Pub Date : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514232
T. U. Sane, Tanuj Sane
With the ever-growing population, demand of good quality food has also increased. This demand is also constrained by shortage of skillful labor & involved costs. Considering these, efforts have been made to automate and improve current crop harvesting processes, using advancements in artificial intelligence (AI) and deep learning (DL) algorithms. This paper explores various robotic harvesting systems, which have already implemented or plan to utilize such techniques to detect a crop, navigate to it and efficiently harvest it in a reliable way. The paper states the harvested crop, investigates the selection criteria of an AI/ DL method, the respective benefits & challenges faced in its field implementation. Lastly, the paper states the possible metrics for selection of such a method and finds that Convoluted Neural Networks (CNN) are a popular choice of DL method for such applications based on their robustness and performance.
{"title":"Artificial Intelligence and Deep Learning Applications in Crop Harvesting Robots -A Survey","authors":"T. U. Sane, Tanuj Sane","doi":"10.1109/ICECCE52056.2021.9514232","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514232","url":null,"abstract":"With the ever-growing population, demand of good quality food has also increased. This demand is also constrained by shortage of skillful labor & involved costs. Considering these, efforts have been made to automate and improve current crop harvesting processes, using advancements in artificial intelligence (AI) and deep learning (DL) algorithms. This paper explores various robotic harvesting systems, which have already implemented or plan to utilize such techniques to detect a crop, navigate to it and efficiently harvest it in a reliable way. The paper states the harvested crop, investigates the selection criteria of an AI/ DL method, the respective benefits & challenges faced in its field implementation. Lastly, the paper states the possible metrics for selection of such a method and finds that Convoluted Neural Networks (CNN) are a popular choice of DL method for such applications based on their robustness and performance.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117321687","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514108
Waqas Arshad, Muhammad Ali, Muhammad Mumtaz Ali, A. Javed, S. Hussain
The objective of text classification is to categorize documents into a specific number of predefined categories. We can easily imagine the issue of arranging documents, not by topic, but rather by and large assessment, e.g. deciding if the sentiment of a document is whether positive or negative. While working on a supervised machine learning problem with a defined dataset, there are many classifiers that can be used in text classification. Utilizing dataset of stack overflow questions, answers, and tags as information, we find that standard machine learning systems completely beat human-delivered baselines. These majorly include Naive Bayes Classifier for multinomial models, Linear Support Vector Machine, Logistic Regression, Word to vector (Word2vec) and Logistic Regression, Document to vector (Doc2vc) and logistic regression, Bag of Words (BOW) with Keras. Our paper is a detailed examination and comparison of accuracies among these algorithms.
{"title":"Multi-Class Text Classification: Model Comparison and Selection","authors":"Waqas Arshad, Muhammad Ali, Muhammad Mumtaz Ali, A. Javed, S. Hussain","doi":"10.1109/ICECCE52056.2021.9514108","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514108","url":null,"abstract":"The objective of text classification is to categorize documents into a specific number of predefined categories. We can easily imagine the issue of arranging documents, not by topic, but rather by and large assessment, e.g. deciding if the sentiment of a document is whether positive or negative. While working on a supervised machine learning problem with a defined dataset, there are many classifiers that can be used in text classification. Utilizing dataset of stack overflow questions, answers, and tags as information, we find that standard machine learning systems completely beat human-delivered baselines. These majorly include Naive Bayes Classifier for multinomial models, Linear Support Vector Machine, Logistic Regression, Word to vector (Word2vec) and Logistic Regression, Document to vector (Doc2vc) and logistic regression, Bag of Words (BOW) with Keras. Our paper is a detailed examination and comparison of accuracies among these algorithms.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114719051","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514154
Fehmida Usmani, I. Khan, M. Siddiqui, Mahnoor Khan, Muhamamd Bilal, M. U. Masood, Arsalan Ahmad, M. Shahzad, V. Curri
The rapid increase in bandwidth-driven applications has resulted in exponential internet traffic growth, especially in the backbone networks. To address this growth of internet traffic, operators always demand the total capacity utilization of underlying infrastructure. In this perspective, precise estimation of the quality of transmission (QoT) of the lightpaths (LPs) is vital for reducing the margins provisioned by uncertainty in network equipment's working point. This article proposes and compares several data-driven Machine learning (ML) based models to estimate QoT of unestablished LP before its deployment in the future deploying network. The proposed models are cross-trained on the data acquired from an already established LP of an entirely different in-service network. The metric considered to evaluate the QoT of LP is the Generalized Signal-to-Noise Ratio (GSNR). The dataset is generated synthetically using well tested GNPy simulation tool. Promising results are achieved to reduce the GSNR uncertainty and, consequently, the provisioning margin.
{"title":"Evaluating Cross- feature Trained Machine Learning Models for Estimating QoT of Unestablished Lightpaths","authors":"Fehmida Usmani, I. Khan, M. Siddiqui, Mahnoor Khan, Muhamamd Bilal, M. U. Masood, Arsalan Ahmad, M. Shahzad, V. Curri","doi":"10.1109/ICECCE52056.2021.9514154","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514154","url":null,"abstract":"The rapid increase in bandwidth-driven applications has resulted in exponential internet traffic growth, especially in the backbone networks. To address this growth of internet traffic, operators always demand the total capacity utilization of underlying infrastructure. In this perspective, precise estimation of the quality of transmission (QoT) of the lightpaths (LPs) is vital for reducing the margins provisioned by uncertainty in network equipment's working point. This article proposes and compares several data-driven Machine learning (ML) based models to estimate QoT of unestablished LP before its deployment in the future deploying network. The proposed models are cross-trained on the data acquired from an already established LP of an entirely different in-service network. The metric considered to evaluate the QoT of LP is the Generalized Signal-to-Noise Ratio (GSNR). The dataset is generated synthetically using well tested GNPy simulation tool. Promising results are achieved to reduce the GSNR uncertainty and, consequently, the provisioning margin.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121891723","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514158
S. V. Fernandes, T. R. Chaves, M. A. Martins, R. O. Brandão, A. F. Macedo, K. Martins
The development of new technologies linked to Smart Grid has led to a series of technological advances in the area of power systems. The IEC 61850, since its advent in 2002, has revolutionized projects and operations in substations, bringing several improvements, such as the use of high speed and high availability data communication networks. With this, it has been possible to readjust and modernize the protection systems found in a substation. In this perspective, this article proposes the development and implementation of a substation protection architecture different from those already registered, reducing the amount of IEDs used and finding a technological-financial balance. This new architecture can be used as a model for the digitalization and improvement of other substations. This study is part of the scope of the Urban Futurability R&D project, carried out by ENEL Distribuição São Paulo, located in the Vila Olímpia neighborhood, a region with very favorable characteristics to carry out this type of study because of its different types of grids, from overhead grids with medium load density to underground grids with high load density.
智能电网相关新技术的发展带动了电力系统领域的一系列技术进步。IEC 61850自2002年问世以来，已经彻底改变了变电站的项目和操作，带来了一些改进，例如使用高速和高可用性数据通信网络。有了这个，就有可能重新调整和现代化变电站中的保护系统。从这个角度来看，本文建议开发和实施一种不同于已注册的变电站保护架构，减少简易爆炸装置的使用数量，并找到技术与财务的平衡。这种新的结构可以作为其他变电站数字化改造的样板。这项研究是城市未来能力研发项目的一部分，由ENEL distribui o s o Paulo开展，该项目位于Vila Olímpia社区，该地区具有非常有利的特征，因为它具有不同类型的电网，从中等负荷密度的架空电网到高负荷密度的地下电网。
{"title":"Study of the Primary Substation Digitalization","authors":"S. V. Fernandes, T. R. Chaves, M. A. Martins, R. O. Brandão, A. F. Macedo, K. Martins","doi":"10.1109/ICECCE52056.2021.9514158","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514158","url":null,"abstract":"The development of new technologies linked to Smart Grid has led to a series of technological advances in the area of power systems. The IEC 61850, since its advent in 2002, has revolutionized projects and operations in substations, bringing several improvements, such as the use of high speed and high availability data communication networks. With this, it has been possible to readjust and modernize the protection systems found in a substation. In this perspective, this article proposes the development and implementation of a substation protection architecture different from those already registered, reducing the amount of IEDs used and finding a technological-financial balance. This new architecture can be used as a model for the digitalization and improvement of other substations. This study is part of the scope of the Urban Futurability R&D project, carried out by ENEL Distribuição São Paulo, located in the Vila Olímpia neighborhood, a region with very favorable characteristics to carry out this type of study because of its different types of grids, from overhead grids with medium load density to underground grids with high load density.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"158 1-2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123500772","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514086
Z. Soltani, Kresten Kjaer Soerensen, J. Leth, Jan Dimon Bendtsen
Supermarket refrigeration systems represent an important type of energy demanding appliances, which is in such widespread use that any development in the associated technology can have a huge impact on general health and global warming. Using automatic fault detection and diagnosis may for instance improve energy efficiency and reduce food waste as well as reduce expenses for the supermarket owners. In this paper, three model-free classification algorithms are tested on faulty/non-faulty data obtained from an actual refrigeration system. It is found that support vector machines (SVM) are able to classify fan faults in a real refrigeration system with near-100% classification accuracy, independent of the number of input variables. The classification performance and robustness against an unseen operation mode, low-resolution data, noisy data, and data of different operating points is tested for three different classifier configurations. The results show Principle Component Analysis (PCA)-SVM is highly robust to different operating points, disturbances, and gives the best computational efficiency, as it is able to reduce the feature space to only two dimensions. It is concluded that while all of the examined methods are insensitive to noise, and effective in terms of detecting faults from relatively small amounts of data, overall, PCA -SVM is slightly more computationally efficient.
{"title":"Robustness analysis of PCA-SVM model used for fault detection in supermarket refrigeration systems *","authors":"Z. Soltani, Kresten Kjaer Soerensen, J. Leth, Jan Dimon Bendtsen","doi":"10.1109/ICECCE52056.2021.9514086","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514086","url":null,"abstract":"Supermarket refrigeration systems represent an important type of energy demanding appliances, which is in such widespread use that any development in the associated technology can have a huge impact on general health and global warming. Using automatic fault detection and diagnosis may for instance improve energy efficiency and reduce food waste as well as reduce expenses for the supermarket owners. In this paper, three model-free classification algorithms are tested on faulty/non-faulty data obtained from an actual refrigeration system. It is found that support vector machines (SVM) are able to classify fan faults in a real refrigeration system with near-100% classification accuracy, independent of the number of input variables. The classification performance and robustness against an unseen operation mode, low-resolution data, noisy data, and data of different operating points is tested for three different classifier configurations. The results show Principle Component Analysis (PCA)-SVM is highly robust to different operating points, disturbances, and gives the best computational efficiency, as it is able to reduce the feature space to only two dimensions. It is concluded that while all of the examined methods are insensitive to noise, and effective in terms of detecting faults from relatively small amounts of data, overall, PCA -SVM is slightly more computationally efficient.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124266883","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}
To reduce the risk of botnet malware, methods of detecting botnet malware using machine learning have received enormous attention in recent years. Most of the traditional methods are based on supervised learning that relies on static features with defined labels. However, recent studies show that supervised machine learning-based IoT malware botnet models are more vulnerable to intentional attacks, known as an adversarial attack. In this paper, we study the adversarial attack on PSI-graph based researches. To perform the efficient attack, we proposed a reinforcement learning based method with a trained target classifier to modify the structures of PSI-graphs. We show that PSI-graphs are vulnerable to such attack. We also discuss about defense method which uses adversarial training to train a defensive model. Experiment result achieves 94.1% accuracy on the adversarial dataset; thus, shows that our defensive model is much more robust than the previous target classifier.
{"title":"Adversarial Attack and Defense on Graph-based IoT Botnet Detection Approach","authors":"Quoc-Dung Ngo, Huy-Trung Nguyen, Viet-Dung Nguyen, C. Dinh, Anh-Tu Phung, Quy-Tung Bui","doi":"10.1109/ICECCE52056.2021.9514255","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514255","url":null,"abstract":"To reduce the risk of botnet malware, methods of detecting botnet malware using machine learning have received enormous attention in recent years. Most of the traditional methods are based on supervised learning that relies on static features with defined labels. However, recent studies show that supervised machine learning-based IoT malware botnet models are more vulnerable to intentional attacks, known as an adversarial attack. In this paper, we study the adversarial attack on PSI-graph based researches. To perform the efficient attack, we proposed a reinforcement learning based method with a trained target classifier to modify the structures of PSI-graphs. We show that PSI-graphs are vulnerable to such attack. We also discuss about defense method which uses adversarial training to train a defensive model. Experiment result achieves 94.1% accuracy on the adversarial dataset; thus, shows that our defensive model is much more robust than the previous target classifier.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"22 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123449608","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514122
Abdulbari Ali Mohamed Frei, M. Güneser
In this paper an optimal integration of Distributed Energy Resource (DER) such as Photo-Voltaic Generation System (PVGS), Wind Turbine Generation System (WTGS), and Electric Vehicles (EVs) in supply network simultaneously implemented for motive of abatement of overall power loss, overall cost and emanations dispatched through the thermal generators. To accomplish these planned purposes and profits, we designed a multi-objective function. For optimization of the cost we used artificial bee colony algorithm.
{"title":"Optimal Accommodation of DERs in Practical Radial Distribution Feeder for Techno-Economic with Artificial Bee Colony Algorithm","authors":"Abdulbari Ali Mohamed Frei, M. Güneser","doi":"10.1109/ICECCE52056.2021.9514122","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514122","url":null,"abstract":"In this paper an optimal integration of Distributed Energy Resource (DER) such as Photo-Voltaic Generation System (PVGS), Wind Turbine Generation System (WTGS), and Electric Vehicles (EVs) in supply network simultaneously implemented for motive of abatement of overall power loss, overall cost and emanations dispatched through the thermal generators. To accomplish these planned purposes and profits, we designed a multi-objective function. For optimization of the cost we used artificial bee colony algorithm.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123861812","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514205
Jiayi Fan, Yongkeun Lee
Torque sharing function (TSF) method is widely used in switched reluctance motor (SRM) drive to reduce the torque ripple. Besides maintaining the torque control performance, the copper loss reduction should also be considered while determining the TSF profiles. In this paper, an improved TSF method modified from the previous method recently done by the other research group is proposed focusing on the optimal allocation of torque component in the commutation phases and reduction of copper loss. Based on the torque generating nature of SRM, the commutation region is suggested to be divided into two regions where the incoming phase and outgoing phase have different torque generating capacity. The commutation phase with higher rate of change of inductance with respect to the rotor position is preferred to mainly contribute to the torque production while the other phase is penalized to have reduced current. Thus, the total copper loss can be reduced. Simulation is carried out in MATLAB/Simulink environment and the simulation results show that the modified TSF with region division has a lower copper loss compared to the previous method done by the other research group.
{"title":"Copper Loss Reduction of Torque Sharing Function in Switched Reluctance Motor by Division of Commutation Region","authors":"Jiayi Fan, Yongkeun Lee","doi":"10.1109/ICECCE52056.2021.9514205","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514205","url":null,"abstract":"Torque sharing function (TSF) method is widely used in switched reluctance motor (SRM) drive to reduce the torque ripple. Besides maintaining the torque control performance, the copper loss reduction should also be considered while determining the TSF profiles. In this paper, an improved TSF method modified from the previous method recently done by the other research group is proposed focusing on the optimal allocation of torque component in the commutation phases and reduction of copper loss. Based on the torque generating nature of SRM, the commutation region is suggested to be divided into two regions where the incoming phase and outgoing phase have different torque generating capacity. The commutation phase with higher rate of change of inductance with respect to the rotor position is preferred to mainly contribute to the torque production while the other phase is penalized to have reduced current. Thus, the total copper loss can be reduced. Simulation is carried out in MATLAB/Simulink environment and the simulation results show that the modified TSF with region division has a lower copper loss compared to the previous method done by the other research group.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130277048","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514162
Horacio M. Frene, C. D. Arrojo, R. Dias, J. C. Scaramutti
This work presents a mathematical and parametric analysis of physical and electrical variables involved in electromechanical forces due to three-phase short-circuit currents. Focus is on three-phase currents since they usually cause higher stress on electrical power equipment. Since, in the authors' opinion, a fully practical understanding of IEC 60865-1 Standard [2] is not straightforward, electromagnetic force parameters are analyzed, evaluated, and compared aiming to relate the mentioned phenomenon to the standard. Graphical material is included to make the topic clear. Future papers will be focus on tests at a testing facility.
{"title":"Mechanical stresses of electromagnetic origin. Effects produced by three-phase short-circuit currents on a rigid busbar system","authors":"Horacio M. Frene, C. D. Arrojo, R. Dias, J. C. Scaramutti","doi":"10.1109/ICECCE52056.2021.9514162","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514162","url":null,"abstract":"This work presents a mathematical and parametric analysis of physical and electrical variables involved in electromechanical forces due to three-phase short-circuit currents. Focus is on three-phase currents since they usually cause higher stress on electrical power equipment. Since, in the authors' opinion, a fully practical understanding of IEC 60865-1 Standard [2] is not straightforward, electromagnetic force parameters are analyzed, evaluated, and compared aiming to relate the mentioned phenomenon to the standard. Graphical material is included to make the topic clear. Future papers will be focus on tests at a testing facility.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130911495","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514115
Hafizza Abdul Ghapar, U. Khairuddin, Rubiyah Yusof, A. S. M. Khairuddin, Azlin Ahmad
A key to wood identification is the distinguishable features found on the cross-sectional surface of each tree species. The surface pattern on the wood cross-section may look very similar to non-experts. However, trained experts may identify wood species based on distinct and discriminant features of the pattern. An automatic wood recognition system based on machine vision to emulate the experts, the KenalKayu has been developed with high classification accuracy. Unfortunately, when more wood species were added into the system's database, the accuracy of the system reduced. It is important for the system to have a customized feature extractor solely for wood pattern such as the statistical properties of pores distribution (SPPD) which has been proven to increase the system's accuracy. As the wood surface pattern is not only defined by pores, but lines as well, this paper presented additional new feature extraction method based on statistical properties of line distribution (SPLD) to capture the discriminant line features of each species. When used alone as feature extractor, the SPLD managed to get 88% accuracy, and the number increases to 99.5% when combined with SPPD features and 100% when combined with both SPPD and Basic Grey Level Aura Matrix features. It shows that the SPLD is an essential customized feature extractor for wood identification purposes.
{"title":"New Feature Extraction for Wood Species Recognition System via Statistical Properties of Line Distribution","authors":"Hafizza Abdul Ghapar, U. Khairuddin, Rubiyah Yusof, A. S. M. Khairuddin, Azlin Ahmad","doi":"10.1109/ICECCE52056.2021.9514115","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514115","url":null,"abstract":"A key to wood identification is the distinguishable features found on the cross-sectional surface of each tree species. The surface pattern on the wood cross-section may look very similar to non-experts. However, trained experts may identify wood species based on distinct and discriminant features of the pattern. An automatic wood recognition system based on machine vision to emulate the experts, the KenalKayu has been developed with high classification accuracy. Unfortunately, when more wood species were added into the system's database, the accuracy of the system reduced. It is important for the system to have a customized feature extractor solely for wood pattern such as the statistical properties of pores distribution (SPPD) which has been proven to increase the system's accuracy. As the wood surface pattern is not only defined by pores, but lines as well, this paper presented additional new feature extraction method based on statistical properties of line distribution (SPLD) to capture the discriminant line features of each species. When used alone as feature extractor, the SPLD managed to get 88% accuracy, and the number increases to 99.5% when combined with SPPD features and 100% when combined with both SPPD and Basic Grey Level Aura Matrix features. It shows that the SPLD is an essential customized feature extractor for wood identification purposes.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130433124","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：