Pub Date : 2019-03-14DOI: 10.1109/INFOCT.2019.8711380
K. Utsu, Shun Ueta, S. Tajima, Y. Kajita, Y. Murakami, O. Uchida
We have developed a web system, Disaster Information Tweeting and Mapping System (DITS/DIMS) to facilitate information sharing in disaster situations because of frequent large-scale natural disasters occurring in Japan. Moreover, we have held town watching workshops in terms of disaster prevention and mitigation. One such town watching workshop using DITS/DIMS was held on October 2018 in Minami Wards, Sapporo City, Japan. The area was affected by the Hokkaido Eastern Iburi Earthquake in September 2018. The outcome of the workshop is presented in this paper.
{"title":"Town Watching Workshop Using DITS/DIMS in Community Affected by 2018 Hokkaido Eastern Iburi Earthquake in Japan","authors":"K. Utsu, Shun Ueta, S. Tajima, Y. Kajita, Y. Murakami, O. Uchida","doi":"10.1109/INFOCT.2019.8711380","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8711380","url":null,"abstract":"We have developed a web system, Disaster Information Tweeting and Mapping System (DITS/DIMS) to facilitate information sharing in disaster situations because of frequent large-scale natural disasters occurring in Japan. Moreover, we have held town watching workshops in terms of disaster prevention and mitigation. One such town watching workshop using DITS/DIMS was held on October 2018 in Minami Wards, Sapporo City, Japan. The area was affected by the Hokkaido Eastern Iburi Earthquake in September 2018. The outcome of the workshop is presented in this paper.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121819981","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 : 2019-03-14DOI: 10.1109/INFOCT.2019.8711180
Yi Wang, Tao Li, Fangdong Zhu
Negative selection algorithm is an important algorithm in the artificial immune system, inspired by the biological immune system. Traditional negative selection algorithms lack adaptive learning ability in high-dimensional space due to data sparsity and meaningless distance measurement. To solve these problems, an improved negative selection algorithm called Negative Selection Algorithm with Complete Random Subspace Technique (RS-NSA), is proposed in this paper. It adopts a bootstrap method to reduce the rate of misclassification resulting from the anomalies covered by the regions of normal samples. By using the complete random subspace technology, it reduces dimensionality to alleviate the curse of dimensionality. In addition, the ensemble learning technique is introduced to improve accuracy, in which component classifiers can be replaced by any negative selection algorithm. Empirical evaluation on UCI datasets reveals that, compared with V-detector, our proposed method can not only achieve a higher detection rate and a lower false alarm rate, but also shorten the training time.
{"title":"Augmented Negative Selection Algorithm with Complete Random Subspace Technique for Anomaly Detection","authors":"Yi Wang, Tao Li, Fangdong Zhu","doi":"10.1109/INFOCT.2019.8711180","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8711180","url":null,"abstract":"Negative selection algorithm is an important algorithm in the artificial immune system, inspired by the biological immune system. Traditional negative selection algorithms lack adaptive learning ability in high-dimensional space due to data sparsity and meaningless distance measurement. To solve these problems, an improved negative selection algorithm called Negative Selection Algorithm with Complete Random Subspace Technique (RS-NSA), is proposed in this paper. It adopts a bootstrap method to reduce the rate of misclassification resulting from the anomalies covered by the regions of normal samples. By using the complete random subspace technology, it reduces dimensionality to alleviate the curse of dimensionality. In addition, the ensemble learning technique is introduced to improve accuracy, in which component classifiers can be replaced by any negative selection algorithm. Empirical evaluation on UCI datasets reveals that, compared with V-detector, our proposed method can not only achieve a higher detection rate and a lower false alarm rate, but also shorten the training time.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122426659","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 : 2019-03-14DOI: 10.1109/INFOCT.2019.8711346
Kang Namseon, Jeong Yujun, Son Gumjun
In this paper, we developed a Navigation monitoring and Assistance service data model for SMART-Navigation project. In order to develop a data model, we analyzed the status of maritime data exchange standard and procedure. We developed accident management application schema, feature catalog and portrayal catalog in accordance with S-100 standard data model development procedure by collecting requirements related services and referring to related standards. In order to verify accident management model, we test data set based on Gwang-yang Port. The model and test data verified verification software, and it was confirmed that the designated symbol was displayed at the correct position through the S-100 simple viewer.
{"title":"Development of Navigation Monitoring & Assistance Service Data Model","authors":"Kang Namseon, Jeong Yujun, Son Gumjun","doi":"10.1109/INFOCT.2019.8711346","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8711346","url":null,"abstract":"In this paper, we developed a Navigation monitoring and Assistance service data model for SMART-Navigation project. In order to develop a data model, we analyzed the status of maritime data exchange standard and procedure. We developed accident management application schema, feature catalog and portrayal catalog in accordance with S-100 standard data model development procedure by collecting requirements related services and referring to related standards. In order to verify accident management model, we test data set based on Gwang-yang Port. The model and test data verified verification software, and it was confirmed that the designated symbol was displayed at the correct position through the S-100 simple viewer.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115315186","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 : 2019-03-14DOI: 10.1109/INFOCT.2019.8711024
Kaicong Wei, Ying Gao, W. Zhang, Sheng-Ling Lin
Path optimization is especially useful for improving freight efficiency, and the problem of finding the maximum load path is an important issue in path optimization. Although the problem of finding the shortest path is similar to the problem of finding the maximum load path, the Dijkstra’s algorithm for solving the problem of finding the shortest path is not suitable for solving the problem of finding the maximum load path. In this paper, the Dijkstra’s algorithm for solving the problem of finding the shortest path is introduced, and the Dijkstra’s algorithm is modified to solve the problem of finding the maximum load path. Finally, the running process of the modified Dijkstra’s algorithm is described by an example.
{"title":"A Modified Dijkstra’s Algorithm for Solving the Problem of Finding the Maximum Load Path","authors":"Kaicong Wei, Ying Gao, W. Zhang, Sheng-Ling Lin","doi":"10.1109/INFOCT.2019.8711024","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8711024","url":null,"abstract":"Path optimization is especially useful for improving freight efficiency, and the problem of finding the maximum load path is an important issue in path optimization. Although the problem of finding the shortest path is similar to the problem of finding the maximum load path, the Dijkstra’s algorithm for solving the problem of finding the shortest path is not suitable for solving the problem of finding the maximum load path. In this paper, the Dijkstra’s algorithm for solving the problem of finding the shortest path is introduced, and the Dijkstra’s algorithm is modified to solve the problem of finding the maximum load path. Finally, the running process of the modified Dijkstra’s algorithm is described by an example.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127473306","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 : 2019-03-14DOI: 10.1109/INFOCT.2019.8711355
Iheb Abdellatif
Several universities in the world have taken the path to become smart universities. The main purpose of such move is to increase the education quality and to provide students/teachers a safe and comfortable environment. A smart university consists of several smart components: smart classroom, smart parking, smart maintenance, smart traffic flow management, etc. In this paper we propose to design and implement smart classrooms. The other smart components will be the subject of future research projects. Nowadays, smart classrooms are based on Internet of Things (IoT). However, IoT based systems tend to become more and more complex over the time. This complexity is related to the increasing number of IoT platforms, technologies and components (hardware and software), as well as the increasing number of vendors in this evolving ecosystem. This situation makes selecting the appropriate IoT system for smart classrooms a time-consuming challenge, especially since several actors (Teachers, Students, Managers, IT specialists, Financial officials, etc.) may participate in such process of selecting the most suitable IoT systems for a smart classroom; with each of them viewing and acting on the choice of IoT systems from one single perspective at a time. This paper proposes a multi-perspective decision-making approach in order to assist managers in the process of selecting the most suitable IoT systems for smart classrooms. This approach is promising because of its ability to: (1) represent graphically all the perspectives of an IoT system and (2) measure the compliance of an IoT system with the smart classrooms’ requirements.
{"title":"Towards A Novel Approach for Designing Smart Classrooms","authors":"Iheb Abdellatif","doi":"10.1109/INFOCT.2019.8711355","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8711355","url":null,"abstract":"Several universities in the world have taken the path to become smart universities. The main purpose of such move is to increase the education quality and to provide students/teachers a safe and comfortable environment. A smart university consists of several smart components: smart classroom, smart parking, smart maintenance, smart traffic flow management, etc. In this paper we propose to design and implement smart classrooms. The other smart components will be the subject of future research projects. Nowadays, smart classrooms are based on Internet of Things (IoT). However, IoT based systems tend to become more and more complex over the time. This complexity is related to the increasing number of IoT platforms, technologies and components (hardware and software), as well as the increasing number of vendors in this evolving ecosystem. This situation makes selecting the appropriate IoT system for smart classrooms a time-consuming challenge, especially since several actors (Teachers, Students, Managers, IT specialists, Financial officials, etc.) may participate in such process of selecting the most suitable IoT systems for a smart classroom; with each of them viewing and acting on the choice of IoT systems from one single perspective at a time. This paper proposes a multi-perspective decision-making approach in order to assist managers in the process of selecting the most suitable IoT systems for smart classrooms. This approach is promising because of its ability to: (1) represent graphically all the perspectives of an IoT system and (2) measure the compliance of an IoT system with the smart classrooms’ requirements.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128811156","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 : 2019-03-14DOI: 10.1109/INFOCT.2019.8710862
Meng-Hsuan Tsai, Jia-Ning Luo, Ming-Hour Yang, N. Lo
Police often use location tracking technologies to monitor or track the locations of suspects. In densely populated urban areas, wireless positioning is often unable to retrieve the exact locations of suspects. This paper presents a passive location tracking system by using low-cost IoT devices to predict the footprints of suspects. When the IoT devices capture wireless signals, they can upload the observation data to a cloud server. The cloud server can quickly analyze and locate the footprints of the suspect.
{"title":"Location Tracking and Forensic Analysis of Criminal Suspects’ Footprints","authors":"Meng-Hsuan Tsai, Jia-Ning Luo, Ming-Hour Yang, N. Lo","doi":"10.1109/INFOCT.2019.8710862","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8710862","url":null,"abstract":"Police often use location tracking technologies to monitor or track the locations of suspects. In densely populated urban areas, wireless positioning is often unable to retrieve the exact locations of suspects. This paper presents a passive location tracking system by using low-cost IoT devices to predict the footprints of suspects. When the IoT devices capture wireless signals, they can upload the observation data to a cloud server. The cloud server can quickly analyze and locate the footprints of the suspect.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128433740","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 : 2019-03-14DOI: 10.1109/INFOCT.2019.8710946
O. Inam, M. Qureshi, Hamza Akram, H. Omer, Zoia Laraib
Magnetic Resonance Imaging (MRI) is a noninvasive and powerful technique for clinical diagnosis and treatment monitoring. However, long data acquisition time in conventional MRI may cause patient discomfort and compliance. Recently, parallel magnetic resonance imaging (pMRI) techniques have been developed to speed-up the MR data acquisition time by collecting a reduced data set (k-space) using multi-channel receiver coils. However, with an increasing number of receiver coils, the handling and processing of a massive MR data limits the performance of pMRI techniques in terms of reconstruction time. Therefore, in real-time clinical settings, high speed systems have become imperative to meet the large data processing requirements of pMRI technique i.e. Generalized Auto-calibrating Partially Parallel Acquisition (GRAPPA). Graphics processing units (GPUs) have recently emerged as a viable solution to adhere the rising demands of fast data processing in pMRI. This work presents the GPU accelerated GRAPPA reconstruction method using optimized CUDA kernels to obtain high-speed reconstructions, where multiple threads simultaneously communicate and cooperate to exploit the fine grained parallelism of GRAPPA reconstruction process. For a fair comparison, the performance of the proposed GPU based GRAPPA reconstruction is evaluated against CPU based GRAPPA. Several experiments against various GRAPPA configuration settings are performed using 8-channel in-vivo 1.5T human head datasets. Experimental results show that the proposed method speeds up the GRAPPA reconstruction time up to 15x without compromising the image quality.
{"title":"Accelerating Parallel Magnetic Resonance Image Reconstruction on Graphics Processing Units Using CUDA","authors":"O. Inam, M. Qureshi, Hamza Akram, H. Omer, Zoia Laraib","doi":"10.1109/INFOCT.2019.8710946","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8710946","url":null,"abstract":"Magnetic Resonance Imaging (MRI) is a noninvasive and powerful technique for clinical diagnosis and treatment monitoring. However, long data acquisition time in conventional MRI may cause patient discomfort and compliance. Recently, parallel magnetic resonance imaging (pMRI) techniques have been developed to speed-up the MR data acquisition time by collecting a reduced data set (k-space) using multi-channel receiver coils. However, with an increasing number of receiver coils, the handling and processing of a massive MR data limits the performance of pMRI techniques in terms of reconstruction time. Therefore, in real-time clinical settings, high speed systems have become imperative to meet the large data processing requirements of pMRI technique i.e. Generalized Auto-calibrating Partially Parallel Acquisition (GRAPPA). Graphics processing units (GPUs) have recently emerged as a viable solution to adhere the rising demands of fast data processing in pMRI. This work presents the GPU accelerated GRAPPA reconstruction method using optimized CUDA kernels to obtain high-speed reconstructions, where multiple threads simultaneously communicate and cooperate to exploit the fine grained parallelism of GRAPPA reconstruction process. For a fair comparison, the performance of the proposed GPU based GRAPPA reconstruction is evaluated against CPU based GRAPPA. Several experiments against various GRAPPA configuration settings are performed using 8-channel in-vivo 1.5T human head datasets. Experimental results show that the proposed method speeds up the GRAPPA reconstruction time up to 15x without compromising the image quality.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131086567","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 : 2019-03-14DOI: 10.1109/INFOCT.2019.8710981
Ya-ping Huang, Linghua Zhang
In wireless sensor networks, DV-Hop localization algorithm which uses average hop distance to represent the actual distance is a commonly used range-free localization technology. But this algorithm has great error and node energy consumption in practical applications. Evolutionary algorithm has a branch which is differential evolution algorithm. DE algorithm has been widely used in a large number of fields, as a result of DE algorithm has simple structure and can combine with other methods easily. To solve the disadvantages of DV-Hop algorithm, an advanced DV-Hop localization algorithm on basic of differential evolution in this paper has been proposed. To reduce the hop distance error, the improved algorithm advances weighted process in the second step of DV-hop algorithm by leading the average hop distance error correction value. The differential evolution algorithm is used to optimize the positioning result of the unknown node in the third step of DV-hop algorithm. From the advanced localization algorithm’s simulation, the positioning accuracy has improved.
{"title":"Weighted DV-Hop Localization Algorithm for Wireless Sensor Network based on Differential Evolution Algorithm","authors":"Ya-ping Huang, Linghua Zhang","doi":"10.1109/INFOCT.2019.8710981","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8710981","url":null,"abstract":"In wireless sensor networks, DV-Hop localization algorithm which uses average hop distance to represent the actual distance is a commonly used range-free localization technology. But this algorithm has great error and node energy consumption in practical applications. Evolutionary algorithm has a branch which is differential evolution algorithm. DE algorithm has been widely used in a large number of fields, as a result of DE algorithm has simple structure and can combine with other methods easily. To solve the disadvantages of DV-Hop algorithm, an advanced DV-Hop localization algorithm on basic of differential evolution in this paper has been proposed. To reduce the hop distance error, the improved algorithm advances weighted process in the second step of DV-hop algorithm by leading the average hop distance error correction value. The differential evolution algorithm is used to optimize the positioning result of the unknown node in the third step of DV-hop algorithm. From the advanced localization algorithm’s simulation, the positioning accuracy has improved.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"311 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121433224","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 : 2019-03-14DOI: 10.1109/INFOCT.2019.8711372
Amma Kazuo
An Excel form was developed by the author for calculating partial scoring of item reordering questions. It is a transplant of the algorithm realised in an application also devised by the author for the same purpose of calculation. Whereas the computer application is quick and efficient, the internal mechanism is a blackbox to general users unless the coding is understood. The present tool shows explicitly how each step of calculation is combined to reach the final score, together with possible combinations of partially correct elements within a target sequence. Given a correct answer A-B-C-D-E, a test-taker answer C-D-A-B-E, for instance, will be evaluated for two partial sequences C-D-E or A-B-E. In these partial sequences (Maximal Relative Sequences), elements run in an ascending order while allowing gaps, and they are the longest possible sequences. The partial score is 2, counting the number of transitions of elements, out of the full score of 4. Any MRS is a result of dislocating elements from the correct answer, which is measurable by ‘Minimal Edit Distance’ (MED). Unlike MED, MRS is locally calculable and therefore eligible for Excel transplantation. This paper explains how each step of forming an MRS is conducted. Despite limitations of memory, the present Excel form is a popular tool which helps users to understand the rationale behind MRS, and of more practical significance it is a convenient tool to get partial scores by simply copying and pasting test-taker answers.
作者开发了一个Excel表格，用于计算项目重新排序问题的部分得分。它是作者为同样的计算目的而设计的一个应用程序中实现的算法的移植。虽然计算机应用程序是快速和高效的，但其内部机制对一般用户来说是一个黑盒子，除非编码被理解。本工具明确显示了如何将计算的每个步骤组合起来以获得最终分数，以及目标序列中部分正确元素的可能组合。例如，给定正确答案a - b -C-D-E，考生的答案C-D-A-B-E将被评估为两个部分序列C-D-E或a - b - e。在这些部分序列(最大相对序列)中，元素在允许间隙的情况下以升序运行，并且它们是最长的可能序列。部分得分为2分，计算元素转换的次数，满分为4分。任何MRS都是将正确答案中的元素错位的结果，这可以通过“最小编辑距离”(MED)来衡量。与MED不同，MRS是局部可计算的，因此适合Excel移植。本文解释了形成磁流变的每个步骤是如何进行的。尽管内存有限，目前的Excel表格是一个很受欢迎的工具，它可以帮助用户理解MRS背后的原理，更有实际意义的是，它是一个方便的工具，通过简单地复制和粘贴考生的答案来获得部分分数。
{"title":"Partial Scoring of Reordering Tasks : Maximal Relative Sequence by Excel","authors":"Amma Kazuo","doi":"10.1109/INFOCT.2019.8711372","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8711372","url":null,"abstract":"An Excel form was developed by the author for calculating partial scoring of item reordering questions. It is a transplant of the algorithm realised in an application also devised by the author for the same purpose of calculation. Whereas the computer application is quick and efficient, the internal mechanism is a blackbox to general users unless the coding is understood. The present tool shows explicitly how each step of calculation is combined to reach the final score, together with possible combinations of partially correct elements within a target sequence. Given a correct answer A-B-C-D-E, a test-taker answer C-D-A-B-E, for instance, will be evaluated for two partial sequences C-D-E or A-B-E. In these partial sequences (Maximal Relative Sequences), elements run in an ascending order while allowing gaps, and they are the longest possible sequences. The partial score is 2, counting the number of transitions of elements, out of the full score of 4. Any MRS is a result of dislocating elements from the correct answer, which is measurable by ‘Minimal Edit Distance’ (MED). Unlike MED, MRS is locally calculable and therefore eligible for Excel transplantation. This paper explains how each step of forming an MRS is conducted. Despite limitations of memory, the present Excel form is a popular tool which helps users to understand the rationale behind MRS, and of more practical significance it is a convenient tool to get partial scores by simply copying and pasting test-taker answers.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"38 18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121442216","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 : 2019-03-14DOI: 10.1109/INFOCT.2019.8711099
Yang Tao, Zhu Cui, Zhang Jiazhe
Keyword extraction is a basic text retrieval technique in natural language processing, which can highly summarize text content and reflect the author’s writing purposes. It plays an important role in document retrieval, text classification and data mining. In this paper, we propose a TextRank algorithm based on PMI (pointwise mutual information) weighting for extracting keywords from documents. The initial transition probability of the candidate words is constructed by calculating the PMI between vocabularies, which is used for iterative calculation of the vocabulary graph model within TextRank and keyword extraction. Taking into account the mutual information between the vocabulary in the document set, the word relationship in the single document is corrected, which is helpful to improve the accuracy of document keyword extraction. Experiments show that our method achieves better performance in extracting keywords in large-scale text data.
{"title":"Research on Keyword Extraction Algorithm Using PMI and TextRank","authors":"Yang Tao, Zhu Cui, Zhang Jiazhe","doi":"10.1109/INFOCT.2019.8711099","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8711099","url":null,"abstract":"Keyword extraction is a basic text retrieval technique in natural language processing, which can highly summarize text content and reflect the author’s writing purposes. It plays an important role in document retrieval, text classification and data mining. In this paper, we propose a TextRank algorithm based on PMI (pointwise mutual information) weighting for extracting keywords from documents. The initial transition probability of the candidate words is constructed by calculating the PMI between vocabularies, which is used for iterative calculation of the vocabulary graph model within TextRank and keyword extraction. Taking into account the mutual information between the vocabulary in the document set, the word relationship in the single document is corrected, which is helpful to improve the accuracy of document keyword extraction. Experiments show that our method achieves better performance in extracting keywords in large-scale text data.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134614384","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：