Recent advanced 3D technologies have increased availability of 3D geospatial data. With this trend, new opportunities for creating geospatial-based realistic 3D digital contents are emerging. Among the various options, 3D city models are in particular demand from various domains. Many developed countries have transitioned from 2D to 3D city models including Korea. 3D city models using high-resolution geospatial information can be constructed simulating the real world by incorporating into them virtual reality or augmented reality. In this paper, we seek to understand the methodologies currently used to create 3D city models and present our planned research directions based on current trends. In addition, we briefly present our current implementation of Web 3D service (W3DS) according to the Open Geospatial Consortium (OGC) standards, as part of services essential to develop high-resolution 3D city models.
{"title":"Workflow for Developing High-Resolution 3D City Models in Korea","authors":"Junghee Jo, Insung Jang","doi":"10.1145/3177457.3177505","DOIUrl":"https://doi.org/10.1145/3177457.3177505","url":null,"abstract":"Recent advanced 3D technologies have increased availability of 3D geospatial data. With this trend, new opportunities for creating geospatial-based realistic 3D digital contents are emerging. Among the various options, 3D city models are in particular demand from various domains. Many developed countries have transitioned from 2D to 3D city models including Korea. 3D city models using high-resolution geospatial information can be constructed simulating the real world by incorporating into them virtual reality or augmented reality. In this paper, we seek to understand the methodologies currently used to create 3D city models and present our planned research directions based on current trends. In addition, we briefly present our current implementation of Web 3D service (W3DS) according to the Open Geospatial Consortium (OGC) standards, as part of services essential to develop high-resolution 3D city models.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114601407","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}
It is challenging to figure out the most common appraisal of an online product since there are too many reviews about it uploaded on the internet. Several research methods using opinion mining in the context of the online reviews have been suggested to solve this issue. The existing research on opinion mining can be classified into three general levels: document-level, sentence-level, and aspect-level sentiment analysis. Aspect-based evaluation is the most meaningful application in opinion mining, and researchers are getting more interested in product aspect extraction; however, more complex algorithms are needed to address this issue precisely with larger corpora. This paper introduces a method to automatically gain a knowledge-based system, which then is used to capture product aspects and corresponding opinions from a large number of product reviews in a specific domain. Our efforts tend to improve accuracy and the usefulness of review summaries by leveraging knowledge of product aspect extraction and provide both appropriate level of detail and richer representation capabilities.
{"title":"Automatic Knowledge Extraction for Aspect-based Sentiment Analysis of Customer Reviews","authors":"Anh-Dung Vo, Quang-Phuoc Nguyen, Cheolyoung Ock","doi":"10.1145/3177457.3177462","DOIUrl":"https://doi.org/10.1145/3177457.3177462","url":null,"abstract":"It is challenging to figure out the most common appraisal of an online product since there are too many reviews about it uploaded on the internet. Several research methods using opinion mining in the context of the online reviews have been suggested to solve this issue. The existing research on opinion mining can be classified into three general levels: document-level, sentence-level, and aspect-level sentiment analysis. Aspect-based evaluation is the most meaningful application in opinion mining, and researchers are getting more interested in product aspect extraction; however, more complex algorithms are needed to address this issue precisely with larger corpora. This paper introduces a method to automatically gain a knowledge-based system, which then is used to capture product aspects and corresponding opinions from a large number of product reviews in a specific domain. Our efforts tend to improve accuracy and the usefulness of review summaries by leveraging knowledge of product aspect extraction and provide both appropriate level of detail and richer representation capabilities.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"17 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125614184","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 rise of social media usage in the form of multimedia is on an exponential increase owing to the increased internet bandwidths in the recent past. As a result, people communicate in the form of videos and images a lot more than ever. One such video sharing and content developer platform is YouTube. YouTube has many features on video analytics in the form of recommendation systems, monetisation etc. It also offers many features for developers to evaluate their content and offers insights on the performance of their videos. Though these features are available, there is not even a single feature for developers to evaluate their content based on the performance of other's videos, which share the same nature of the content - the similarity between any two videos. Here, the similarity between two videos has a statistical measure apart from the content, which includes description and comments of a video. Thus, we propose an analysis of a query video and a range of videos to determine the most similar videos using statistical and textual similarity. The statistical similarity is evident from the number of derived features extracted from a video and the textual similarity is found by analysing the text data from the description and comments of a video. Experimental results show that the resultant similar videos are highly representative of both the statistical and textual similarity and can be used as a measure to compare two videos.
{"title":"YouTree: A Visualization Paradigm of Statistically and Textually Similar Videos","authors":"Dhanasekar Sundararaman, Vishwanath Seshagiri, Balaji Ramesh, Priya Arora","doi":"10.1145/3177457.3177467","DOIUrl":"https://doi.org/10.1145/3177457.3177467","url":null,"abstract":"The rise of social media usage in the form of multimedia is on an exponential increase owing to the increased internet bandwidths in the recent past. As a result, people communicate in the form of videos and images a lot more than ever. One such video sharing and content developer platform is YouTube. YouTube has many features on video analytics in the form of recommendation systems, monetisation etc. It also offers many features for developers to evaluate their content and offers insights on the performance of their videos. Though these features are available, there is not even a single feature for developers to evaluate their content based on the performance of other's videos, which share the same nature of the content - the similarity between any two videos. Here, the similarity between two videos has a statistical measure apart from the content, which includes description and comments of a video. Thus, we propose an analysis of a query video and a range of videos to determine the most similar videos using statistical and textual similarity. The statistical similarity is evident from the number of derived features extracted from a video and the textual similarity is found by analysing the text data from the description and comments of a video. Experimental results show that the resultant similar videos are highly representative of both the statistical and textual similarity and can be used as a measure to compare two videos.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133462958","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}
Emergencies can occur at any location and time, so all stakeholders should get themselves prepared for providing emergency actions and responses. Such actions are especially important in sophisticated but vulnerable systems, e.g., mass transport systems, hospitals and power plants. Crichton and Flin [1] showed multiple examples that the performance of incident management teams in the initial stage of a crisis could affect the development of the incident. Therefore, regular training should be provided to the stakeholders, particularly the operators of the organisation, so that they can work together to deal with the emergencies effectively. Although conducting a drill in the real system may be the most direct way for stakeholders to practice their emergency response abilities, performing a drill usually requires many resources and a disruption of the real system. Therefore, this paper introduces an approach to conduct the drill in a virtual environment. It proposes a virtual collaborative simulation-based training system with an aim to improve the emergency management ability of the staff in sophisticated but vulnerable systems. There are four major advantages of the proposed system: 1). It is off-line from the real system so that there is no space or time constraint to carry out the training. 2). It requires fewer physical resources to carry out the training, which makes the training much cost-effective. 3.) The managers, as well as the operators, can have a better understanding of the real operations by looking at the 3D simulation model. 4.) It provides flexibility to train the operators in various hypothetical scenarios, including some rarely occurred ones. To better illustrate the ideas, this paper takes the mass transport system as an example. However, it should be stressed that the proposed system can be applied to other areas like exhibition centres, emergency rooms of the hospitals and nuclear plants.
{"title":"A Virtual Collaborative Simulation-based Training System","authors":"P. Kwok, Bill K. P. Chan, H. Lau","doi":"10.1145/3177457.3177494","DOIUrl":"https://doi.org/10.1145/3177457.3177494","url":null,"abstract":"Emergencies can occur at any location and time, so all stakeholders should get themselves prepared for providing emergency actions and responses. Such actions are especially important in sophisticated but vulnerable systems, e.g., mass transport systems, hospitals and power plants. Crichton and Flin [1] showed multiple examples that the performance of incident management teams in the initial stage of a crisis could affect the development of the incident. Therefore, regular training should be provided to the stakeholders, particularly the operators of the organisation, so that they can work together to deal with the emergencies effectively. Although conducting a drill in the real system may be the most direct way for stakeholders to practice their emergency response abilities, performing a drill usually requires many resources and a disruption of the real system. Therefore, this paper introduces an approach to conduct the drill in a virtual environment. It proposes a virtual collaborative simulation-based training system with an aim to improve the emergency management ability of the staff in sophisticated but vulnerable systems. There are four major advantages of the proposed system: 1). It is off-line from the real system so that there is no space or time constraint to carry out the training. 2). It requires fewer physical resources to carry out the training, which makes the training much cost-effective. 3.) The managers, as well as the operators, can have a better understanding of the real operations by looking at the 3D simulation model. 4.) It provides flexibility to train the operators in various hypothetical scenarios, including some rarely occurred ones. To better illustrate the ideas, this paper takes the mass transport system as an example. However, it should be stressed that the proposed system can be applied to other areas like exhibition centres, emergency rooms of the hospitals and nuclear plants.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130540544","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}
Machine Learning allows systems to learn and improve automatically from experiences without hand-coding. Thus, in recent years, many technology companies have been developing such application if Artificial Intelligence, from face recognition by Facebook, to the AlphaGo program by Google. The irrigation systems in the market nowadays mostly allow users to set them to a certain amount of water and at specific time intervals. However, there are usually more than one type of plants in a garden, and each species requires different amount of water. In order to resolve this issue, in this paper, we have developed an irrigation system, with the use of deep learning, that is able to adjust the amounts of water foe each type pf plant through plants recognition. There are two main parts of the solution, the software and the hardware. The prior is connected with cameras to undergo plant recognition, and utilizes database to find the suitable amount of water; the latter controls the amount of water that is able to flow out.
{"title":"A Smart IoT-Based Irrigation System with Automated Plant Recognition using Deep Learning","authors":"Jessica Kwok, Yu Sun","doi":"10.1145/3177457.3177506","DOIUrl":"https://doi.org/10.1145/3177457.3177506","url":null,"abstract":"Machine Learning allows systems to learn and improve automatically from experiences without hand-coding. Thus, in recent years, many technology companies have been developing such application if Artificial Intelligence, from face recognition by Facebook, to the AlphaGo program by Google. The irrigation systems in the market nowadays mostly allow users to set them to a certain amount of water and at specific time intervals. However, there are usually more than one type of plants in a garden, and each species requires different amount of water. In order to resolve this issue, in this paper, we have developed an irrigation system, with the use of deep learning, that is able to adjust the amounts of water foe each type pf plant through plants recognition. There are two main parts of the solution, the software and the hardware. The prior is connected with cameras to undergo plant recognition, and utilizes database to find the suitable amount of water; the latter controls the amount of water that is able to flow out.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115976832","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}
With the rapid development of the national economy and society, put forward higher requirements for power supply safety, as an important support system for power grid safety production and management, the development of communication network and the safe and reliable operation is very important. Therefore, in practical work, network construction, upgrading, maintenance and management are the quality of network requires the corresponding evaluation criteria and assessment, all kinds of simulation and analysis technology to use, analyze and evaluate the bearing business ability, so as to establish a reliable network system to improve and optimize business structure business capacity. The data collection, the report on the actual situation of communication and communication network management system using the application range of comprehensive simulation and service quality evaluation system of the status quo of data exchange technology and communication network. To lay the foundation for the establishment of integrated simulation and evaluation system.
{"title":"Research on Application Mode of Integrated Simulation in Power System Operation","authors":"Jia Xue, Xiangzhou Chen, Huixia Ding, Huanhuan Xu","doi":"10.1145/3177457.3191711","DOIUrl":"https://doi.org/10.1145/3177457.3191711","url":null,"abstract":"With the rapid development of the national economy and society, put forward higher requirements for power supply safety, as an important support system for power grid safety production and management, the development of communication network and the safe and reliable operation is very important. Therefore, in practical work, network construction, upgrading, maintenance and management are the quality of network requires the corresponding evaluation criteria and assessment, all kinds of simulation and analysis technology to use, analyze and evaluate the bearing business ability, so as to establish a reliable network system to improve and optimize business structure business capacity. The data collection, the report on the actual situation of communication and communication network management system using the application range of comprehensive simulation and service quality evaluation system of the status quo of data exchange technology and communication network. To lay the foundation for the establishment of integrated simulation and evaluation system.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129813819","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}
It is necessary to establish the longitudinal dynamic model of the tractor for the cruise control system to design a fixed speed control algorithm according to the characteristics of the model and the external disturbance characteristics. Aiming at the complexity of the longitudinal power transmission system of the tractor, this paper uses the modular mechanism modeling and the experimental data modeling to establish the longitudinal dynamic model of the tractor. Due to the nonlinearity of the longitudinal dynamics system, the inverse model method is used to linearize the model, which is convenient for the design of control structure and control algorithm of the standard cruise control system. The longitudinal dynamics model is simulated on Simulink, and the model is verified by real vehicle under driving condition. Comparing the simulation data with the experimental data, the results show that the model can accurately reflect the longitudinal dynamics characteristics of tractor, and can meet the requirements for the design of cruise control system.
{"title":"Linearized Longitudinal Dynamic Model for Tractor Cruise Control System","authors":"Zhixiang Liu, Zhuo Wang, X. Bai, Lei Gao","doi":"10.1145/3177457.3177493","DOIUrl":"https://doi.org/10.1145/3177457.3177493","url":null,"abstract":"It is necessary to establish the longitudinal dynamic model of the tractor for the cruise control system to design a fixed speed control algorithm according to the characteristics of the model and the external disturbance characteristics. Aiming at the complexity of the longitudinal power transmission system of the tractor, this paper uses the modular mechanism modeling and the experimental data modeling to establish the longitudinal dynamic model of the tractor. Due to the nonlinearity of the longitudinal dynamics system, the inverse model method is used to linearize the model, which is convenient for the design of control structure and control algorithm of the standard cruise control system. The longitudinal dynamics model is simulated on Simulink, and the model is verified by real vehicle under driving condition. Comparing the simulation data with the experimental data, the results show that the model can accurately reflect the longitudinal dynamics characteristics of tractor, and can meet the requirements for the design of cruise control system.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"1988 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128487541","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 paper will review practical techniques and procedures employed to quiet gearboxes units. The gearbox noise problem solution is focused on improvement of gear design, on verification of its mathematical models on the radiated noise and determination of the gears contribution to the vehicle overall noise levels and on analytical and/or numerical computer-based tools needed to perform signal processing and diagnostics of geared axis systems. This paper prefers solving the gear noise problem that enclosure as a means to reduce radiated noise, which using math model to estimate effect on the sound pressure level. All the analytical methods are based on the way to build up modal parameter of gear box. The paper will review the progress in technique of the gear angular vibration analysis and its effect on gear noise due to the self excited vibration. The presentation will include some sample of model in 3D and the real one.
{"title":"Analysis Noise Vibration of the Gearboxes using Mathematical Models","authors":"C. H. Phi, T. Hoàng, T. T. Tung","doi":"10.1145/3177457.3177491","DOIUrl":"https://doi.org/10.1145/3177457.3177491","url":null,"abstract":"The paper will review practical techniques and procedures employed to quiet gearboxes units. The gearbox noise problem solution is focused on improvement of gear design, on verification of its mathematical models on the radiated noise and determination of the gears contribution to the vehicle overall noise levels and on analytical and/or numerical computer-based tools needed to perform signal processing and diagnostics of geared axis systems. This paper prefers solving the gear noise problem that enclosure as a means to reduce radiated noise, which using math model to estimate effect on the sound pressure level. All the analytical methods are based on the way to build up modal parameter of gear box. The paper will review the progress in technique of the gear angular vibration analysis and its effect on gear noise due to the self excited vibration. The presentation will include some sample of model in 3D and the real one.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"165 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123426972","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 Discrete Element Method (DEM) is a Lagrangian approach initially developed for predicting particles flow. The eXtended Discrete Element Method (XDEM) framework, developed at the LuXDEM Research Centre of the University of Luxembourg, extends DEM by including the thermochemical state of particles, as well as their interaction with a Computational Fluid Dynamics (CFD) domain. The level of detail of its predictions makes the XDEM suite a powerful tool for predicting complex industrial processes like steel making, powder metallurgy and additive manufacturing. Like in any other DEM software, the critical aspect of the simulations is the computation requirement that grows rapidly as the number of particles increases. Indeed, such burden currently represents the main bottleneck to its full exploitation in large-scale scenarios. Digital Twin, a research project founded by the European Regional Development Fund (ERDF), aims at drastically accelerate XDEM through different approaches and make it an effective tool for numerical predictions in industry as well as virtual prototyping. The Multiphase Particle-In-Cell (MP-PIC) method has been introduced for reducing the computation burden of DEM. It has been initially developed for predicting particles flow and uses a two-way transfer of information between the Lagrangian entities and a computation grid. The method avoids explicit contact detection and can potentially achieve a drastic reduction of the time-to-solution respect to DEM. The present contribution introduces a multiphase approach for predicting the conductive heat transfer within a static packed bed of particles. Results from a test case are qualitatively and quantitatively compared against reference XDEM predictions. The method can be effectively exploited in combination with MP-PIC for predicting the thermochemical state of particles.
{"title":"A comparison between discrete analysis and a multiphase approach for predicting heat conduction in packed beds","authors":"Edoardo Copertaro, A. Donoso, B. Peters","doi":"10.1145/3177457.3177497","DOIUrl":"https://doi.org/10.1145/3177457.3177497","url":null,"abstract":"The Discrete Element Method (DEM) is a Lagrangian approach initially developed for predicting particles flow. The eXtended Discrete Element Method (XDEM) framework, developed at the LuXDEM Research Centre of the University of Luxembourg, extends DEM by including the thermochemical state of particles, as well as their interaction with a Computational Fluid Dynamics (CFD) domain. The level of detail of its predictions makes the XDEM suite a powerful tool for predicting complex industrial processes like steel making, powder metallurgy and additive manufacturing. Like in any other DEM software, the critical aspect of the simulations is the computation requirement that grows rapidly as the number of particles increases. Indeed, such burden currently represents the main bottleneck to its full exploitation in large-scale scenarios. Digital Twin, a research project founded by the European Regional Development Fund (ERDF), aims at drastically accelerate XDEM through different approaches and make it an effective tool for numerical predictions in industry as well as virtual prototyping. The Multiphase Particle-In-Cell (MP-PIC) method has been introduced for reducing the computation burden of DEM. It has been initially developed for predicting particles flow and uses a two-way transfer of information between the Lagrangian entities and a computation grid. The method avoids explicit contact detection and can potentially achieve a drastic reduction of the time-to-solution respect to DEM. The present contribution introduces a multiphase approach for predicting the conductive heat transfer within a static packed bed of particles. Results from a test case are qualitatively and quantitatively compared against reference XDEM predictions. The method can be effectively exploited in combination with MP-PIC for predicting the thermochemical state of particles.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128121477","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}
In recent years, prone images and other such indecent matter are available on the social media and the Internet for children. Filtering of image porn has become one of the big changes for searches; they are tied to finding methods to filter porn images. Social media network is interested in filter porn images from normal ones. Analysis method uses the bright image to automatically detect and filter images in the media. In this paper, we have reviewed methods such as color based, shape based, local and global feature approach, deep learning and bag-of-words for filtering porn images which include comparing with the advantages and disadvantages.
{"title":"Methods of Pornography Detection: Review","authors":"Sasan Karamizadeh, Abouzar Arabsorkhi","doi":"10.1145/3177457.3177484","DOIUrl":"https://doi.org/10.1145/3177457.3177484","url":null,"abstract":"In recent years, prone images and other such indecent matter are available on the social media and the Internet for children. Filtering of image porn has become one of the big changes for searches; they are tied to finding methods to filter porn images. Social media network is interested in filter porn images from normal ones. Analysis method uses the bright image to automatically detect and filter images in the media. In this paper, we have reviewed methods such as color based, shape based, local and global feature approach, deep learning and bag-of-words for filtering porn images which include comparing with the advantages and disadvantages.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"328 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124621137","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：