Pub Date : 2017-05-01DOI: 10.1109/ICEMIS.2017.8273114
Chahira Lhioui, A. Zouaghi, M. Zrigui
There is a widely held belief in the natural language and computational linguistics communities that knowledge extraction such us Temporal Expression (TE) extraction is a significant step toward, improving important applications, e.g. Question/Answering (Q/A) and Language Understanding (LU). In this paper, we present a TE extraction system for Modern Standard Arabic using NooJ platform. This system exploits many aspects of the rich morphological features of the language. The experiments on the pilot Arabic Propbank data show that our system based on linguistic rules produces a global TE extraction F-measure score of 95.5%, which improves the current state-of-the-art in Arabic TE extraction.
{"title":"A rule-based approach for Arabic temporal expression extraction","authors":"Chahira Lhioui, A. Zouaghi, M. Zrigui","doi":"10.1109/ICEMIS.2017.8273114","DOIUrl":"https://doi.org/10.1109/ICEMIS.2017.8273114","url":null,"abstract":"There is a widely held belief in the natural language and computational linguistics communities that knowledge extraction such us Temporal Expression (TE) extraction is a significant step toward, improving important applications, e.g. Question/Answering (Q/A) and Language Understanding (LU). In this paper, we present a TE extraction system for Modern Standard Arabic using NooJ platform. This system exploits many aspects of the rich morphological features of the language. The experiments on the pilot Arabic Propbank data show that our system based on linguistic rules produces a global TE extraction F-measure score of 95.5%, which improves the current state-of-the-art in Arabic TE extraction.","PeriodicalId":117908,"journal":{"name":"2017 International Conference on Engineering & MIS (ICEMIS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128484332","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 : 2017-05-01DOI: 10.1109/ICEMIS.2017.8273069
D. B. Salem, Wajdi Saad, A. Sellami, G. García
This paper proposes an integral sliding mode control (ISMC) for a class of linear systems with time-varying state and input delays. An integral sliding surface is firstly constructed. Then, by using the Lyapunov-Krasovskii functional and some specified matrices, a sufficient condition is obtained in the form of linear matrix inequalities (LMIs) to ensure the sliding mode dynamics to be asymptotically stable. Furthermore, a sliding mode controller law is synthesized to guarantee that the system trajectories can be driven onto the specified sliding surface in a finite time and maintained there for all subsequent time. Finally, an inverted pendulum model is used to illustrate the advantages and effectiveness of the design method.
{"title":"Integral sliding mode control for systems with time-varying input and state delays","authors":"D. B. Salem, Wajdi Saad, A. Sellami, G. García","doi":"10.1109/ICEMIS.2017.8273069","DOIUrl":"https://doi.org/10.1109/ICEMIS.2017.8273069","url":null,"abstract":"This paper proposes an integral sliding mode control (ISMC) for a class of linear systems with time-varying state and input delays. An integral sliding surface is firstly constructed. Then, by using the Lyapunov-Krasovskii functional and some specified matrices, a sufficient condition is obtained in the form of linear matrix inequalities (LMIs) to ensure the sliding mode dynamics to be asymptotically stable. Furthermore, a sliding mode controller law is synthesized to guarantee that the system trajectories can be driven onto the specified sliding surface in a finite time and maintained there for all subsequent time. Finally, an inverted pendulum model is used to illustrate the advantages and effectiveness of the design method.","PeriodicalId":117908,"journal":{"name":"2017 International Conference on Engineering & MIS (ICEMIS)","volume":"159 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117181989","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 : 2017-05-01DOI: 10.1109/ICEMIS.2017.8273010
Afef Badis, M. Mansouri, Mohamed Habib Boujmil
Because of the non-linearity of the P-V characteristic of the Photovoltaic (PV) panel, a power electronic interface is mandatory to reach the desired fixed voltage level. This paper deals with the design of a PID controller in order to control a DC-DC boost converter in the PV system. For the design of the whole system, the used approach is based on the Energetic Macroscopic Representation (EMR). This technique goes from a complex command to a simpler one and is characterized by the use of cascading of one or more controllers. The three parameters of the controller are tuned by using Genetic Algorithm (GA). Both of the system responses using PID MPPT controller tuned by genetic algorithm and PID controller tuned by Pole Placement (PP) are tested when fast changing the solar irradiation is experienced. Finally, in order to obtain the best system performance, Perturb and Observe (P&O) MPPT method is applied to generate the output voltage reference Vref. The simulation results are compared in terms of mean squared error (MSE) criterion, percentage overshoot and rising time. The results show that parameters tuned by GA PID controller gives better performance.
{"title":"A genetic algorithm optimized MPPT controller for a PV system with DC-DC boost converter","authors":"Afef Badis, M. Mansouri, Mohamed Habib Boujmil","doi":"10.1109/ICEMIS.2017.8273010","DOIUrl":"https://doi.org/10.1109/ICEMIS.2017.8273010","url":null,"abstract":"Because of the non-linearity of the P-V characteristic of the Photovoltaic (PV) panel, a power electronic interface is mandatory to reach the desired fixed voltage level. This paper deals with the design of a PID controller in order to control a DC-DC boost converter in the PV system. For the design of the whole system, the used approach is based on the Energetic Macroscopic Representation (EMR). This technique goes from a complex command to a simpler one and is characterized by the use of cascading of one or more controllers. The three parameters of the controller are tuned by using Genetic Algorithm (GA). Both of the system responses using PID MPPT controller tuned by genetic algorithm and PID controller tuned by Pole Placement (PP) are tested when fast changing the solar irradiation is experienced. Finally, in order to obtain the best system performance, Perturb and Observe (P&O) MPPT method is applied to generate the output voltage reference Vref. The simulation results are compared in terms of mean squared error (MSE) criterion, percentage overshoot and rising time. The results show that parameters tuned by GA PID controller gives better performance.","PeriodicalId":117908,"journal":{"name":"2017 International Conference on Engineering & MIS (ICEMIS)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117210549","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 : 2017-05-01DOI: 10.1109/ICEMIS.2017.8272963
David de la Peña, J. Lara, D. Lizcano, María-Aurora Martínez, Concepción Burgos, María L. Campanario
E-learning systems have major benefits but also pose major challenges. One of these is how to do a good job of tutoring students without face-to-face contact. This calls for the interpretation of large quantities of data generated as a result of the activities performed by students, which e-learning platforms collect and store. These data are also potentially very useful for preventing student dropout. We propose the use of knowledge discovery techniques to analyse historical student course grade data in order to be able to predict in real time whether or not a student will drop out of a course in the future. Logistic regression models are used for the purpose of classification. Experiments conducted with data on over 100 students for several real distance learning courses confirm the predictive power of our proposal that outperforms other existing approaches in terms of accuracy.
{"title":"Mining activity grades to model students' performance","authors":"David de la Peña, J. Lara, D. Lizcano, María-Aurora Martínez, Concepción Burgos, María L. Campanario","doi":"10.1109/ICEMIS.2017.8272963","DOIUrl":"https://doi.org/10.1109/ICEMIS.2017.8272963","url":null,"abstract":"E-learning systems have major benefits but also pose major challenges. One of these is how to do a good job of tutoring students without face-to-face contact. This calls for the interpretation of large quantities of data generated as a result of the activities performed by students, which e-learning platforms collect and store. These data are also potentially very useful for preventing student dropout. We propose the use of knowledge discovery techniques to analyse historical student course grade data in order to be able to predict in real time whether or not a student will drop out of a course in the future. Logistic regression models are used for the purpose of classification. Experiments conducted with data on over 100 students for several real distance learning courses confirm the predictive power of our proposal that outperforms other existing approaches in terms of accuracy.","PeriodicalId":117908,"journal":{"name":"2017 International Conference on Engineering & MIS (ICEMIS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125407383","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 : 2017-05-01DOI: 10.1109/ICEMIS.2017.8273038
M. Jemai, Siwar Ben haj hassine, A. Mtibaa, B. Ouni
To reduce the power consumption, in the literature, most works have focused in the field of batteries. However despite the progress made in this area, it is difficult to increase the battery capacity without increasing the weight, volume and price. To overcome such problems, in this paper we present a new approach based on hardware-software partitioning to reduce power consumption. In fact, in this paper we aim to solve the following issue: Given a control data flow graph a System on a Programmable Chip circuit; find a possible hardware-software partitioning of the graph on the System on a Programmable Chip in order to minimize the logic power and satisfying a temporal constraint.
{"title":"Systemized software hardware partitioning algorithm for system on programmable chip to minimize logic power","authors":"M. Jemai, Siwar Ben haj hassine, A. Mtibaa, B. Ouni","doi":"10.1109/ICEMIS.2017.8273038","DOIUrl":"https://doi.org/10.1109/ICEMIS.2017.8273038","url":null,"abstract":"To reduce the power consumption, in the literature, most works have focused in the field of batteries. However despite the progress made in this area, it is difficult to increase the battery capacity without increasing the weight, volume and price. To overcome such problems, in this paper we present a new approach based on hardware-software partitioning to reduce power consumption. In fact, in this paper we aim to solve the following issue: Given a control data flow graph a System on a Programmable Chip circuit; find a possible hardware-software partitioning of the graph on the System on a Programmable Chip in order to minimize the logic power and satisfying a temporal constraint.","PeriodicalId":117908,"journal":{"name":"2017 International Conference on Engineering & MIS (ICEMIS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126075992","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 : 2017-05-01DOI: 10.1109/ICEMIS.2017.8272968
Dabbabi Karim, Chérif Adnen, Hajji Salah
A system for speaker-based audio indexing and for speaker tracking in broadcast news audio is presented. Several tasks which are treated as a multistage process construct the process of producing indexing information in continuous audio streams based on detected speakers. The main constructing blocks of such an indexing system contain components for an audio segmentation, speaker detection, speaker clustering, and speaker identification. In the proposed speaker-based audio indexing system, three probabilistic Linear Disciminant Analysis (PLDA) variants-standard, simplified and two-covariance-, and Gaussian Mixture Model (GMM) are proposed in the speaker identification stage. The evaluation is performed on audio data from the broadcast news domain and the obtained results demonstrate the superiority of two-covariance PLDA model in terms of performance results compared to other proposed algorithms.
{"title":"A system for speaker detection and tracking in audio broadcast news","authors":"Dabbabi Karim, Chérif Adnen, Hajji Salah","doi":"10.1109/ICEMIS.2017.8272968","DOIUrl":"https://doi.org/10.1109/ICEMIS.2017.8272968","url":null,"abstract":"A system for speaker-based audio indexing and for speaker tracking in broadcast news audio is presented. Several tasks which are treated as a multistage process construct the process of producing indexing information in continuous audio streams based on detected speakers. The main constructing blocks of such an indexing system contain components for an audio segmentation, speaker detection, speaker clustering, and speaker identification. In the proposed speaker-based audio indexing system, three probabilistic Linear Disciminant Analysis (PLDA) variants-standard, simplified and two-covariance-, and Gaussian Mixture Model (GMM) are proposed in the speaker identification stage. The evaluation is performed on audio data from the broadcast news domain and the obtained results demonstrate the superiority of two-covariance PLDA model in terms of performance results compared to other proposed algorithms.","PeriodicalId":117908,"journal":{"name":"2017 International Conference on Engineering & MIS (ICEMIS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125765998","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 : 2017-05-01DOI: 10.1109/ICEMIS.2017.8273013
Intissar Khoja, T. Ladhari, A. Sakly, F. Msahli
This paper investigates the application of an optimization method, which is the genetic algorithm, in order to identify the parameters of an activated sludge process for waste water treatment. The studied model is a hybrid reduced-order one. The genetic algorithm tries to find out the optimal parameters that ensure a minimal mean square error between the measured and simulation outputs. Simulation results show the competence of the proposed approach to seize the true model's parameter values.
{"title":"Activated sludge process identification based on genetic algorithm","authors":"Intissar Khoja, T. Ladhari, A. Sakly, F. Msahli","doi":"10.1109/ICEMIS.2017.8273013","DOIUrl":"https://doi.org/10.1109/ICEMIS.2017.8273013","url":null,"abstract":"This paper investigates the application of an optimization method, which is the genetic algorithm, in order to identify the parameters of an activated sludge process for waste water treatment. The studied model is a hybrid reduced-order one. The genetic algorithm tries to find out the optimal parameters that ensure a minimal mean square error between the measured and simulation outputs. Simulation results show the competence of the proposed approach to seize the true model's parameter values.","PeriodicalId":117908,"journal":{"name":"2017 International Conference on Engineering & MIS (ICEMIS)","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124248163","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 : 2017-05-01DOI: 10.1109/ICEMIS.2017.8273060
Yosra Saad, M. Selmi, M. H. Gazzah, H. Belmabrouk
In the present work, we have studied the phenomenon of surface plasmon resonance by analyzing the detection method. So we have studied the effect of physical and geometric parameters on the spectral response of optical fiber SPR sensors. We have found that this response is strongly dependent on the thickness of the metal layer, the diameter of the core of optical fiber, the length of the sensitive area, and the nature of the metal used. This study is an important step to get the optimization of these sensors.
{"title":"Numerical modeling of surface plasmon resonance response of fiber optic sensors","authors":"Yosra Saad, M. Selmi, M. H. Gazzah, H. Belmabrouk","doi":"10.1109/ICEMIS.2017.8273060","DOIUrl":"https://doi.org/10.1109/ICEMIS.2017.8273060","url":null,"abstract":"In the present work, we have studied the phenomenon of surface plasmon resonance by analyzing the detection method. So we have studied the effect of physical and geometric parameters on the spectral response of optical fiber SPR sensors. We have found that this response is strongly dependent on the thickness of the metal layer, the diameter of the core of optical fiber, the length of the sensitive area, and the nature of the metal used. This study is an important step to get the optimization of these sensors.","PeriodicalId":117908,"journal":{"name":"2017 International Conference on Engineering & MIS (ICEMIS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131408681","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 : 2017-05-01DOI: 10.1109/ICEMIS.2017.8273025
H. Othmani, H. Chaouali, D. Mezghani, A. Mami
This document is a study of a Sepic DC-DC converter topology devoted to photovoltaic generator, type Kaneka GSA-60, in order to enhance its performance against sudden variations in weather conditions. This work shows the enhancements realized with this converter by various simulations under MATLAB-SIMULINK, the adapted approach for the design phase under Porteus ISIS software and finally the results of experimental tests of the developed. The Speic dispositive is controlled with an Arduino Board by generating different duty cycle values for PWM (Pulse Width Modulation) signals to simulate different operating conditions.
{"title":"Design and building of sepie DC-DC converter devoted to Kaneka GSA-60 PV panels","authors":"H. Othmani, H. Chaouali, D. Mezghani, A. Mami","doi":"10.1109/ICEMIS.2017.8273025","DOIUrl":"https://doi.org/10.1109/ICEMIS.2017.8273025","url":null,"abstract":"This document is a study of a Sepic DC-DC converter topology devoted to photovoltaic generator, type Kaneka GSA-60, in order to enhance its performance against sudden variations in weather conditions. This work shows the enhancements realized with this converter by various simulations under MATLAB-SIMULINK, the adapted approach for the design phase under Porteus ISIS software and finally the results of experimental tests of the developed. The Speic dispositive is controlled with an Arduino Board by generating different duty cycle values for PWM (Pulse Width Modulation) signals to simulate different operating conditions.","PeriodicalId":117908,"journal":{"name":"2017 International Conference on Engineering & MIS (ICEMIS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133181694","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 : 2017-05-01DOI: 10.1109/ICEMIS.2017.8273053
Hajer Maraoui, K. Haddar, Laurent Romary
The processing of Al-Hadith Al-Shareef is the interest not only for professional researchers but also for all Muslims in all over the world. Moreover, the language of Al-Hadith Al-Shareef is the Classical Arabic, which came out of the pre-Islamic era. It is the language, which preserved its sacred traditions and characterized with the nuance and the sophistication. In this paper, we present a model for normalizing Al-Hadith Al-Shareef with the Text Encoding Initiative (TEI) standard in order to reduce structuring problems and make unify representation for Hadith corpus.
{"title":"Modeling of Al-Hadith Al-Shareef with TEI","authors":"Hajer Maraoui, K. Haddar, Laurent Romary","doi":"10.1109/ICEMIS.2017.8273053","DOIUrl":"https://doi.org/10.1109/ICEMIS.2017.8273053","url":null,"abstract":"The processing of Al-Hadith Al-Shareef is the interest not only for professional researchers but also for all Muslims in all over the world. Moreover, the language of Al-Hadith Al-Shareef is the Classical Arabic, which came out of the pre-Islamic era. It is the language, which preserved its sacred traditions and characterized with the nuance and the sophistication. In this paper, we present a model for normalizing Al-Hadith Al-Shareef with the Text Encoding Initiative (TEI) standard in order to reduce structuring problems and make unify representation for Hadith corpus.","PeriodicalId":117908,"journal":{"name":"2017 International Conference on Engineering & MIS (ICEMIS)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134127473","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：