Pub Date : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645647
Shuai Feng, Shigang Wang, Xueshan Gao
The economy of medical ultrasound images comes at the expense of image quality that is usually affected by speckle noise. In this paper, a method for 2D ultrasound medical image despeckling is presented, which combines homomorphic filtering and MAD (Median Anisotropic Diffusion) filtering that the improved Anisotropic Diffusion filter. First, the preprocessed image after dilution of speckle-noise is obtained by homomorphic transformation of the ultrasound image with Gaussian high-pass filtering and median filtering. Then the speckle is removed with the MAD filtering, and finally, the contrast is enhanced. Experimental results demonstrate that the algorithm can effectively reduce the speckle noise and maintain high image quality. The algorithm in this paper helps remove speckle in 2D static ultrasound images, which is potentially valuable for improving the quality of medical ultrasound images.
{"title":"Homomorphic Filtering and MAD Filtering Based Speckle Removal in Ultrasound Images","authors":"Shuai Feng, Shigang Wang, Xueshan Gao","doi":"10.1109/ECICE52819.2021.9645647","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645647","url":null,"abstract":"The economy of medical ultrasound images comes at the expense of image quality that is usually affected by speckle noise. In this paper, a method for 2D ultrasound medical image despeckling is presented, which combines homomorphic filtering and MAD (Median Anisotropic Diffusion) filtering that the improved Anisotropic Diffusion filter. First, the preprocessed image after dilution of speckle-noise is obtained by homomorphic transformation of the ultrasound image with Gaussian high-pass filtering and median filtering. Then the speckle is removed with the MAD filtering, and finally, the contrast is enhanced. Experimental results demonstrate that the algorithm can effectively reduce the speckle noise and maintain high image quality. The algorithm in this paper helps remove speckle in 2D static ultrasound images, which is potentially valuable for improving the quality of medical ultrasound images.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114568701","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645695
Chien-Chung Tsai, Chih-Chun Chan
Laser processing could be applied to the process of CMOS-MEMS fabrication. The TSMC/TSRI D35 common process is an example in this study. There are different laser wavelengths, laser energy, interval time, and light targets for different material fabrication. This study proposes the laser ablation quality of silicon nitride as the measurement of laser processing. According to the experimental results, the best quality of the green laser is 93% while the energy is 0.228 mJ, the interval time is 60 s and the light target size is 30 x 30 μm2. On the other hand, the best quality of the ultraviolet ablation is 92% which is generated at an energy of 0.48 mJ, an interval of 30 s, and an aperture size of 30 x 30 μm2. As the energy increases, the ablation quality becomes large. The results demonstrate the Fraunhofer diffraction is a dominant role in this study of laser ablation quality. This study simultaneously investigates the ablation phenomenon of microfabrication in green laser applied to CMOS-MEMS components by machine learning and data science. That proposes the approaching methodology for the optimal operation of the laser processing. The experimental results show that the pulse interval time is 90 s and the energy density is 57 J/m2, which has a good quality of ablation. Data science and machine learning successfully predict the quality level of ablation by using the random forest algorithm to achieve a mean accuracy of 98.04%.
{"title":"Laser Ablation Quality Study of Silicon Nitride during CMOS-MEMS post Processing by Using Machine Learning and Data Science","authors":"Chien-Chung Tsai, Chih-Chun Chan","doi":"10.1109/ECICE52819.2021.9645695","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645695","url":null,"abstract":"Laser processing could be applied to the process of CMOS-MEMS fabrication. The TSMC/TSRI D35 common process is an example in this study. There are different laser wavelengths, laser energy, interval time, and light targets for different material fabrication. This study proposes the laser ablation quality of silicon nitride as the measurement of laser processing. According to the experimental results, the best quality of the green laser is 93% while the energy is 0.228 mJ, the interval time is 60 s and the light target size is 30 x 30 μm2. On the other hand, the best quality of the ultraviolet ablation is 92% which is generated at an energy of 0.48 mJ, an interval of 30 s, and an aperture size of 30 x 30 μm2. As the energy increases, the ablation quality becomes large. The results demonstrate the Fraunhofer diffraction is a dominant role in this study of laser ablation quality. This study simultaneously investigates the ablation phenomenon of microfabrication in green laser applied to CMOS-MEMS components by machine learning and data science. That proposes the approaching methodology for the optimal operation of the laser processing. The experimental results show that the pulse interval time is 90 s and the energy density is 57 J/m2, which has a good quality of ablation. Data science and machine learning successfully predict the quality level of ablation by using the random forest algorithm to achieve a mean accuracy of 98.04%.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123577002","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645639
Che-Cheng Chang, Kuan-Chang Shih, Hung-Che Ting, Yi-Syuan Su
A depth camera provides distance information. However, in the real environment, uncertain measurement conditions may bring incorrect distance information, e.g., environmental conditions, hardware component tolerances, and so on. Thus, we may always obtain unstable and inaccurate information. On the other hand, even sensors with the same specification are used in the experiment, we may obtain different information as well. Therefore, in this work, we intend to solve this issue by incorporating some machine learning approaches in the real environment to improve accuracy and stability. Particularly, we use the concept of machine learning for overall consideration instead of a particular statistics model to evaluate the uncertainty.
{"title":"Utilizing Machine Learning to Improve the Distance Information from Depth Camera","authors":"Che-Cheng Chang, Kuan-Chang Shih, Hung-Che Ting, Yi-Syuan Su","doi":"10.1109/ECICE52819.2021.9645639","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645639","url":null,"abstract":"A depth camera provides distance information. However, in the real environment, uncertain measurement conditions may bring incorrect distance information, e.g., environmental conditions, hardware component tolerances, and so on. Thus, we may always obtain unstable and inaccurate information. On the other hand, even sensors with the same specification are used in the experiment, we may obtain different information as well. Therefore, in this work, we intend to solve this issue by incorporating some machine learning approaches in the real environment to improve accuracy and stability. Particularly, we use the concept of machine learning for overall consideration instead of a particular statistics model to evaluate the uncertainty.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121916692","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645621
Badereddine Fares, Haïfa Souifi, M. Ghribi, Y. Bouslimani
Omnidirectional mobile platforms are holonomic robots that can independently and simultaneously perform translational and rotational motions. In order to develop an autonomous omnidirectional mobile manipulator, this paper presents a platform based on four mecanum wheels. It has a higher carrying capacity and mobility than a standard four-wheel platform. The used manipulator is a Fanuc LR Mate 200 iD/7l robot with an R-30iB Mate Plus Controller. The heavy weight of the industrial arm and the controller makes collision-free navigation a challenge. To navigate with this robot in an unknown semi-structured indoor environment, a Hokuyo 2D Lidar and a Realsense D435i camera have been used. The Central Processing Unit is an Nvidia Jetson TX2 running Ubuntu Linux on which ROS (robot operating system) was installed. The robot is capable of autonomously performing Simultaneous Localization and Mapping (SLAM), navigation, obstacle detection, and object recognition, vision-guided robot motions. A map of our workplace was generated. Most mobile robot motion control approaches rely on dynamic or kinematic models. The study also covers mathematical modeling of the four-wheeled omnidirectional platform that leads to the robot's kinematics. The simulations were carried out using MATLAB to establish and verify the kinematic model of the omnidirectional platform. The robot was controlled to follow curves with a constant translation velocity of 1m/s.
{"title":"Omnidirectional Platform for Autonomous Mobile Industrial Robot","authors":"Badereddine Fares, Haïfa Souifi, M. Ghribi, Y. Bouslimani","doi":"10.1109/ECICE52819.2021.9645621","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645621","url":null,"abstract":"Omnidirectional mobile platforms are holonomic robots that can independently and simultaneously perform translational and rotational motions. In order to develop an autonomous omnidirectional mobile manipulator, this paper presents a platform based on four mecanum wheels. It has a higher carrying capacity and mobility than a standard four-wheel platform. The used manipulator is a Fanuc LR Mate 200 iD/7l robot with an R-30iB Mate Plus Controller. The heavy weight of the industrial arm and the controller makes collision-free navigation a challenge. To navigate with this robot in an unknown semi-structured indoor environment, a Hokuyo 2D Lidar and a Realsense D435i camera have been used. The Central Processing Unit is an Nvidia Jetson TX2 running Ubuntu Linux on which ROS (robot operating system) was installed. The robot is capable of autonomously performing Simultaneous Localization and Mapping (SLAM), navigation, obstacle detection, and object recognition, vision-guided robot motions. A map of our workplace was generated. Most mobile robot motion control approaches rely on dynamic or kinematic models. The study also covers mathematical modeling of the four-wheeled omnidirectional platform that leads to the robot's kinematics. The simulations were carried out using MATLAB to establish and verify the kinematic model of the omnidirectional platform. The robot was controlled to follow curves with a constant translation velocity of 1m/s.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124010104","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645721
Aishwarya Gowda A G, Hui-Kai Su, W. Kuo
The rapid evolution in science and technology, has lead the vigorous development of the technology industry. This development witnessed the changes of the Earth's climatic conditions, dwindle of precious natural resources. Among which, water is an indispensable resource for our human life. But, there are many factors like pollution or loss of resources which result in making water as an important resource for usage. Whereas, the current monitoring system has various problems as most of the people are not very familiar with the proper usage of water and the methods to handle water. Hence, addressing this issue our solution aims in monitoring and controlling water resources by our hardware and software system. This system is combined with a database, PAC (Programmable Automation Controllers) and different types of sensors. This blend of software and hardware initially supports the operators to predict and judge each value accurately. This ensures to make the best processing method and improves work efficiency in short period. Meanwhile, it helps and can reduce the workload drastically helping each process flow smoother and with better results. This solution also can be used to reduce the loss of water resource which occurs due to mis-operation by operators. In addition, this system ensures an ease environment for managers and operators to handle the complete process with confidence. Use of this system can help a huge group of people to achieve a win-win situation with convenient management and easy operation.
{"title":"System Integration of Remote Sensing and Industrial Control with IoT Technologies for Water Purification Plant","authors":"Aishwarya Gowda A G, Hui-Kai Su, W. Kuo","doi":"10.1109/ECICE52819.2021.9645721","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645721","url":null,"abstract":"The rapid evolution in science and technology, has lead the vigorous development of the technology industry. This development witnessed the changes of the Earth's climatic conditions, dwindle of precious natural resources. Among which, water is an indispensable resource for our human life. But, there are many factors like pollution or loss of resources which result in making water as an important resource for usage. Whereas, the current monitoring system has various problems as most of the people are not very familiar with the proper usage of water and the methods to handle water. Hence, addressing this issue our solution aims in monitoring and controlling water resources by our hardware and software system. This system is combined with a database, PAC (Programmable Automation Controllers) and different types of sensors. This blend of software and hardware initially supports the operators to predict and judge each value accurately. This ensures to make the best processing method and improves work efficiency in short period. Meanwhile, it helps and can reduce the workload drastically helping each process flow smoother and with better results. This solution also can be used to reduce the loss of water resource which occurs due to mis-operation by operators. In addition, this system ensures an ease environment for managers and operators to handle the complete process with confidence. Use of this system can help a huge group of people to achieve a win-win situation with convenient management and easy operation.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128686691","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645730
H. Hsin, C. Su
Convolutional neural networks have been widely used in deep learning recently. This paper presents an adaptive scheme to modify the input layers of the conventional convolutional neural networks such that images of arbitrary sizes can be directly input. Specifically, motivated by the advantage of content-aware image resizing, which takes the regions of interest into account for effective displaying on various screens with different dimensions and aspect ratios, it is beneficial to incorporate content-aware image resizing into convolutional neural networks. Experimental results show that image classification can be improved in terms of mean average precision.
{"title":"Adaptive Pooling for Convolutional Neural Networks with Arbitrary Input Sizes","authors":"H. Hsin, C. Su","doi":"10.1109/ECICE52819.2021.9645730","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645730","url":null,"abstract":"Convolutional neural networks have been widely used in deep learning recently. This paper presents an adaptive scheme to modify the input layers of the conventional convolutional neural networks such that images of arbitrary sizes can be directly input. Specifically, motivated by the advantage of content-aware image resizing, which takes the regions of interest into account for effective displaying on various screens with different dimensions and aspect ratios, it is beneficial to incorporate content-aware image resizing into convolutional neural networks. Experimental results show that image classification can be improved in terms of mean average precision.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129312412","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645726
Kaisen Yang, Zhengyan Guo
A BP neural network is an algorithm for forward multi-layer backpropagation learning. Its basic idea is forward propagation and error backpropagation in the learning process. At present, the most common result of a BP neural network is a three-layer structure. In view of the performance evaluation of fresh agricultural supply chain, this paper proposes a performance evaluation method based on BP neural network. First, three first-level indicators and six more detailed second-level indicators are set up according to the characteristics of the data, and the BP neural network is trained and tested by cross-checking method. The BP neural network after training was evaluated by using the confusion matrix, accuracy and recall rate, MMC, ROC curve, and AUC value. It was found that in the confusion matrix output by BP neural network, TP values of the three first-level indicators were all large, while the accuracy and recall rate, MMC, ROC curve, and AUC values were all high. The values of 0.958, 0.678, and 0.588 respectively indicate that BPNN has good reliability and prediction accuracy. This paper further compares the BP neural network, decision tree model, SVM, and various evaluation results of ARIMA. The BP neural network is second only to ARIMA in accuracy and recall rate, and improves MCC and AUC values by 10.54% and 14.05% compared with ARIMA, with the best comprehensive performance. Meanwhile, with the increase of data volume, compared with the other three models, BP neural network has more advantages on AUC and has stronger evaluation authenticity and reliability in the big data environment.
{"title":"Study on Performance Evaluation of Fresh Agricultural Supply Chain Based on BP Neural Network","authors":"Kaisen Yang, Zhengyan Guo","doi":"10.1109/ECICE52819.2021.9645726","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645726","url":null,"abstract":"A BP neural network is an algorithm for forward multi-layer backpropagation learning. Its basic idea is forward propagation and error backpropagation in the learning process. At present, the most common result of a BP neural network is a three-layer structure. In view of the performance evaluation of fresh agricultural supply chain, this paper proposes a performance evaluation method based on BP neural network. First, three first-level indicators and six more detailed second-level indicators are set up according to the characteristics of the data, and the BP neural network is trained and tested by cross-checking method. The BP neural network after training was evaluated by using the confusion matrix, accuracy and recall rate, MMC, ROC curve, and AUC value. It was found that in the confusion matrix output by BP neural network, TP values of the three first-level indicators were all large, while the accuracy and recall rate, MMC, ROC curve, and AUC values were all high. The values of 0.958, 0.678, and 0.588 respectively indicate that BPNN has good reliability and prediction accuracy. This paper further compares the BP neural network, decision tree model, SVM, and various evaluation results of ARIMA. The BP neural network is second only to ARIMA in accuracy and recall rate, and improves MCC and AUC values by 10.54% and 14.05% compared with ARIMA, with the best comprehensive performance. Meanwhile, with the increase of data volume, compared with the other three models, BP neural network has more advantages on AUC and has stronger evaluation authenticity and reliability in the big data environment.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129313206","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645594
Yuting He, Shigang Wang, Xueshan Gao
With the passage of time and improper preservation methods, many ancient books and texts have disappeared in our world. How to preserve ancient books which carry excellent traditional Chinese culture has also become a problem of people's concern. One of the most popular discussions and the most modern methods is to digitize ancient books. This paper proposes a digital processing method for ancient books based on Freeman chain code. The process of the method is, firstly, to gray the acquired image with the maximum grayscale method, then to perform median filtering and morphological denoising to get the clear image edge. Finally, the processed image is extracted with the Roberts operator, and then the continuity of the edge is strengthened through Freeman chain code to obtain a clear and continuous edge of ancient text. The experimental results show that the proposed method can extract the text edges quickly and accurately, providing an effective method for further research on the digital processing of ancient books.
{"title":"Edge Extraction of Ancient Books Based on Freeman Chain Code","authors":"Yuting He, Shigang Wang, Xueshan Gao","doi":"10.1109/ECICE52819.2021.9645594","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645594","url":null,"abstract":"With the passage of time and improper preservation methods, many ancient books and texts have disappeared in our world. How to preserve ancient books which carry excellent traditional Chinese culture has also become a problem of people's concern. One of the most popular discussions and the most modern methods is to digitize ancient books. This paper proposes a digital processing method for ancient books based on Freeman chain code. The process of the method is, firstly, to gray the acquired image with the maximum grayscale method, then to perform median filtering and morphological denoising to get the clear image edge. Finally, the processed image is extracted with the Roberts operator, and then the continuity of the edge is strengthened through Freeman chain code to obtain a clear and continuous edge of ancient text. The experimental results show that the proposed method can extract the text edges quickly and accurately, providing an effective method for further research on the digital processing of ancient books.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129969947","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645671
Juan Luo, Jianying Xiong
Social network is an important channel for users to vent their emotions, such as microblog community. This paper proposes a method to calculate the emotional heat of social network nodes based on text sentiment analysis and text classification model. Firstly, the sentiment tendency of the text content is analyzed by sentiment dictionary and semantic analysis, and the emotional value of each text content is calculated. Secondly, the text classification model is used to distinguish the different text topics of each node. And finally, the weighted algorithm is used to calculate the comprehensive evaluation value of different topic texts published by the node as the emotional heat. Taking the microblog community as an example, we use this method to collect text information published by social network nodes. The results show that integration of sentiment analysis, topic analysis, semantic analysis of text mining is conducive to the intuitive display of users' emotions in social networks, and helps regulators guide netizens' emotions.
{"title":"Using Text Semantic Mining to Calculate Emotional Heat of Social Network Nodes","authors":"Juan Luo, Jianying Xiong","doi":"10.1109/ECICE52819.2021.9645671","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645671","url":null,"abstract":"Social network is an important channel for users to vent their emotions, such as microblog community. This paper proposes a method to calculate the emotional heat of social network nodes based on text sentiment analysis and text classification model. Firstly, the sentiment tendency of the text content is analyzed by sentiment dictionary and semantic analysis, and the emotional value of each text content is calculated. Secondly, the text classification model is used to distinguish the different text topics of each node. And finally, the weighted algorithm is used to calculate the comprehensive evaluation value of different topic texts published by the node as the emotional heat. Taking the microblog community as an example, we use this method to collect text information published by social network nodes. The results show that integration of sentiment analysis, topic analysis, semantic analysis of text mining is conducive to the intuitive display of users' emotions in social networks, and helps regulators guide netizens' emotions.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130476706","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645610
C. Yeh, Tun-Chih Yang, K. Lai, Cheng-Yeh Ke
The catalyst tube lifetime of a practical steam methane reformer is analyzed numerically in this paper. The effect of reformer geometry on the flow development, chemical reaction, and catalyst tube lifetime is discussed. The results of this study reveal that the catalyst tubes in the downstream areas of the reformer have longer lifetimes while those in the upstream areas have shorter lifetimes. In most areas of the reformer, as the shifted height of the reformer roof increases, the temperatures and pressures reduce while the catalyst tube lifetime increases. However, near the sidewalls, as the shifted height of the reformer roof increases, the temperatures and pressures may increase while the catalyst tube lifetime may reduce. Nevertheless, from an overall view, raising the reformer roof reduces the temperatures and pressures and increases the catalyst tube lifetime. Finally, the shift of the reformer roof has a minor effect on the hydrogen yields at the catalyst tube outlets, although a careful observation reveals a similar trend to the temperature distributions.
{"title":"Numerical Study of the Effect of Furnace Geometry on the Catalyst Tube Lifetime of a Steam Methane Reformer","authors":"C. Yeh, Tun-Chih Yang, K. Lai, Cheng-Yeh Ke","doi":"10.1109/ECICE52819.2021.9645610","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645610","url":null,"abstract":"The catalyst tube lifetime of a practical steam methane reformer is analyzed numerically in this paper. The effect of reformer geometry on the flow development, chemical reaction, and catalyst tube lifetime is discussed. The results of this study reveal that the catalyst tubes in the downstream areas of the reformer have longer lifetimes while those in the upstream areas have shorter lifetimes. In most areas of the reformer, as the shifted height of the reformer roof increases, the temperatures and pressures reduce while the catalyst tube lifetime increases. However, near the sidewalls, as the shifted height of the reformer roof increases, the temperatures and pressures may increase while the catalyst tube lifetime may reduce. Nevertheless, from an overall view, raising the reformer roof reduces the temperatures and pressures and increases the catalyst tube lifetime. Finally, the shift of the reformer roof has a minor effect on the hydrogen yields at the catalyst tube outlets, although a careful observation reveals a similar trend to the temperature distributions.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126728469","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：