Pub Date : 2016-12-17DOI: 10.1109/SKIMA.2016.7916194
A. Shabut, Khin T. Lwin, Mohammed Alamgir Hossain
Thousands of cyber-attacks (fraudulent online activities to acquire users' sensitive information via email, during online transactions, live video streaming, online gaming and browsing) are launched every day against Internet users across the world. To prevent these attacks, researchers have responded with a number of protection systems. Currently, the methods which cyber-attackers use to conduct attacks is associated with exploiting humans. Such attacks are recorded more frequently than before, and they are more challenging to control. Traditional security countermeasures are unable to prevent breaches targeting the human element. This paper describes the state of the art of cyber security attacks, countermeasures, and protection tools related to everyday online activities. It provides a useful cyber-attack taxonomy and classification which helps to involve in a protection process to identify attacks and measures for cyber security. Existing protection schemes that target the cyber threats and risks are evaluated against three of our criteria for an effective measure: resilience to cyber-attacks' countermeasures; real-time support and needs-based action; and training and educational materials to increase users' awareness of cybercrimes. Potential features of smart solutions to cybercrime are also identified.
{"title":"Cyber attacks, countermeasures, and protection schemes — A state of the art survey","authors":"A. Shabut, Khin T. Lwin, Mohammed Alamgir Hossain","doi":"10.1109/SKIMA.2016.7916194","DOIUrl":"https://doi.org/10.1109/SKIMA.2016.7916194","url":null,"abstract":"Thousands of cyber-attacks (fraudulent online activities to acquire users' sensitive information via email, during online transactions, live video streaming, online gaming and browsing) are launched every day against Internet users across the world. To prevent these attacks, researchers have responded with a number of protection systems. Currently, the methods which cyber-attackers use to conduct attacks is associated with exploiting humans. Such attacks are recorded more frequently than before, and they are more challenging to control. Traditional security countermeasures are unable to prevent breaches targeting the human element. This paper describes the state of the art of cyber security attacks, countermeasures, and protection tools related to everyday online activities. It provides a useful cyber-attack taxonomy and classification which helps to involve in a protection process to identify attacks and measures for cyber security. Existing protection schemes that target the cyber threats and risks are evaluated against three of our criteria for an effective measure: resilience to cyber-attacks' countermeasures; real-time support and needs-based action; and training and educational materials to increase users' awareness of cybercrimes. Potential features of smart solutions to cybercrime are also identified.","PeriodicalId":417370,"journal":{"name":"2016 10th International Conference on Software, Knowledge, Information Management & Applications (SKIMA)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121648342","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 : 2016-12-15DOI: 10.1109/SKIMA.2016.7916250
Baudouin Dafflon, Madeleine El-Zaher
This paper introduces a verification and validation (V&V) process in a product life-cycle, where we consider a V&V process as the composition of the three tasks: formal verification, simulation and experimentation. The considered application is a platoon system, a set of autonomous vehicles that move together without any material connection. The platoon system development considers the specification of the SafePlatoon project1. Main goal of the V&V process is to put to the proof the platoon controller (Decision making unit). V&V is then a corner stone for critical functions that require zero default. Algorithm and hardware must respect some security concerns such as collision free between platoon vehicles, platoon integrity, obstacles avoidance, and etc. After a specification phase, where safety properties are defined, a classical or agile V&V cycle can be applied. In the case of SafePlatoon project, where different partners are evolving simultaneously on the models, an agile development method is used; where formal verification and benchmark simulation works together in order to improve model's safety. Formal verification is made using The SAL model checker. Validation by simulation is made using an internal tool called Vivus.
{"title":"An agile development method for platoon system based on verification and validation","authors":"Baudouin Dafflon, Madeleine El-Zaher","doi":"10.1109/SKIMA.2016.7916250","DOIUrl":"https://doi.org/10.1109/SKIMA.2016.7916250","url":null,"abstract":"This paper introduces a verification and validation (V&V) process in a product life-cycle, where we consider a V&V process as the composition of the three tasks: formal verification, simulation and experimentation. The considered application is a platoon system, a set of autonomous vehicles that move together without any material connection. The platoon system development considers the specification of the SafePlatoon project1. Main goal of the V&V process is to put to the proof the platoon controller (Decision making unit). V&V is then a corner stone for critical functions that require zero default. Algorithm and hardware must respect some security concerns such as collision free between platoon vehicles, platoon integrity, obstacles avoidance, and etc. After a specification phase, where safety properties are defined, a classical or agile V&V cycle can be applied. In the case of SafePlatoon project, where different partners are evolving simultaneously on the models, an agile development method is used; where formal verification and benchmark simulation works together in order to improve model's safety. Formal verification is made using The SAL model checker. Validation by simulation is made using an internal tool called Vivus.","PeriodicalId":417370,"journal":{"name":"2016 10th International Conference on Software, Knowledge, Information Management & Applications (SKIMA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125708426","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 : 2016-12-15DOI: 10.1109/SKIMA.2016.7916207
Yi Chen, Zhonglai Wang, Erfu Yang, Yun Li
In practical applications, multi-objective optimisation is one of the most challenging problems that engineers face. For this, Pareto-optimality is the most widely adopted concept, which is a set of optimal trade-offs between conflicting objectives without committing to a recommendation for decision-making. In this paper, a fast approach to Pareto-optimal solution recommendation is developed. It recommends an optimal ranking for decision-makers using a Pareto reliability index. Further, a mean average precision and a mean standard deviation are utilised to gauge the trend of the evolutionary process. A multi-objective artificial wolf-pack algorithm is thus developed to handle the multi-objective problem using a non-dominated sorting method (MAWNS). This is tested in a case study, where the MAWNS is employed as an optimiser for a widely adopted standard test problem, ZDT6. The results show that the proposed method works valuably for the multi-objective optimisations.
{"title":"Pareto-optimality solution recommendation using a multi-objective artificial wolf-pack algorithm","authors":"Yi Chen, Zhonglai Wang, Erfu Yang, Yun Li","doi":"10.1109/SKIMA.2016.7916207","DOIUrl":"https://doi.org/10.1109/SKIMA.2016.7916207","url":null,"abstract":"In practical applications, multi-objective optimisation is one of the most challenging problems that engineers face. For this, Pareto-optimality is the most widely adopted concept, which is a set of optimal trade-offs between conflicting objectives without committing to a recommendation for decision-making. In this paper, a fast approach to Pareto-optimal solution recommendation is developed. It recommends an optimal ranking for decision-makers using a Pareto reliability index. Further, a mean average precision and a mean standard deviation are utilised to gauge the trend of the evolutionary process. A multi-objective artificial wolf-pack algorithm is thus developed to handle the multi-objective problem using a non-dominated sorting method (MAWNS). This is tested in a case study, where the MAWNS is employed as an optimiser for a widely adopted standard test problem, ZDT6. The results show that the proposed method works valuably for the multi-objective optimisations.","PeriodicalId":417370,"journal":{"name":"2016 10th International Conference on Software, Knowledge, Information Management & Applications (SKIMA)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129658979","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 : 2016-12-15DOI: 10.1109/SKIMA.2016.7916245
Fatima Zohra Tanane, Jannik Laval, V. Cheutet
Currently, the information systems agility and the satisfaction of the dynamic environment requirements is essential challenges for companies. The purpose of this paper is to represent the existing approaches for achieving agility in software development as well as in production system. The objective is to identify the relevant metrics for evaluating information system agility. Then, we propose an analysis model that contains these agile metrics, to observe their combination in information system.
{"title":"Towards assessment of information system agility","authors":"Fatima Zohra Tanane, Jannik Laval, V. Cheutet","doi":"10.1109/SKIMA.2016.7916245","DOIUrl":"https://doi.org/10.1109/SKIMA.2016.7916245","url":null,"abstract":"Currently, the information systems agility and the satisfaction of the dynamic environment requirements is essential challenges for companies. The purpose of this paper is to represent the existing approaches for achieving agility in software development as well as in production system. The objective is to identify the relevant metrics for evaluating information system agility. Then, we propose an analysis model that contains these agile metrics, to observe their combination in information system.","PeriodicalId":417370,"journal":{"name":"2016 10th International Conference on Software, Knowledge, Information Management & Applications (SKIMA)","volume":"209 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122433664","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 : 2016-12-15DOI: 10.1109/SKIMA.2016.7916222
D. Krishnan, Xujuan Zhou, Subrata Chakraborty, Rashmi Gururajan, R. Gururajan
In this paper, we present the development and use of a nutrition assessment software namely Nutritracs for Type II Diabetes Mellitus (T2DM). We conducted a case study in India to understand how diet counselling impacts upon Type II Diabetes Mellitus (T2DM) management. We also highlight practical challenges in conducting such studies in developing countries and how we have addressed them, and the promising outcome in T2DM management — reduced the dependency on insulin as a management tool.
在本文中，我们介绍了一个营养评估软件的开发和使用，即nutritrac for II型糖尿病(T2DM)。我们在印度进行了一个案例研究，以了解饮食咨询对II型糖尿病(T2DM)管理的影响。我们还强调了在发展中国家开展此类研究的实际挑战以及我们如何解决这些挑战，以及在T2DM管理方面的有希望的结果-减少了对胰岛素作为管理工具的依赖。
{"title":"Software development for managing nutrition intake for Type II diabetes mellitus","authors":"D. Krishnan, Xujuan Zhou, Subrata Chakraborty, Rashmi Gururajan, R. Gururajan","doi":"10.1109/SKIMA.2016.7916222","DOIUrl":"https://doi.org/10.1109/SKIMA.2016.7916222","url":null,"abstract":"In this paper, we present the development and use of a nutrition assessment software namely Nutritracs for Type II Diabetes Mellitus (T2DM). We conducted a case study in India to understand how diet counselling impacts upon Type II Diabetes Mellitus (T2DM) management. We also highlight practical challenges in conducting such studies in developing countries and how we have addressed them, and the promising outcome in T2DM management — reduced the dependency on insulin as a management tool.","PeriodicalId":417370,"journal":{"name":"2016 10th International Conference on Software, Knowledge, Information Management & Applications (SKIMA)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131895936","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 : 1900-01-01DOI: 10.1109/SKIMA.2016.7916263
Muhammad Hasnain Abbas Naqvi, Jiang Yushi, Mishal Hasnain Naqvi, Malik Muneeb Abid
The main focus on the company's marketing is advertising nowadays, which has so much influence that nothing can be marketed without advertising. Just to inform your customers of what your company is offering media is the only option now to let people know. Media is so influential these days they repeat advertisements of companies just to get into the customers mind. Repeating advertisements has surely been a tool to grab customers for a company's offerings. This research focuses on the effects of repeat advertisements on the purchase decisions of customers. In this research we will be focusing just on the PEPSI ads which are aired on TV during the cricket matches on different sports channels. This will also show attitudes of people towards the ads, are they motivated by those ads to use the product of the company or not. The analysis and finding section shows that the television ads which are repeated several times during a cricket match do not get much of attention. Repeating advertisements show little effect on the customers purchase decisions. Consumers find that the theme of the ads plays an important role in grabbing the customer's interest. Advertisement is the most important source to promote the brand.
{"title":"Attitudes of audience towards repeat advertisements a case of PEPSI ads","authors":"Muhammad Hasnain Abbas Naqvi, Jiang Yushi, Mishal Hasnain Naqvi, Malik Muneeb Abid","doi":"10.1109/SKIMA.2016.7916263","DOIUrl":"https://doi.org/10.1109/SKIMA.2016.7916263","url":null,"abstract":"The main focus on the company's marketing is advertising nowadays, which has so much influence that nothing can be marketed without advertising. Just to inform your customers of what your company is offering media is the only option now to let people know. Media is so influential these days they repeat advertisements of companies just to get into the customers mind. Repeating advertisements has surely been a tool to grab customers for a company's offerings. This research focuses on the effects of repeat advertisements on the purchase decisions of customers. In this research we will be focusing just on the PEPSI ads which are aired on TV during the cricket matches on different sports channels. This will also show attitudes of people towards the ads, are they motivated by those ads to use the product of the company or not. The analysis and finding section shows that the television ads which are repeated several times during a cricket match do not get much of attention. Repeating advertisements show little effect on the customers purchase decisions. Consumers find that the theme of the ads plays an important role in grabbing the customer's interest. Advertisement is the most important source to promote the brand.","PeriodicalId":417370,"journal":{"name":"2016 10th International Conference on Software, Knowledge, Information Management & Applications (SKIMA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125884659","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 : 1900-01-01DOI: 10.1109/SKIMA.2016.7916205
R. Limaye, R. Choudhary, A. Upadhyay, Hongnian Yu
Worldwide 1.3 billion people remain without electricity and 2.7 billion are still cooking on inefficient stoves. In remote rural village communities, need to develop and improve lives. Smart villages (SV) capture many of the benefits of urban living while retaining aspects of rural life and ensuring development at the national level. This enables villagers to attain healthy and fulfilling lives, achieve development, earn a sustainable living and be connected to the wider world. This gives the stakeholders in villages a real choice between the route of migration to a city, or life in a smart village. Smart villages are an emerging global challenge. There is a gap in urban rural setup worldwide. Technology can be a level playing enabler if Smart Village Framework is made in holistic analytical manner. Besides Technology best practices, motivated teams can transform the villages. Extenics theory is a tool for evolving a framework for Smart villages, as it minutely identifies various elements as matter in different conditions, contexts and also assigns measurable attributes. In this paper the various attributes related to a Smart Village are being analyzed using Extenics and a Smart Village Planning Framework is suggested for Indian Context.
{"title":"Smart village planning framework using extenics theory","authors":"R. Limaye, R. Choudhary, A. Upadhyay, Hongnian Yu","doi":"10.1109/SKIMA.2016.7916205","DOIUrl":"https://doi.org/10.1109/SKIMA.2016.7916205","url":null,"abstract":"Worldwide 1.3 billion people remain without electricity and 2.7 billion are still cooking on inefficient stoves. In remote rural village communities, need to develop and improve lives. Smart villages (SV) capture many of the benefits of urban living while retaining aspects of rural life and ensuring development at the national level. This enables villagers to attain healthy and fulfilling lives, achieve development, earn a sustainable living and be connected to the wider world. This gives the stakeholders in villages a real choice between the route of migration to a city, or life in a smart village. Smart villages are an emerging global challenge. There is a gap in urban rural setup worldwide. Technology can be a level playing enabler if Smart Village Framework is made in holistic analytical manner. Besides Technology best practices, motivated teams can transform the villages. Extenics theory is a tool for evolving a framework for Smart villages, as it minutely identifies various elements as matter in different conditions, contexts and also assigns measurable attributes. In this paper the various attributes related to a Smart Village are being analyzed using Extenics and a Smart Village Planning Framework is suggested for Indian Context.","PeriodicalId":417370,"journal":{"name":"2016 10th International Conference on Software, Knowledge, Information Management & Applications (SKIMA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129470730","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 : 1900-01-01DOI: 10.1109/SKIMA.2016.7916243
Md Sajib Ahmed, Teresa Gonçalves, H. Sarwar
Bangla OCR (Optical Character Recognition) is a long deserving software for Bengali community all over the world. Numerous efforts suggest that due to the inherent complex nature of Bangla alphabet and its word formation process development of high fidelity OCR producing a reasonably acceptable output still remains a challenge. One possible way of improvement is by using post processing of OCR's output; algorithms such as Edit Distance and the use of n-grams statistical information have been used to rectify misspelled words in language processing. This work presents the first known approach to use these algorithms to replace misrecognized words produced by Bangla OCR. The assessment is made on a set of fifty documents written in Bangla script and uses a dictionary of 541,167 words. The proposed correction model can correct several words lowering the recognition error rate by 2.87% and 3.18% for the character based n-gram and edit distance algorithms respectively. The developed system suggests a list of 5 (five) alternatives for a misspelled word. It is found that in 33.82% cases, the correct word is the topmost suggestion of 5 words list for n-gram algorithm while using Edit distance algorithm the first word in the suggestion properly matches 36.31% of the cases. This work will ignite rooms of thoughts for possible improvements in character recognition endeavor.
{"title":"Improving Bangla OCR output through correction algorithms","authors":"Md Sajib Ahmed, Teresa Gonçalves, H. Sarwar","doi":"10.1109/SKIMA.2016.7916243","DOIUrl":"https://doi.org/10.1109/SKIMA.2016.7916243","url":null,"abstract":"Bangla OCR (Optical Character Recognition) is a long deserving software for Bengali community all over the world. Numerous efforts suggest that due to the inherent complex nature of Bangla alphabet and its word formation process development of high fidelity OCR producing a reasonably acceptable output still remains a challenge. One possible way of improvement is by using post processing of OCR's output; algorithms such as Edit Distance and the use of n-grams statistical information have been used to rectify misspelled words in language processing. This work presents the first known approach to use these algorithms to replace misrecognized words produced by Bangla OCR. The assessment is made on a set of fifty documents written in Bangla script and uses a dictionary of 541,167 words. The proposed correction model can correct several words lowering the recognition error rate by 2.87% and 3.18% for the character based n-gram and edit distance algorithms respectively. The developed system suggests a list of 5 (five) alternatives for a misspelled word. It is found that in 33.82% cases, the correct word is the topmost suggestion of 5 words list for n-gram algorithm while using Edit distance algorithm the first word in the suggestion properly matches 36.31% of the cases. This work will ignite rooms of thoughts for possible improvements in character recognition endeavor.","PeriodicalId":417370,"journal":{"name":"2016 10th International Conference on Software, Knowledge, Information Management & Applications (SKIMA)","volume":"891 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126975100","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 : 1900-01-01DOI: 10.1109/SKIMA.2016.7916200
J. Mo, W. Lorchirachoonkul
In today's supply chain management, products are being track by many technologies including barcode and RFID. Such technologies are rigid and often prone to errors. In this paper, we will examine the reciprocated picking processes that exist within the supply chain, from manufacturing to retail chains. Utilising an array of 3D cameras, a new method to capture the user's physical interaction and gesture within the picking environment has been developed. Unlike other technologies, this new method has no physical scanning performed by the users, since there are already relationship established between product and pick face's location. Since the item picked can be randomised without the utilisation of a pick slip, it is then possible for the new method to be incorporated as part of an automated checkout procedure for retail chain.
{"title":"Gesture interpreter for randomised supply chain operations using 3D cameras array","authors":"J. Mo, W. Lorchirachoonkul","doi":"10.1109/SKIMA.2016.7916200","DOIUrl":"https://doi.org/10.1109/SKIMA.2016.7916200","url":null,"abstract":"In today's supply chain management, products are being track by many technologies including barcode and RFID. Such technologies are rigid and often prone to errors. In this paper, we will examine the reciprocated picking processes that exist within the supply chain, from manufacturing to retail chains. Utilising an array of 3D cameras, a new method to capture the user's physical interaction and gesture within the picking environment has been developed. Unlike other technologies, this new method has no physical scanning performed by the users, since there are already relationship established between product and pick face's location. Since the item picked can be randomised without the utilisation of a pick slip, it is then possible for the new method to be incorporated as part of an automated checkout procedure for retail chain.","PeriodicalId":417370,"journal":{"name":"2016 10th International Conference on Software, Knowledge, Information Management & Applications (SKIMA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134433258","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 : 1900-01-01DOI: 10.1109/SKIMA.2016.7916254
Prakash Poudyal, Teresa Gonçalves, P. Quaresma
The main purpose of this study is to evaluate the best set of features that automatically enables the identification of argumentative sentences from unstructured text. As corpus, we use case laws from the European Court of Human Rights (ECHR). Three kinds of experiments are conducted: Basic Experiments, Multi Feature Experiments and Tree Kernel Experiments. These experiments are basically categorized according to the type of features available in the corpus. The features are extracted from the corpus and Support Vector Machine (SVM) and Random Forest are the used as Machine learning algorithms. We achieved F1 score of 0.705 for identifying the argumentative sentences which is quite promising result and can be used as the basis for a general argument-mining framework.
{"title":"Experiments on identification of argumentative sentences","authors":"Prakash Poudyal, Teresa Gonçalves, P. Quaresma","doi":"10.1109/SKIMA.2016.7916254","DOIUrl":"https://doi.org/10.1109/SKIMA.2016.7916254","url":null,"abstract":"The main purpose of this study is to evaluate the best set of features that automatically enables the identification of argumentative sentences from unstructured text. As corpus, we use case laws from the European Court of Human Rights (ECHR). Three kinds of experiments are conducted: Basic Experiments, Multi Feature Experiments and Tree Kernel Experiments. These experiments are basically categorized according to the type of features available in the corpus. The features are extracted from the corpus and Support Vector Machine (SVM) and Random Forest are the used as Machine learning algorithms. We achieved F1 score of 0.705 for identifying the argumentative sentences which is quite promising result and can be used as the basis for a general argument-mining framework.","PeriodicalId":417370,"journal":{"name":"2016 10th International Conference on Software, Knowledge, Information Management & Applications (SKIMA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115481830","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：