Pub Date : 2019-04-01DOI: 10.1109/IranianCEE.2019.8786557
Reza Razmand, Mehrdad Naemi Dehkharghani, Alireza Karimpour, F. Hossein-Babaei
Layers of graphene oxide (GO) deposited on various substrates have been investigated for their capacitive and resistive features. It has been shown that such layers demonstrate large specific capacitances. Here we report the fabrication of a first GO-on-textile capacitive humidity sensor. GO layers are deposited on aluminum silicate textile, and the impedances of the deposits are measured at different atmospheric conditions using various voltage sweeping frequencies. The results demonstrate the dependence of the layer impedance on the humidity level in the surrounding atmosphere. Further, it is clarified that the layer capacitance is humidity dependent. A capacitive humidity sensor is designed and fabricated. The capacitance of a typical device varies from 130 pF, measured in dry synthetic air, to 5000 pF measured in air with 95% relative humidity (RH). Interestingly, these high sensitivities are measured at low frequencies (f=0.01 Hz); sensitivity to humidity decreases as the voltage sweeping frequency increase. For the first time, it is shown that the sensitivity of these capacitive humidity sensors considerably increase when very low frequencies are used for capacitance measurement. The ratio of the capacitance at RH= 95% to the capacitance at RH < 0.1% both measured at 0.01 Hz is 32 times larger than the same calculated at 100 Hz. The device is suitable for wearable electronic applications.
{"title":"A Graphene Oxide-Based Humidity Sensor for Wearable Electronic","authors":"Reza Razmand, Mehrdad Naemi Dehkharghani, Alireza Karimpour, F. Hossein-Babaei","doi":"10.1109/IranianCEE.2019.8786557","DOIUrl":"https://doi.org/10.1109/IranianCEE.2019.8786557","url":null,"abstract":"Layers of graphene oxide (GO) deposited on various substrates have been investigated for their capacitive and resistive features. It has been shown that such layers demonstrate large specific capacitances. Here we report the fabrication of a first GO-on-textile capacitive humidity sensor. GO layers are deposited on aluminum silicate textile, and the impedances of the deposits are measured at different atmospheric conditions using various voltage sweeping frequencies. The results demonstrate the dependence of the layer impedance on the humidity level in the surrounding atmosphere. Further, it is clarified that the layer capacitance is humidity dependent. A capacitive humidity sensor is designed and fabricated. The capacitance of a typical device varies from 130 pF, measured in dry synthetic air, to 5000 pF measured in air with 95% relative humidity (RH). Interestingly, these high sensitivities are measured at low frequencies (f=0.01 Hz); sensitivity to humidity decreases as the voltage sweeping frequency increase. For the first time, it is shown that the sensitivity of these capacitive humidity sensors considerably increase when very low frequencies are used for capacitance measurement. The ratio of the capacitance at RH= 95% to the capacitance at RH < 0.1% both measured at 0.01 Hz is 32 times larger than the same calculated at 100 Hz. The device is suitable for wearable electronic applications.","PeriodicalId":6683,"journal":{"name":"2019 27th Iranian Conference on Electrical Engineering (ICEE)","volume":"83 1","pages":"423-426"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76512411","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 : 2019-04-01DOI: 10.1109/IranianCEE.2019.8786688
Maryam Masoumi Estahbanati, G. Mirjalily
One of the most important tasks of the wireless terminals in heterogeneous wireless environments is selecting the best available network based on the quality of services. Considering the fact that multimedia applications are known to be high energy consumers and since the battery lifetime is an important factor for mobile users, multimedia wireless communication is the most challenging issue in the network selection. Enhanced power-friendly access network selection (E-POFANS) has been introduced to maintain an acceptable user perceived quality by selecting the network that consumes minimum energy. In this paper, to improve E-POFANS, the networks' behavior in the past is considered as a metric for network selection. Also, a mechanism to monitor the energy consumption of the mobile device is devised to guarantee that the multimedia stream is played the whole lot before the battery lifetime is finished. This solution achieves about 29% energy saving in comparison with E-POFANS. Through different simulations, we show that the proposed solutions improve the energy consumption and user's throughput, considerably.
{"title":"History-based Network Selection in Heterogeneous Wireless Multimedia Networks","authors":"Maryam Masoumi Estahbanati, G. Mirjalily","doi":"10.1109/IranianCEE.2019.8786688","DOIUrl":"https://doi.org/10.1109/IranianCEE.2019.8786688","url":null,"abstract":"One of the most important tasks of the wireless terminals in heterogeneous wireless environments is selecting the best available network based on the quality of services. Considering the fact that multimedia applications are known to be high energy consumers and since the battery lifetime is an important factor for mobile users, multimedia wireless communication is the most challenging issue in the network selection. Enhanced power-friendly access network selection (E-POFANS) has been introduced to maintain an acceptable user perceived quality by selecting the network that consumes minimum energy. In this paper, to improve E-POFANS, the networks' behavior in the past is considered as a metric for network selection. Also, a mechanism to monitor the energy consumption of the mobile device is devised to guarantee that the multimedia stream is played the whole lot before the battery lifetime is finished. This solution achieves about 29% energy saving in comparison with E-POFANS. Through different simulations, we show that the proposed solutions improve the energy consumption and user's throughput, considerably.","PeriodicalId":6683,"journal":{"name":"2019 27th Iranian Conference on Electrical Engineering (ICEE)","volume":"1 1","pages":"1408-1412"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80206477","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 : 2019-04-01DOI: 10.1109/IranianCEE.2019.8786567
Ehsan Rashidi-Ranjbar, M. Dehmollaian
Single-shot computational microwave imaging of a target is obtained using a frequency-diverse aperture. The idea is to use random rough surfaces to generate random scatterings at various frequencies. Radiation from a conducting rough reflector, normally illuminated by an ultrawideband antenna working within 20–45 GHz frequency range provides random patterns at various frequencies. To offer as much spatially uncorrelated near-field scans as possible four conducting walls are placed around the rough surface. Scattering is calculated using geometrical optics approximation that takes into account multiple interactions. Applying the standard back-projection method and the least-squares reconstruction technique, it is shown that for a 1 square meter image size, by using 801 frequency samples a descent focused image with a pixel size of about 1/801 square meters is realizable.
{"title":"Microwave Imaging Using Frequency-Diverse Scattering of a Random Rough surface","authors":"Ehsan Rashidi-Ranjbar, M. Dehmollaian","doi":"10.1109/IranianCEE.2019.8786567","DOIUrl":"https://doi.org/10.1109/IranianCEE.2019.8786567","url":null,"abstract":"Single-shot computational microwave imaging of a target is obtained using a frequency-diverse aperture. The idea is to use random rough surfaces to generate random scatterings at various frequencies. Radiation from a conducting rough reflector, normally illuminated by an ultrawideband antenna working within 20–45 GHz frequency range provides random patterns at various frequencies. To offer as much spatially uncorrelated near-field scans as possible four conducting walls are placed around the rough surface. Scattering is calculated using geometrical optics approximation that takes into account multiple interactions. Applying the standard back-projection method and the least-squares reconstruction technique, it is shown that for a 1 square meter image size, by using 801 frequency samples a descent focused image with a pixel size of about 1/801 square meters is realizable.","PeriodicalId":6683,"journal":{"name":"2019 27th Iranian Conference on Electrical Engineering (ICEE)","volume":"158 1","pages":"1679-1681"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79967272","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 : 2019-04-01DOI: 10.1109/IranianCEE.2019.8786722
Mahmoud Tayebi, A. Dastranj, A. Alighanbari
In this paper, a tapered triangular corrugated edge antipodal vivaldi antenna (TTCE-AVA) is presented. The total size of the antenna is 49.5 × 57 mm2and it operates in a bandwidth of almost five octaves, from 1.3GHz to 44GHz. The introduced technique will result in ultra-wide bandwidth while having a small size compare to other works. To achieve this, first, a minimum-size conventional antipodal vivaldi antenna (CAVA) is designed, with respect to the tradeoff between the lowest operating frequency and the substrate dielectric constant. Then, the low end operating frequency is extended and the gain over the entire frequency bandwidth was enhanced, by adding two circular-shape loads (CL) to the CAVA. The reflection coefficient of the resulting CL-AVA is then improved, by applying a tapered triangular corrugation at the edges (TTCE) of the circular sections. The resulting TTCE-AVA is manufactured and tested. The simulation and experimental results demonstrate excellent performance in an ultra-wide frequency band from 1.3 to 44 GHz.
{"title":"Ultra Wide Band Antipodal Vivaldi Antenna with Tapered Triangular Corrugated Edges","authors":"Mahmoud Tayebi, A. Dastranj, A. Alighanbari","doi":"10.1109/IranianCEE.2019.8786722","DOIUrl":"https://doi.org/10.1109/IranianCEE.2019.8786722","url":null,"abstract":"In this paper, a tapered triangular corrugated edge antipodal vivaldi antenna (TTCE-AVA) is presented. The total size of the antenna is 49.5 × 57 mm2and it operates in a bandwidth of almost five octaves, from 1.3GHz to 44GHz. The introduced technique will result in ultra-wide bandwidth while having a small size compare to other works. To achieve this, first, a minimum-size conventional antipodal vivaldi antenna (CAVA) is designed, with respect to the tradeoff between the lowest operating frequency and the substrate dielectric constant. Then, the low end operating frequency is extended and the gain over the entire frequency bandwidth was enhanced, by adding two circular-shape loads (CL) to the CAVA. The reflection coefficient of the resulting CL-AVA is then improved, by applying a tapered triangular corrugation at the edges (TTCE) of the circular sections. The resulting TTCE-AVA is manufactured and tested. The simulation and experimental results demonstrate excellent performance in an ultra-wide frequency band from 1.3 to 44 GHz.","PeriodicalId":6683,"journal":{"name":"2019 27th Iranian Conference on Electrical Engineering (ICEE)","volume":"109 1","pages":"1637-1642"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80528522","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 : 2019-04-01DOI: 10.1109/IranianCEE.2019.8786405
S. Hamedi, A. Gharavi
In this paper, polymer-based channel waveguides on azo chromophores with direct-laser writing technique is presented. The waveguides were written with a low power continuous-wave 532 nm laser in the absorption spectrum of the polymer. The optical properties of the waveguide were analyzed. The experimental results showed that the written waveguides have Gaussian refractive index profile in the lateral direction. It was shown that the refractive index of the waveguide have linear relation to the writing laser power. From the ATR spectrum we measured a difference of about 0.009 in the index between waveguide and slab which is given by slight angle shift in the coupled modes.
{"title":"Polymer-Based Channel Waveguides with Direct-Laser Writing Technique","authors":"S. Hamedi, A. Gharavi","doi":"10.1109/IranianCEE.2019.8786405","DOIUrl":"https://doi.org/10.1109/IranianCEE.2019.8786405","url":null,"abstract":"In this paper, polymer-based channel waveguides on azo chromophores with direct-laser writing technique is presented. The waveguides were written with a low power continuous-wave 532 nm laser in the absorption spectrum of the polymer. The optical properties of the waveguide were analyzed. The experimental results showed that the written waveguides have Gaussian refractive index profile in the lateral direction. It was shown that the refractive index of the waveguide have linear relation to the writing laser power. From the ATR spectrum we measured a difference of about 0.009 in the index between waveguide and slab which is given by slight angle shift in the coupled modes.","PeriodicalId":6683,"journal":{"name":"2019 27th Iranian Conference on Electrical Engineering (ICEE)","volume":"26 1","pages":"15-17"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81686064","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 : 2019-04-01DOI: 10.1109/IranianCEE.2019.8786513
M. Montazeri, Elahe Rezaeifard, Pouya Abbasi
Heat recovery steam generator (HRSG) boiler is one of the main components of combined cycle power plants that its proper and safe operation is subject to drum level being in a specified range. In this paper, an application of ANFIS structure is presented for modeling the dynamic behavior of IP drum level changes of Qom Combined Cycle Power Plant, with emphasis on accurate modeling of its transient behavior in order to improve the transient response and consequently prevent steam unit from tripping. Next, the response of the developed model is compared with the experimental data to validate its accuracy. Then, a self-tuning PID controller based on BP neural network is developed to control the drum level changes. Simulation results show improved performance of this controller in terms of less overshoot and settling time, compared to the classic PID controller used in Qom power plant.
{"title":"Adaptive Neuro-Fuzzy Modeling and Control of IP Drum Level of a Power Plant for Improving Transient Response","authors":"M. Montazeri, Elahe Rezaeifard, Pouya Abbasi","doi":"10.1109/IranianCEE.2019.8786513","DOIUrl":"https://doi.org/10.1109/IranianCEE.2019.8786513","url":null,"abstract":"Heat recovery steam generator (HRSG) boiler is one of the main components of combined cycle power plants that its proper and safe operation is subject to drum level being in a specified range. In this paper, an application of ANFIS structure is presented for modeling the dynamic behavior of IP drum level changes of Qom Combined Cycle Power Plant, with emphasis on accurate modeling of its transient behavior in order to improve the transient response and consequently prevent steam unit from tripping. Next, the response of the developed model is compared with the experimental data to validate its accuracy. Then, a self-tuning PID controller based on BP neural network is developed to control the drum level changes. Simulation results show improved performance of this controller in terms of less overshoot and settling time, compared to the classic PID controller used in Qom power plant.","PeriodicalId":6683,"journal":{"name":"2019 27th Iranian Conference on Electrical Engineering (ICEE)","volume":"63 1","pages":"944-950"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82027826","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 : 2019-04-01DOI: 10.1109/IranianCEE.2019.8786583
Mozhdeh Doustali, Mohammad Zoofaghari, H. Arjmandi
Diffusive Molecular Communication (DMC) is considered as a promising approach to realize information exchange among nanomachines in biological environments, particularly for healthcare applications. Inspired by structure of blood vessel clogged partially by a blockage (e.g. due to atherosclerosis disease), a DMC system in a partially blocked biological cylinder is considered in this paper. Diffusive information molecules in the fluid medium are assumed to be exposed to biological receptors on the boundary, degradation reaction, and constant flow. The channel impulse response (CIR) for a point-to-point DMC system is numerically analyzed employing COMSOL Multiphysics tool as a finite-element solver. The impact of different system parameters on the CIR is examined. Our results reveal that the blockage significantly affects the CIR in the biological cylinder which may be employed by nanomachines for detection and characterization of the blockage in the blood vessels.
{"title":"Diffusive Molecular Communication in Partially Blocked Cylindrical Environment","authors":"Mozhdeh Doustali, Mohammad Zoofaghari, H. Arjmandi","doi":"10.1109/IranianCEE.2019.8786583","DOIUrl":"https://doi.org/10.1109/IranianCEE.2019.8786583","url":null,"abstract":"Diffusive Molecular Communication (DMC) is considered as a promising approach to realize information exchange among nanomachines in biological environments, particularly for healthcare applications. Inspired by structure of blood vessel clogged partially by a blockage (e.g. due to atherosclerosis disease), a DMC system in a partially blocked biological cylinder is considered in this paper. Diffusive information molecules in the fluid medium are assumed to be exposed to biological receptors on the boundary, degradation reaction, and constant flow. The channel impulse response (CIR) for a point-to-point DMC system is numerically analyzed employing COMSOL Multiphysics tool as a finite-element solver. The impact of different system parameters on the CIR is examined. Our results reveal that the blockage significantly affects the CIR in the biological cylinder which may be employed by nanomachines for detection and characterization of the blockage in the blood vessels.","PeriodicalId":6683,"journal":{"name":"2019 27th Iranian Conference on Electrical Engineering (ICEE)","volume":"2016 1","pages":"1704-1709"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87780971","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 : 2019-04-01DOI: 10.1109/IranianCEE.2019.8786749
Mojtaba Hadi Barhaghtalab, Saleh Mobayen, Farshad Merrikh-Bavat
In this research, an LMI-based global sliding mode controller law with a novel switching function for the sliding surface using hyperbolic functions is presented and is used for stabilization and robustness of three-dimensional nonlinear systems with uncertainty. The asymptotic stability of the system's state variables is guaranteed by Linear Matrix Inequality (LMI) and furthermore, considering the uncertainty and nonlinear terms, the reaching phase of the sliding surface is deleted. Finally, the proposed control technique is implemented on Genesio-Tesi chaotic system and the results of the simulation are analyzed.
{"title":"Design of a Global Sliding Mode Controller Using Hyperbolic Functions for Nonlinear Systems and Application in Chaotic Systems","authors":"Mojtaba Hadi Barhaghtalab, Saleh Mobayen, Farshad Merrikh-Bavat","doi":"10.1109/IranianCEE.2019.8786749","DOIUrl":"https://doi.org/10.1109/IranianCEE.2019.8786749","url":null,"abstract":"In this research, an LMI-based global sliding mode controller law with a novel switching function for the sliding surface using hyperbolic functions is presented and is used for stabilization and robustness of three-dimensional nonlinear systems with uncertainty. The asymptotic stability of the system's state variables is guaranteed by Linear Matrix Inequality (LMI) and furthermore, considering the uncertainty and nonlinear terms, the reaching phase of the sliding surface is deleted. Finally, the proposed control technique is implemented on Genesio-Tesi chaotic system and the results of the simulation are analyzed.","PeriodicalId":6683,"journal":{"name":"2019 27th Iranian Conference on Electrical Engineering (ICEE)","volume":"1614 1","pages":"1030-1034"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86510277","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 : 2019-04-01DOI: 10.1109/IranianCEE.2019.8786587
Negar Mashhadi Seyyed Abadi, M. Banihashemi, A. Kashaninia
In perovskite solar cells, (FAPbI3)0.85(MAPbBr3)0.15as absorber layer has resulted in high stability over 1000 h under real outdoor conditions. In this paper, we used solar cell capacitance simulator (SCAPS-1D) to study the effect of various bandgaps and electron affinities of hole/electron transport material layers (HTM/ETM) on Voc, Jsc, fill factor (FF), and power conversion efficiency (PCE). This study defines the proper values of HTM/ETM bandgaps and electron affinities to have high PCE.
{"title":"Simulation and Analysis of a Perovskite Solar Cell with (FAPbI3)0.85(MAPbBr3)0.15 as Absorber Layer","authors":"Negar Mashhadi Seyyed Abadi, M. Banihashemi, A. Kashaninia","doi":"10.1109/IranianCEE.2019.8786587","DOIUrl":"https://doi.org/10.1109/IranianCEE.2019.8786587","url":null,"abstract":"In perovskite solar cells, (FAPbI<inf>3</inf>)<inf>0.85</inf>(MAPbBr<inf>3</inf>)<inf>0.15</inf>as absorber layer has resulted in high stability over 1000 h under real outdoor conditions. In this paper, we used solar cell capacitance simulator (SCAPS-1D) to study the effect of various bandgaps and electron affinities of hole/electron transport material layers (HTM/ETM) on V<inf>oc</inf>, J<inf>sc</inf>, fill factor (FF), and power conversion efficiency (PCE). This study defines the proper values of HTM/ETM bandgaps and electron affinities to have high PCE.","PeriodicalId":6683,"journal":{"name":"2019 27th Iranian Conference on Electrical Engineering (ICEE)","volume":"27 1","pages":"173-177"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87648021","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 : 2019-04-01DOI: 10.1109/IranianCEE.2019.8786690
S. Masoudian, V. Derhami, S. Zarifzadeh
Hierarchical text categorization is used in many real-world applications, such as webpage topic classification and product categorization. Large quantities of labeled training data are needed to build an accurate hierarchical classification model. However, labeled samples are difficult and very time-consuming to obtain. On the other hand, due to the expansion of the Internet, plenty of unlabeled documents are available. In this paper, we propose a top-down method to hierarchically categorize partially labeled documents (having labeled documents only at first few levels of the hierarchy) using “local classifier per parent node” approach. We utilize a classification algorithm for the parent nodes with training data available. We use a labeling strategy for other parent nodes that do not have labeled data to be able to train a classifier. In our knowledge, this is the first study on hierarchical Persian text categorization, and our experiments show that the proposed approach achieves an acceptable performance.
{"title":"Hierarchical Persian Text Categorization in Absence of Labeled Data","authors":"S. Masoudian, V. Derhami, S. Zarifzadeh","doi":"10.1109/IranianCEE.2019.8786690","DOIUrl":"https://doi.org/10.1109/IranianCEE.2019.8786690","url":null,"abstract":"Hierarchical text categorization is used in many real-world applications, such as webpage topic classification and product categorization. Large quantities of labeled training data are needed to build an accurate hierarchical classification model. However, labeled samples are difficult and very time-consuming to obtain. On the other hand, due to the expansion of the Internet, plenty of unlabeled documents are available. In this paper, we propose a top-down method to hierarchically categorize partially labeled documents (having labeled documents only at first few levels of the hierarchy) using “local classifier per parent node” approach. We utilize a classification algorithm for the parent nodes with training data available. We use a labeling strategy for other parent nodes that do not have labeled data to be able to train a classifier. In our knowledge, this is the first study on hierarchical Persian text categorization, and our experiments show that the proposed approach achieves an acceptable performance.","PeriodicalId":6683,"journal":{"name":"2019 27th Iranian Conference on Electrical Engineering (ICEE)","volume":"53 1","pages":"1951-1955"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89840175","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：