Search Results (99)

Hybrid metaheuristic algorithms have been widely used to solve global optimization problems, making the concept of hybridization increasingly important. This study proposes a new hybrid multi-strategy metaheuristic algorithm named COSGO, which combines the strengths of grey wolf optimization (GWO) and Sand Cat Swarm Optimization (SCSO) to effectively address global optimization tasks. Additionally, a chaotic opposition-based learning strategy is incorporated to enhance the efficiency and global search capability of the algorithm. One of the main challenges in metaheuristic algorithms is premature convergence or getting trapped in local optima. To overcome this, the proposed strategy is designed to improve exploration and help the algorithm escape local minima. As a real-world application, multi-level thresholding for color image segmentation—a well-known problem in image processing—is studied. The COSGO algorithm is applied using two objective functions, Otsu’s method and Kapur’s entropy, to determine optimal multi-level thresholds. Experiments are conducted on 10 images from the widely used BSD500 dataset. The results show that the COSGO algorithm achieves competitive performance compared to other State-of-the-Art algorithms. To further evaluate its effectiveness, the CEC2017 benchmark functions are employed, and a Friedman ranking test is used to statistically analyze the results. Full article

This paper proposes an integrated tree model architecture and a low-cost data construction method based on an improved Stacking strategy. It systematically analyzes the importance of safety indicators for mountainous sharp bends in plateau regions and conducts safety evaluation and optimization-strategy research for ten typical sharp-bend road segments in Tibet. In response to the challenges of traditional data collection in Tibet’s unique geographical and policy constraints, we innovatively use drone aerial video as the data source, integrating Tracker motion trajectory analysis, SegFormer road segmentation, and CAD annotation techniques to construct a dataset covering multi-dimensional features of “human–vehicle–road–environment” for mountainous plateau sharp-bend highways. Compared with similar studies, the cost of this dataset is significantly lower. Based on the strong interpretability of tree models and the excellent generalization ability of ensemble learning, we propose an improved Stacking strategy tree model structure to interpret the importance of each indicator. The Spearman correlation coefficient and TOPSIS algorithm are used to conduct safety evaluation for ten sharp-bend roads in Tibet. The results show that the output of the improved Stacking strategy and the sensitivity analysis of the three tree models indicate that curvature variation rate and acceleration are the most significant factors influencing safety, while speed and road width are secondary factors. The study also provides a safety ranking for the ten selected sharp-bend roads, offering a reference for the 318 Quality Improvement Project. From the perspective of indicator importance, curvature variation rate, acceleration, vehicle speed, and road width are crucial for the safety of mountainous plateau sharp-bend roads. It is recommended to implement speed limits for vehicles and widen the road-bend radius. The technical framework constructed in this study provides a reusable methodology for safety assessment of high-altitude roads in complex terrains. Full article

Artificial intelligence-based biomedical image processing has become an important area of research in recent decades. In this context, one of the most important problems encountered is the close contrast values between the pixels to be segmented in the image and the remaining pixels. Among the crucial advantages provided by metaheuristic algorithms, they are generally able to provide better performances in the segmentation of biomedical images due to their randomized and gradient-free global search abilities. Math-inspired metaheuristic algorithms can be considered to be one of the most robust groups of algorithms, while also generally presenting non-complex structures. In this work, the recently proposed Circle Search Algorithm (CSA), Tangent Search Algorithm (TSA), Arithmetic Optimization Algorithm (AOA), Generalized Normal Distribution Optimization (GNDO), Global Optimization Method based on Clustering and Parabolic Approximation (GOBC-PA), and Sine Cosine Algorithm (SCA) were implemented for clustering and then applied to the retinal vessel segmentation task on retinal images from the DRIVE and STARE databases. Firstly, the segmentation results of each algorithm were obtained and compared with each other. Then, to compare the statistical performances of the algorithms, analyses were carried out in terms of sensitivity (Se), specificity (Sp), accuracy (Acc), standard deviation, and the Wilcoxon rank-sum test results. Finally, detailed convergence analyses were also carried out in terms of the convergence speed, mean squared error (MSE), CPU time, and number of function evaluations (NFEs) metrics. Full article

The present study investigates consumer preferences for eco-friendly practices implemented by outdoor sport brands, identifying which practices are perceived as most significant among the overall consumer group and within consumer segments differentiated by ecological consciousness. This study targeted consumers who had purchased outdoor sport brand products within the past one to two years. The results indicated that overall consumers regarded ‘Materials usage’, particularly ‘100% organic materials’, as the most critical eco-friendly attribute. The second most significant attribute identified was the ‘Type of campaign’, specifically ‘Consumer behavioral engagement campaigns’. ‘Carbon footprint reduction’, notably ‘Reducing 50% by 2030’, ranked third, while ‘Implementation of donations’ was considered the least important. Segment-specific analysis revealed that high-ecological-conscious consumers prioritized carbon footprint reduction more than other groups. Furthermore, the optimal combination of eco-friendly practices identified for overall and low-ecological-consciousness consumers consisted of using 100% organic materials, implementing consumer behavioral engagement campaigns, reducing carbon footprint by 50%, and actively participating in environmental conservation donations. Highly ecological-conscious consumers preferred a slightly adjusted combination, emphasizing 100% organic materials, followed by reducing carbon footprint by 50%, implementing consumer behavioral engagement campaigns, and actively participating in environmental conservation donations. These findings suggest that outdoor sport brands can strengthen their competitive advantage and sustainability by aligning eco-friendly practices with consumer preferences segmented by ecological consciousness. Full article

The fusion of infrared and visible images provides complementary information from both modalities and has been widely used in surveillance, military, and other fields. However, most of the available fusion methods have only been evaluated with subjective metrics of visual quality of the fused images, which are often independent of the following relevant high-level visual tasks. Moreover, as a useful technique especially used in low-light scenarios, the effect of low-light conditions on the fusion result has not been well-addressed yet. To address these challenges, a decoupled and semantic segmentation-driven infrared and visible image fusion network is proposed in this paper, which connects both image fusion and the downstream task to drive the network to be optimized. Firstly, a cross-modality transformer fusion module is designed to learn rich hierarchical feature representations. Secondly, a semantic-driven fusion module is developed to enhance the key features of prominent targets. Thirdly, a weighted fusion strategy is adopted to automatically adjust the fusion weights of different modality features. This effectively merges the thermal characteristics from infrared images and detailed information from visible images. Additionally, we design a refined loss function that employs the decoupling network to constrain the pixel distributions in the fused images and produce more-natural fusion images. To evaluate the robustness and generalization of the proposed method in practical challenge applications, a Maritime Infrared and Visible (MIV) dataset is created and verified for maritime environmental perception, which will be made available soon. The experimental results from both widely used public datasets and the practically collected MIV dataset highlight the notable strengths of the proposed method with the best-ranking quality metrics among its counterparts. Of more importance, the fusion image achieved with the proposed method has over 96% target detection accuracy and a dominant high mAP@[50:95] value that far surpasses all the competitors. Full article

Accurate and efficient white-spot defects detection for the surface of galvanized strip steel is one of the most important guarantees for the quality of steel production. It is a fundamental but “hard” small target detection problem due to its small pixel occupation in low-contrast images. By fully exploiting the low-rank and sparse prior information of a surface defect image, a Schatten-p norm-based low-rank tensor decomposition (SLRTD) method is proposed to decompose the defect image into low-rank background, sparse defect, and random noise. Firstly, the original defect images are transformed into a new patch-based tensor mode through data reconstruction for mining valuable information of the defect image. Then, considering the over-shrinkage problem in the low-rank component estimation caused by a vanilla nuclear norm and a weighted nuclear norm, a nonlinear reweighting strategy based on a Schatten $p$-norm is incorporated to improve the decomposition performance. Finally, a solution framework is proposed via a well-designed alternating direction method of multipliers to obtain the white-spot defect target image by a simple segmenting algorithm. The white-spot defect dataset from a real-world galvanized strip steel production line is constructed, and the experimental results demonstrate that the proposed SLRTD method outperforms existing state-of-the-art methods qualitatively and quantitatively. Full article

The study aims to identify key attributes driving yacht tourism and analyze their relative importance using conjoint analysis. This method quantifies attribute importance and utility values to evaluate their impact on consumer choices and optimize market segmentation strategies through attribute combination simulations. The research was conducted with a sample of 484 yacht tourists at yacht marinas, focusing on four key attributes: program, safety, service, and accessibility. The analysis revealed that yacht sailing programs were considered the most important attribute overall. However, preferences varied significantly depending on prior experience. Experienced yacht tourists ranked the attributes in the following order of importance: program, safety, service, and accessibility. In contrast, inexperienced tourists prioritized safety above all, followed by program, service, and accessibility. The study identified that all tourist groups preferred the same optimal combination: “a yacht sailing experience program that provides safety education and equipment, operates a tourism information platform, and is accessible within one hour by public transportation from the city center”. Although this optimal combination was consistent across groups, the utility values differed, with experienced yacht tourists exhibiting the highest values, followed by inexperienced tourists and overall tourists. The findings highlight the importance of prioritizing both sailing programs and safety measures in yacht tourism development, while also considering tourists’ experience levels. These insights provide practical implications for the development of targeted promotion strategies. Full article

Deep learning models possess the ability to precisely analyze medical images such as MRI, CT scans, and ultrasound images. This automated diagnostic process facilitates the early detection of kidney disease by identifying any abnormalities or signs of disease. Consequently, it allows for timely intervention and treatment, while also reducing the need for manual interpretation by radiologists or clinicians. As a result, the diagnosis process is expedited, leading to improved efficiency in healthcare. The proposed technique focuses on enhancing parallel convolutional layer architectures in kidney disease segmentation through the utilization of advanced optimization techniques. This approach integrates Firefly Sigma Seeker and MagWeight Rank methodologies into the design of these architectures. The Firefly Sigma Seeker methodology dynamically adjusts key parameters related to standard deviation during training to enable early stopping in the initial phase. Subsequently, MagWeight Rank optimizes parameter weighting and ranking within the architecture to prune less important weights, thereby reducing computational time and overfitting. By leveraging these techniques, the parallel convolutional layers are specifically tailored for kidney disease segmentation tasks. Finally, the Multi-Stream Neural Network (MSNN) efficiently classifies kidney disease. Through extensive experimentation and evaluation on kidney disease segmentation datasets, a comparative analysis of different architectures was conducted in terms of segmentation accuracy, computational efficiency, and scalability. The proposed framework achieves optimal segmentation performance, with an accuracy of 98.2%, a minimized loss of 0.1, a reduced computational time of 15 min and 4 s, and successfully avoids overfitting. Full article

Traffic network resilience refers to the ability of a traffic network to maintain a certain capacity and service level even when disturbed by external factors, as well as its capacity to recover following a disruptive event. This paper integrates traffic simulation with resilience analysis of urban road traffic networks and proposes a framework for identifying critical roads in urban road traffic networks from a resilience perspective. This framework is both theoretical and applicable to any unanticipated disruptive event. By incorporating four attribute indicators—traffic, topology, urban function, and socio-economic factors—the framework assesses the importance ranking of each road segment in an urban road traffic network both before and after an unanticipated disruptive event. A case study is conducted using a real urban road traffic network in Shanghai. From the perspective of policymakers, corresponding policy recommendations are made to enhance the resilience of urban road traffic networks against unanticipated disruptive events and to mitigate socio-economic losses. Full article

Given an untrimmed video and a natural language query, the video temporal grounding task aims to accurately locate the target segment within the video. Functioning as a critical conduit between computer vision and natural language processing, this task holds profound importance in advancing video comprehension. Current research predominantly centers on enhancing the performance of individual models, thereby overlooking the extensive possibilities afforded by multi-model synergy. While knowledge flow methods have been adopted for multi-model and cross-modal collaborative learning, several critical concerns persist, including the unidirectional transfer of knowledge, low-quality pseudo-label generation, and gradient conflicts inherent in cooperative training. To address these issues, this research proposes a Multi-Model Collaborative Learning (MMCL) framework. By incorporating a bidirectional knowledge transfer paradigm, the MMCL framework empowers models to engage in collaborative learning through the interchange of pseudo-labels. Concurrently, the mechanism for generating pseudo-labels is optimized using the CLIP model’s prior knowledge, bolstering both the accuracy and coherence of these labels while efficiently discarding extraneous temporal fragments. The framework also integrates an iterative training algorithm for multi-model collaboration, mitigating gradient conflicts through alternate optimization and achieving a dynamic balance between collaborative and independent learning. Empirical evaluations across multiple benchmark datasets indicate that the MMCL framework markedly elevates the performance of video temporal grounding models, exceeding existing state-of-the-art approaches in terms of mIoU and Rank@1. Concurrently, the framework accommodates both homogeneous and heterogeneous model configurations, demonstrating its broad versatility and adaptability. This investigation furnishes an effective avenue for multi-model collaborative learning in video temporal grounding, bolstering efficient knowledge dissemination and charting novel pathways in the domain of video comprehension. Full article

The Indian Ocean Rim (IOR) is a crucial hub for global commerce, possessing key maritime corridors and competitive markets for China and the United States. Assessing the evolving positions of China and the United States in regional trade provides critical insights into their economic competition. This study quantitatively investigated their changing positions in the IOR trade networks from 1992 to 2020 through an interdisciplinary approach combining the Fisher optimal segmentation, chord-diagram visualization, and five weighted centrality indicators, including two advanced metrics derived from physical current flow theory. The results reveal a significant shift in their trade positions in the IOR trade networks across four phases (1992–2002, 2003–2008, 2009–2014, and 2015–2020); in particular, the United States occupied a dominant position in the IOR trade networks until 2008, after which China rose to the central trading position, as reflected in its top ranking across four weighted indicators (excluding weighted authority centrality). In machinery and transport equipment (SITC7), China also surpassed the United States in 2008 and further consolidated its supremacy, driven by its strong manufacturing capabilities and the growing demand from the IOR countries. Meanwhile, the United States experienced a noticeable decline but maintained substantial influence as a key importer. This research develops a quantitative framework that integrates the temporal segmentation with weighted centrality indicators to provide insights into the dynamics and structural changes of trade networks across sectors and regions. Full article

There are numerous applications for building dimension data, including building performance simulation and urban heat island investigations. In this context, object detection and instance segmentation methods—based on deep learning—are often used with Street View Images (SVIs) to estimate building dimensions. However, these methods typically depend on large and diverse datasets. Image augmentation can artificially boost dataset diversity, yet its role in building dimension estimation from SVIs remains under-studied. This research presents a methodology that applies eight distinct augmentation techniques—brightness, contrast, perspective, rotation, scale, shearing, translation augmentation, and a combined “sum of all” approach—to train models in two tasks: object detection with Faster Region-Based Convolutional Neural Networks (Faster R-CNNs) and instance segmentation with You Only Look Once (YOLO)v10. Comparing the performance with and without augmentation revealed that contrast augmentation consistently provided the greatest improvement in both bounding-box detection and instance segmentation. Using all augmentations at once rarely outperformed the single most effective method, and sometimes degraded the accuracy; shearing augmentation ranked as the second-best approach. Notably, the validation and test findings were closely aligned. These results, alongside the potential applications and the method’s current limitations, underscore the importance of carefully selected augmentations for reliable building dimension estimation. Full article

The aboveground biomass (AGB) of individual trees is a critical indicator for assessing urban forest productivity and carbon storage. In the context of global warming, it plays a pivotal role in understanding urban forest carbon sequestration and regulating the global carbon cycle. Recent advances in light detection and ranging (LiDAR) have enabled the detailed characterization of three-dimensional (3D) structures, significantly enhancing the accuracy of individual tree AGB estimation. This review examines studies that use LiDAR-derived 3D structural metrics to model and estimate individual tree AGB, identifying key metrics that influence estimation accuracy. A bibliometric analysis of 795 relevant articles from the Web of Science Core Collection was conducted using R Studio (version 4.4.1) and VOSviewer 1.6.20 software, followed by an in-depth review of 80 papers focused on urban forests, published after 2010 and selected from the first and second quartiles of the Chinese Academy of Sciences journal ranking. The results show the following: (1) Dalponte2016 and watershed are more widely used among 2D raster-based algorithms, and 3D point cloud-based segmentation algorithms offer greater potential for innovation; (2) tree height and crown volume are important 3D structural metrics for individual tree AGB estimation, and biomass indices that integrate these parameters can further improve accuracy and applicability; (3) machine learning algorithms such as Random Forest and deep learning consistently outperform parametric methods, delivering stable AGB estimates; (4) LiDAR data sources, point cloud density, and forest types are important factors that significantly affect the accuracy of individual tree AGB estimation. Future research should emphasize deep learning applications for improving point cloud segmentation and 3D structure extraction accuracy in complex forest environments. Additionally, optimizing multi-sensor data fusion strategies to address data matching and resolution differences will be crucial for developing more accurate and widely applicable AGB estimation models. Full article

Resilience against extreme rainfall and its induced flooding is critical for a truck freight system during extreme events and post-event recovery. This study presents a two-step modeling framework that integrates a flood simulation model and a freight demand model to quantify the resilience of the truck freight system against extreme rainfall events. In the initial step, using rainfall data from meteorological stations, the catchment-based macro-scale floodplain (CaMa-Flood) model was introduced to simulate the rainfall event and its impacts on each road segment’s capacity within the study region. Then, a regional truck freight demand model was built using vehicle trajectory data from heavy-duty trucks operating during the study period to simulate the travel time changes for each affected road segment as a metric to analyze their importance to both functional and topological resilience of the truck freight system. These road segments were ranked based on the travel time increases, with the segment showing the greatest increase ranked as the most critical. To validate the proposed method, an extreme rainfall event in Beijing, Tianjin, and Hebei in July 2023 was modeled. The proposed method can be used to identify key infrastructure improvements to minimize disruptions to the truck freight system, providing decision support for climate-resilient transportation planning essential for achieving UN Sustainable Development Goals (SDG 9 on resilient infrastructure and SDG 13 on climate action). Full article

With the rapid development of large model technology, data storage as well as collection is very important to improve the accuracy of model training, and Feature Selection (FS) methods can greatly eliminate redundant features in the data warehouse and improve the interpretability of the model, which makes it particularly important in the field of large model training. In order to better reduce redundant features in data warehouses, this paper proposes an enhanced Secretarial Bird Optimization Algorithm (SBOA), called BSFSBOA, by combining three learning strategies. First, for the problem of insufficient algorithmic population diversity in SBOA, the best-rand exploration strategy is proposed, which utilizes the randomness and optimality of random individuals as well as optimal individuals to effectively improve the population diversity of the algorithm. Second, to address the imbalance in the exploration/exploitation phase of SBOA, the segmented balance strategy is proposed to improve the balance by segmenting the individuals in the population, targeting individuals of different natures with different degrees of exploration and exploitation performance, and improving the quality of the FS subset when the algorithm is solved. Finally, for the problem of insufficient exploitation performance of SBOA, a four-role exploitation strategy is proposed, which strengthens the effective exploitation ability of the algorithm and enhances the classification accuracy of the FS subset by different degrees of guidance through the four natures of individuals in the population. Subsequently, the proposed BSFSBOA-based FS method is applied to solve 36 FS problems involving low, medium, and high dimensions, and the experimental results show that, compared to SBOA, BSFSBOA improves the performance of classification accuracy by more than 60%, also ranks first in feature subset size, obtains the least runtime, and confirms that the BSFSBOA-based FS method is a robust FS method with efficient solution performance, high stability, and high practicality. Full article