Pub Date : 2022-12-21DOI: 10.1109/NTIC55069.2022.10100571
Sabrina Tadjine, Ali Lemouari, M. Kara
Multicast routing is a telecommunication technique that simultaneously sending data from one, or more source to several destination. Multimedia applications are widely used. These applications require several QoS constraints. This paper proposes a multi-constrained QoS multicast routing method using simulated annealing metaheuristic. The proposed algorithm minimizes the cost of multicast tree while satisfying bandwidth, delay, delay jitter, and packet loss constraints. In the proposed approach we use R-Path move method to construct neighbors. The simulation results demonstrate that our algorithm is better for cost performance, best multicast tree obtained, compared to others algorithms.
{"title":"Solving Multiconstrained Quality of service Multicast Routing Problem using Simulated Annealing Algorithm","authors":"Sabrina Tadjine, Ali Lemouari, M. Kara","doi":"10.1109/NTIC55069.2022.10100571","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100571","url":null,"abstract":"Multicast routing is a telecommunication technique that simultaneously sending data from one, or more source to several destination. Multimedia applications are widely used. These applications require several QoS constraints. This paper proposes a multi-constrained QoS multicast routing method using simulated annealing metaheuristic. The proposed algorithm minimizes the cost of multicast tree while satisfying bandwidth, delay, delay jitter, and packet loss constraints. In the proposed approach we use R-Path move method to construct neighbors. The simulation results demonstrate that our algorithm is better for cost performance, best multicast tree obtained, compared to others algorithms.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"70 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":"115171170","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}
Deterioration of the bone’s microarchitecture and low bone mineral density, which results in increased fragility of bone, are symptoms of the disease osteoporosis, which decreases bone mass. Early osteoporosis identification can prevent the disease and predict fracture risk. Usually, the diagnosis is based on the analysis of X-ray images. However, the healthy and osteoporotic subject radiography shows a great resemblance. This study aims to develop an evaluation of an automatic osteoporosis identification system based on texture analysis. This paper proposes a Local Optimal Oriented Pattern (LOOP) to address some of the shortcomings of existing feature descriptors such as Local Binary Pattern (LBP) and Local Directional Pattern (LDP). Ensemble and SVM learning algorithms were used for the classification task. The obtained results were compared with some state-of-art methods used in the literature. Experimental results show that the proposed approach outperforms the previous binary descriptor in terms of recognition accuracy proving that the proposed approach is efficient for real clinical applications.
{"title":"Evaluation of Local Binary Pattern for Osteoporosis Classification","authors":"Mebarkia Meriem, Meraoumia Abdallah, Houam Lotfi, Khemaissia Seddik","doi":"10.1109/NTIC55069.2022.10100543","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100543","url":null,"abstract":"Deterioration of the bone’s microarchitecture and low bone mineral density, which results in increased fragility of bone, are symptoms of the disease osteoporosis, which decreases bone mass. Early osteoporosis identification can prevent the disease and predict fracture risk. Usually, the diagnosis is based on the analysis of X-ray images. However, the healthy and osteoporotic subject radiography shows a great resemblance. This study aims to develop an evaluation of an automatic osteoporosis identification system based on texture analysis. This paper proposes a Local Optimal Oriented Pattern (LOOP) to address some of the shortcomings of existing feature descriptors such as Local Binary Pattern (LBP) and Local Directional Pattern (LDP). Ensemble and SVM learning algorithms were used for the classification task. The obtained results were compared with some state-of-art methods used in the literature. Experimental results show that the proposed approach outperforms the previous binary descriptor in terms of recognition accuracy proving that the proposed approach is efficient for real clinical applications.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"36 2-4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120893394","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/NTIC55069.2022.10100506
Khadidja Nesrine Boubakeur, M. Debyeche, A. Amrouche, Youssouf Bentrcia
The use of prosodic characteristics, mainly pitch and intensity, for speaker identification in noisy environments is examined in this work. To make the acoustic models more resistant to the variability in the speech signal in noisy situations, these features are supplemented with cepstral parameters. As a consequence, two systems for Automatic Speaker Identification (ASI) in the independent mode of text are implemented. The first based on Hidden Markov Models (HMM), whereas Support Vector Machines (SVM) are employed in the second. The addition of prosodic features improves recognition, especially in high-noise environments. The performance of SVM-based systems is better than HMM-based systems
{"title":"Prosodic Modelling based Speaker Identification","authors":"Khadidja Nesrine Boubakeur, M. Debyeche, A. Amrouche, Youssouf Bentrcia","doi":"10.1109/NTIC55069.2022.10100506","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100506","url":null,"abstract":"The use of prosodic characteristics, mainly pitch and intensity, for speaker identification in noisy environments is examined in this work. To make the acoustic models more resistant to the variability in the speech signal in noisy situations, these features are supplemented with cepstral parameters. As a consequence, two systems for Automatic Speaker Identification (ASI) in the independent mode of text are implemented. The first based on Hidden Markov Models (HMM), whereas Support Vector Machines (SVM) are employed in the second. The addition of prosodic features improves recognition, especially in high-noise environments. The performance of SVM-based systems is better than HMM-based systems","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"23 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":"122149176","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/NTIC55069.2022.10100511
Wafaa Mohammed Cherif, T. B. Stambouli
Biometric authentication has proven to be a successful strategy for correctly recognizing a person’s identification. in particular, palmprint-based biometric systems have received increased attention in recent years, due to its high identification accuracy, utility and acceptance. The traditional method of palmprint recognition requires the extraction of palmprint characteristics before the classification, which has an impact on the recognition rate. To address this problem, the CNN Model LeNet-5 is used to propose a method for extracting discriminative features using Convolution Neural Networks. First, Segmentation based on Active Contours is used for ROI palmprint Extraction. Then the convolutional neural network is trained based on the extracted ROI region by selecting the optimal learning rate and hyperparameters. Finally, the palmprint was identified. The experiments demonstrated that The ROI extraction system could accurately find the most suitable Regions Of Interest, compared with existing main ROI extraction methods, our model proved competitive with the state-of-the-art. We achieved an overall accuracy of 97% using two hand databases : IITD hand database, and Tongji Contactless Palmprint Dataset.
{"title":"Active Contour Based Segmentation and CNN for Palmprint Recognition","authors":"Wafaa Mohammed Cherif, T. B. Stambouli","doi":"10.1109/NTIC55069.2022.10100511","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100511","url":null,"abstract":"Biometric authentication has proven to be a successful strategy for correctly recognizing a person’s identification. in particular, palmprint-based biometric systems have received increased attention in recent years, due to its high identification accuracy, utility and acceptance. The traditional method of palmprint recognition requires the extraction of palmprint characteristics before the classification, which has an impact on the recognition rate. To address this problem, the CNN Model LeNet-5 is used to propose a method for extracting discriminative features using Convolution Neural Networks. First, Segmentation based on Active Contours is used for ROI palmprint Extraction. Then the convolutional neural network is trained based on the extracted ROI region by selecting the optimal learning rate and hyperparameters. Finally, the palmprint was identified. The experiments demonstrated that The ROI extraction system could accurately find the most suitable Regions Of Interest, compared with existing main ROI extraction methods, our model proved competitive with the state-of-the-art. We achieved an overall accuracy of 97% using two hand databases : IITD hand database, and Tongji Contactless Palmprint Dataset.","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":"128662879","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/ntic55069.2022.10100501
Rahima Boukerma, Bachir Boucheham, Salah Bougueroua
In this paper we present Dynamic Pattern Weighting (DPW), a novel method for Content-Based Image Retrieval (CBIR). This method has the capability to reduce the semantic gap by giving dynamically an appropriate weight to each pattern of the image according to the image class and the importance of the pattern in the image. After an offline optimization phase using a metaheuristic algorithm, a weight vector is obtained for each class of the image database. Thereafter, to choose the proper weight vector for the query image, an assumed class is determined by applying K-nearest neighbors algorithm. Furthermore, for each individual pattern a different importance is determined adaptively, depending on the occurrences number of the pattern in the image. The proposed method has been evaluated using four local pattern methods to extract image texture features. Experiments on Corel-1K database reveals that the performance of the dynamic weighted methods outperforms the other methods.
{"title":"Image Retrieval Based on Dynamic Weighted Patterns","authors":"Rahima Boukerma, Bachir Boucheham, Salah Bougueroua","doi":"10.1109/ntic55069.2022.10100501","DOIUrl":"https://doi.org/10.1109/ntic55069.2022.10100501","url":null,"abstract":"In this paper we present Dynamic Pattern Weighting (DPW), a novel method for Content-Based Image Retrieval (CBIR). This method has the capability to reduce the semantic gap by giving dynamically an appropriate weight to each pattern of the image according to the image class and the importance of the pattern in the image. After an offline optimization phase using a metaheuristic algorithm, a weight vector is obtained for each class of the image database. Thereafter, to choose the proper weight vector for the query image, an assumed class is determined by applying K-nearest neighbors algorithm. Furthermore, for each individual pattern a different importance is determined adaptively, depending on the occurrences number of the pattern in the image. The proposed method has been evaluated using four local pattern methods to extract image texture features. Experiments on Corel-1K database reveals that the performance of the dynamic weighted methods outperforms the other methods.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"35 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":"132780109","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/NTIC55069.2022.10100395
Bilal Benmessahel
We are nowadays obligated to deal with rich datasets with exceptionally high dimensions due to big data and IoT. Therefore, a technique known as feature selection (FS) is employed to carry out any machine learning activity or get insights from such dimensions data. One of the most fundamental issues in the analysis of high-dimensional data is feature selection. In this work, we suggest a new approach to the problem of feature selection, which involves selecting a subset of pertinent features for the research topic from a wide number of attributes. To tackle the FS problem, a new bio-inspired algorithm called PSODA is developed in this study, and a novel approach is suggested to maintain a balance between the capacities for exploration and exploitation. The Dragonfly Technique (DA) and the particle swarm optimization (PSO) approach were combined to create the suggested algorithm. Over the most popular datasets in literature, the proposed approach was adequately compared to other algorithms. The outcomes show how PSODA outperforms all other algorithms.
{"title":"New hybrid Particle Swarm and Dragonfly Algorithm for features selection","authors":"Bilal Benmessahel","doi":"10.1109/NTIC55069.2022.10100395","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100395","url":null,"abstract":"We are nowadays obligated to deal with rich datasets with exceptionally high dimensions due to big data and IoT. Therefore, a technique known as feature selection (FS) is employed to carry out any machine learning activity or get insights from such dimensions data. One of the most fundamental issues in the analysis of high-dimensional data is feature selection. In this work, we suggest a new approach to the problem of feature selection, which involves selecting a subset of pertinent features for the research topic from a wide number of attributes. To tackle the FS problem, a new bio-inspired algorithm called PSODA is developed in this study, and a novel approach is suggested to maintain a balance between the capacities for exploration and exploitation. The Dragonfly Technique (DA) and the particle swarm optimization (PSO) approach were combined to create the suggested algorithm. Over the most popular datasets in literature, the proposed approach was adequately compared to other algorithms. The outcomes show how PSODA outperforms all other algorithms.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"21 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":"127822967","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}
Learning through games is a pedagogical approach that promotes the use of playful activities to stimulate many aspects of children’s development and learning. We know that children spend a long duration on social media and intensive games that have a negative impact on their development and behavior. Therefore, it is important to teach them how to use their smartphones using fun and creative robot educational games that help in developing their social, emotional, and soft skills.Existing educational robot games are too expensive for Algerian parents and the government, that why Algerian children could not access and use them even in school or at home. For that reason, This project aims to develop an educational robot game accessible to everyone, based on a robot that moves on a map using a mobile application that controls the movement of this robot in real-time, according to the children’s answers.We have adopted the Scrum agile methodology for the development of this project for more flexibility, adaptability, and quality, and in the requirement analysis and design phases, we used SysML language which is suitable for modeling IoT-based applications.We have offered a scalable mobile application adaptable to the child’s age and learning level. Many educational games are offered: mental calculations, learning letters, numbers, objects, and languages through word games, and recognition of hidden objects; all are available in three languages, Arabic, French, and English.
{"title":"DZRobot4Kids: a mobile robot application for educational games","authors":"Meriem Belguidoum, Ammar Hamlaoui, Houssem Eddine Bendaas","doi":"10.1109/NTIC55069.2022.10100359","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100359","url":null,"abstract":"Learning through games is a pedagogical approach that promotes the use of playful activities to stimulate many aspects of children’s development and learning. We know that children spend a long duration on social media and intensive games that have a negative impact on their development and behavior. Therefore, it is important to teach them how to use their smartphones using fun and creative robot educational games that help in developing their social, emotional, and soft skills.Existing educational robot games are too expensive for Algerian parents and the government, that why Algerian children could not access and use them even in school or at home. For that reason, This project aims to develop an educational robot game accessible to everyone, based on a robot that moves on a map using a mobile application that controls the movement of this robot in real-time, according to the children’s answers.We have adopted the Scrum agile methodology for the development of this project for more flexibility, adaptability, and quality, and in the requirement analysis and design phases, we used SysML language which is suitable for modeling IoT-based applications.We have offered a scalable mobile application adaptable to the child’s age and learning level. Many educational games are offered: mental calculations, learning letters, numbers, objects, and languages through word games, and recognition of hidden objects; all are available in three languages, Arabic, French, and English.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"2002 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":"125768084","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/NTIC55069.2022.10100485
Abdelmalek Bengheni
This article offers a Multi-threshold Energy approach for Energy-Harvesting Wireless Sensor Network (MTE-EHWSN) to enhance the lifetime and Wireless Sensor Network (WSN) performance by minimizing the duty-cycle more radically and profoundly of each sensor node. The use of MTE-EHWSN by any sensor node in the WSN allows for energy harvesting management and energy consumption, helping it to ensure its balance and to dynamically regulate its duty-cycle through calculating its sleep interval more radically and profoundly according on the amount of current remaining energy. In addition, our proposed approach allows WSN to function well in the case of low energy harvesting. Through OMNeT++/MiXiM simulations, we demonstrated that MTE-EHWSN approach enhances the WSN performance compared to other current energy harvesting administration approach such as EH2M by incorporating these two approaches into the sender-initiated MAC mode of communication.
{"title":"A Multi-Threshold Energy approach for Energy Harvesting WSN","authors":"Abdelmalek Bengheni","doi":"10.1109/NTIC55069.2022.10100485","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100485","url":null,"abstract":"This article offers a Multi-threshold Energy approach for Energy-Harvesting Wireless Sensor Network (MTE-EHWSN) to enhance the lifetime and Wireless Sensor Network (WSN) performance by minimizing the duty-cycle more radically and profoundly of each sensor node. The use of MTE-EHWSN by any sensor node in the WSN allows for energy harvesting management and energy consumption, helping it to ensure its balance and to dynamically regulate its duty-cycle through calculating its sleep interval more radically and profoundly according on the amount of current remaining energy. In addition, our proposed approach allows WSN to function well in the case of low energy harvesting. Through OMNeT++/MiXiM simulations, we demonstrated that MTE-EHWSN approach enhances the WSN performance compared to other current energy harvesting administration approach such as EH2M by incorporating these two approaches into the sender-initiated MAC mode of communication.","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":"130617164","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/NTIC55069.2022.10100457
Abdelwahhab Boudjelal, Bilal Attallah, A. Elmoataz, Y. Chahir, Abdelhak Goudjil
In this paper, we study the algorithm of MAP-OSEM for PET reconstruction which is a well known iterative algorithm. It is desired to use a spatial regularization technique can improve the quality of reconstructed images and help to provide accurate diagnosis. The MAP-OSEM algorithm is a powerful image reconstruction algorithm that has been used in a variety of medical imaging applications, including PET reconstruction. In this work, we use the regularized MAP-OSEM algorithm that incorporates a regularization term into the objective function. The regularization term is used to promote smoothness in the reconstructed image, and it is typically chosen based on prior knowledge about the image. The MAP-OSEM algorithm is a gradient ascent optimization method which seeks to maximize the posterior distribution of an image by taking into account a Poisson-Gaussian noise model for the likelihood and a uniform prior to reduce bias. The objective function is maximized by the gradient ascent optimization method.
{"title":"The Effect of Regularization on the MAP-OSEM Algorithm for PET Reconstruction","authors":"Abdelwahhab Boudjelal, Bilal Attallah, A. Elmoataz, Y. Chahir, Abdelhak Goudjil","doi":"10.1109/NTIC55069.2022.10100457","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100457","url":null,"abstract":"In this paper, we study the algorithm of MAP-OSEM for PET reconstruction which is a well known iterative algorithm. It is desired to use a spatial regularization technique can improve the quality of reconstructed images and help to provide accurate diagnosis. The MAP-OSEM algorithm is a powerful image reconstruction algorithm that has been used in a variety of medical imaging applications, including PET reconstruction. In this work, we use the regularized MAP-OSEM algorithm that incorporates a regularization term into the objective function. The regularization term is used to promote smoothness in the reconstructed image, and it is typically chosen based on prior knowledge about the image. The MAP-OSEM algorithm is a gradient ascent optimization method which seeks to maximize the posterior distribution of an image by taking into account a Poisson-Gaussian noise model for the likelihood and a uniform prior to reduce bias. The objective function is maximized by the gradient ascent optimization method.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"100 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":"128876472","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/NTIC55069.2022.10100521
Nour El Houda Boulkrinat, N. Benblidia, A. Meziane
This paper addresses the issue of interest evolution based on social activities. The evolution of social interests emphasizes the use of various types of information and relationships between users. It’s based on social interactions (share, comment, like, etc.) and on resources (text, images, videos, etc.). Although evolution techniques have undergone distinct developments in recent years, they still have limitations, particularly when the user is inactive and the data is sparse. The evolution and detection of the passive user interests are challenging because this kind of user does not or rarely interacts in social networks and has few or no friends. In this paper, we present a novel evolutionary approach to detect the passive user interests based on the research history and resources clicked, taking into account the temporal factors of the information. We applied resource indexing, we elicited the top interests by calculating the weight of each term in queries, and we used a similarity function to further enrich the interests of passive users. An evolution system based on this approach has been developed, and experiments have been conducted using the Facebook social network. The evaluation results demonstrated that the proposed approach returns positive results and solves the cold start problem.
{"title":"Evolution of passive user interests by analyzing Social Network activities","authors":"Nour El Houda Boulkrinat, N. Benblidia, A. Meziane","doi":"10.1109/NTIC55069.2022.10100521","DOIUrl":"https://doi.org/10.1109/NTIC55069.2022.10100521","url":null,"abstract":"This paper addresses the issue of interest evolution based on social activities. The evolution of social interests emphasizes the use of various types of information and relationships between users. It’s based on social interactions (share, comment, like, etc.) and on resources (text, images, videos, etc.). Although evolution techniques have undergone distinct developments in recent years, they still have limitations, particularly when the user is inactive and the data is sparse. The evolution and detection of the passive user interests are challenging because this kind of user does not or rarely interacts in social networks and has few or no friends. In this paper, we present a novel evolutionary approach to detect the passive user interests based on the research history and resources clicked, taking into account the temporal factors of the information. We applied resource indexing, we elicited the top interests by calculating the weight of each term in queries, and we used a similarity function to further enrich the interests of passive users. An evolution system based on this approach has been developed, and experiments have been conducted using the Facebook social network. The evaluation results demonstrated that the proposed approach returns positive results and solves the cold start problem.","PeriodicalId":403927,"journal":{"name":"2022 2nd International Conference on New Technologies of Information and Communication (NTIC)","volume":"14 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":"115301338","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：