Pub Date : 2023-07-01DOI: 10.53106/160792642023072404013
Wenge Le Wenge Le, Yong Wang Wenge Le, Cuiyun Gao Yong Wang, Liangfen Wei Cuiyun Gao, Fei Yang Liangfen Wei
For mobile user interface (M-UI) design, it has an important impact on app user’s usage. However, M-UI design is limited by subjective factors, even professional developers can’t determine whether the M-UI design is good or bad. App reviews provide an opportunity to proactively collect user complaints and promptly improve the user experience of apps. Therefore, it is meaningful to explore whether app reviews can help developers to improve M-UI design. In this article, we randomly select six different categories of apps from Google Play Store and App Store, with over 160000 reviews, and conduct a preliminary empirical study to answer the question. Specially, we gather M-UI-related reviews, and compare the average rating of M-UI-related reviews and total reviews of each app. We observe that the M-UI is concerned by users and the average rating for M-UI-related reviews is lower than the average rating for total reviews. By extracting the topics of M-UI-related reviews, we estimate the sentiment of the M-UI-related topics. The results show that the number of M-UI-related topics are about three or four, and the sentiment of M-UI-related topics is related to the app itself. Further, by investigating the relation between the M-UI-related topics and M-UI design. We observe that users are concerned about the M-UI usability the most, and it is the various aspects of the M-UI that are causing user frustration. In particular, our findings show that M-UI-related reviews reflect the severity of M-UI-related issues and app reviews can help developers to improve M-UI design about appearance, usability, fault-tolerance, of which usability deserves the most attention.
{"title":"Can App Reviews Help Developers to Improve Mobile User Interface Design?","authors":"Wenge Le Wenge Le, Yong Wang Wenge Le, Cuiyun Gao Yong Wang, Liangfen Wei Cuiyun Gao, Fei Yang Liangfen Wei","doi":"10.53106/160792642023072404013","DOIUrl":"https://doi.org/10.53106/160792642023072404013","url":null,"abstract":"\u0000 For mobile user interface (M-UI) design, it has an important impact on app user’s usage. However, M-UI design is limited by subjective factors, even professional developers can’t determine whether the M-UI design is good or bad. App reviews provide an opportunity to proactively collect user complaints and promptly improve the user experience of apps. Therefore, it is meaningful to explore whether app reviews can help developers to improve M-UI design. In this article, we randomly select six different categories of apps from Google Play Store and App Store, with over 160000 reviews, and conduct a preliminary empirical study to answer the question. Specially, we gather M-UI-related reviews, and compare the average rating of M-UI-related reviews and total reviews of each app. We observe that the M-UI is concerned by users and the average rating for M-UI-related reviews is lower than the average rating for total reviews. By extracting the topics of M-UI-related reviews, we estimate the sentiment of the M-UI-related topics. The results show that the number of M-UI-related topics are about three or four, and the sentiment of M-UI-related topics is related to the app itself. Further, by investigating the relation between the M-UI-related topics and M-UI design. We observe that users are concerned about the M-UI usability the most, and it is the various aspects of the M-UI that are causing user frustration. In particular, our findings show that M-UI-related reviews reflect the severity of M-UI-related issues and app reviews can help developers to improve M-UI design about appearance, usability, fault-tolerance, of which usability deserves the most attention.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129208124","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 : 2023-07-01DOI: 10.53106/160792642023072404017
Ziyuan Wang Ziyuan Wang, Jinwu Guo Ziyuan Wang, Dexin Bu Jinwu Guo, Chongchong Shi Dexin Bu
Object detection, one of the popular tasks in computer vision, is to find all objects of interest in an image and determine their category and location. When people use deep learning frameworks to implement object detection networks, defects are often caused by human-introduced faults. These defects may cause different types of failures. Exploring frequent failure patterns in object detection programs can help developers detect and fix defects more effectively and efficiently. Therefore, we conducted an empirical study on failure patterns in deep learning-based object detection programs submitted in university software development courses. By exploring 101 submissions of a Yolov4 object detection task completed by 104 students, we found the most frequent 13 failure patterns in these submissions and six types of root causes of these failures. To help students and entry-level software engineers avoid possible faults in object detection programs, 13 concrete suggestions that belong to six classes are given in this paper. These results can reveal some basic laws of failures and mistakes in the development of deep learning-based object detection programs and provide guidances to assist students and entry-level developers in improving their skills in developing object detection programs.
{"title":"Investigating Failure Patterns in Machine Learning-based Object Detection Tasks in Software Development Courses","authors":"Ziyuan Wang Ziyuan Wang, Jinwu Guo Ziyuan Wang, Dexin Bu Jinwu Guo, Chongchong Shi Dexin Bu","doi":"10.53106/160792642023072404017","DOIUrl":"https://doi.org/10.53106/160792642023072404017","url":null,"abstract":"\u0000 Object detection, one of the popular tasks in computer vision, is to find all objects of interest in an image and determine their category and location. When people use deep learning frameworks to implement object detection networks, defects are often caused by human-introduced faults. These defects may cause different types of failures. Exploring frequent failure patterns in object detection programs can help developers detect and fix defects more effectively and efficiently. Therefore, we conducted an empirical study on failure patterns in deep learning-based object detection programs submitted in university software development courses. By exploring 101 submissions of a Yolov4 object detection task completed by 104 students, we found the most frequent 13 failure patterns in these submissions and six types of root causes of these failures. To help students and entry-level software engineers avoid possible faults in object detection programs, 13 concrete suggestions that belong to six classes are given in this paper. These results can reveal some basic laws of failures and mistakes in the development of deep learning-based object detection programs and provide guidances to assist students and entry-level developers in improving their skills in developing object detection programs. \u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128699060","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 light of recent advancements in deep and machine learning, federated learning has been proposed as a means to prevent privacy invasion. However, a reconstruction attack that exploits gradients to leak learning data has recently been developed. With increasing research into federated learning and the importance of data usage, it is crucial to prepare for such attacks. Specifically, when face data are used in federated learning, the damage caused by privacy infringement can be significant. Therefore, attack studies are necessary to develop effective defense strategies against these attacks. In this study, we propose a new attack method that uses labels to achieve faster and more accurate reconstruction performance than previous reconstruction attacks. We demonstrate the effectiveness of our proposed method on the Yale Face Database B, MNIST, and CIFAR-10 datasets, as well as under non-IID conditions, similar to real federated learning. The results show that our proposed method outperforms random labeling in terms of reconstruction performance in all evaluations for MNIST and CIFAR-10 datasets in round 1.
{"title":"Data Reconstruction Attack with Label Guessing for Federated Learning","authors":"Jinhyeok Jang Jinhyeok Jang, Yoonju Oh Jinhyeok Jang, Gwonsang Ryu Yoonju Oh, Daeseon Choi Gwonsang Ryu","doi":"10.53106/160792642023072404007","DOIUrl":"https://doi.org/10.53106/160792642023072404007","url":null,"abstract":"\u0000 In light of recent advancements in deep and machine learning, federated learning has been proposed as a means to prevent privacy invasion. However, a reconstruction attack that exploits gradients to leak learning data has recently been developed. With increasing research into federated learning and the importance of data usage, it is crucial to prepare for such attacks. Specifically, when face data are used in federated learning, the damage caused by privacy infringement can be significant. Therefore, attack studies are necessary to develop effective defense strategies against these attacks. In this study, we propose a new attack method that uses labels to achieve faster and more accurate reconstruction performance than previous reconstruction attacks. We demonstrate the effectiveness of our proposed method on the Yale Face Database B, MNIST, and CIFAR-10 datasets, as well as under non-IID conditions, similar to real federated learning. The results show that our proposed method outperforms random labeling in terms of reconstruction performance in all evaluations for MNIST and CIFAR-10 datasets in round 1.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117031653","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 : 2023-07-01DOI: 10.53106/160792642023072404014
Changsheng Du Changsheng Du, Yong Li Changsheng Du, Ming Wen Yong Li
In software engineering, software personnel faced many large-scale software and complex systems, these need programmers to quickly and accurately read and understand the code, and efficiently complete the tasks of software change or maintenance tasks. Code-NN is the first model to use deep learning to accomplish the task of code summary generation, but it is not used the structural information in the code itself. In the past five years, researchers have designed different code summarization systems based on neural networks. They generally use the end-to-end neural machine translation framework, but many current research methods do not make full use of the structural information of the code. This paper raises a new model called G-DCS to automatically generate a summary of java code; the generated summary is designed to help programmers quickly comprehend the effect of java methods. G-DCS uses natural language processing technology, and training the model uses a code corpus. This model could generate code summaries directly from the code files in the coded corpus. Compared with the traditional method, it uses the information of structural on the code. Through Graph Convolutional Neural Network (GCN) extracts the structural information on the code to generate the code sequence, which makes the generated code summary more accurate. The corpus used for training was obtained from GitHub. Evaluation criteria using BLEU-n. Experimental results show that our approach outperforms models that do not utilize code structure information.
{"title":"G-DCS: GCN-Based Deep Code Summary Generation Model","authors":"Changsheng Du Changsheng Du, Yong Li Changsheng Du, Ming Wen Yong Li","doi":"10.53106/160792642023072404014","DOIUrl":"https://doi.org/10.53106/160792642023072404014","url":null,"abstract":"\u0000 In software engineering, software personnel faced many large-scale software and complex systems, these need programmers to quickly and accurately read and understand the code, and efficiently complete the tasks of software change or maintenance tasks. Code-NN is the first model to use deep learning to accomplish the task of code summary generation, but it is not used the structural information in the code itself. In the past five years, researchers have designed different code summarization systems based on neural networks. They generally use the end-to-end neural machine translation framework, but many current research methods do not make full use of the structural information of the code. This paper raises a new model called G-DCS to automatically generate a summary of java code; the generated summary is designed to help programmers quickly comprehend the effect of java methods. G-DCS uses natural language processing technology, and training the model uses a code corpus. This model could generate code summaries directly from the code files in the coded corpus. Compared with the traditional method, it uses the information of structural on the code. Through Graph Convolutional Neural Network (GCN) extracts the structural information on the code to generate the code sequence, which makes the generated code summary more accurate. The corpus used for training was obtained from GitHub. Evaluation criteria using BLEU-n. Experimental results show that our approach outperforms models that do not utilize code structure information.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134031030","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 : 2023-07-01DOI: 10.53106/160792642023072404008
Yaru Zhang Yaru Zhang
This topic focuses on the corresponding research and simulation of multiple convolutional models for the detection methods of leaf pests and disease identification. Currently, crop pest identification in China mainly relies on field observation by farmers or experts, which is less accurate, time-consuming and extremely expensive, and not feasible for millions of small and medium-sized farms. To improve the recognition accuracy, crop pest recognition is performed by a convolutional neural network (CNN) after combining the plant leaf collection dataset, which has the features of automatic image feature extraction, strong generalization ability, and high recognition rate, and combined with the advantage of similarity by transfer learning, a crop pest recognition algorithm based on the comparison of multiple convolutional neural networks is implemented. After comparison experiments, the algorithm has 99.8% accuracy in the test set and can accurately distinguish seven health states of apples and grapes. This algorithm can help agricultural workers to conduct agricultural activities more scientifically, which is important for improving crop yield and agricultural intelligence.
{"title":"IoT Agricultural Pest Identification Based on Multiple Convolutional Models","authors":"Yaru Zhang Yaru Zhang","doi":"10.53106/160792642023072404008","DOIUrl":"https://doi.org/10.53106/160792642023072404008","url":null,"abstract":"\u0000 This topic focuses on the corresponding research and simulation of multiple convolutional models for the detection methods of leaf pests and disease identification. Currently, crop pest identification in China mainly relies on field observation by farmers or experts, which is less accurate, time-consuming and extremely expensive, and not feasible for millions of small and medium-sized farms. To improve the recognition accuracy, crop pest recognition is performed by a convolutional neural network (CNN) after combining the plant leaf collection dataset, which has the features of automatic image feature extraction, strong generalization ability, and high recognition rate, and combined with the advantage of similarity by transfer learning, a crop pest recognition algorithm based on the comparison of multiple convolutional neural networks is implemented. After comparison experiments, the algorithm has 99.8% accuracy in the test set and can accurately distinguish seven health states of apples and grapes. This algorithm can help agricultural workers to conduct agricultural activities more scientifically, which is important for improving crop yield and agricultural intelligence.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124097778","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 : 2023-07-01DOI: 10.53106/160792642023072404009
dan Zhang dan ZHANG, Ting-Jie Lu Dan Zhang, Wenyu Zhang Tingjie Lu, Chenxing Yang Wenyu Zhang
The systematic evaluation of informatization development level (IDL) is an evaluation that follows the development trend of digitization, networking and intelligence, and focuses on the formation of business capabilities of informatization. Research on informatization evaluation methods has been extensively studied by both domestic and international academics over the years. However, traditional evaluation methods suffer from flaws like complex mechanism design, unreliable metric conversion, difficulty obtaining the relative importance of indexes, complex evaluation process, and high computational volume. This paper attempts to introduce the neural network method into the information system evaluation, and uses the Extreme Learning Machine (ELM) algorithm to establish the evaluation model. The evaluation of the smart court system is used as an example to simulate and test the model, and the results show that the neural network-based evaluation model of informatization system is more applicable to large-scale evaluation indexes, and by continuously increasing the learning samples, it objectively improves the accuracy of evaluation, effectively avoids human subjective factors, and has the advantageous features of advanced, accurate and convenient.
{"title":"A Neural Network Method for Systematic Evaluation of Informatization Development Level in Smart Court Construction","authors":"dan Zhang dan ZHANG, Ting-Jie Lu Dan Zhang, Wenyu Zhang Tingjie Lu, Chenxing Yang Wenyu Zhang","doi":"10.53106/160792642023072404009","DOIUrl":"https://doi.org/10.53106/160792642023072404009","url":null,"abstract":"\u0000 The systematic evaluation of informatization development level (IDL) is an evaluation that follows the development trend of digitization, networking and intelligence, and focuses on the formation of business capabilities of informatization. Research on informatization evaluation methods has been extensively studied by both domestic and international academics over the years. However, traditional evaluation methods suffer from flaws like complex mechanism design, unreliable metric conversion, difficulty obtaining the relative importance of indexes, complex evaluation process, and high computational volume. This paper attempts to introduce the neural network method into the information system evaluation, and uses the Extreme Learning Machine (ELM) algorithm to establish the evaluation model. The evaluation of the smart court system is used as an example to simulate and test the model, and the results show that the neural network-based evaluation model of informatization system is more applicable to large-scale evaluation indexes, and by continuously increasing the learning samples, it objectively improves the accuracy of evaluation, effectively avoids human subjective factors, and has the advantageous features of advanced, accurate and convenient.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121365528","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 : 2023-07-01DOI: 10.53106/160792642023072404015
Yubin Qu Yubin Qu, Tie Bao Yubin Qu, Meng Yuan Tie Bao, Long Li Meng Yuan
Self-Admitted Technical Debt (SATD) is a workaround for current gains and subsequent software quality in software comments. Some studies have been conducted using NLP-based techniques or CNN-based classifiers. However, there exists a class imbalance problem in different software projects since the software code comments with SATD features are significantly less than those without Non-SATD. Therefore, to design a classification model with the ability of dealing with this class imbalance problem is necessary for SATD detection. We propose an improved loss function based on information entropy. Our proposed function is studied in a variety of application scenarios. Empirical research on 10 JAVA software projects is conducted to show the competitiveness of our new approach. We find our proposed approach can perform significantly better than state-of-the-art baselines.
{"title":"Deep Learning-Based Self-Admitted Technical Debt Detection Empirical Research","authors":"Yubin Qu Yubin Qu, Tie Bao Yubin Qu, Meng Yuan Tie Bao, Long Li Meng Yuan","doi":"10.53106/160792642023072404015","DOIUrl":"https://doi.org/10.53106/160792642023072404015","url":null,"abstract":"\u0000 Self-Admitted Technical Debt (SATD) is a workaround for current gains and subsequent software quality in software comments. Some studies have been conducted using NLP-based techniques or CNN-based classifiers. However, there exists a class imbalance problem in different software projects since the software code comments with SATD features are significantly less than those without Non-SATD. Therefore, to design a classification model with the ability of dealing with this class imbalance problem is necessary for SATD detection. We propose an improved loss function based on information entropy. Our proposed function is studied in a variety of application scenarios. Empirical research on 10 JAVA software projects is conducted to show the competitiveness of our new approach. We find our proposed approach can perform significantly better than state-of-the-art baselines. \u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"405 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126679054","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: 10.53106/160792642023052403014
C. R. K. C. Ramesh Kumar, T. G. K. C. Ramesh Kumar, A. H. T. Ganesh Kumar, D. R. T. A. Hemlathadhevi
A wireless network composed of wearable sensing along with computing systems connected via a wireless communication channel is termed Wireless Body Sensor Network (WBSN). It enables continuous monitoring through sensors for medical and nonmedical applications. WBSN faces several security problems such as loss of information, access control, and authentication. As WBSN collects vital information and operates in an unfriendly environment, severe security mechanisms are needed in order to prevent the network from anonymous interactions. The different security threats are evaluated with the support of the data transmitted via the sensor networks amongst smart wearable devices. The whole network lifetime together with the Data Transmission (DT) quality is mitigated whilst performing DT utilizing sensor networks, which consume more energy. Hence, in this paper, an energy-efficient secure data transmission mechanism is proposed in WBSN using a novel authentication id-based group signature model and SECC technique. At first, the Group Manager (GM) is selected from the sensors in the remote body sensor system using Normalized Opposition Based Learning BAT Optimization Algorithm (NOBL-BOA). Afterward, clustering with Information Entropy induced K-Means Algorithm (IEKMA) takes place to improve energy efficiency. Next, to provide security to the WBSN, message authentication is carried out based on novel authentication ID-based group signature protocol. Finally, Secret key induced Elliptic Curve Cryptography (SECC) is used to encrypt the message for secure transmission. The simulation results reveal that in comparison with existing works, the proposed work achieves improved security and energy efficiency.
{"title":"An Energy Efficiency Based Secure Data Transmission in WBSN Using Novel Id-Based Group Signature Model and SECC Technique","authors":"C. R. K. C. Ramesh Kumar, T. G. K. C. Ramesh Kumar, A. H. T. Ganesh Kumar, D. R. T. A. Hemlathadhevi","doi":"10.53106/160792642023052403014","DOIUrl":"https://doi.org/10.53106/160792642023052403014","url":null,"abstract":"\u0000 A wireless network composed of wearable sensing along with computing systems connected via a wireless communication channel is termed Wireless Body Sensor Network (WBSN). It enables continuous monitoring through sensors for medical and nonmedical applications. WBSN faces several security problems such as loss of information, access control, and authentication. As WBSN collects vital information and operates in an unfriendly environment, severe security mechanisms are needed in order to prevent the network from anonymous interactions. The different security threats are evaluated with the support of the data transmitted via the sensor networks amongst smart wearable devices. The whole network lifetime together with the Data Transmission (DT) quality is mitigated whilst performing DT utilizing sensor networks, which consume more energy. Hence, in this paper, an energy-efficient secure data transmission mechanism is proposed in WBSN using a novel authentication id-based group signature model and SECC technique. At first, the Group Manager (GM) is selected from the sensors in the remote body sensor system using Normalized Opposition Based Learning BAT Optimization Algorithm (NOBL-BOA). Afterward, clustering with Information Entropy induced K-Means Algorithm (IEKMA) takes place to improve energy efficiency. Next, to provide security to the WBSN, message authentication is carried out based on novel authentication ID-based group signature protocol. Finally, Secret key induced Elliptic Curve Cryptography (SECC) is used to encrypt the message for secure transmission. The simulation results reveal that in comparison with existing works, the proposed work achieves improved security and energy efficiency.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"40 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":"124473814","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}
With international travel trending toward globalization, countries are increasingly focusing on preserving their unique local cultures while maintaining awareness about global tourism perspectives. Since 2017, Taiwan’s Tourism Bureau proposed the Taiwanese Sustainable Tourism Development Program for further development, the Program aims to encourage local governments to promote “Time for Celebration – Taiwan Tourism Events” and create tourism event highlights by promoting developments in regional tourism and related industries. This study aims to explore the role of local residents in festivals from a sustainable development perspective using survey data. It examines local residents’ attitudes and support residents toward festivals. The study details the influence of local residents on festivals, which in turn, depends on the benefits visitors gain from such participation.
{"title":"Exploring the Sustainable Strategies to Reinforce the Benefit Awareness from Festival Events Management","authors":"Yu-San Ting Yu-San Ting, Yu-Lun Hsu Yu-San Ting, Pi-Tzong Jan Yu-Lun Hsu","doi":"10.53106/160792642023052403002","DOIUrl":"https://doi.org/10.53106/160792642023052403002","url":null,"abstract":"\u0000 With international travel trending toward globalization, countries are increasingly focusing on preserving their unique local cultures while maintaining awareness about global tourism perspectives. Since 2017, Taiwan’s Tourism Bureau proposed the Taiwanese Sustainable Tourism Development Program for further development, the Program aims to encourage local governments to promote “Time for Celebration – Taiwan Tourism Events” and create tourism event highlights by promoting developments in regional tourism and related industries. This study aims to explore the role of local residents in festivals from a sustainable development perspective using survey data. It examines local residents’ attitudes and support residents toward festivals. The study details the influence of local residents on festivals, which in turn, depends on the benefits visitors gain from such participation.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"44 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":"123559347","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: 10.53106/160792642023052403007
Jingyang Wang Jingyang Wang, Daoqun Liu Jingyang Wang, Lukai Jin Daoqun Liu, Qiuhong Sun Lukai Jin, Zhihong Xue Qiuhong Sun
Accurate stock price prediction is significant for investors to avoid risks and improve the return on investment. Stock price prediction is a typical nonlinear time-series problem, which many factors affect. Still, too much analysis of influencing factors will lead to input redundancy and a large amount of computation in the model. Although the stock prediction model based on Recurrent Neural Network (RNN) has a good prediction effect, it has the problem of oversaturation. This paper proposes a prediction model of stock closing price based on Principal Component Analysis (PCA) and Improved Gated Recurrent Unit (IGRU), PCA-IGRU. PCA can reduce the redundancy of input information without destroying the correlation of original data, thus reducing the time of model training and prediction. IGRU is an improved Gated Recurrent Unit (GRU) model, which prevents oversaturation by introducing the Anti-oversaturation Conversion Module (ACM) and enhances the sensitivity of model learning. This paper selects the stock trading data of the Shanghai Composite Index (SCI) of China as experimental data. The PCA-IGRU is compared with seven baseline models. The experimental results show that the model has better prediction accuracy and shorter training time.
{"title":"A PCA-IGRU Model for Stock Price Prediction","authors":"Jingyang Wang Jingyang Wang, Daoqun Liu Jingyang Wang, Lukai Jin Daoqun Liu, Qiuhong Sun Lukai Jin, Zhihong Xue Qiuhong Sun","doi":"10.53106/160792642023052403007","DOIUrl":"https://doi.org/10.53106/160792642023052403007","url":null,"abstract":"\u0000 Accurate stock price prediction is significant for investors to avoid risks and improve the return on investment. Stock price prediction is a typical nonlinear time-series problem, which many factors affect. Still, too much analysis of influencing factors will lead to input redundancy and a large amount of computation in the model. Although the stock prediction model based on Recurrent Neural Network (RNN) has a good prediction effect, it has the problem of oversaturation. This paper proposes a prediction model of stock closing price based on Principal Component Analysis (PCA) and Improved Gated Recurrent Unit (IGRU), PCA-IGRU. PCA can reduce the redundancy of input information without destroying the correlation of original data, thus reducing the time of model training and prediction. IGRU is an improved Gated Recurrent Unit (GRU) model, which prevents oversaturation by introducing the Anti-oversaturation Conversion Module (ACM) and enhances the sensitivity of model learning. This paper selects the stock trading data of the Shanghai Composite Index (SCI) of China as experimental data. The PCA-IGRU is compared with seven baseline models. The experimental results show that the model has better prediction accuracy and shorter training time.\u0000 \u0000","PeriodicalId":442331,"journal":{"name":"網際網路技術學刊","volume":"36 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":"128299914","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：