Search

In recent years, the wide application of deep neural network models has brought serious risks of intellectual property rights infringement. Embedding a watermark in a network model is an effective solution to protect intellectual property rights. Although researchers have proposed schemes to add watermarks to models, they cannot prevent attackers from adding and overwriting original information, and embedding rates cannot be quantified. Therefore, aiming at these problems, this paper designs a high embedding rate and tamper-proof watermarking scheme. We employ wet paper coding (WPC), in which important parameters are regarded as wet blocks and the remaining unimportant parameters are regarded as dry blocks in the model. To obtain the important parameters more easily, we propose an optimized probabilistic selection strategy (OPSS). OPSS defines the unimportant-level function and sets the importance threshold to select the important parameter positions and to ensure that the original function is not affected after the model parameters are changed. We regard important parameters as an unmodifiable part, and only modify the part that includes the unimportant parameters. We selected the MNIST, CIFAR-10, and ImageNet datasets to test the performance of the model after adding a watermark and to analyze the fidelity, robustness, embedding rate, and comparison schemes of the model. Our experiment shows that the proposed scheme has high fidelity and strong robustness along with a high embedding rate and the ability to prevent malicious tampering.

This document is a special issue of the journal Algorithms, featuring selected papers from the journal's editorial board members from 2022 and 2023. The issue includes 16 research papers covering a range of topics such as game theory, fault detection in cellular networks, optimization algorithms, machine learning, cryptocurrency trading, and more. Each paper presents its own unique research findings and methodologies. The issue aims to showcase the diverse research interests and expertise of the journal's editorial board members. [Extracted from the article]

The electrocardiogram (ECG) signal describes the heart's electrical activity, allowing it to detect several health conditions, including cardiac system abnormalities and dysfunctions. Nowadays, most patient medical records are still paper-based, especially those made in past decades. The importance of collecting digitized ECGs is twofold: firstly, all medical applications can be easily implemented with an engineering approach if the ECGs are treated as signals; secondly, paper ECGs can deteriorate over time, therefore a correct evaluation of the patient's clinical evolution is not always guaranteed. The goal of this paper is the realization of an automatic conversion algorithm from paper-based ECGs (images) to digital ECG signals. The algorithm involves a digitization process tested on an image set of 16 subjects, also with pathologies. The quantitative analysis of the digitization method is carried out by evaluating the repeatability and reproducibility of the algorithm. The digitization accuracy is evaluated both on the entire signal and on six ECG time parameters (R-R peak distance, QRS complex duration, QT interval, PQ interval, P-wave duration, and heart rate). Results demonstrate the algorithm efficiency has an average Pearson correlation coefficient of 0.94 and measurement errors of the ECG time parameters are always less than 1 mm. Due to the promising experimental results, the algorithm could be embedded into a graphical interface, becoming a measurement and collection tool for cardiologists. [ABSTRACT FROM AUTHOR]

With the development of the customization concept, small-batch and multi-variety production will become one of the major production modes, especially for fast-moving consumer goods. However, this production mode has two issues: high production cost and the long manufacturing period. To address these issues, this study proposes a multi-objective optimization model for the flexible flow-shop to optimize the production scheduling, which would maximize the production efficiency by minimizing the production cost and makespan. The model is designed based on hybrid algorithms, which combine a fast non-dominated genetic algorithm (NSGA-II) and a variable neighborhood search algorithm (VNS). In this model, NSGA-II is the major algorithm to calculate the optimal solutions. VNS is to improve the quality of the solution obtained by NSGA-II. The model is verified by an example of a real-world typical FFS, a tissue papermaking mill. The results show that the scheduling model can reduce production costs by 4.2% and makespan by 6.8% compared with manual scheduling. The hybrid VNS-NSGA-II model also shows better performance than NSGA-II, both in production cost and makespan. Hybrid algorithms are a good solution for multi-objective optimization issues in flexible flow-shop production scheduling. [ABSTRACT FROM AUTHOR]

Compared to the conventional boost power factor correction (PFC) converter, a totem-pole bridgeless PFC has high efficiency because it does not have an input diode rectifier stage, but a current spike may occur when the polarity of the grid voltage changes. This paper proposes a digital control algorithm for bridgeless totem-pole PFC with a simple control structure based on the phase angle of grid voltage. The proposed algorithm has a PI-based double-loop control structure and performs DC-link voltage and input inductor current control. Rectifying switches operate based on the proposed rectification algorithm using phase angle information calculated through a single-phase phase-locked loop (PLL) to prevent current spikes. The feed-forward duty ratio value is calculated according to the polarity of the grid voltage and added to the double-loop controller to perform appropriate power factor control. The performance and feasibility of the proposed control algorithm are verified through a 3 kW hardware prototype. [ABSTRACT FROM AUTHOR]

The intrinsic features of documents, such as paper color, texture, aging, translucency, the kind of printing, typing or handwriting, etc., are important with regard to how to process and enhance their image. Image binarization is the process of producing a monochromatic image having its color version as input. It is a key step in the document processing pipeline. The recent Quality-Time Binarization Competitions for documents have shown that no binarization algorithm is good for any kind of document image. This paper uses a sample of the texture of the scanned historical documents as the main document feature to select which of the 63 widely used algorithms, using five different versions of the input images, totaling 315 document image-binarization schemes, provides a reasonable quality-time trade-off. [ABSTRACT FROM AUTHOR]

To facilitate better interpretation of dielectric response measurements--thereby directing numerical evidence for condition assessments of oil-paper-insulated equipment in high-voltage alternating current (HVAC) transmission systems--a novel approach is presented to estimate the parameters in the extended Debye model (EDM) using wideband frequency domain spectroscopy (FDS). A syncretic algorithm that integrates a genetic algorithm (GA) and the Levenberg-Marquardt (L-M) algorithm is introduced in the present study to parameterize EDM using the FDS measurements of a real-life 126 kV oil-impregnated paper (OIP) bushing under different controlled temperatures. As for the uncertainty of the EDM structure due to variable branch quantity, Akaike's information criterion (AIC) is employed to determine the model orders. For verification, comparative analysis of FDS reconstruction and results of FDS transformation to polarization--depolarization current (PDC)/return voltage measurement (RVM) are presented. The comparison demonstrates good agreement between the measured and reconstructed spectroscopies of complex capacitance and tan δover the full tested frequency band (10-4 Hz-10³ Hz) with goodness of fit over 0.99. Deviations between the tested and modelled PDC/RVM from FDS are then discussed. Compared with the previous studies to parameterize the model using time domain dielectric responses, the proposed method solves the problematic matching between EDM and FDS especially in a wide frequency band, and therefore assures a basis for quantitative insulation condition assessment of OIP-insulated apparatus in energy systems. [ABSTRACT FROM AUTHOR]

Smart communication has significantly advanced with the integration of the Internet of Things (IoT). Many devices and online services are utilized in the network system to cope with data gathering and forwarding. Recently, many traffic-aware solutions have explored autonomous systems to attain the intelligent routing and flowing of internet traffic with the support of artificial intelligence. However, the inefficient usage of nodes' batteries and long-range communication degrades the connectivity time for the deployed sensors with the end devices. Moreover, trustworthy route identification is another significant research challenge for formulating a smart system. Therefore, this paper presents a smart Random walk Distributed Secured Edge algorithm (RDSE), using a multi-regression model for IoT networks, which aims to enhance the stability of the chosen IoT network with the support of an optimal system. In addition, by using secured computing, the proposed architecture increases the trustworthiness of smart devices with the least node complexity. The proposed algorithm differs from other works in terms of the following factors. Firstly, it uses the random walk to form the initial routes with certain probabilities, and later, by exploring a multi-variant function, it attains long-lasting communication with a high degree of network stability. This helps to improve the optimization criteria for the nodes' communication, and efficiently utilizes energy with the combination of mobile edges. Secondly, the trusted factors successfully identify the normal nodes even when the system is compromised. Therefore, the proposed algorithm reduces data risks and offers a more reliable and private system. In addition, the simulations-based testing reveals the significant performance of the proposed algorithm in comparison to the existing work. [ABSTRACT FROM AUTHOR]

Millimeter-wave radar-based identification technology has a wide range of applications in persistent identity verification, covering areas such as security production, healthcare, and personalized smart consumption systems. It has received extensive attention from the academic community due to its advantages of being non-invasive, environmentally insensitive and privacy-preserving. Existing identification algorithms mainly rely on a single signal, such as breathing or heartbeat. The reliability and accuracy of these algorithms are limited due to the high similarity of breathing patterns and the low signal-to-noise ratio of heartbeat signals. To address the above issues, this paper proposes an algorithm for multimodal fusion for identity recognition. This algorithm extracts and fuses features derived from phase signals, respiratory signals, and heartbeat signals for identity recognition purposes. The spatial features of signals with different modes are first extracted by the residual network (ResNet), after which these features are fused with a spatial-channel attention fusion module. On this basis, the temporal features are further extracted with a time series-based self-attention mechanism. Finally, the feature vectors of the user's vital sign modality are obtained to perform identity recognition. This method makes full use of the correlation and complementarity between different modal signals to improve the accuracy and reliability of identification. Simulation experiments show that the algorithm identity recognition proposed in this paper achieves an accuracy of 94.26% on a 20-subject self-test dataset, which is much higher than that of the traditional algorithm, which is about 85%. [ABSTRACT FROM AUTHOR]

Federated learning (FL) is a scheme in which several consumers work collectively to unravel machine learning (ML) problems, with a dominant collector synchronizing the procedure. This decision correspondingly enables the training data to be distributed, guaranteeing that the individual device's data are secluded. The paper systematically reviewed the available literature using the Preferred Reporting Items for Systematic Review and Meta-analysis (PRISMA) guiding principle. The study presents a systematic review of appliable ML approaches for FL, reviews the categorization of FL, discusses the FL application areas, presents the relationship between FL and Blockchain Technology (BT), and discusses some existing literature that has used FL and ML approaches. The study also examined applicable machine learning models for federated learning. The inclusion measures were (i) published between 2017 and 2021, (ii) written in English, (iii) published in a peer-reviewed scientific journal, and (iv) Preprint published papers. Unpublished studies, thesis and dissertation studies, (ii) conference papers, (iii) not in English, and (iv) did not use artificial intelligence models and blockchain technology were all removed from the review. In total, 84 eligible papers were finally examined in this study. Finally, in recent years, the amount of research on ML using FL has increased. Accuracy equivalent to standard feature-based techniques has been attained, and ensembles of many algorithms may yield even better results. We discovered that the best results were obtained from the hybrid design of an ML ensemble employing expert features. However, some additional difficulties and issues need to be overcome, such as efficiency, complexity, and smaller datasets. In addition, novel FL applications should be investigated from the standpoint of the datasets and methodologies. [ABSTRACT FROM AUTHOR]

An early detection tool for latent COVID-19 infections in oncology staff and patients is essential to prevent outbreaks in a cancer center. (1) Background: In this study, we developed and implemented two early detection tools for the radiotherapy area to identify COVID-19 cases opportunely. (2) Methods: Staff and patients answered a questionnaire (electronic and paper surveys, respectively) with clinical and epidemiological information. The data were collected through two online survey tools: Real-Time Tracking (R-Track) and Summary of Factors (S-Facts). Cut-off values were established according to the algorithm models. SARS-CoV-2 qRT-PCR tests confirmed the positive algorithms individuals. (3) Results: Oncology staff members (n = 142) were tested, and 14% (n = 20) were positives for the R-Track algorithm; 75% (n = 15) were qRT-PCR positive. The S-Facts Algorithm identified 7.75% (n = 11) positive oncology staff members, and 81.82% (n = 9) were qRT-PCR positive. Oncology patients (n = 369) were evaluated, and 1.36% (n = 5) were positive for the Algorithm used. The five patients (100%) were confirmed by qRT-PCR. (4) Conclusions: The proposed early detection tools have proved to be a low-cost and efficient tool in a country where qRT-PCR tests and vaccines are insufficient for the population. [ABSTRACT FROM AUTHOR]

The paper [[10]] considers an assignment problem and some modifications which can be converted to routing, distribution, or scheduling problems. This special issue of I Algorithms i is dedicated to recent developments of scheduling algorithms and new applications. References 1 Werner F., Burtseva L., Sotskov Y. Special Issue on Algorithms for Scheduling Problems. For this problem, a hybrid metaheuristic algorithm is presented which combines a genetic algorithm with a so-called spotted hyena optimization algorithm. [Extracted from the article]

Context: Software product lines (SPLs) have reached a considerable level of adoption in the software industry. The most commonly used models for managing the variability of SPLs are feature models (FMs). The analysis of FMs is an error-prone, tedious task, and it is not feasible to accomplish this task manually with large-scale FMs. In recent years, much effort has been devoted to developing reasoning algorithms for FMs. Aim: To synthesize the evidence on the use of reasoning algorithms for feature modeling. Method: We conducted a systematic mapping study, including six research questions. This study included 66 papers published from 2010 to 2020. Results: We found that most algorithms were used in the domain stage (70%). The most commonly used technologies were transformations (18%). As for the origins of the proposals, they were mainly rooted in academia (76%). The FODA model continued to be the most frequently used representation for feature modeling (70%). A large majority of the papers presented some empirical validation process (90%). Conclusion: We were able to respond to the RQs. The FODA model is consolidated as a reference within SPLs to manage variability. Responses to RQ2 and RQ6 require further review. [ABSTRACT FROM AUTHOR]

The efficient and accurate identification of traffic signs is crucial to the safety and reliability of active driving assistance and driverless vehicles. However, the accurate detection of traffic signs under extreme cases remains challenging. Aiming at the problems of missing detection and false detection in traffic sign recognition in fog traffic scenes, this paper proposes a recognition algorithm for traffic signs based on pix2pixHD+YOLOv5-T. Firstly, the defogging model is generated by training the pix2pixHD network to meet the advanced visual task. Secondly, in order to better match the defogging algorithm with the target detection algorithm, the algorithm YOLOv5-Transformer is proposed by introducing a transformer module into the backbone of YOLOv5. Finally, the defogging algorithm pix2pixHD is combined with the improved YOLOv5 detection algorithm to complete the recognition of traffic signs in foggy environments. Comparative experiments proved that the traffic sign recognition algorithm proposed in this paper can effectively reduce the impact of a foggy environment on traffic sign recognition. Compared with the YOLOv5-T and YOLOv5 algorithms in moderate fog environments, the overall improvement of this algorithm is achieved. The precision of traffic sign recognition of the algorithm in the fog traffic scene reached 78.5%, the recall rate was 72.2%, and mAP@0.5 was 82.8%. [ABSTRACT FROM AUTHOR]

This paper focuses on the problem of information source identification in online social networks (OSNs). By analyzing the research situation of source identification problems and challenges (such as the randomness of the information dissemination process and complexity of the underlying network topology), this paper studies the problem of multiple source diffusion and proposes a source identification algorithm based on multi-attribute topological clustering (MaTC). The basic idea of the algorithm is to decompose the multi-source problems into a series of single-source problems by using clustering partitioning to improve accuracy and efficiency. Firstly, it estimates the number of source nodes, which is also the number of network partitions, then characterizes the combination of multiple attribute structures as an attribute index of topological clustering, performs an analysis of the distribution of real source nodes in each partition to evaluate the accuracy of the clustering partition, and finally uses Jordan centrality within each partition for single-source identification. Through comparative experiments, it is verified that the proposed MaTC algorithm is superior to the comparison algorithms in evaluating indicators. [ABSTRACT FROM AUTHOR]

This research studied the strategies that players use in sequential adversarial games. We took the Rock-Paper-Scissors (RPS) game as an example and ran players in two experiments. The first experiment involved two humans, who played the RPS together for 100 times. Importantly, our payoff design in the RPS allowed us to differentiate between participants who used a random strategy from those who used a Nash strategy. We found that participants did not play in agreement with the Nash strategy, but rather, their behavior was closer to random. Moreover, the analyses of the participants' sequential actions indicated heterogeneous cycle-based behaviors: some participants' actions were independent of their past outcomes, some followed a well-known win-stay/lose-change strategy, and others exhibited the win-change/lose-stay behavior. To understand the sequential patterns of outcome-dependent actions, we designed probabilistic computer algorithms involving specific change actions (i.e., to downgrade or upgrade according to the immediate past outcome): the Win-Downgrade/Lose-Stay (WDLS) or Win-Stay/Lose-Upgrade (WSLU) strategies. Experiment 2 used these strategies against a human player. Our findings show that participants followed a win-stay strategy against the WDLS algorithm and a lose-change strategy against the WSLU algorithm, while they had difficulty in using an upgrade/downgrade direction, suggesting humans' limited ability to detect and counter the actions of the algorithm. Taken together, our two experiments showed a large diversity of sequential strategies, where the win-stay/lose-change strategy did not describe the majority of human players' dynamic behaviors in this adversarial situation. [ABSTRACT FROM AUTHOR]

The increasing demand for smart vehicles with many sensing capabilities will escalate data traffic in vehicular networks. Meanwhile, available network resources are limited. The emergence of AI implementation in vehicular network resource allocation opens the opportunity to improve resource utilization to provide more reliable services. Accordingly, many resource allocation schemes with various machine learning algorithms have been proposed to dynamically manage and allocate network resources. This survey paper presents how machine learning is leveraged in the vehicular network resource allocation strategy. We focus our study on determining its role in the mechanism. First, we provide an analysis of how authors designed their scenarios to orchestrate the resource allocation strategy. Secondly, we classify the mechanisms based on the parameters they chose when designing the algorithms. Finally, we analyze the challenges in designing a resource allocation strategy in vehicular networks using machine learning. Therefore, a thorough understanding of how machine learning algorithms are utilized to offer a dynamic resource allocation in vehicular networks is provided in this study.

Objective: This study compared the aerosol and splatter diameter and count numbers produced by a dental mouth prop with a suction holder device and a saliva ejector during ultrasonic scaling in a clinical setting. Methodology: Fluorescein dye was placed in the dental equipment irrigation reservoirs with a mannequin, and an ultrasonic scaler was employed. The procedures were performed three times per device. The upper and bottom board papers were placed on the laboratory platform. All processes used an ultrasonic scaler to generate aerosol and splatter. A dental mouth prop with a suction holder and a saliva ejector were also tested. Photographic analysis was used to examine the fluorescein samples, followed by image processing in Python and assessment of the diameter and count number. For device comparison, statistics were used with an independent t-test. Result: When using the dental mouth prop with a suction holder, the scaler produced aerosol particles that were maintained on the upper board paper (mean ± SD: 1080 ± 662 µm) compared to on the bottom board paper (1230 ± 1020 µm). When the saliva ejector was used, it was found that the diameter of the aerosol on the upper board paper was 900 ± 580 µm, and the diameter on the bottom board paper was 1000 ± 756 µm. Conclusion: There was a significant difference in the aerosol and splatter particle diameter and count number between the dental mouth prop with a suction holder and saliva ejector (p < 0.05). Furthermore, the results revealed that there was a statistically significant difference between the two groups on the upper and bottom board papers. [ABSTRACT FROM AUTHOR]

In response to the challenges posed by small objects in remote sensing images, such as low resolution, complex backgrounds, and severe occlusions, this paper proposes a lightweight improved model based on YOLOv8n. During the detection of small objects, the feature fusion part of the YOLOv8n algorithm retrieves relatively fewer features of small objects from the backbone network compared to large objects, resulting in low detection accuracy for small objects. To address this issue, firstly, this paper adds a dedicated small object detection layer in the feature fusion network to better integrate the features of small objects into the feature fusion part of the model. Secondly, the SSFF module is introduced to facilitate multi-scale feature fusion, enabling the model to capture more gradient paths and further improve accuracy while reducing model parameters. Finally, the HPANet structure is proposed, replacing the Path Aggregation Network with HPANet. Compared to the original YOLOv8n algorithm, the recognition accuracy of mAP@0.5 on the VisDrone data set and the AI-TOD data set has increased by 14.3% and 17.9%, respectively, while the recognition accuracy of mAP@0.5:0.95 has increased by 17.1% and 19.8%, respectively. The proposed method reduces the parameter count by 33% and the model size by 31.7% compared to the original model. Experimental results demonstrate that the proposed method can quickly and accurately identify small objects in complex backgrounds. [ABSTRACT FROM AUTHOR]

To achieve effective and accurate segmentation of photovoltaic panels in various working contexts, this paper proposes a comprehensive image segmentation strategy that integrates an improved Meanshift algorithm and an adaptive Shi-Tomasi algorithm. This approach effectively addresses the challenge of low precision in segmenting target regions and boundary contours in routine photovoltaic panel inspection. Firstly, based on the image information of photovoltaic panels collected under different environments by cameras, an improved Meanshift algorithm based on platform histogram optimization is used for preliminary processing, and images containing target information are cut out; then, the adaptive Shi-Tomasi algorithm is used to extract and screen feature points from the target area; finally, the extracted feature points generate the segmentation contour of the target photovoltaic panel, achieving accurate segmentation of the target area and boundary contour of the photovoltaic panel. Experiments verified that in photovoltaic panel images under different background environments, the method proposed in this paper enhances the accuracy of segmenting the target area and boundary contour of photovoltaic panels. [ABSTRACT FROM AUTHOR]

When facing problems in the aerial pursuit game, most of the current unmanned aerial vehicles (UAVs) have good maneuverability performance, but it is difficult to utilize the overload maneuverability of UAVs properly; further, UAVs tend to be more costly, and it is often difficult to effectively prevent the enemy from reaching the tailgating position behind the UAV in the aerial pursuit game. Therefore, there is a pressing need for a maneuvering algorithm that can effectively allow a UAV to quickly protect itself in a disadvantageous position, stably and effectively select a maneuver with the maneuvering algorithm, and stably and effectively establish an advantage by moving to an advantageous position. Therefore, this paper establishes a cloud model-based UAV-maneuvering aerial pursuit decision-making model based on pursuit-and-evasion game positions. Based on the evaluation of the latter, when the UAV is at a disadvantage, we use the constructed defensive maneuver expert pool to abandon the disadvantageous position. When the UAV is at an advantage, we use cloud model-based pursuit-and-evasion game maneuvering decision making to establish an advantageous position. According to the results of the simulation examples, the maneuvering decision-making method designed in this paper confirms that the UAV can quickly abandon its position and establish an advantage in case of parity or disadvantage and that it can also stably establish a tail-chasing position in case of advantage. [ABSTRACT FROM AUTHOR]

Cellular structures consist of foams, honeycombs, and lattices. Lattices have many outstanding properties over foams and honeycombs, such as lightweight, high strength, absorbing energy, and reducing vibration, which has been extensively studied and concerned. Because of excellent properties, lattice structures have been widely used in aviation, bio-engineering, automation, and other industrial fields. In particular, the application of additive manufacturing (AM) technology used for fabricating lattice structures has pushed the development of designing lattice structures to a new stage and made a breakthrough progress. By searching a large number of research literature, the primary work of this paper reviews the lattice structures. First, based on the introductions about lattices of literature, the definition and classification of lattice structures are concluded. Lattice structures are divided into two general categories in this paper: uniform and non-uniform. Second, the performance and application of lattice structures are introduced in detail. In addition, the fabricating methods of lattice structures, i.e., traditional processing and additive manufacturing, are evaluated. Third, for uniform lattice structures, the main concern during design is to develop highly functional unit cells, which in this paper is summarized as three different methods, i.e., geometric unit cell based, mathematical algorithm generated, and topology optimization. Forth, non-uniform lattice structures are reviewed from two aspects of gradient and topology optimization. These methods include Voronoi-tessellation, size gradient method (SGM), size matching and scaling (SMS), and homogenization, optimization, and construction (HOC). Finally, the future development of lattice structures is prospected from different aspects. [ABSTRACT FROM AUTHOR]

Emotion recognition commonly relies on single-modal recognition methods, such as voice and video signals, which demonstrate a good practicability and universality in some scenarios. Nevertheless, as emotion-recognition application scenarios continue to expand and the data volume surges, single-modal emotion recognition proves insufficient to meet people's needs for accuracy and comprehensiveness when the amount of data reaches a certain scale. Thus, this paper proposes the application of multimodal thought to enhance emotion-recognition accuracy and conducts corresponding data preprocessing on the selected dataset. Appropriate models are constructed for both audio and video modalities: for the audio-modality emotion-recognition task, this paper adopts the "time-distributed CNNs + LSTMs" model construction scheme; for the video-modality emotion-recognition task, the "DeepID V3 + Xception architecture" model construction scheme is selected. Furthermore, each model construction scheme undergoes experimental verification and comparison with existing emotion-recognition algorithms. Finally, this paper attempts late fusion and proposes and implements a late-fusion method based on the idea of weight adaptation. The experimental results demonstrate the superiority of the multimodal fusion algorithm proposed in this paper. When compared to the single-modal emotion-recognition algorithm, the accuracy of recognition is increased by almost 4%, reaching 84.33%. [ABSTRACT FROM AUTHOR]

The integration of machine learning (ML) techniques into marketing strategies has become increasingly relevant in modern business. Utilizing scientific manuscripts indexed in the Scopus database, this article explores how this integration is being carried out. Initially, a focused search is undertaken for academic articles containing both the terms "machine learning" and "marketing" in their titles, which yields a pool of papers. These papers have been processed using the Supabase platform. The process has included steps like text refinement and feature extraction. In addition, our study uses two key ML methodologies: topic modeling through NMF and a comparative analysis utilizing the k-means clustering algorithm. Through this analysis, three distinct clusters emerged, thus clarifying how ML techniques are influencing marketing strategies, from enhancing customer segmentation practices to optimizing the effectiveness of advertising campaigns. [ABSTRACT FROM AUTHOR]

In the field of risk assessment, the traditional econometric models are generally used to assess credit risk. And with the introduction of the "dual-carbon" goals to promote the development of a low-carbon economy, the scale of green credit in China has rapidly expanded. But with the advent of the big data era, due to the poor interpretability of a traditional single machine learning model, it is difficult to capture nonlinear relationships, and there are shortcomings in prediction accuracy and robustness. This paper selects the adjusted ensemble learning model based on the homogeneous and heterogeneous factors for user default prediction, which can efficiently process large quantities of high-dimensional data. This article adjusts each model to adapt to the task and innovatively compares various models. In this paper, the missing value filling method, feature selection, and ensemble model are studied and discussed, and the optimal ensemble model is obtained. When comparing the predictions of single models and ensemble models, the accuracy, sensitivity, specificity, F1-Score, Kappa, and MCC of Categorical Features Gradient Boosting (CatBoost) and Random undersampling Boosting (RUSBoost) all reach 100%. The experimental results prove that the algorithm based on adjusted homogeneous and heterogeneous ensemble learning can predict the user default efficiently and accurately. This paper also provides some references for establishing a risk assessment index system. [ABSTRACT FROM AUTHOR]

Efficient multiprocessor scheduling is pivotal in optimizing the performance of parallel computing systems. This paper leverages the power of Petri nets and the tool GPenSIM to model and simulate a variety of multiprocessor scheduling algorithms (the basic algorithms such as first come first serve, shortest job first, and round robin, and more sophisticated schedulers like multi-level feedback queue and Linux's completely fair scheduler). This paper presents the evaluation of three crucial performance metrics in multiprocessor scheduling (such as turnaround time, response time, and throughput) under various scheduling algorithms. However, the primary focus of the paper is to develop a robust simulation platform consisting of Petri Modules to facilitate the dynamic representation of concurrent processes, enabling us to explore the real-time interactions and dependencies in a multiprocessor environment; more advanced and newer schedulers can be tested with the simulation platform presented in this paper. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicle (UAV)-based object detection methods are widely used in traffic detection due to their high flexibility and extensive coverage. In recent years, with the increasing complexity of the urban road environment, UAV object detection algorithms based on deep learning have gradually become a research hotspot. However, how to further improve algorithmic efficiency in response to the numerous and rapidly changing road elements, and thus achieve high-speed and accurate road object detection, remains a challenging issue. Given this context, this paper proposes the high-efficiency multi-object detection algorithm for UAVs (HeMoDU). HeMoDU reconstructs a state-of-the-art, deep-learning-based object detection model and optimizes several aspects to improve computational efficiency and detection accuracy. To validate the performance of HeMoDU in urban road environments, this paper uses the public urban road datasets VisDrone2019 and UA-DETRAC for evaluation. The experimental results show that the HeMoDU model effectively improves the speed and accuracy of UAV object detection. [ABSTRACT FROM AUTHOR]

Oblique photography is a regional digital surface model generation technique that can be widely used for building 3D model construction. However, due to the lack of geometric and semantic information about the building, these models make it difficult to differentiate more detailed components in the building, such as roofs and balconies. This paper proposes a deep learning-based method (U-NET) for constructing 3D models of low-rise buildings that address the issues. The method ensures complete geometric and semantic information and conforms to the LOD2 level. First, digital orthophotos are used to perform building extraction based on U-NET, and then a contour optimization method based on the main direction of the building and the center of gravity of the contour is used to obtain the regular building contour. Second, the pure building point cloud model representing a single building is extracted from the whole point cloud scene based on the acquired building contour. Finally, the multi-decision RANSAC algorithm is used to segment the building detail point cloud and construct a triangular mesh of building components, followed by a triangular mesh fusion and splicing method to achieve monolithic building components. The paper presents experimental evidence that the building contour extraction algorithm can achieve a 90.3% success rate and that the resulting single building 3D model contains LOD2 building components, which contain detailed geometric and semantic information. [ABSTRACT FROM AUTHOR]

To address the current steel surface defect detection algorithms in practical applications involving low detection accuracy, an efficient and highly accurate strip steel surface defect detection algorithm, DEW-YOLO, is proposed in this paper. Firstly, by combining the advantages of deformable convolutional networks (DCNs), this paper innovates the C2F module in YOLOv8 and proposes a C2f_DCN module that can flexibly sample features to enhance the abilities of learning and expressing defect features of different sizes and shapes. Secondly, the explicit visual center (EVC) is introduced into the backbone network, which enhances feature extraction capabilities and adaptability and enables the model to better adjust features at different levels and scales. Finally, the original loss function is replaced with the Wise-IoU (WIoU) loss function to accurately measure the similarity between the target frames and improve the defect detection performance of the model. The experimental results on the NEU-DET dataset demonstrate that the algorithms proposed in this paper achieved a mean average precision (mAP) of 80.3% in steel surface defect detection tasks, which was a 3.9% improvement over the original YOLOv8 model. The model's inference speed reached 91 frames per second (FPS). DEW-YOLO effectively enhances the accuracy of steel defect detection and better satisfies industrial inspection requirements. [ABSTRACT FROM AUTHOR]

For visible and Synthetic Aperture Radar (SAR) image fusion, this paper proposes a visible and SAR image fusion algorithm based on a Transformer and a Convolutional Neural Network (CNN). Firstly, in this paper, the Restormer Block is used to extract cross-modal shallow features. Then, we introduce an improved Transformer–CNN Feature Extractor (TCFE) with a two-branch residual structure. This includes a Transformer branch that introduces the Lite Transformer (LT) and DropKey for extracting global features and a CNN branch that introduces the Convolutional Block Attention Module (CBAM) for extracting local features. Finally, the fused image is output based on global features extracted by the Transformer branch and local features extracted by the CNN branch. The experiments show that the algorithm proposed in this paper can effectively achieve the extraction and fusion of global and local features of visible and SAR images, so that high-quality visible and SAR fusion images can be obtained. [ABSTRACT FROM AUTHOR]

Mutual exclusion is a fundamental problem in concurrent/parallel/distributed systems. The first pure-software solution to this problem for two processes, which is not based on hardware instructions like test-and-set, was proposed in 1965 by Th.J. Dekker and communicated by E.W. Dijkstra. The correctness of this algorithm has generally been studied under the strong memory model, where the read and write operations on a memory cell are atomic or indivisible. In recent years, some variants of the algorithm have been proposed to make it RW-safe when using the weak memory model, which makes it possible, e.g., for multiple read operations to occur simultaneously to a write operation on the same variable, with the read operations returning (flickering) a non-deterministic value. This paper proposes a novel approach to formal modeling and reasoning on a mutual exclusion algorithm using Timed Automata and the Uppaal tool, and it applies this approach through exhaustive model checking to conduct a thorough analysis of the Dekker's algorithm and some of its variants proposed in the literature. This paper aims to demonstrate that model checking, although necessarily limited in the scalability of the number N of the processes due to the state explosions problem, is effective yet powerful for reasoning on concurrency and process action interleaving, and it can provide significant results about the correctness and robustness of the basic version and variants of the Dekker's algorithm under both the strong and weak memory models. In addition, the properties of these algorithms are also carefully studied in the context of a tournament-based binary tree for N ≥ 2 processes. [ABSTRACT FROM AUTHOR]

In the process of fabric production, various types of defects affect the quality of a fabric. However, due to the wide variety of fabric defects, the complexity of fabric textures, and the concealment of small target defects, current fabric defect detection algorithms suffer from issues such as having a slow detection speed, low detection accuracy, and a low recognition rate of small target defects. Therefore, developing an efficient and accurate fabric defect detection system has become an urgent problem that needs to be addressed in the textile industry. Addressing the aforementioned issues, this paper proposes an improved YOLOv8n-LAW algorithm based on the YOLOv8n algorithm. First, LSKNet attention mechanisms are added to both ends of the C2f module in the backbone network to provide a broader context area, enhancing the algorithm's feature extraction capability. Next, the PAN-FPN structure of the backbone network is replaced by the AFPN structure, so that the different levels of features of the defects are closer to the semantic information in the progressive fusion. Finally, the CIoU loss is replaced with the WIoU v3 loss, allowing the model to dynamically adjust gradient gains based on the features of fabric defects, effectively focusing on distinguishing between defective and non-defective regions. The experimental results show that the improved YOLOv8n-LAW algorithm achieved an accuracy of 97.4% and a detection speed of 46 frames per second, while effectively increasing the recognition rate of small target defects. [ABSTRACT FROM AUTHOR]

Train wheels are crucial components for ensuring the safety of trains. The accurate and fast identification of wheel tread defects is necessary for the timely maintenance of wheels, which is essential for achieving the premise of conditional repair. Image-based detection methods are commonly used for detecting tread defects, but they still have issues with the misdetection of water stains and the leaking of small defects. In this paper, we address the challenges posed by the detection of wheel tread defects by proposing improvements to the YOLOv8 model. Firstly, the impact of water stains on tread defect detection is avoided by optimising the structure of the detection layer. Secondly, an improved SPPCSPC module is introduced to enhance the detection of small targets. Finally, the SIoU loss function is used to accelerate the convergence speed of the network, which ensures defect recognition accuracy with high operational efficiency. Validation was performed on the constructed tread defect dataset. The results demonstrate that the enhanced YOLOv8 model in this paper outperforms the original network and significantly improves the tread defect detection indexes. The average precision, accuracy, and recall reached 96.95%, 96.30%, and 95.31%. [ABSTRACT FROM AUTHOR]

Buildings are significant components of digital cities, and their precise extraction is essential for the three-dimensional modeling of cities. However, it is difficult to accurately extract building features effectively in complex scenes, especially where trees and buildings are tightly adhered. This paper proposes a highly accurate building point cloud extraction method based solely on the geometric information of points in two stages. The coarsely extracted building point cloud in the first stage is iteratively refined with the help of mask polygons and the region growing algorithm in the second stage. To enhance accuracy, this paper combines the Alpha Shape algorithm with the neighborhood expansion method to generate mask polygons, which help fill in missing boundary points caused by the region growing algorithm. In addition, this paper performs mask extraction on the original points rather than non-ground points to solve the problem of incorrect identification of facade points near the ground using the cloth simulation filtering algorithm. The proposed method has shown excellent extraction accuracy on the Urban-LiDAR and Vaihingen datasets. Specifically, the proposed method outperforms the PointNet network by 20.73% in precision for roof extraction of the Vaihingen dataset and achieves comparable performance with the state-of-the-art HDL-JME-GGO network. Additionally, the proposed method demonstrated high accuracy in extracting building points, even in scenes where buildings were closely adjacent to trees. [ABSTRACT FROM AUTHOR]

The purpose of the self-driving car is to minimize the number casualties of traffic accidents. One of the effects of traffic accidents is an improper speed of a car, especially at the road turn. If we can make the anticipation of the road turn, it is possible to avoid traffic accidents. This paper presents a cutting edge curve lane detection algorithm based on the Kalman filter for the self-driving car. It uses parabola equation and circle equation models inside the Kalman filter to estimate parameters of a using curve lane. The proposed algorithm was tested with a self-driving vehicle. Experiment results show that the curve lane detection algorithm has a high success rate. The paper also presents simulation results of the autonomous vehicle with the feature to control steering and speed using the results of the full curve lane detection algorithm. [ABSTRACT FROM AUTHOR]

In the work reported in this paper, a lost-in-space star pattern identification algorithm for agile spacecraft was studied. Generally, the operation of a star tracker is known to exhibit serious degradation or even failure during fast attitude maneuvers. While tracking methods are widely used solutions to handle the dynamic conditions, they require prior information about the initial orientation. Therefore, the tracking methods may not be adequate for autonomy of attitude and control systems. In this paper a novel autonomous identification method for dynamic conditions is proposed. Additional constraints are taken into account that can significantly decrease the number of stars imaged and the centroid accuracy. A strategy combining two existing classes for star pattern identification is proposed. The new approach is intended to provide a unique way to determine the identity of stars that promises robustness against noise and rapid identification. Moreover, representative algorithms implemented in actual space applications were utilized as counterparts to analyze the performance of the proposed method in various scenarios. Numerical simulations show that the proposed method is not only highly robust against positional noise and false stars, but also guarantees fast run-time, which is appropriate for high-speed applications. [ABSTRACT FROM AUTHOR]

Featured Application: A self-configurable assembly workstation with integrated I4.0 technologies and controlled by smart algorithm provides an ergonomic workplace for each worker and prevents errors during assembly. Due to increasing competition in the global market and to meet the need for rapid changes in product variability, it is necessary to introduce self-configurable and smart solutions within the entire process chain, including manual assembly to ensure the more efficient and ergonomic performance of the manual assembly process. This paper presents a smart assembly system including newly developed smart manual assembly workstation controlled by a smart algorithm. The smart assembly workstation is self-configurable according to the anthropometry of the individual worker, the complexity of the assembly process, the product characteristics, and the product structure. The results obtained by a case study show that is possible to organize manual assembly process with rapid adaptation of the smart assembly system to new products and workers characteristics, to achieve ergonomic working conditions through Digital Human Modelling (DHM), to minimize assembly time, and to prevent error during the assembly process. The proposed system supports the manual assembly process redesign to ensure a better working environment and aims to have an important value for applying the smart algorithms to manual assembly workstations in human-centered manufacturing systems. [ABSTRACT FROM AUTHOR]

Topographic maps comprise a rich data source for the processing and analysis of geographic information. However, the management of paper topographic maps is still dominated by an inefficient manual method, and there is no counting equipment for topographic maps that is suitable for narrow map warehouse passages. The existing algorithms relating to paper counting require paper hardness and cannot directly obtain the internal information of topographic maps. To address the above problems, using a map inventory machine transformed from a paddle-type paper counting machine to perform a preliminary count and obtain the video data of the counting progress, an automatic counting algorithm for topographic maps for map management is proposed in this study. First, the periodic feature changes of all the targets and each individual target in the videos are analyzed. Second, a deformable parts model accelerated by fast feature pyramids and by reducing the region of interest is used for the object detection of mechanical wheels. The grayscale variance function is selected to quantify the quality change in the images. Finally, a fusion window counting model is constructed with the adaptive window and fixed window methods. The experimental results show that the average counting accuracy of the model is about 95%, which can verify the initial counting results of the machine and provide high-quality keyframes for the subsequent sheet designation recognition. [ABSTRACT FROM AUTHOR]

To overcome the deficiencies in segmenting hot spots from thermal infrared images, such as difficulty extracting the edge features, low accuracy, and a high missed detection rate, an improved Mask R-CNN photovoltaic hot spot thermal image segmentation algorithm has been proposed in this paper. Firstly, the edge image features of hot spots were extracted based on residual neural networks. Secondly, by combining the feature pyramid structure, an edge-guided feature pyramid structure was designed, and the hot spot edge features were injected into a Mask R-CNN network. Thirdly, an infrared spatial attention module was introduced into the Mask R-CNN network when feature extraction and the infrared features of the detected hot spots were enhanced. Fourthly, the size ratio of the candidate frames was adjusted self-adaptively according to the structural characteristics of the aspect ratio of the hot spots. Finally, the validation experiments were conducted, and the results demonstrated that the hot spot contours of thermal infrared images were enhanced through the algorithm proposed in this paper, and the segmentation accuracy was significantly improved. [ABSTRACT FROM AUTHOR]

With the rapid development of remote sensing technology, remote sensing products have found increasingly widespread applications across various fields. Nevertheless, as the volume of remote sensing image data continues to grow, traditional data retrieval techniques have encountered several challenges such as substantial query results, data overlap, and variations in data quality. Users need to manually browse and filter a large number of remote sensing datasets, which is a cumbersome and inefficient process. In order to cope with these problems of traditional remote sensing image retrieval methods, this paper proposes a remote sensing image retrieval algorithm for dense data (DD-RSIRA). The algorithm establishes evaluation metrics based on factors like imaging time, cloud coverage, and image coverage. The algorithm utilizes the global grids to create an ensemble coverage relation between images and grids. A locally optimal initial solution is obtained by a greedy algorithm, and then a local search is performed to search for the optimal solution by combining the strategies of weighted gain-loss scheme and novel mechanism. Ultimately, it achieves an optimal coverage of remote sensing images within the region of interest. In this paper, it is shown that the method obtains a smaller number of datasets with lower redundancy and higher data utilization and ensures the data quality to a certain extent in order to accurately meet the requirements of the regional coverage of remote sensing images. [ABSTRACT FROM AUTHOR]

The article discusses recent advances in information-centric networks (ICNs) and their potential benefits for current network uses and mobile networks. It highlights the implementation of ICN through named data networking (NDN), which focuses on content rather than location. The article includes several research papers that address various issues related to ICN, such as in-network storage, resource efficiency, caching algorithms, satellite communications, and security. These papers propose innovative solutions and strategies to improve the performance and effectiveness of ICNs in different contexts. [Extracted from the article]

With the rapid development of adversarial example technologies, the concept of adversarial patches has been proposed, which can successfully transfer adversarial attacks to the real world and fool intelligent object detection systems. However, the real-world environment is complex and changeable, and the adversarial patch attack technology is susceptible to real-world factors, resulting in a decrease in the success rate of attack. Existing adversarial-patch-generation algorithms have a single direction of patch initialization and do not fully consider the impact of initial diversification on its upper limit of adversarial patch attack. Therefore, this paper proposes an initial diversified adversarial patch generation technology to improve the effect of adversarial patch attacks on the underlying algorithms in the real world. The method uses YOLOv4 as the attack model, and the experimental results show that the attack effect of the adversarial-patch-attack method proposed in this paper is higher than the baseline 8.46%, and it also has a stronger attack effect and fewer training rounds. [ABSTRACT FROM AUTHOR]

The problem of information security and copyright protection of video is becoming increasingly prominent. The current video watermarking algorithm does not have strong anti-compression, which has a significant impact on the visual effect of video. To solve this problem, this paper proposes a video watermarking algorithm based on H.264/AVC. The algorithm combines the non-zero quantization coefficient and the energy factor to select the appropriate chroma subblock, and then an optimized modulation is designed to embed the watermark into its DCT quantization coefficients in order to minimize the number of modifications of the subblocks. The invisibility and robustness experiments of the algorithm are conducted in the paper, and the Structural Similarity Indexes are above 0.99, and the False Bit Rates are all below 0.03. The results show that the algorithm has good invisibility, anti-compression performance and obvious advantages compared with other similar methods. [ABSTRACT FROM AUTHOR]

With the rapid advancement of Unmanned Aerial Vehicle (UAV) technologies in recent years, their uses have been increasingly adopted in the architecture, engineering, and construction industries. To satisfy the needs of various types of construction projects, a considerable amount of research work has been performed to implement and refine the operations, safety, and accuracy of UAVs. This paper presents the findings of a comprehensive literature review that focuses on UAV research in construction management during the timeframe of 2016 to 2021. A total of 95 papers were identified and collected from a list of 21 relevant journals and conference proceedings, and were then categorized by their research topic, sensor types, and targeted structures. The results of 47 exemplary studies were reported in two categories, namely UAV uses and construction uses. The research topics identified for UAV uses include algorithm, applications, operations, framework, and training, while research topics identified for construction use include inspection, surveying, safety, and monitoring. The connection between the research topics, sensor types, targeted structures, and other advanced technologies were also discussed. This paper summarizes the current results of UAV research in construction management, reviews the methodology, benefits, and limitations of the reviewed literature, and provides valuable knowledge for the future trend of UAV applications in the civil, infrastructure, and construction industries. [ABSTRACT FROM AUTHOR]

At present, any industry that wanted to be considered a vanguard must be willing to improve itself, developing innovative techniques to generate a competitive advantage against its direct competitors. Hence, many methods are employed to optimize production processes, such as Lot Streaming, which consists of partitioning the productive lots into overlapping small batches to reduce the overall operating times known as Makespan, reducing the delivery time to the final customer. This work proposes carrying out a systematic review following the PRISMA methodology to the existing literature in indexed databases that demonstrates the application of Lot Streaming in the different production systems, giving the scientific community a strong consultation tool, useful to validate the different important elements in the definition of the Makespan reduction objectives and their applicability in the industry. Two hundred papers were identified on the subject of this study. After applying a group of eligibility criteria, 63 articles were analyzed, concluding that Lot Streaming can be applied in different types of industrial processes, always keeping the main objective of reducing Makespan, becoming an excellent improvement tool, thanks to the use of different optimization algorithms, attached to the reality of each industry. [ABSTRACT FROM AUTHOR]

This paper considers the confrontation problem for two tank swarms of equal size and capability in a complex urban scenario. Based on the Unity platform (2022.3.20f1c1), the confrontation scenario is constructed featuring multiple crossing roads. Through the analysis of a substantial amount of biological data and wildlife videos regarding animal behavioral strategies during confrontations for hunting or food competition, two strategies are been utilized to design a novel bio-inspired intelligent swarm confrontation algorithm. The first one is the "fire concentration" strategy, which assigns a target for each tank in a way that the isolated opponent will be preferentially attacked with concentrated firepower. The second one is the "back and forth maneuver" strategy, which makes the tank tactically retreat after firing in order to avoid being hit when the shell is reloading. Two state-of-the-art swarm confrontation algorithms, namely the reinforcement learning algorithm and the assign nearest algorithm, are chosen as the opponents for the bio-inspired swarm confrontation algorithm proposed in this paper. Data of comprehensive confrontation tests show that the bio-inspired swarm confrontation algorithm has significant advantages over its opponents from the aspects of both win rate and efficiency. Moreover, we discuss how vital algorithm parameters would influence the performance indices. [ABSTRACT FROM AUTHOR]

Loop closure detection is an important component of the Simultaneous Localization and Mapping (SLAM) algorithm, which is utilized in environmental sensing. It helps to reduce drift errors during long-term operation, improving the accuracy and robustness of localization. Such improvements are sorely needed, as conventional visual-based loop detection algorithms are greatly affected by significant changes in viewpoint and lighting conditions. In this paper, we present a semantic spatial structure-based loop detection algorithm. In place of feature points, robust semantic features are used to cope with the variation in the viewpoint. In consideration of the semantic features, which are region-based, we provide a corresponding matching algorithm. Constraints on semantic information and spatial structure are used to determine the existence of loop-back. A multi-stage pipeline framework is proposed to systematically leverage semantic information at different levels, enabling efficient filtering of potential loop closure candidates. To validate the effectiveness of our algorithm, we conducted experiments using the uHumans2 dataset. Our results demonstrate that, even when there are significant changes in viewpoint, the algorithm exhibits superior robustness compared to that of traditional loop detection methods. [ABSTRACT FROM AUTHOR]

To reduce safety accidents caused by distracted driving and address issues such as low recognition accuracy and deployment difficulties in current algorithms for distracted behavior detection, this paper proposes an algorithm that utilizes an improved KNN for classifying driver posture features to predict distracted driving behavior. Firstly, the number of channels in the Lightweight OpenPose network is pruned to predict and output the coordinates of key points in the upper body of the driver. Secondly, based on the principles of ergonomics, driving behavior features are modeled, and a set of five-dimensional feature values are obtained through geometric calculations. Finally, considering the relationship between the distance between samples and the number of samples, this paper proposes an adjustable distance-weighted KNN algorithm (ADW-KNN), which is used for classification and prediction. The experimental results show that the proposed algorithm achieved a recognition rate of 94.04% for distracted driving behavior on the public dataset SFD3, with a speed of up to 50FPS, superior to mainstream deep learning algorithms in terms of accuracy and speed. The superiority of ADW-KNN was further verified through experiments on other public datasets. [ABSTRACT FROM AUTHOR]

Generalized target detection algorithms perform well for large- and medium-sized targets but struggle with small ones. However, with the growing importance of aerial images in urban transportation and environmental monitoring, detecting small targets in such imagery has been a promising research hotspot. The challenge in small object detection lies in the limited pixel proportion and the complexity of feature extraction. Moreover, current mainstream detection algorithms tend to be overly complex, leading to structural redundancy for small objects. To cope with these challenges, this paper recommends the PCSG model based on yolov5, which optimizes both the detection head and backbone networks. (1) An enhanced detection header is introduced, featuring a new structure that enhances the feature pyramid network and the path aggregation network. This enhancement bolsters the model's shallow feature reuse capability and introduces a dedicated detection layer for smaller objects. Additionally, redundant structures in the network are pruned, and the lightweight and versatile upsampling operator CARAFE is used to optimize the upsampling algorithm. (2) The paper proposes the module named SPD-Conv to replace the strided convolution operation and pooling structures in yolov5, thereby enhancing the backbone's feature extraction capability. Furthermore, Ghost convolution is utilized to optimize the parameter count, ensuring that the backbone meets the real-time needs of aerial image detection. The experimental results from the RSOD dataset show that the PCSG model exhibits superior detection performance. The value of mAP increases from 97.1% to 97.8%, while the number of model parameters decreases by 22.3%, from 1,761,871 to 1,368,823. These findings unequivocally highlight the effectiveness of this approach. [ABSTRACT FROM AUTHOR]

A deep learning-based Visual Inertial SLAM technique is proposed in this paper to ensure accurate autonomous localization of mobile robots in environments with dynamic objects. Addressing the limitations of real-time performance in deep learning algorithms and the poor robustness of pure visual geometry algorithms, this paper presents a deep learning-based Visual Inertial SLAM technique. Firstly, a non-blocking model is designed to extract semantic information from images. Then, a motion probability hierarchy model is proposed to obtain prior motion probabilities of feature points. For image frames without semantic information, a motion probability propagation model is designed to determine the prior motion probabilities of feature points. Furthermore, considering that the output of inertial measurements is unaffected by dynamic objects, this paper integrates inertial measurement information to improve the estimation accuracy of feature point motion probabilities. An adaptive threshold-based motion probability estimation method is proposed, and finally, the positioning accuracy is enhanced by eliminating feature points with excessively high motion probabilities. Experimental results demonstrate that the proposed algorithm achieves accurate localization in dynamic environments while maintaining real-time performance. [ABSTRACT FROM AUTHOR]