检索结果-内蒙古大学图书馆

11th IEEE International Conference on Behavioural and Social Computing, BESC 2024

作者： Qi, Shuhan Huang, Chengkai Li, Yifan School of Computer Science and Technology Harbin Institute of Technology Shenzhen Shenzhen China School of Computer Science and Engineering The University of New South Wales Sydney Australia

ISBN: (纸本)9798331531904

With the increasing popularity of short video plat-forms, the massive UGC provides high-quality materials for brand advertising. Recently, personalized content discovery methods have been proposed to recommend appropriate posts for brands to attract potential consumers. However, there are some drawbacks of them. Firstly, these methods only use images but ignore the multimodal information, which is not suitable for video-based brand advertising. Secondly, the generated features of brands are too coarse to distinguish the subtle differences from similar brands. In this paper, we propose a fine-grained multimodal content discovery (FGMCD) framework, which uses a large number of multimodal data to recommend informative videos for brands. Further, we designed a new hierarchical model, which adopts fine-grained features of different levels to make distinctions of similar brands exactly. We also collect a high-quality dataset with 50 car brands from Instagram and the experiments show the effectiveness of our method. © 2024 IEEE.

关键词： Content Discovery Multi-modal Recommendation Social Media Marketing

来源：评论

学校读者我要写书评

暂无评论

Research on Image Fusion Method Based on Nonsubsampled Contourlet Transform 4

Research on Image Fusion Method Based on Nonsubsampled Conto...

引用

4th International Conference on Electronic information engineering and computer science, EIECS 2024

作者： Zhao, Pengfei Liu, Peng Zhao, Haili Zhao, Zhi School of Electronic Information Engineering Changchun University of Science and Technology Changchun China

ISBN: (纸本)9798331531409

In modern military operations, as camouflage technology advances, soldiers, weaponry, and other military materials have become highly similar to their surroundings, making it difficult for traditional optical target recognition techniques to effectively identify camouflaged targets. Polarization imaging technology captures the polarization characteristics of light reflected from object surfaces, enhancing contrast between the object and the background, providing additional image information, and helping to distinguish optically similar materials or surface features, particularly excelling in complex environments. This paper proposes a multi-scale, multi-directional fusion algorithm based on NSCT, incorporating the local similarity preservation of LSP features, adaptive weight allocation, and an improved PCNN algorithm to handle details, nonlinear information, noise, and directionality issues in images. Experimental results show that this algorithm outperforms traditional fusion methods in evaluation metrics such as EN, AG, SNR, and SF, with both subjective and objective assessments demonstrating significant advantages. The proposed algorithm offers a new approach to image fusion and camouflage target recognition, demonstrating significant potential for military applications. © 2024 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Research on Multipoint Collaborative Target Recognition and Tracking Algorithm 4

Research on Multipoint Collaborative Target Recognition and ...

引用

4th International Conference on Electronic information engineering and computer science, EIECS 2024

作者： Zhang, Yang Yang, Guang Gao, Siqi School of Electronic Information Engineering Changchun University of Science and Technology Changchun China

ISBN: (纸本)9798331531409

Frame differencing method can adapt well to dynamic environments with changes in lighting and complex background transformations. However, its characteristic of determining whether an object is in motion by extracting the object's contour leads to misdetection and missed detection when detecting moving objects. Meanwhile, frame difference operation also increases the calculation processing time and thus generates a higher delay. To address the mentioned issues, the article proposes a multi-point collaborative object recognition algorithm. Firstly, perform grayscale processing on the image. Secondly, it employs an improved BM3D (Block Matching 3D) algorithm for denoising. Then the image data after noise removal is identified and tracked by an improved adaptive interframe difference algorithm. Finally, a multi-point collaborative FPGA-based object recognition and tracking system is designed to validate the algorithm. Experimental results show that, compared to traditional frame differencing methods, the improved algorithm reduces latency by approximately 200 microseconds and significantly enhances the accuracy of object recognition. © 2024 IEEE.

关键词： Contourlet transform

来源：评论

学校读者我要写书评

暂无评论

Trajectory Planning of Rechargeable UAVs for AoS Minimization in IoT Networks 16

Trajectory Planning of Rechargeable UAVs for AoS Minimizatio...

引用

16th International Conference on Wireless Communications and Signal Processing, WCSP 2024

作者： Liu, Yunchao Lin, Suling Gong, Jie School of Computer Science and Engineering Sun Yat-sen University Guangdong Key Laboratory of Information Security Technology Guangzhou510006 China

ISBN: (纸本)9798350390643

Freshness of information is a critical issue for real-time Internet of Things (IoT) applications. Unmanned aerial vehicles (UAVs), due to their high flexibility and low cost, are widely deployed in time-sensitive IoT scenarios. In this article, we explore the trajectory planning problem in rechargeable-UAV-aided IoT Networks. To accurately measure the freshness of information, we introduce Age of information (AoI) and Age of Synchronization (AoS). AoI is utilized to plan the UAVs' trajectories for accessing sensors (SNs) and reduce the average AoS of the system. UAVs can recharge at charging stations to maintain energy above a certain threshold. We formulate a Markov decision process with the objective of minimizing the average AoS under the energy constraint. To adjust the dynamic environment, we propose a multi-agent deep reinforcement learning method to jointly optimize the UAVs' flight trajectories and battery recharging. Simulation results demonstrate that the proposed algorithm can significantly reduce the total average AoS under the energy constraint. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

SN-TOOD: An Improved TOOD-Based Steel Surface Defect Detection

SN-TOOD: An Improved TOOD-Based Steel Surface Defect Detecti...

引用

2024 International Annual Conference on Complex Systems and Intelligent science, CSIS-IAC 2024

作者： Liu, Guanghu Chu, Maoxiang Gong, Rongfen University of Science and Technology Liaoning School of Electronic and Information Engineering Anshan China

ISBN: (纸本)9798331504755

The quality of steel products is a critical determinant in the competitive landscape and growth of the steel industry. Despite this, the surfaces of steel products are inevitably marred by various imperfections due to a multitude of factors encountered in the manufacturing process. Consequently, the detection and analysis of these imperfections are paramount for improving product quality and enhancing the competitive edge of steel enterprises. In this context, the present study introduces an enhanced defect detection model based on Task-aligned One-stage Object Detection (TOOD), which exhibits superior performance in the identification of surface defects on steel plates, designated as SN-TOOD. Firstly, an Spatial and Channel Multi-scale Attention module is proposed to refine the model's spatial and channel-based feature representation of steel surface defects. Following this, feature pyramid networks augmented by neural architecture search is integrated as a feature fusion network, which autonomously identifies the optimal configuration for feature fusion pertinent to steel surface defect detection during the training phase. Furthermore, the soft non-maximum suppression is utilized in the post-processing stage to remove redundant bounding boxes generated during the model's predictive phase, thereby augmenting the detection accuracy. Finally, a comprehensive experimental validation has substantiated that the proposed methodology surpasses alternative approaches in terms of the mAP50 metric (NEU-DET: 0.712). © 2024 IEEE.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

Non-metal inducing charge rearrangement in carbon nitride to promote photocatalytic hydrogen production

引用

Journal of Materials science & technology 2024年第28期195卷 1-8页

作者： Guanyu Wu Zhiyu He Qiuheng Wang Haibo Wang Zeyu Wang Peipei Sun Zhao Mo Huanzhi Liu Hui Xu School of the Environment and Safety Engineering School of Materials Science&EngineeringJiangsu UniversityZhenjiang 212013China Jiangsu Vocational College of Electronics and Information Huaian 223003China College of Chemical Engineering and Environment China University of PetroleumBeijing 102249China Jiangsu Collaborative Innovation Center of Technology and Material of Water Treatment Suzhou University of Science and TechnologySuzhou 215009China

Photocatalytic hydrogen production technology offers a means of converting solar energy into chemical energy contained in hydrogen for human ***,traditional photocatalysts restrict the progress of photocatalytic technology owing to the straightforward complexation of carriers and lack of active ***,in this work,the number of active sites and carrier separation efficiency have been significantly improved by non-metallic modification and modulation of the geometry of carbon *** has been demonstrated that oxygen doping enhances the energy band structure of benzene-substituted Odoped g-CN nanotubes(BOCN).Oxygen,in conjunction with the benzene ring,creates redox energy level positions that are spatially ***-dimensional tubular structures synthesised by supramolecular self-assembly have a thin-walled structure capable of exposing more active ***,the adsorption equilibrium of H+on the catalyst is further *** in-depth analysis of each component through experiments and theoretical calculations contributes to a reasonable photocatalytic mechanism for decomposing aquatic hydrogen.

关键词： Carbon nitride Photocatalysis Hydrogen evolution Charge separation

来源：评论

学校读者我要写书评

暂无评论

Visual SLAM-based fire extinguishing robot for energy storage power plants 3

Visual SLAM-based fire extinguishing robot for energy storag...

引用

3rd International Conference on Energy, Power and Electrical technology, ICEPET 2024

作者： Long, Xiang Liu, Zheng Changsha University of Science and Technology School of Electrical and Information Engineering Changsha China

ISBN: (纸本)9798350352658

With the increase of energy storage stations, fire accidents in lithium battery energy storage compartments occur frequently, seriously threatening the stable operation of the power system and the safety of personnel. To solve the danger of manual fire extinguishing, a visual SLAM based fire extinguishing robot for energy storage stations has been designed. In response to the environment of the energy storage station, the main structure and firefighting operation mechanism of the robot have been designed to ensure that the robot can smoothly carry out firefighting operations at the energy storage station. Explored the characteristics of lithium-ion battery fires and the laws of thermal runaway, analyzed the fire extinguishing mechanism of liquid nitrogen, and found that using liquid nitrogen as a fire extinguishing agent has a good inhibitory effect on lithium-ion battery fires. In order to achieve efficient fire extinguishing, and due to the limited liquid nitrogen capacity that robots can carry, a fast autonomous positioning and mapping (SLAM) fire extinguishing strategy for energy storage power plant fire extinguishing robots in unknown environments was designed to ensure maximum utilization of liquid nitrogen. Simulation experiments were conducted on this fire extinguishing strategy, and the results showed that it can extinguish open flames within 10 seconds, effectively suppress the spread of battery thermal runaway, and control the concentration of combustible gases in the cabin beyond the explosion limit. The fire extinguishing robot and extinguishing strategy have a significant inhibitory effect on lithium battery fires in energy storage stations. © 2024 IEEE.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

Health Status Evaluation for PV Inverter Based on Enhanced MPdist-HMM-K-means Models 4

Health Status Evaluation for PV Inverter Based on Enhanced M...

引用

4th International Conference on Electronic information engineering and computer science, EIECS 2024

作者： Zhang, Zhaohua Chen, Xiaojuan School of Electronic Information Engineering Changchun University of Science and Technology Changchun China

ISBN: (纸本)9798331531409

The performance and dependability of photovoltaic (PV) power systems depend heavily on the condition of the inverters. As the solar industry develops quickly, the inverter, a vital component, becomes even more important in guaranteeing the effective conversion of solar energy. However, basic data weighting or classification evaluation is frequently used in traditional health state evaluation methods, which makes it challenging to accurately portray the true state of the device. The MPdist-HMM-K-means health state evaluation method is presented in this paper. It integrates PV inverter environmental data with operational performance data, uses the MPdist algorithm to measure the similarity of time-series data under various conditions, builds a virtual health factor model of PV inverters, uses the Hidden Markov Model (HMM) to extract potential health states, and uses K-means clustering to classify and refine the hidden states. The results of the experiment demonstrate that the MPdist-HMM-K-means model can identify the process by which the instantaneous health state of PV inverters changes. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Research on AGADIA-based Resource Allocation Techniques for Dense D2D Communications 5

Research on AGADIA-based Resource Allocation Techniques for ...

引用

5th International Symposium on computer engineering and Intelligent Communications, ISCEIC 2024

作者： Zhou, Jialu Chen, Guifen Li, Xinzhou Zheng, Kaijin Changchun University of Science and Technology School of Electronic and Information Engineering Changchun China

ISBN: (纸本)9798331518677

The swift advancement of 5G technology has rendered device-to-device (D2D) communication methods a focal point of research. A resource allocation technique based on Adapt GADIA (AGADIA) is proposed to address the issue of low system throughput in a single-cell, user-dense D2D communication network. The approach initially develops a bidirectional interference model. Subsequently, it developed an adaptive iterative subchannel allocation mechanism for D2D communication in hybrid mode. Ultimately, it dynamically ascertains the appropriate allocation technique. A dedicated channel was established exclusively for edge D2D users within the cell to enhance communication quality for these users. The experimental findings indicate that the scheme described in this work enhances the overall transmission rate of the system while satisfying the communication requirements of cellular users. © 2024 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Research on multisensor fusion UAV sensing strategy based on forest information collection 3

Research on multisensor fusion UAV sensing strategy based on...

引用

3rd International Symposium on computer Applications and information Systems, ISCAIS 2024

作者： Du, Kang Song, Dalei School of Information Science and Engineering Shenyang University of Technology Shenyang110023 China

ISBN: (纸本)9781510681316

In today's information society, the importance of collecting data through multiple channels continues to increase. Among them, the use of drones to collect information on large-area forests is in line with the modern green development concept. In actual drone collection tasks, it is crucial to ensure the accuracy of collected data and the safe flight of the drone. In order to deal with these challenges, a multi-sensor fusion algorithm based on Bayesian estimation is proposed to overcome the problems of insufficient data accuracy of a single sensor and data duplication and noise caused by simple fusion of multiple sensors. At the same time, considering the actual need for path planning without a global map when flying over a large area in the woods, a local grid mapping strategy based on sliding windows is proposed, that is, a moving map is established with the drone body as the map center to ensure the maintenance of a fixed map size. This strategy effectively reduces the memory usage problem and is consistent with the actual scenario of large-scale outdoor flight. © 2024 SPIE.

关键词： Sensor data fusion

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：