Recent studies have shown that adjusting HVAC systems based on the number of people inside the room can save at least 38% of energy consumed for reheating. Besides, accurate estimate of room's occupants is useful in improving the safety and security of the buildings. There are many research proposals and commercial products for reliable and efficient people counting, however, these solutions are expensive, hard to deploy, or obstructive to people flow. We investigate the possibility of utilizing wireless and light sensing technologies in the doorways to track the entrances/exits to/from the room. Our solution is inexpensive, unobtrusive with much fewer deployment constraints compared to existing people counting solutions. For RF based sensing, we use ultra-wideband signals at center frequency of 4 GHz with 500 MHz bandwidth and narrowband wireless signals (WiFi) at the center frequency of 2.4 GHz with the bandwidth of 20 MHz. We also evaluate the possibility of using existing WiFi infrastructure to count people. Ambient light is second physical phenomenon which we utilize for accurately counting number of people walk through the doors. We place low cost photodiode on door frames to detect changes in light illuminance level when there are people walking through the door. Light based people counting requires an installation of just one inexpensive photodiode at the doorway which makes our solution highly applicable for large scale deployments. We evaluated our solution via several controlled and uncontrolled real-world environments. The results show an average of 96% accuracy in estimating the number of occupants in rooms.
{"title":"Room occupancy estimation through wifi, UWB, and light sensors mounted on doorways","authors":"Hessam Mohammadmoradi, Shengrong Yin, O. Gnawali","doi":"10.1145/3128128.3128133","DOIUrl":"https://doi.org/10.1145/3128128.3128133","url":null,"abstract":"Recent studies have shown that adjusting HVAC systems based on the number of people inside the room can save at least 38% of energy consumed for reheating. Besides, accurate estimate of room's occupants is useful in improving the safety and security of the buildings. There are many research proposals and commercial products for reliable and efficient people counting, however, these solutions are expensive, hard to deploy, or obstructive to people flow. We investigate the possibility of utilizing wireless and light sensing technologies in the doorways to track the entrances/exits to/from the room. Our solution is inexpensive, unobtrusive with much fewer deployment constraints compared to existing people counting solutions. For RF based sensing, we use ultra-wideband signals at center frequency of 4 GHz with 500 MHz bandwidth and narrowband wireless signals (WiFi) at the center frequency of 2.4 GHz with the bandwidth of 20 MHz. We also evaluate the possibility of using existing WiFi infrastructure to count people. Ambient light is second physical phenomenon which we utilize for accurately counting number of people walk through the doors. We place low cost photodiode on door frames to detect changes in light illuminance level when there are people walking through the door. Light based people counting requires an installation of just one inexpensive photodiode at the doorway which makes our solution highly applicable for large scale deployments. We evaluated our solution via several controlled and uncontrolled real-world environments. The results show an average of 96% accuracy in estimating the number of occupants in rooms.","PeriodicalId":362403,"journal":{"name":"Proceedings of the 2017 International Conference on Smart Digital Environment","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124868477","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}
Abdelaziz Mouhou, A. Badri, A. Ballouk, Y. Sayouti
This paper concentrates on the off-line optimization of adaptive generalized predictive control (AGPC) tuning parameters using genetic algorithms (GAs). The Adaptive generalized predictive control algorithm is detailed and presented. A single input single output (SISO) controlled autoregressive integrated moving average (CARIMA) model is used to predict the future behavior of the system. The online parametric adaptation algorithm (PAA) used in this work is based on recursive least squares (RLS) identification algorithm with fixed forgetting factor. The synthesis parameters (minimal prediction horizon, maximal prediction horizon, control horizon and cost weighting factor) are optimized using genetic algorithms, this technique improves the closed-loop performances. The fitness function to be minimized is a set of closed loop performance metrics (the settling time, the rise time, the overshoot and the variance of the control signal). In order to verify the validity of the proposed strategy, a simulation example of asynchronous motor speed is presented. The obtained results shows the effectiveness of this approach.
{"title":"Optimization of synthesis parameters of adaptive generalized predictive control using genetic algorithms","authors":"Abdelaziz Mouhou, A. Badri, A. Ballouk, Y. Sayouti","doi":"10.1145/3128128.3128150","DOIUrl":"https://doi.org/10.1145/3128128.3128150","url":null,"abstract":"This paper concentrates on the off-line optimization of adaptive generalized predictive control (AGPC) tuning parameters using genetic algorithms (GAs). The Adaptive generalized predictive control algorithm is detailed and presented. A single input single output (SISO) controlled autoregressive integrated moving average (CARIMA) model is used to predict the future behavior of the system. The online parametric adaptation algorithm (PAA) used in this work is based on recursive least squares (RLS) identification algorithm with fixed forgetting factor. The synthesis parameters (minimal prediction horizon, maximal prediction horizon, control horizon and cost weighting factor) are optimized using genetic algorithms, this technique improves the closed-loop performances. The fitness function to be minimized is a set of closed loop performance metrics (the settling time, the rise time, the overshoot and the variance of the control signal). In order to verify the validity of the proposed strategy, a simulation example of asynchronous motor speed is presented. The obtained results shows the effectiveness of this approach.","PeriodicalId":362403,"journal":{"name":"Proceedings of the 2017 International Conference on Smart Digital Environment","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128523182","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}
Mounir El Mejjatti, A. Habbani, Bilal Essaid, Hicham Amraoui
Behavior of the propagation medium in reaction with electromagnetic fields is described by its dielectric permittivity; this electric property is a function of the physical characteristics of the medium and those of the propagating wave. Among the parameters, which considerably affect the dielectric permittivity of a medium, its water content. In fact, when the snow wetness varies from 0 to 50% in the melting layer, real part of the mixture permittivity varies from 1.47 to 5.86. Similarly, when soil moisture varies from 0 to 40% real and imaginary parts of effective permittivity of soil, air and water mixture vary from 4.13 to 24.85 and from 0 to 3.44 respectively. This dynamism in the permittivity as a function of the humidity is able to alter the efficiency of the antenna within the application. In this paper, we propose a study to analyze the impact of wetness on the performance of a dipole antenna with central frequency of 900 MHz. The study was carried out by simulating the behavior of the dipole antenna model in Finite Element Method (FEM) full wave simulator with different values of the water content of two propagation mediums: melting layer and soil. Simulation results concerning the resonant frequency, bandwidth, directivity are presented through paragraphs of the paper.
{"title":"Moisture vulnerability of antenna operation in UHF band","authors":"Mounir El Mejjatti, A. Habbani, Bilal Essaid, Hicham Amraoui","doi":"10.1145/3128128.3128138","DOIUrl":"https://doi.org/10.1145/3128128.3128138","url":null,"abstract":"Behavior of the propagation medium in reaction with electromagnetic fields is described by its dielectric permittivity; this electric property is a function of the physical characteristics of the medium and those of the propagating wave. Among the parameters, which considerably affect the dielectric permittivity of a medium, its water content. In fact, when the snow wetness varies from 0 to 50% in the melting layer, real part of the mixture permittivity varies from 1.47 to 5.86. Similarly, when soil moisture varies from 0 to 40% real and imaginary parts of effective permittivity of soil, air and water mixture vary from 4.13 to 24.85 and from 0 to 3.44 respectively. This dynamism in the permittivity as a function of the humidity is able to alter the efficiency of the antenna within the application. In this paper, we propose a study to analyze the impact of wetness on the performance of a dipole antenna with central frequency of 900 MHz. The study was carried out by simulating the behavior of the dipole antenna model in Finite Element Method (FEM) full wave simulator with different values of the water content of two propagation mediums: melting layer and soil. Simulation results concerning the resonant frequency, bandwidth, directivity are presented through paragraphs of the paper.","PeriodicalId":362403,"journal":{"name":"Proceedings of the 2017 International Conference on Smart Digital Environment","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124068480","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}
This paper presents a method two segment moving objects from video sequences by combining spatial and temporal information. The segmentation is performed in two steps : automatic seeds detection, and random walk segmentation. In the first step, seeds are detected by using optical flow in specific pixels so in every d × d grid there is one pixel to represent the grid, then initial seeds are chosen automatically by thresholding the distance of estimated motion vector of the sparse pixels. In the second step, we treat our motion segmentation as a graph based problem, then an energy function is defined to evaluate spatial and temporal smoothness, and we apply random walk algorithm to solve the energy minimization problem, the solution leads to affecting a label to every pixel in sequences video and get the final segmentation. The experimental results illustrate its promising performance and can be integrated in real-time application.
{"title":"Automatic motion segmentation using random walks","authors":"Idir Boulfrifi, K. Housni, A. Mouloudi","doi":"10.1145/3128128.3128139","DOIUrl":"https://doi.org/10.1145/3128128.3128139","url":null,"abstract":"This paper presents a method two segment moving objects from video sequences by combining spatial and temporal information. The segmentation is performed in two steps : automatic seeds detection, and random walk segmentation. In the first step, seeds are detected by using optical flow in specific pixels so in every d × d grid there is one pixel to represent the grid, then initial seeds are chosen automatically by thresholding the distance of estimated motion vector of the sparse pixels. In the second step, we treat our motion segmentation as a graph based problem, then an energy function is defined to evaluate spatial and temporal smoothness, and we apply random walk algorithm to solve the energy minimization problem, the solution leads to affecting a label to every pixel in sequences video and get the final segmentation. The experimental results illustrate its promising performance and can be integrated in real-time application.","PeriodicalId":362403,"journal":{"name":"Proceedings of the 2017 International Conference on Smart Digital Environment","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127953363","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}
Ayoub Bahnasse, M. Talea, Fatima Ezzahraa Louhab, Sara Laafar, Adel Harbi, Azeddine Khiat
IP Multimedia Subsystem (IMS) is a standardized Next Generation Network (NGN) architecture, used to provide users access to different services even in case of roaming. Although this architecture is deployed in cellular (mobile) networks, the latter represents several limitations, notably in terms of security. To overcome this inadequacy, IPsec protocol can be deployed between user equipment (UE) and Proxy Call Session Control Functions (P-CSCF). This solution has certain limitations in terms of reliability, i.e. the same security policy deployed between UE and P-CSCF will be applied to any type of the client traffic. In other words, if network performances are critical and the security policy deployed requires high processing, the transported traffic of real-time characteristic will suffer from a quality deterioration. In this work, we propose a new approach for the adaptive management of the IPsec protocol for IMS architectures, called Smart Adaptive Security for IMS, an acronym for SAS-IMS.
{"title":"SAS-IMS for smart mobile security in IP multimedia subsystem","authors":"Ayoub Bahnasse, M. Talea, Fatima Ezzahraa Louhab, Sara Laafar, Adel Harbi, Azeddine Khiat","doi":"10.1145/3128128.3128134","DOIUrl":"https://doi.org/10.1145/3128128.3128134","url":null,"abstract":"IP Multimedia Subsystem (IMS) is a standardized Next Generation Network (NGN) architecture, used to provide users access to different services even in case of roaming. Although this architecture is deployed in cellular (mobile) networks, the latter represents several limitations, notably in terms of security. To overcome this inadequacy, IPsec protocol can be deployed between user equipment (UE) and Proxy Call Session Control Functions (P-CSCF). This solution has certain limitations in terms of reliability, i.e. the same security policy deployed between UE and P-CSCF will be applied to any type of the client traffic. In other words, if network performances are critical and the security policy deployed requires high processing, the transported traffic of real-time characteristic will suffer from a quality deterioration. In this work, we propose a new approach for the adaptive management of the IPsec protocol for IMS architectures, called Smart Adaptive Security for IMS, an acronym for SAS-IMS.","PeriodicalId":362403,"journal":{"name":"Proceedings of the 2017 International Conference on Smart Digital Environment","volume":"86 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132536227","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}
This work addresses the problem inherent in internal induction motor parameters variation during the operation, which significantly degrades the performance of a direct torque controlled (DTC-SVM), DTC-SVM scheme is the alternative to the classical DTC schemes based on space vector modulation (SVM) strategy that minimizes the torque ripples is introduced in the first part of this work. In order to overcome these disturbances, we present in the second part of this paper a new robust command called Active disturbance rejection control (ADRC) which has been acquired an important concern of researchers and developed to ensure good dynamic performance of induction machine. ADRC can precisely estimate the derivative signals owing to extended state observer (ESO), the basic element of ADRC and accurate decoupling of induction motor is attained. The third part of the paper deals with the description of an Advanced SM-MRAS observer based on a combination of sliding mode designed for speed estimation is investigated in this work. In the last part, the proposed schemes shown in simulation results demonstrate the good efficiency, adaptability and robustness of sensorless induction motor against the internal as well as the external disturbances.
{"title":"DTC-SVM based on active disturbance rejection control applied on sensorless induction motor","authors":"Chalawane Haitam, A. Essadki, Nasser Tamou","doi":"10.1145/3128128.3128148","DOIUrl":"https://doi.org/10.1145/3128128.3128148","url":null,"abstract":"This work addresses the problem inherent in internal induction motor parameters variation during the operation, which significantly degrades the performance of a direct torque controlled (DTC-SVM), DTC-SVM scheme is the alternative to the classical DTC schemes based on space vector modulation (SVM) strategy that minimizes the torque ripples is introduced in the first part of this work. In order to overcome these disturbances, we present in the second part of this paper a new robust command called Active disturbance rejection control (ADRC) which has been acquired an important concern of researchers and developed to ensure good dynamic performance of induction machine. ADRC can precisely estimate the derivative signals owing to extended state observer (ESO), the basic element of ADRC and accurate decoupling of induction motor is attained. The third part of the paper deals with the description of an Advanced SM-MRAS observer based on a combination of sliding mode designed for speed estimation is investigated in this work. In the last part, the proposed schemes shown in simulation results demonstrate the good efficiency, adaptability and robustness of sensorless induction motor against the internal as well as the external disturbances.","PeriodicalId":362403,"journal":{"name":"Proceedings of the 2017 International Conference on Smart Digital Environment","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117277253","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 use of water quality sensors for the prediction of the coupling of urban food, energy and water (FEW) subsystems is discussed. A high level model of FEW coupling is presented. The role of fine grained sensing in determination of system coupling is introduced. An archetypical water quality sensing element is demonstrated and calibrated. A physical model for an environmentally stressed water system is presented. Sensor calibration data is applied to the problem of using an array of a water quality sensors for determining system stressors and thereby FEW couplings. The requirements for resource management derived from smart city control system data and FEW system coupling is discussed.
{"title":"Water quality sensors for smart cities","authors":"A. Mickelson, Daniel Tsvankin","doi":"10.1145/3128128.3129386","DOIUrl":"https://doi.org/10.1145/3128128.3129386","url":null,"abstract":"The use of water quality sensors for the prediction of the coupling of urban food, energy and water (FEW) subsystems is discussed. A high level model of FEW coupling is presented. The role of fine grained sensing in determination of system coupling is introduced. An archetypical water quality sensing element is demonstrated and calibrated. A physical model for an environmentally stressed water system is presented. Sensor calibration data is applied to the problem of using an array of a water quality sensors for determining system stressors and thereby FEW couplings. The requirements for resource management derived from smart city control system data and FEW system coupling is discussed.","PeriodicalId":362403,"journal":{"name":"Proceedings of the 2017 International Conference on Smart Digital Environment","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131933562","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 use of renewable energies has grown significantly in the world. Given the growing demand for electrical energy. In this paper we discuss the optimization of the production of a GPV by two different techniques MPPT. In order to make a full operation of photovoltaic array, its compulsory to inaugurate a protocol or an algorithm to help extract, track and maximize the available power, this technique is called Maximum Power Point Tracking (MPPT).A several number of technique has been presented, such as the classic techniques; Perturb and Observe (P&O) [1], and incremental conductance [2], which are largely used mostly due to their simplicity of implementation and less complexity. In this paper, a Fuzzy Logic Controller (FLC) based MPPT technique [3] is compared to conventional P&O technique. The simulation in MATLAB/Simulink environment reveals the superior performance of FLC based technique over P&O method.
{"title":"Maximum power point tracking using fuzzy logic based controllers compared to P&O technique in photovoltaic generator","authors":"Manari Otmane, Zazi Malika, Chtouki Ihssane","doi":"10.1145/3128128.3128149","DOIUrl":"https://doi.org/10.1145/3128128.3128149","url":null,"abstract":"The use of renewable energies has grown significantly in the world. Given the growing demand for electrical energy. In this paper we discuss the optimization of the production of a GPV by two different techniques MPPT. In order to make a full operation of photovoltaic array, its compulsory to inaugurate a protocol or an algorithm to help extract, track and maximize the available power, this technique is called Maximum Power Point Tracking (MPPT).A several number of technique has been presented, such as the classic techniques; Perturb and Observe (P&O) [1], and incremental conductance [2], which are largely used mostly due to their simplicity of implementation and less complexity. In this paper, a Fuzzy Logic Controller (FLC) based MPPT technique [3] is compared to conventional P&O technique. The simulation in MATLAB/Simulink environment reveals the superior performance of FLC based technique over P&O method.","PeriodicalId":362403,"journal":{"name":"Proceedings of the 2017 International Conference on Smart Digital Environment","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130908822","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}
Generally, the user preferences change over time which implies the need to adapt the recommendation technique used in order to recommend pertinent items. For this reason, in this paper we propose a meta-recommender that follows the change of user's interests over time to propose the appropriate recommendation technique. The proposed approach is based on meta-knowledge called explanation and a hybrid approach, and has two main phases: the first phase is to fill the meta-knowledge database with explanations using a hybrid recommendation approach. In the second phase, we calculate the average of each explanation for a user to determine the recommendation technique to use.
{"title":"Meta-recommender approach using meta-knowledge","authors":"Nadia Boufardi, O. Baida, A. Sedqui, A. Lyhyaoui","doi":"10.1145/3128128.3128153","DOIUrl":"https://doi.org/10.1145/3128128.3128153","url":null,"abstract":"Generally, the user preferences change over time which implies the need to adapt the recommendation technique used in order to recommend pertinent items. For this reason, in this paper we propose a meta-recommender that follows the change of user's interests over time to propose the appropriate recommendation technique. The proposed approach is based on meta-knowledge called explanation and a hybrid approach, and has two main phases: the first phase is to fill the meta-knowledge database with explanations using a hybrid recommendation approach. In the second phase, we calculate the average of each explanation for a user to determine the recommendation technique to use.","PeriodicalId":362403,"journal":{"name":"Proceedings of the 2017 International Conference on Smart Digital Environment","volume":"237 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114818781","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}
Taoufiq Zarra, R. Chiheb, Rajae Moumen, R. Faizi, A. E. Afia
Recently, the multiplication of communication and sharing platforms such as social networks, personal blogs, forums, etc., has facilitated the expression of views and opinions about products, personalities, and public policy. However, gathering these points of view is a complex task that requires resolution of many problems in different disciplines, especially issues related to our language. Among the research areas, topic modeling and sentiment analysis stimulates interest and curiosity of the scientific community. Lately, the current economic, geo-political and geostrategic trends have made researchers specifically more interested in Arabic language, except that the majority of these studies focus on the classical Arabic; nevertheless it is a language of the elites which is different from what is mainly used on the Web. Our paper focuses on Maghrebi colloquial Arabic since the little research that exists in this area is limited to East colloquial Arabic. On a corpus extracted from different Facebook pages we implemented a supervised approach to extract the sentiments, and an unsupervised approach to extract topic, then we proposed a new, semi-supervised, approach in the Arabic language that combines the topic and the sentiment in a single model, in order to join each topic to a specific sentiment.
{"title":"Topic and sentiment model applied to the colloquial Arabic: a case study of Maghrebi Arabic","authors":"Taoufiq Zarra, R. Chiheb, Rajae Moumen, R. Faizi, A. E. Afia","doi":"10.1145/3128128.3128155","DOIUrl":"https://doi.org/10.1145/3128128.3128155","url":null,"abstract":"Recently, the multiplication of communication and sharing platforms such as social networks, personal blogs, forums, etc., has facilitated the expression of views and opinions about products, personalities, and public policy. However, gathering these points of view is a complex task that requires resolution of many problems in different disciplines, especially issues related to our language. Among the research areas, topic modeling and sentiment analysis stimulates interest and curiosity of the scientific community. Lately, the current economic, geo-political and geostrategic trends have made researchers specifically more interested in Arabic language, except that the majority of these studies focus on the classical Arabic; nevertheless it is a language of the elites which is different from what is mainly used on the Web. Our paper focuses on Maghrebi colloquial Arabic since the little research that exists in this area is limited to East colloquial Arabic. On a corpus extracted from different Facebook pages we implemented a supervised approach to extract the sentiments, and an unsupervised approach to extract topic, then we proposed a new, semi-supervised, approach in the Arabic language that combines the topic and the sentiment in a single model, in order to join each topic to a specific sentiment.","PeriodicalId":362403,"journal":{"name":"Proceedings of the 2017 International Conference on Smart Digital Environment","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129273531","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：