Pub Date : 2016-12-01DOI: 10.1109/SETIT.2016.7939870
S. Gharbi, S. Labidi
The study was aimed at evaluating the value of current modulation (mAs) and iterative reconstructions algorithms during Computed Tomography examinations in terms of dose reduction and image quality. The focus was mainly on non-contrast head and chest-abdomen-pelvis examinations. A total of 40 adult patients with weighting between 65 and 80 kg underwent CT examinations (20 head and 20 chest-abdomen-pelvis). All examinations were performed on a 128-slice scanner (Somatom Definition AS from Siemens, Forchheim, Germany) using CARE Dose 4D technology. The radiation dose values were compared with reference levels values recommended for head and chest-abdomen-pelvis regions. Image quality was evaluated both objectively and subjectively using Students' test. The results on the present study showed that through the combination of CARE Dose 4D and SAFIRE; the radiation dose could be reduced by 20.10% and 59 % for the examination of head and chest-abdomen-pelvis respectively. There was a substantial difference in the image quality when using FBP or SAFIRE (p < 0.05). The noise level dropped significantly during SAFIRE when compared to FBP by 14.25% for head and by 27.60% and for chest-abdomen-pelvis scans. We conclude that automatic exposure control mechanism based on tube current modulation CARE Dose 4D when combined with iterative reconstruction SAFIRE delivers good image quality with low dose for non-enhanced head and chest-abdomen-pelvis scans.
{"title":"Radiation dose optimization in computed tomography with current modulation and Iterative Reconstruction","authors":"S. Gharbi, S. Labidi","doi":"10.1109/SETIT.2016.7939870","DOIUrl":"https://doi.org/10.1109/SETIT.2016.7939870","url":null,"abstract":"The study was aimed at evaluating the value of current modulation (mAs) and iterative reconstructions algorithms during Computed Tomography examinations in terms of dose reduction and image quality. The focus was mainly on non-contrast head and chest-abdomen-pelvis examinations. A total of 40 adult patients with weighting between 65 and 80 kg underwent CT examinations (20 head and 20 chest-abdomen-pelvis). All examinations were performed on a 128-slice scanner (Somatom Definition AS from Siemens, Forchheim, Germany) using CARE Dose 4D technology. The radiation dose values were compared with reference levels values recommended for head and chest-abdomen-pelvis regions. Image quality was evaluated both objectively and subjectively using Students' test. The results on the present study showed that through the combination of CARE Dose 4D and SAFIRE; the radiation dose could be reduced by 20.10% and 59 % for the examination of head and chest-abdomen-pelvis respectively. There was a substantial difference in the image quality when using FBP or SAFIRE (p < 0.05). The noise level dropped significantly during SAFIRE when compared to FBP by 14.25% for head and by 27.60% and for chest-abdomen-pelvis scans. We conclude that automatic exposure control mechanism based on tube current modulation CARE Dose 4D when combined with iterative reconstruction SAFIRE delivers good image quality with low dose for non-enhanced head and chest-abdomen-pelvis scans.","PeriodicalId":426951,"journal":{"name":"2016 7th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126661865","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 : 2016-12-01DOI: 10.1109/SETIT.2016.7939893
Ben Jdira Makrem, Jemâa Imen, Ouni Kaïs
We aim by this work to follow the significant progress in speaker recognition systems getting the benefits of the advancement in the artificial intelligence (AI). Indeed, the deep learning algorithms have proved a real performance in the recognition and classification data. In this contest, we present a study of three different speaker recognition system based in Feed Forward neural networks. The first one is the logic regression, the second one is the Multilayer Perceptron (MLP) and the third one is the Stacked Denoising Autoencodeurs (SDA). We evaluated these recognition rates using the parameterization technique Mel Frequency Cepstral Coefficients (MFCC). To find the best results and to better optimize automatic recognition algorithms, we tested our speaker recognition system under the text-dependent database RSR2015. We studied the recognition rates by varying the values of neural networks parameters, number of neurons and number of hidden layers…etc. We discussed the different results obtained and we selected best parameter values which lead the minimum rate error of recognition.
{"title":"Study of speaker recognition system based on Feed Forward deep neural networks exploring text-dependent mode","authors":"Ben Jdira Makrem, Jemâa Imen, Ouni Kaïs","doi":"10.1109/SETIT.2016.7939893","DOIUrl":"https://doi.org/10.1109/SETIT.2016.7939893","url":null,"abstract":"We aim by this work to follow the significant progress in speaker recognition systems getting the benefits of the advancement in the artificial intelligence (AI). Indeed, the deep learning algorithms have proved a real performance in the recognition and classification data. In this contest, we present a study of three different speaker recognition system based in Feed Forward neural networks. The first one is the logic regression, the second one is the Multilayer Perceptron (MLP) and the third one is the Stacked Denoising Autoencodeurs (SDA). We evaluated these recognition rates using the parameterization technique Mel Frequency Cepstral Coefficients (MFCC). To find the best results and to better optimize automatic recognition algorithms, we tested our speaker recognition system under the text-dependent database RSR2015. We studied the recognition rates by varying the values of neural networks parameters, number of neurons and number of hidden layers…etc. We discussed the different results obtained and we selected best parameter values which lead the minimum rate error of recognition.","PeriodicalId":426951,"journal":{"name":"2016 7th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126459893","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 : 2016-12-01DOI: 10.1109/SETIT.2016.7939887
Ali Mehanaoui, T. Laroussi, M. Attalah, Aladdine Aouane
This paper investigates the problem of automatic target detection in a Pareto background under multiple target situations. The number of interfering targets is assumed to be unknown. We derive the Enhanced Variability Index Automatic Selection and Detection Constant False Alarm Rate (EVI-ASD-CFAR) Processor. This latter selects and matches dynamically the suitable detector among the Geometric Mean (GM)-CFAR, Greatest Of(GO)-CFAR and Trimmed Mean (TM)-CFAR. The unknown background level is then estimated and set to the corresponding threshold. The detection performances of the proposed processor are assessed via Monte Carlo simulations.
{"title":"An EVI-ASD-CFAR Processor in a Pareto background and multiple target situations","authors":"Ali Mehanaoui, T. Laroussi, M. Attalah, Aladdine Aouane","doi":"10.1109/SETIT.2016.7939887","DOIUrl":"https://doi.org/10.1109/SETIT.2016.7939887","url":null,"abstract":"This paper investigates the problem of automatic target detection in a Pareto background under multiple target situations. The number of interfering targets is assumed to be unknown. We derive the Enhanced Variability Index Automatic Selection and Detection Constant False Alarm Rate (EVI-ASD-CFAR) Processor. This latter selects and matches dynamically the suitable detector among the Geometric Mean (GM)-CFAR, Greatest Of(GO)-CFAR and Trimmed Mean (TM)-CFAR. The unknown background level is then estimated and set to the corresponding threshold. The detection performances of the proposed processor are assessed via Monte Carlo simulations.","PeriodicalId":426951,"journal":{"name":"2016 7th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122432183","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 : 2016-12-01DOI: 10.1109/SETIT.2016.7939901
M. Salah, S. Azizi, A. Boukhachem, C. Khaldi, J. Lamloumi
In this work, structural, electrical properties of Li doped ZnO thin films, by chemical pulverization grown on glass substrates at different Li doping concentrations, were reported. Besides, The effects of lithium doping on structural properties of ZnO: Li thin films were studied by means of XRD technique. This study demonstrated that all prepared thin films consisted of unique phase ZnO and were well crystallized in wurtzite structure with the preferentially orientation (002) in the direction parallel to c-axis. The obtained results showed that these films have polycrystalline wurtzite-structure and high c-axis preferred orientation. Besides, the ZnO photodetectors revealed superior performance in the view of photocurrent.
{"title":"Doped zinc oxide thin films for photodetectors devices","authors":"M. Salah, S. Azizi, A. Boukhachem, C. Khaldi, J. Lamloumi","doi":"10.1109/SETIT.2016.7939901","DOIUrl":"https://doi.org/10.1109/SETIT.2016.7939901","url":null,"abstract":"In this work, structural, electrical properties of Li doped ZnO thin films, by chemical pulverization grown on glass substrates at different Li doping concentrations, were reported. Besides, The effects of lithium doping on structural properties of ZnO: Li thin films were studied by means of XRD technique. This study demonstrated that all prepared thin films consisted of unique phase ZnO and were well crystallized in wurtzite structure with the preferentially orientation (002) in the direction parallel to c-axis. The obtained results showed that these films have polycrystalline wurtzite-structure and high c-axis preferred orientation. Besides, the ZnO photodetectors revealed superior performance in the view of photocurrent.","PeriodicalId":426951,"journal":{"name":"2016 7th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"15 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133002175","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 : 2016-12-01DOI: 10.1109/SETIT.2016.7939877
Neziha Jaouedi, Noureddine Boujnah, Oumayma Htiwich, M. Bouhlel
Human machine interaction becomes one of the most research topics in multimedia processing, traditional techniques for communication are developed in order to tackle technology advances and allow disable person to communicate easily with the machine, and to understand their activity using computer computing. In this paper we are focused on human behavior analysis from video scene and it is worth noticed that many information are hidden behind gesture, sudden motion and walking speed, many research works tried to model and then recognize human behavior through motion analysis. In our work we will explain the human action recognition By K Nearest Neighbors approach.
{"title":"Human action recognition to human behavior analysis","authors":"Neziha Jaouedi, Noureddine Boujnah, Oumayma Htiwich, M. Bouhlel","doi":"10.1109/SETIT.2016.7939877","DOIUrl":"https://doi.org/10.1109/SETIT.2016.7939877","url":null,"abstract":"Human machine interaction becomes one of the most research topics in multimedia processing, traditional techniques for communication are developed in order to tackle technology advances and allow disable person to communicate easily with the machine, and to understand their activity using computer computing. In this paper we are focused on human behavior analysis from video scene and it is worth noticed that many information are hidden behind gesture, sudden motion and walking speed, many research works tried to model and then recognize human behavior through motion analysis. In our work we will explain the human action recognition By K Nearest Neighbors approach.","PeriodicalId":426951,"journal":{"name":"2016 7th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128751385","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 : 2016-12-01DOI: 10.1109/SETIT.2016.7939866
Majdi Benzarti, Zouhaira Abdellaoui
The need for high data rate is growing since the multimedia applications are gaining popularity which needs high data rate and quality of service. Multiple Input Multiple Output (MIMO) transmission system is one of the most promising approach of the Smart Antenna Technology which uses multiple antennas in the transmitter and the receiver side and is currently followed for high-rate wireless communication[1]. Synchronization is crucial in all wireless communication systems and especially in OFDM and MIMO-OFDM system [2]. The receivers cannot know the beginning and the end of the OFDM symbols, so the placement of the FFT window. In reception, they have their own frequency rate which is asynchronous with the frequency of the transmitter. Several estimation techniques for time and frequency offset have been proposed in the literature, but varied test conditions make comparison difficult. This paper presents the results of a comparative Study of Frequency Synchronization in SISO and MIMO-OFDM Systems.
{"title":"Comparative Study of Frequency Synchronization in SISO and MIMO-OFDM Systems","authors":"Majdi Benzarti, Zouhaira Abdellaoui","doi":"10.1109/SETIT.2016.7939866","DOIUrl":"https://doi.org/10.1109/SETIT.2016.7939866","url":null,"abstract":"The need for high data rate is growing since the multimedia applications are gaining popularity which needs high data rate and quality of service. Multiple Input Multiple Output (MIMO) transmission system is one of the most promising approach of the Smart Antenna Technology which uses multiple antennas in the transmitter and the receiver side and is currently followed for high-rate wireless communication[1]. Synchronization is crucial in all wireless communication systems and especially in OFDM and MIMO-OFDM system [2]. The receivers cannot know the beginning and the end of the OFDM symbols, so the placement of the FFT window. In reception, they have their own frequency rate which is asynchronous with the frequency of the transmitter. Several estimation techniques for time and frequency offset have been proposed in the literature, but varied test conditions make comparison difficult. This paper presents the results of a comparative Study of Frequency Synchronization in SISO and MIMO-OFDM Systems.","PeriodicalId":426951,"journal":{"name":"2016 7th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115227123","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 : 2016-12-01DOI: 10.1109/SETIT.2016.7939842
Marwa Ben Hassen, Sofiane Ben Mbarek, F. Choubani
In this paper, CPW-Antennas for Near-Field Applications were modelized with metal tips. In this study, we demonstrated that those antennas are near-field probes capable of transferring evanescent information into the far-field. As we expected, the results of the field distributions agree very well theoretically. The metal tips are investigated by the finite difference time-domain (FDTD) with Transverse ElectroMagnetic (TEM) propagation mode.
{"title":"2-D FDTD analysis of CPW Antenna for electromagnetic Near-field Applications","authors":"Marwa Ben Hassen, Sofiane Ben Mbarek, F. Choubani","doi":"10.1109/SETIT.2016.7939842","DOIUrl":"https://doi.org/10.1109/SETIT.2016.7939842","url":null,"abstract":"In this paper, CPW-Antennas for Near-Field Applications were modelized with metal tips. In this study, we demonstrated that those antennas are near-field probes capable of transferring evanescent information into the far-field. As we expected, the results of the field distributions agree very well theoretically. The metal tips are investigated by the finite difference time-domain (FDTD) with Transverse ElectroMagnetic (TEM) propagation mode.","PeriodicalId":426951,"journal":{"name":"2016 7th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121714880","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}
The braking system is the most critical system of the vehicle. Maintenance and proper operation are vital for us, for this reason, and since the 70s, a growing number of scientists have been interested in the braking systems. Currently the braking system has become a mechatronic system. It consists of a hydraulic part, a mechanical part and an electronic part. Indeed, while the car is rolling, the system continuously monitors each wheel by means of a wheel speed sensor and an electronic calculator which will be displayed on the car's dashboard to inform the driver. This communication gives an idea about the functioning of an ABS type system which is an “anti blocking system”. It proposes a model based on two methods which are: the first method is functional analysis; the second is the bond graph of the measurement section and the speed display, and then shows the simulation of these models by the Matlab Simulink software and 20 Sim.
{"title":"Modeling the speed measuring chain in ABS braking system","authors":"Ben Salem J., L. M.N., E. l.","doi":"10.1109/dt.2017.8012079","DOIUrl":"https://doi.org/10.1109/dt.2017.8012079","url":null,"abstract":"The braking system is the most critical system of the vehicle. Maintenance and proper operation are vital for us, for this reason, and since the 70s, a growing number of scientists have been interested in the braking systems. Currently the braking system has become a mechatronic system. It consists of a hydraulic part, a mechanical part and an electronic part. Indeed, while the car is rolling, the system continuously monitors each wheel by means of a wheel speed sensor and an electronic calculator which will be displayed on the car's dashboard to inform the driver. This communication gives an idea about the functioning of an ABS type system which is an “anti blocking system”. It proposes a model based on two methods which are: the first method is functional analysis; the second is the bond graph of the measurement section and the speed display, and then shows the simulation of these models by the Matlab Simulink software and 20 Sim.","PeriodicalId":426951,"journal":{"name":"2016 7th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115841933","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：