Saad Yasser Chadli, A. Idri, J. Alemán, J. Nicolás
{"title":"Frameworks for risk management in GSD projects: A survey","authors":"Saad Yasser Chadli, A. Idri, J. Alemán, J. Nicolás","doi":"10.1109/SITA.2015.7358381","DOIUrl":"https://doi.org/10.1109/SITA.2015.7358381","url":null,"abstract":"To reduce the high failure rate of software projects, managers need better instruments to assess and manage software project risk. In order to create such instruments, however, researchers must first develop a better understanding of the dimensions of software project risk and how they can affect project performance. The first task in risk management is to identify these risks then to counter them using one of four response strategies namely Share, Avoid, Reduce or Accept (Mnemonic: SARA). The aim of this paper is to present a survey of the current available frameworks in literature for risk management in global software development projects. The selected two frameworks are analyzed and a comparison between them is made.","PeriodicalId":174405,"journal":{"name":"2015 10th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125134065","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}
{"title":"A JADE based testbed for evaluating computational trust models","authors":"Mifrah Youssef, A. En-Nouaary, Dahchour Mohamed","doi":"10.1109/SITA.2015.7358407","DOIUrl":"https://doi.org/10.1109/SITA.2015.7358407","url":null,"abstract":"Trust and reputation are commonly considered critical concepts in open dynamic multi-agent systems, where agents must rely on their peers to achieve their goals. Several computational trust models have been proposed to manage trust in such situation. The diversity of those models makes user confused about which one to choose. Different testbeds were proposed to evaluate trust and reputation systems and verify the robustness of the underlying trust models. However, those testbeds are not flexible to handle different scenarios in various contexts. In this paper, we present a testbed for evaluating computational trust models that could provide user more flexibility while comparing trust models in open systems. The ultimate objective is to evaluate and classify available computational trust models.","PeriodicalId":174405,"journal":{"name":"2015 10th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123945870","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}
{"title":"Survey on supply chain ICT requirments","authors":"Sara El Ouadaa, Slimane Bah, A. Berrado","doi":"10.1109/SITA.2015.7358399","DOIUrl":"https://doi.org/10.1109/SITA.2015.7358399","url":null,"abstract":"Information and communication technologies are an important driver for supply chain performance. This paper analyses the ICTs' relative requirements for efficient supply chain management. Logistical systems in a supply chain, can integrate a combination of compatible information access, sensing and communication technologies. Such as RFID, WSN, GSM, GPRS, Wi-fi. The existing Applications of ICTs within SC have been trying to optimize the performance of individual areas of SC. This practice often results in conflicting actions that reduce the SC surplus. This paper also provides a critical analysis of the existing solutions and highlights their impeding factors.","PeriodicalId":174405,"journal":{"name":"2015 10th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117110866","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}
{"title":"A new wrapper feature selection model using Skewed Variable Neighborhood Search with CE-SVM algorithm","authors":"Naoual El Aboudi, Laila Benhlima","doi":"10.1109/SITA.2015.7358426","DOIUrl":"https://doi.org/10.1109/SITA.2015.7358426","url":null,"abstract":"Feature selection is an important step in many Machine Learning classification problems. It reduces the dimensionality of the feature space by removing noisy, irrelevant and redundant data, such that classification accuracy is enhanced while computational time remains affordable. In this paper, we present a new wrapper feature subset selection model based on Skewed Variable Neighborhood Search (SVNS). In order to determine classification accuracy, we endorse Support Vector Machine (SVM) which is a well tested classification algorithm. The optimal feature subset is investigated using SVNS while SVM hyperparameters are automatically tuned by Cross Entropy (CE) technique which is recognized to be a powerful optimization tool. The performance of proposed model is compared with some existent methods regarding the task of feature selection on 3 well-known UCI datasets. Simulation results show that the suggested system achieves promising classification accuracy using a smaller feature set.","PeriodicalId":174405,"journal":{"name":"2015 10th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117025843","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}
{"title":"A hybrid Deep belief network approach for Financial distress prediction","authors":"Zineb Lanbouri, Saaid Achchab","doi":"10.1109/SITA.2015.7358416","DOIUrl":"https://doi.org/10.1109/SITA.2015.7358416","url":null,"abstract":"After the subprime crisis in 2008, an efficient Financial Distress Prediction (FDP) model has become necessary. Many research works have attempted to provide a model using statistical or intelligent methods. In this respect, this paper adopts a two-stage hybrid model that integrates Deep Learning and Support Vector Machine as a FDP modeling method. Local receptive fields is a technique used in order to select the nodes for each layer of our deep network. Then, stacked Restricted Boltzmann Machine is applied to form a Deep Belief Network as pre-training. Subsequently, Support Vector Machine follows for classification. An experiment over a sample of French firms offers accuracy details about this method. The proposed model actually provides a result of 76,8% instances that are correctly classified. Henceforth, the new technique could prevent Financial distress before it happens. As such, investors, managers, banks, decision makers and others could benefit from its significant impact.","PeriodicalId":174405,"journal":{"name":"2015 10th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132667296","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}
{"title":"A new trust model to secure routing protocols against DoS attacks in MANETs","authors":"Adel Echchaachoui, A. Kobbane, M. Elkoutbi","doi":"10.1109/SITA.2015.7358397","DOIUrl":"https://doi.org/10.1109/SITA.2015.7358397","url":null,"abstract":"In mobile Ad hoc networks, data is transmitted in airspace between mobile entities without any centralized control. This environment offers many and very important services for mobile users. However, the level of security in this kind of network has not yet reached a significant level of maturity against the ferocious attacks. In this work, we present a new model to trust routing protocols communications in MANETs against DoS attacks. We have used the box plot theory to define accurately the threshold to detect a DoS attack and to reduce the number of false positives.","PeriodicalId":174405,"journal":{"name":"2015 10th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"259 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133103665","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}
{"title":"Schema Matching as complex adaptive system","authors":"Hicham Assoudi, H. Lounis","doi":"10.1109/SITA.2015.7358442","DOIUrl":"https://doi.org/10.1109/SITA.2015.7358442","url":null,"abstract":"Many algorithms and approaches were proposed to deal with the problem of automatic schema matching and mapping. Yet, managing uncertainty and complexity for Schema Matching still remains as an open question. The challenges and difficulties caused by the complexity characterising the process of Schema Matching motivated us to investigate how the application of a bio-inspired emerging paradigm can lead us to understand, manage and ultimately overcome the inherent uncertainty in this process. The central idea of our work, is to consider the process of matching as a complex adaptive system and model it using the approach of agent-based modeling and simulation. The aim being the exploitation of the intrinsic properties of the agent-based models, such as emergence, stochasticity and self-organization, to help provide answers to better manage complexity and uncertainty of Schema Matching.","PeriodicalId":174405,"journal":{"name":"2015 10th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131522948","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}
{"title":"AMEG: Adaptive mechanism for educational games based on IMSLD and artificial intelligence","authors":"N. Hamdaoui, Mohammed Khalidi, S. Bennani","doi":"10.1109/SITA.2015.7358424","DOIUrl":"https://doi.org/10.1109/SITA.2015.7358424","url":null,"abstract":"Video games are very well known for their engaging and immersive capacities as well as motivation enhancement. Recently, we have witnessed their use in different serious areas such as education. Educational games must ensure an effective educational experience as well as an entertaining gameplay for each kind of player/learner. Most commercial video games adapt the playing experience to the player by using different artificial intelligence algorithms. In this paper we will propose an adaptive mechanism, which is constituted of two bricks, the first one, `AI brick' will adapt the gameplay based on the player's playing style personal decisions and performance in the game. The second one, `IMSLD brick' will be based on IMSLD elements to adapt the learning content depending on the learner's knowledge and learning style. Thus, ensuring both fun and effective educational experience at the same time.","PeriodicalId":174405,"journal":{"name":"2015 10th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133756955","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}
{"title":"Fuzzy ant colony based routing protocol for delay tolerant network","authors":"Ababou Mohamed, M. Bellafkih, R. Kouch","doi":"10.1109/SITA.2015.7358386","DOIUrl":"https://doi.org/10.1109/SITA.2015.7358386","url":null,"abstract":"Routing in DTN networks is a difficult task due to the high mobility of nodes, intermittent connections, and the limited capacity of the buffer and the battery of the nodes. In addition, the majority of routing protocols in DTN environment do not take into account the energy level of the nodes as well as the relays that have already received a copy of the message in order to determine if a node can participate or not to forward a message. This paper proposes a new approach called FBADTN routing protocol based on the intelligence of ants colony and fuzzy logic to select the best relay by using the energy level of the relays as well as information on the nodes that have already received a copy of the message. Simulation results show that the performances of the proposed protocol are better than the existing protocols.","PeriodicalId":174405,"journal":{"name":"2015 10th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122984745","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}
{"title":"A distributed graph based approach for rough classifications considering dominance relations between overlapping classes","authors":"Khalil Laghmari, M. Ramdani, C. Marsala","doi":"10.1109/SITA.2015.7358388","DOIUrl":"https://doi.org/10.1109/SITA.2015.7358388","url":null,"abstract":"Several data from real world applications involves overlapping classes. Data is allowed to belong to multiple classes with different membership degrees. In this paper, we explore a different concept characterizing social networks, documents, and most of biological and chemical datasets: data could have multiple classes, but dominant classes are better noticed than dominated classes. For example, a document could discuss economy and politics, but it would be more focused on politics. A molecule could have multiple odors, but experts could notice some odors better than others. We are interested in this type of data, where a dominance relation exists between classes. Experts could easily make mistakes because dominated classes are hardly noticed. Data incoherence is a serious problem but not the only one. There is too much irrelevant and redundant attributes. Unfortunately this increases the computational time of generating classifiers. Our first challenge is to find an adapted model to overlapping classes considering dominance relations. The second challenge is to find the most relevant attributes. Finally the third challenge is to ensure that the approach gives results in an acceptable time. We address those challenges by taking advantage of the rough set theory, which is suited for incoherent data and allows multiple classes and attributes selection. The proposed approach works in a parallel and decentralized way to reduce the computational time. We tested it on real chemical data and the collected results are very promising.","PeriodicalId":174405,"journal":{"name":"2015 10th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128195778","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}