International Journal of Hybrid Intelligent Systems
Efficient and accurate early prediction of Alzheimer’s disease (AD) based on the neuroimaging dat... more Efficient and accurate early prediction of Alzheimer’s disease (AD) based on the neuroimaging data has attracted interest from many researchers to prevent its progression. Deep learning networks have demonstrated an optimal ability to analyse large-scale multimodal neuroimaging for AD classification. The most widely used architecture of deep learning is the Convolution neural networks (CNN) that have shown great potential in AD detection. However CNN does not capture long range dependencies within the input image and does not ensure a good global feature extraction. Furthermore, increasing the receptive field of CNN by increasing the kernels sizes can cause a feature granularity loss. Another limitation is that CNN lacks a weighing mechanism of image features; the network doesn’t focus on the relevant features within the image. Recently,vision transformer have shown an outstanding performance over the CNN and overcomes its main limitations. The vision transformer relies on the self-...
2017 IEEE 26th International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE), 2017
Cloud computing represents a new computing approach that allows creating robust and on-demand ser... more Cloud computing represents a new computing approach that allows creating robust and on-demand services controlled by means of Service Level Agreements (SLA). These documents are generated following a process of negotiation during which the client chooses a subset of clauses among choices predefined by the provider on a "take it or leave it" basis. However, the heterogeneity between client requests and provider offers may result in inappropriate SLA. In addition, the cloud service context may change over the time which causes a client requirements adjustment and therefore, the SLA remains unsatisfactory. In this paper, we propose a cloud SLA negotiation and re-negotiation approach that integrate a semantic mapping between client requests and provider offers with the aim of generating a suitable SLA document. Moreover, our approach includes a context-aware system to adapt the SLA throughout reasoning techniques and automatically ensure the re-negotiation. A prototype implementation demonstrates the feasibility and the efficiency of our approach.
2019 7th International conference on ICT & Accessibility (ICTA), 2019
The adoption of the Internet of Things (IoT) in the medical sector improves health care services ... more The adoption of the Internet of Things (IoT) in the medical sector improves health care services and guarantees continuous and efficient monitoring of patients with chronic disease. Accordingly, heterogeneous health data (medical devices and medical records) is obtained and requires to be efficiently managed and diverse risk factors should be smartly considered in order to predict and prevent complex and dangerous events. The modeling and processing of this kind of events present an emerging challenge that necessitates to be addressed. In this context, we aim to propose a semantic-driven complex event processing approach for Cardiovascular Disease (CVD) prevention for diabetic patients. Particularly, we focus on the semantic modeling of medical events; Then, we propose diverse rules for processing purposes.
Service Level Agreements (SLA) represents the principal means to control the Quality of Service (... more Service Level Agreements (SLA) represents the principal means to control the Quality of Service (QoS). In cloud computing, various advanced SLA strategies are used; some techniques among others try to avoid the SLA violations. Taking into account the cloud consumer contextual parameters is a promising way to predict and avoid costly SLA violations. Therefore, in this paper, we propose a context-aware system for the SLA in order to guarantee the QoS. We create a contextual ontology to introduce the semantic meaning of the cloud consumer contextual parameters. In addition, using reasoning techniques, we (1) predict SLA violations and we (2) choose and apply the corrective actions in autonomous manner. This allows getting a proactive adjustment of the cloud service execution and respecting the SLA parameters.
The rapid adoption of Electronic Health Record (EHR) systems requires advanced enactment strategi... more The rapid adoption of Electronic Health Record (EHR) systems requires advanced enactment strategies for analyzing medical reports. Indeed, the information presented in these reports is difficult to access and it is onerous to analyze it by medical decision support systems. Medical reports characterize full descriptions of the patient diagnosis process. They bring together information about exam steps such as applied techniques, results, synthesis and medical conclusions. In this paper, we propose a medical report modeling and analyzing approach that aims to analyze medical reports for Magnetic Resonance Imaging (MRI) exams. Ontological model is dedicated to represent information from radiological reports in order to make them comprehensible and machine readable. Moreover, reasoning techniques are used to treat a large amount of clinical data. This provides an analyzing system allowing user to be informed about the evolution of the patient state. The proposed system was successfully applied to a set of Hepatocellular Carcinoma (HCC) medical reports from University Hospital of Clermont-Ferrand (CHU), France.
2019 IEEE 12th International Conference on Cloud Computing (CLOUD), 2019
Several DevOps tools have emerged to orchestrate cloud resources. However, inherent heterogeneity... more Several DevOps tools have emerged to orchestrate cloud resources. However, inherent heterogeneity and complex implementation within these tools make it hard for DevOps users to design required resource-related artifacts. Currently, the defacto standard for cloud resource modeling and orchestration is TOSCA. Nonetheless, TOSCA is usually bound to TOSCA-compliant orchestration tools. Moreover, the actual integration between TOSCA and DevOps tools is still performed using costly coding and in ad-hoc manner. To resolve this, we believe that mapping and translation mechanisms between TOSCA and DevOps tools should be provided. In this paper, we propose a new model-driven approach for cloud resource orchestration. Our approach (i) adopts TOSCA to design resource-related artifacts regardless of a specific DevOps tool; (ii) enables a new model-driven translation technique that serves to translate the designed artifacts using TOSCA into DevOps specific artifacts and (iii) provides Connectors that intend to establish the bridge between DevOps-specific artifacts and the DevOps tools. Our approach provides a powerful enhancement to DevOps productivity and reusability by assisting toward a seamless integration between TOSCA and DevOps tools.
Advances in Intelligent Systems and Computing, 2018
As the main way for knowledge representation for the purpose of completely machine understanding,... more As the main way for knowledge representation for the purpose of completely machine understanding, ontologies are widely used in different application domains. This full machine understanding makes them harder to be easily understood by a human. This necessitates the need to develop ontology visualization tools, which results in the existence of a large number of approaches and visualization tools. Along with this development direction, the number of published research papers related to ontology visualization is largely increasing. To this end, in this paper, we introduce a systemic review on different directions related to ontology visualization. In particular, we start by describing different application domains that make use of ontology visualization. Then, we propose a generic visualization pipeline that incorporates main steps in ontology visualization that could be later used as main criteria during comparing and discussing different visualization tools. By this review, we aim to introduce a general visualization pipeline that is useful when comparing ontology visualization tools and when developing a new visualization technique. Finally, the paper moves into the description of future trends and research issues that still need to be addressed.
International Journal of Hybrid Intelligent Systems
Efficient and accurate early prediction of Alzheimer’s disease (AD) based on the neuroimaging dat... more Efficient and accurate early prediction of Alzheimer’s disease (AD) based on the neuroimaging data has attracted interest from many researchers to prevent its progression. Deep learning networks have demonstrated an optimal ability to analyse large-scale multimodal neuroimaging for AD classification. The most widely used architecture of deep learning is the Convolution neural networks (CNN) that have shown great potential in AD detection. However CNN does not capture long range dependencies within the input image and does not ensure a good global feature extraction. Furthermore, increasing the receptive field of CNN by increasing the kernels sizes can cause a feature granularity loss. Another limitation is that CNN lacks a weighing mechanism of image features; the network doesn’t focus on the relevant features within the image. Recently,vision transformer have shown an outstanding performance over the CNN and overcomes its main limitations. The vision transformer relies on the self-...
2017 IEEE 26th International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE), 2017
Cloud computing represents a new computing approach that allows creating robust and on-demand ser... more Cloud computing represents a new computing approach that allows creating robust and on-demand services controlled by means of Service Level Agreements (SLA). These documents are generated following a process of negotiation during which the client chooses a subset of clauses among choices predefined by the provider on a "take it or leave it" basis. However, the heterogeneity between client requests and provider offers may result in inappropriate SLA. In addition, the cloud service context may change over the time which causes a client requirements adjustment and therefore, the SLA remains unsatisfactory. In this paper, we propose a cloud SLA negotiation and re-negotiation approach that integrate a semantic mapping between client requests and provider offers with the aim of generating a suitable SLA document. Moreover, our approach includes a context-aware system to adapt the SLA throughout reasoning techniques and automatically ensure the re-negotiation. A prototype implementation demonstrates the feasibility and the efficiency of our approach.
2019 7th International conference on ICT & Accessibility (ICTA), 2019
The adoption of the Internet of Things (IoT) in the medical sector improves health care services ... more The adoption of the Internet of Things (IoT) in the medical sector improves health care services and guarantees continuous and efficient monitoring of patients with chronic disease. Accordingly, heterogeneous health data (medical devices and medical records) is obtained and requires to be efficiently managed and diverse risk factors should be smartly considered in order to predict and prevent complex and dangerous events. The modeling and processing of this kind of events present an emerging challenge that necessitates to be addressed. In this context, we aim to propose a semantic-driven complex event processing approach for Cardiovascular Disease (CVD) prevention for diabetic patients. Particularly, we focus on the semantic modeling of medical events; Then, we propose diverse rules for processing purposes.
Service Level Agreements (SLA) represents the principal means to control the Quality of Service (... more Service Level Agreements (SLA) represents the principal means to control the Quality of Service (QoS). In cloud computing, various advanced SLA strategies are used; some techniques among others try to avoid the SLA violations. Taking into account the cloud consumer contextual parameters is a promising way to predict and avoid costly SLA violations. Therefore, in this paper, we propose a context-aware system for the SLA in order to guarantee the QoS. We create a contextual ontology to introduce the semantic meaning of the cloud consumer contextual parameters. In addition, using reasoning techniques, we (1) predict SLA violations and we (2) choose and apply the corrective actions in autonomous manner. This allows getting a proactive adjustment of the cloud service execution and respecting the SLA parameters.
The rapid adoption of Electronic Health Record (EHR) systems requires advanced enactment strategi... more The rapid adoption of Electronic Health Record (EHR) systems requires advanced enactment strategies for analyzing medical reports. Indeed, the information presented in these reports is difficult to access and it is onerous to analyze it by medical decision support systems. Medical reports characterize full descriptions of the patient diagnosis process. They bring together information about exam steps such as applied techniques, results, synthesis and medical conclusions. In this paper, we propose a medical report modeling and analyzing approach that aims to analyze medical reports for Magnetic Resonance Imaging (MRI) exams. Ontological model is dedicated to represent information from radiological reports in order to make them comprehensible and machine readable. Moreover, reasoning techniques are used to treat a large amount of clinical data. This provides an analyzing system allowing user to be informed about the evolution of the patient state. The proposed system was successfully applied to a set of Hepatocellular Carcinoma (HCC) medical reports from University Hospital of Clermont-Ferrand (CHU), France.
2019 IEEE 12th International Conference on Cloud Computing (CLOUD), 2019
Several DevOps tools have emerged to orchestrate cloud resources. However, inherent heterogeneity... more Several DevOps tools have emerged to orchestrate cloud resources. However, inherent heterogeneity and complex implementation within these tools make it hard for DevOps users to design required resource-related artifacts. Currently, the defacto standard for cloud resource modeling and orchestration is TOSCA. Nonetheless, TOSCA is usually bound to TOSCA-compliant orchestration tools. Moreover, the actual integration between TOSCA and DevOps tools is still performed using costly coding and in ad-hoc manner. To resolve this, we believe that mapping and translation mechanisms between TOSCA and DevOps tools should be provided. In this paper, we propose a new model-driven approach for cloud resource orchestration. Our approach (i) adopts TOSCA to design resource-related artifacts regardless of a specific DevOps tool; (ii) enables a new model-driven translation technique that serves to translate the designed artifacts using TOSCA into DevOps specific artifacts and (iii) provides Connectors that intend to establish the bridge between DevOps-specific artifacts and the DevOps tools. Our approach provides a powerful enhancement to DevOps productivity and reusability by assisting toward a seamless integration between TOSCA and DevOps tools.
Advances in Intelligent Systems and Computing, 2018
As the main way for knowledge representation for the purpose of completely machine understanding,... more As the main way for knowledge representation for the purpose of completely machine understanding, ontologies are widely used in different application domains. This full machine understanding makes them harder to be easily understood by a human. This necessitates the need to develop ontology visualization tools, which results in the existence of a large number of approaches and visualization tools. Along with this development direction, the number of published research papers related to ontology visualization is largely increasing. To this end, in this paper, we introduce a systemic review on different directions related to ontology visualization. In particular, we start by describing different application domains that make use of ontology visualization. Then, we propose a generic visualization pipeline that incorporates main steps in ontology visualization that could be later used as main criteria during comparing and discussing different visualization tools. By this review, we aim to introduce a general visualization pipeline that is useful when comparing ontology visualization tools and when developing a new visualization technique. Finally, the paper moves into the description of future trends and research issues that still need to be addressed.
Uploads
Papers by Faiez Gargouri