Pub Date : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00027
Xingzhe Sun, Shanna Zhuang, Zhengyou Wang
Person re-identification is a major application of computer vision in reality. Since the data obtained by monitoring in real life is often in video format, and the walking poses of pedestrians are different, in addition to the appearance of pedestrians, how to obtain the motion features of pedestrians, is extremely important for video-based person re-identification. Therefore, for the temporal information of the video, we propose a Long-short Temporal Information Fusion (LSTIF) network. We aggregate temporal information from two perspectives, short-term features containing detailed information and long-term features containing global information. Simultaneously, in order to reduce the amount of calculation, this network also uses non-local blocks, and extend the outpu feature map to the same size as the input, which is convenient for calculation. This paper verifies the effectiveness of our method on two commonly used datasets iLIDS-VID and DukeMTMC-VideoReID.
{"title":"LSTIF:Long-short Temporal Information Fusion Architecture for Video-based Person Re-identification","authors":"Xingzhe Sun, Shanna Zhuang, Zhengyou Wang","doi":"10.1109/ICCEAI52939.2021.00027","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00027","url":null,"abstract":"Person re-identification is a major application of computer vision in reality. Since the data obtained by monitoring in real life is often in video format, and the walking poses of pedestrians are different, in addition to the appearance of pedestrians, how to obtain the motion features of pedestrians, is extremely important for video-based person re-identification. Therefore, for the temporal information of the video, we propose a Long-short Temporal Information Fusion (LSTIF) network. We aggregate temporal information from two perspectives, short-term features containing detailed information and long-term features containing global information. Simultaneously, in order to reduce the amount of calculation, this network also uses non-local blocks, and extend the outpu feature map to the same size as the input, which is convenient for calculation. This paper verifies the effectiveness of our method on two commonly used datasets iLIDS-VID and DukeMTMC-VideoReID.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127335914","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}
Pub Date : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00004
Junghwan Lee, Longda Wang
Software complexity is increased in automotive systems because many software functions are required for autonomous driving, electrified vehicles, and connected cars. In addition, autonomous driving requires centralized software that generally decreases evolvability with many connections. Thus, the automotive industry adopted the microservice architecture within the service-oriented architecture (SOA), which was already being used in distributed computing environments in the information and communication technology (ICT) industry. However, the software characteristics of an automotive system are different from those of an ICT system. Automotive software generally fulfills safety and real-time requirements that are not required in ICT software. Another challenge is integrating electric control units (ECUs) because software platforms supporting SOA require relatively high computational power and network bandwidth, which increases ECU cost. Thus, the deployment of software functions must be considered before integrating ECUs to find an optimal design solution for evolvability, dependability, real-time performance, cost, etc. However, many OEMs integrate ECUs based on deploying vehicular features without software architecture. It causes optimality problems during integrating ECUs. We propose component-based sensor-process-actuator architectural style for high-level architecture to handle quality attributes. Software architecture for an autonomous electrified vehicle will be presented with the proposed architectural style. The architecture is used to deploy software components and integrated ECUs with empirical quantitative analysis. Four design patterns for dependability with the architectural style will also be introduced.
{"title":"A Method for Designing and Analyzing Automotive Software Architecture: A Case Study for an Autonomous Electric Vehicle","authors":"Junghwan Lee, Longda Wang","doi":"10.1109/ICCEAI52939.2021.00004","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00004","url":null,"abstract":"Software complexity is increased in automotive systems because many software functions are required for autonomous driving, electrified vehicles, and connected cars. In addition, autonomous driving requires centralized software that generally decreases evolvability with many connections. Thus, the automotive industry adopted the microservice architecture within the service-oriented architecture (SOA), which was already being used in distributed computing environments in the information and communication technology (ICT) industry. However, the software characteristics of an automotive system are different from those of an ICT system. Automotive software generally fulfills safety and real-time requirements that are not required in ICT software. Another challenge is integrating electric control units (ECUs) because software platforms supporting SOA require relatively high computational power and network bandwidth, which increases ECU cost. Thus, the deployment of software functions must be considered before integrating ECUs to find an optimal design solution for evolvability, dependability, real-time performance, cost, etc. However, many OEMs integrate ECUs based on deploying vehicular features without software architecture. It causes optimality problems during integrating ECUs. We propose component-based sensor-process-actuator architectural style for high-level architecture to handle quality attributes. Software architecture for an autonomous electrified vehicle will be presented with the proposed architectural style. The architecture is used to deploy software components and integrated ECUs with empirical quantitative analysis. Four design patterns for dependability with the architectural style will also be introduced.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125784653","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}
Pub Date : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00032
Haohan Hu, Hongbo Guo, Li Zhang, Wanlong Liu, Ning Li, Yan Li
According to the new power system reform, the power sales market has become an emerging industry in the power industry. For a single high-power user, more and more detailed energy consumption analysis is required. At present, the in-depth analysis of consumer energy by various market entities has produced certain results, but rigorous academic research is scarce. According to the actual situation of the electricity sales market, this article applies the relevant principles of machine learning to electricity users. Combine the collected user power big data to extract various user energy characteristics in multiple dimensions. Use a variety of load forecasting algorithms to simulate user portraits and apply them to feature engineering. The use of non-dimensional, binarization, dimensionality reduction and other methods has improved the main influencing factors of user energy consumption. According to the energy distribution diagram, a class of load forecasting methods suitable for current electricity market entities expanded. Finally, an example used to verify the effectiveness of the research results. The load forecasting of users through the forecasting algorithm shows that the average error result is 2.65%, and the error of the overall forecast result is generally 2% to 7%. Ensure the reliability of the forecasting method.
{"title":"Research of User Power Profile and Load Forecast Based on Power Big Data","authors":"Haohan Hu, Hongbo Guo, Li Zhang, Wanlong Liu, Ning Li, Yan Li","doi":"10.1109/ICCEAI52939.2021.00032","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00032","url":null,"abstract":"According to the new power system reform, the power sales market has become an emerging industry in the power industry. For a single high-power user, more and more detailed energy consumption analysis is required. At present, the in-depth analysis of consumer energy by various market entities has produced certain results, but rigorous academic research is scarce. According to the actual situation of the electricity sales market, this article applies the relevant principles of machine learning to electricity users. Combine the collected user power big data to extract various user energy characteristics in multiple dimensions. Use a variety of load forecasting algorithms to simulate user portraits and apply them to feature engineering. The use of non-dimensional, binarization, dimensionality reduction and other methods has improved the main influencing factors of user energy consumption. According to the energy distribution diagram, a class of load forecasting methods suitable for current electricity market entities expanded. Finally, an example used to verify the effectiveness of the research results. The load forecasting of users through the forecasting algorithm shows that the average error result is 2.65%, and the error of the overall forecast result is generally 2% to 7%. Ensure the reliability of the forecasting method.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122066621","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}
Pub Date : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00059
Feng Jun, Dong Zhiyi, Shi Yichen, Hu Jingjing
Different datasets have more apparent differences due to lighting, background and image quality issues, which makes the generalization problem of face anti-spoofing detection more prominent. A domain adaptive method for face spoofing detection based on ResADDA model is proposed, which adopts the ResNet34 network to extract deep convolutional features, and draws on the GAN network idea to use adversarial training by alternately optimizing the domain discriminator and feature encoder, adjusting the parameters of the target domain feature encoder and reducing the difference of feature distribution between the target domain and the source domain to improve the detection ability of the model on the target domain. Crossover experiments on the publicly available dataset CASIA-FASD and Replay-Attack are conducted to verify the effectiveness of the ResADDA model which is superior to other methods.
{"title":"Domain Adaptation Based on ResADDA Model for Face Anti-Spoofing Detection","authors":"Feng Jun, Dong Zhiyi, Shi Yichen, Hu Jingjing","doi":"10.1109/ICCEAI52939.2021.00059","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00059","url":null,"abstract":"Different datasets have more apparent differences due to lighting, background and image quality issues, which makes the generalization problem of face anti-spoofing detection more prominent. A domain adaptive method for face spoofing detection based on ResADDA model is proposed, which adopts the ResNet34 network to extract deep convolutional features, and draws on the GAN network idea to use adversarial training by alternately optimizing the domain discriminator and feature encoder, adjusting the parameters of the target domain feature encoder and reducing the difference of feature distribution between the target domain and the source domain to improve the detection ability of the model on the target domain. Crossover experiments on the publicly available dataset CASIA-FASD and Replay-Attack are conducted to verify the effectiveness of the ResADDA model which is superior to other methods.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129833318","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}
Compared with other biometrics, biometric based on gait features can be collected under long-distance and contactless conditions to achieve identity recognition under contactless and long-distance conditions. At present, gait recognition methods are still sensitive to illumination and background changes and are susceptible to noise in feature extraction, the gait template approach suffers from inflexibility and neglect of timing information in recognition tasks. In this paper, Mask R-CNN, a deep learning detection and segmentation model, is used to extract gait silhouettes and achieve effective and real-time segmentation of human gait silhouettes. We propose an improved GaitSet algorithm with a vertical-horizontal pyramid pooling module, and introduce a Softmax loss function for joint training to address the problem that the triplet loss function does not consider intra-class compactness. The proposed algorithm achieves the current more advanced recognition performance on the gait dataset CASIAB, and for gait recognition under jacket walking conditions, the improvement in accuracy is more obvious.
{"title":"V-HPM Based Gait Recognition","authors":"Yunpeng Zhang, Zhengyou Wang, Xiangpan Zhang, Shanna Zhuang","doi":"10.1109/ICCEAI52939.2021.00089","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00089","url":null,"abstract":"Compared with other biometrics, biometric based on gait features can be collected under long-distance and contactless conditions to achieve identity recognition under contactless and long-distance conditions. At present, gait recognition methods are still sensitive to illumination and background changes and are susceptible to noise in feature extraction, the gait template approach suffers from inflexibility and neglect of timing information in recognition tasks. In this paper, Mask R-CNN, a deep learning detection and segmentation model, is used to extract gait silhouettes and achieve effective and real-time segmentation of human gait silhouettes. We propose an improved GaitSet algorithm with a vertical-horizontal pyramid pooling module, and introduce a Softmax loss function for joint training to address the problem that the triplet loss function does not consider intra-class compactness. The proposed algorithm achieves the current more advanced recognition performance on the gait dataset CASIAB, and for gait recognition under jacket walking conditions, the improvement in accuracy is more obvious.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128592906","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}
The monitoring of harmful algae is extremely important for early warning of red tide and protecting water ecological resources. Addressing the problem that manual algae identification is time-consuming, expensive and requires professionals with substantial experience, multiple Convolutional Neural Networks (CNNs) and deep learning based on transfer learning were used to achieve automatic classification of various algae and identification of harmful algae. In this paper, 11 species of harmful algae and 31 species of harmless algae were collected as the input dataset, and transferred to five fine-tuned classical CNN classification models of AlexNet, VGG16, GoogLeNet, ResNet50, and MobileNetV2 for comparison experiments, and finally, the GoogLeN et model reached a relatively higher recognition accuracy. In addition, a new harmful algae identification method was proposed combining the recognition results of five models, and the recall rate is 98.8%. The experiments of this work show that combing multiple CNN s can realize the recognition of harmful algae, which method plays a key role in the preliminary screening of harmful algae.
{"title":"Automatic Recognition of Harmful Algae Images Using Multiple CNN s","authors":"Mengyu Yang, Wensi Wang, Qiang Gao, Liting Zhang, Yanping Ji, Shuqin Geng","doi":"10.1109/ICCEAI52939.2021.00055","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00055","url":null,"abstract":"The monitoring of harmful algae is extremely important for early warning of red tide and protecting water ecological resources. Addressing the problem that manual algae identification is time-consuming, expensive and requires professionals with substantial experience, multiple Convolutional Neural Networks (CNNs) and deep learning based on transfer learning were used to achieve automatic classification of various algae and identification of harmful algae. In this paper, 11 species of harmful algae and 31 species of harmless algae were collected as the input dataset, and transferred to five fine-tuned classical CNN classification models of AlexNet, VGG16, GoogLeNet, ResNet50, and MobileNetV2 for comparison experiments, and finally, the GoogLeN et model reached a relatively higher recognition accuracy. In addition, a new harmful algae identification method was proposed combining the recognition results of five models, and the recall rate is 98.8%. The experiments of this work show that combing multiple CNN s can realize the recognition of harmful algae, which method plays a key role in the preliminary screening of harmful algae.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130665740","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}
Pub Date : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00050
Xiaoding Lu, Zhengyou Wang, Shanna Zhuang
With the rapid development of deep learning, the accuracy of models is getting higher and higher, but it is difficult to balance the interpretability and accuracy of deep network. This paper proposes a modular aggregation-attention module, which has the same topological structure. After channel grouping, channel level information is exchanged through channel level attention, and finally, a new NDF variant CA-NEXT is obtained by combining with NDF. We provide detailed empirical data and the resulting model accuracy can improve the accuracy.
{"title":"Age Estimation Using Channel Aggregation Transform Based On Deep Neural Network","authors":"Xiaoding Lu, Zhengyou Wang, Shanna Zhuang","doi":"10.1109/ICCEAI52939.2021.00050","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00050","url":null,"abstract":"With the rapid development of deep learning, the accuracy of models is getting higher and higher, but it is difficult to balance the interpretability and accuracy of deep network. This paper proposes a modular aggregation-attention module, which has the same topological structure. After channel grouping, channel level information is exchanged through channel level attention, and finally, a new NDF variant CA-NEXT is obtained by combining with NDF. We provide detailed empirical data and the resulting model accuracy can improve the accuracy.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116497015","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}
Pub Date : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00001
Yuan-yuan Zhou, Xiaoyan Hu
We propose a context-based two-stage 3D human pose estimation network structure. The first stage is to obtain the 2D human pose and 2D key-points in the video stream data, this stage is crucial to the subsequent work and the entire process. By analyzing the limitations and shortcomings of existing models, we proposed a context-based human pose estimation network structure, and incorporate the BILSTM structure into the pose machine method. In our model, Invisible key-points can be jointly predicted by human pose in current frame and context information. Through quantification and visualization experiments, we have proved that it has a good mitigating effect on the invisible key points caused by occlusion and the wrong linking of human key-points. In the second stage, the 3D human pose is obtained through sparse representation and 3D reconstruction. The experimental results show that the method we designed has higher accuracy than the existing human body pose estimation method of video streaming, and has better performance in the occlusion problem.
{"title":"3D Human Pose Estimation: Using Context Information in Monocular Video","authors":"Yuan-yuan Zhou, Xiaoyan Hu","doi":"10.1109/ICCEAI52939.2021.00001","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00001","url":null,"abstract":"We propose a context-based two-stage 3D human pose estimation network structure. The first stage is to obtain the 2D human pose and 2D key-points in the video stream data, this stage is crucial to the subsequent work and the entire process. By analyzing the limitations and shortcomings of existing models, we proposed a context-based human pose estimation network structure, and incorporate the BILSTM structure into the pose machine method. In our model, Invisible key-points can be jointly predicted by human pose in current frame and context information. Through quantification and visualization experiments, we have proved that it has a good mitigating effect on the invisible key points caused by occlusion and the wrong linking of human key-points. In the second stage, the 3D human pose is obtained through sparse representation and 3D reconstruction. The experimental results show that the method we designed has higher accuracy than the existing human body pose estimation method of video streaming, and has better performance in the occlusion problem.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114759868","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}
Pub Date : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00012
Ying Fang, Shuai Wang, Hai Tan, Xin Zhang, Jun Zhang
With the continuous development of big data, the increase speed of hardware expansion used for HDFS has been far behind the volume of big data. As a data redundancy strategy, the traditional data replication strategy has been gradually replaced by Erasure Code due to its smaller redundancy rate and storage overhead. However, compared with replicas, Erasure Code needs to read a certain amount of data blocks during the process of data recovery, resulting in a large amount overhead of I/O and network. Based on the RS algorithm, a new CLRC algorithm is proposed to optimize the locality of RS algorithm by grouping RS coded blocks and generating local check blocks. Evaluations show that the algorithm can reduce about 61% bandwidth and I/O consumption during the process of data recovery when a single block is damaged. What's more, the cost of decoding time is only 59% of RS algorithm.
{"title":"CLRC: a New Erasure Code Localization Algorithm for HDFS","authors":"Ying Fang, Shuai Wang, Hai Tan, Xin Zhang, Jun Zhang","doi":"10.1109/ICCEAI52939.2021.00012","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00012","url":null,"abstract":"With the continuous development of big data, the increase speed of hardware expansion used for HDFS has been far behind the volume of big data. As a data redundancy strategy, the traditional data replication strategy has been gradually replaced by Erasure Code due to its smaller redundancy rate and storage overhead. However, compared with replicas, Erasure Code needs to read a certain amount of data blocks during the process of data recovery, resulting in a large amount overhead of I/O and network. Based on the RS algorithm, a new CLRC algorithm is proposed to optimize the locality of RS algorithm by grouping RS coded blocks and generating local check blocks. Evaluations show that the algorithm can reduce about 61% bandwidth and I/O consumption during the process of data recovery when a single block is damaged. What's more, the cost of decoding time is only 59% of RS algorithm.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124058201","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}
Pub Date : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00078
Liu Cong, Wang Xingru
This paper reviewed the development process and the current status of comprehensive mechanized coal mining equipment technology in China. The definition and technical connotation of the intelligent coal mine on the basis of the artificial intelligence and technology of the Internet of Things (IoT) are proposed. The paper researched and practiced the key technology related to the high efficient and adaptive shearer autonomous positioning technology, shearer autonomous obstacle avoidance technology, intelligent diagnosis of coal mining equipment, intelligent recognition technology of coal-rock interface. Through theoretical research and application practice, the feasibility, necessity, and advancement of the intelligent coal mine are proved. Finally, this paper looks forward to the development direction of intelligent coal mines and puts forward the development concept of coal-based multielement clean energy collaborative mining and the development and utilization integration of coal
{"title":"Research and Practice of China's Intelligent Coal Mines","authors":"Liu Cong, Wang Xingru","doi":"10.1109/ICCEAI52939.2021.00078","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00078","url":null,"abstract":"This paper reviewed the development process and the current status of comprehensive mechanized coal mining equipment technology in China. The definition and technical connotation of the intelligent coal mine on the basis of the artificial intelligence and technology of the Internet of Things (IoT) are proposed. The paper researched and practiced the key technology related to the high efficient and adaptive shearer autonomous positioning technology, shearer autonomous obstacle avoidance technology, intelligent diagnosis of coal mining equipment, intelligent recognition technology of coal-rock interface. Through theoretical research and application practice, the feasibility, necessity, and advancement of the intelligent coal mine are proved. Finally, this paper looks forward to the development direction of intelligent coal mines and puts forward the development concept of coal-based multielement clean energy collaborative mining and the development and utilization integration of coal","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128118038","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：