Pub Date : 2020-11-28DOI: 10.1109/ICAASE51408.2020.9380127
Yacine Khaldi, Amir Benzaoui
Most ear recognition techniques use cropped ear images, as they are, with backgrounds, hair, part of the face or neck skin, and even cloths. These non-ear pixels of the image can negatively affect the classification decision. To avoid that, and to make sure that the classifier depends on ear pixels only, we propose using a tight Region-of-Interest (RoI) segmentation of the ear instead. This paper uses Image-to-Image translation to synthesize ear RoI segmentation and remove irrelevant pixels from input images. Furthermore, missing parts of the ear due to occlusion or distortion can also be synthesized. To accomplish that, we used Pix2Pix Generative Adversarial Network (GAN) trained on the AWE dataset, which is a challenging ear dataset. Experimental results show that using ear RoI segmentation positively affects the classification process, and significantly increases the recognition rate.
{"title":"Region of Interest Synthesis using Image-to-Image Translation for ear recognition","authors":"Yacine Khaldi, Amir Benzaoui","doi":"10.1109/ICAASE51408.2020.9380127","DOIUrl":"https://doi.org/10.1109/ICAASE51408.2020.9380127","url":null,"abstract":"Most ear recognition techniques use cropped ear images, as they are, with backgrounds, hair, part of the face or neck skin, and even cloths. These non-ear pixels of the image can negatively affect the classification decision. To avoid that, and to make sure that the classifier depends on ear pixels only, we propose using a tight Region-of-Interest (RoI) segmentation of the ear instead. This paper uses Image-to-Image translation to synthesize ear RoI segmentation and remove irrelevant pixels from input images. Furthermore, missing parts of the ear due to occlusion or distortion can also be synthesized. To accomplish that, we used Pix2Pix Generative Adversarial Network (GAN) trained on the AWE dataset, which is a challenging ear dataset. Experimental results show that using ear RoI segmentation positively affects the classification process, and significantly increases the recognition rate.","PeriodicalId":405638,"journal":{"name":"2020 International Conference on Advanced Aspects of Software Engineering (ICAASE)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129459766","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}
The varied number of suggested meals put people who spend most of their time outside to a confusing situation. In addition, the proposed items (meals) are standard for all people, meaning that they receive the same menu, although they differ in many attributes such as age, weight, health status, eating habits and tastes. A recommendation based on nutritional value can help people to prevent or control certain diseases such as diabetes, hypertension and obesity. However, learning about people’s food preferences and making recommendations that simultaneously appeal to their health expectations, which can be very difficult, is really a very difficult task. Many existing recommendation systems do not take into account the context in which the user is placed and often suffer from the cold start system problem. Through this work, we propose a new collaborative and contextual recommendation system that allows the target user to be directed towards healthy menu of tasty meals. For this, the proposed approach was named Healthy and Tasty (H&T). H&T is a recommendation system based on a multilayer architecture, where the highest layer is based on the pre-filtering algorithm, which eliminates the cold start system problem, and is based mainly on the thresholds of the compatible nutritional elements with the user profile, thus ensuring the healthy factor in the recommendations. The middle layer based on collaborative filtering algorithm works in particular to ensure the taste factor, while the deepest layer is the pertinent layer based on the post-filtering algorithm, where the recommendation will be much more adapted to the environment of the user. The proposed approach has been realized via an Android application where the experimental results are promoters.
{"title":"Personalized Menu: a New Contextual Collaborative Recommender System","authors":"Hanane Zitouni, Khadidja Bouchelik, Ramla Saidi, Nassira Chekkai","doi":"10.1109/ICAASE51408.2020.9380111","DOIUrl":"https://doi.org/10.1109/ICAASE51408.2020.9380111","url":null,"abstract":"The varied number of suggested meals put people who spend most of their time outside to a confusing situation. In addition, the proposed items (meals) are standard for all people, meaning that they receive the same menu, although they differ in many attributes such as age, weight, health status, eating habits and tastes. A recommendation based on nutritional value can help people to prevent or control certain diseases such as diabetes, hypertension and obesity. However, learning about people’s food preferences and making recommendations that simultaneously appeal to their health expectations, which can be very difficult, is really a very difficult task. Many existing recommendation systems do not take into account the context in which the user is placed and often suffer from the cold start system problem. Through this work, we propose a new collaborative and contextual recommendation system that allows the target user to be directed towards healthy menu of tasty meals. For this, the proposed approach was named Healthy and Tasty (H&T). H&T is a recommendation system based on a multilayer architecture, where the highest layer is based on the pre-filtering algorithm, which eliminates the cold start system problem, and is based mainly on the thresholds of the compatible nutritional elements with the user profile, thus ensuring the healthy factor in the recommendations. The middle layer based on collaborative filtering algorithm works in particular to ensure the taste factor, while the deepest layer is the pertinent layer based on the post-filtering algorithm, where the recommendation will be much more adapted to the environment of the user. The proposed approach has been realized via an Android application where the experimental results are promoters.","PeriodicalId":405638,"journal":{"name":"2020 International Conference on Advanced Aspects of Software Engineering (ICAASE)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129502599","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 : 2020-11-28DOI: 10.1109/ICAASE51408.2020.9380106
Sofiane Aouag, Salim Kadri, D. Hedjazi
Architecture-Driven Modernization claims that MDA (Model-Driven Architecture) concepts should be used for modernization projects in the process. One of the largest challenges when contemplating ADM (Architecture-Driven Modernization) is the modernization of developed system in order to ensure interoperability between tools for maintenance, evolution, assessment and allow the success of modernization projects that preserving architecture quality. ADM supports reengineering by providing standard meta-models, such as Knowledge Discovery Metamodel (KDM). Modernizing a large legacy or existing system is therefore a complex and expensive process that requires a thorough understanding of the system design architecture and its components. However, legacy systems have also experienced several modifications that lead them to deviate from their original designed architecture and lose its properties of quality. To facilitate the analysis of the system, the projection process proposed as part of our approach is based on facet cutting which allows determining the views having anomalies in order to facilitate quality control. The proposed approach in this paper is of great importance in the context of the modernization process, since it is committed to improving the KDM framework as methods used to assist in the detection of architecture violation.
{"title":"Towards architectural view-driven modernization","authors":"Sofiane Aouag, Salim Kadri, D. Hedjazi","doi":"10.1109/ICAASE51408.2020.9380106","DOIUrl":"https://doi.org/10.1109/ICAASE51408.2020.9380106","url":null,"abstract":"Architecture-Driven Modernization claims that MDA (Model-Driven Architecture) concepts should be used for modernization projects in the process. One of the largest challenges when contemplating ADM (Architecture-Driven Modernization) is the modernization of developed system in order to ensure interoperability between tools for maintenance, evolution, assessment and allow the success of modernization projects that preserving architecture quality. ADM supports reengineering by providing standard meta-models, such as Knowledge Discovery Metamodel (KDM). Modernizing a large legacy or existing system is therefore a complex and expensive process that requires a thorough understanding of the system design architecture and its components. However, legacy systems have also experienced several modifications that lead them to deviate from their original designed architecture and lose its properties of quality. To facilitate the analysis of the system, the projection process proposed as part of our approach is based on facet cutting which allows determining the views having anomalies in order to facilitate quality control. The proposed approach in this paper is of great importance in the context of the modernization process, since it is committed to improving the KDM framework as methods used to assist in the detection of architecture violation.","PeriodicalId":405638,"journal":{"name":"2020 International Conference on Advanced Aspects of Software Engineering (ICAASE)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117263673","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 : 2020-11-28DOI: 10.1109/icaase51408.2020.9380122
{"title":"ICAASE 2020 Table of Contents","authors":"","doi":"10.1109/icaase51408.2020.9380122","DOIUrl":"https://doi.org/10.1109/icaase51408.2020.9380122","url":null,"abstract":"","PeriodicalId":405638,"journal":{"name":"2020 International Conference on Advanced Aspects of Software Engineering (ICAASE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125831336","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 : 2020-11-28DOI: 10.1109/ICAASE51408.2020.9380114
Chafia Bouanaka, N. Benlahrache, Sana Benhamaid, Emira Bouhamed
We are gradually witnessing a transformation of our technological environment; more and more physical objects are connected to the Internet. The so called “Internet of Things” (IoT) is a revolution that has been going on for more than 10 years. However, the rapid evolution of this field and the special features of its systems make their engineering very delicate and the application of conventional development methodologies unsuitable. Indeed, there exists a limited number of methodologies that can be used to effectively develop IoT systems and clearly represent their specific concerns and characteristics. The aim of our work is to establish a state of the art on the IoT technology to identify the different characteristics of IoT systems and then analyze the existing methodologies used to design them and see to which extent those methodologies respect the selected criteria. On the basis of this synthesis, the IDeA methodology meets well the established criteria and is adopted for the design and development of IoT systems. Besides, we contribute to the extension of its domain model so that it can support the security aspects and mechanisms to make safe IoT systems. We illustrate the methodology adopted through the design and implementation of a smart traffic lights system.
{"title":"A Review of IoT Systems Engineering: Application to the Smart traffic lights system","authors":"Chafia Bouanaka, N. Benlahrache, Sana Benhamaid, Emira Bouhamed","doi":"10.1109/ICAASE51408.2020.9380114","DOIUrl":"https://doi.org/10.1109/ICAASE51408.2020.9380114","url":null,"abstract":"We are gradually witnessing a transformation of our technological environment; more and more physical objects are connected to the Internet. The so called “Internet of Things” (IoT) is a revolution that has been going on for more than 10 years. However, the rapid evolution of this field and the special features of its systems make their engineering very delicate and the application of conventional development methodologies unsuitable. Indeed, there exists a limited number of methodologies that can be used to effectively develop IoT systems and clearly represent their specific concerns and characteristics. The aim of our work is to establish a state of the art on the IoT technology to identify the different characteristics of IoT systems and then analyze the existing methodologies used to design them and see to which extent those methodologies respect the selected criteria. On the basis of this synthesis, the IDeA methodology meets well the established criteria and is adopted for the design and development of IoT systems. Besides, we contribute to the extension of its domain model so that it can support the security aspects and mechanisms to make safe IoT systems. We illustrate the methodology adopted through the design and implementation of a smart traffic lights system.","PeriodicalId":405638,"journal":{"name":"2020 International Conference on Advanced Aspects of Software Engineering (ICAASE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129526860","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 : 2020-11-28DOI: 10.1109/ICAASE51408.2020.9380116
Souheir Merkouche, Chafia Bouanaka, Fatma Kachi
Modern software systems tend to become increasingly complex and dynamic where unpredictable changes in user needs, in platforms and in execution contexts are unavoidable. Therefore, self-adaptation presents a promising approach for managing the complexity of current systems. One major objective of software engineering for self-adaptive systems is to deal with such complexity, changing contexts and mainly uncertainty, but still maintaining the quality requirements of the system, namely security, reliability, robustness, and so on. Uncertainty can be of various sources as the changeable environment and variability in resource availability. In this paper, we introduce a formal model for self-adaptive systems operating under uncertainty, in which we make use of both high-level petri nets and plausible petri nets, in order to help the designer to model systems that are capable of monitoring their operation and adapt their behavior when their contexts or environment change.
{"title":"Towards Formal Modeling of Quality-driven Systems under uncertainty","authors":"Souheir Merkouche, Chafia Bouanaka, Fatma Kachi","doi":"10.1109/ICAASE51408.2020.9380116","DOIUrl":"https://doi.org/10.1109/ICAASE51408.2020.9380116","url":null,"abstract":"Modern software systems tend to become increasingly complex and dynamic where unpredictable changes in user needs, in platforms and in execution contexts are unavoidable. Therefore, self-adaptation presents a promising approach for managing the complexity of current systems. One major objective of software engineering for self-adaptive systems is to deal with such complexity, changing contexts and mainly uncertainty, but still maintaining the quality requirements of the system, namely security, reliability, robustness, and so on. Uncertainty can be of various sources as the changeable environment and variability in resource availability. In this paper, we introduce a formal model for self-adaptive systems operating under uncertainty, in which we make use of both high-level petri nets and plausible petri nets, in order to help the designer to model systems that are capable of monitoring their operation and adapt their behavior when their contexts or environment change.","PeriodicalId":405638,"journal":{"name":"2020 International Conference on Advanced Aspects of Software Engineering (ICAASE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132707994","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：