Pub Date : 2019-10-01DOI: 10.1109/iciteed.2019.8929950
{"title":"ICITEE 2019 Program","authors":"","doi":"10.1109/iciteed.2019.8929950","DOIUrl":"https://doi.org/10.1109/iciteed.2019.8929950","url":null,"abstract":"","PeriodicalId":6598,"journal":{"name":"2019 11th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"126 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75488220","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}
Feature selection is one of the commonly used technique in machine learning literature. It aims to reduce irrelevant, redundant, unneeded attributes from data that do not contribute to improve or even decrease the performance of analytical model. This paper proposes a new feature selection method that evaluate by back-propagated weighting the nongaussianity, Kurtosis, of the corresponding independent components. The nongaussianity scores are normalized using a suitable logistic function where the parameters of the logistic function are selected using an auto fitting curve technique. This proposed method is called the Logistic function of Kurtosis of Independent Component Analysis (KL-ICA). The results on various benchmarks show significant improvement of analytical model performance over existing technique.
{"title":"An unsupervised feature selection by back-propagated weighting the non-Gaussianity score of independence components","authors":"Wachiravit Modecrua, Praisan Padungwiang, Worarat Krathu","doi":"10.1109/ICITEED.2019.8929992","DOIUrl":"https://doi.org/10.1109/ICITEED.2019.8929992","url":null,"abstract":"Feature selection is one of the commonly used technique in machine learning literature. It aims to reduce irrelevant, redundant, unneeded attributes from data that do not contribute to improve or even decrease the performance of analytical model. This paper proposes a new feature selection method that evaluate by back-propagated weighting the nongaussianity, Kurtosis, of the corresponding independent components. The nongaussianity scores are normalized using a suitable logistic function where the parameters of the logistic function are selected using an auto fitting curve technique. This proposed method is called the Logistic function of Kurtosis of Independent Component Analysis (KL-ICA). The results on various benchmarks show significant improvement of analytical model performance over existing technique.","PeriodicalId":6598,"journal":{"name":"2019 11th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"20 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74737902","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 : 2019-10-01DOI: 10.1109/ICITEED.2019.8929970
I. Ardiyanto
Discovering and drawing out the relationship between users and items in a service-based companies or organizations are the essence of a recommendation system. It attracts many researches trying to solve such problems. Here we address a novel approach for the recommendation system, incorporating the means of collaborative aspect between the users internal hidden patterns and the items or goods to be recommended. Unlike the existing methods, our algorithm introduces a guiding factor between the user hidden state and the choice over the item set, such that it gives additional degree of freedom for the recommendation system to opt on which factor is more prominent. Experimental results suggest the advantages of the proposed algorithm over the existing state-of-the-art algorithms for the recommendation system.
{"title":"Guided-Gated Recurrent Unit for Deep Learning-Based Recommendation System","authors":"I. Ardiyanto","doi":"10.1109/ICITEED.2019.8929970","DOIUrl":"https://doi.org/10.1109/ICITEED.2019.8929970","url":null,"abstract":"Discovering and drawing out the relationship between users and items in a service-based companies or organizations are the essence of a recommendation system. It attracts many researches trying to solve such problems. Here we address a novel approach for the recommendation system, incorporating the means of collaborative aspect between the users internal hidden patterns and the items or goods to be recommended. Unlike the existing methods, our algorithm introduces a guiding factor between the user hidden state and the choice over the item set, such that it gives additional degree of freedom for the recommendation system to opt on which factor is more prominent. Experimental results suggest the advantages of the proposed algorithm over the existing state-of-the-art algorithms for the recommendation system.","PeriodicalId":6598,"journal":{"name":"2019 11th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"18 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77754644","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 : 2019-10-01DOI: 10.1109/ICITEED.2019.8929944
Nattanon Krittayanawach, P. Vateekul
For vehicle detection, YOLOv3 has shown promising accuracy. Since the number of parameters in this network can be more than ten million parameters, it cannot be fit into a commodity camera. In this paper, we propose a compression mechanism designed specifically for YOLOv 3's network by removing unnecessary filters. Since YOLOv3 composes of two network components: backbone and pyramid networks, we propose a robust pruning mechanism to prune filters of each network separately. This can help to avoid over-pruning the network in some part of the model making our model more robust. There are two main pruning criteria investigated: Average Percentage of Zero (APoZ) and Sum Magnitude Weight. The experiment was conducted on UA-DETRAC. The results show that our compression mechanism with APoZ criterion can reduce more than 90% of the network size, while the accuracy is even higher than the full model for about 2%.
{"title":"Robust Compression Technique for YOLOv3 on Real-Time Vehicle Detection","authors":"Nattanon Krittayanawach, P. Vateekul","doi":"10.1109/ICITEED.2019.8929944","DOIUrl":"https://doi.org/10.1109/ICITEED.2019.8929944","url":null,"abstract":"For vehicle detection, YOLOv3 has shown promising accuracy. Since the number of parameters in this network can be more than ten million parameters, it cannot be fit into a commodity camera. In this paper, we propose a compression mechanism designed specifically for YOLOv 3's network by removing unnecessary filters. Since YOLOv3 composes of two network components: backbone and pyramid networks, we propose a robust pruning mechanism to prune filters of each network separately. This can help to avoid over-pruning the network in some part of the model making our model more robust. There are two main pruning criteria investigated: Average Percentage of Zero (APoZ) and Sum Magnitude Weight. The experiment was conducted on UA-DETRAC. The results show that our compression mechanism with APoZ criterion can reduce more than 90% of the network size, while the accuracy is even higher than the full model for about 2%.","PeriodicalId":6598,"journal":{"name":"2019 11th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"139 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86550030","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 : 2019-10-01DOI: 10.1109/ICITEED.2019.8929971
Rizki Firmansyah Setya Budi, Sarjiya, S. P. Hadi
A deregulated multi-objective generation expansion planning (DMGEP) has been modeled in the previous research. The research used loss of load probability (LOLP) as a reliability objective function. LOLP is a probabilistic reliability index that has a disadvantage on computation time. On the other hand, there is a deterministic reliability index that has an advantage on computation time. The deterministic reliability index is reserve margin (RM). This study will conduct a DMGEP by using two reliability index scenarios. The scenarios are LOLP scenario and RM scenario. This research aims to analyze the impact of using RM on DMGEP. To do the impact analysis, it is needed a comparison between LOLP scenario results and RM scenario results. Based on the results of both scenarios, it can be known the impacts of RM scenario. Using RM can accelerate computation time by 70.7% and cause additional total installed capacity of power plants. The total installed capacity in the RM scenario is higher of 3.2% than the LOLP scenario.
{"title":"The impact of a deterministic reliability index on deregulated multi-objective generation expansion planning","authors":"Rizki Firmansyah Setya Budi, Sarjiya, S. P. Hadi","doi":"10.1109/ICITEED.2019.8929971","DOIUrl":"https://doi.org/10.1109/ICITEED.2019.8929971","url":null,"abstract":"A deregulated multi-objective generation expansion planning (DMGEP) has been modeled in the previous research. The research used loss of load probability (LOLP) as a reliability objective function. LOLP is a probabilistic reliability index that has a disadvantage on computation time. On the other hand, there is a deterministic reliability index that has an advantage on computation time. The deterministic reliability index is reserve margin (RM). This study will conduct a DMGEP by using two reliability index scenarios. The scenarios are LOLP scenario and RM scenario. This research aims to analyze the impact of using RM on DMGEP. To do the impact analysis, it is needed a comparison between LOLP scenario results and RM scenario results. Based on the results of both scenarios, it can be known the impacts of RM scenario. Using RM can accelerate computation time by 70.7% and cause additional total installed capacity of power plants. The total installed capacity in the RM scenario is higher of 3.2% than the LOLP scenario.","PeriodicalId":6598,"journal":{"name":"2019 11th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"80 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91227457","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 : 2019-10-01DOI: 10.1109/ICITEED.2019.8929937
M. W. A. Kesiman, G. Pradnyana
The word spotting system is urgently needed to be able to work with thousand pages of digitized ancient Balinese palm leaf manuscript. This system will be very helpful for the scholars to perform a keyword searching in all manuscript collections with a query image. In this paper, we present a complete scheme of word spotting system for the Balinese palm leaf manuscripts. Our proposed complete scheme of word spotting system for the Balinese palm leaf manuscripts consists of three main sub schemes: the offline patch images extraction process, the feature extraction method, and the patch ranking scheme. We applied six filters of Gabor from six different orientations for the patch image extraction process, and we proposed the use of 64 Gabor filters which are combined with seven different Zoning methods for the feature extraction methods. We also propose an adaptive sliding patch algorithm to spot all possible patches in manuscript page and the patch ranking scheme to rank the spotting results. For the test and evaluation, we used a published dataset of AMADI_LontarSet. Our scheme shows a very promising results. The word spotting system is able to spot many query patch images in different manuscript pages.
{"title":"A Complete Scheme of Word Spotting System for the Balinese Palm Leaf Manuscripts","authors":"M. W. A. Kesiman, G. Pradnyana","doi":"10.1109/ICITEED.2019.8929937","DOIUrl":"https://doi.org/10.1109/ICITEED.2019.8929937","url":null,"abstract":"The word spotting system is urgently needed to be able to work with thousand pages of digitized ancient Balinese palm leaf manuscript. This system will be very helpful for the scholars to perform a keyword searching in all manuscript collections with a query image. In this paper, we present a complete scheme of word spotting system for the Balinese palm leaf manuscripts. Our proposed complete scheme of word spotting system for the Balinese palm leaf manuscripts consists of three main sub schemes: the offline patch images extraction process, the feature extraction method, and the patch ranking scheme. We applied six filters of Gabor from six different orientations for the patch image extraction process, and we proposed the use of 64 Gabor filters which are combined with seven different Zoning methods for the feature extraction methods. We also propose an adaptive sliding patch algorithm to spot all possible patches in manuscript page and the patch ranking scheme to rank the spotting results. For the test and evaluation, we used a published dataset of AMADI_LontarSet. Our scheme shows a very promising results. The word spotting system is able to spot many query patch images in different manuscript pages.","PeriodicalId":6598,"journal":{"name":"2019 11th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"6 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86760708","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 : 2019-10-01DOI: 10.1109/ICITEED.2019.8929946
B. Hantono, L. Nugroho, P. Santosa
In the last few years, the approach to introducing cognitive performance automatically gained significant scientific interest. Likewise, cognitive performance observation research using the method of collecting the results of objective measurements that occur in everyday life. Today almost everyone has a smartphone, and they have become partners in living their daily lives. The smartphone has been equipped with various kinds of sensors to facilitate its use and for its full features. The existence of sensors on a smartphone is also the potential to be used to obtain information and the user’s situation for a long time and does not disturb the user. Therefore, research using smartphone sensing provides research opportunities in the field of psychology, especially for observing the cognitive performance of users. This study aimed to investigate the possibility of using smartphones as a medium to detect cognitive performance in general outside laboratory conditions.
{"title":"Estimating Cognitive Performance Changes Based on Psychophysiological Sensor in the Smartphone: A Proposed Model","authors":"B. Hantono, L. Nugroho, P. Santosa","doi":"10.1109/ICITEED.2019.8929946","DOIUrl":"https://doi.org/10.1109/ICITEED.2019.8929946","url":null,"abstract":"In the last few years, the approach to introducing cognitive performance automatically gained significant scientific interest. Likewise, cognitive performance observation research using the method of collecting the results of objective measurements that occur in everyday life. Today almost everyone has a smartphone, and they have become partners in living their daily lives. The smartphone has been equipped with various kinds of sensors to facilitate its use and for its full features. The existence of sensors on a smartphone is also the potential to be used to obtain information and the user’s situation for a long time and does not disturb the user. Therefore, research using smartphone sensing provides research opportunities in the field of psychology, especially for observing the cognitive performance of users. This study aimed to investigate the possibility of using smartphones as a medium to detect cognitive performance in general outside laboratory conditions.","PeriodicalId":6598,"journal":{"name":"2019 11th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"35 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85152851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper describes the design of a hybrid leg-wheel robot. A hybrid leg-wheel robot is designed with the ability to walk, turn left, turn right and stand on the ground. The shape of a robot’s body is an equilateral triangle. Both front legs have been designed with three degrees of freedom. A back leg is designed with 2 omni-directional wheels without additional motors. This paper presents abilities that are walking, turning left, turning right and autonomous balancing. The PID controllers are proposed to control the robot’s position while robot is standing on the ground.
{"title":"Design of A Hybrid Leg-Wheel Robot","authors":"Supaphon Kamon, Uthai Aoungchareon, Sommart Thongkom","doi":"10.1109/ICITEED.2019.8929979","DOIUrl":"https://doi.org/10.1109/ICITEED.2019.8929979","url":null,"abstract":"This paper describes the design of a hybrid leg-wheel robot. A hybrid leg-wheel robot is designed with the ability to walk, turn left, turn right and stand on the ground. The shape of a robot’s body is an equilateral triangle. Both front legs have been designed with three degrees of freedom. A back leg is designed with 2 omni-directional wheels without additional motors. This paper presents abilities that are walking, turning left, turning right and autonomous balancing. The PID controllers are proposed to control the robot’s position while robot is standing on the ground.","PeriodicalId":6598,"journal":{"name":"2019 11th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"6 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87985847","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 : 2019-10-01DOI: 10.1109/iciteed.2019.8929993
{"title":"ICITEE 2019 Copyright Page","authors":"","doi":"10.1109/iciteed.2019.8929993","DOIUrl":"https://doi.org/10.1109/iciteed.2019.8929993","url":null,"abstract":"","PeriodicalId":6598,"journal":{"name":"2019 11th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"36 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88264302","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}
Dogs are one of the most common domestic animals. Due to a large number of dogs, there are several issues such as population control, decrease outbreak such as Rabies, vaccination control, and legal ownership. At present, there are over 180 dog breeds. Each dog breed has specific characteristics and health conditions. In order to provide appropriate treatments and training, it is essential to identify individuals and their breeds. The paper presents the classification methods for dog breed classification using two image processing approaches 1) conventional based approaches by Local Binary Pattern (LBP) and Histogram of Oriented Gradient (HOG) 2) the deep learning based approach by using convolutional neural networks (CNN) with transfer learning. The result shows that our retrained CNN model performs better in classifying a dog breeds. It achieves 96.75% accuracy compared with 79.25% using the HOG descriptor.
{"title":"Breakthrough Conventional Based Approach for Dog Breed Classification Using CNN with Transfer Learning","authors":"Punyanuch Borwarnginn, Kittikhun Thongkanchorn, Sarattha Kanchanapreechakorn, Worapan Kusakunniran","doi":"10.1109/ICITEED.2019.8929955","DOIUrl":"https://doi.org/10.1109/ICITEED.2019.8929955","url":null,"abstract":"Dogs are one of the most common domestic animals. Due to a large number of dogs, there are several issues such as population control, decrease outbreak such as Rabies, vaccination control, and legal ownership. At present, there are over 180 dog breeds. Each dog breed has specific characteristics and health conditions. In order to provide appropriate treatments and training, it is essential to identify individuals and their breeds. The paper presents the classification methods for dog breed classification using two image processing approaches 1) conventional based approaches by Local Binary Pattern (LBP) and Histogram of Oriented Gradient (HOG) 2) the deep learning based approach by using convolutional neural networks (CNN) with transfer learning. The result shows that our retrained CNN model performs better in classifying a dog breeds. It achieves 96.75% accuracy compared with 79.25% using the HOG descriptor.","PeriodicalId":6598,"journal":{"name":"2019 11th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"10 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89042680","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：