Pub Date : 2015-12-01DOI: 10.1109/INTELCIS.2015.7397289
I. Ismail, Walaa K. Gad, M. Hamdy, Khaled Bahnsy
A huge number of documents are available that may cause information overload problems. Text document annotation provides a solution to such type of problems. Text annotation is the process of attaching comments, notes, or explanations to text documents. From a technical point of view, annotations are usually seen as metadata, as they give additional information about an existing piece of data. Annotations facilitate the task of finding the document topic and assist the reader to quickly overview and understand document. In this paper, we study different methods of text document annotation and comparisons among different methods are shown indicating advantages and disadvantages of each method used in annotation.
{"title":"Text document annotation methods: Stat of art","authors":"I. Ismail, Walaa K. Gad, M. Hamdy, Khaled Bahnsy","doi":"10.1109/INTELCIS.2015.7397289","DOIUrl":"https://doi.org/10.1109/INTELCIS.2015.7397289","url":null,"abstract":"A huge number of documents are available that may cause information overload problems. Text document annotation provides a solution to such type of problems. Text annotation is the process of attaching comments, notes, or explanations to text documents. From a technical point of view, annotations are usually seen as metadata, as they give additional information about an existing piece of data. Annotations facilitate the task of finding the document topic and assist the reader to quickly overview and understand document. In this paper, we study different methods of text document annotation and comparisons among different methods are shown indicating advantages and disadvantages of each method used in annotation.","PeriodicalId":6478,"journal":{"name":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","volume":"12 1","pages":"634-640"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91027048","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 : 2015-12-01DOI: 10.1109/INTELCIS.2015.7397204
T. Schrader, K. Loewe, Lutz Pelchen, Eberhard Beck
5%-10% of all medical procedures are erroneous. It is estimated that about 10.000 persons in Germany die due to errors in medical interventions. The clinical risk management analyses the reasons for errors and avoidable events, in most cases retrospectively. Approaches such as Hazards & Operability Study (HAZOP) are applied routinely in technical environments. In a quite small number of rather medical specific procedures especially in laboratories the risk management demands HAZOP. In the clinical domain this approach is not used due to the difficulties to describe medical processes and task with all different kinds of properties.
{"title":"Prospective, knowledge based clinical risk analysis: The OPT-model","authors":"T. Schrader, K. Loewe, Lutz Pelchen, Eberhard Beck","doi":"10.1109/INTELCIS.2015.7397204","DOIUrl":"https://doi.org/10.1109/INTELCIS.2015.7397204","url":null,"abstract":"5%-10% of all medical procedures are erroneous. It is estimated that about 10.000 persons in Germany die due to errors in medical interventions. The clinical risk management analyses the reasons for errors and avoidable events, in most cases retrospectively. Approaches such as Hazards & Operability Study (HAZOP) are applied routinely in technical environments. In a quite small number of rather medical specific procedures especially in laboratories the risk management demands HAZOP. In the clinical domain this approach is not used due to the difficulties to describe medical processes and task with all different kinds of properties.","PeriodicalId":6478,"journal":{"name":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","volume":"89 3","pages":"94-99"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72617552","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 : 2015-12-01DOI: 10.1109/INTELCIS.2015.7397191
Mahmoud Elbattah, Mohamed Roushdy, M. Aref, Abdel-badeeh M. Salem
Ontology has been increasingly recognised as an instrumental artifact to help make sense of large amounts of data. However, the challenges of Big Data significantly overburden the process of ontology storage and query particularly. In this respect, the paper aims to convey considerations in relation to improving the practice of storing or querying large-scale ontologies. Initially, a systematic literature review is conducted with the aim of thoroughly inspecting the state-of-the-art in literature. Subsequently, a graph database-oriented approach is proposed, considering ontology as a large graph. The approach endeavours to address the limitations encountered within traditional relational models. Furthermore, scalability and query efficiency of the approach are verified based on empirical experiments using a subset of Freebase data. The Freebase subset is utilised to build a large-scale ontology graph composed of more than 500K nodes, and 2M edges.
{"title":"Large-scale ontology storage and query using graph database-oriented approach: The case of Freebase","authors":"Mahmoud Elbattah, Mohamed Roushdy, M. Aref, Abdel-badeeh M. Salem","doi":"10.1109/INTELCIS.2015.7397191","DOIUrl":"https://doi.org/10.1109/INTELCIS.2015.7397191","url":null,"abstract":"Ontology has been increasingly recognised as an instrumental artifact to help make sense of large amounts of data. However, the challenges of Big Data significantly overburden the process of ontology storage and query particularly. In this respect, the paper aims to convey considerations in relation to improving the practice of storing or querying large-scale ontologies. Initially, a systematic literature review is conducted with the aim of thoroughly inspecting the state-of-the-art in literature. Subsequently, a graph database-oriented approach is proposed, considering ontology as a large graph. The approach endeavours to address the limitations encountered within traditional relational models. Furthermore, scalability and query efficiency of the approach are verified based on empirical experiments using a subset of Freebase data. The Freebase subset is utilised to build a large-scale ontology graph composed of more than 500K nodes, and 2M edges.","PeriodicalId":6478,"journal":{"name":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","volume":"21 1","pages":"39-43"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75588828","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 : 2015-12-01DOI: 10.1109/INTELCIS.2015.7397217
Zainab Abdel Wahed El-Waily
The enormous acceleration in using information technology beside the Changing and complexity of the Beneficiaries tasks although that the researchers have no much time, for one side, From another side The emergence of the Internet network the strong contender for digital libraries, all of that led to the need to make our libraries keep pace with the current reality through opening the digital libraries as a part of its traditional libraries or independently from it. But unfortunately most of the digital libraries establishment experiments have failed in doing its job for many reasons, from the most important reasons is that there is no the needed strategy for establish the digital library, and from that the researchers start focus on how important is the establishment strategy and it is needed to go throw each stage in the Strategy in order to have a successful experiment achieving the tasks which it has been built for.
{"title":"Strategy to establish an e-library for university theses in the central library of the University of Mustansiriya (experimental study)","authors":"Zainab Abdel Wahed El-Waily","doi":"10.1109/INTELCIS.2015.7397217","DOIUrl":"https://doi.org/10.1109/INTELCIS.2015.7397217","url":null,"abstract":"The enormous acceleration in using information technology beside the Changing and complexity of the Beneficiaries tasks although that the researchers have no much time, for one side, From another side The emergence of the Internet network the strong contender for digital libraries, all of that led to the need to make our libraries keep pace with the current reality through opening the digital libraries as a part of its traditional libraries or independently from it. But unfortunately most of the digital libraries establishment experiments have failed in doing its job for many reasons, from the most important reasons is that there is no the needed strategy for establish the digital library, and from that the researchers start focus on how important is the establishment strategy and it is needed to go throw each stage in the Strategy in order to have a successful experiment achieving the tasks which it has been built for.","PeriodicalId":6478,"journal":{"name":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","volume":"38 1","pages":"172-178"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78141073","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 : 2015-12-01DOI: 10.1109/INTELCIS.2015.7397258
M. Aly, M. Aref, M.I. Hassan
Real-time strategy games are strategic war games where two or more players operate on a virtual battlefield, controlling resources, buildings, units and technologies to achieve victory by destroying others. Achieving victory depends on selecting a suitable plan (set of actions), selecting a suitable plan depends on building an imagination (building a model) of the opponent to know how to deal with. This imagination is the opponent model, the stronger the opponent modelling process is, the more accurate the selected suitable plan is and consequently the higher probability achieving the victory is. One of the environment's challenges in real-time strategy games is that classifying the opponent model is game specific. This paper introduces a new methodology through which we can classify the observed opponent model in a way that is not game specific. Our methodology includes two paths, only one of them is executed per real-time strategy game type (per opponent models trained), which means that different type of real-time strategy games will execute different paths of the two paths of our methodology.
{"title":"Dimensions-based classifier for strategy classification of opponent models in real-time strategy games","authors":"M. Aly, M. Aref, M.I. Hassan","doi":"10.1109/INTELCIS.2015.7397258","DOIUrl":"https://doi.org/10.1109/INTELCIS.2015.7397258","url":null,"abstract":"Real-time strategy games are strategic war games where two or more players operate on a virtual battlefield, controlling resources, buildings, units and technologies to achieve victory by destroying others. Achieving victory depends on selecting a suitable plan (set of actions), selecting a suitable plan depends on building an imagination (building a model) of the opponent to know how to deal with. This imagination is the opponent model, the stronger the opponent modelling process is, the more accurate the selected suitable plan is and consequently the higher probability achieving the victory is. One of the environment's challenges in real-time strategy games is that classifying the opponent model is game specific. This paper introduces a new methodology through which we can classify the observed opponent model in a way that is not game specific. Our methodology includes two paths, only one of them is executed per real-time strategy game type (per opponent models trained), which means that different type of real-time strategy games will execute different paths of the two paths of our methodology.","PeriodicalId":6478,"journal":{"name":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","volume":"1 1","pages":"442-446"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89971134","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 : 2015-12-01DOI: 10.1109/INTELCIS.2015.7397283
Hussein Mazaar, E. Emary, H. Onsi
The paper presents an approach for feature selection in human activity recognition. Features are extracted based on spatiotemporal orientation energy and activity template, while feature reduction has been studied thoroughly using various techniques. Due to high dimensional data from extraction phase, a model with less features which are important and significant can build attractive, interpretative and accurate model. Finally, activity classification is done using SVM. With experiments to classify six activities of the KTH Dataset, significant feature reductions were reported with optimal embedded selection recorded for Gradient Boosting and R-Square techniques. The results show a reduction in time and improvement in accuracy. The Comparison to related work were given.
{"title":"Evaluation of feature selection on human activity recognition","authors":"Hussein Mazaar, E. Emary, H. Onsi","doi":"10.1109/INTELCIS.2015.7397283","DOIUrl":"https://doi.org/10.1109/INTELCIS.2015.7397283","url":null,"abstract":"The paper presents an approach for feature selection in human activity recognition. Features are extracted based on spatiotemporal orientation energy and activity template, while feature reduction has been studied thoroughly using various techniques. Due to high dimensional data from extraction phase, a model with less features which are important and significant can build attractive, interpretative and accurate model. Finally, activity classification is done using SVM. With experiments to classify six activities of the KTH Dataset, significant feature reductions were reported with optimal embedded selection recorded for Gradient Boosting and R-Square techniques. The results show a reduction in time and improvement in accuracy. The Comparison to related work were given.","PeriodicalId":6478,"journal":{"name":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","volume":"213 1","pages":"591-599"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89086057","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 : 2015-12-01DOI: 10.1109/INTELCIS.2015.7397239
E. Elsayed, Eman M. Elgamal, K. Eldahshan
Reading the opinion behind the text is a big challenge. In another way, we need to automatically read opinions and moods as a natural language. Ontology -based plays a main role to solve the problems in this field. That is from the features of the ontology based as covering the semantics of the concepts. So, in this paper, we propose a flexible classification opinion mining tool. This proposed method based on ontology- based. The proposed method uses NLTK (Natural Language Processing Toolkit) with Python as a useful knowledge to get more representative word occurrences in the corpus. Also, we not only use a WordNet and SentiWordNet ontologies to assign the word as POS (part of speech), but we also create a specific purpose ontology by OWL editor as Protégé. Then we create a more general opinion mining tool where the specific purpose ontology file was selected to use for classification the text. We apply our proposed method on lists of long texts for different writers, and then we can classify these writers depending on their writings.
{"title":"Deep analysis of knowledge in one's writings","authors":"E. Elsayed, Eman M. Elgamal, K. Eldahshan","doi":"10.1109/INTELCIS.2015.7397239","DOIUrl":"https://doi.org/10.1109/INTELCIS.2015.7397239","url":null,"abstract":"Reading the opinion behind the text is a big challenge. In another way, we need to automatically read opinions and moods as a natural language. Ontology -based plays a main role to solve the problems in this field. That is from the features of the ontology based as covering the semantics of the concepts. So, in this paper, we propose a flexible classification opinion mining tool. This proposed method based on ontology- based. The proposed method uses NLTK (Natural Language Processing Toolkit) with Python as a useful knowledge to get more representative word occurrences in the corpus. Also, we not only use a WordNet and SentiWordNet ontologies to assign the word as POS (part of speech), but we also create a specific purpose ontology by OWL editor as Protégé. Then we create a more general opinion mining tool where the specific purpose ontology file was selected to use for classification the text. We apply our proposed method on lists of long texts for different writers, and then we can classify these writers depending on their writings.","PeriodicalId":6478,"journal":{"name":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","volume":"174 1","pages":"306-312"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88442436","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 : 2015-12-01DOI: 10.1109/INTELCIS.2015.7397221
A. M. Salem
Researchers have been used the artificial intelligence (AI) area of research in education to develop a new generation of intelligent tutoring and learning systems. AI concepts, theories and approaches receive increasing attention within the educational technology community. This paper discusses the AI approaches, methodologies and techniques for developing the intelligent e-Learning and tutoring systems. In addition, the paper presents some examples of the developed systems by the author and his colleagues at Artificial intelligence and Knowledge Engineering Research Labs, Ain Shams University, Cairo, Egypt.
{"title":"Towards of intelligence education and learning","authors":"A. M. Salem","doi":"10.1109/INTELCIS.2015.7397221","DOIUrl":"https://doi.org/10.1109/INTELCIS.2015.7397221","url":null,"abstract":"Researchers have been used the artificial intelligence (AI) area of research in education to develop a new generation of intelligent tutoring and learning systems. AI concepts, theories and approaches receive increasing attention within the educational technology community. This paper discusses the AI approaches, methodologies and techniques for developing the intelligent e-Learning and tutoring systems. In addition, the paper presents some examples of the developed systems by the author and his colleagues at Artificial intelligence and Knowledge Engineering Research Labs, Ain Shams University, Cairo, Egypt.","PeriodicalId":6478,"journal":{"name":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","volume":"108 1","pages":"196-202"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83290648","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 : 2015-12-01DOI: 10.1109/INTELCIS.2015.7397192
Safi Ibrahim, M. Hamdy, E. Shaaban
In Vehicular Ad Hoc Networks (VANETs), nodes are represented by Vehicles. Communication in VANETs can take place either between vehicles Vehicle-to-Vehicle (V2V), or between Vehicle and Infrastructure (V2I). Securing exchanged messages between Vehicles is of great importance, especially when they are life critical messages. Some of the Previous security researches discussed how to enable secure communication depending on the support of Infrastructure. In this work, security supported by infrastructure is defined by Services Oriented. Service Oriented Architecture (SOA) can be a novel alternative to satisfy all security requirements. We show the completeness of the proposed system by comparing it with previous security researches.
{"title":"A proposed security service set for VANET SOA","authors":"Safi Ibrahim, M. Hamdy, E. Shaaban","doi":"10.1109/INTELCIS.2015.7397192","DOIUrl":"https://doi.org/10.1109/INTELCIS.2015.7397192","url":null,"abstract":"In Vehicular Ad Hoc Networks (VANETs), nodes are represented by Vehicles. Communication in VANETs can take place either between vehicles Vehicle-to-Vehicle (V2V), or between Vehicle and Infrastructure (V2I). Securing exchanged messages between Vehicles is of great importance, especially when they are life critical messages. Some of the Previous security researches discussed how to enable secure communication depending on the support of Infrastructure. In this work, security supported by infrastructure is defined by Services Oriented. Service Oriented Architecture (SOA) can be a novel alternative to satisfy all security requirements. We show the completeness of the proposed system by comparing it with previous security researches.","PeriodicalId":6478,"journal":{"name":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","volume":"1 1","pages":"649-653"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83070932","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 : 2015-12-01DOI: 10.1109/INTELCIS.2015.7397209
S. Soliman, Safia Abbas, A. M. Salem
Recently, collagen diseases propagated due to many factors such as pressure and pollution. Thrombosis is one of the most famous collagen diseases that obstruct the blood flow causing vital complications for crucial parts of the circulatory system. Such diseases cause a high risk for the doctors due to the huge number of the laboratory examinations and the efforts to diagnosis. Accordingly, this paper implements C4.5 algorithm, as one of the most famous data mining techniques, on real thrombosis dataset. The dataset was collected from Chiba University as a challenging dataset for thrombosis diagnosis. The results show that the C4.5 could diagnose the thrombosis degree with accuracy 98.4%.
{"title":"Classification of thrombosis collagen diseases based on C4.5 algorithm","authors":"S. Soliman, Safia Abbas, A. M. Salem","doi":"10.1109/INTELCIS.2015.7397209","DOIUrl":"https://doi.org/10.1109/INTELCIS.2015.7397209","url":null,"abstract":"Recently, collagen diseases propagated due to many factors such as pressure and pollution. Thrombosis is one of the most famous collagen diseases that obstruct the blood flow causing vital complications for crucial parts of the circulatory system. Such diseases cause a high risk for the doctors due to the huge number of the laboratory examinations and the efforts to diagnosis. Accordingly, this paper implements C4.5 algorithm, as one of the most famous data mining techniques, on real thrombosis dataset. The dataset was collected from Chiba University as a challenging dataset for thrombosis diagnosis. The results show that the C4.5 could diagnose the thrombosis degree with accuracy 98.4%.","PeriodicalId":6478,"journal":{"name":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","volume":"40 1","pages":"131-136"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80418066","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：