Cancer, a disease that has gradually attracted attention in the world now, it has even become one of the main causes of death. Among them, liver cancer occurs in the liver or deadly tumors starting from the liver. According to the World Cancer Report (2014), the liver cancer is primary the cancer that the occurrence of 6% ranked second highest, and the death rate is 9% ranked sixth. So the liver cancer has become the target of academic research and discussion. If we can find out the key factors that affect the death of liver cancer when identifying liver cancer, it can improve the survival prediction of patients with liver cancer, and it will bring more effective treatment and confidence to the disease. In this paper, we chose a data that a real clinically diagnosed HCC patient was collected from a University of Coimbra and Coimbra Hospital in Portugal, and we separated the data into testing and training to predict the death of HCC and find out the key factors from the prediction model. The prediction model includes Decision Tree (DT), Support vector machine (SVM), and Logistic Regression (LR). The results of this paper showed that the G-means of the three modeling methods are 0.76 (LR), 0.72 (DT), and 0.68 (SVM). The best performance is logistic regression (LR), and find out the key factors that affect the survival rate of HCC include Aspartate transaminase (U / L), Age at diagnosis, and Alkaline phosphatase (U / L).
癌症，一种逐渐引起世界关注的疾病，甚至已经成为人类死亡的主要原因之一。其中肝癌发生在肝脏或从肝脏开始的致命肿瘤。根据《世界癌症报告(2014)》，肝癌是原发性癌症，发生率为6%，排名第二高，死亡率为9%，排名第六。因此肝癌已成为学术界研究和讨论的对象。如果我们在鉴别肝癌时能够找出影响肝癌死亡的关键因素，可以提高肝癌患者的生存预测，也会给疾病带来更有效的治疗和信心。在本文中，我们选择了来自葡萄牙科英布拉大学和科英布拉医院的真实临床诊断HCC患者的数据，我们将数据分为测试和训练两部分来预测HCC的死亡，并从预测模型中找出关键因素。预测模型包括决策树(DT)、支持向量机(SVM)和逻辑回归(LR)。结果表明，三种建模方法的g均值分别为0.76 (LR)、0.72 (DT)和0.68 (SVM)。采用logistic回归(LR)分析效果最佳，发现影响HCC生存率的关键因素有天冬氨酸转氨酶(U / L)、诊断时年龄(Age at diagnosis)和碱性磷酸酶(U / L)。
{"title":"Applying Artificial Intelligence to Survival Prediction of Hepatocellular Carcinoma Patients","authors":"Kun-Huang Chen, Hui-Wu Wang, Chung-Ming Liu","doi":"10.1145/3417188.3417197","DOIUrl":"https://doi.org/10.1145/3417188.3417197","url":null,"abstract":"Cancer, a disease that has gradually attracted attention in the world now, it has even become one of the main causes of death. Among them, liver cancer occurs in the liver or deadly tumors starting from the liver. According to the World Cancer Report (2014), the liver cancer is primary the cancer that the occurrence of 6% ranked second highest, and the death rate is 9% ranked sixth. So the liver cancer has become the target of academic research and discussion. If we can find out the key factors that affect the death of liver cancer when identifying liver cancer, it can improve the survival prediction of patients with liver cancer, and it will bring more effective treatment and confidence to the disease. In this paper, we chose a data that a real clinically diagnosed HCC patient was collected from a University of Coimbra and Coimbra Hospital in Portugal, and we separated the data into testing and training to predict the death of HCC and find out the key factors from the prediction model. The prediction model includes Decision Tree (DT), Support vector machine (SVM), and Logistic Regression (LR). The results of this paper showed that the G-means of the three modeling methods are 0.76 (LR), 0.72 (DT), and 0.68 (SVM). The best performance is logistic regression (LR), and find out the key factors that affect the survival rate of HCC include Aspartate transaminase (U / L), Age at diagnosis, and Alkaline phosphatase (U / L).","PeriodicalId":373913,"journal":{"name":"Proceedings of the 2020 4th International Conference on Deep Learning Technologies","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125879292","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}
Traditional design methods are inspired by introverted self-salvation or creativity-driven design. In the era of big data, they are gradually driven by vast data. Design innovation without data is increasingly lacking in persuasion. The design of data participation increasingly faces market risks. Moreover, with the progress of artificial intelligence, such a technological innovation will eventually deconstruct the existing field of design innovation, its impact will continue, and it may fundamentally spawn new design ideas and methods.
{"title":"The Development Trend of Design Methodology under the Influence of Artificial Intelligence and Big Data","authors":"W. Shu, Fuliang Sun, Yueen Li","doi":"10.1145/3417188.3417214","DOIUrl":"https://doi.org/10.1145/3417188.3417214","url":null,"abstract":"Traditional design methods are inspired by introverted self-salvation or creativity-driven design. In the era of big data, they are gradually driven by vast data. Design innovation without data is increasingly lacking in persuasion. The design of data participation increasingly faces market risks. Moreover, with the progress of artificial intelligence, such a technological innovation will eventually deconstruct the existing field of design innovation, its impact will continue, and it may fundamentally spawn new design ideas and methods.","PeriodicalId":373913,"journal":{"name":"Proceedings of the 2020 4th International Conference on Deep Learning Technologies","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115790374","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}
Based on the scores of selected undergraduates with two kinds of educational system in an ordinary university, with the help of variance analysis and multiple regression, the effects of different factors and their interaction on the total scores and the scores of moral, intellectual and physical courses are studied by using the ideas of discovering (the difference of students' scores in different categories), verifying (the effect of influential factors and their interaction on students' scores) and analyzing (trends and causes of scores changed based on different factors ). The key results are as follows: (1) College students' scores are significantly correlated with time, gender, birthplace, starting point for admission and their interaction, but the influence of different factors on each course is diverse. (2) The scores of female students are higher than those of male students, especially public courses; in addition to public courses, the scores of technical-school-source students are higher than those of high-school-source students, especially moral courses; students with high entrance score remain excellent in college, especially specialized courses. (3) The students in the 1st and 2nd years have the lowest academic performance, the reason of which are that many students failed; the grades of specialized course determine the total grades. (4) Curriculum classification plays a key role in studying influential factors of college students' scores. The research can provide reference for practical teaching work.
{"title":"An Empirical Analysis of the Influential Factors of College Students' Academic Performance","authors":"Yansha Guo","doi":"10.1145/3417188.3417212","DOIUrl":"https://doi.org/10.1145/3417188.3417212","url":null,"abstract":"Based on the scores of selected undergraduates with two kinds of educational system in an ordinary university, with the help of variance analysis and multiple regression, the effects of different factors and their interaction on the total scores and the scores of moral, intellectual and physical courses are studied by using the ideas of discovering (the difference of students' scores in different categories), verifying (the effect of influential factors and their interaction on students' scores) and analyzing (trends and causes of scores changed based on different factors ). The key results are as follows: (1) College students' scores are significantly correlated with time, gender, birthplace, starting point for admission and their interaction, but the influence of different factors on each course is diverse. (2) The scores of female students are higher than those of male students, especially public courses; in addition to public courses, the scores of technical-school-source students are higher than those of high-school-source students, especially moral courses; students with high entrance score remain excellent in college, especially specialized courses. (3) The students in the 1st and 2nd years have the lowest academic performance, the reason of which are that many students failed; the grades of specialized course determine the total grades. (4) Curriculum classification plays a key role in studying influential factors of college students' scores. The research can provide reference for practical teaching work.","PeriodicalId":373913,"journal":{"name":"Proceedings of the 2020 4th International Conference on Deep Learning Technologies","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114479004","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}
Under the background of education informationization, combining with the characteristics of "Production and Operation Management" curriculum and the problems in teaching, we design and practice an online teaching model based on "smart classroom". First, analyze the current teaching situation of the course "Production and Operation Management". Then, a three-stage online teaching model based on "smart classroom" is given. Finally, according to the characteristics of the curriculum, the online teaching implementation measures of the "production and operation management" course based on the "smart classroom" are formulated, and the practical effect analysis is conducted. It aims to meet the learning needs of students, stimulate students' interest in learning, cultivate students' autonomous learning ability and application innovation ability, and promote students' intelligent development. It also provides a reference to more effective online teaching during the epidemic.
{"title":"Design and Practice of Online Teaching Based on \"Smart Classroom\": Take the \"Production and Operations Management\" Course as an Example","authors":"Huaimin Li, Ying Yang, Huaming Liu","doi":"10.1145/3417188.3417202","DOIUrl":"https://doi.org/10.1145/3417188.3417202","url":null,"abstract":"Under the background of education informationization, combining with the characteristics of \"Production and Operation Management\" curriculum and the problems in teaching, we design and practice an online teaching model based on \"smart classroom\". First, analyze the current teaching situation of the course \"Production and Operation Management\". Then, a three-stage online teaching model based on \"smart classroom\" is given. Finally, according to the characteristics of the curriculum, the online teaching implementation measures of the \"production and operation management\" course based on the \"smart classroom\" are formulated, and the practical effect analysis is conducted. It aims to meet the learning needs of students, stimulate students' interest in learning, cultivate students' autonomous learning ability and application innovation ability, and promote students' intelligent development. It also provides a reference to more effective online teaching during the epidemic.","PeriodicalId":373913,"journal":{"name":"Proceedings of the 2020 4th International Conference on Deep Learning Technologies","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133108016","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 recent years, game theory has been widely used in the field of deep learning, mainly including intelligent competition strategies of complete information games and incomplete information games. This paper focuses on incomplete information games, and proposes a low-dimensional semantic feature based on category coding and an incomplete information competition strategy based on the improved Asynchronous Advantage Actor-Critic (A3C) network model. First, the A3C network model in deep reinforcement learning is adopted in the competition strategy, and its network structure is improved according to the semantic features based on category coding. The improved A3C model is implemented in parallel by a series of "workers". The "workers" is a new deep learning model structure proposed in this paper. Secondly, this article combines supervised learning and Deep Reinforcement Learning (DRL) to propose a new competitive strategy. Through conducting a large number of real-time experiments with human players on online competitive websites, the comparison with the existing methods in terms of the ratio of winning and losing and the ranking rate, the experimental results indicate the superiority of the new competitive strategy.
{"title":"Incomplete Information Competition Strategy Based on Improved Asynchronous Advantage Actor Critical Model","authors":"Cong Zhao, Bing Xiao, Lin Zha","doi":"10.1145/3417188.3417189","DOIUrl":"https://doi.org/10.1145/3417188.3417189","url":null,"abstract":"In recent years, game theory has been widely used in the field of deep learning, mainly including intelligent competition strategies of complete information games and incomplete information games. This paper focuses on incomplete information games, and proposes a low-dimensional semantic feature based on category coding and an incomplete information competition strategy based on the improved Asynchronous Advantage Actor-Critic (A3C) network model. First, the A3C network model in deep reinforcement learning is adopted in the competition strategy, and its network structure is improved according to the semantic features based on category coding. The improved A3C model is implemented in parallel by a series of \"workers\". The \"workers\" is a new deep learning model structure proposed in this paper. Secondly, this article combines supervised learning and Deep Reinforcement Learning (DRL) to propose a new competitive strategy. Through conducting a large number of real-time experiments with human players on online competitive websites, the comparison with the existing methods in terms of the ratio of winning and losing and the ranking rate, the experimental results indicate the superiority of the new competitive strategy.","PeriodicalId":373913,"journal":{"name":"Proceedings of the 2020 4th International Conference on Deep Learning Technologies","volume":"2015 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134406767","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 enhance the scientificity of practice teaching evaluation, this paper selected three primary indexes and 17 secondary indexes to construct a practice teaching evaluation system of the course Introduction to Logistics which based on analytic hierarchy process (AHP) and guided by Gagne's learning theory as well as three-stage control principle. This paper provided a relatively objective weight by analysis of quantitative results and put forward some suggestions to improve practice teaching level according to the weight information.
{"title":"Construction of Practice Teaching Evaluation System for Undergraduate Introduction to Logistics Based on AHP Method and Gagne's Learning Theory","authors":"Rong Zhou, Cuiling Guan","doi":"10.1145/3417188.3417208","DOIUrl":"https://doi.org/10.1145/3417188.3417208","url":null,"abstract":"In order to enhance the scientificity of practice teaching evaluation, this paper selected three primary indexes and 17 secondary indexes to construct a practice teaching evaluation system of the course Introduction to Logistics which based on analytic hierarchy process (AHP) and guided by Gagne's learning theory as well as three-stage control principle. This paper provided a relatively objective weight by analysis of quantitative results and put forward some suggestions to improve practice teaching level according to the weight information.","PeriodicalId":373913,"journal":{"name":"Proceedings of the 2020 4th International Conference on Deep Learning Technologies","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126772579","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：