The K-means clustering algorithm can take a lot of time to converge, especially for large datasets in high dimension and a large number of clusters. By applying several enhancements it is possible to improve the performance without significantly changing the quality of the clustering. In this paper we first find a good clustering in a reduced-dimension version of the dataset, before fine-tuning the clustering in the original dimension. This saves time because accelerated K-means algorithms are fastest in low dimension, and the initial low-dimensional clustering bring us close to a good solution for the original data. We use random projection to reduce the dimension, as it is fast and maintains the cluster properties we want to preserve. In our experiments, we see that this approach significantly reduces the time needed for clustering a dataset and in most cases produces better results.
{"title":"Clustering Faster and Better with Projected Data","authors":"Alibek Zhakubayev, Greg Hamerly","doi":"10.1145/3546157.3546158","DOIUrl":"https://doi.org/10.1145/3546157.3546158","url":null,"abstract":"The K-means clustering algorithm can take a lot of time to converge, especially for large datasets in high dimension and a large number of clusters. By applying several enhancements it is possible to improve the performance without significantly changing the quality of the clustering. In this paper we first find a good clustering in a reduced-dimension version of the dataset, before fine-tuning the clustering in the original dimension. This saves time because accelerated K-means algorithms are fastest in low dimension, and the initial low-dimensional clustering bring us close to a good solution for the original data. We use random projection to reduce the dimension, as it is fast and maintains the cluster properties we want to preserve. In our experiments, we see that this approach significantly reduces the time needed for clustering a dataset and in most cases produces better results.","PeriodicalId":422215,"journal":{"name":"Proceedings of the 6th International Conference on Information System and Data Mining","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122768167","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}
Jefferson A. Costales, J. J. J. Catulay, Jeffrey Costales, Noel Bermudez
Technology allows us to progress and innovate in today's world, which advances at a faster pace. We innovate from traditional to digital life with the use of technology. There have been several technological advances, such as Mobile Gaming, that have occurred as a result of the evolution of technology. Gaming is a recreational pastime that has become available through technology in the form of apps for mobile devices. Technology is beneficial, but it also has a negative side effect: addiction. The goal of the study is to see if there is any link between a student's time spent playing mobile games and their social interactions. The study also attempts to discover different features that are important in mobile gaming addiction since they can be used to detect early signs of addiction. For the feature of importance, the researchers applied Random Forest Classifier. To ensure that the data is adequate, the study will employ factor analysis and Kaiser-Meyer-Olkin. This information can be utilized to improve the future study. The researchers gathered and used data from 513 college students from several Philippine universities.
{"title":"Kaiser-Meyer-Olkin Factor Analysis: A Quantitative Approach on Mobile Gaming Addiction using Random Forest Classifier","authors":"Jefferson A. Costales, J. J. J. Catulay, Jeffrey Costales, Noel Bermudez","doi":"10.1145/3546157.3546161","DOIUrl":"https://doi.org/10.1145/3546157.3546161","url":null,"abstract":"Technology allows us to progress and innovate in today's world, which advances at a faster pace. We innovate from traditional to digital life with the use of technology. There have been several technological advances, such as Mobile Gaming, that have occurred as a result of the evolution of technology. Gaming is a recreational pastime that has become available through technology in the form of apps for mobile devices. Technology is beneficial, but it also has a negative side effect: addiction. The goal of the study is to see if there is any link between a student's time spent playing mobile games and their social interactions. The study also attempts to discover different features that are important in mobile gaming addiction since they can be used to detect early signs of addiction. For the feature of importance, the researchers applied Random Forest Classifier. To ensure that the data is adequate, the study will employ factor analysis and Kaiser-Meyer-Olkin. This information can be utilized to improve the future study. The researchers gathered and used data from 513 college students from several Philippine universities.","PeriodicalId":422215,"journal":{"name":"Proceedings of the 6th International Conference on Information System and Data Mining","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131995396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Unified Modeling Language (UML) is considered the de facto standard for object-oriented software model development. This makes it appropriate to be used in academia courses at both the graduate and undergraduate levels of education. Some challenges to using the UML is academia are its large number of model concepts and the imprecise semantic of some of these concepts. These challenges are daunting for students who are being introduced to the UML. One approach that can be taken in teaching UML towards addressing these concerns is to limit the number of UML concepts taught and recognize that students may not be able to develop correct UML system models. This approach leads to research work that develop a limited set of UML model concepts that are fewer in number and have more precise semantics. In this paper, we present a new approach to resolve an aspect of this problem by simplifying the generalization/specialization semantics of the class diagram through the application of mathematical formality to usage of these class diagram concepts. This research work derives a core set of concepts suitable for graduate and undergraduate comprehension of UML modeling and defines more precise semantics for those modeling concepts. The applicable mathematical principles applied in this work are from the domains of set theory and predicate logic. This approach is particularly relevant for the pedagogy of software engineering and the development of software systems that require a high level of reliability.
{"title":"Towards Simplifying and Formalizing UML Class Diagram Generalization/Specialization Relationship with Mathematical Set Theory","authors":"Kruti Shah, Emanuel S. Grant","doi":"10.1145/3546157.3546171","DOIUrl":"https://doi.org/10.1145/3546157.3546171","url":null,"abstract":"The Unified Modeling Language (UML) is considered the de facto standard for object-oriented software model development. This makes it appropriate to be used in academia courses at both the graduate and undergraduate levels of education. Some challenges to using the UML is academia are its large number of model concepts and the imprecise semantic of some of these concepts. These challenges are daunting for students who are being introduced to the UML. One approach that can be taken in teaching UML towards addressing these concerns is to limit the number of UML concepts taught and recognize that students may not be able to develop correct UML system models. This approach leads to research work that develop a limited set of UML model concepts that are fewer in number and have more precise semantics. In this paper, we present a new approach to resolve an aspect of this problem by simplifying the generalization/specialization semantics of the class diagram through the application of mathematical formality to usage of these class diagram concepts. This research work derives a core set of concepts suitable for graduate and undergraduate comprehension of UML modeling and defines more precise semantics for those modeling concepts. The applicable mathematical principles applied in this work are from the domains of set theory and predicate logic. This approach is particularly relevant for the pedagogy of software engineering and the development of software systems that require a high level of reliability.","PeriodicalId":422215,"journal":{"name":"Proceedings of the 6th International Conference on Information System and Data Mining","volume":"94 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114040708","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}
Meiryani Meiryani, Cindy Cornelia, Satami Doi Kikkawa, H. Ulinnuha, Lidiyawati Lidiyawati
As we've seen in the history of IoT devices, connecting traditionally unconnected objects like the refrigerator at Carnegie Mellon has been possible since the early 1980s, but the costs are significant. This requires the processing power of the DEC PDP11 mainframe computer. Moore's Law demonstrates an increase in the number and density of transistors in silicon chipsets, while Dennard scaling improves the computer's power profile. Given these two trends, we are now producing devices that use more powerful CPUs and increased memory capacity and run operating systems capable of running the full network stack. Only with these requirements met, IoT has become an industry into itself.
{"title":"Examining User Acceptance and Adoption of the Internet of Things in Indonesia","authors":"Meiryani Meiryani, Cindy Cornelia, Satami Doi Kikkawa, H. Ulinnuha, Lidiyawati Lidiyawati","doi":"10.1145/3546157.3546176","DOIUrl":"https://doi.org/10.1145/3546157.3546176","url":null,"abstract":"As we've seen in the history of IoT devices, connecting traditionally unconnected objects like the refrigerator at Carnegie Mellon has been possible since the early 1980s, but the costs are significant. This requires the processing power of the DEC PDP11 mainframe computer. Moore's Law demonstrates an increase in the number and density of transistors in silicon chipsets, while Dennard scaling improves the computer's power profile. Given these two trends, we are now producing devices that use more powerful CPUs and increased memory capacity and run operating systems capable of running the full network stack. Only with these requirements met, IoT has become an industry into itself.","PeriodicalId":422215,"journal":{"name":"Proceedings of the 6th International Conference on Information System and Data Mining","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121315728","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 this paper we share interim results of an ongoing mixed method evaluative study of 43 students enrolled in an elective course “Doing Business with A.I.” at the Lee Kong Chian School of Business (LKCSB), Singapore Management University. A key component of the course design is an experiential chatbot workshop that provides non-STEM students with an opportunity to acquire basic skills to build a chatbot prototype using the ‘Dialogflow’ program. The workshop and the experiential learning activity were designed to impart students with relevant knowledge and skills such as conversation and user-centric design know how and know why that are transferrable to other situational contexts beyond the course. Based on ongoing class surveys and qualitative interviews with students, we are trying to corroborate a conceptual model developed from learning theories and models related to technology mediated learning (TML) aimed at measuring the effects of a hands-on knowledge-based chatbot workshop designed by the authors on students’ engagement and motivation as drivers of acquiring AI-related competencies such as natural language processing skills (NLP). One important didactical aspect during the design and roll-out of the chatbot workshop is that novice learners with no or very little knowledge about A.I. recognize and create the important linkage between knowledge inputs and outputs of NLP-powered conversational agents (chatbots) so that user queries are effectively addressed. The knowledge-based chatbot workshop design as described in the paper provides useful practical information for instructors interested in designing educational chatbot prototypes for effective digital teaching and learning in a business school (higher education) context that can be transferred to other organizational units beyond the university (e.g. quality customer service) in order to make learners future-ready.
{"title":"Engaging Undergraduate Students in an Introductory A.I. Course through a Knowledge-Based Chatbot Workshop","authors":"T. Menkhoff, Ying Qian Lydia Teo","doi":"10.1145/3546157.3546175","DOIUrl":"https://doi.org/10.1145/3546157.3546175","url":null,"abstract":"In this paper we share interim results of an ongoing mixed method evaluative study of 43 students enrolled in an elective course “Doing Business with A.I.” at the Lee Kong Chian School of Business (LKCSB), Singapore Management University. A key component of the course design is an experiential chatbot workshop that provides non-STEM students with an opportunity to acquire basic skills to build a chatbot prototype using the ‘Dialogflow’ program. The workshop and the experiential learning activity were designed to impart students with relevant knowledge and skills such as conversation and user-centric design know how and know why that are transferrable to other situational contexts beyond the course. Based on ongoing class surveys and qualitative interviews with students, we are trying to corroborate a conceptual model developed from learning theories and models related to technology mediated learning (TML) aimed at measuring the effects of a hands-on knowledge-based chatbot workshop designed by the authors on students’ engagement and motivation as drivers of acquiring AI-related competencies such as natural language processing skills (NLP). One important didactical aspect during the design and roll-out of the chatbot workshop is that novice learners with no or very little knowledge about A.I. recognize and create the important linkage between knowledge inputs and outputs of NLP-powered conversational agents (chatbots) so that user queries are effectively addressed. The knowledge-based chatbot workshop design as described in the paper provides useful practical information for instructors interested in designing educational chatbot prototypes for effective digital teaching and learning in a business school (higher education) context that can be transferred to other organizational units beyond the university (e.g. quality customer service) in order to make learners future-ready.","PeriodicalId":422215,"journal":{"name":"Proceedings of the 6th International Conference on Information System and Data Mining","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116439659","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}
Shota Tamaru, Hyuga Taki, Rune Usuki, T. Nakanishi
This paper presents a recipe recommendation method by similarity measure with food image recognition. In general, it is difficult for users with little cooking experience to find out what kind of dishes they can make from the ingredients they currently have. Therefore, we propose a system that recommends recipes based on the ingredients in the user's current inventory, thereby increasing the number of dishes in the user's cooking repertoire. This system uses camera images of foodstuffs as input, recognizes the foodstuffs, and searches for recipes. In the experiment, we conducted a questionnaire survey of the recognized food ingredients and a questionnaire survey of recipe suggestions, and the results showed that more than 3/4 of the respondents answered that the recognition results and recipe contents were correct for some of the images. In this way, possible for users to search for recipes with fewer steps.
{"title":"Recipe Recommendation Method by Similarity Measure with Food Image Recognition","authors":"Shota Tamaru, Hyuga Taki, Rune Usuki, T. Nakanishi","doi":"10.1145/3546157.3546170","DOIUrl":"https://doi.org/10.1145/3546157.3546170","url":null,"abstract":"This paper presents a recipe recommendation method by similarity measure with food image recognition. In general, it is difficult for users with little cooking experience to find out what kind of dishes they can make from the ingredients they currently have. Therefore, we propose a system that recommends recipes based on the ingredients in the user's current inventory, thereby increasing the number of dishes in the user's cooking repertoire. This system uses camera images of foodstuffs as input, recognizes the foodstuffs, and searches for recipes. In the experiment, we conducted a questionnaire survey of the recognized food ingredients and a questionnaire survey of recipe suggestions, and the results showed that more than 3/4 of the respondents answered that the recognition results and recipe contents were correct for some of the images. In this way, possible for users to search for recipes with fewer steps.","PeriodicalId":422215,"journal":{"name":"Proceedings of the 6th International Conference on Information System and Data Mining","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122189039","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}
Novelty modeling in unstructured text data is a research topic within the Natural Language Processing (NLP) Community. Effective novelty models can play a key role in providing relevant and interesting content to the users which is the central goal in many applications including education and recommender systems. This paper presents a framework for comparing different approaches and applications of computational models of novelty in unstructured text data. We focus on computational models that apply methods such as natural language processing and information theory. The framework provides an ontology for computational novelty with respect to the source of text data, methods for representing the data, and models for measuring novelty. We explore the value of the framework by applying it to research on computational novelty in news articles, research publications, books, and recipes. This framework is independent of the type of data in the items and can be used as a tool for researchers to study, compare, and extend existing computational novelty models and applications.
{"title":"A Framework for Exploring Computational Models of Novelty in Unstructured Text","authors":"M. Mohseni, M. Maher","doi":"10.1145/3546157.3546164","DOIUrl":"https://doi.org/10.1145/3546157.3546164","url":null,"abstract":"Novelty modeling in unstructured text data is a research topic within the Natural Language Processing (NLP) Community. Effective novelty models can play a key role in providing relevant and interesting content to the users which is the central goal in many applications including education and recommender systems. This paper presents a framework for comparing different approaches and applications of computational models of novelty in unstructured text data. We focus on computational models that apply methods such as natural language processing and information theory. The framework provides an ontology for computational novelty with respect to the source of text data, methods for representing the data, and models for measuring novelty. We explore the value of the framework by applying it to research on computational novelty in news articles, research publications, books, and recipes. This framework is independent of the type of data in the items and can be used as a tool for researchers to study, compare, and extend existing computational novelty models and applications.","PeriodicalId":422215,"journal":{"name":"Proceedings of the 6th International Conference on Information System and Data Mining","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128820694","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}
Purpose – This study aims to provide a systematic knowledge map for researchers who work in the field of enterprise social capital. Additionally, the aim is to help them quickly understand the trending research topics, hot spots and evolutionary trends from the context of incubation networks. Design/methodology/approach – The authors searched for 874 articles on corporate social capital from the Web of Science database source journals from 1986 to 2021. Then, CITESPACE and VOSviewer software are used to extract the fields of the literature and perform data visualization. Findings – The results show that the number of corporate social capital research papers under the incubation network increases year by year. At present, the research hotspots include social capital, corporate social responsibility, corporate performance, innovation, corporate management and governance, network and strategy. Research will be paid more attention to corporate social responsibility, social capital promotion of new enterprises under incubator network, and social capital accumulation of family enterprises. Incubation network provides an integrated platform for new enterprises to obtain external social capital, and strengthens the social capital of enterprises through cooperative relations. Originality/value – This paper adopts bibliometrics method to mine data and draws knowledge map to systematically reveal research progress and trend.
目的:本研究旨在为企业社会资本领域的研究者提供一个系统的知识图谱。此外，旨在帮助他们从孵化网络的背景下快速了解趋势研究主题，热点和进化趋势。设计/方法/方法-作者从1986年至2021年的Web of Science数据库源期刊中检索了874篇关于企业社会资本的文章。然后利用CITESPACE和VOSviewer软件提取文献字段并进行数据可视化。研究结果表明:孵化网络下的企业社会资本研究论文数量逐年增加。目前的研究热点包括社会资本、企业社会责任、企业绩效、创新、企业管理与治理、网络与战略。企业社会责任、孵化器网络下新企业的社会资本提升、家族企业的社会资本积累等方面的研究将更加关注。孵化网络为新企业获取外部社会资本提供了一个整合平台，通过合作关系强化企业的社会资本。原创性/价值——本文采用文献计量学方法挖掘数据，绘制知识图谱，系统揭示研究进展和趋势。
{"title":"A Visualized Knowledge Map of Enterprise Social Capital in the Context of Incubation Networks","authors":"Ke Ding, Hongxia Li","doi":"10.1145/3546157.3546174","DOIUrl":"https://doi.org/10.1145/3546157.3546174","url":null,"abstract":"Purpose – This study aims to provide a systematic knowledge map for researchers who work in the field of enterprise social capital. Additionally, the aim is to help them quickly understand the trending research topics, hot spots and evolutionary trends from the context of incubation networks. Design/methodology/approach – The authors searched for 874 articles on corporate social capital from the Web of Science database source journals from 1986 to 2021. Then, CITESPACE and VOSviewer software are used to extract the fields of the literature and perform data visualization. Findings – The results show that the number of corporate social capital research papers under the incubation network increases year by year. At present, the research hotspots include social capital, corporate social responsibility, corporate performance, innovation, corporate management and governance, network and strategy. Research will be paid more attention to corporate social responsibility, social capital promotion of new enterprises under incubator network, and social capital accumulation of family enterprises. Incubation network provides an integrated platform for new enterprises to obtain external social capital, and strengthens the social capital of enterprises through cooperative relations. Originality/value – This paper adopts bibliometrics method to mine data and draws knowledge map to systematically reveal research progress and trend.","PeriodicalId":422215,"journal":{"name":"Proceedings of the 6th International Conference on Information System and Data Mining","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125379664","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}
Customer lifetime value (CLV) is a powerful tool to determine the value of customers and filter customers most likely to attrite or most likely to make their first purchase, especially for e-commerce companies. This article reviewed machine learning models in analyzing CLV and prospected some potential directions for future research. Data of 8099 samples were collected and analyzed through four kinds of machine learning methods: Linear Regression, Support Vector Machine, Random Forest, Neural Network. The correlations between features showed that CLV are generally affected by monthly premium auto, total claim amount, and coverage. Analysis through machine learning models has high precision and Random Forest performs best. CLV prediction and customer segmentation are vital in business field today. Marketers could take advantage of the huge amount of data and machine learning models to portrait customer behaviors. Collecting browsing and purchase histories is also beneficial for providing best offers to individual customers.
{"title":"Customer Lifetime Value Analysis Based on Machine Learning","authors":"Xinqian Dai","doi":"10.1145/3546157.3546160","DOIUrl":"https://doi.org/10.1145/3546157.3546160","url":null,"abstract":"Customer lifetime value (CLV) is a powerful tool to determine the value of customers and filter customers most likely to attrite or most likely to make their first purchase, especially for e-commerce companies. This article reviewed machine learning models in analyzing CLV and prospected some potential directions for future research. Data of 8099 samples were collected and analyzed through four kinds of machine learning methods: Linear Regression, Support Vector Machine, Random Forest, Neural Network. The correlations between features showed that CLV are generally affected by monthly premium auto, total claim amount, and coverage. Analysis through machine learning models has high precision and Random Forest performs best. CLV prediction and customer segmentation are vital in business field today. Marketers could take advantage of the huge amount of data and machine learning models to portrait customer behaviors. Collecting browsing and purchase histories is also beneficial for providing best offers to individual customers.","PeriodicalId":422215,"journal":{"name":"Proceedings of the 6th International Conference on Information System and Data Mining","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124199332","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}
Traffic sign recognition plays a significant role in intelligent transportation system. Therefore, in this paper, I propose a traffic sign recognition algorithm based on Convolutional Neural Network (CNN). The dataset collected to train and test in experiments is the “German Traffic Sign Recognition Benchmark” (GTSRB). In addition, the CNN model is evaluated by comparing with a Deep Neural Network (DNN) model based on the accuracy rate and loss rate. Finally, the result shows the proposed CNN model yields high accuracy rate on both training and test images.
{"title":"Traffic Sign Recognition Based on Deep Learning Technique","authors":"Yihan Lai","doi":"10.1145/3546157.3546167","DOIUrl":"https://doi.org/10.1145/3546157.3546167","url":null,"abstract":"Traffic sign recognition plays a significant role in intelligent transportation system. Therefore, in this paper, I propose a traffic sign recognition algorithm based on Convolutional Neural Network (CNN). The dataset collected to train and test in experiments is the “German Traffic Sign Recognition Benchmark” (GTSRB). In addition, the CNN model is evaluated by comparing with a Deep Neural Network (DNN) model based on the accuracy rate and loss rate. Finally, the result shows the proposed CNN model yields high accuracy rate on both training and test images.","PeriodicalId":422215,"journal":{"name":"Proceedings of the 6th International Conference on Information System and Data Mining","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126144675","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：