2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)最新文献_第10页

Cross-Granularity Fusion Network for Fine-Grained Image Classification 面向细粒度图像分类的跨粒度融合网络

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212436

Wenjin Pang, Wei Song

{"title":"Cross-Granularity Fusion Network for Fine-Grained Image Classification","authors":"Wenjin Pang, Wei Song","doi":"10.1109/AINIT59027.2023.10212436","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212436","url":null,"abstract":"Fine-grained image classification (FGIC) aims to identify subtle visual differences among subcategories, which is challenging due to the small inter-class variances. Existing methods recognize subcategories mainly by locating discriminative parts which exists in the regions with high responses in deep feature maps. However, the regions with high responses in deep feature maps correspond to large receptive fields in the input image, leading to the result that subtle visual differences among subcategories cannot be captured precisely. In this paper we propose a novel Cross-Granularity Fusion Network (CGFN), which excavates subtle yet discriminative granularity features within each part and captures potential interactions among granularity features to build powerful part feature representations. The CGFN consists of two modules: First, the Multi-Granularity Proposal (MGP) module locates diverse and discriminative parts and focuses context-complementary granularities across different hierarchies within each part. Second, a Cross-Granularity Fusion (CGF) module is developed by fusing granularity features to acquire robust part features for the final classification. We conduct a series of experiments on publicly available datasets i.e., CUB-200-2011, Stanford Cars and FGVC-Aircraft datasets and experimental results demonstrate that the CGFN achieves state-of-the-art performance.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130821699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design study of a rotorless Unmanned Aerial Vehicle 一种无旋翼无人机的设计研究

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10210723

Hongxia Xu, Liang Jiang, Zhongwen Cao, Xiangwen Bao

引用次数: 0

Research on GIS-Based Open Simulation System for Visualization of Complex Underwater Environment 基于gis的复杂水下环境可视化开放仿真系统研究

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212727

Datian Tao, Xuedong Liu, Tingchao Shi, Yi Zhong, Yi Han

引用次数: 0

Double encryption of digital grid edge cloud data in complex dynamic networks 复杂动态网络中数字网格边缘云数据的双重加密

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212441

Xiang Huang, Yuxu Chen, Liming Wan, Xichi Zeng, Guopeng Liang

引用次数: 0

Autonomous Path Planning Logistics Sorting Robot Experimental Teaching Platform Based on Aruco Marker 基于Aruco Marker的自主路径规划物流分拣机器人实验教学平台

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212971

Kai Zhao, Xiaolin Song, Y. Xu, Ruiheng Mao, Sheng Fan, Jia-bo Zhang

{"title":"Autonomous Path Planning Logistics Sorting Robot Experimental Teaching Platform Based on Aruco Marker","authors":"Kai Zhao, Xiaolin Song, Y. Xu, Ruiheng Mao, Sheng Fan, Jia-bo Zhang","doi":"10.1109/AINIT59027.2023.10212971","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212971","url":null,"abstract":"In order to optimize the teaching content of “Engineering Training II” for Automation Specialty, the curriculum teaching system has been reshaped with project-based teaching as the center based on the characteristics of the discipline. We have designed a logistics robot experimental teaching platform that combines intelligent vehicles and robotic arms based on ARUCO Marker positioning. The system uses STM32 as the main control chip, Quanzhi H6 as the computing power platform, L298N and DC deceleration motor as running drivers, and the Yuejiang robotic arm as the cargo grabbing device. At the same time, combining ARUCO Marker recognition, Dijkstra optimal path planning, and incremental PID as intelligent algorithms, it achieves functions such as navigation control, cargo handling, and fixed point stacking for the logistics sorting robot system. The experimental results show that the system has fast recognition speed, high positioning accuracy, low price, and is easy to expand. It can effectively improve students' ability to comprehensively apply basic theoretical knowledge to solve practical problems and enhance their engineering literacy.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124865994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Balanced Overall and Local: Improving Image Captioning with Enhanced Transformer Model 平衡整体和局部:改进图像字幕与增强变压器模型

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212804

Haotian Xian, Baoyi Guo, Youyu Zhou

引用次数: 0

Research on positioning and navigation of medical robot based on RGB-D visual SLAM 基于RGB-D视觉SLAM的医疗机器人定位导航研究

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212975

Pei-fa Jia

引用次数: 0

Distracted Driver Detection with MobileVGG Network 基于MobileVGG网络的分心驾驶员检测

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212841

Yueying Zhu

引用次数: 0

Research on reinforced corrosion monitoring system based on Multi-sensor data fusion and wireless sensor network 基于多传感器数据融合和无线传感器网络的钢筋腐蚀监测系统研究

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212580

A. Yu, Ziyang Shang, Hongbing Sun, Hao Kuang

{"title":"Research on reinforced corrosion monitoring system based on Multi-sensor data fusion and wireless sensor network","authors":"A. Yu, Ziyang Shang, Hongbing Sun, Hao Kuang","doi":"10.1109/AINIT59027.2023.10212580","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212580","url":null,"abstract":"This paper applies multi-sensor data fusion technology and wireless sensor network (WSN) to monitor and predict steel corrosion parameters in real-time. To overcome the difficulties and low accuracy in identifying rebar corrosion, this study selected five parameters for data fusion, including chloride ion concentration, pH value, rebar corrosion potential, and internal temperature and humidity of concrete. A three-level data fusion structure is designed with corresponding fusion algorithms chosen for each level. The primary fusion is completed through data cleaning and median average filtering methods, followed by using adaptive weighting algorithms to fuse sensor data of the same type to obtain parameter characteristics of the region. Finally, an improved PSO-BP neural network fuses the data from the previous level of fusion to achieve prediction of steel corrosion. Experimental results show that the steel corrosion monitoring system based on multi-sensor data fusion technology and WSN has higher reliability and accuracy compared to traditional corrosion monitoring methods.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114668347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on the Robustness of Degree-Fitness-Distance Evolutionary Networks Based on Response Surface Methodology 基于响应面方法的度-适应度-距离进化网络鲁棒性研究

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212689

Weisen Deng, Jizhuang Hui, Kai Ding, Haixin Zhang, Shaowei Zhi

{"title":"Research on the Robustness of Degree-Fitness-Distance Evolutionary Networks Based on Response Surface Methodology","authors":"Weisen Deng, Jizhuang Hui, Kai Ding, Haixin Zhang, Shaowei Zhi","doi":"10.1109/AINIT59027.2023.10212689","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212689","url":null,"abstract":"This paper introduces a Degree-Fitness-Distance (DFD) evolutionary network, utilizing Response Surface Methodology to investigate the impact of degree strength, fitness strength, distance strength, and their interactions on the robustness of the DFD network. The regression equation was determined, followed by a variance analysis of different factors affecting the target response. The results show that the influence of different factors on the size of the largest connected component and the overall efficiency of the network are in the following order: degree strength > fitness strength > distance strength. When degree strength is 1, fitness strength is 2, and distance strength is 3, the size of the largest connected component of the network and the overall efficiency reach their peak values, respectively at 56.57% and 10.15%. Multi-objective optimization was performed on the DFD network; when degree strength is 1, fitness strength is 1, and distance strength is 3, the predicted size of the largest connected component is 58.39%, and the overall efficiency is 10.37%. These figures deviate by approximately 5% from the actual values, which demonstrates that the predictive model possesses high accuracy and reliability.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"170 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114396576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0