performance due to simplification. This study provides important insights into balancing computational efficiency and model accuracy in urban flood analysis. Full article

As green energy technology develops, so too grows research interest in topics such as solar power forecasting. The output of solar power generation is uncontrollable, which makes accurate prediction of output an important task in the management of power grids. Despite a plethora of theoretical models, most frameworks encounter problems in practice because they assume that received data is error-free, which is unlikely, as this type of data is gathered by outdoor sensors. We thus designed a robust solar power forecasting model and methodology based on the concept of ensembling, with three key design elements. First, as models established using the ensembling concept typically have high computational costs, we pruned the deep learning model architecture to reduce the size of the model. Second, the mediation model often used for pruning is not suitable for solar power forecasting problems, so we designed a numerical–categorical radial basis function deep neural network (NC-RBF-DNN) to replace the mediation model. Third, existing pruning methods can only establish one model at a time, but the ensembling concept involves the establishment of multiple sub-models simultaneously. We therefore designed a factor combination search algorithm, which can identify the most suitable factor combinations for the sub-models of ensemble models using very few experiments, thereby ensuring that we can establish the target ensemble model with the smallest architecture and minimal error. Experiments using a dataset from real-world solar power plants verified that the proposed method could be used to build an ensemble model of the target within ten attempts. Furthermore, despite considerable error in the model inputs (two inputs contained 10% error), the predicted NRMSE of our model is still over 10 times better than the recent model. Full article

Ginseng is a common medicinal herb with high value due to its unique medicinal properties. Traditional methods for classifying ginseng rely heavily on manual judgment, which is time-consuming and subjective. In contrast, deep learning methods can objectively learn the features of ginseng, saving both labor and time. This experiment proposes a ginseng-grade classification model based on an improved ResNeXt50 model. First, each convolutional layer in the Bottleneck structure is replaced with the corresponding Ghost module, reducing the model’s computational complexity and parameter count without compromising performance. Second, the SE attention mechanism is added to the model, allowing it to capture feature information more accurately and precisely. Next, the ELU activation function replaces the original ReLU activation function. Then, the dataset is augmented and divided into four categories for model training. A model suitable for ginseng grade classification was obtained through experimentation. Compared with classic convolutional neural network models ResNet50, AlexNet, iResNet, and EfficientNet_v2_s, the accuracy improved by 10.22%, 5.92%, 4.63%, and 3.4%, respectively. The proposed model achieved the best results, with a validation accuracy of up to 93.14% and a loss value as low as 0.105. Experiments have shown that this method is effective in recognition and can be used for ginseng grade classification research. Full article

This article introduces the R package pspatreg, which is publicly available for download from the Comprehensive R Archive Network, for estimating semiparametric spatial econometric penalized spline (P-Spline) models. These models can incorporate a nonparametric spatiotemporal trend, a spatial lag of the dependent variable, independent variables, noise, and time-series autoregressive noise. The primary functions in this package cover the estimation of P-Spline spatial econometric models using either Restricted Maximum Likelihood (REML) or Maximum Likelihood (ML) methods, as well as the computation of marginal impacts for both parametric and nonparametric terms. Additionally, the package offers methods for the graphical display of estimated nonlinear functions and spatial or spatiotemporal trend maps. Applications to cross-sectional and panel spatial data are provided to illustrate the package’s functionality. Full article

There are two crucial resources (i.e., labor and equipment) of productivity in the construction industry. Productivity modeling of these resources would aid stakeholders in project management and improve construction scheduling and monitoring. Hence, this research aims to review machine learning (ML) applications in the process of construction productivity modeling (CPM) for construction labor productivity (CLP) and construction equipment productivity (CEP) from dataset acquisition to data analysis and evaluation, which includes their trends and applicability. An extensive analysis of 131 journals focused on the application of machine learning in construction productivity (ML-CP) from 1990 to 2024 via a mixed review methodology (bibliometric analysis and systematic review) was conducted. It can be concluded that despite the rise in automated dataset collection, the traditional method has its advantages. The review further found that the selection of ML models relies on each particular application, available data, and computational resources. Noticeably, artificial neural networks, convolutional neural networks, support vector machines, and even deep learning demonstrating have been adopted due to their effectiveness in different functionalities and processes in CPM. This study will supplement the insights gained in the review with a comprehensive understanding of how ML applications operate at each stage of CPM, enabling researchers to make future improvements. Full article

Background/Objectives: Periodontitis is a common oral disease marked by gingival inflammation and alveolar bone loss. This study evaluated the efficacy of chamomile tincture and lidocaine hydrochloride (CLH) gel in mitigating periodontal inflammation and bone loss and uncovered the molecular mechanisms involved, both in vitro and in vivo. Methods: A periodontitis model was induced in Sprague Dawley rats by ligating the mandibular first molars. Sixty rats were divided into four groups: control (C), periodontitis (PD), periodontitis + CLH gel once daily (G1), and periodontitis + CLH gel thrice daily (G3). Clinical, micro-computed tomography (micro-CT), biological, and histological evaluations were performed, focusing on osteoclastogenesis, osteogenesis, and inflammatory cytokine production. The effect of CLH gel on inflammatory responses in RAW264.7 cells was also assessed through co-culture assays under Porphyromonas gingivalis (P. gingivalis) infection, with RNA-sequencing, qPCR, and Western blot analyses to explore underlying mechanisms. Results: CLH gel significantly reduced gingival and systemic inflammation and mitigated bone loss by enhancing the bone volume to tissue volume ratio and trabecular thickness via the RANKL/OPG axis in rats. The G3 group showed marked reductions in osteoclasts and increases in osterix-positive cells compared to other groups. In vitro, CLH gel reduced the inflammatory phenotype of macrophages in the periodontitis microenvironment by modulating Type II interferon (IFN-γ) networks. Conclusions: CLH gel reduced inflammation and bone loss in rat periodontitis, promoting osteogenesis and inhibiting osteoclastogenesis. It also suppressed macrophage inflammation via Type II interferon networks under P. gingivalis stimulation. These findings suggest that CLH gel has potential as an adjunctive therapy for periodontitis. Full article

Cavitation is a common phenomenon in naval and ocean engineering, typically occurring in the wakes of high-speed rotating propellers and on the surfaces of fast-moving underwater vehicles. To investigate cavitation phenomena, computational fluid dynamics (CFD) simulations are indispensable. Nevertheless, the inherently complex nature of cavitation, which involves phase transitions, heat transfer, and significant pressure fluctuations, often results in high computational costs for these simulations. To address the computational challenges associated with cavitation simulations, a DeepCFD model, which leverages convolutional neural networks (CNNs), was employed to accurately predict cavitation around hydrofoils. Through specific modifications, the DeepCFD model was trained on 400 hydrofoil configurations, learned from CFD simulations. The numerical methods were validated against a modified NACA66 hydrofoil. It was found that the model could accurately predict cavitation shapes under various flow conditions, although it showed some discrepancies in velocity predictions, especially for detached cavitating flows. The significance of this study lies in its potential to simply predict cavitating flows and expedite marine vehicle design through the application of CNNs in cavitation prediction, offering a novel and impactful approach to computational fluid dynamics in the field. Full article

Visual object tracking is a fundamental task in computer vision, with applications ranging from video surveillance to autonomous driving. Despite recent advances in transformer-based one-stream trackers, unrestricted feature interactions between the template and the search region often introduce background noise into the template, degrading the tracking performance. To address this issue, we propose FETrack, a feature-enhanced transformer-based network for visual object tracking. Specifically, we incorporate an independent template stream in the encoder of the one-stream tracker to acquire the high-quality template features while suppressing the harmful background noise effectively. Then, we employ a sequence-learning-based causal transformer in the decoder to generate the bounding box autoregressively, simplifying the prediction head network. Further, we present a dynamic threshold-based online template-updating strategy and a template-filtering approach to boost tracking robustness and reduce redundant computations. Extensive experiments demonstrate that our FETrack achieves a superior performance over state-of-the-art trackers. Specifically, the proposed FETrack achieves a 75.1% AO on GOT-10k, 81.2% AUC on LaSOT, and 89.3% Pnorm on TrackingNet. Full article

Large-scale mapping of soil resources can be crucial and indispensable for several of the managerial applications and policy implications. With machine learning models being the most utilized modeling technique for digital soil mapping (DSM), the implementation of model-based deep learning methods for spatial soil predictions is still under scrutiny. In this study, soil continuous (pH and OC) and categorical variables (order and suborder) were predicted using deep learning–multi layer perceptron (DL-MLP) and one-dimensional convolutional neural networks (1D-CNN) for the entire state of Tamil Nadu, India. For training the deep learning models, 27,098 profile observations (0–30 cm) were extracted from the generated soil database, considering soil series as the distinctive stratum. A total of 43 SCORPAN-based environmental covariates were considered, of which 37 covariates were retained after the recursive feature elimination (RFE) process. The validation and test results obtained for each of the soil attributes for both the algorithms were most comparable with the DL-MLP algorithm depicting the attributes’ most intricate spatial organization details, compared to the 1D-CNN model. Irrespective of the algorithms and datasets, the R² and RMSE values of the pH attribute ranged from 0.15 to 0.30 and 0.97 to 1.15, respectively. Similarly, the R² and RMSE of the OC attribute ranged from 0.20 to 0.39 and 0.38 to 0.42, respectively. Further, the overall accuracy (OA) of the order and suborder classification ranged from 39% to 67% and 35% to 64%, respectively. The explicit quantification of the covariate importance derived from the permutation feature importance implied that both the models tried to incorporate the covariate importance with respect to the genesis of the soil attribute under study. Such approaches of the deep learning models integrating soil–environmental relationships under limited parameterization and computing costs can serve as a baseline study, emphasizing opportunities in increasing the transferability and generalizability of the model while accounting for the associated environmental dependencies. Full article

Deep neural networks (DNNs) have achieved great success in various computer vision tasks. However, they are susceptible to artificially designed adversarial perturbations, which limit their deployment in security-critical applications. In this paper, we propose a gradual adversarial training (GAT) method for remote sensing image segmentation. Our method incorporates a domain-adaptive mechanism that dynamically modulates input data, effectively reducing adversarial perturbations. GAT not only improves segmentation accuracy on clean images but also significantly enhances robustness against adversarial attacks, all without necessitating changes to the network architecture. The experimental results demonstrate that GAT consistently outperforms conventional standard adversarial training (SAT), showing increased resilience to adversarial attacks of varying intensities on both optical and Synthetic Aperture Radar (SAR) images. Compared to the SAT defense method, GAT achieves a notable defense performance improvement of 1% to 12%. Full article

Individual physiotherapy is crucial in treating patients with various pain and health issues, and significantly impacts abdominal surgical outcomes and further medical problems. Recent technological and artificial intelligent advancements have equipped healthcare professionals with innovative tools, such as sensor systems and telemedicine equipment, offering groundbreaking opportunities to monitor and analyze patients’ physical activity. This paper investigates the potential applications of mobile accelerometers in evaluating the symmetry of specific rehabilitation exercises using a dataset of 1280 tests on 16 individuals in the age range between 8 and 75 years. A comprehensive computational methodology is introduced, incorporating traditional digital signal processing, feature extraction in both time and transform domains, and advanced classification techniques. The study employs a range of machine learning methods, including support vector machines, Bayesian analysis, and neural networks, to evaluate the balance of various physical activities. The proposed approach achieved a high classification accuracy of 90.6% in distinguishing between left- and right-side motion patterns by employing features from both the time and frequency domains using a two-layer neural network. These findings demonstrate promising applications of precise monitoring of rehabilitation exercises to increase the probability of successful surgical recovery, highlighting the potential to significantly enhance patient care and treatment outcomes. Full article

Routine visual inspection is fundamental to the preventive maintenance of power equipment. Convolutional neural networks (CNNs) substantially reduce the number of parameters and efficiently extract image features for classification tasks. In the actual production and operation process of substations, due to the limitation of safety distance, camera monitoring, inspection robots, etc., cannot be very close to the target. The operational environment of power equipment leads to scale variations in the main target and thus compromises the performance of conventional models. To address the challenges posed by scale fluctuations in power equipment image datasets, while adhering to the requirements for model efficiency and enhanced inter-channel communication, this paper proposed the ResNet Cross-Layer Parameter Sharing (ResNetCPS) framework. The core idea is that the network output should remain consistent for the same object at different scales. The proposed framework facilitates weight sharing across different layers within the convolutional network, establishing connections between pertinent channels across layers and leveraging the scale invariance inherent in image datasets. Additionally, for substation image processing mainly based on edge devices, smaller models must be used to reduce the expenditure of computing power. The Cross-Layer Parameter Sharing framework not only reduces the overall number of model parameters but also decreases training time. To further enhance the representation of critical features while suppressing less important or redundant ones, an Inserting and Adjacency Attention (IAA) module is designed. This mechanism improves the model’s overall performance by dynamically adjusting the importance of different channels. Experimental results demonstrate that the proposed method significantly enhances network efficiency, reduces the total parameter storage space, and improves training efficiency without sacrificing accuracy. Specifically, models incorporating the Cross-Layer Parameter Sharing module achieved a reduction in the number of parameters and model size by 10% to 30% compared to the baseline models. Full article