Pub Date : 2022-12-21DOI: 10.1109/NTIC55069.2022.10100507
Chouaib Bourahla, R. Maamri, Said Brahimi
Many methods are used to retrieve relevant information in big data. One of these is the Skyline operator, which is used to retrieve the best objects in multidimensional datasets. The Skyline result helps to extract the required data with the optimal combination of characteristics of the data efficiently. In real big data, the data is often updated, and new data can be added deleted, or updated. A required recomputation of the Skyline each time the data is updated may lead to unacceptable response time. In this paper, we focus on reducing the Skyline recomputation time every time the dataset is updated. We proposed an approach that benefits from the overlap of precomputed Skyline results. And for this purpose, we used the history of Skyline computation results to recompute the new Skyline after updating the data. Based on the experiments we have performed; our approach can significantly reduce the Skyline recomputation time every time the data is updated.
{"title":"Skyline Computation Based on Previously Computed Results","authors":"Chouaib Bourahla, R. Maamri, Said Brahimi","doi":"10.1109/NTIC55069.2022.10100507","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100507","url":null,"abstract":"Many methods are used to retrieve relevant information in big data. One of these is the Skyline operator, which is used to retrieve the best objects in multidimensional datasets. The Skyline result helps to extract the required data with the optimal combination of characteristics of the data efficiently. In real big data, the data is often updated, and new data can be added deleted, or updated. A required recomputation of the Skyline each time the data is updated may lead to unacceptable response time. In this paper, we focus on reducing the Skyline recomputation time every time the dataset is updated. We proposed an approach that benefits from the overlap of precomputed Skyline results. And for this purpose, we used the history of Skyline computation results to recompute the new Skyline after updating the data. Based on the experiments we have performed; our approach can significantly reduce the Skyline recomputation time every time the data is updated.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115952989","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 : 2022-12-21DOI: 10.1109/NTIC55069.2022.10100494
Said Brahimi, Baha Eddine Founas
In this paper, we propose to use a combination of machine and deep learning tools for online person identification (PI) in a video-surveillance-based tracking system. To this end, we propose a skeleton of an algorithm-based framework that merges face and cloth-based identification to cope with the limitations of each one. We aim especially to complement face recognition based identification by clothing attributes based techniques by using contextual information to deal with complex conditions where there is a variability in lighting, pose, face size and distance from the camera. We therefore proposed to use context information to jointly integrate facial recognition and clothing recognition in unifying framework.
{"title":"Towards a Framework for Context-based Online Person Identification","authors":"Said Brahimi, Baha Eddine Founas","doi":"10.1109/NTIC55069.2022.10100494","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100494","url":null,"abstract":"In this paper, we propose to use a combination of machine and deep learning tools for online person identification (PI) in a video-surveillance-based tracking system. To this end, we propose a skeleton of an algorithm-based framework that merges face and cloth-based identification to cope with the limitations of each one. We aim especially to complement face recognition based identification by clothing attributes based techniques by using contextual information to deal with complex conditions where there is a variability in lighting, pose, face size and distance from the camera. We therefore proposed to use context information to jointly integrate facial recognition and clothing recognition in unifying framework.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"19 829 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132534936","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 : 2022-12-21DOI: 10.1109/NTIC55069.2022.10100517
Lubnaa Abdur Rahman, Poolan Marikannan Booma
Over the past years, autism rates have increased alarmingly, with 1 in 59 children, aged between 1 to 6 years, being affected globally. While treatment is available, if detected at a later stage or not detected at all, children must face lifelong consequences and even a reduced life expectancy. Therefore, an early diagnosis has the potential to enhance the children’s probability of having near-to-normal development. However, current methods of diagnosis are not accessible to everyone due to the high costs involved in clinical assessments and the time taken to reach a conclusive diagnosis thus leading majority of children being under-diagnosed. Deep learning has transformed multiple sectors thanks to its "high perform a nee" feature as opposed to traditional machine learning models and could have been long used for the early detection of autism as an attempt to reduce the affliction rates. Although autistic children have unique facial features which could be exploited using Deep Learning, not much effort has been put in that area. As such, this work takes on a Deep Transfer Learning approach for the detection of autism within children based on facial images by applying CNN-based models of ResNet50, VGG-16 and MobileNet with the latter being the most performant. After tuning, an overall accuracy of 89.5% and AUC of 0.97 were reached. Furthermore, on an endnote, the practical & ethical implications are looked at while also proposing that, as this work shows promising results, future works could look at a more real-time approach for the same.
{"title":"The Early Detection of Autism Within Children Through Facial Recognition; A Deep Transfer Learning Approach","authors":"Lubnaa Abdur Rahman, Poolan Marikannan Booma","doi":"10.1109/NTIC55069.2022.10100517","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100517","url":null,"abstract":"Over the past years, autism rates have increased alarmingly, with 1 in 59 children, aged between 1 to 6 years, being affected globally. While treatment is available, if detected at a later stage or not detected at all, children must face lifelong consequences and even a reduced life expectancy. Therefore, an early diagnosis has the potential to enhance the children’s probability of having near-to-normal development. However, current methods of diagnosis are not accessible to everyone due to the high costs involved in clinical assessments and the time taken to reach a conclusive diagnosis thus leading majority of children being under-diagnosed. Deep learning has transformed multiple sectors thanks to its \"high perform a nee\" feature as opposed to traditional machine learning models and could have been long used for the early detection of autism as an attempt to reduce the affliction rates. Although autistic children have unique facial features which could be exploited using Deep Learning, not much effort has been put in that area. As such, this work takes on a Deep Transfer Learning approach for the detection of autism within children based on facial images by applying CNN-based models of ResNet50, VGG-16 and MobileNet with the latter being the most performant. After tuning, an overall accuracy of 89.5% and AUC of 0.97 were reached. Furthermore, on an endnote, the practical & ethical implications are looked at while also proposing that, as this work shows promising results, future works could look at a more real-time approach for the same.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"27 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132120102","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 : 2022-12-21DOI: 10.1109/NTIC55069.2022.10100581
Koko Sarra, Aissa Boulmerka
The process of dividing aerial images into distinct segments based on their semantic content is a crucial aspect of computer vision research that has numerous real-world applications, including disaster monitoring, land mapping, weather forecasting, and agriculture. This work provides a comprehensive overview of the methods used for semantic segmentation of aerial images and how deep neural networks, especially convolutional neural networks and the U-net architecture, can be employed to achieve this. The methods discussed are trained on aerial image datasets, with the results demonstrating the effectiveness of using U-net and its variations for semantic segmentation of aerial imagery.
{"title":"Semantic segmentation of remote sensing images using U-net and its variants : Conference New Technologies of Information and Communication (NTIC 2022)","authors":"Koko Sarra, Aissa Boulmerka","doi":"10.1109/NTIC55069.2022.10100581","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100581","url":null,"abstract":"The process of dividing aerial images into distinct segments based on their semantic content is a crucial aspect of computer vision research that has numerous real-world applications, including disaster monitoring, land mapping, weather forecasting, and agriculture. This work provides a comprehensive overview of the methods used for semantic segmentation of aerial images and how deep neural networks, especially convolutional neural networks and the U-net architecture, can be employed to achieve this. The methods discussed are trained on aerial image datasets, with the results demonstrating the effectiveness of using U-net and its variations for semantic segmentation of aerial imagery.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115353386","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 : 2022-12-21DOI: 10.1109/NTIC55069.2022.10100408
Dida Hedifa, Charif Fella, B. Abderrazak
The results of resonance magnetic imaging and computerized tomography of the target organ provide complementary information about this organ that helps the radiologist in the diagnosis process. Despite the information provided by these two techniques, the radiologist needs a single sensor result containing the information of the CT and MRI image for better diagnosis of the disease. Image fusion is the process of merging complementary data of several sensors into a unique image. In this study, we propose a new approach for fusing CT and MRI of brain images using a guided filter and curvelet transform. Our method is based mainly on three basic steps, which are as following: Firstly, Extracted detail layers from each input image adopting a guided filter. Secondly, based on removing the blurred images from the input images, clearer images are obtained. Finally, the images are combined using the curvelet transform. The proposed method has been compared to effective fusion methods. Through the obtained qualitatively and quantitatively results, the proposed method showed a good result compared to other methods of fusion.
{"title":"Multimodal medical image fusion using guided filter and curvelet transform","authors":"Dida Hedifa, Charif Fella, B. Abderrazak","doi":"10.1109/NTIC55069.2022.10100408","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100408","url":null,"abstract":"The results of resonance magnetic imaging and computerized tomography of the target organ provide complementary information about this organ that helps the radiologist in the diagnosis process. Despite the information provided by these two techniques, the radiologist needs a single sensor result containing the information of the CT and MRI image for better diagnosis of the disease. Image fusion is the process of merging complementary data of several sensors into a unique image. In this study, we propose a new approach for fusing CT and MRI of brain images using a guided filter and curvelet transform. Our method is based mainly on three basic steps, which are as following: Firstly, Extracted detail layers from each input image adopting a guided filter. Secondly, based on removing the blurred images from the input images, clearer images are obtained. Finally, the images are combined using the curvelet transform. The proposed method has been compared to effective fusion methods. Through the obtained qualitatively and quantitatively results, the proposed method showed a good result compared to other methods of fusion.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122341956","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 : 2022-12-21DOI: 10.1109/NTIC55069.2022.10100615
Maya Souilah Benabdelhafid, M. Boufaida
One real challenge that still remains in healthcare domain is patient behaviour to both healthcare professionals and patients. Thus, it is important, even more crucial, to consider advanced technologies. Enterprise Resource Planning (ERP) applications are gaining increasing attention over the last years since they integrate various functions across an organization into a single information system. Nevertheless, this transition remains relatively slow in healthcare domain, particularly in the public sector. In this paper, we explain this issue and introduce the promising adoption of ERP systems in healthcare domain by highlighting the importance of using SOA and SAAS concepts when building ERP systems for gaining flexibility. After that, we model a simplified version of an ERP system by making use of Coloured Petri Net formalism and simulate it by exploring CPN Tools software in order to gain efficiency. Different properties can be verified.
{"title":"ERP Assimilation in Public Healthcare Sector: A Flexible and Efficient Approach","authors":"Maya Souilah Benabdelhafid, M. Boufaida","doi":"10.1109/NTIC55069.2022.10100615","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100615","url":null,"abstract":"One real challenge that still remains in healthcare domain is patient behaviour to both healthcare professionals and patients. Thus, it is important, even more crucial, to consider advanced technologies. Enterprise Resource Planning (ERP) applications are gaining increasing attention over the last years since they integrate various functions across an organization into a single information system. Nevertheless, this transition remains relatively slow in healthcare domain, particularly in the public sector. In this paper, we explain this issue and introduce the promising adoption of ERP systems in healthcare domain by highlighting the importance of using SOA and SAAS concepts when building ERP systems for gaining flexibility. After that, we model a simplified version of an ERP system by making use of Coloured Petri Net formalism and simulate it by exploring CPN Tools software in order to gain efficiency. Different properties can be verified.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127875426","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 : 2022-12-21DOI: 10.1109/NTIC55069.2022.10100607
Fayçal Imedjdouben
We present here a statistical tool dedicated to the Arabic language. This statistical tool uses encoding from the Unicode standard; the tool was programmed in the MATLAB environment. The statistical processing of the Arabic language constitutes a fundamental step for the realization and analysis of Arabic language corpora dedicated to various fields of application such as: the field of speech synthesis, speech recognition field, and the field of natural language processing. Our system which generates the statistical results related to the Arabic text is essentially based as input on a sequence of the diacritized Arabic text. The latter is transformed into data coded according to the Unicode standard so that the statistical rules base that we have developed can process it. The statistical tool developed provides useful information related to the treated Arabic text such as: number of words, occurrence frequency of each grapheme, and occurrence frequency of syllables "CV/CVV/CVC".
{"title":"Statistical Tool for Arabic Text","authors":"Fayçal Imedjdouben","doi":"10.1109/NTIC55069.2022.10100607","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100607","url":null,"abstract":"We present here a statistical tool dedicated to the Arabic language. This statistical tool uses encoding from the Unicode standard; the tool was programmed in the MATLAB environment. The statistical processing of the Arabic language constitutes a fundamental step for the realization and analysis of Arabic language corpora dedicated to various fields of application such as: the field of speech synthesis, speech recognition field, and the field of natural language processing. Our system which generates the statistical results related to the Arabic text is essentially based as input on a sequence of the diacritized Arabic text. The latter is transformed into data coded according to the Unicode standard so that the statistical rules base that we have developed can process it. The statistical tool developed provides useful information related to the treated Arabic text such as: number of words, occurrence frequency of each grapheme, and occurrence frequency of syllables \"CV/CVV/CVC\".","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129133110","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 : 2022-12-21DOI: 10.1109/NTIC55069.2022.10100422
Pedro Correia, Marcela Gomes, Gabriel Martins, Renato Panda
This paper proposes a low cost LoRaWAN image acquisition and transmission prototype for low rate and un-constrained delay IoT applications. Real scenario tests were performed and images, at distances up to 2.5 km from node to gateway in urban environment, were transmitted and correctly decoded. The obtained results show the effectiveness of a low-power wide-area (LPWAN) technology prototype for long distance image transmission in applications without delay constraints and where other wireless technologies are not available.
{"title":"Low Cost LoRaWAN Image Acquisition System for Low Rate Internet of Things Applications","authors":"Pedro Correia, Marcela Gomes, Gabriel Martins, Renato Panda","doi":"10.1109/NTIC55069.2022.10100422","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100422","url":null,"abstract":"This paper proposes a low cost LoRaWAN image acquisition and transmission prototype for low rate and un-constrained delay IoT applications. Real scenario tests were performed and images, at distances up to 2.5 km from node to gateway in urban environment, were transmitted and correctly decoded. The obtained results show the effectiveness of a low-power wide-area (LPWAN) technology prototype for long distance image transmission in applications without delay constraints and where other wireless technologies are not available.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128092630","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 : 2022-12-21DOI: 10.1109/NTIC55069.2022.10100404
Nabila Azeri, Zeinb Zouikri, Meriem Rezgui, Ouided Hioual, O. Hioual
In the last decade, industry has become highly dependent on smart systems which enable the physical world to merge with the virtual one. This development led to the emergence of Cyber Physical Systems (CPS). In this environment, services and resources must be always available to support the continuity of systems operation. Indeed, CPSs are intended to be flexible systems that can decide automatically how to adapt their internal behavior in response to the dynamics of the environment. The ability to, automatically, recognize and predict any fault or failure, that occurs while delivering services, is a step towards realizing such systems. We present in this paper an approach to early fault prediction using machine learning algorithms. The viability of the proposed solution is confirmed by a real world application in an industrial CPS.
{"title":"Fault Prediction Using Supervised and Unsupervised Learning Algorithms in Cyber Physical Systems","authors":"Nabila Azeri, Zeinb Zouikri, Meriem Rezgui, Ouided Hioual, O. Hioual","doi":"10.1109/NTIC55069.2022.10100404","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100404","url":null,"abstract":"In the last decade, industry has become highly dependent on smart systems which enable the physical world to merge with the virtual one. This development led to the emergence of Cyber Physical Systems (CPS). In this environment, services and resources must be always available to support the continuity of systems operation. Indeed, CPSs are intended to be flexible systems that can decide automatically how to adapt their internal behavior in response to the dynamics of the environment. The ability to, automatically, recognize and predict any fault or failure, that occurs while delivering services, is a step towards realizing such systems. We present in this paper an approach to early fault prediction using machine learning algorithms. The viability of the proposed solution is confirmed by a real world application in an industrial CPS.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122511958","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 : 2022-12-21DOI: 10.1109/ntic55069.2022.10100538
{"title":"NTIC 2022 Cover Page","authors":"","doi":"10.1109/ntic55069.2022.10100538","DOIUrl":"https://doi.org/10.1109/ntic55069.2022.10100538","url":null,"abstract":"","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114393370","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：