Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering最新文献

The Impact of Learning Rate Decay and Periodical Learning Rate Restart on Artificial Neural Network 学习率衰减和周期学习率重启对人工神经网络的影响

Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering Pub Date : 2021-01-15 DOI: 10.1145/3460268.3460270

Yimin Ding

引用次数: 9

Learning-based Point Cloud Registration: A Short Review and Evaluation 基于学习的点云配准:简要回顾与评价

Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering Pub Date : 2021-01-15 DOI: 10.1145/3460268.3460273

Weixuan Tang, Danping Zou, Ping Li

引用次数: 3

Research on the application of artificial intelligence technology in the development of sports teaching video compression algorithm 人工智能技术在体育教学视频压缩算法开发中的应用研究

Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering Pub Date : 2021-01-15 DOI: 10.1145/3460268.3460271

Yibo Dai

引用次数: 2

DQ-DPS Data Partition Strategy Based on Distributed Machine Learning 基于分布式机器学习的DQ-DPS数据分区策略

Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering Pub Date : 2021-01-15 DOI: 10.1145/3460268.3460272

Jiaming Wu, Zunhao Liu, Bowen Yang

{"title":"DQ-DPS Data Partition Strategy Based on Distributed Machine Learning","authors":"Jiaming Wu, Zunhao Liu, Bowen Yang","doi":"10.1145/3460268.3460272","DOIUrl":"https://doi.org/10.1145/3460268.3460272","url":null,"abstract":"With the expansion of the data scale, machine learning develops from centralized to distributed. Generally, distributed machine learning uses parameter server architecture to train in synchronous mode. At this time, data samples are statically and symmetrically allocated to each computing node according to the batch size. Each worker trains synchronously and iterates until the model converges. However, due to the different number of resources at each compute node in a mixed-load scenario, the traditional data partition strategy is usually to statically configure batch size parameters or require manual setting of batch size parameters, which makes the computational efficiency of distributed machine learning model training operations inefficient, and the data adjustment for each node will have an impact on the accuracy of the model. To solve this problem, on the premise of ensuring the accuracy of the distributed machine learning model training task, this paper proposes an optimal configuration scheme for a batch size of distributed machine learning model training task data: a data partition strategy based on distributed machine learning (DQ-DPS). DQ-DPS solves the problem of low computational efficiency caused by static data partitioning, improves the computational efficiency of distributed machine learning tasks, and ensures the accuracy of distributed machine learning training model. Through a large number of experiments, we have proved the effectiveness of DQ-DPS. Compared with the traditional data partition strategy, DQ-DPS improves the computing efficiency of each training round by 38%.","PeriodicalId":215905,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122640222","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

An LSTM Approach for Predicting the Short-time Passenger Flow of Urban Bus 城市公交短时客流预测的LSTM方法

Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering Pub Date : 2021-01-15 DOI: 10.1145/3460268.3460274

Yingying Xu, Kezhong Jin

引用次数: 2

An Exploration for Generative Adversarial Networks Via Adding A Screening Model 基于添加筛选模型的生成对抗网络的探索

Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering Pub Date : 2021-01-15 DOI: 10.1145/3460268.3460269

Kangle Sun

引用次数: 0

Recursive relocation of lost intelligent agent by Aitkin acceleration method and extended Kalman filtering algorithm 利用艾特金加速法和扩展卡尔曼滤波算法递归重新定位丢失智能体

Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering Pub Date : 2021-01-15 DOI: 10.1145/3460268.3460282

Lei Sun, Xiao Yang, Guizhen Wang

引用次数: 0

CPDD: A Cascaded-Parallel Defect Detector with Application to Intelligent Inspection in Substation 级联并联缺陷检测仪在变电站智能检测中的应用

Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering Pub Date : 2021-01-15 DOI: 10.1145/3460268.3460277

Han Sun, Jing Wang, Kunlun Li, Qingwei Zhang

{"title":"CPDD: A Cascaded-Parallel Defect Detector with Application to Intelligent Inspection in Substation","authors":"Han Sun, Jing Wang, Kunlun Li, Qingwei Zhang","doi":"10.1145/3460268.3460277","DOIUrl":"https://doi.org/10.1145/3460268.3460277","url":null,"abstract":"The intelligent inspection is a detection problem that aims to recognize abnormalities in substations. Defects acquired by various devices with small size, truncation, and similar appearance are easily confused, which biases the evaluation metrics. How to correctly explore the relationships between equipment and defects, and fully utilize results from different models is critical for this task. In this work, we propose a novel solution to these problems based on the cascaded-parallel defect detection (CPDD) algorithm. Specifically, it consists of two key components: (1) The cascaded model aims to mine the detailed relationships and filter out the illogical bounding boxes. This way can reduce the miss detection rate. (2) The parallel model is to fuse results from the mentioned cascaded model. It can utilize the information from these two-stage models and promote the detectable rate. Extensive empirical results on the dataset, acquired by our designed inspection system in different voltage-level substations, demonstrate the superiority of our proposed method. It can achieve state-of-the-art performance.","PeriodicalId":215905,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering","volume":"386 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127465812","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

A Novel UAV Aerial Vehicle Detection Method Based on Attention Mechanism and Multi-scale Feature Cross Fusion 一种基于注意机制和多尺度特征交叉融合的无人机飞行器检测方法

Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering Pub Date : 2021-01-15 DOI: 10.1145/3460268.3460276

Zhigang Hou, Jin Yan, Bo Yang, Zhiming Ding

{"title":"A Novel UAV Aerial Vehicle Detection Method Based on Attention Mechanism and Multi-scale Feature Cross Fusion","authors":"Zhigang Hou, Jin Yan, Bo Yang, Zhiming Ding","doi":"10.1145/3460268.3460276","DOIUrl":"https://doi.org/10.1145/3460268.3460276","url":null,"abstract":"With the rapid development of artificial intelligence science, more and more researchers try to use deep learning to train neural networks and have achieved great success in object detection. Vehicle detection based on UAV image is a special field of object detection. Due to the low resolution of the vehicle object, complex background, and less image information, it is challenging to extract robust visual and spatial features from the depth network and accurately locate the object in complex scenes. In this paper, combining the characteristics of vehicles in aerial images, we design a novel feature pyramid network called channel-spatial attention fused feature pyramid network (CSF-FPN) with Faster R-CNN as the basic framework. In CSF-FPN, a hybrid attention mechanism and feature cross-fusion module are introduced, so that feature maps can be generated with enhanced spatial and channel interdependence to extract richer semantic information. After our CSF-FPN is integrated into the Faster R-CNN network, the detection performance of small objects is greatly improved. The experimental results based on the VEDIA Dataset showed that the proposed framework could effectively detect the vehicle in large scene azimuth. Compared with the existing advanced methods, mAP and F1-score are improved.","PeriodicalId":215905,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115586130","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: 4

The Intelligent Agent NLP-based Customer Service System 基于nlp的智能代理客户服务系统

Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering Pub Date : 2021-01-15 DOI: 10.1145/3460268.3460275

C. Huang

{"title":"The Intelligent Agent NLP-based Customer Service System","authors":"C. Huang","doi":"10.1145/3460268.3460275","DOIUrl":"https://doi.org/10.1145/3460268.3460275","url":null,"abstract":"In Nowadays, communication has been more and more important in our lives. It is difficult for us to complete many things without it. With the support of the developing technology, communication is able to become faster and easier. The human-to-machine communication is a creative application used in field of research and industry. To improve the interaction between human and machine, a communication system is specially designed. The technology of natural language processing is implemented in the system to handle the understanding and generation of the chatting language. For higher efficiency, the system is enhanced by designing in the multi-agent system. Which let agents deal with the detailed tasks in the process of NLP by interacting and integrating them together. The system is based on sending and receiving so that it is able to communicate asking question and responding answer. Provide a textbook to the Chatbot, it is capable to understanding the content of book. And then serve as a teaching assistant to help student solve their problems by answering their questions. In this thesis, we will reveal the design and implementation of different parts in the communication system. Which consists of natural language processing system, multi-agent system, user interface (Model-View-Controller Frame), and knowledge base. System is implemented by Java programme language.","PeriodicalId":215905,"journal":{"name":"Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123397111","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: 2