Pub Date : 2023-05-01DOI: 10.53106/160792642023052403008
Milos Mravik Milos Mravik, Marko Sarac Milos Mravik, Nebojsa Bacanin Marko Sarac, Sasa Adamovic Nebojsa Bacanin
This paper represents the impact of new approaches to distance learning during the Covid-19 pandemic. The focus of the paper is on the quality of online teaching in relation to face-to-face teaching. The presented results represent documented empirical research that resulted from 2 years of working with a large group of students. The consequences of this way of everyday life have affected all spheres of business. The results indicate that the professors and students faced self-imposed obstacles, as well as pedagogical, technical, and financial or organizational obstacles. The results obtained are further verified by conducting relevant hypotheses tests.
{"title":"Distance Learning in Difficult Conditions Due to the Pandemic State of Emergency","authors":"Milos Mravik Milos Mravik, Marko Sarac Milos Mravik, Nebojsa Bacanin Marko Sarac, Sasa Adamovic Nebojsa Bacanin","doi":"10.53106/160792642023052403008","DOIUrl":"https://doi.org/10.53106/160792642023052403008","url":null,"abstract":"\u0000 This paper represents the impact of new approaches to distance learning during the Covid-19 pandemic. The focus of the paper is on the quality of online teaching in relation to face-to-face teaching. The presented results represent documented empirical research that resulted from 2 years of working with a large group of students. The consequences of this way of everyday life have affected all spheres of business. The results indicate that the professors and students faced self-imposed obstacles, as well as pedagogical, technical, and financial or organizational obstacles. The results obtained are further verified by conducting relevant hypotheses tests.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134495638","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 : 2023-05-01DOI: 10.53106/160792642023052403009
Yuxuan Zhou Yuxuan Zhou, Wanzhong Chen Yuxuan Zhou, Linlin Li Wanzhong Chen, Linlin Gong Linlin Li, Chang Liu Linlin Gong
For the whole environmental settings in this research, the conventional affective brain-computer interactions can not build a good performance on energy-efficient resource of network’s forwarding ports and routing paths due to its poor allocation function of cognitive radio networks, based on the novel interactive networking architecture, the model of non-linear iterative prediction scheme in interaction was successively proposed. This research proposes a modified LSTM algorithm with a structure of non-linear iterative in complexity prediction, joins the multiple k modes selection and multi-agent systems, maximizes EERA of forwarding and routing while maintaining the communication quality. Firstly, considering whether this affective brain-computer interactions need the networking communication in system. Secondly, adjusting the forwarding and routing factors of energy-efficient resource allocation by selecting the best optimal energy-efficient resource for the links through the non-linear iterative prediction in a multi-modal perception. The simulation results show that compared with the other models and algorithms, the proposed scheme for affective brain-computer interactions, which has a nice performance on a higher EERA and channel utilization of a networking architecture of brain-computer interactions.
{"title":"The Energy-Efficient Resource Allocation of Multi-Modal Perception for Affective Brain-Computer Interactions Based on Non-Linear Iterative Prediction Scheme","authors":"Yuxuan Zhou Yuxuan Zhou, Wanzhong Chen Yuxuan Zhou, Linlin Li Wanzhong Chen, Linlin Gong Linlin Li, Chang Liu Linlin Gong","doi":"10.53106/160792642023052403009","DOIUrl":"https://doi.org/10.53106/160792642023052403009","url":null,"abstract":"\u0000 For the whole environmental settings in this research, the conventional affective brain-computer interactions can not build a good performance on energy-efficient resource of network’s forwarding ports and routing paths due to its poor allocation function of cognitive radio networks, based on the novel interactive networking architecture, the model of non-linear iterative prediction scheme in interaction was successively proposed. This research proposes a modified LSTM algorithm with a structure of non-linear iterative in complexity prediction, joins the multiple k modes selection and multi-agent systems, maximizes EERA of forwarding and routing while maintaining the communication quality. Firstly, considering whether this affective brain-computer interactions need the networking communication in system. Secondly, adjusting the forwarding and routing factors of energy-efficient resource allocation by selecting the best optimal energy-efficient resource for the links through the non-linear iterative prediction in a multi-modal perception. The simulation results show that compared with the other models and algorithms, the proposed scheme for affective brain-computer interactions, which has a nice performance on a higher EERA and channel utilization of a networking architecture of brain-computer interactions.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127218011","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 : 2023-05-01DOI: 10.53106/160792642023052403023
Bo Zhang Bo Zhang, Jun Li Bo Zhang, Yutao Feng Jun Li, Danni Liu Yutao Feng
With the development of 5G network, artificial intelligence, cloud computing, big data and other digital technologies, we have witnessed the E-commerce live broadcasting industry has also jumped on this fast train, injecting fresh blood into People’s Daily shopping. The main contribution of this paper is to combine theory with practice to build a model from three aspects: people, goods and market, set up assumptions, and analyze the purchasing factors that affect people’s daily shopping. Using SmartPLS software to conduct descriptive statistics, reliability analysis and validity test on the collected questionnaires, the following conclusions and research objectives are drawn: the interactivity of live-streaming, entertainment of live-streaming, promotion price of live-streaming and opinion leaders will have a significant impact on consumers’ cognition and emotion, and meanwhile, cognition and emotion will have a significant impact on consumers’ purchase intention. Opinion leaders have the greatest impact on consumers’ willingness to purchase.
{"title":"Factors Analysis of Consumers' Purchasing Intention Under the Background of Live E-commerce Shopping","authors":"Bo Zhang Bo Zhang, Jun Li Bo Zhang, Yutao Feng Jun Li, Danni Liu Yutao Feng","doi":"10.53106/160792642023052403023","DOIUrl":"https://doi.org/10.53106/160792642023052403023","url":null,"abstract":"\u0000 With the development of 5G network, artificial intelligence, cloud computing, big data and other digital technologies, we have witnessed the E-commerce live broadcasting industry has also jumped on this fast train, injecting fresh blood into People’s Daily shopping. The main contribution of this paper is to combine theory with practice to build a model from three aspects: people, goods and market, set up assumptions, and analyze the purchasing factors that affect people’s daily shopping. Using SmartPLS software to conduct descriptive statistics, reliability analysis and validity test on the collected questionnaires, the following conclusions and research objectives are drawn: the interactivity of live-streaming, entertainment of live-streaming, promotion price of live-streaming and opinion leaders will have a significant impact on consumers’ cognition and emotion, and meanwhile, cognition and emotion will have a significant impact on consumers’ purchase intention. Opinion leaders have the greatest impact on consumers’ willingness to purchase.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116767614","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 : 2023-05-01DOI: 10.53106/160792642023052403004
B. R. S. B. R. Sathish, Radha Senthilkumar B. R. Sathish
With a recent spread of intelligent information systems, massive data collections with a lot of repeated and unintentional, unwanted interference oriented data are gathered and a huge feature set are being operated. Higher dimensional inputs, on the other hand, contain more correlated variables, which might have a negative impact on model performance. In our model a Hybrid method of selecting feature was developed by combining Binary Gravitational Search Particle Swarm Optimization (HBGSPSO) method with an Enhanced Convolution Neural Network Bidirectional Long Short Term Memory (ECNN-BiLSTM). In our proposed system, the Bidirectional Long Short Term Memory (BiLSTM) is introduced which extracts the hidden dynamic data and utilizes the memory cells to think of long-term historical data after the convolution process. In this paper, thirteen well-defined datasets are used from the machine learning database of UC Irvine to evaluate the efficiency of the proposed system. The experiments are conducted using K Nearest Neighbor (KNN) and Decision Tree (DT) which are used as classifiers to evaluate the outcome of selected features. The outcomes are contrasted and compared with the bio-enlivened calculations like Genetic Algorithm (GA), Grey Wolf Optimizer (GWO), and Optimization protocol using Particle Swarm Optimization (PSO).
{"title":"A Hybrid Algorithm for Feature Selection and Classification","authors":"B. R. S. B. R. Sathish, Radha Senthilkumar B. R. Sathish","doi":"10.53106/160792642023052403004","DOIUrl":"https://doi.org/10.53106/160792642023052403004","url":null,"abstract":"\u0000 With a recent spread of intelligent information systems, massive data collections with a lot of repeated and unintentional, unwanted interference oriented data are gathered and a huge feature set are being operated. Higher dimensional inputs, on the other hand, contain more correlated variables, which might have a negative impact on model performance. In our model a Hybrid method of selecting feature was developed by combining Binary Gravitational Search Particle Swarm Optimization (HBGSPSO) method with an Enhanced Convolution Neural Network Bidirectional Long Short Term Memory (ECNN-BiLSTM). In our proposed system, the Bidirectional Long Short Term Memory (BiLSTM) is introduced which extracts the hidden dynamic data and utilizes the memory cells to think of long-term historical data after the convolution process. In this paper, thirteen well-defined datasets are used from the machine learning database of UC Irvine to evaluate the efficiency of the proposed system. The experiments are conducted using K Nearest Neighbor (KNN) and Decision Tree (DT) which are used as classifiers to evaluate the outcome of selected features. The outcomes are contrasted and compared with the bio-enlivened calculations like Genetic Algorithm (GA), Grey Wolf Optimizer (GWO), and Optimization protocol using Particle Swarm Optimization (PSO).\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117024667","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 : 2023-05-01DOI: 10.53106/160792642023052403010
Mingxu Wang Mingxu Wang, Jingwen Li Mingxu Wang, Pengfei Shi Jingwen Li
This study aims to identify the factors influencing the online attention to the 2022 Beijing Olympics and Paralympic Winter Games. In order to accomplish the same, data of online attention to its Baidu index were collected. Factors influencing the online attention to the 2022 Beijing Olympics and Paralympic Winter Games included in this study are populations of the gross and regional permanent residents and young and middle-aged residents and the per-capita disposable income in the China Statistical Yearbook, and the Internet penetration rate in Internet Report. The results demonstrated that the online attention to the 2022 Beijing Olympics and Paralympic Winter Games would be significantly enhanced by increasing the Internet penetration rate and per-capita income. Simultaneously, young and middle-aged groups will also play a role in the remarkable enhancement of online attention. In addition, the large population base of the permanent residents will also help in improving it. There is a clear difference in the geographical distribution between North and South of China in terms of online attention.
{"title":"Factors Influencing the Online Attention to the 2022 Beijing Olympics and Paralympic Winter Games","authors":"Mingxu Wang Mingxu Wang, Jingwen Li Mingxu Wang, Pengfei Shi Jingwen Li","doi":"10.53106/160792642023052403010","DOIUrl":"https://doi.org/10.53106/160792642023052403010","url":null,"abstract":"\u0000 This study aims to identify the factors influencing the online attention to the 2022 Beijing Olympics and Paralympic Winter Games. In order to accomplish the same, data of online attention to its Baidu index were collected. Factors influencing the online attention to the 2022 Beijing Olympics and Paralympic Winter Games included in this study are populations of the gross and regional permanent residents and young and middle-aged residents and the per-capita disposable income in the China Statistical Yearbook, and the Internet penetration rate in Internet Report. The results demonstrated that the online attention to the 2022 Beijing Olympics and Paralympic Winter Games would be significantly enhanced by increasing the Internet penetration rate and per-capita income. Simultaneously, young and middle-aged groups will also play a role in the remarkable enhancement of online attention. In addition, the large population base of the permanent residents will also help in improving it. There is a clear difference in the geographical distribution between North and South of China in terms of online attention.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115580169","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 : 2023-05-01DOI: 10.53106/160792642023052403018
M. M. K. M. M. Kamruzzaman, Saad Awadh Alanazi M. M. Kamruzzaman, Madallah Alruwaili Saad Awadh Alanazi, Yousef Alhwaiti Madallah Alruwaili, Ahmed Alsayat Yousef Alhwaiti
Obtaining a person’s facial features is necessary for processing techniques like face tracking, facial expression, and face recognition. Many factors are involved in locating and detecting facial features, and the most important is eye localization and detection. Recognition of facial expressions is not about catching expressions; it is about determining whether or not students feel an emotional connection to the material or the instructor who presents it. Using blockchain as a service (BaaS) is the third-party creation and management of cloud-based networks for companies which could use for student attention evaluation without spending time and money developing their in-house solutions. Hence to overcome the problem mentioned, this paper is solved by proposing a new technique named deep facial feature extraction system (DFFE), through which the student’s attention is examined. The basic features such as feelings, interest, and attention of students are evaluated by implementing the new Expert Facial Feature Focus Algorithm (EFFF) using deep learning strategies. It is possible that shortly, this algorithm will discover a person’s feelings and thoughts accurately comprehensively assess user’s attention degrees to help people work, study, and live better with greater efficiency achieving 93.2% by analyzing emotions and feelings.
{"title":"Blockchain as a Services Based Deep Facial Feature Extraction Architecture for Student Attention Evaluation in Online Education","authors":"M. M. K. M. M. Kamruzzaman, Saad Awadh Alanazi M. M. Kamruzzaman, Madallah Alruwaili Saad Awadh Alanazi, Yousef Alhwaiti Madallah Alruwaili, Ahmed Alsayat Yousef Alhwaiti","doi":"10.53106/160792642023052403018","DOIUrl":"https://doi.org/10.53106/160792642023052403018","url":null,"abstract":"\u0000 Obtaining a person’s facial features is necessary for processing techniques like face tracking, facial expression, and face recognition. Many factors are involved in locating and detecting facial features, and the most important is eye localization and detection. Recognition of facial expressions is not about catching expressions; it is about determining whether or not students feel an emotional connection to the material or the instructor who presents it. Using blockchain as a service (BaaS) is the third-party creation and management of cloud-based networks for companies which could use for student attention evaluation without spending time and money developing their in-house solutions. Hence to overcome the problem mentioned, this paper is solved by proposing a new technique named deep facial feature extraction system (DFFE), through which the student’s attention is examined. The basic features such as feelings, interest, and attention of students are evaluated by implementing the new Expert Facial Feature Focus Algorithm (EFFF) using deep learning strategies. It is possible that shortly, this algorithm will discover a person’s feelings and thoughts accurately comprehensively assess user’s attention degrees to help people work, study, and live better with greater efficiency achieving 93.2% by analyzing emotions and feelings.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114515670","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}
In order to support real time IoT services, the ultra Reliable and Low Latency Communications (uRLLC) was proposed in 5G wireless communication network. Different from the grant based access in 4G, the grant free technique is proposed in 5G to reduce the random access delay of uRLLC-required applications. This paper proposes the dedicated resource for exclusive access of individual UE and the shared resource pool for the contention of multiple UEs by adopting the reinforcement learning approach. The objective of this paper is to accomplish the uplink successful rate above 99.9% under certain transmission error probability. The proposed Prediction based Hybrid Resource Allocation (PHRA) scheme allocates the access resource in a heuristic manner by referring to the activity of UEs. The dedicated resource is mainly allocated to the high activity UEs and the initial transmission of UEs with medium activity while the shared resource pool is allocated for the re-transmission of medium activity UEs and low activity UEs by using the reinforcement learning model. The burst traffic model was applied during the exhaustive experiments. And the simulation results show that the proposed scheme achieves higher uplink packet delivery ratio and more effective resource utilization than the other schemes.
{"title":"Study of Uplink Resource Allocation for 5G IoT Services by Using Reinforcement Learning","authors":"Yen-Wen Chen Yen-Wen Chen, ChengYu Tsai Yen-Wen Chen","doi":"10.53106/160792642023052403013","DOIUrl":"https://doi.org/10.53106/160792642023052403013","url":null,"abstract":"\u0000 In order to support real time IoT services, the ultra Reliable and Low Latency Communications (uRLLC) was proposed in 5G wireless communication network. Different from the grant based access in 4G, the grant free technique is proposed in 5G to reduce the random access delay of uRLLC-required applications. This paper proposes the dedicated resource for exclusive access of individual UE and the shared resource pool for the contention of multiple UEs by adopting the reinforcement learning approach. The objective of this paper is to accomplish the uplink successful rate above 99.9% under certain transmission error probability. The proposed Prediction based Hybrid Resource Allocation (PHRA) scheme allocates the access resource in a heuristic manner by referring to the activity of UEs. The dedicated resource is mainly allocated to the high activity UEs and the initial transmission of UEs with medium activity while the shared resource pool is allocated for the re-transmission of medium activity UEs and low activity UEs by using the reinforcement learning model. The burst traffic model was applied during the exhaustive experiments. And the simulation results show that the proposed scheme achieves higher uplink packet delivery ratio and more effective resource utilization than the other schemes.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126810808","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 : 2023-05-01DOI: 10.53106/160792642023052403016
Sungwook Ryu Sungwook Ryu, Jinsu Kim Sungwook Ryu, Namje Park Jinsu Kim
The indiscriminate convergence of technologies makes prediction difficult and can cause many difficulties in technology investment. This makes it difficult to choose capital investment and can induce excessive investment in inefficient technologies. Therefore, analyzing the trend of convergence technology and predicting a highly influential convergence area in the future can induce effective investment, and lead the highly influential technology to achieve great technological development. The purpose of this paper is to analyze technologies that are expected to have high influence in the future through prediction of major fusion areas and to present fusion areas that can be used as indicators of investment. The proposed mechanism selected four prominent journals in the security area and collected metadata to generate a dataset in terms of technological excellence and a dataset in terms of commercialization through patent metadata collection. Thereafter, a process of extracting a main keyword according to a topic from a metadata set by applying a Latent Dirichlet Allocation (LDA) is performed. The extracted topics and keywords are not related to topics and keywords of other years. Therefore, a dynamic topic model (DTM) is applied to analyze the trend of the extracted topics and perform prediction. DTM analyzes the topics in the fusion area classified by LDA and the trend of changing topics linked by year for each topic keyword. Finally, the association of the fusion region is analyzed to derive a fusion region with high influence. These results are believed to be used as an indicator of effective technology investment by providing a high impact area in the convergence area of cybersecurity.
{"title":"Study on Trends and Predictions of Convergence in Cybersecurity Technology Using Machine Learning","authors":"Sungwook Ryu Sungwook Ryu, Jinsu Kim Sungwook Ryu, Namje Park Jinsu Kim","doi":"10.53106/160792642023052403016","DOIUrl":"https://doi.org/10.53106/160792642023052403016","url":null,"abstract":"\u0000 The indiscriminate convergence of technologies makes prediction difficult and can cause many difficulties in technology investment. This makes it difficult to choose capital investment and can induce excessive investment in inefficient technologies. Therefore, analyzing the trend of convergence technology and predicting a highly influential convergence area in the future can induce effective investment, and lead the highly influential technology to achieve great technological development. The purpose of this paper is to analyze technologies that are expected to have high influence in the future through prediction of major fusion areas and to present fusion areas that can be used as indicators of investment. The proposed mechanism selected four prominent journals in the security area and collected metadata to generate a dataset in terms of technological excellence and a dataset in terms of commercialization through patent metadata collection. Thereafter, a process of extracting a main keyword according to a topic from a metadata set by applying a Latent Dirichlet Allocation (LDA) is performed. The extracted topics and keywords are not related to topics and keywords of other years. Therefore, a dynamic topic model (DTM) is applied to analyze the trend of the extracted topics and perform prediction. DTM analyzes the topics in the fusion area classified by LDA and the trend of changing topics linked by year for each topic keyword. Finally, the association of the fusion region is analyzed to derive a fusion region with high influence. These results are believed to be used as an indicator of effective technology investment by providing a high impact area in the convergence area of cybersecurity.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123141613","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 : 2023-05-01DOI: 10.53106/160792642023052403020
Bao-Wei Zhang Bao-Wei Zhang, Lin Xu Bao-Wei Zhang, Yong-Hua Wang Lin Xu
This study aimed to propose a method to predict yarn unevenness grounded on the generalized regression neural network and traditional neural network model to further improve the prediction accuracy. The yarn unevenness model was constructed. Under this model, a three-layer neural network, a four-layer neural network, a five-layer neural network, and a generalized regression neural network were designed. Finally, Python was used for training and simulation. The training parameters and the three network models data were made consistent to ensure the comparability of the results. The results showed that using the yarn unevenness model, the average relative error of the four-layer neural network to cut down 0.87% compared with that of the three-layer neural network. Compared with the five-layer neural network, the four-layer neural network performance was not much different, but the running speed was increased by 46.05%. Compared with the four-layer neural network, the average relative error of the generalized regression neural network was reduced by 0.57%, the mean square error was reduced by 0.98%, he root mean square error was reduced by 4.76%, and the running speed was increased by 74.70%.
{"title":"Yarn Unevenness Prediction using Generalized Regression Neural Network","authors":"Bao-Wei Zhang Bao-Wei Zhang, Lin Xu Bao-Wei Zhang, Yong-Hua Wang Lin Xu","doi":"10.53106/160792642023052403020","DOIUrl":"https://doi.org/10.53106/160792642023052403020","url":null,"abstract":"\u0000 This study aimed to propose a method to predict yarn unevenness grounded on the generalized regression neural network and traditional neural network model to further improve the prediction accuracy. The yarn unevenness model was constructed. Under this model, a three-layer neural network, a four-layer neural network, a five-layer neural network, and a generalized regression neural network were designed. Finally, Python was used for training and simulation. The training parameters and the three network models data were made consistent to ensure the comparability of the results. The results showed that using the yarn unevenness model, the average relative error of the four-layer neural network to cut down 0.87% compared with that of the three-layer neural network. Compared with the five-layer neural network, the four-layer neural network performance was not much different, but the running speed was increased by 46.05%. Compared with the four-layer neural network, the average relative error of the generalized regression neural network was reduced by 0.57%, the mean square error was reduced by 0.98%, he root mean square error was reduced by 4.76%, and the running speed was increased by 74.70%.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132382681","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 : 2023-05-01DOI: 10.53106/160792642023052403011
Qingru Ma Qingru Ma, Haowen Tan Qingru Ma
The home area network (HAN) is one of the most widely researched areas in recent years. HANs integrate 5G/6G networks and artificial intelligence technology to provide data services for home users. The devices in HANs collect and transmit data relating to users’ daily activities for analysis by remote service providers. These data often contain a large number of users’ personal privacy. The disclosure of these data could have far-reaching consequences for the privacy of the individuals involved. Some researchers are dedicated to investigating the authentication of smart devices by the system. However, the increased frequency of interactions between devices and gateways, as well as between devices themselves, is a defining characteristic of HANs. In this paper, a device-to-gateway (D2G) authentication scheme is proposed. Based on the authentication result, a partial key is generated for smart devices and the gateway. Finally, a device-to-device (D2D) group key agreement scheme is presented. The security and efficiency of the proposed scheme are proved according to the analysis.
{"title":"D2D Group Key Agreement Scheme for Smart Devices in HANs","authors":"Qingru Ma Qingru Ma, Haowen Tan Qingru Ma","doi":"10.53106/160792642023052403011","DOIUrl":"https://doi.org/10.53106/160792642023052403011","url":null,"abstract":"\u0000 The home area network (HAN) is one of the most widely researched areas in recent years. HANs integrate 5G/6G networks and artificial intelligence technology to provide data services for home users. The devices in HANs collect and transmit data relating to users’ daily activities for analysis by remote service providers. These data often contain a large number of users’ personal privacy. The disclosure of these data could have far-reaching consequences for the privacy of the individuals involved. Some researchers are dedicated to investigating the authentication of smart devices by the system. However, the increased frequency of interactions between devices and gateways, as well as between devices themselves, is a defining characteristic of HANs. In this paper, a device-to-gateway (D2G) authentication scheme is proposed. Based on the authentication result, a partial key is generated for smart devices and the gateway. Finally, a device-to-device (D2D) group key agreement scheme is presented. The security and efficiency of the proposed scheme are proved according to the analysis.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114407138","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：