2022 4th International Conference on Intelligent Information Processing (IIP)最新文献_第2页

A Chinese Entity-Relation Extraction Method Via Improved Machine Reading Comprehension 基于改进机器阅读理解的中文实体关系抽取方法

2022 4th International Conference on Intelligent Information Processing (IIP) Pub Date : 2022-10-01 DOI: 10.1109/iip57348.2022.00043

Tianci Shang, Baosong Deng, Tingsong Jiang

{"title":"A Chinese Entity-Relation Extraction Method Via Improved Machine Reading Comprehension","authors":"Tianci Shang, Baosong Deng, Tingsong Jiang","doi":"10.1109/iip57348.2022.00043","DOIUrl":"https://doi.org/10.1109/iip57348.2022.00043","url":null,"abstract":"As the downstream task of building a knowledge graph, Chinese entity relationship extraction from unstructured texts plays an important role in the field of natural language processing. There are two main ways for Chinese entity relation extraction: joint extraction method and pipeline extraction method. The joint extraction method outputs the relation triples contained in the texts directly in a row, which causes two problems: the lack of external knowledge and the nesting of entities. This article proposes a method to take the advantage of the similarity between the span extraction task and the information extraction task, and transforms entity relation extraction problem into a task similar to machine reading comprehension. This method first uses the Roberta pre-training model to obtain word representation with relation information, and then identifies entity pairs that may exists under per relation through a global pointer network, which outperforms better than the normal pointer network. By comparing different models’ performance on the same dataset, the results show the accuracy, recall and F1 scores of our method are higher than other methods, which proves the effectiveness of our method.","PeriodicalId":412907,"journal":{"name":"2022 4th International Conference on Intelligent Information Processing (IIP)","volume":"451 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116778457","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 Power Gateway Design Based on Edge Computing 基于边缘计算的电源网关设计研究

2022 4th International Conference on Intelligent Information Processing (IIP) Pub Date : 2022-10-01 DOI: 10.1109/iip57348.2022.00055

Huafeng Luo, Chaowen Dong, Hui Zhou, Liuwang Wang, Jun Yu, Jibo He

{"title":"Research on Power Gateway Design Based on Edge Computing","authors":"Huafeng Luo, Chaowen Dong, Hui Zhou, Liuwang Wang, Jun Yu, Jibo He","doi":"10.1109/iip57348.2022.00055","DOIUrl":"https://doi.org/10.1109/iip57348.2022.00055","url":null,"abstract":"With the help of Docker virtualization technology, this paper builds a special computing service model for the gateway. Based on the analysis of different applications of edge computing in the existing power industry, it comprehensively sorts out Python language and Docker technology to form a unique service system, and makes a reasonable design experiment on the specific related system displayed by the final edge computing network. The final test results show that the model designed in this paper can accurately obtain the final coordinate position information of grounding knife and the actual rotation angle of the knife. At the same time, it can also calculate the loss rate and defect rejection rate according to the final processing information of the gateway image, and then choose a more appropriate convolution kernel size, which is 5×5. It can successfully handle the logic confusion in Docker’s power gateway design process. Following this idea to complete the follow-up work can ensure the final realization of the design goal, that is, the optimal design of power gateway based on edge computing.","PeriodicalId":412907,"journal":{"name":"2022 4th International Conference on Intelligent Information Processing (IIP)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126966737","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

Negative review detection model based on LightGBM 基于LightGBM的差评检测模型

2022 4th International Conference on Intelligent Information Processing (IIP) Pub Date : 2022-10-01 DOI: 10.1109/iip57348.2022.00042

Chengying Zhu, Jingyi Yao, Gege Zhao, Sinuo Wang, Shasha Liu, Zhaoyang Liu

引用次数: 0

Unpaired Image-To-Image Translation Using Generative Adversarial Networks With Coordinate Attention Loss 基于坐标注意力损失的生成对抗网络的非配对图像到图像翻译

2022 4th International Conference on Intelligent Information Processing (IIP) Pub Date : 2022-10-01 DOI: 10.1109/IIP57348.2022.00021

Xiangdan Hou, Jinlin Song, Hongpu Liu

引用次数: 3

Research and Application of Fruit and Vegetable Recognition Based on Deep Learning 基于深度学习的果蔬识别研究与应用

2022 4th International Conference on Intelligent Information Processing (IIP) Pub Date : 2022-10-01 DOI: 10.1109/iip57348.2022.00023

Mali Sun, Chengwei Sun, XiaoHui Zhang

{"title":"Research and Application of Fruit and Vegetable Recognition Based on Deep Learning","authors":"Mali Sun, Chengwei Sun, XiaoHui Zhang","doi":"10.1109/iip57348.2022.00023","DOIUrl":"https://doi.org/10.1109/iip57348.2022.00023","url":null,"abstract":"Intelligent recognition is applied to fruit and vegetable classification, the main function is to make fruit and vegetable freshness and other information is mastered by the merchant to infer customer preference, which is convenient for personalized recommendation. Therefore, this paper studies the fruit and vegetable intelligent recognition method based on deep learning. The fruit and vegetable image is collected, the fruit and vegetable image is preprocessed, the fruit and vegetable recognition module is established, and the fruit and vegetable classification module is constructed to realize the fruit and vegetable intelligent classification and recognition method. The experimental results show that the design method can identify fruits and vegetables comprehensively and accurately, and has certain application value. The fruit and vegetable intelligent classification recognition method, realize fruit and vegetable classification recognition. The experimental results show that the design method can identify fruits and vegetables comprehensively and accurately, and has certain application value.","PeriodicalId":412907,"journal":{"name":"2022 4th International Conference on Intelligent Information Processing (IIP)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129057464","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 Credit Risk Prediction Based on Cart Classification Tree 基于购物车分类树的信用风险预测研究

2022 4th International Conference on Intelligent Information Processing (IIP) Pub Date : 2022-10-01 DOI: 10.1109/iip57348.2022.00058

Taoning Zhang, Rui Zhou

{"title":"Research on Credit Risk Prediction Based on Cart Classification Tree","authors":"Taoning Zhang, Rui Zhou","doi":"10.1109/iip57348.2022.00058","DOIUrl":"https://doi.org/10.1109/iip57348.2022.00058","url":null,"abstract":"The rapid development of domestic Internet technology has made the domestic Internet + industry model a great success. Various traditional industries have produced some new industries after combining Internet technology. Since the beginning of the 21 st century, the connection between the Internet and the financial industry has become increasingly close, which has spawned a new financial model of Internet finance. P2P platform is one of them. Because its lending process is simple and convenient, and there is no strict loan application standard like traditional banks, it has been favored by many small and mediumsized enterprises. Various P2P platforms have mushroomed. However, the rapid development of P2P platforms has also brought security problems that cannot be ignored. This is largely due to the lack of adequate credit evaluation of borrowers before loans or the lack of accuracy of credit evaluation methods. Therefore, the accurate credit evaluation of the relevant lending data of the borrower has become the entry point for reducing the risk of borrowing. Considering that machine learning has been very mature in processing and analyzing data, and has many successful experiences, the CART classification tree model has the advantages of good effect, easy to understand, and less affected by outliers and missing values. It can also find fields that have important warning effects on the risk of borrowing, so this experiment uses the CART classification tree to train the data. Considering that only a single CART classification tree is used to analyze data, there is still room for improvement in analysis accuracy, so this model is optimized to use an Ensemble model to analyze data. The results show that a single CART classification tree model has high accuracy in credit evaluation of borrowers.","PeriodicalId":412907,"journal":{"name":"2022 4th International Conference on Intelligent Information Processing (IIP)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131110906","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

Parameter Optimization and Its Application of Support Vector Machines Based on Improved Particle Swarm Optimization Algorithm 基于改进粒子群优化算法的支持向量机参数优化及其应用

2022 4th International Conference on Intelligent Information Processing (IIP) Pub Date : 2022-10-01 DOI: 10.1109/iip57348.2022.00050

Lu Zhou, Yu-qing Cui

引用次数: 0

An adaptive CFAR threshold determination algorithm based on IR-UWB radar 基于IR-UWB雷达的自适应CFAR阈值确定算法

2022 4th International Conference on Intelligent Information Processing (IIP) Pub Date : 2022-10-01 DOI: 10.1109/IIP57348.2022.00061

Jinlong Zhang, Xiao-chao Dang, Le Wang

{"title":"An adaptive CFAR threshold determination algorithm based on IR-UWB radar","authors":"Jinlong Zhang, Xiao-chao Dang, Le Wang","doi":"10.1109/IIP57348.2022.00061","DOIUrl":"https://doi.org/10.1109/IIP57348.2022.00061","url":null,"abstract":"The problem of inaccurate threshold setting on IRUWB (Impulse Radio-Ultra Wide Band) radar echo signals due to small or large subject movements by the conventional CFAR (Constant False Alarm Rate) algorithm is addressed. In this paper, an adaptive CFAR-based threshold determination algorithm is proposed. The acquired IR-UWB radar echo signal is passed through setting three different MTI filters to obtain three sets of CFAR thresholds. These three values are logically operated to derive the final CFAR thresholds for the test target. Next, the original radar echo signal is passed through the operator of the leakage detection rate to obtain the final MDR value of the tested target. The thresholds are determined by combining the noise signal-based thresholds with the target signal-based thresholds according to the designed weights. Adjusting the designed weights allows the final signal thresholds to be determined based on the critical intersection points. The algorithm proposed in this paper can set the thresholds adaptively for different test target states (e.g., stationary, slight motion, and large motion). The experimental results show that the threshold determination algorithm proposed in this paper is effective and easy to implement.","PeriodicalId":412907,"journal":{"name":"2022 4th International Conference on Intelligent Information Processing (IIP)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126663323","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

Multi-class Target Detection for Optical Remote Sensing Images Based on Improved RetinaNet 基于改进视网膜网的光学遥感图像多类目标检测

2022 4th International Conference on Intelligent Information Processing (IIP) Pub Date : 2022-10-01 DOI: 10.1109/iip57348.2022.00025

Lingzhuo Kong, Lin Li, Shengye Xu, Jianhong Han

引用次数: 0

Design of remote interactive system based on Internet of Things 基于物联网的远程交互系统设计

2022 4th International Conference on Intelligent Information Processing (IIP) Pub Date : 2022-10-01 DOI: 10.1109/iip57348.2022.00073

Zhen Chen, Jianfeng Wang, Cheng Zhang, Zhao Wang

{"title":"Design of remote interactive system based on Internet of Things","authors":"Zhen Chen, Jianfeng Wang, Cheng Zhang, Zhao Wang","doi":"10.1109/iip57348.2022.00073","DOIUrl":"https://doi.org/10.1109/iip57348.2022.00073","url":null,"abstract":"With the progress of science and technology and the continuous improvement of people’s living standards, communication equipment has brought people closer to each other. At the same time, people have higher requirements for the way of interaction in different places. Based on the rapid development of Internet of Things technology, this paper designs a set of remote interactive system using Alibaba Cloud Internet of Things platform.This system is composed of STM32F103C8T6, ESP32-CAM and ESP8266 (CP2102). STM32 is fixed in the interactive area, and ESP32-CAM and ESP8266 (CP2101) are set on the movable trolley. Peripheral sensors mainly STM32 use DHTII temperature and humidity sensor, BH1750 light brightness sensor and capacitive soil humidity detection sensor. The ESP8266 microcontroller controls the trolley movement and the four degrees of freedom rotation of the camera. The ESP32-CAM microcontroller mounted on the trolley can transmit images to users in real time. This system is economical, practical and stable, so that users can better experience the happiness brought by the interaction between different places, and can achieve good results in practical applications. It has certain production value and broad application prospects.","PeriodicalId":412907,"journal":{"name":"2022 4th International Conference on Intelligent Information Processing (IIP)","volume":"2017 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127545143","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