Pub Date : 2018-10-01DOI: 10.1109/ICICOS.2018.8621666
Sutrisno, Widowati, R. H. Tjahiana
In this paper, a dynamical model of single product inventory system with unknown demand in a linear state space equation with unknown parameter for inventory control purposes was formulated. An existing control method, robust linear quadratic regulator (RLQR), was applied to control the inventory level by generating the optimal purchasing product volume so that the product stock follows a reference trajectory with minimal cost. The result of the performed numerical experiments showed that the optimal purchasing product volume was determined for every time period and the product stock was closed to the given trajectory level desired by the decision maker.
{"title":"Application of Robust Linear Quadratic Control for Inventory System with Unknown Demand: Single Product Case","authors":"Sutrisno, Widowati, R. H. Tjahiana","doi":"10.1109/ICICOS.2018.8621666","DOIUrl":"https://doi.org/10.1109/ICICOS.2018.8621666","url":null,"abstract":"In this paper, a dynamical model of single product inventory system with unknown demand in a linear state space equation with unknown parameter for inventory control purposes was formulated. An existing control method, robust linear quadratic regulator (RLQR), was applied to control the inventory level by generating the optimal purchasing product volume so that the product stock follows a reference trajectory with minimal cost. The result of the performed numerical experiments showed that the optimal purchasing product volume was determined for every time period and the product stock was closed to the given trajectory level desired by the decision maker.","PeriodicalId":438473,"journal":{"name":"2018 2nd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126406572","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 : 2018-10-01DOI: 10.1109/ICICOS.2018.8621760
R. Efendi, N. Yanti, A. Wenda, Susnaningsih Mu’at, N. Samsudin, M. M. Deris
the ordinary least square model has been widely considered to estimate the significant factors which influence the student achievement. Some factor is qualitative type and measured using criteria or categories. However, the decisive criteria for each factor which affect to the cumulative grade point average of student cannot be determined by this model. In this paper, we are interested to build a new procedure using rough-regression model in determining the dominant criteria from each factor based on generalization of dependency attribute. Based on result, the proposed procedure is capable to investigate the dominant criteria and factors affecting student achievement, such as, language spoken with dominant criteria is “many-many”, FB friend with dominant criteria is “many” and fast food with dominant criteria is “never”. This proposed procedure is very appropriate to implement for handling categorical data.
{"title":"Dominant Criteria and Its Factor Affecting Student Achievement Based on Rough-Regression Model","authors":"R. Efendi, N. Yanti, A. Wenda, Susnaningsih Mu’at, N. Samsudin, M. M. Deris","doi":"10.1109/ICICOS.2018.8621760","DOIUrl":"https://doi.org/10.1109/ICICOS.2018.8621760","url":null,"abstract":"the ordinary least square model has been widely considered to estimate the significant factors which influence the student achievement. Some factor is qualitative type and measured using criteria or categories. However, the decisive criteria for each factor which affect to the cumulative grade point average of student cannot be determined by this model. In this paper, we are interested to build a new procedure using rough-regression model in determining the dominant criteria from each factor based on generalization of dependency attribute. Based on result, the proposed procedure is capable to investigate the dominant criteria and factors affecting student achievement, such as, language spoken with dominant criteria is “many-many”, FB friend with dominant criteria is “many” and fast food with dominant criteria is “never”. This proposed procedure is very appropriate to implement for handling categorical data.","PeriodicalId":438473,"journal":{"name":"2018 2nd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132696725","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 : 2018-10-01DOI: 10.1109/ICICOS.2018.8621783
E. Widiyanti, S. Endah
Feature selection is step in preprocessing that can be used to reduce data dimension and eliminate the irrelevan data. There are several algorithms in feature selection. This study will compare several feature selection algorithms, namely Sequential Forward Selection, Sequential Backward Selection, and Relief F to find features that are very influential in musical emotional recognition. The method in music emotion recognition uses Support Vector Machine with the RBF kernel. The experimental results show that based on the recognition results with the highest accuracy, the most influential features are the zero crossing rate, music mode, harmonics, pitch and energy obtained through the Sequential Backward Selection algorithm. The selection of features in this study can increase accuracy up to 8%.
{"title":"Feature Selection for Music Emotion Recognition","authors":"E. Widiyanti, S. Endah","doi":"10.1109/ICICOS.2018.8621783","DOIUrl":"https://doi.org/10.1109/ICICOS.2018.8621783","url":null,"abstract":"Feature selection is step in preprocessing that can be used to reduce data dimension and eliminate the irrelevan data. There are several algorithms in feature selection. This study will compare several feature selection algorithms, namely Sequential Forward Selection, Sequential Backward Selection, and Relief F to find features that are very influential in musical emotional recognition. The method in music emotion recognition uses Support Vector Machine with the RBF kernel. The experimental results show that based on the recognition results with the highest accuracy, the most influential features are the zero crossing rate, music mode, harmonics, pitch and energy obtained through the Sequential Backward Selection algorithm. The selection of features in this study can increase accuracy up to 8%.","PeriodicalId":438473,"journal":{"name":"2018 2nd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124707359","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 : 2018-10-01DOI: 10.1109/ICICOS.2018.8621842
Gabe Dhiar Simorangkir, E. Sarwoko, P. S. Sasongko, Sutikno, S. Endah
Corn has become one of the most prevalent key food production in various countries worldwide due to its high nutritional content. However, corn is prone to diseases or pests which might severely hamper its cultivation. Therefore, Online At Sawah (OAS) is developed in order to do detection of diseases or pests suffered by the corn based on the symptoms given by the users using decision tree method. In accordance with the detected diseases or pests acquired, OAS is going to further provide proper solutions to treat such corn diseases or pests for the users. The challenge that OAS should handle is pertaining to how its quality can be guaranteed in order to be accepted well by the users. To ensure that the quality of the application is in good condition, it's imperative to conduct usability testing as means to acquire the value of satisfaction, learnability, efficiency, and effectiveness of the mobile application as the assessments for further improvement in the future. Without usability testing, the application may cause unacceptable troubles for the users. In this research, ten participants from different professions in agricultural field were gathered as subjects for the conduct of usability testing to evaluate the application. They were asked to finish/complete the given tasks and answer the questionnaires as means to assess the application. In the end, the results obviously portray that OAS has good/excellent value of effectiveness as much as 82,5; efficiency as much as 93,12%; learnability as much as 77,33%; and satisfaction as much as 73%.
玉米因其高营养成分，已成为世界各国最普遍的主要粮食生产之一。然而，玉米容易发生疾病或害虫，这可能严重阻碍其种植。因此，开发了Online At Sawah (OAS)，以便根据用户使用决策树方法给出的症状对玉米遭受的病虫害进行检测。美洲国家组织将根据所获得的检测到的病虫害，进一步为用户提供适当的解决方案来处理这些玉米病虫害。美洲国家组织应该处理的挑战是如何保证其质量，以便为用户所接受。为了确保应用的质量处于良好状态，必须进行可用性测试，以获取移动应用的满意度、可学习性、效率和有效性的价值，作为未来进一步改进的评估。如果没有可用性测试，应用程序可能会给用户带来不可接受的麻烦。在本研究中，从农业领域的不同专业中收集了10名参与者作为研究对象，进行可用性测试，以评估应用。他们被要求完成给定的任务并回答问卷，作为评估应用程序的手段。最后，结果明显表明，OAS具有良好/优良的有效性值高达82,5;效率高达93、12%;易学程度高达77.33%;满意度高达73%。
{"title":"Usability Testing of Corn Diseases and Pests Detection on a Mobile Application","authors":"Gabe Dhiar Simorangkir, E. Sarwoko, P. S. Sasongko, Sutikno, S. Endah","doi":"10.1109/ICICOS.2018.8621842","DOIUrl":"https://doi.org/10.1109/ICICOS.2018.8621842","url":null,"abstract":"Corn has become one of the most prevalent key food production in various countries worldwide due to its high nutritional content. However, corn is prone to diseases or pests which might severely hamper its cultivation. Therefore, Online At Sawah (OAS) is developed in order to do detection of diseases or pests suffered by the corn based on the symptoms given by the users using decision tree method. In accordance with the detected diseases or pests acquired, OAS is going to further provide proper solutions to treat such corn diseases or pests for the users. The challenge that OAS should handle is pertaining to how its quality can be guaranteed in order to be accepted well by the users. To ensure that the quality of the application is in good condition, it's imperative to conduct usability testing as means to acquire the value of satisfaction, learnability, efficiency, and effectiveness of the mobile application as the assessments for further improvement in the future. Without usability testing, the application may cause unacceptable troubles for the users. In this research, ten participants from different professions in agricultural field were gathered as subjects for the conduct of usability testing to evaluate the application. They were asked to finish/complete the given tasks and answer the questionnaires as means to assess the application. In the end, the results obviously portray that OAS has good/excellent value of effectiveness as much as 82,5; efficiency as much as 93,12%; learnability as much as 77,33%; and satisfaction as much as 73%.","PeriodicalId":438473,"journal":{"name":"2018 2nd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132428026","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 : 2018-10-01DOI: 10.1109/ICICOS.2018.8621736
Muhammad Iqbal Fadholi, Suhartono, P. S. Sasongko, Sutikno
Quadcopter is a helicopter VAV that uses four rotors of propeller to maneuver [1]. Some Quadcopter development uses the concept of artificial intelligence behavior-based intelligent fuzzy control (BBIFC). Some quadcopter maneuver movements that are currently being developed include cooperative movement between quadcopter, rotating and reversing movements, ball throwing movements, obstacle avoidance movements, ball capture movements, and automation of balancing motion on quadcopter. The balancing motion includes balancing when flying at a certain position, balancing for landing, and balancing when carrying loads [2]. Autonomous Pole Balancing on Quadcopter has been designed and implemented using Behavior-Based Intelligent Fuzzy Control, the design of automation of quadcopter motion in balancing with carrying loads namely a pole placed on a quadcopter. Quadcopter is used to balance the pole, so that in one calculation cycle must be completed before the pole falls. With an angle of 800 tolerance, the pole will arrive at the slope angle within 1 second, so that, in one calculation cycle must be completed in less than 1 second.
{"title":"Autonomous Pole Balancing Design In Quadcopter Using Behaviour-Based Intelligent Fuzzy Control","authors":"Muhammad Iqbal Fadholi, Suhartono, P. S. Sasongko, Sutikno","doi":"10.1109/ICICOS.2018.8621736","DOIUrl":"https://doi.org/10.1109/ICICOS.2018.8621736","url":null,"abstract":"Quadcopter is a helicopter VAV that uses four rotors of propeller to maneuver [1]. Some Quadcopter development uses the concept of artificial intelligence behavior-based intelligent fuzzy control (BBIFC). Some quadcopter maneuver movements that are currently being developed include cooperative movement between quadcopter, rotating and reversing movements, ball throwing movements, obstacle avoidance movements, ball capture movements, and automation of balancing motion on quadcopter. The balancing motion includes balancing when flying at a certain position, balancing for landing, and balancing when carrying loads [2]. Autonomous Pole Balancing on Quadcopter has been designed and implemented using Behavior-Based Intelligent Fuzzy Control, the design of automation of quadcopter motion in balancing with carrying loads namely a pole placed on a quadcopter. Quadcopter is used to balance the pole, so that in one calculation cycle must be completed before the pole falls. With an angle of 800 tolerance, the pole will arrive at the slope angle within 1 second, so that, in one calculation cycle must be completed in less than 1 second.","PeriodicalId":438473,"journal":{"name":"2018 2nd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130799435","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 : 2018-10-01DOI: 10.1109/ICICOS.2018.8621803
Anisa Dewi Prajanti, Bambang Wahyuaji, Fandhy Bayu Rukmana, R. Harwahyu, R. F. Sari
The integration of LoRA modulation methods in the LPWAN wireless network and the LoRaWanprotocol network is utilized in LoRa technology, which provides long range coverage to end devices in license-free frequency bands. Implementation of this technology covers a broad range of fields, from smart house and Internet of Things (IoT) to industry and Smart Cities. In this article, we conducted simulation of LoRaWAN deployment in Jakarta area using NS3 simulator. We calculated the total number of end devices for Jakarta area coverage that gives the best performance. Jakarta has 662,33 km2 area with many buildings, especially high rise buildings. Our simulation results with various gateway radiuses indicate that best performances are reached in 3000 m for smaller and 6500 m for larger radius. Optimum number of end devices that covered by each gateway is 3000. Estimated number of gateways is 26, so it takes up to 78.000 end devices for entire Jakarta. From economic consideration, service provider will optimize its capital expenditure in about five years by deployment of 1750 end devices which will grow up to 3049 on the next fifth year while maintain its Packet Success Rate above 91%.
{"title":"Performance Analysis of LoRa WAnTechnology for Optimum Deployment of Jakarta Smart City","authors":"Anisa Dewi Prajanti, Bambang Wahyuaji, Fandhy Bayu Rukmana, R. Harwahyu, R. F. Sari","doi":"10.1109/ICICOS.2018.8621803","DOIUrl":"https://doi.org/10.1109/ICICOS.2018.8621803","url":null,"abstract":"The integration of LoRA modulation methods in the LPWAN wireless network and the LoRaWanprotocol network is utilized in LoRa technology, which provides long range coverage to end devices in license-free frequency bands. Implementation of this technology covers a broad range of fields, from smart house and Internet of Things (IoT) to industry and Smart Cities. In this article, we conducted simulation of LoRaWAN deployment in Jakarta area using NS3 simulator. We calculated the total number of end devices for Jakarta area coverage that gives the best performance. Jakarta has 662,33 km2 area with many buildings, especially high rise buildings. Our simulation results with various gateway radiuses indicate that best performances are reached in 3000 m for smaller and 6500 m for larger radius. Optimum number of end devices that covered by each gateway is 3000. Estimated number of gateways is 26, so it takes up to 78.000 end devices for entire Jakarta. From economic consideration, service provider will optimize its capital expenditure in about five years by deployment of 1750 end devices which will grow up to 3049 on the next fifth year while maintain its Packet Success Rate above 91%.","PeriodicalId":438473,"journal":{"name":"2018 2nd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"166 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120941310","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 : 2018-10-01DOI: 10.1109/ICICOS.2018.8621644
E. Putri, J. L. Buliali, Myrna Ermawati
We observe the use of data from social media for traffic simulation in a situation where there is an incident in a road. The required data to run the simulation do not come at once. Rather, one traffic incident message will be followed later by other messages which may or may not contain additional required data related to the incident. These messages have to be monitored in real-time. We propose the use of text similarity method, time relevance concepts, and state machine diagram for detecting the degree of data completeness for traffic simulation in real time. The degree of data completeness determines the initialization and execution of simulation. Evaluation shows that the performance of the system using text similarity and time relevance weighting method is better than that of the system using text similarity only. Analyzing the state diagram shows that simulation execution can be controlled in various degree of information entities completeness. The system changes to the subsequent state depending on which other information entities become available. The more the available information entities are, the higher simulation results can be obtained. This is because the more complete information entities mean less uncertainty about the place and/or the beginning time of the incident in the simulation execution.
{"title":"Real-time Detection of Data Completeness Degree for Traffic Simulation Using Text Similarity and Time Relevance of Data from Social Media","authors":"E. Putri, J. L. Buliali, Myrna Ermawati","doi":"10.1109/ICICOS.2018.8621644","DOIUrl":"https://doi.org/10.1109/ICICOS.2018.8621644","url":null,"abstract":"We observe the use of data from social media for traffic simulation in a situation where there is an incident in a road. The required data to run the simulation do not come at once. Rather, one traffic incident message will be followed later by other messages which may or may not contain additional required data related to the incident. These messages have to be monitored in real-time. We propose the use of text similarity method, time relevance concepts, and state machine diagram for detecting the degree of data completeness for traffic simulation in real time. The degree of data completeness determines the initialization and execution of simulation. Evaluation shows that the performance of the system using text similarity and time relevance weighting method is better than that of the system using text similarity only. Analyzing the state diagram shows that simulation execution can be controlled in various degree of information entities completeness. The system changes to the subsequent state depending on which other information entities become available. The more the available information entities are, the higher simulation results can be obtained. This is because the more complete information entities mean less uncertainty about the place and/or the beginning time of the incident in the simulation execution.","PeriodicalId":438473,"journal":{"name":"2018 2nd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115163542","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 : 2018-10-01DOI: 10.1109/icicos.2018.8621729
{"title":"Copyright","authors":"","doi":"10.1109/icicos.2018.8621729","DOIUrl":"https://doi.org/10.1109/icicos.2018.8621729","url":null,"abstract":"","PeriodicalId":438473,"journal":{"name":"2018 2nd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114333282","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 : 2018-10-01DOI: 10.1109/ICICOS.2018.8621781
Rismiyati, Khadijah, D. E. Riyanto
The recognition of handwritten characters remain one of challenging task in character recognition problems. The variations created by each person in writing the characters affect the character recognition result. Many studies have been performed to increase the performance of Javanese character recognition. The efforts are to extract the best feature for classification or to get the best classifier for classification. In this study, HOG feature and Zoning Based Feature will be used to classify Javanese Characters. The performance of both features will be compared for classifying Javanese character by using SVM classifier. Two types of inputs will be used for each feature extractor, binary and skeleton of the character image. The experiment showed that HOG feature is able to show higher accuracy as compared to the simple zone based feature (88.45%). The best accuracy for HOG is achieved by using binary input. On the other hand, despite its simplicity zone based feature is able to achive 81.98% accuracy by using skeleton input. Considering that the zone based feature used in this research is simply the pixel count in each zone, future research may be performed to extract more statistical properties on each zone. Future works may also focus on rotation free feature extraction for Javanese character classification.
手写体字符的识别一直是字符识别领域的难点之一。每个人在书写汉字时产生的差异会影响汉字识别的结果。为了提高爪哇文字识别的性能，已经进行了许多研究。其目的是提取最佳特征进行分类，或者得到最佳分类器进行分类。本研究将使用HOG特征和Zoning Based feature对爪哇文字进行分类。比较了这两种特征在使用SVM分类器进行爪哇文字分类时的性能。对于每个特征提取器，将使用两种类型的输入，即字符图像的二进制和骨架。实验表明，HOG特征比简单的基于区域的特征具有更高的准确率(88.45%)。采用二进制输入可以达到最佳的HOG精度。另一方面，基于区域的特征虽然简单，但使用骨架输入可以达到81.98%的准确率。考虑到本研究中使用的基于区域的特征仅仅是每个区域的像素数，未来的研究可以提取更多关于每个区域的统计属性。未来的工作还可能集中在爪哇文字分类的无旋转特征提取上。
{"title":"HOG and Zone Base Features for Handwritten Javanese Character Classification","authors":"Rismiyati, Khadijah, D. E. Riyanto","doi":"10.1109/ICICOS.2018.8621781","DOIUrl":"https://doi.org/10.1109/ICICOS.2018.8621781","url":null,"abstract":"The recognition of handwritten characters remain one of challenging task in character recognition problems. The variations created by each person in writing the characters affect the character recognition result. Many studies have been performed to increase the performance of Javanese character recognition. The efforts are to extract the best feature for classification or to get the best classifier for classification. In this study, HOG feature and Zoning Based Feature will be used to classify Javanese Characters. The performance of both features will be compared for classifying Javanese character by using SVM classifier. Two types of inputs will be used for each feature extractor, binary and skeleton of the character image. The experiment showed that HOG feature is able to show higher accuracy as compared to the simple zone based feature (88.45%). The best accuracy for HOG is achieved by using binary input. On the other hand, despite its simplicity zone based feature is able to achive 81.98% accuracy by using skeleton input. Considering that the zone based feature used in this research is simply the pixel count in each zone, future research may be performed to extract more statistical properties on each zone. Future works may also focus on rotation free feature extraction for Javanese character classification.","PeriodicalId":438473,"journal":{"name":"2018 2nd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117127548","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 : 2018-10-01DOI: 10.1109/ICICOS.2018.8621657
Khadijah, S. Endah, R. Kusumaningrum, Rismiyati
Microarray data classification has a great challenge due to number of samples which is much smaller compared to the number of genes. The problem is getting harder when the dataset has multiclass target and the number of samples in each class is not well distributed (which is called imbalance data distribution). In this research, two different approaches to handle imbalance data distribution are studied, they are SMOTE (based on data approach) and weighted ELM (based on algorithmic approach). To evaluate the performance of the proposed method, two public imbalanced multiclass microarray dataset are used, GCM (Global Cancer Map) and Subtypes-Leukemia dataset. The results of experiment show that the implementation of SMOTE and weighted ELM on GCM dataset have no significant effect in the classification performance. Different with the Subtypes-Leukemia dataset, the implementation of SMOTE and weighted ELM has improved the classification performance compared to the previous research. Generally, the results show that weighted ELM perform slightly better compared to SMOTE to increase the accuracy of the minority class.
由于样本数量远小于基因数量，微阵列数据分类具有很大的挑战。当数据集具有多类目标并且每个类中的样本数量分布不好(称为不平衡数据分布)时，问题变得更加困难。本文研究了两种不同的处理不平衡数据分布的方法，即SMOTE(基于数据方法)和加权ELM(基于算法方法)。为了评估该方法的性能，使用了两个公开的不平衡多类微阵列数据集，GCM (Global Cancer Map)和Subtypes-Leukemia数据集。实验结果表明，在GCM数据集上实现SMOTE和加权ELM对分类性能没有显著影响。与Subtypes-Leukemia数据集不同，SMOTE和加权ELM的实现比以往的研究提高了分类性能。通常，结果表明加权ELM比SMOTE在提高少数类别的准确性方面表现略好。
{"title":"The Study of Synthetic Minority Over-sampling Technique (SMOTE) and Weighted Extreme Learning Machine for Handling Imbalance Problem on Multiclass Microarray classification","authors":"Khadijah, S. Endah, R. Kusumaningrum, Rismiyati","doi":"10.1109/ICICOS.2018.8621657","DOIUrl":"https://doi.org/10.1109/ICICOS.2018.8621657","url":null,"abstract":"Microarray data classification has a great challenge due to number of samples which is much smaller compared to the number of genes. The problem is getting harder when the dataset has multiclass target and the number of samples in each class is not well distributed (which is called imbalance data distribution). In this research, two different approaches to handle imbalance data distribution are studied, they are SMOTE (based on data approach) and weighted ELM (based on algorithmic approach). To evaluate the performance of the proposed method, two public imbalanced multiclass microarray dataset are used, GCM (Global Cancer Map) and Subtypes-Leukemia dataset. The results of experiment show that the implementation of SMOTE and weighted ELM on GCM dataset have no significant effect in the classification performance. Different with the Subtypes-Leukemia dataset, the implementation of SMOTE and weighted ELM has improved the classification performance compared to the previous research. Generally, the results show that weighted ELM perform slightly better compared to SMOTE to increase the accuracy of the minority class.","PeriodicalId":438473,"journal":{"name":"2018 2nd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128751577","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：