Zhiwei Zeng, Simon Fauvel, Benny Toh Hsiang Tan, D. Wang, Yang Qiu, Pamela Chew Oi Khuan, Cyril Leung, Zhiqi Shen, J. Chin
Effective diagnosis of mild cognitive impairment (MCI), in many cases preceding dementia, is important in determining the efficacy of dementia treatments. Inherent in the transition from normal ageing to MCI to and then to dementia is cognitive decline, which can be detected using multiple assessments over an extended period of time. Computerized cognitive tests arise as a promising way of long-term cognitive monitoring in home environment and supplementing clinical evaluation. Compared to conventional paper-and-pencil tests, they are cheaper, more repeatable, and easier to distribute and administer. Over the years, research efforts have been devoted to improve the validity, reliability and comprehensiveness of the computerized cognitive tests. However, it has long been omitted that the usability and entertainment aspects are also crucial to their overall effectiveness and user experience. To reduce dropout rates and improve effectiveness of long-term cognitive monitoring, we present a first-of-its-kind gamified computerized cognitive test battery, called Virtual ADL+ House. It consists of a series of mini-games, each embedded a cognitive test and featured one of the daily living activities in the Lawton IADL. Virtual ADL+ House can be used to monitor cognitive functions in long-term, alert signs of cognitive decline and provide longitudinal data to facilitate clinical diagnosis. In focus group studies conducted with doctors and older adults, we received positive feedback on the usability and entertainment value of Virtual ADL+ House. We plan to evaluate the validity and reliability of it in subsequent studies.
{"title":"Towards Long-term Tracking and Detection of Early Dementia: A Computerized Cognitive Test Battery with Gamification","authors":"Zhiwei Zeng, Simon Fauvel, Benny Toh Hsiang Tan, D. Wang, Yang Qiu, Pamela Chew Oi Khuan, Cyril Leung, Zhiqi Shen, J. Chin","doi":"10.1145/3265689.3265719","DOIUrl":"https://doi.org/10.1145/3265689.3265719","url":null,"abstract":"Effective diagnosis of mild cognitive impairment (MCI), in many cases preceding dementia, is important in determining the efficacy of dementia treatments. Inherent in the transition from normal ageing to MCI to and then to dementia is cognitive decline, which can be detected using multiple assessments over an extended period of time. Computerized cognitive tests arise as a promising way of long-term cognitive monitoring in home environment and supplementing clinical evaluation. Compared to conventional paper-and-pencil tests, they are cheaper, more repeatable, and easier to distribute and administer. Over the years, research efforts have been devoted to improve the validity, reliability and comprehensiveness of the computerized cognitive tests. However, it has long been omitted that the usability and entertainment aspects are also crucial to their overall effectiveness and user experience.\u0000 To reduce dropout rates and improve effectiveness of long-term cognitive monitoring, we present a first-of-its-kind gamified computerized cognitive test battery, called Virtual ADL+ House. It consists of a series of mini-games, each embedded a cognitive test and featured one of the daily living activities in the Lawton IADL. Virtual ADL+ House can be used to monitor cognitive functions in long-term, alert signs of cognitive decline and provide longitudinal data to facilitate clinical diagnosis. In focus group studies conducted with doctors and older adults, we received positive feedback on the usability and entertainment value of Virtual ADL+ House. We plan to evaluate the validity and reliability of it in subsequent studies.","PeriodicalId":370356,"journal":{"name":"International Conference on Crowd Science and Engineering","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125656987","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 popularity of smart phones has made rapid development of crowdsourcing. The emergence of these crowdsourcing software has brought great convenience to our life. Traditional crowdsourcing platforms, such as Amazon Mechanical Turk and Crowdflower, publish some tasks on the site, Workers choose the tasks that are of interest and submit the answers to the tasks by browsing the tasks on the platform. And spatial crowdsourcing platforms (like gMission) are used to assign crowdsourcing tasks related to location. However, most crowdsourcing platforms support a small number of assignment and quality control algorithms. In this paper, a benchmark for spatial crowdsourcing platforms, called LBTask, is designed in order to adapt to the emergence of spatial crowdsourcing tasks, which focuses on solving location aware crowdsourcing tasks. Compared with other crowdsourcing platforms, LBTask can support various assignment and quality control algorithms in the architecture according to different strategies. In the distribution and assignment of tasks, the position factors of tasks and workers are taken into consideration in addition to considering the time and other factors.
{"title":"LBTask: A Benchmark for Spatial Crowdsourcing Platforms","authors":"Qian Yang, Li-zhen Cui, Miao Zheng, Shijun Liu, Wei Guo, Xudong Lu, Yongqing Zheng, Qingzhong Li","doi":"10.1145/3265689.3265716","DOIUrl":"https://doi.org/10.1145/3265689.3265716","url":null,"abstract":"The popularity of smart phones has made rapid development of crowdsourcing. The emergence of these crowdsourcing software has brought great convenience to our life. Traditional crowdsourcing platforms, such as Amazon Mechanical Turk and Crowdflower, publish some tasks on the site, Workers choose the tasks that are of interest and submit the answers to the tasks by browsing the tasks on the platform. And spatial crowdsourcing platforms (like gMission) are used to assign crowdsourcing tasks related to location. However, most crowdsourcing platforms support a small number of assignment and quality control algorithms. In this paper, a benchmark for spatial crowdsourcing platforms, called LBTask, is designed in order to adapt to the emergence of spatial crowdsourcing tasks, which focuses on solving location aware crowdsourcing tasks. Compared with other crowdsourcing platforms, LBTask can support various assignment and quality control algorithms in the architecture according to different strategies. In the distribution and assignment of tasks, the position factors of tasks and workers are taken into consideration in addition to considering the time and other factors.","PeriodicalId":370356,"journal":{"name":"International Conference on Crowd Science and Engineering","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116825857","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}
Human activity recognition plays an important role in people's daily life. However, it is often expensive and time-consuming to acquire sufficient labeled activity data. To solve this problem, transfer learning leverages the labeled samples from the source domain to annotate the target domain which has few or none labels. Unfortunately, when there are several source domains available, it is difficult to select the right source domains for transfer. The right source domain means that it has the most similar properties with the target domain, thus their similarity is higher, which can facilitate transfer learning. Choosing the right source domain helps the algorithm perform well and prevents the negative transfer. In this paper, we propose an effective Unsupervised Source Selection algorithm for Activity Recognition (USSAR). USSAR is able to select the most similar K source domains from a list of available domains. After this, we propose an effective Transfer Neural Network to perform knowledge transfer for Activity Recognition (TNNAR). TNNAR could capture both the time and spatial relationship between activities while transferring knowledge. Experiments on three public activity recognition datasets demonstrate that: 1) The USSAR algorithm is effective in selecting the best source domains. 2) The TNNAR method can reach high accuracy when performing activity knowledge transfer.
{"title":"Deep Transfer Learning for Cross-domain Activity Recognition","authors":"Jindong Wang, V. Zheng, Yiqiang Chen, Meiyu Huang","doi":"10.1145/3265689.3265705","DOIUrl":"https://doi.org/10.1145/3265689.3265705","url":null,"abstract":"Human activity recognition plays an important role in people's daily life. However, it is often expensive and time-consuming to acquire sufficient labeled activity data. To solve this problem, transfer learning leverages the labeled samples from the source domain to annotate the target domain which has few or none labels. Unfortunately, when there are several source domains available, it is difficult to select the right source domains for transfer. The right source domain means that it has the most similar properties with the target domain, thus their similarity is higher, which can facilitate transfer learning. Choosing the right source domain helps the algorithm perform well and prevents the negative transfer. In this paper, we propose an effective Unsupervised Source Selection algorithm for Activity Recognition (USSAR). USSAR is able to select the most similar K source domains from a list of available domains. After this, we propose an effective Transfer Neural Network to perform knowledge transfer for Activity Recognition (TNNAR). TNNAR could capture both the time and spatial relationship between activities while transferring knowledge. Experiments on three public activity recognition datasets demonstrate that: 1) The USSAR algorithm is effective in selecting the best source domains. 2) The TNNAR method can reach high accuracy when performing activity knowledge transfer.","PeriodicalId":370356,"journal":{"name":"International Conference on Crowd Science and Engineering","volume":"330 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134335705","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}
In1 this paper, we focus on providing a deep theoretical review and analysis of knowledge management. And we conduct both quantitative and qualitative studies. Firstly, we provide an overview of the knowledge management literature from 2005 to 2017 on a sample of 800 most relevant articles by CiteSpace. And this process includes both bibliometric and text mining analysis. We examine the impact of factors such as variations across publication years, the contribution of different countries, keywords statistics and most cited references. Next this study summarizes and analyses the theoretical conceptions of knowledge management which include definitions and stages about knowledge management. Then we review some major apporaches for designing the knowledge management system from different perspective including information technology tools, knowledge representation and organization, knowledge sharing, performance measure for knowledge management and intelligent applications for knowledge management. At last we investigate the major research trends in knowledge management and give some recommendations for future research of knowledge management.
{"title":"A review of knowledge management and future research trend","authors":"Tingwei Gao, Y. Chai, Yi Liu","doi":"10.1145/3126973.3126997","DOIUrl":"https://doi.org/10.1145/3126973.3126997","url":null,"abstract":"In1 this paper, we focus on providing a deep theoretical review and analysis of knowledge management. And we conduct both quantitative and qualitative studies. Firstly, we provide an overview of the knowledge management literature from 2005 to 2017 on a sample of 800 most relevant articles by CiteSpace. And this process includes both bibliometric and text mining analysis. We examine the impact of factors such as variations across publication years, the contribution of different countries, keywords statistics and most cited references. Next this study summarizes and analyses the theoretical conceptions of knowledge management which include definitions and stages about knowledge management. Then we review some major apporaches for designing the knowledge management system from different perspective including information technology tools, knowledge representation and organization, knowledge sharing, performance measure for knowledge management and intelligent applications for knowledge management. At last we investigate the major research trends in knowledge management and give some recommendations for future research of knowledge management.","PeriodicalId":370356,"journal":{"name":"International Conference on Crowd Science and Engineering","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126792789","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}
With1 the rapid growth of the internet of things (IoT) market and requirement, low power wide area (LPWA) technologies have become popular. In various LPWA technologies, Narrow Band IoT (NB-IoT) and long range (LoRa) are two main leading competitive technologies. Comparing to NB-IoT network that mainly built and managed by mobile network operators, LoRa wide-area network (LoRaWAN) is mainly operated by private companies or organizations, which will bring the trust issues between application customers and network operations. In this paper, we proposed a blockchain technology based solution to build an open, trusted, decentralized and tamper-proof system for LoRaWAN. To the best of our knowledge, this is the first work that integrating blockchain technology and LoRaWAN IoT technology.
{"title":"Using Blockchain Technology to Build Trust in Sharing LoRaWAN IoT","authors":"Jun Lin, Zhiqi Shen, C. Miao","doi":"10.1145/3126973.3126980","DOIUrl":"https://doi.org/10.1145/3126973.3126980","url":null,"abstract":"With1 the rapid growth of the internet of things (IoT) market and requirement, low power wide area (LPWA) technologies have become popular. In various LPWA technologies, Narrow Band IoT (NB-IoT) and long range (LoRa) are two main leading competitive technologies. Comparing to NB-IoT network that mainly built and managed by mobile network operators, LoRa wide-area network (LoRaWAN) is mainly operated by private companies or organizations, which will bring the trust issues between application customers and network operations. In this paper, we proposed a blockchain technology based solution to build an open, trusted, decentralized and tamper-proof system for LoRaWAN. To the best of our knowledge, this is the first work that integrating blockchain technology and LoRaWAN IoT technology.","PeriodicalId":370356,"journal":{"name":"International Conference on Crowd Science and Engineering","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128301352","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}
Li-zhen Cui, Xudong Zhao, Lei Liu, Han Yu, Yuan Miao
Efficient allocation of complex tasks, which typically include heterogeneous attributes such as value, difficulty, skill required, effort required and deadline, is a challenging open problem in crowdsourcing. Existing approaches are mostly designed based on expert knowledge and fail to leverage on user generated data to capture the complex interaction of crowdsourcing participants' behaviours. In this paper, we propose a data-driven learning approach to address this challenge. The proposed approach combines supervised learning and reinforcement learning to enable agents to imitate human task allocation strategies which have shown good performance. The policy network component selects task allocation strategies and the reputation network component calculates the trends of worker reputation fluctuations. The two networks have been trained and evaluated using a large-scale real human task allocation strategy dataset derived from the Agile Manager game. Extensive experiments based on this dataset demonstrate the validity and efficiency of our approach.
{"title":"Learning Complex Crowdsourcing Task Allocation Strategies from Humans","authors":"Li-zhen Cui, Xudong Zhao, Lei Liu, Han Yu, Yuan Miao","doi":"10.1145/3126973.3126988","DOIUrl":"https://doi.org/10.1145/3126973.3126988","url":null,"abstract":"Efficient allocation of complex tasks, which typically include heterogeneous attributes such as value, difficulty, skill required, effort required and deadline, is a challenging open problem in crowdsourcing. Existing approaches are mostly designed based on expert knowledge and fail to leverage on user generated data to capture the complex interaction of crowdsourcing participants' behaviours. In this paper, we propose a data-driven learning approach to address this challenge. The proposed approach combines supervised learning and reinforcement learning to enable agents to imitate human task allocation strategies which have shown good performance. The policy network component selects task allocation strategies and the reputation network component calculates the trends of worker reputation fluctuations. The two networks have been trained and evaluated using a large-scale real human task allocation strategy dataset derived from the Agile Manager game. Extensive experiments based on this dataset demonstrate the validity and efficiency of our approach.","PeriodicalId":370356,"journal":{"name":"International Conference on Crowd Science and Engineering","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128287354","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}
This 1 paper aims to study the material conscious information network(MCIN) to present new models of clothing products and persons and propose new crowd-designing patterns to reconstruct an improved supply-demand relationship in clothing industry. Compared to traditional, large-scaled and one-styled design patterns in clothing industry, we propose some new design patterns based on Crowd Science. In order to operate such patterns to achieve clothing customization, new models of persons and clothing are necessary. Different from most related works just focusing on the physiology dimension in the matching of customer and clothing, we propose that the dimension of physiology, character, knowledge and experience should be synthetically considered. That's how the Crowd-designing Clothing Industry(CDCI) to be modeled. At last, we implement a prototype system of novel E-commerce platform based on the CDCI to illustrate the effectiveness and soundness of the CDCI modeling.
本文旨在通过材料意识信息网络(material conscious information network, MCIN)的研究，呈现服装产品和人的新模式，提出新的人群设计模式，重构服装产业的优化供需关系。对比服装行业传统的、大规模的、单一风格的设计模式，提出了基于人群科学的设计模式。为了操作这样的模式来实现服装定制，需要新的人物和服装模型。与大多数相关工作只关注顾客与服装搭配中的生理维度不同，我们提出要综合考虑生理、性格、知识和经验的维度。这就是大众设计服装业(CDCI)的模式。最后，我们实现了一个基于CDCI的新型电子商务平台原型系统，以说明CDCI建模的有效性和合理性。
{"title":"A MCIN-based Model of Crowd-designing Clothing Industry","authors":"Yixuan Nan, Yi Liu, Jianping Shen, Y. Chai","doi":"10.1145/3126973.3126998","DOIUrl":"https://doi.org/10.1145/3126973.3126998","url":null,"abstract":"This 1 paper aims to study the material conscious information network(MCIN) to present new models of clothing products and persons and propose new crowd-designing patterns to reconstruct an improved supply-demand relationship in clothing industry. Compared to traditional, large-scaled and one-styled design patterns in clothing industry, we propose some new design patterns based on Crowd Science. In order to operate such patterns to achieve clothing customization, new models of persons and clothing are necessary. Different from most related works just focusing on the physiology dimension in the matching of customer and clothing, we propose that the dimension of physiology, character, knowledge and experience should be synthetically considered. That's how the Crowd-designing Clothing Industry(CDCI) to be modeled. At last, we implement a prototype system of novel E-commerce platform based on the CDCI to illustrate the effectiveness and soundness of the CDCI modeling.","PeriodicalId":370356,"journal":{"name":"International Conference on Crowd Science and Engineering","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127291432","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}
Some1 platform enterprises in the Internet industry have formed a monopoly or monopoly trends, and the Internet antitrust problem has become a research hotspot. However, the use of market share as an anti-monopoly judgment is biased So we take e-commerce enterprises as an example and measure the market power of Internet platform enterprises by using the new empirical industrial organization (NEIO) methods The research shows that the high market share of large Internet platform enterprises hasn't had market power, and the whole industry still maintains high levels of competition. The conclusion of this paper provides a new foothold for regulation.
{"title":"Will the Monopolistic Market Structure Produce Market Power?: a direct measure of market power of Internet platform enterprises","authors":"Baowen Sun, Wenjun Jing, Xuankai Zhao, Yi He","doi":"10.1145/3126973.3126983","DOIUrl":"https://doi.org/10.1145/3126973.3126983","url":null,"abstract":"Some1 platform enterprises in the Internet industry have formed a monopoly or monopoly trends, and the Internet antitrust problem has become a research hotspot. However, the use of market share as an anti-monopoly judgment is biased So we take e-commerce enterprises as an example and measure the market power of Internet platform enterprises by using the new empirical industrial organization (NEIO) methods The research shows that the high market share of large Internet platform enterprises hasn't had market power, and the whole industry still maintains high levels of competition. The conclusion of this paper provides a new foothold for regulation.","PeriodicalId":370356,"journal":{"name":"International Conference on Crowd Science and Engineering","volume":"225 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116202638","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}
Xinping Min, Yuliang Shi, Li-zhen Cui, Han Yu, Yuan Miao
To mitigate uncertainty in the quality of online purchases (e.g., e-commerce), many people rely on review comments from others in their decision-making processes. The key challenge in this situation is how to identify useful comments among a large corpus of candidate review comments with potentially varying usefulness. In this paper, we propose the Reliable Review Evaluation Framework (RREF) which combines crowdsourcing with machine learning to address this problem. To improve crowdsourcing quality control, we propose a novel review query crowdsourcing approach which jointly considers workers' track records in review provision and current workloads when allocating review comments for workers to rate. Using the ratings crowdsourced from workers, RREF then enhances the adaptive topic classification model selection and weighting functions of AdaBoost with dynamic keyword list reconstruction. RREF has been compared with state-of-the-art related frameworks using a large-scale real-world dataset, and demonstrated over 50% reduction in average classification errors.
{"title":"Efficient Crowd-Powered Active Learning for Reliable Review Evaluation","authors":"Xinping Min, Yuliang Shi, Li-zhen Cui, Han Yu, Yuan Miao","doi":"10.1145/3126973.3129307","DOIUrl":"https://doi.org/10.1145/3126973.3129307","url":null,"abstract":"To mitigate uncertainty in the quality of online purchases (e.g., e-commerce), many people rely on review comments from others in their decision-making processes. The key challenge in this situation is how to identify useful comments among a large corpus of candidate review comments with potentially varying usefulness. In this paper, we propose the Reliable Review Evaluation Framework (RREF) which combines crowdsourcing with machine learning to address this problem. To improve crowdsourcing quality control, we propose a novel review query crowdsourcing approach which jointly considers workers' track records in review provision and current workloads when allocating review comments for workers to rate. Using the ratings crowdsourced from workers, RREF then enhances the adaptive topic classification model selection and weighting functions of AdaBoost with dynamic keyword list reconstruction. RREF has been compared with state-of-the-art related frameworks using a large-scale real-world dataset, and demonstrated over 50% reduction in average classification errors.","PeriodicalId":370356,"journal":{"name":"International Conference on Crowd Science and Engineering","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127571864","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 extract structured medical information and related temporal information from online health communities, an integrate method based on syntactic parsing was proposed in this paper. We treated the extraction of medical and temporal phrases as a series tagging problem and trained two conditional random fled model respectively. The temporal relation identification is considered as a classification task and several support vector machine classifiers are built in the proposed method. For the feature engineering, we extracted some high level semantic features including co-reference relationship of medical concepts and the semantic similarity among tokens. The experiment results show that the proposed method has good performance in both phrase recognition and relation classification and could helped to automatically display a patient's clinical situation in chronological order.
{"title":"Extracting Temporal Information from Online Health Communities","authors":"Lichao Zhu, Hangzhou Yang, Zhijun Yan","doi":"10.1145/3126973.3126975","DOIUrl":"https://doi.org/10.1145/3126973.3126975","url":null,"abstract":"In order to extract structured medical information and related temporal information from online health communities, an integrate method based on syntactic parsing was proposed in this paper. We treated the extraction of medical and temporal phrases as a series tagging problem and trained two conditional random fled model respectively. The temporal relation identification is considered as a classification task and several support vector machine classifiers are built in the proposed method. For the feature engineering, we extracted some high level semantic features including co-reference relationship of medical concepts and the semantic similarity among tokens. The experiment results show that the proposed method has good performance in both phrase recognition and relation classification and could helped to automatically display a patient's clinical situation in chronological order.","PeriodicalId":370356,"journal":{"name":"International Conference on Crowd Science and Engineering","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124918485","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：