Pub Date : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715185
Ouissal Sadouni, Abdelhafid Zitouni
The advent of the internet has strongly influenced the way we learn, by introducing e-learning systems as an aid to traditional education, sometimes even as the sole means of learning. An online learner can generate a multitude of learning analytics indicators that can be used to improve these learning systems using artificial intelligence algorithms. Nevertheless, the use of a large number of learning indicators causes overfitting that degrades the performance of machine learning algorithms. Therefore, in this paper, we will focus on the implementation of dynamic optimization of the number of learning indicators, based on the type of the considered task. This optimization will be done through two different machine learning algorithms: Naive Bayes Classifier for the classification tasks and Regression Decision Trees for the regression task. The adaptation of these two algorithms with various scenarios provides convincing results that demonstrate a significant improvement in the predictions made.
{"title":"Task-based Learning Analytics Indicators Selection Using Naive Bayes Classifier And Regression Decision Trees","authors":"Ouissal Sadouni, Abdelhafid Zitouni","doi":"10.1109/ICTAACS53298.2021.9715185","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715185","url":null,"abstract":"The advent of the internet has strongly influenced the way we learn, by introducing e-learning systems as an aid to traditional education, sometimes even as the sole means of learning. An online learner can generate a multitude of learning analytics indicators that can be used to improve these learning systems using artificial intelligence algorithms. Nevertheless, the use of a large number of learning indicators causes overfitting that degrades the performance of machine learning algorithms. Therefore, in this paper, we will focus on the implementation of dynamic optimization of the number of learning indicators, based on the type of the considered task. This optimization will be done through two different machine learning algorithms: Naive Bayes Classifier for the classification tasks and Regression Decision Trees for the regression task. The adaptation of these two algorithms with various scenarios provides convincing results that demonstrate a significant improvement in the predictions made.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122084172","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 : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715190
Mohammed Nassim Lacheheub, Aymen Bakhbakh, Ahmed Nabih Benlabiod, R. Maamri, M. Boutarfa, Salheddine Sadouni
In recent years, cloud computing has seen a phenomenal explosion in services use. Moreover, these ones can be used in any area such as service composition, business process construction, creating a complex service…Etc. In our work, we focused on the cloud services use for business process construction. But the problems that arise are firstly, the multitude of similar services for a business process construction and secondly, the divergence in the resource consumption of these services. In this paper we have chosen to use a formal model to describe, verify business process construction by using cloud services and to calculate for each business process activity the resource consumption of all similar services, in order to select the best services (which have a low resource consumption) for the business process construction. In such a way that selection of cloud services is done on the basis of a formal model to prove the correct execution and to achieve formal verification of the business process with a resources representation. In other words, it enables the selection of best similar cloud services based on re-source consumption and this is done through a transformation from a business process model to a formal model.
{"title":"A Transformation Approach Combining BPMN and Petri Net to Verify Business Processes Construction in terms of Resource Consumption using Cloud Services","authors":"Mohammed Nassim Lacheheub, Aymen Bakhbakh, Ahmed Nabih Benlabiod, R. Maamri, M. Boutarfa, Salheddine Sadouni","doi":"10.1109/ICTAACS53298.2021.9715190","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715190","url":null,"abstract":"In recent years, cloud computing has seen a phenomenal explosion in services use. Moreover, these ones can be used in any area such as service composition, business process construction, creating a complex service…Etc. In our work, we focused on the cloud services use for business process construction. But the problems that arise are firstly, the multitude of similar services for a business process construction and secondly, the divergence in the resource consumption of these services. In this paper we have chosen to use a formal model to describe, verify business process construction by using cloud services and to calculate for each business process activity the resource consumption of all similar services, in order to select the best services (which have a low resource consumption) for the business process construction. In such a way that selection of cloud services is done on the basis of a formal model to prove the correct execution and to achieve formal verification of the business process with a resources representation. In other words, it enables the selection of best similar cloud services based on re-source consumption and this is done through a transformation from a business process model to a formal model.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116754537","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 : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715182
Adel Saadi
Belief-Desire-Intention (BDI) is a well known model for designing agents behaving intelligently and in a flexible manner. The concept of goal is an important BDI agent’s component that plays a central role in this flexibility of behavior. Besides, as the concept of motive is another relevant one for the agent’s behavioral flexibility and as the BDI model originally does not include motives, some extensions of the BDI agent, with a new component for expressing the motive, have been proposed. In a recent work, it has been shown that the concept of motive can be specified via the goal concept, so it is not required to add a new component to express a motive. In this paper, we further explore this idea at the architectural level of a BDI agent. In particular, we look at how the added values of incorporating motives in BDI agents, can be obtained via the goal concept.
{"title":"A Further Exploration of the Natural Incorporation of Motives in BDI Architectures","authors":"Adel Saadi","doi":"10.1109/ICTAACS53298.2021.9715182","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715182","url":null,"abstract":"Belief-Desire-Intention (BDI) is a well known model for designing agents behaving intelligently and in a flexible manner. The concept of goal is an important BDI agent’s component that plays a central role in this flexibility of behavior. Besides, as the concept of motive is another relevant one for the agent’s behavioral flexibility and as the BDI model originally does not include motives, some extensions of the BDI agent, with a new component for expressing the motive, have been proposed. In a recent work, it has been shown that the concept of motive can be specified via the goal concept, so it is not required to add a new component to express a motive. In this paper, we further explore this idea at the architectural level of a BDI agent. In particular, we look at how the added values of incorporating motives in BDI agents, can be obtained via the goal concept.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134519359","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}
Real-time object tracking is still a critical challenge in artificial vision research. In such a mission, it is essential to assign a unique identifier or label to each tracked object, regardless of the area, time of appearance, or detector camera, to distinguish it from other objects and to conserve as much information as possible about the tracked objects with the same label. This conservation is a significant issue, especially in largescale video surveillance systems, due to the linear complexity of the sequential search to find the labels of detected objects in data increasing with time, the number of tracked objects, and the number of active cameras in the network. To overcome this problem, we propose a new automatic multi-object labeling solution for efficient real-time tracking based on an indexing mechanism. This mechanism organizes the massive metadata of objects extracted during tracking into a tree-based indexing structure. The main advantage of this structure in a tracking system is its logarithmic search complexity, which implicitly reduces the search response time, and its quality of research results, which ensure coherent labeling of the tracked objects. This paper discusses the effectiveness of the label search algorithms and the tracking quality compared to other recent tracking systems on real-world datasets. Experimental results showed good performance in reducing search time and improving tracking quality.
{"title":"Automatic labeling of tracked objects based on an indexing mechanism","authors":"Imane Allele, Ala-Eddine Benrazek, Zineddine Kouahla, Brahim Farou, Hamid Seridi, M. Kurulay","doi":"10.1109/ICTAACS53298.2021.9715189","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715189","url":null,"abstract":"Real-time object tracking is still a critical challenge in artificial vision research. In such a mission, it is essential to assign a unique identifier or label to each tracked object, regardless of the area, time of appearance, or detector camera, to distinguish it from other objects and to conserve as much information as possible about the tracked objects with the same label. This conservation is a significant issue, especially in largescale video surveillance systems, due to the linear complexity of the sequential search to find the labels of detected objects in data increasing with time, the number of tracked objects, and the number of active cameras in the network. To overcome this problem, we propose a new automatic multi-object labeling solution for efficient real-time tracking based on an indexing mechanism. This mechanism organizes the massive metadata of objects extracted during tracking into a tree-based indexing structure. The main advantage of this structure in a tracking system is its logarithmic search complexity, which implicitly reduces the search response time, and its quality of research results, which ensure coherent labeling of the tracked objects. This paper discusses the effectiveness of the label search algorithms and the tracking quality compared to other recent tracking systems on real-world datasets. Experimental results showed good performance in reducing search time and improving tracking quality.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131819130","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 : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715218
Ali Abdelkrim, Abdelkrim Bouramoul, Imene Zenbout
Drug development represents the most challenging phase to pharmaceutical industry, as it is extremely expensive and time consumable. But, under increasing demand to produce safe and innovative drugs faster and at a lower cost, the focus has switched to enhance the lead identification and the lead optimization at the early discovery phase by incorporating insilico recent technologies. Among recent technologies, Artificial Intelligence (AI) has been introduced as a powerful solution to the adressed issues, and it results to speed up significantly the development process. Where, machine-learning played a key role in producing fresh drug candidates. In this work, we walk through the fundamentals of machine learning algorithms, review and discuss their application and current issues in drug development.
{"title":"Machine Learning Methods In Drug Discovery: A Selective Review","authors":"Ali Abdelkrim, Abdelkrim Bouramoul, Imene Zenbout","doi":"10.1109/ICTAACS53298.2021.9715218","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715218","url":null,"abstract":"Drug development represents the most challenging phase to pharmaceutical industry, as it is extremely expensive and time consumable. But, under increasing demand to produce safe and innovative drugs faster and at a lower cost, the focus has switched to enhance the lead identification and the lead optimization at the early discovery phase by incorporating insilico recent technologies. Among recent technologies, Artificial Intelligence (AI) has been introduced as a powerful solution to the adressed issues, and it results to speed up significantly the development process. Where, machine-learning played a key role in producing fresh drug candidates. In this work, we walk through the fundamentals of machine learning algorithms, review and discuss their application and current issues in drug development.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"53 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132867823","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 : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715180
Samira Telghamti, Lakhdhar Derdouri
Privacy and data security are critical aspects in databases, mainly when the latter are publically accessed such in social networks. Furthermore, for advanced databases, such as NoSQL ones, security models and security meta-data must be integrated to the business specification and data. In the literature, the proposed models for NoSQL databases can be considered as static, in the sense where the privileges for a given user are predefined and remain unchanged during job sessions. In this paper, we propose a novel model for NoSQL database access control that we aim that it will be dynamic. To be able to design such model, we have considered the Trust concept to compute the reputation degree for a given user that plays a given role.
{"title":"Towards a Trust-based Model for Access Control for Graph-Oriented Databases","authors":"Samira Telghamti, Lakhdhar Derdouri","doi":"10.1109/ICTAACS53298.2021.9715180","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715180","url":null,"abstract":"Privacy and data security are critical aspects in databases, mainly when the latter are publically accessed such in social networks. Furthermore, for advanced databases, such as NoSQL ones, security models and security meta-data must be integrated to the business specification and data. In the literature, the proposed models for NoSQL databases can be considered as static, in the sense where the privileges for a given user are predefined and remain unchanged during job sessions. In this paper, we propose a novel model for NoSQL database access control that we aim that it will be dynamic. To be able to design such model, we have considered the Trust concept to compute the reputation degree for a given user that plays a given role.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115073962","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 : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715209
Abdenacer Nafir, S. Mazouzi, S. Chikhi
Distributed Denial of Service (DDoS) are known as fearsome and hard to detect and to deal with. We introduce in this paper a collective technique for DDoS detection in wide network areas. Entropy of the distances traveled by the packets is calculated and exchanged between routers in order to locally decide if there is an ongoing DDoS or not. Contrary to most of the similar methods in the literature, that are based on the entropy of source addresses, we have opted for the entropy of the distances traveled by the packets in order to prevent IP spoofing techniques. Collective detection consists in combining decisions within local neighborhoods. Experiments using the platform OMNet++ show the potential of the new technique for efficient collective detection of DDoS attacks.
{"title":"Collective DDoS Detection by an Entropy-based Method","authors":"Abdenacer Nafir, S. Mazouzi, S. Chikhi","doi":"10.1109/ICTAACS53298.2021.9715209","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715209","url":null,"abstract":"Distributed Denial of Service (DDoS) are known as fearsome and hard to detect and to deal with. We introduce in this paper a collective technique for DDoS detection in wide network areas. Entropy of the distances traveled by the packets is calculated and exchanged between routers in order to locally decide if there is an ongoing DDoS or not. Contrary to most of the similar methods in the literature, that are based on the entropy of source addresses, we have opted for the entropy of the distances traveled by the packets in order to prevent IP spoofing techniques. Collective detection consists in combining decisions within local neighborhoods. Experiments using the platform OMNet++ show the potential of the new technique for efficient collective detection of DDoS attacks.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125490857","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 : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715228
Selma Ouareth, Soufiane Boulehouache, S. Mazouzi
To ensure self-adaptation, the Manager Subsystem must include Control Loop (CL). However, create and perform a single CL able to achieve multi-attributes self-adaptation is difficult. So, the system must include many CLs to ensure separation of concerns. The major challenge is that how multiple CL entities can interact with each other to coordinate the system management? On the other hand, how concerns can separate among different CLs? In this paper, we propose HCLs (Hierarchical Control Loops), a pattern for the manager sub-system, with benefits from the leveraging of the hierarchical and dynamic component model, Fractal. The proposed approach allows managing the complexity of self-adaptation by separating concerns using Fractal component model in the form of an hierarchy of MAPE loops. Furthermore, we distinguish three types of adaptations as following: Local Adaptation, Regional Adaptation, and Superior Adaptation in order to achieve multi-level adapting.
{"title":"An Approach for Composing Multiple Control Loops Hierarchically","authors":"Selma Ouareth, Soufiane Boulehouache, S. Mazouzi","doi":"10.1109/ICTAACS53298.2021.9715228","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715228","url":null,"abstract":"To ensure self-adaptation, the Manager Subsystem must include Control Loop (CL). However, create and perform a single CL able to achieve multi-attributes self-adaptation is difficult. So, the system must include many CLs to ensure separation of concerns. The major challenge is that how multiple CL entities can interact with each other to coordinate the system management? On the other hand, how concerns can separate among different CLs? In this paper, we propose HCLs (Hierarchical Control Loops), a pattern for the manager sub-system, with benefits from the leveraging of the hierarchical and dynamic component model, Fractal. The proposed approach allows managing the complexity of self-adaptation by separating concerns using Fractal component model in the form of an hierarchy of MAPE loops. Furthermore, we distinguish three types of adaptations as following: Local Adaptation, Regional Adaptation, and Superior Adaptation in order to achieve multi-level adapting.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"182 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124589176","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 : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715191
Farida Ali Guechi, R. Maamri
Make search over encrypted data with encrypted query, to find those who correspond to a keyword or keywords; is called searchable encryption. Our proposed searchable encryption approach is: precise, fast, secure and support access control. These advantages come from the index structure proposed in addition to multi-multi-cloud used. The goal of this paper is an implementation and simulation of our approach. Results indicate it’s efficient in multi-cloudIoT.
{"title":"Searchable encryption for multi-cloudIoT simulation","authors":"Farida Ali Guechi, R. Maamri","doi":"10.1109/ICTAACS53298.2021.9715191","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715191","url":null,"abstract":"Make search over encrypted data with encrypted query, to find those who correspond to a keyword or keywords; is called searchable encryption. Our proposed searchable encryption approach is: precise, fast, secure and support access control. These advantages come from the index structure proposed in addition to multi-multi-cloud used. The goal of this paper is an implementation and simulation of our approach. Results indicate it’s efficient in multi-cloudIoT.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"4 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123895933","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 : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715211
Khadidja Makhlouf, Zohra Hmidi, L. Kahloul, Saber Benhrazallah, Tarek Ababsa
Artificial Intelligence (AI) knows a high exploitation in medical computing to enhance patient care by accelerating processes and increasing accuracy, thus providing improvements healthcare in general. Temperature is an important health factor that has to be regularly monitored and even early detected in some situations. Thus, this paper aims to invest in the advances in Internet of Things (IoT) and in Machine Learning (ML) techniques to develop a monitoring system that is able to forecast body temperature. The proposed solution consists in: i) designing and implementing a wearable device using a temperature sensor and a micro-controller, to monitor body temperature permanently, then ii) those monitored measurements are collected and stored as a time-series dataset in a cloud storage server accessible by doctors, and iii) finally the time-series dataset is used by machine learning forecasting techniques to get early body temperature values for the next hours.
{"title":"On the Forecasting of Body Temperature using IoT and Machine Learning Techniques","authors":"Khadidja Makhlouf, Zohra Hmidi, L. Kahloul, Saber Benhrazallah, Tarek Ababsa","doi":"10.1109/ICTAACS53298.2021.9715211","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715211","url":null,"abstract":"Artificial Intelligence (AI) knows a high exploitation in medical computing to enhance patient care by accelerating processes and increasing accuracy, thus providing improvements healthcare in general. Temperature is an important health factor that has to be regularly monitored and even early detected in some situations. Thus, this paper aims to invest in the advances in Internet of Things (IoT) and in Machine Learning (ML) techniques to develop a monitoring system that is able to forecast body temperature. The proposed solution consists in: i) designing and implementing a wearable device using a temperature sensor and a micro-controller, to monitor body temperature permanently, then ii) those monitored measurements are collected and stored as a time-series dataset in a cloud storage server accessible by doctors, and iii) finally the time-series dataset is used by machine learning forecasting techniques to get early body temperature values for the next hours.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"03 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130241354","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：