Pub Date : 2020-06-01DOI: 10.1109/ISCV49265.2020.9204248
Kaoutar Lahmadi, I. Boumhidi
This paper deals with quandary of wind turbine control for Takagi Sugeno fuzzy model (TS) in finite frequency domain. The objective is to design a controller which can the asymptotic stability of the global system and minimize the perturbances level caused by the wind haste. The TS fuzzy model is proposed to deal with a nonlinear deportment of wind system, and the finite frequency approach sanctions the command in a specific domain of frequency. By utilizing the lemma of generalized Kalman-Yakubovich-Popuv (GKYP), the H$infty$ control theory and Linear Matrix Inequality technique (LMI), an incipient approach for the robust fuzzy control in finite frequency domain is given. When the disturbances of the systems occur in a range of finite frequencies which is known in advance, it is better to control the system on a very precise frequency domain and not over the whole range of frequencies, to obtain more efficient results and more conservative. In comparison with the full frequency control, the specific domain of frequency approach proves the better performances in wind turbine control. All the developed results are presented in the format of linear matrix inequalities (LMIs) and the simulation results were given provides satisfactory of the proposed approach.
{"title":"LMI approach to Robust Fuzzy H∞ Control for Wind Generator System in Finite Frequency Domain","authors":"Kaoutar Lahmadi, I. Boumhidi","doi":"10.1109/ISCV49265.2020.9204248","DOIUrl":"https://doi.org/10.1109/ISCV49265.2020.9204248","url":null,"abstract":"This paper deals with quandary of wind turbine control for Takagi Sugeno fuzzy model (TS) in finite frequency domain. The objective is to design a controller which can the asymptotic stability of the global system and minimize the perturbances level caused by the wind haste. The TS fuzzy model is proposed to deal with a nonlinear deportment of wind system, and the finite frequency approach sanctions the command in a specific domain of frequency. By utilizing the lemma of generalized Kalman-Yakubovich-Popuv (GKYP), the H$infty$ control theory and Linear Matrix Inequality technique (LMI), an incipient approach for the robust fuzzy control in finite frequency domain is given. When the disturbances of the systems occur in a range of finite frequencies which is known in advance, it is better to control the system on a very precise frequency domain and not over the whole range of frequencies, to obtain more efficient results and more conservative. In comparison with the full frequency control, the specific domain of frequency approach proves the better performances in wind turbine control. All the developed results are presented in the format of linear matrix inequalities (LMIs) and the simulation results were given provides satisfactory of the proposed approach.","PeriodicalId":313743,"journal":{"name":"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128893757","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 : 2020-06-01DOI: 10.1109/ISCV49265.2020.9204133
Soukaina Fatimi, Chama El Saili, L. Alaoui
Text clustering is the discipline that purports to find related groups in a collection of documents. Based on text clustering the use of documents can be more salubrious. Researchers have used various methods to implement text clustering either agglomerative, divisive, or itemsets-based clustering. Most of these proposed approaches do not take into account the semantic relationships between words, in this case, the documents are considered only as bags of unrelated words. Our work aims to consider the semantics of the text phrases in the clustering task, and to get full usage and exploitation of documents. The semantic web concept is overloaded with valuable techniques allowing the significant use of documents. Our goal is to take full advantage of these techniques. Using the Resource Description Framework (RDF) to represent textual data as triplets. They provide a semantic representation of data on which the clustering process will be based, to provide a more efficient clustering system. On the other hand, and based on the clustering process, we opt on incorporating other techniques such as ontology representation using RDF, RDF Schemas (RDFS), and Web Ontology Language (OWL) to manipulate and extract meaningful information. In this paper, we propose a framework of semantic oriented text clustering based on RDF by the means of a semantic similarity measure, and we highlight the benefits of using semantic web techniques in clustering, topic modeling, and information extraction based on questioning, reasoning and inferencing processes.
文本聚类是一门旨在从文档集合中找到相关组的学科。基于文本聚类的文档使用可以更加有益。研究人员使用了各种方法来实现文本聚类，包括聚类、分裂聚类和基于项集的聚类。这些建议的方法大多没有考虑词之间的语义关系，在这种情况下，文档只是被认为是不相关的词的包。我们的工作旨在在聚类任务中考虑文本短语的语义，并充分利用和利用文档。语义网概念包含了大量有价值的技术，允许大量使用文档。我们的目标是充分利用这些技术。使用资源描述框架(RDF)将文本数据表示为三元组。它们提供了数据的语义表示，聚类过程将以此为基础，从而提供更有效的聚类系统。另一方面，基于聚类过程，我们选择结合其他技术，如使用RDF、RDF schema (RDFS)和Web ontology Language (OWL)的本体表示来操作和提取有意义的信息。在本文中，我们提出了一个基于RDF的基于语义相似性度量的面向语义的文本聚类框架，并强调了在聚类、主题建模和基于提问、推理和推理过程的信息提取中使用语义web技术的好处。
{"title":"Semantic Oriented Text Clustering Based on RDF","authors":"Soukaina Fatimi, Chama El Saili, L. Alaoui","doi":"10.1109/ISCV49265.2020.9204133","DOIUrl":"https://doi.org/10.1109/ISCV49265.2020.9204133","url":null,"abstract":"Text clustering is the discipline that purports to find related groups in a collection of documents. Based on text clustering the use of documents can be more salubrious. Researchers have used various methods to implement text clustering either agglomerative, divisive, or itemsets-based clustering. Most of these proposed approaches do not take into account the semantic relationships between words, in this case, the documents are considered only as bags of unrelated words. Our work aims to consider the semantics of the text phrases in the clustering task, and to get full usage and exploitation of documents. The semantic web concept is overloaded with valuable techniques allowing the significant use of documents. Our goal is to take full advantage of these techniques. Using the Resource Description Framework (RDF) to represent textual data as triplets. They provide a semantic representation of data on which the clustering process will be based, to provide a more efficient clustering system. On the other hand, and based on the clustering process, we opt on incorporating other techniques such as ontology representation using RDF, RDF Schemas (RDFS), and Web Ontology Language (OWL) to manipulate and extract meaningful information. In this paper, we propose a framework of semantic oriented text clustering based on RDF by the means of a semantic similarity measure, and we highlight the benefits of using semantic web techniques in clustering, topic modeling, and information extraction based on questioning, reasoning and inferencing processes.","PeriodicalId":313743,"journal":{"name":"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125655270","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 : 2020-06-01DOI: 10.1109/ISCV49265.2020.9204291
Fadwa Abakarim, A. Abenaou
This work presents a method for the automatic recognition of amazigh isolated word speech based on the orthogonal adaptive transformation by creating an adaptive operator according to the analyzed signals that extracts the characteristics of each of them to obtain a vector of minimum dimensional information characteristics that will allow the identification of voice signals with high certainty and we will make a comparison with other approaches used for speech recognition system such as principal component analysis, empirical modal decomposition and discrete wavelet transform. The experimental results show the importance of the creation of the adaptive operator which gives an added value to our approach.
{"title":"Amazigh isolated word speech recognition system using the Adaptive Orthogonal Transform Method.","authors":"Fadwa Abakarim, A. Abenaou","doi":"10.1109/ISCV49265.2020.9204291","DOIUrl":"https://doi.org/10.1109/ISCV49265.2020.9204291","url":null,"abstract":"This work presents a method for the automatic recognition of amazigh isolated word speech based on the orthogonal adaptive transformation by creating an adaptive operator according to the analyzed signals that extracts the characteristics of each of them to obtain a vector of minimum dimensional information characteristics that will allow the identification of voice signals with high certainty and we will make a comparison with other approaches used for speech recognition system such as principal component analysis, empirical modal decomposition and discrete wavelet transform. The experimental results show the importance of the creation of the adaptive operator which gives an added value to our approach.","PeriodicalId":313743,"journal":{"name":"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126549999","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 : 2020-06-01DOI: 10.1109/ISCV49265.2020.9204258
E. Ennadifi, S. Laraba, Damien Vincke, B. Mercatoris, B. Gosselin
The world has been witnessing a population boom that has several implications including food security. Wheat is one of the world’s most important crops in terms of production and consumption, and demand for it is increasing. On the other hand, diseases can damage the abundance and the quality of the crop, so this needs to be revealed through advanced methods. In recent years, along with the various technological developments, using Convolutional Neural Networks (CNN) has proved to be showing great results in many image classification tasks. However, deep learning models are generally considered as black boxes and it is difficult to understand what the model has learned. The purpose of this article is to detect diseases from wheat images using CNNs and to use visualization methods to understand what these models have learned. For this reason, a wheat database has been collected by CRA-W (Walloon Agricultural Research Center), which contains 1163 images and is classified into two groups namely sick and healthy. Moreover, we propose to use the mask R-CNN for segmentation and extraction of wheat spikes from the background. Furthermore, a visualization and interpretation method, namely Gradient-weighted Class Activation Mapping (GradCAM), is used to locate the disease on the wheat spikes in a non-supervised way. GradCAM is actually used generally to highlight the most important regions from the CNN model’s viewpoint that are used to perform the classification.
世界正在见证人口激增，这有几个方面的影响，包括粮食安全。就生产和消费而言，小麦是世界上最重要的作物之一，对它的需求正在增加。另一方面，病害会损害作物的丰度和质量，因此需要通过先进的方法来揭示这一点。近年来，随着各种技术的发展，使用卷积神经网络(CNN)在许多图像分类任务中显示出了很好的效果。然而，深度学习模型通常被认为是黑盒，很难理解模型学习了什么。本文的目的是使用cnn从小麦图像中检测疾病，并使用可视化方法来理解这些模型学到了什么。为此，瓦隆农业研究中心(cron - w)收集了一个小麦数据库，其中包含1163幅图像，并将其分为患病和健康两组。此外，我们提出使用掩模R-CNN从背景中分割和提取小麦穗。在此基础上，采用梯度加权类激活映射(Gradient-weighted Class Activation Mapping, GradCAM)可视化解译方法，以无监督的方式对小麦穗部病害进行定位。实际上，GradCAM通常用于从CNN模型的角度突出显示用于执行分类的最重要的区域。
{"title":"Wheat Diseases Classification and Localization Using Convolutional Neural Networks and GradCAM Visualization","authors":"E. Ennadifi, S. Laraba, Damien Vincke, B. Mercatoris, B. Gosselin","doi":"10.1109/ISCV49265.2020.9204258","DOIUrl":"https://doi.org/10.1109/ISCV49265.2020.9204258","url":null,"abstract":"The world has been witnessing a population boom that has several implications including food security. Wheat is one of the world’s most important crops in terms of production and consumption, and demand for it is increasing. On the other hand, diseases can damage the abundance and the quality of the crop, so this needs to be revealed through advanced methods. In recent years, along with the various technological developments, using Convolutional Neural Networks (CNN) has proved to be showing great results in many image classification tasks. However, deep learning models are generally considered as black boxes and it is difficult to understand what the model has learned. The purpose of this article is to detect diseases from wheat images using CNNs and to use visualization methods to understand what these models have learned. For this reason, a wheat database has been collected by CRA-W (Walloon Agricultural Research Center), which contains 1163 images and is classified into two groups namely sick and healthy. Moreover, we propose to use the mask R-CNN for segmentation and extraction of wheat spikes from the background. Furthermore, a visualization and interpretation method, namely Gradient-weighted Class Activation Mapping (GradCAM), is used to locate the disease on the wheat spikes in a non-supervised way. GradCAM is actually used generally to highlight the most important regions from the CNN model’s viewpoint that are used to perform the classification.","PeriodicalId":313743,"journal":{"name":"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125055393","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 : 2020-06-01DOI: 10.1109/ISCV49265.2020.9204292
Amel Hammouya, R. Chaib
Risk analysis and assessment are extremely important in the oil sector to prevent potential risks. The objective of this work is to propose a thorough risk analysis approach with the integration of the human factor, since he is considered as a weak point of the system and a performance and safety limiter. This study is based on a combination of three tools: SADT, BORA method and ALOHA software. Each of these tools has a function in the proposed approach. Thus, SADT breaks down the studied system and determines the contribution of each component. The functions of the barriers, the success and fault scenarios and the causes of an initial event have been defined by BORA, so the consequences of safety system fault have been studied by ALOHA software. The safety system of the crude oil tank (S106) at the Skikda storage terminal in Algeria was considered as a case study. Based on the results of this research, it was determined that the function fault of a barrier in this system can produce a dangerous situation where humans can be a major cause of these faults since they contribute most of the functions of this system. The originality of this in-depth analysis is the identification of the weak points of a hydrocarbon storage tank's safety system with the integration of the human being where his role and the consequences of their error are determined.
{"title":"Human Factor: A Key Element in A Fire Safety System Of Hydrocarbon Storage Tank","authors":"Amel Hammouya, R. Chaib","doi":"10.1109/ISCV49265.2020.9204292","DOIUrl":"https://doi.org/10.1109/ISCV49265.2020.9204292","url":null,"abstract":"Risk analysis and assessment are extremely important in the oil sector to prevent potential risks. The objective of this work is to propose a thorough risk analysis approach with the integration of the human factor, since he is considered as a weak point of the system and a performance and safety limiter. This study is based on a combination of three tools: SADT, BORA method and ALOHA software. Each of these tools has a function in the proposed approach. Thus, SADT breaks down the studied system and determines the contribution of each component. The functions of the barriers, the success and fault scenarios and the causes of an initial event have been defined by BORA, so the consequences of safety system fault have been studied by ALOHA software. The safety system of the crude oil tank (S106) at the Skikda storage terminal in Algeria was considered as a case study. Based on the results of this research, it was determined that the function fault of a barrier in this system can produce a dangerous situation where humans can be a major cause of these faults since they contribute most of the functions of this system. The originality of this in-depth analysis is the identification of the weak points of a hydrocarbon storage tank's safety system with the integration of the human being where his role and the consequences of their error are determined.","PeriodicalId":313743,"journal":{"name":"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127413421","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 : 2020-04-23DOI: 10.1109/ISCV49265.2020.9204045
Felix Nilsson, J. Jakobsen, F. Alonso-Fernandez
Industrial manufacturing has developed during the last decades from a labor-intensive manual control of machines to a fully-connected automated process. The next big leap is known as industry 4.0, or smart manufacturing. With industry 4.0 comes increased integration between IT systems and the factory floor from the customer order system to final delivery of the product. One benefit of this integration is mass production of individually customized products. However, this has proven challenging to implement into existing factories, considering that their lifetime can be up to 30 years. The single most important parameter to measure in a factory is the operating hours of each machine. Operating hours can be affected by machine maintenance as well as re-configuration for different products. For older machines without connectivity, the operating state is typically indicated by signal lights of green, yellow and red colours. Accordingly, the goal is to develop a solution which can measure the operational state using the input from a video camera capturing a factory floor. Using methods commonly employed for traffic light recognition in autonomous cars, a system with an accuracy of over 99% in the specified conditions is presented. It is believed that if more diverse video data becomes available, a system with high reliability that generalizes well could be developed using a similar methodology.
{"title":"Detection and Classification of Industrial Signal Lights for Factory Floors","authors":"Felix Nilsson, J. Jakobsen, F. Alonso-Fernandez","doi":"10.1109/ISCV49265.2020.9204045","DOIUrl":"https://doi.org/10.1109/ISCV49265.2020.9204045","url":null,"abstract":"Industrial manufacturing has developed during the last decades from a labor-intensive manual control of machines to a fully-connected automated process. The next big leap is known as industry 4.0, or smart manufacturing. With industry 4.0 comes increased integration between IT systems and the factory floor from the customer order system to final delivery of the product. One benefit of this integration is mass production of individually customized products. However, this has proven challenging to implement into existing factories, considering that their lifetime can be up to 30 years. The single most important parameter to measure in a factory is the operating hours of each machine. Operating hours can be affected by machine maintenance as well as re-configuration for different products. For older machines without connectivity, the operating state is typically indicated by signal lights of green, yellow and red colours. Accordingly, the goal is to develop a solution which can measure the operational state using the input from a video camera capturing a factory floor. Using methods commonly employed for traffic light recognition in autonomous cars, a system with an accuracy of over 99% in the specified conditions is presented. It is believed that if more diverse video data becomes available, a system with high reliability that generalizes well could be developed using a similar methodology.","PeriodicalId":313743,"journal":{"name":"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123177268","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：