Search Results (6,238)

In this paper a new state model is introduced, an adaptative state model in a binary temporal representation (ASMBRT) as well as its application in constructing an algorithmic trading system. The presented model uses the binary temporal representation, which allows for a precise analysis of exchange rates without losing any informative value of the data. The basis of the model is the trajectory analysis for the ensuing changes in price quotations and dependencies between the duration of each change. The main advantage of the model is to eliminate the threshold analysis, used in existing state models. This solution allows for a more accurate identification of investor behavior patterns, which translates into a reduction of investment risk. In order to verify obtained results in practice, the paper presents a concept of creating an algorithmic trading system and an analysis of its financial effectiveness for the exchange rate most popular among investors, namely EUR/USD. Full article

Skeleton-based action recognition is an important subject in deep learning. Graph Convolutional Networks (GCNs) have demonstrated strong performance by modeling the human skeleton as a natural topological graph, representing the connections between joints. However, most existing methods rely on non-adaptive topologies or insufficiently expressive representations. To address these limitations, we propose a Multi-view Topology Refinement Graph Convolutional Network (MTR-GCN), which is efficient, lightweight, and delivers high performance. Specifically: (1) We propose a new spatial topology modeling approach that incorporates two views. A dynamic view fuses joint information from dual streams in a pairwise manner, while a static view encodes the shortest static paths between joints, preserving the original connectivity relationships. (2) We propose a new MultiScale Temporal Convolutional Network (MSTC), which is efficient and lightweight. (3) Furthermore, we introduce a new temporal topology strategy by modeling temporal frames as a graph, which strengthens the extraction of temporal features. By modeling the human skeleton as both a spatial and a temporal graph, we reveal a topological symmetry between space and time within the unified spatio-temporal framework. The proposed model achieves state-of-the-art performance on several benchmark datasets, including NTU RGB + D (XSub: 92.8%, XView: 96.8%), NTU RGB + D 120 (XSub: 89.6%, XSet: 90.8%), and NW-UCLA (95.7%), demonstrating the effectiveness of our GCN module, TCN module, and overall architecture. Full article

Adverse drug events (ADEs) significantly impact patient safety and health outcomes. Manual ADE detection from clinical narratives is time-consuming, labor-intensive, and costly. Recent advancements in large language models (LLMs), including transformer-based architectures such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pretrained Transformer (GPT) series, offer promising methods for automating ADE extraction from clinical data. These models have been applied to various aspects of pharmacovigilance and clinical decision support, demonstrating potential in extracting ADE-related information from real-world clinical data. Additionally, chatbot-assisted systems have been explored as tools in clinical management, aiding in medication adherence, patient engagement, and symptom monitoring. This narrative review synthesizes the current state of LLMs in ADE detection from a clinical perspective, organizing studies into categories such as human-facing decision support tools, immune-related ADE detection, cancer-related and non-cancer-related ADE surveillance, and personalized decision support systems. In total, 39 articles were included in this review. Across domains, LLM-driven methods have demonstrated promising performances, often outperforming traditional approaches. However, critical limitations persist, such as domain-specific variability in model performance, interpretability challenges, data quality and privacy concerns, and infrastructure requirements. By addressing these challenges, LLM-based ADE detection could enhance pharmacovigilance practices, improve patient safety outcomes, and optimize clinical workflows. Full article

Semantic segmentation is one of the key tasks in the intelligent interpretation of remote sensing images with extensive potential applications. However, when ultra-high resolution (UHR) remote sensing images exhibit complex background intersections and significant variations in object sizes, existing multimodal fusion segmentation methods based on convolutional neural networks and Transformers face challenges such as limited receptive fields and high secondary complexity, leading to inadequate global context modeling and multimodal feature representation. Moreover, the lack of accurate boundary detail feature constraints in the final segmentation further limits segmentation accuracy. To address these challenges, we propose a novel boundary-enhanced multilevel multimodal fusion Mamba-Large Strip Convolution network (FMLSNet) for remote sensing image segmentation, which offers the advantages of a global receptive field and efficient linear complexity. Specifically, this paper introduces a new multistage Mamba multimodal fusion framework (FMB) for UHR remote sensing image segmentation. By employing an innovative multimodal scanning mechanism integrated with disentanglement strategies to deepen the fusion process, FMB promotes deep fusion of multimodal features and captures cross-modal contextual information at multiple levels, enabling robust and comprehensive feature integration with enriched global semantic context. Additionally, we propose a Large Strip Spatial Detail (LSSD) extraction module, which adaptively combines multi-directional large strip convolutions to capture more precise and fine-grained boundary features. This enables the network to learn detailed spatial features from shallow layers. A large number of experimental results on challenging remote sensing image datasets show that our method exhibits superior performance over state-of-the-art models. Full article

Unsupervised feature selection aims to characterize the cluster structure of original features and select the optimal subset without label guidance. However, existing methods overlook fuzzy information in the data, failing to model cluster structures between data effectively, and rely on squared error for data reconstruction, exacerbating noise impact. Therefore, a robust unsupervised feature selection algorithm based on fuzzy anchor graphs (FWFGFS) is proposed. To address the inaccuracies in neighbor assignments, a fuzzy anchor graph learning mechanism is designed. This mechanism models the association between nodes and clusters using fuzzy membership distributions, effectively capturing potential fuzzy neighborhood relationships between nodes and avoiding rigid assignments to specific clusters. This soft cluster assignment mechanism improves clustering accuracy and the robustness of the graph structure while maintaining low computational costs. Additionally, to mitigate the interference of noise in the feature selection process, an adaptive fuzzy weighting mechanism is presented. This mechanism assigns different weights to features based on their contribution to the error, thereby reducing errors caused by redundant features and noise. Orthogonal tri-factorization is applied to the low-dimensional representation matrix. This guarantees that each center represents only one class of features, resulting in more independent cluster centers. Experimental results on 12 public datasets show that FWFGFS improves the average clustering accuracy by 5.68% to 13.79% compared with the state-of-the-art methods. Full article

With the popularization of social media, information related to public health events has seen explosive growth online, making it essential to accurately identify informative tweets with decision-making and management value for public health emergency response and risk monitoring. However, existing methods often suffer performance degradation during cross-event transfer due to differences in data distribution, and research specifically targeting public health events remains limited. To address this, we propose the Label Confusion Domain Adversarial Network (LCDAN), which innovatively integrates label confusion with domain adaptation to enhance the detection of informative tweets across different public health events. First, LCDAN employs an adversarial domain adaptation model to learn cross-domain feature representation. Second, it dynamically evaluates the importance of different source domain samples to the target domain through label confusion to optimize the migration effect. Experiments were conducted on datasets related to COVID-19, Ebola disease, and Middle East Respiratory Syndrome public health events. The results demonstrate that LCDAN significantly outperforms existing methods across all tasks. This research provides an effective tool for information detection during public health emergencies, with substantial theoretical and practical implications. Full article

Filled pauses are thought to be reflections of linguistic processes (e.g., lexical retrieval, speech planning and execution). Uh may be a self-directed cue for when a speaker needs more time to retrieve lexical–semantic representations, whereas um serves as a listener-directed, pragmatic cue. The use of filled pauses has not been examined in children who are hard of hearing (CHH). Participants included 68 CHH and 33 children with typical hearing (CTH). Participants engaged in conversations, expository discourse, and fable retells. We analyzed filled pauses as a function of hearing status and discourse contexts and evaluated the relationship between filled pauses and language ability. CHH produced uh across discourse contexts more often than their hearing peers. CHH did not differ in their use of um relative to CTH. Both um and uh were used more often in conversational samples compared to other types of discourse. Spearman’s correlations did not show any significant associations between the rate of filled pauses and standardized language scores. These results indicate that CHH produces uh more often than CTH, suggesting that they may have difficulty retrieving lexical–semantic items during ongoing speech. This information may be useful for interventionists who are collecting language samples during assessment. Full article

Climate change represents one of the main challenges of this century. The hazards generated by this process are various and involve territorial assets all over the globe. Hydrogeological risk represents one of these aspects, and the violence of rain precipitations has led experts to focus their interest on the study of geotechnical assets in relation to these dangerous weather events. At the same time, geospatial representation in 3D WebGIS based on open-source solutions led specialists to employ this kind of technology to remotely analyze and monitor territorial events considering different sources of information. This study considers the construction of a 3D WebGIS framework for the real-time management of geospatial information developed with open-source technologies applied to the dynamic mapping of precipitation in the metropolitan area of Palermo (Italy) based on real-time weather station acquisitions. The structure considered is a WebGIS platform developed with Cesium.js JavaScript libraries, the Postgres database, Geoserver and Mapserver geospatial servers, and the Anaconda Python platform for activating real-time data connections using Python scripts. This framework represents a basic geospatial digital twin structure useful to municipalities, civil protection services, and firefighters for land management and for activating any preventive operations to ensure territorial safety. Furthermore, the open-source nature of the platform favors the free diffusion of this solution, avoiding expensive applications based on property software. The components of the framework are available and shared using GitHub. Full article

With the expansion of muskmelon cultivation, manual pollination is increasingly inadequate for sustaining industry development. Therefore, the development of automatic pollination robots holds significant importance in improving pollination efficiency and reducing labor dependency. Accurate flower detection and localization is a key technology for enabling automated pollination robots. In this study, the YOLO-MDL model was developed as an enhancement of YOLOv7 to achieve real-time detection and localization of muskmelon flowers. This approach adds a Coordinate Attention (CA) module to focus on relevant channel information and a Contextual Transformer (CoT) module to leverage contextual relationships among input tokens, enhancing the model’s visual representation. The pollination robot converts the 2D coordinates into 3D coordinates using a depth camera and conducts experiments on real-time detection and localization of muskmelon flowers in a greenhouse. The YOLO-MDL model was deployed in ROS to control a robotic arm for automatic pollination, verifying the accuracy of flower detection and measurement localization errors. The results indicate that the YOLO-MDL model enhances AP and F1 scores by 3.3% and 1.8%, respectively, compared to the original model. It achieves AP and F1 scores of 91.2% and 85.1%, demonstrating a clear advantage in accuracy over other models. In the localization experiments, smaller errors were revealed in all three directions. The RMSE values were 0.36 mm for the X-axis, 1.26 mm for the Y-axis, and 3.87 mm for the Z-axis. The YOLO-MDL model proposed in this study demonstrates strong performance in detecting and localizing muskmelon flowers. Based on this model, the robot can execute more precise automatic pollination and provide technical support for the future deployment of automatic pollination robots in muskmelon cultivation. Full article

Accurate prediction of airport delays under convective weather conditions is essential for effective traffic coordination and improving overall airport efficiency. Traditional methods mainly rely on numerical weather and traffic indicators, but they often fail to capture the spatial distribution of traffic flows within the terminal area. To address this limitation, we propose a novel image-based representation named Multi-Channel Traffic and Weather Scene Image (MTWSI), which maps both meteorological and traffic information onto a two-dimensional airspace grid, thereby preserving spatial relationships. Based on the MTWSI, we develop a delay prediction model named ADLCNN. This model first uses a convolutional neural network to extract deep spatial features from the scene images and then classifies each sample into a delay level. Using real operational data from Guangzhou Baiyun Airport, this paper shows that ADLCNN achieves significantly higher prediction accuracy compared to traditional machine learning methods. The results confirm that MTWSI provides a more accurate representation of real traffic conditions under convective weather. Full article

Knowledge-graph-based recommendation aims to provide personalized recommendation services to users based on their historical interaction information, which is of great significance for shopping transaction rates and other aspects. With the rapid growth of online shopping, the knowledge graph constructed from users’ historical interaction data now incorporates multiattribute information, including timestamps, images, and textual content. The information of multiple modalities is difficult to effectively utilize due to their different representation structures and spaces. The existing methods attempt to utilize the above information through simple embedding representation and aggregation, but ignore targeted representation learning for information with different attributes and learning effective weights for aggregation. In addition, existing methods are not sufficient for effectively modeling temporal information. In this article, we propose MTR, a knowledge graph recommendation framework based on mixture of experts network. To achieve this goal, we use a mixture-of-experts network to learn targeted representations and weights of different product attributes for effective modeling and utilization. In addition, we effectively model the temporal information during the user shopping process. A thorough experimental study on popular benchmarks validates that MTR can achieve competitive results. Full article

In intelligent vehicular networks, the accuracy of semantic segmentation in road scenes is crucial for vehicle-mounted artificial intelligence to achieve environmental perception, decision support, and safety control. Although deep learning methods have made significant progress, two main challenges remain: first, the difficulty in balancing global and local features leads to blurred object boundaries and misclassification; second, conventional convolutions have limited ability to perceive irregular objects, causing information loss and affecting segmentation accuracy. To address these issues, this paper proposes a global–local collaborative attention module and a spider web convolution module. The former enhances feature representation through bidirectional feature interaction and dynamic weight allocation, reducing false positives and missed detections. The latter introduces an asymmetric sampling topology and six-directional receptive field paths to effectively improve the recognition of irregular objects. Experiments on the Cityscapes, CamVid, and BDD100K datasets, collected using vehicle-mounted cameras, demonstrate that the proposed method performs excellently across multiple evaluation metrics, including mIoU, mRecall, mPrecision, and mAccuracy. Comparative experiments with classical segmentation networks, attention mechanisms, and convolution modules validate the effectiveness of the proposed approach. The proposed method demonstrates outstanding performance in sensor-based semantic segmentation tasks and is well-suited for environmental perception systems in autonomous driving. Full article

According to the United Nations Environment Programme reports, buildings are responsible for nearly 40% of energy-related emissions; therefore, energy-optimized building design is crucial to reduce the reliance on non-renewable energy sources as well as greenhouse gas emissions. The OECD reports indicate the use of Building Information Modelling (BIM) as one of the effective strategies for decarbonization of buildings, since a 3D digital representation of both physical and functional characteristics of a building can help to design a more efficient infrastructure. An efficient integration of solar energy in building design can be vital for the enhancement of energy performance in terms of heating, cooling, and lighting demand. This paper presents results of an analysis of how factors related to the use of daylight, such as automatic control of artificial lighting, external shading, or the visual absorptance of internal surfaces, influence the energy efficiency within an example room in two different climatic zones. The simulation was conducted using Design Builder software, with predefined occupancy schedules and internal heat gains, and standard EPW weather files for Warsaw and Genua climate zones. The study indicates that for the examined room, when no automatic sunshades or a lighting control system is utilized, most of the final energy demand is for cooling purposes (45–54%), followed by lighting (42–43%), with only 3–12% for heating purposes. The introduction of sunshades and/or the use of daylight allowed for a reduction of the total demand by up to half. Moreover, it was pointed out that often neglected factors, like the colour of the internal surfaces, can have a significant effect on the final energy consumption. In variants with light interior, the total energy consumption was lower by about 3–4% of the baseline demand, compared to their corresponding ones with dark surfaces. These results are consistent with previous studies on daylighting strategies and highlight the importance of considering both visual and thermal impacts when evaluating energy performance. Similarly, possible side effects of certain actions were highlighted, such as an increase in heat demand resulting from a reduced need for artificial lighting. The results of the analysis highlight the potential of a simulation-based design approach in optimizing daylight use, contributing to the broader goals of building decarbonization. Full article

Community detection in complex networks plays a pivotal role in modern scientific research, including in social network analysis and protein structure analysis. Traditional community detection methods face challenges in integrating heterogeneous multi-source information, capturing global semantic relationships, and adapting to dynamic network evolution. This paper proposes a novel unsupervised multimodal community detection algorithm (UMM) based on fractal iteration. The core idea is to design a dual-channel encoder that comprehensively considers node semantic features and network topological structures. Initially, node representation vectors are derived from structural information (using feature vectors when available, or singular value decomposition to obtain feature vectors for nodes without attributes). Subsequently, a parameter-free graph convolutional encoder (PFGC) is developed based on fractal iteration principles to extract high-order semantic representations from structural encodings without requiring any training process. Furthermore, a semantic–structural dual-channel encoder (DC-SSE) is designed, which integrates semantic encodings—reduced in dimensionality via UMAP—with structural features extracted by PFGC to obtain the final node embeddings. These embeddings are then clustered using the K-means algorithm to achieve community partitioning. Experimental results demonstrate that the UMM outperforms existing methods on multiple real-world network datasets. Full article

To address the limitations of the existing cotton seedling growth prediction methods in field environments, specifically, poor representation of spatiotemporal features and low visual fidelity in texture rendering, this paper proposes an algorithm for the prediction of cotton seedling growth from images based on FCA-STNet. The model leverages historical sequences of cotton seedling RGB images to generate an image of the predicted growth at time t + 1 and extracts 37 phenotypic traits from the predicted image. A novel STNet structure is designed to enhance the representation of spatiotemporal dependencies, while an Adaptive Fine-Grained Channel Attention (FCA) module is integrated to capture both global and local feature information. This attention mechanism focuses on individual cotton plants and their textural characteristics, effectively reducing the interference from common field-related challenges such as insufficient lighting, leaf fluttering, and wind disturbances. The experimental results demonstrate that the predicted images achieved an MSE of 0.0086, MAE of 0.0321, SSIM of 0.8339, and PSNR of 20.7011 on the test set, representing improvements of 2.27%, 0.31%, 4.73%, and 11.20%, respectively, over the baseline STNet. The method outperforms several mainstream spatiotemporal prediction models. Furthermore, the majority of the predicted phenotypic traits exhibited correlations with actual measurements with coefficients above 0.8, indicating high prediction accuracy. The proposed FCA-STNet model enables visually realistic prediction of cotton seedling growth in open-field conditions, offering a new perspective for research in growth prediction. Full article