rss_2.0International Journal of Advanced Network, Monitoring and Controls FeedSciendo RSS Feed for International Journal of Advanced Network, Monitoring and Controlshttps://sciendo.com/journal/IJANMChttps://www.sciendo.comInternational Journal of Advanced Network, Monitoring and Controls Feedhttps://sciendo-parsed.s3.eu-central-1.amazonaws.com/6471f5b6215d2f6c89db6d2e/cover-image.jpghttps://sciendo.com/journal/IJANMC140216A Baseline for Violence Behavior Detection in Complex Surveillance Scenarioshttps://sciendo.com/article/10.2478/ijanmc-2024-0036<abstract> <title style='display:none'>Abstract</title> <p>Violence detection can improve the ability to deal with emergencies, but there is still no data set specifically for violence detection. In this work, we propose VioData, a datasets specialized for detection in complex surveillance scenarios, and to more accurately assess the efficacy of these datasets, we propose a violence detection model based on target detection and 3D convolution. The model consists of two key modules: spatio-temporal feature extraction module and spatiotemporal feature fusion module. Among them, the spatio-temporal feature extraction module consists of a spatial feature module that extracts key frames using ordinary convolutional networks and a temporal feature extraction module that establishes temporal features using 3D convolution. The spatio-temporal feature fusion module Channel Fusion and Attention Mechanism (CFAM) fuses the temporal and spatial features. The experimental results indicate that the precision of the suggested detection model on UCF101-24, JHMDB behavioral detection datasets, and our proposed violence detection datasets, VioData, is improved compared to other violence detection models, which not only verifies the validity of the datasets, but also provides a baseline for the subsequent research and improvement in this area.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00362024-12-31T00:00:00.000+00:00Cognitive Map Construction Based on Grid Representationhttps://sciendo.com/article/10.2478/ijanmc-2024-0037<abstract> <title style='display:none'>Abstract</title> <p>This paper investigates a grid-representation-based approach to spatial cognition for intelligent agents, aiming to develop an effective neural network model that simulates the functions of the olfactory cortex and hippocampus for spatial cognition and navigation. Despite progress made by existing models in simulating biological nervous system functions, issues such as model simplification, lack of biological similarity, and practical application challenges remain. To address these issues, this paper proposes a neural network model that integrates grid representation, reinforcement learning, and encoding/decoding techniques. The model forms a grid representation by simulating the integration of grid cells in the medial entorhinal cortex (MEC) with perceptual information from the lateral entorhinal cortex (LEC), which encodes and retains spatial location information. By leveraging attractor networks, convolutional neural networks (CNNs), and multilayer perceptrons (MLPs), the model achieves the storage of spatial location and environmental information, as well as the construction of cognitive maps. The experimental results show that after using this model, the map generation accuracy increased by 15%, the navigation accuracy of the agent in complex environments by 20%, and the target localization error was reduced to less than 10%, demonstrating a significant overall performance improvement in the grid-based cognitive map construction.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00372024-12-31T00:00:00.000+00:00Long-term Target Tracking Based on Template Updating and Redetectionhttps://sciendo.com/article/10.2478/ijanmc-2024-0035<abstract> <title style='display:none'>Abstract</title> <p>To address the issue of targets frequently disappearing and reappearing in long-term tracking scenarios due to occlusion and being out of view, we have developed a long-term target tracking algorithm based on template updating and redetection (LTUSiam). Firstly, on the basis of the basic tracker SiamRPN, a three-level cascade gated cycle unit is introduced to assess the state of the target and select the right time to adopt the template update network to adapt the update template information. Secondly, a re-detection algorithm based on template matching is proposed. The candidate region extraction module is utilized to adjust the target's position and size in the basic tracker, and the evaluation score sequence is used to judge the target loss to determine the tracking state of the next frame. Experiments show that LTUSiam achieves 28 frames per second on VOT2018_LT dataset, achieving good results in real-time tracking, and 0.644 performance on F-score, which has better robustness in handling the problem of target loss recurrence, and effectively improves the performance of long-term tracking.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00352024-12-31T00:00:00.000+00:00Research on Construction Site Safety Q&A System Based on BERThttps://sciendo.com/article/10.2478/ijanmc-2024-0039<abstract> <title style='display:none'>Abstract</title> <p>This paper aims to utilize the pre-trained language model BERT from deep learning to construct A question and answer system specifically targeting safety knowledge in construction sites, thereby enhancing safety management on-site and increasing workers’ awareness of safety issues. Through extensive reading of literature related to construction site safety and the integration of practical case studies, this research compares various pre-trained language models such as word2vec, Pre-trained RNN, GPT, and BERT, analyzing their respective advantages and disadvantages. Despite the fact that word embedding methods such as word2vec have improved the effectiveness of natural language processing to some extent, their ability to understand context is limited. Pre-trained RNNs, although capable of handling sequential data, suffer from the problem of gradient disappearance when dealing with long-range dependencies. In contrast, the GPT model performs well in generative tasks; however, due to its reliance on a unidirectional language model, it falls short in understanding bidirectional contexts. Ultimately, it was determined that a method based on BERT would be most suitable for improving the model to meet the safety needs of construction sites. The system can accurately understand and respond to safety-related questions posed by workers, thereby preventing accidents and ensuring the safety of construction site personnel. This study not only explores the optimization and adjustment of the BERT model but also evaluates its performance in practical application scenarios, providing new technological means for safety education and management within the construction industry.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00392024-12-31T00:00:00.000+00:00Nystagmus Detection Method Based on Gating Mechanism and Attention Mechanismhttps://sciendo.com/article/10.2478/ijanmc-2024-0041<abstract> <title style='display:none'>Abstract</title> <p>In this paper, a new model based on the combination of improved LSTM and self-attention mechanism is studied for the detection of nystagmus caused by vestibular illusion in pilots during flight. An efficient and robust nystagmus detection method was proposed by constructing experimental simulation scenarios and collecting and analyzing pilot eye movement data. The improved LSTM model enhances the ability of capturing the medium and long term dependence of the ocular shock sequence by adding a gating unit, and the introduction of self-attention mechanism further improves the analytical accuracy of the model for complex eye movement sequences. The experimental results show that the model has excellent performance in accuracy, recall rate and F1 score, which is significantly better than the traditional model, providing a new technical means for the detection of vestibular illusion.The LSTM-GRU-Attention model has been experimentally verified to perform best in accuracy, recall, and F1 score, reaching 095, 0.91, and 0.93 respectively, indicating that the outperforms the other two models in overall classification performance, positive sample recognition ability, and balance between accuracy and recall.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00412024-12-31T00:00:00.000+00:00Research on the Financial Event Extraction Method Based on Fin-BERThttps://sciendo.com/article/10.2478/ijanmc-2024-0038<abstract> <title style='display:none'>Abstract</title> <p>Event extraction is based on the event in the text as the subject information, based on the predefined event type and template, the structured event information is extracted, the existing event extraction model is mainly in the general domain, ignoring the prior knowledge in the domain and the dependency information between entities, and the existing methods do not address the problem of event theory dispersion and multiple events. In response to the above issues, this paper proposes a model based on Fin-Bert (Financial Bidirectional Encoder Representation from Transformers) and RATT (Relation-Augmented Attention Transformer). At the same time, this paper will make use of the structured self-attention mechanism to extract the dependencies between entities, use RAAT to fuse the dependency information between entities into sentence coding, and finally use the binary classification method to identify type of event and generate event records. Compared with the baseline method, the F1 value of the event extraction task on the ChFinAnn and Duee-fin datasets was improved by 2.5% and 2.8%, respectively.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00382024-12-31T00:00:00.000+00:00Improvement of Helmet Detection Algorithm Based on YOLOv8https://sciendo.com/article/10.2478/ijanmc-2024-0034<abstract> <title style='display:none'>Abstract</title> <p>In order to solve the problems of safety helmets in complex factory environments due to the complex background, dense targets, etc., which cause the YOLOv8s algorithm to be prone to leakage and misdetection, and low recognition accuracy, a safety casque detection algorithm based on the YOLOv8s improved YOLOv8s-improved is proposed. By incorporating a deformable convolutional module into the backbone network of YOLOv8s, the occurrences of false negatives and false positives are effectively reduced, and detection accuracy is enhanced. To tackle the issue of small target detection being easily disturbed by image backgrounds and noise, the CBAM attention mechanism is embedded to sift out the relatively important information from a large amount of information, and enhances the ability of helmet information extraction; for the problem that the loss of small target classification and localization is not easy to calculate, a new For the problem of small target classification and localization loss is not easy to calculate, a new IoU loss function is introduced to improve the training effect of the model. The experiment shows that the detection accuracy mAP of the improved YOLOv8s algorithm in this paper is 1.3% higher than that of the original YOLOv8s algorithm. Experimental results have shown that the improved algorithm proposed in this paper not only reduces false positives and false negatives in helmet wearing detection, but also enhances the detection capability for small targets, thus improving the performance of helmet wearing detection to a certain extent.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00342024-12-31T00:00:00.000+00:00Structure-guided Generative Adversarial Network for Image Inpaintinghttps://sciendo.com/article/10.2478/ijanmc-2024-0031<abstract> <title style='display:none'>Abstract</title> <p>Generative Adversarial Network based image inpainting algorithms often make errors when filling arbitrary masked areas because all input pixels are treated as effective pixels during convolutional operations. To resolve this matter, we present a novel solution: an image inpainting algorithm that utilizes gated convolutions within the residual blocks of the network. By incorporating gated convolutions instead of traditional convolutions, our algorithm effectively learns and captures the relationship between the known regions and the masked regions. The algorithm utilizes a two-stage generative adversarial restoration network, where the structure and texture restoration are performed sequentially. Specifically, the structural information of the known region in the damaged image is detected using an edge detection algorithm. Subsequently, the edges of the masked area are combined with the color and texture information of the known region for structure restoration. Finally, the complete structure and the image to be restored are fed into the texture restoration network for texture restoration, yielding the complete image output. During network training, a spectral normalization Markovian discriminator is employed to address the slow weight changes during iteration, thereby increasing convergence speed and model accuracy. Based on the Places2 dataset, our experimental findings indicate that our algorithm surpasses existing two-stage restoration algorithms in terms of improving peak signal-to-noise ratio and structural similarity. Specifically, our proposed algorithm achieves a 4.3% enhancement in peak signal-to-noise ratio and a 3.7% improvement in structural similarity when restoring images with various shapes and sizes of damaged areas. Additionally, it produces noticeable visual enhancements, further validating its effectiveness.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00312024-12-31T00:00:00.000+00:00SEGNN4SLP: Structure Enhanced Graph Neural Networks for Service Link Predictionhttps://sciendo.com/article/10.2478/ijanmc-2024-0032<abstract> <title style='display:none'>Abstract</title> <p>For the provision of accurate link prediction, this study's neural network-based method for API recommendation uses structure encoding to capture topological context. SEGNN4SLP, a Graph Neural Network (GNN) framework that integrates node attributes and graph structure to enhance GNNs' link prediction skills, makes a substantial contribution. Utilizing an actual dataset with 21,900 APIs, 6,435 Mashups, and 13, 340 interactions, ProgrammableWeb.com was the source of the evaluation. Eighty percent of the data were test sets and twenty percent were training sets after single API-invocation Mashups were eliminated. The results demonstrate high link prediction accuracy, which is attributed to the incorporation of structural encoding in embedding learning and improved collaborative signal extraction from users and APIs, which improves API recommendation performance overall.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00322024-12-31T00:00:00.000+00:00A Novel Variance Reduction Proximal Stochastic Newton Algorithm for Large-Scale Machine Learning Optimizationhttps://sciendo.com/article/10.2478/ijanmc-2024-0040<abstract> <title style='display:none'>Abstract</title> <p>This paper introduces the Variance Reduction Proximal Stochastic Newton Algorithm (SNVR) for solving composite optimization problems in machine learning, specifically minimizing F(w) + Ω(w), where F is a smooth convex function and Ω is a non-smooth convex regularizer. SNVR combines variance reduction techniques with the proximal Newton method to achieve faster convergence while handling non-smooth regularizers. Theoretical analysis establishes that SNVR achieves linear convergence under standard assumptions, outperforming existing methods in terms of iteration complexity. Experimental results on the "heart" dataset (N=600, d=13) demonstrate SNVR's superior performance: Convergence speed: SNVR reaches optimal solution in 5 iterations, compared to 14 for ProxSVRG, and &gt;20 for proxSGD and ProxGD. Solution quality: SNVR achieves an optimal objective function value of 0.1919, matching ProxSVRG, and outperforming proxSGD (0.1940) and ProxGD (0.2148). Efficiency: SNVR shows a 10.5% reduction in objective function value within the first two iterations. These results indicate that SNVR offers significant improvements in both convergence speed (180-300% faster) and solution quality (up to 11.9% better) compared to existing methods, making it a valuable tool for large-scale machine learning optimization tasks.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00402024-12-31T00:00:00.000+00:00Advancing Large Language Model Agent via Iterative Contrastive Trajectory Optimizationhttps://sciendo.com/article/10.2478/ijanmc-2024-0033<abstract> <title style='display:none'>Abstract</title> <p>Recent advancements in Large Language Models (LLMs) have expanded their application across a variety of tasks. However, open-source LLMs often fail to achieve the same efficiency as proprietary models. To address this issue, we propose Iterative Contrastive Trajectory Optimization (ICTO), a novel framework designed to enhance the task-solving capabilities of LLM-based agents. ICTO facilitates iterative learning from both successful and failed task trajectories by utilizing Partially Observable Markov Decision Processes (POMDP) to provide step-level guidance. Experimental results demonstrate that ICTO improves task-solving efficiency by 12.4% and generalization ability by 15.7% compared to baseline models. The framework not only enhances the performance of open-source LLMs but also shows promise for broader applications in autonomous learning environments.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00332024-12-31T00:00:00.000+00:003D Reconstruction of Indoor Scenes Based on 3DGS Modelshttps://sciendo.com/article/10.2478/ijanmc-2024-0027<abstract> <title style='display:none'>Abstract</title> <p>A<sc>bstract</sc> With the rapid development of computer vision and artificial intelligence technologies, indoor scene reconstruction has been more and more widely used in the fields of virtual reality, augmented reality and architectural design. In this paper, we study an indoor scene reconstruction method based on the 3DGS model, which has been widely used in computer graphics and vision processing with powerful scene representation and rendering capabilities. In this study, we optimize the 3DGS model to enhance the detail preservation and realism of the reconstruction results by adjusting the opacity of the Gaussian function. We used the Replica dataset and the self-harvested dataset for model training. Through experimental validation, the peak signal-to-noise ratio as well as the structural similarity ratio of the reconstruction results of the optimized model have an improvement effect of more than 1%, which indicates that the optimized model has a significant improvement in detail retention and realism, and the reconstructed scene performs more realistically in terms of texture details and light and shadow effects.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00272024-09-30T00:00:00.000+00:009D Rotation Representation-SVD Fusion with Deep Learning for Unconstrained Head Pose Estimationhttps://sciendo.com/article/10.2478/ijanmc-2024-0028<abstract> <title style='display:none'>Abstract</title> <p>Accurately estimating human head pose poses a significant challenge across various application domains. To address the inherent limitations of previous approaches, this research proposes an unconstrained head pose estimation strategy. The method combines deep learning with rotation matrices, utilizing nine-dimensional vectors output by the neural network, which are projected back to rotation matrices in SO (3) space through singular value decomposition. This ensures both the smoothness and uniqueness of the rotation representation. The approach demonstrates distinct advantages in handling the rotation estimation task, particularly when the rotated representation is used as the model output. It not only avoids the discontinuity and double-coverage issues associated with prior methods but also enhances the stability of the representation in high-dimensional space, thereby improving the learning process. Additionally, the geodesic loss function is incorporated to train the network. The proposed strategy surpasses previous state-of-the-art methods, as evidenced by experiments conducted on the AFLW2000 and BIWI datasets.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00282024-09-30T00:00:00.000+00:00Improved Pedestrian Vehicle Detection for Small Objects Based on Attention Mechanismhttps://sciendo.com/article/10.2478/ijanmc-2024-0030<abstract> <title style='display:none'>Abstract</title> <p>This study aims to solve the low detection accuracy and susceptibility to false detection and omission in pedestrian and vehicle detection by proposing an improved YOLOv5s algorithm. Firstly, a small target detection module is added to better acquire and determine the information of pedestrians from long-range vehicles. Secondly, the multi-scale channel attention CBAM attention module is added, and the dual attention mechanism is not only flexible and convenient, but also improves the computational efficiency. Finally, the MPDIoU loss function based on minimum point distance is introduced to replace the original GIoU loss function, and this change not only enhances the regression accuracy of the model. At the same time, the convergence speed of the model is accelerated. KITTI data set was used for experiments, and the experimental results showed that the average accuracy of the model trained by the improved YOLOv5s algorithm on the data set reached 84.9%, which was 3.7% higher than that of the original YOLOv5s algorithm. It is verified that the model is suitable for high accuracy of pedestrian and vehicle recognition in complex environments, and has high value for promotion.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00302024-09-30T00:00:00.000+00:00Vector Storage Based Long-term Memory Research on LLMhttps://sciendo.com/article/10.2478/ijanmc-2024-0029<abstract> <title style='display:none'>Abstract</title> <p>Current large language model (LLM) intelligences face the challenges of high inference cost and low decision quality when dealing with complex tasks, and are especially deficient in maintaining context coherence during long tasks. This research presents an innovative vector storage long-term memory mechanism model (VIMBank) to enhance the long-term context retention ability and task execution efficiency of LLM intelligences by storing and retrieving historical interaction data through a vector database. VIMBank utilizes a dynamic memory updating strategy and the Ebbinghaus forgetting curve theory to efficiently manage the memory of intelligences and reinforce critical information, forgetting unimportant data, and optimizing storage and reasoning costs. The experimental results show that VIMBank significantly improves the decision quality and efficiency of LLM intelligences in multi-tasking scenarios and reduces the computational cost. Compared with different agents, the success rate of task decision is increased by 10% to 20%, and the reasoning cost is reduced by about 23%, which provides an important theoretical basis and practical support for the future development of intelligences with long term memory and adaptive learning ability.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00292024-09-30T00:00:00.000+00:00Real-Time Extraction of News Events Based on BERT Modelhttps://sciendo.com/article/10.2478/ijanmc-2024-0023<abstract> <title style='display:none'>Abstract</title> <p>For the large number of news reports generated every day, in order to obtain effective information from these unstructured news text data more efficiently. In this paper, we study the real-time crawling of news data from news websites through crawling techniques and propose a BERT model-based approach to extract events from news long text. In this study, NetEase news website is selected as an example for real-time extraction to crawl the news data of this website. BERT model as a pre-trained model based on two-way encoded representation of transformer performs well on natural language understanding and natural language generation tasks. In this study, we will fine-tune the training based on BERT model on news corpus related dataset and perform sequence annotation through CRF layer to finally complete the event extraction task. In this paper, the DUEE dataset is chosen to train the model, and the experiments show that the overall performance of the BERT model is better than other network models. Finally, the model of this paper is further optimised, using the ALBERT and RoBERTa models improved on the basis of the BERT model, experiments were conducted, the results show that both models are improved compared to the BERT model, the ALBERT model algorithm performs the best, the model algorithm's F1 value is 1% higher than that of BERT. The results show that the performance is optimised.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00232024-09-30T00:00:00.000+00:00Infrared Weak and Small Target Detection Algorithm Based on Deep Learninghttps://sciendo.com/article/10.2478/ijanmc-2024-0026<abstract> <title style='display:none'>Abstract</title> <p>In the infrared imaging scene where the target is at a long distance and the background is cluttered, due to the interference of noise and background texture information, the infrared image is prone to problems such as low contrast between the target and the background, and feature confusion, which makes it difficult to accurately extract and detect the target. To solve this problem, firstly, the infrared image is enhanced by combining DDE and MSR algorithm to improve the contrast and detail visibility of the image. For the RT-DETR network structure, the EMA attention mechanism is introduced into the backbone to enhance the feature extraction ability of the model by extracting context information. The CAMixing convolutional attention module is introduced into CCFM, and the multi-scale convolutional self-attention mechanism is introduced to focus on local information and enhance the detection ability of small targets. The filtering rules of the prediction box are improved, combined with Shape-IoU, and the convergence speed of the loss function in the detection and the detection accuracy of small targets are improved by paying attention to the influence of the intrinsic properties of the bounding box itself on the regression. In the experiment, the infrared weak target image dataset of the National University of Defense Technology was selected, labeled and trained. Experimental results show that compared with the original DETR algorithm, the average precision of the improved algorithm (mAP) is increased by 3.2%, and it can effectively detect infrared weak and small targets in different complex backgrounds, which reflects good robustness and adaptability, and can be effectively applied to infrared weak and small target detection in complex backgrounds.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00262024-09-30T00:00:00.000+00:00Enhancing Quantum Key Distribution Protocols for Extended Range and Reduced Errorhttps://sciendo.com/article/10.2478/ijanmc-2024-0022<abstract> <title style='display:none'>Abstract</title> <p>this paper proposes an optimized Quantum Key Distribution (QKD) protocol using entanglement swapping techniques to extend transmission range and improve error correction. Additionally, integrates an advanced error correction technique which is Low Density Parity Check (LDPC) and multi-hop quantum repeaters for more enhancement of the protocol performance. Hybrid Quantum Classical Error Correction Methods is applied ensuring compatibility and optimal performance and to manage the increased complexity. Simulations prove that 25% improvement in transmission distance with entanglement swapping. 50% improvement with advanced error correction and a 100% improvement with multi-hop quantum repeaters compared to existing protocols. These discoveries are supported by both theoretical analysis and simulation results, indicating significant decreases in error rates and extensions in maximum transmission distances. Comparative analysis made with existing protocols and that demonstrated the superiority of proposed approach in terms of extended secure communication distance, higher key generation rate and improved resilience to attacks.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00222024-09-30T00:00:00.000+00:00Hippocampal Cognitive Function Based on Deep Learninghttps://sciendo.com/article/10.2478/ijanmc-2024-0024<abstract> <title style='display:none'>Abstract</title> <p>This research focuses on the study of agent behavior decision-making based on hippocampal cognitive functions, aiming to enhance the decision-making capabilities of agents in complex task environments by deeply exploring the crucial role of the hippocampus in learning, memory, and cognitive processes. By drawing inspiration from the biological structure and functional characteristics of the hippocampus, researchers are dedicated to designing and developing more intelligent and adaptive decision-making models to enhance agents' behavioral performance, problem-solving abilities, and adaptability to new situations. To achieve this goal, the research integrates advanced artificial intelligence technologies such as reinforcement learning and deep learning to simulate the complex functions of the hippocampus in memory encoding, storage, retrieval, and cognitive reasoning. This research not only contributes to advancing intelligent systems towards higher levels of intelligence and personalization but also plays a significant role in improving the interaction between intelligent agents and humans, providing intelligent services that better meet user needs. We found that the neural network trained in multi-task learning benefits from a loss term that promotes relevant and irrelevant representations. Therefore, the complementary coding we found in CA3 can provide extensive computational advantages for solving complex tasks. Furthermore, the study emphasizes the importance of further elucidating the functional mechanisms of the hippocampus, with the expectation of providing a more solid theoretical foundation for the optimization and refinement of agent decision-making models in the future.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00242024-09-30T00:00:00.000+00:00Remote Sensing Building Damage Assessment Based on Machine Learninghttps://sciendo.com/article/10.2478/ijanmc-2024-0021<abstract> <title style='display:none'>Abstract</title> <p>After the occurrence of various types of disasters, including natural disasters and man-made damage, aid workers need accurate and timely data, such as the damage status of buildings, in order to take effective measures for rescue. So as to solve this problem, this paper researches and designs a building damage classification system based on machine learning. The damage assessment system consists of two network models (building extraction network and damage classification network). This article analyzes and designs the structure of each network model, and discusses the principles related to computer vision in machine learning. Buildings in satellite images are segmented through Siamese Convolutional Neural Network, the BottleNeck Module and Feature Pyramid Network are used in the damage classification assessment network to detect damage to buildings in sub-temporal remote sensing images. Subsequently, the model was trained and tested on different disaster events on the xBD dataset. The results show that the building damage detection system based on Siamese-CNN achieves good detection accuracy, and the system has the advantages of simple operation, good timeliness and low resource consumption, and can well meet the needs of disaster assessment.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijanmc-2024-00212024-09-30T00:00:00.000+00:00en-us-1