Pub Date : 2022-03-22DOI: 10.1109/IC_ASET53395.2022.9765908
Mokhtar Abbassi, Abdelkarim Aouiti, F. Bacha
In this paper, a cascade control technique implied for a three-phase grid-tied photovoltaic system, has been proposed. This last comprises of a PV generator, a DC/DC converter, an inverter and an electrical grid. In this structure, a new control strategy using the simplified sliding mode technique is developed for the inverter. While the boost converter control strategy has two objectives, namely, the control of maximum power by injecting the power into the grid employing the Perturb and Observe (P&O) technique and for the purpose of controlling the chopper at its maximum efficiency, the switching frequency is generated by estimating voltages and currents from the DC/AC converter. The proposed control adjusts well to the cascade control strategy. Simulations were performed thanks to Matlab / Simulink and that in aim to validate the robustness of the employed techniques for different operating states, such as the irradiation and the temperature variation.
{"title":"Variable Frequency Control of MPTT using Two-Stage Grid Converters -Integrated Photovoltaic System","authors":"Mokhtar Abbassi, Abdelkarim Aouiti, F. Bacha","doi":"10.1109/IC_ASET53395.2022.9765908","DOIUrl":"https://doi.org/10.1109/IC_ASET53395.2022.9765908","url":null,"abstract":"In this paper, a cascade control technique implied for a three-phase grid-tied photovoltaic system, has been proposed. This last comprises of a PV generator, a DC/DC converter, an inverter and an electrical grid. In this structure, a new control strategy using the simplified sliding mode technique is developed for the inverter. While the boost converter control strategy has two objectives, namely, the control of maximum power by injecting the power into the grid employing the Perturb and Observe (P&O) technique and for the purpose of controlling the chopper at its maximum efficiency, the switching frequency is generated by estimating voltages and currents from the DC/AC converter. The proposed control adjusts well to the cascade control strategy. Simulations were performed thanks to Matlab / Simulink and that in aim to validate the robustness of the employed techniques for different operating states, such as the irradiation and the temperature variation.","PeriodicalId":6874,"journal":{"name":"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)","volume":"92 1","pages":"433-438"},"PeriodicalIF":0.0,"publicationDate":"2022-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83818341","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 : 2022-03-22DOI: 10.1109/IC_ASET53395.2022.9765936
Helmi Abrougui, Ayoub Neffati, S. Nejim
This paper proposes an approach for modeling and controlling a coaxial helicopter. An autopilot is designed using sliding mode control. It consists of a low-level controller for attitude stabilization and a high-level controller for path following control. Speed controller is also performed using the helicopter dynamics in pitch motion. Simulations are carried out to show the behavior of the overall system and the effectiveness of the designed autopilot.
{"title":"Modeling and Path Following Control of a Coaxial Helicopter","authors":"Helmi Abrougui, Ayoub Neffati, S. Nejim","doi":"10.1109/IC_ASET53395.2022.9765936","DOIUrl":"https://doi.org/10.1109/IC_ASET53395.2022.9765936","url":null,"abstract":"This paper proposes an approach for modeling and controlling a coaxial helicopter. An autopilot is designed using sliding mode control. It consists of a low-level controller for attitude stabilization and a high-level controller for path following control. Speed controller is also performed using the helicopter dynamics in pitch motion. Simulations are carried out to show the behavior of the overall system and the effectiveness of the designed autopilot.","PeriodicalId":6874,"journal":{"name":"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)","volume":"94 1","pages":"369-374"},"PeriodicalIF":0.0,"publicationDate":"2022-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74416075","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 : 2022-03-22DOI: 10.1109/IC_ASET53395.2022.9765888
Imen Azzouz, Inès Hammami, Kais Brik, F. B. Ammar
Multi-source photovoltaic system structures, play an important role in photovoltaic installations especially in isolated sites. However, requirements in terms of performance, power availability and lifetime have to meet the consumption requirements for their integration. In this context, authors propose a consistent approach to improve the choice of an adequate electrical topology of a multi-source photovoltaic system located in an isolated site. This approach is essentially performed by applying a multi-criteria analysis based on a comparison study including four criteria. Four different multi-source photovoltaic system structures are compared according to their life-time, power availability, installation complexity and cost. The comparison process is performed by applying the multi-criteria decision method PROMETHEE II.
{"title":"Multi criteria analysis of multi-sources photovoltaic electrical structures in isolated sites","authors":"Imen Azzouz, Inès Hammami, Kais Brik, F. B. Ammar","doi":"10.1109/IC_ASET53395.2022.9765888","DOIUrl":"https://doi.org/10.1109/IC_ASET53395.2022.9765888","url":null,"abstract":"Multi-source photovoltaic system structures, play an important role in photovoltaic installations especially in isolated sites. However, requirements in terms of performance, power availability and lifetime have to meet the consumption requirements for their integration. In this context, authors propose a consistent approach to improve the choice of an adequate electrical topology of a multi-source photovoltaic system located in an isolated site. This approach is essentially performed by applying a multi-criteria analysis based on a comparison study including four criteria. Four different multi-source photovoltaic system structures are compared according to their life-time, power availability, installation complexity and cost. The comparison process is performed by applying the multi-criteria decision method PROMETHEE II.","PeriodicalId":6874,"journal":{"name":"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)","volume":"73 1","pages":"345-350"},"PeriodicalIF":0.0,"publicationDate":"2022-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83211623","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 : 2022-03-22DOI: 10.1109/IC_ASET53395.2022.9765881
Abdessami Soyed, Abdelkarim Aouiti, O. Hasnaoui, F. Bacha
This paper proposes a fuzzy logic direct torque control strategy to control the speed of the induction motor (IM) which is fed by an indirect matrix converter (IMC). For the matrix converter rectifier stage, a space vector modulation (SVM) technique is adopted; moreover, for the matrix converter inverter stage, the technique fuzzy logic direct torque control (FL-DTC) is used. The torque reference is synthesized from the difference in speed (motor speed and reference speed) using a PI controller. The performance of the proposed drive system is evaluated by numerical simulation using the Matlab/Simulink environment. The simulation results are used to verify the effectiveness of the proposed strategy compared to the analytical results obtained.
{"title":"SVM-FL-DTC Control Induction Motor Drives Fed by Indirect Matrix Converter","authors":"Abdessami Soyed, Abdelkarim Aouiti, O. Hasnaoui, F. Bacha","doi":"10.1109/IC_ASET53395.2022.9765881","DOIUrl":"https://doi.org/10.1109/IC_ASET53395.2022.9765881","url":null,"abstract":"This paper proposes a fuzzy logic direct torque control strategy to control the speed of the induction motor (IM) which is fed by an indirect matrix converter (IMC). For the matrix converter rectifier stage, a space vector modulation (SVM) technique is adopted; moreover, for the matrix converter inverter stage, the technique fuzzy logic direct torque control (FL-DTC) is used. The torque reference is synthesized from the difference in speed (motor speed and reference speed) using a PI controller. The performance of the proposed drive system is evaluated by numerical simulation using the Matlab/Simulink environment. The simulation results are used to verify the effectiveness of the proposed strategy compared to the analytical results obtained.","PeriodicalId":6874,"journal":{"name":"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)","volume":"73 1","pages":"301-306"},"PeriodicalIF":0.0,"publicationDate":"2022-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83211692","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 : 2022-03-22DOI: 10.1109/IC_ASET53395.2022.9765831
Tasnime Hamdeni, Soufiane Gasmi, M. Sayadi, J. Ginoux
A new survival model called the Marshall-Olkin Generalized Defective Gompertz Distribution (MO-GDGD) has been recently developed. We present in this paper some mathematical properties of the model. An exhaustive simulation study is conducted for various values of the parameters of MO-GDGD and different sample sizes. Statistical inference methods were applied for the survival analysis of patients suffering from the neurogenerative pathology Amyotrophic Lateral Sclerosis. The type I right-censorship of the data was taken into account. Interesting results have been obtained.
{"title":"Statistical modeling for the prediction of survival rate in a neurodegenerative disease","authors":"Tasnime Hamdeni, Soufiane Gasmi, M. Sayadi, J. Ginoux","doi":"10.1109/IC_ASET53395.2022.9765831","DOIUrl":"https://doi.org/10.1109/IC_ASET53395.2022.9765831","url":null,"abstract":"A new survival model called the Marshall-Olkin Generalized Defective Gompertz Distribution (MO-GDGD) has been recently developed. We present in this paper some mathematical properties of the model. An exhaustive simulation study is conducted for various values of the parameters of MO-GDGD and different sample sizes. Statistical inference methods were applied for the survival analysis of patients suffering from the neurogenerative pathology Amyotrophic Lateral Sclerosis. The type I right-censorship of the data was taken into account. Interesting results have been obtained.","PeriodicalId":6874,"journal":{"name":"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)","volume":"88 1","pages":"245-249"},"PeriodicalIF":0.0,"publicationDate":"2022-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86593941","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 : 2022-03-22DOI: 10.1109/IC_ASET53395.2022.9765948
Ahmed Abadulla Ashlam, A. Badii, Frederic T. Stahl
The increasing use of Information Technology applications in the distributed environment is increasing security exploits. Information about vulnerabilities is also available on the open web in an unstructured format that developers can take advantage of to fix vulnerabilities in their IT applications. SQL injection (SQLi) attacks are frequently launched with the objective of exfiltration of data typically through targeting the back-end server organisations to compromise their customer databases. There have been a number of high profile attacks against large enterprises in recent years. With the ever-increasing growth of online trading, it is possible to see how SQLi attacks can continue to be one of the leading routes for cyber-attacks in the future, as indicated by findings reported in OWASP. Various machine learning and deep learning algorithms have been applied to detect and prevent these attacks. However, such preventive attempts have not limited the incidence of cyber-attacks and the resulting compromised database as reported by (CVE) repository. In this paper, the potential of using data mining approaches is pursued in order to enhance the efficacy of SQL injection safeguarding measures by reducing the false-positive rates in SQLi detection. The proposed approach uses CountVectorizer to extract features and then apply various supervised machine-learning models to automate the classification of SQLi. The model that returns the highest accuracy has been chosen among available models. Also a new model has been created PALOSDM (Performance analysis and Iterative optimisation of the SQLI Detection Model) for reducing false-positive rate and false-negative rate. The detection rate accuracy has also been improved significantly from a baseline of 94% up to 99%.
{"title":"A Novel Approach Exploiting Machine Learning to Detect SQLi Attacks","authors":"Ahmed Abadulla Ashlam, A. Badii, Frederic T. Stahl","doi":"10.1109/IC_ASET53395.2022.9765948","DOIUrl":"https://doi.org/10.1109/IC_ASET53395.2022.9765948","url":null,"abstract":"The increasing use of Information Technology applications in the distributed environment is increasing security exploits. Information about vulnerabilities is also available on the open web in an unstructured format that developers can take advantage of to fix vulnerabilities in their IT applications. SQL injection (SQLi) attacks are frequently launched with the objective of exfiltration of data typically through targeting the back-end server organisations to compromise their customer databases. There have been a number of high profile attacks against large enterprises in recent years. With the ever-increasing growth of online trading, it is possible to see how SQLi attacks can continue to be one of the leading routes for cyber-attacks in the future, as indicated by findings reported in OWASP. Various machine learning and deep learning algorithms have been applied to detect and prevent these attacks. However, such preventive attempts have not limited the incidence of cyber-attacks and the resulting compromised database as reported by (CVE) repository. In this paper, the potential of using data mining approaches is pursued in order to enhance the efficacy of SQL injection safeguarding measures by reducing the false-positive rates in SQLi detection. The proposed approach uses CountVectorizer to extract features and then apply various supervised machine-learning models to automate the classification of SQLi. The model that returns the highest accuracy has been chosen among available models. Also a new model has been created PALOSDM (Performance analysis and Iterative optimisation of the SQLI Detection Model) for reducing false-positive rate and false-negative rate. The detection rate accuracy has also been improved significantly from a baseline of 94% up to 99%.","PeriodicalId":6874,"journal":{"name":"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)","volume":"32 1","pages":"513-517"},"PeriodicalIF":0.0,"publicationDate":"2022-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82609291","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 : 2022-03-22DOI: 10.1109/IC_ASET53395.2022.9765894
N. Fezai, A. Jouini, Feten Slimeni, A. Amor
Metrology is the science of measurement. It is applied in several fields where quantitative measurements are made. In fact, in any industrial activity (food processing, electrical energy, chemistry, mechanics, aeronautics, space, defense, agriculture, electronics) various measuring instruments are used. After a certain period of operation, their indications will be erroneous, which leads to major risks for the safety of people and industrial installations. Thus all equipment drifts over time, it is a well known phenomenon. A measuring instrument that is "accurate" today will not be so tomorrow because it will have drifted! The causes of drift are multiple and varied (mechanical origin: shocks and vibrations, oxidation, wear, conditions of use, aging...). This calibration interval or drift is determined either by the manufacturer or by the needs of the company or the laboratory. Historically, the periodicity is 12 months in metrology for all the instruments, this drift allows to have a management of periodicity of the equipments but sometimes the calibration will be with a high cost. Therefore, to avoid costly periodic calibrations, methods have been created to adjust and optimize calibration costs according to the criticality and use of the measuring instrument. The optimization and justification of periodicity are increasingly crucial problems over time, they are now the subject of strict guides defining the methods of calculating periodicity such as the method of max drift, the method of weight and the method OPPERET. In this paper, we will demonstrate the adequate method for a special laboratory that has a limited number of equipments according to the ISO/CEI 17025 version 2017.
{"title":"Metrological map of a fleet of equipment a metrology laboratory: application of weight method according to FDX-07-014","authors":"N. Fezai, A. Jouini, Feten Slimeni, A. Amor","doi":"10.1109/IC_ASET53395.2022.9765894","DOIUrl":"https://doi.org/10.1109/IC_ASET53395.2022.9765894","url":null,"abstract":"Metrology is the science of measurement. It is applied in several fields where quantitative measurements are made. In fact, in any industrial activity (food processing, electrical energy, chemistry, mechanics, aeronautics, space, defense, agriculture, electronics) various measuring instruments are used. After a certain period of operation, their indications will be erroneous, which leads to major risks for the safety of people and industrial installations. Thus all equipment drifts over time, it is a well known phenomenon. A measuring instrument that is \"accurate\" today will not be so tomorrow because it will have drifted! The causes of drift are multiple and varied (mechanical origin: shocks and vibrations, oxidation, wear, conditions of use, aging...). This calibration interval or drift is determined either by the manufacturer or by the needs of the company or the laboratory. Historically, the periodicity is 12 months in metrology for all the instruments, this drift allows to have a management of periodicity of the equipments but sometimes the calibration will be with a high cost. Therefore, to avoid costly periodic calibrations, methods have been created to adjust and optimize calibration costs according to the criticality and use of the measuring instrument. The optimization and justification of periodicity are increasingly crucial problems over time, they are now the subject of strict guides defining the methods of calculating periodicity such as the method of max drift, the method of weight and the method OPPERET. In this paper, we will demonstrate the adequate method for a special laboratory that has a limited number of equipments according to the ISO/CEI 17025 version 2017.","PeriodicalId":6874,"journal":{"name":"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)","volume":"10 1","pages":"336-339"},"PeriodicalIF":0.0,"publicationDate":"2022-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79074108","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 : 2022-03-22DOI: 10.1109/IC_ASET53395.2022.9765934
Abdoulaye Bodian, A. Cárdenas, A. B. Ben Abdelghani
The work presented in this paper deals with power electronics topologies for electric vehicle chargers and more generally in mobility applications. The paper proposes a dual output wireless charger, a 120V/60Hz AC and 24V DC output, operating at a resonant frequency of 75 kHz. Considering that the targeted applications of the charger are intended to operate with a voltage of 120V/60Hz, the designed wireless charger will have to be powered from a standard 120V/60Hz outlet. The maximum current drawn by the load will be limited to 20A, a nominal apparent power of 2.4 kVA is then defined according to SAE J2954. This power belongs to class 1 as defined by this standard. All active and passive components are designed on the basis of a charger defined by the SAE J2954 standard. To validate the feasibility, the proposed topology is modelled and then simulated on MATLAB Simulink to show its performance and analyse its limits.
{"title":"Double Outputs Resonant-based Wireless Charger for Electric Vehicle and Robotic Applications","authors":"Abdoulaye Bodian, A. Cárdenas, A. B. Ben Abdelghani","doi":"10.1109/IC_ASET53395.2022.9765934","DOIUrl":"https://doi.org/10.1109/IC_ASET53395.2022.9765934","url":null,"abstract":"The work presented in this paper deals with power electronics topologies for electric vehicle chargers and more generally in mobility applications. The paper proposes a dual output wireless charger, a 120V/60Hz AC and 24V DC output, operating at a resonant frequency of 75 kHz. Considering that the targeted applications of the charger are intended to operate with a voltage of 120V/60Hz, the designed wireless charger will have to be powered from a standard 120V/60Hz outlet. The maximum current drawn by the load will be limited to 20A, a nominal apparent power of 2.4 kVA is then defined according to SAE J2954. This power belongs to class 1 as defined by this standard. All active and passive components are designed on the basis of a charger defined by the SAE J2954 standard. To validate the feasibility, the proposed topology is modelled and then simulated on MATLAB Simulink to show its performance and analyse its limits.","PeriodicalId":6874,"journal":{"name":"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)","volume":"10 1","pages":"439-444"},"PeriodicalIF":0.0,"publicationDate":"2022-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75780920","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 : 2022-03-22DOI: 10.1109/IC_ASET53395.2022.9765873
Mohamed Boussif
Since 1977, many cryptographic attacks have been applied to RSA (Rivest Shamir Adleman). Researchers have proposed security solutions against these attacks, such as padding into the data to be encrypted and using keys of significant length from 1024 bits to 4096 bits. Therefore, to implement RSA., we need an arithmetic unit working with a big integer like in Python and Maple. The maximal length of almost programming platforms doesn't exceed 64 bits. This article presents a scalable algorithm of the RSA cryptosystem with a large key size based on arrays of 8 bits. Therefore, keys, message to be encrypted, and encrypted data are arrays. Each array case is of type unsigned integer 8 bit. However, it codes only 7 bits; the 8th bit is used for the carrying of an arithmetic operation. The proposed arithmetic unit allows subtraction, division, and multiplication of large numbers, and it is scalable with all platforms like C/C++, Java, and PHP. The proposed algorithm is implemented on MATLAB environment. Simulation tests are verified with Python, where we find that the proposed implementation generates RSA keys, encrypts, and decrypts data with 0% failure.
{"title":"Scalable Implementation of Array of 8-bit-Based RSA With Large Key Size","authors":"Mohamed Boussif","doi":"10.1109/IC_ASET53395.2022.9765873","DOIUrl":"https://doi.org/10.1109/IC_ASET53395.2022.9765873","url":null,"abstract":"Since 1977, many cryptographic attacks have been applied to RSA (Rivest Shamir Adleman). Researchers have proposed security solutions against these attacks, such as padding into the data to be encrypted and using keys of significant length from 1024 bits to 4096 bits. Therefore, to implement RSA., we need an arithmetic unit working with a big integer like in Python and Maple. The maximal length of almost programming platforms doesn't exceed 64 bits. This article presents a scalable algorithm of the RSA cryptosystem with a large key size based on arrays of 8 bits. Therefore, keys, message to be encrypted, and encrypted data are arrays. Each array case is of type unsigned integer 8 bit. However, it codes only 7 bits; the 8th bit is used for the carrying of an arithmetic operation. The proposed arithmetic unit allows subtraction, division, and multiplication of large numbers, and it is scalable with all platforms like C/C++, Java, and PHP. The proposed algorithm is implemented on MATLAB environment. Simulation tests are verified with Python, where we find that the proposed implementation generates RSA keys, encrypts, and decrypts data with 0% failure.","PeriodicalId":6874,"journal":{"name":"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)","volume":"120 1","pages":"375-380"},"PeriodicalIF":0.0,"publicationDate":"2022-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80709210","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 : 2022-03-22DOI: 10.1109/IC_ASET53395.2022.9765885
Wadhah Ayadi, W. Elhamzi, M. Atri
Brain tumor segmentation represents a hard job for radiologists as the brain is the most complicated and complex organ. Among the several brain tumors that existed, gliomas are the most aggressive and common. They lead to a short life in their highest grade especially. It is usually the most found tumors, which have various shapes, sizes, and brightness. It can appear anywhere in the brain. These causes make the automatic brain tumor segmentation a challenging problem. In this area, different Deep Learning (DL) models are suggested to help doctors. In this work, a new deep Convolutional Neural Network (CNN) architecture is presented to surpass these drawbacks. Our contributions incorporate three aspects. First, we exploited a pre-processing step based on intensity normalization with the goal to enhance the quality of the images. Second, we suggested an automatic segmentation model using CNN. The new scheme contains various convolutional layers, all exploiting 3 × 3 kernels, and one fully connected layer. Finally, we exploit a post-processing approach with the goal to ameliorate the segmentation results of the suggested model. We have evaluated the proposed technique based on the Multimodal Brain Tumor Image Segmentation Challenge datasets (BRATS 2017). The gained results provide the effectiveness of the suggested model compared with several techniques.
{"title":"Glioma segmentation based on deep CNN","authors":"Wadhah Ayadi, W. Elhamzi, M. Atri","doi":"10.1109/IC_ASET53395.2022.9765885","DOIUrl":"https://doi.org/10.1109/IC_ASET53395.2022.9765885","url":null,"abstract":"Brain tumor segmentation represents a hard job for radiologists as the brain is the most complicated and complex organ. Among the several brain tumors that existed, gliomas are the most aggressive and common. They lead to a short life in their highest grade especially. It is usually the most found tumors, which have various shapes, sizes, and brightness. It can appear anywhere in the brain. These causes make the automatic brain tumor segmentation a challenging problem. In this area, different Deep Learning (DL) models are suggested to help doctors. In this work, a new deep Convolutional Neural Network (CNN) architecture is presented to surpass these drawbacks. Our contributions incorporate three aspects. First, we exploited a pre-processing step based on intensity normalization with the goal to enhance the quality of the images. Second, we suggested an automatic segmentation model using CNN. The new scheme contains various convolutional layers, all exploiting 3 × 3 kernels, and one fully connected layer. Finally, we exploit a post-processing approach with the goal to ameliorate the segmentation results of the suggested model. We have evaluated the proposed technique based on the Multimodal Brain Tumor Image Segmentation Challenge datasets (BRATS 2017). The gained results provide the effectiveness of the suggested model compared with several techniques.","PeriodicalId":6874,"journal":{"name":"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)","volume":"187 1","pages":"285-289"},"PeriodicalIF":0.0,"publicationDate":"2022-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72737430","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：