Pub Date : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9003055
Fatima Ezzahra Sakhi, A. Ait Allal, K. Mansouri, Mohammed Qbadou
Maritime transport is the main mode of transport used for the intercontinental transit of freights. Since the mid-sixties, and as international trade has developed, several types of ships have appeared. This plurality is an asset in that shippers can find the vessel that best suits the port infrastructure and the type of goods to be transported. Today with the technological revolution, most projects and studies seek to automate these different types of vessels in order to have a remotely controlled or autonomous vessel. Indeed, the automation of this mode of transport has as many advantages as limits given the sensitive sector. In this article, the different types of vessels are analyzed according to four axes: network and navigation, logistics, safety and environment in order to determine the most likely vessels to be autonomous.
{"title":"Determination of Merchant Ships that Most Likely to be Autonomously Operated","authors":"Fatima Ezzahra Sakhi, A. Ait Allal, K. Mansouri, Mohammed Qbadou","doi":"10.1109/ICSSD47982.2019.9003055","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9003055","url":null,"abstract":"Maritime transport is the main mode of transport used for the intercontinental transit of freights. Since the mid-sixties, and as international trade has developed, several types of ships have appeared. This plurality is an asset in that shippers can find the vessel that best suits the port infrastructure and the type of goods to be transported. Today with the technological revolution, most projects and studies seek to automate these different types of vessels in order to have a remotely controlled or autonomous vessel. Indeed, the automation of this mode of transport has as many advantages as limits given the sensitive sector. In this article, the different types of vessels are analyzed according to four axes: network and navigation, logistics, safety and environment in order to determine the most likely vessels to be autonomous.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"43 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113956418","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9002705
Kamal El Guemmat, Sara Ouahabi
The purpose of this paper is to propose an effective system to automate the work between learning actors and manage interoperability between contents in the Educational Cloud (EC). Building e-learning systems in the cloud computing is a multidisciplinary endeavor that involves Learning Object (LO), Instructional Management Systems Learning Design (IMS-LD) specification, semi-automatic semantic indexing techniques according to ontologies, algorithms for the automatic processing of natural language (NLP) and system development framework. Our project implements a group of engaging, affectionate, and effective IMS-LD package equipped with abilities to facilitate and support reuse, sharing and identification of the LO between learning actors in the EC. We proposed a pedagogical system in EC that offer more benefits for the various actors to collaborate and to share LO flexibly.
{"title":"Keeping interoperability between IMS-LD scenarios in Educational Cloud Computing based on Semantic Indexing","authors":"Kamal El Guemmat, Sara Ouahabi","doi":"10.1109/ICSSD47982.2019.9002705","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002705","url":null,"abstract":"The purpose of this paper is to propose an effective system to automate the work between learning actors and manage interoperability between contents in the Educational Cloud (EC). Building e-learning systems in the cloud computing is a multidisciplinary endeavor that involves Learning Object (LO), Instructional Management Systems Learning Design (IMS-LD) specification, semi-automatic semantic indexing techniques according to ontologies, algorithms for the automatic processing of natural language (NLP) and system development framework. Our project implements a group of engaging, affectionate, and effective IMS-LD package equipped with abilities to facilitate and support reuse, sharing and identification of the LO between learning actors in the EC. We proposed a pedagogical system in EC that offer more benefits for the various actors to collaborate and to share LO flexibly.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115158006","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9003111
Jalal Eddine Bahbouhi, N. Moussa
In this study, we investigated the evolutionary public goods games (PGG) on scale-free networks and studied the effect of network emergence. We used Hub emergence, which is an open-loop emergent process that restructures any dynamic network by creating hubs. Also we used Cluster emergence defined as an open-loop emergent process that increases the cluster coefficient of a dynamic network. With the aid of the analysis of the PGG on a graph, we are able to investigate intuitively how the emergence affects the transformation of individuals’ strategies. We find that the Hub emergence inhibits the emergence and sustainment of the cooperation, due to the fact that the vertices gather in big groups, and as a result diffuses cooperation among vertices and impact remote leaf-vertices to cooperate. However, Cluster emergence has also an impact on the evolution of cooperation, but with a lower intensity than the Hub emergence. As a result, the cooperation in PGG is more related to gathering in big groups than the cluster size.
{"title":"Impact of emergence on the evolution of cooperation in public goods games","authors":"Jalal Eddine Bahbouhi, N. Moussa","doi":"10.1109/ICSSD47982.2019.9003111","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9003111","url":null,"abstract":"In this study, we investigated the evolutionary public goods games (PGG) on scale-free networks and studied the effect of network emergence. We used Hub emergence, which is an open-loop emergent process that restructures any dynamic network by creating hubs. Also we used Cluster emergence defined as an open-loop emergent process that increases the cluster coefficient of a dynamic network. With the aid of the analysis of the PGG on a graph, we are able to investigate intuitively how the emergence affects the transformation of individuals’ strategies. We find that the Hub emergence inhibits the emergence and sustainment of the cooperation, due to the fact that the vertices gather in big groups, and as a result diffuses cooperation among vertices and impact remote leaf-vertices to cooperate. However, Cluster emergence has also an impact on the evolution of cooperation, but with a lower intensity than the Hub emergence. As a result, the cooperation in PGG is more related to gathering in big groups than the cluster size.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122136077","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9003123
Omar Souissi, Zineb El Akkaoui, Mohamed Assellaou
Data classification problems have been intensively studied by several groups of researchers including computer scientists, statisticians, engineers, biologists. Within the context of widespread use of databases and the explosive growth in their sizes, “Big Data”, new challenges are introduced in order to permit to several organizations to take benefits and efficiently utilize their data. The main objective of this paper is to review main published works which propose mathematical programming approaches in order to solve data classification problems with Support Vector Machine (SVM).
{"title":"Mathematical programming for data classification: A short survey","authors":"Omar Souissi, Zineb El Akkaoui, Mohamed Assellaou","doi":"10.1109/ICSSD47982.2019.9003123","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9003123","url":null,"abstract":"Data classification problems have been intensively studied by several groups of researchers including computer scientists, statisticians, engineers, biologists. Within the context of widespread use of databases and the explosive growth in their sizes, “Big Data”, new challenges are introduced in order to permit to several organizations to take benefits and efficiently utilize their data. The main objective of this paper is to review main published works which propose mathematical programming approaches in order to solve data classification problems with Support Vector Machine (SVM).","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117338935","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9002672
Hajar Zankadi, Imane Hilal, A. Idrissi
E-learning environments have witnessed a growing demand and shown great potential to provide learning opportunities for the seeker of knowledge around the world. However, e-learning environments have been plagued by extremely high drop-out rate due to the lack of interactivity. In this context, e-learning environments should adopt a model for a new form of communication and interaction in order to improve the performance of their learners.We suggest in this paper a social course design that helps learners to explore and finish their courses in an interactive and social way. At the same time, learners will be able to evaluate the effectiveness of the course which will make it easier for tutors to have an idea about the learners’ satisfaction.
{"title":"Designing a Middleware course for a real time interactive learning in Social Learning Environment","authors":"Hajar Zankadi, Imane Hilal, A. Idrissi","doi":"10.1109/ICSSD47982.2019.9002672","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002672","url":null,"abstract":"E-learning environments have witnessed a growing demand and shown great potential to provide learning opportunities for the seeker of knowledge around the world. However, e-learning environments have been plagued by extremely high drop-out rate due to the lack of interactivity. In this context, e-learning environments should adopt a model for a new form of communication and interaction in order to improve the performance of their learners.We suggest in this paper a social course design that helps learners to explore and finish their courses in an interactive and social way. At the same time, learners will be able to evaluate the effectiveness of the course which will make it easier for tutors to have an idea about the learners’ satisfaction.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127211890","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9002939
Zineb Lamghari, M. Radgui, R. Saidi, M. D. Rahmani
Nowadays, Big data promises automated actionable knowledge creation and predictive models for use by humans and computers. Therefore, one of the principal responsibilities of a data scientist is to make reliable predictions based on data, particularly, when the amount of available data is enormous. To do so, it is useful if some of the analysis can be automated and used process mining techniques.In this context, the ability to know in advance the trend of running process instances, with respect to different features, such as the expected completion time, would allow business managers to timely counteract to undesired situations, in order to prevent losses. Therefore, the techniques focus on predicting the remaining time influence other predictive process monitoring dimensions like: cost, delays, etc, i.e., predicting the remaining time, to accomplish an activity, helps respectively to predict the suitable resource and the next executing probable event. Indeed, a considerable number of methods have been put forward to address this prediction remaining time problem. However, none of the existing works have been grouped these methods (published from 2006 to 2019) in a framework.Therefore, the main objective of this paper is developing a value-driven framework for classifying existing work on predictive process monitoring, related to the remaining time dimension.This framework can support organizations to navigate in this predictive process monitoring specification field and help them to find value and exploit the opportunities enabled by these analysis techniques. This objective is achieved by systematically identifying, categorizing, and analyzing existing approaches for predictive process monitoring.
{"title":"Predictive Process Monitoring related to the remaining time dimension: a value-driven framework","authors":"Zineb Lamghari, M. Radgui, R. Saidi, M. D. Rahmani","doi":"10.1109/ICSSD47982.2019.9002939","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002939","url":null,"abstract":"Nowadays, Big data promises automated actionable knowledge creation and predictive models for use by humans and computers. Therefore, one of the principal responsibilities of a data scientist is to make reliable predictions based on data, particularly, when the amount of available data is enormous. To do so, it is useful if some of the analysis can be automated and used process mining techniques.In this context, the ability to know in advance the trend of running process instances, with respect to different features, such as the expected completion time, would allow business managers to timely counteract to undesired situations, in order to prevent losses. Therefore, the techniques focus on predicting the remaining time influence other predictive process monitoring dimensions like: cost, delays, etc, i.e., predicting the remaining time, to accomplish an activity, helps respectively to predict the suitable resource and the next executing probable event. Indeed, a considerable number of methods have been put forward to address this prediction remaining time problem. However, none of the existing works have been grouped these methods (published from 2006 to 2019) in a framework.Therefore, the main objective of this paper is developing a value-driven framework for classifying existing work on predictive process monitoring, related to the remaining time dimension.This framework can support organizations to navigate in this predictive process monitoring specification field and help them to find value and exploit the opportunities enabled by these analysis techniques. This objective is achieved by systematically identifying, categorizing, and analyzing existing approaches for predictive process monitoring.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114632737","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9002674
Imane Sadgali, N. Sael, F. Benabbou
Credit card transactions are nowadays more and more frequent. Using your credit card to buy online, as a mobile wallet or for a simple payment to a merchant has become a daily action for most cardholders. The virtual world and technological development that we know, makes banking transactions become digitized. As a result, a flow of millions of online transactions is subject to various types of fraud. Traditional techniques for detecting fraud cannot detect sophisticated fraudulent techniques. To be limited to an analysis of the cardholder behavior’s, or to static rules of risk management of the frauds, had never stopped the fraudulent to commit their crimes. However, machine-learning techniques have been able to meet this need, as we found in literature [1]. In this paper, we will present a comparative study of some machine learning techniques, which gave the best results, according to our state of art [1] but applied to the same set of data. The objective of this study is to choose the best credit card fraud detection techniques to implement in our future work.
{"title":"Fraud detection in credit card transaction using machine learning techniques","authors":"Imane Sadgali, N. Sael, F. Benabbou","doi":"10.1109/ICSSD47982.2019.9002674","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002674","url":null,"abstract":"Credit card transactions are nowadays more and more frequent. Using your credit card to buy online, as a mobile wallet or for a simple payment to a merchant has become a daily action for most cardholders. The virtual world and technological development that we know, makes banking transactions become digitized. As a result, a flow of millions of online transactions is subject to various types of fraud. Traditional techniques for detecting fraud cannot detect sophisticated fraudulent techniques. To be limited to an analysis of the cardholder behavior’s, or to static rules of risk management of the frauds, had never stopped the fraudulent to commit their crimes. However, machine-learning techniques have been able to meet this need, as we found in literature [1]. In this paper, we will present a comparative study of some machine learning techniques, which gave the best results, according to our state of art [1] but applied to the same set of data. The objective of this study is to choose the best credit card fraud detection techniques to implement in our future work.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129820789","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}
Today’s supply chains data should be harnessed more than ever. This data is the oil of the 21st century and industry 4.0 technologies are the engines to burn it. More precisely, thanks to internet of things devices, supply chains generated huge amounts of data. However, with the adequate tools, insights could be extracted for enhanced decision-making. In fact, industry 4.0 offers nine key technologies to address supply chain data. the aim of this paper is to illustrate the role of industry 4.0 towards supply chains, highlight its key technologies, clarify the importance of mathematical optimization in the era of digitalization and match these key technologies with supply chain processes so as to deliver customized products at the right time and in the right place.
{"title":"Industry 4.0: A roadmap to digital Supply Chains","authors":"Mariam Moufaddal, Asmaa Benghabrit, Imane Bouhaddou","doi":"10.1109/ICSSD47982.2019.9002751","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002751","url":null,"abstract":"Today’s supply chains data should be harnessed more than ever. This data is the oil of the 21st century and industry 4.0 technologies are the engines to burn it. More precisely, thanks to internet of things devices, supply chains generated huge amounts of data. However, with the adequate tools, insights could be extracted for enhanced decision-making. In fact, industry 4.0 offers nine key technologies to address supply chain data. the aim of this paper is to illustrate the role of industry 4.0 towards supply chains, highlight its key technologies, clarify the importance of mathematical optimization in the era of digitalization and match these key technologies with supply chain processes so as to deliver customized products at the right time and in the right place.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125314511","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9002699
B. Faqihi, N. Daoudi, R. Ajhoun
At present, there is a rapid increase of educational resources in various learning stands. The lesson producer is a fundamental as well as a responsible actor in the creation and the outline of educational resources. First, due to the cost caused by the process of producing new educational resources, and because of the fullness within these lasts. The author is invited to evade all sorts of vain duplications, and so take advantage and join the efforts. Our aim is to suggest a reference system to the author profile during the lesson creation, which may require the production of several educational resources to respond to general and specific objectives. Therefore, we have previously created a mode or a representation for the resource sought or the creation’s object by the author throughout a global ontology.In this paper, we hope for the launch of research based on the criteria drawn from the ontology and the mensuration techniques depending on the similarity degrees. We will bound this paper to two recommendations criteria that are; educational objectives and tags. Indeed, each educational resource contains, not only but an educational objective and at least a tag alone from its creation environment (Open Educational Resource, MOOC or e-learning). During the lesson creation, the author is beholden to identifying, above all the domain assigned, the specific objective, few tags and annotations or keywords; these elements are going to serve our ontology. Based the measures’ techniques of similarity amidst the author and the bank’s content of utilization cases, the recommendation system has to place a result sorted through a descending similarity degree. The author requires the possibility of updating the results by interposing under an administrator’s supervision a weighting, an indexation or a memorization related to each resource. For this reason, we firstly are going to limit our learning environment to; OER MOOC and e-learning. Then, we will limit the research domain to the Artificial Intelligence. Afterwards, we are going to perform researches on resources acknowledging the concept in question. Lastly, we will proceed to a comparative study amongst these studies in order to be able to choose the convenient technique to our work context. The first section consists of presenting the adapted method for the extraction educational resources. Thereafter, we are going to move towards the enhancement of our ontology from the identified extraction. Finally, we are going to prioritize the criteria according to our needs and present some measures techniques and choose one to adopt for our context.
{"title":"Proposition of the recommendation system for the author based on similarity degrees","authors":"B. Faqihi, N. Daoudi, R. Ajhoun","doi":"10.1109/ICSSD47982.2019.9002699","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002699","url":null,"abstract":"At present, there is a rapid increase of educational resources in various learning stands. The lesson producer is a fundamental as well as a responsible actor in the creation and the outline of educational resources. First, due to the cost caused by the process of producing new educational resources, and because of the fullness within these lasts. The author is invited to evade all sorts of vain duplications, and so take advantage and join the efforts. Our aim is to suggest a reference system to the author profile during the lesson creation, which may require the production of several educational resources to respond to general and specific objectives. Therefore, we have previously created a mode or a representation for the resource sought or the creation’s object by the author throughout a global ontology.In this paper, we hope for the launch of research based on the criteria drawn from the ontology and the mensuration techniques depending on the similarity degrees. We will bound this paper to two recommendations criteria that are; educational objectives and tags. Indeed, each educational resource contains, not only but an educational objective and at least a tag alone from its creation environment (Open Educational Resource, MOOC or e-learning). During the lesson creation, the author is beholden to identifying, above all the domain assigned, the specific objective, few tags and annotations or keywords; these elements are going to serve our ontology. Based the measures’ techniques of similarity amidst the author and the bank’s content of utilization cases, the recommendation system has to place a result sorted through a descending similarity degree. The author requires the possibility of updating the results by interposing under an administrator’s supervision a weighting, an indexation or a memorization related to each resource. For this reason, we firstly are going to limit our learning environment to; OER MOOC and e-learning. Then, we will limit the research domain to the Artificial Intelligence. Afterwards, we are going to perform researches on resources acknowledging the concept in question. Lastly, we will proceed to a comparative study amongst these studies in order to be able to choose the convenient technique to our work context. The first section consists of presenting the adapted method for the extraction educational resources. Thereafter, we are going to move towards the enhancement of our ontology from the identified extraction. Finally, we are going to prioritize the criteria according to our needs and present some measures techniques and choose one to adopt for our context.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122457646","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 the era of Big Data, an ever-growing stream of information is available online in different formats structured, semi-structured and unstructured, more and more companies and organizations are trying to take advantage of this phenomena and make data-based decisions through the use of automatic processes and software which gave birth to competitive intelligence systems. Though traditional techniques of data mining and statistics used in these systems do not respond to the main challenges of big data such as volume, variety, and velocity, which makes it a must for enterprises to harness the power of new technologies in big data analytics and create value out of its advantages. In this paper, we propose a framework based on Apache Spark for competitive intelligence strategy implementation in all its steps from data collection, data analysis, data visualization to results and findings communication in order to assist the decision-making process of an organization.
{"title":"A Spark Based Big Data Analytics Framework for Competitive Intelligence","authors":"Bouktaib Adil, Fennan Abdelhadi, Bahra Mohamed, Hmami Haytam","doi":"10.1109/ICSSD47982.2019.9002837","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002837","url":null,"abstract":"In the era of Big Data, an ever-growing stream of information is available online in different formats structured, semi-structured and unstructured, more and more companies and organizations are trying to take advantage of this phenomena and make data-based decisions through the use of automatic processes and software which gave birth to competitive intelligence systems. Though traditional techniques of data mining and statistics used in these systems do not respond to the main challenges of big data such as volume, variety, and velocity, which makes it a must for enterprises to harness the power of new technologies in big data analytics and create value out of its advantages. In this paper, we propose a framework based on Apache Spark for competitive intelligence strategy implementation in all its steps from data collection, data analysis, data visualization to results and findings communication in order to assist the decision-making process of an organization.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130501903","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：