Pub Date : 2014-10-20DOI: 10.1109/ICITACEE.2014.7065756
Hermawan Prasetyo, A. Purwarianti
Clustering is one of the most popular methods in data mining. Many algorithms can be applied for data clustering with numeric or categorical attributes. However, most of data in the real world contain both numeric and categorical attributes. A clustering method which can be applied on attributes in mix types become important to handle the problem. K-prototypes algorithm is one of the algorithms which can deal for clustering data with mix attribute types. However, it has a drawback on its dissimilarity measure between categorical data. The selection of proper dissimilarity measure between categorical data is thus important to increase its performance. This paper compares distance and dissimilarity measures for clustering data with mix attribute types. We used the k-prototypes algorithm on UCI datasets, i.e. Echocardiogram, Hepatitis, and Zoo, to assign cluster membership of the objects. Silhouette index was employed to evaluate clustering results. The results show that Euclidean distance and Ratio on Mismatches dissimilarity are the best combination for clustering data with numeric and categorical attribute types, as it shown with average Silhouette index towards 1. As a result, to cluster data with mix attribute types, we propose to employ Euclidean distance and Ratio on Mismatches dissimilarity to be applied on k-prototypes algorithm.
聚类是数据挖掘中最流行的方法之一。许多算法可以应用于具有数字或分类属性的数据聚类。然而，现实世界中的大多数数据都包含数值属性和分类属性。一种适用于混合类型属性的聚类方法对于解决这一问题至关重要。k -原型算法是一种处理混合属性类型数据聚类的算法。然而，它在分类数据之间的不相似度量上有一个缺点。因此，在分类数据之间选择合适的不相似度量对于提高分类数据的性能具有重要意义。本文比较了混合属性类型数据聚类的距离度量和不相似度量。我们在UCI数据集(即Echocardiogram, Hepatitis, and Zoo)上使用k-prototype算法来分配对象的聚类隶属度。采用剪影指数评价聚类结果。结果表明，对于数值和分类属性类型的聚类数据，欧几里得距离和错配不相似度比是最佳组合，剪影指数平均趋近于1。因此，为了对混合属性类型的数据进行聚类，我们提出将欧几里得距离和错配不相似率应用于k-原型算法。
{"title":"Comparison of distance and dissimilarity measures for clustering data with mix attribute types","authors":"Hermawan Prasetyo, A. Purwarianti","doi":"10.1109/ICITACEE.2014.7065756","DOIUrl":"https://doi.org/10.1109/ICITACEE.2014.7065756","url":null,"abstract":"Clustering is one of the most popular methods in data mining. Many algorithms can be applied for data clustering with numeric or categorical attributes. However, most of data in the real world contain both numeric and categorical attributes. A clustering method which can be applied on attributes in mix types become important to handle the problem. K-prototypes algorithm is one of the algorithms which can deal for clustering data with mix attribute types. However, it has a drawback on its dissimilarity measure between categorical data. The selection of proper dissimilarity measure between categorical data is thus important to increase its performance. This paper compares distance and dissimilarity measures for clustering data with mix attribute types. We used the k-prototypes algorithm on UCI datasets, i.e. Echocardiogram, Hepatitis, and Zoo, to assign cluster membership of the objects. Silhouette index was employed to evaluate clustering results. The results show that Euclidean distance and Ratio on Mismatches dissimilarity are the best combination for clustering data with numeric and categorical attribute types, as it shown with average Silhouette index towards 1. As a result, to cluster data with mix attribute types, we propose to employ Euclidean distance and Ratio on Mismatches dissimilarity to be applied on k-prototypes algorithm.","PeriodicalId":404830,"journal":{"name":"2014 The 1st International Conference on Information Technology, Computer, and Electrical Engineering","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128214618","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 : 2014-10-20DOI: 10.1109/ICITACEE.2014.7065774
I. Abadi, A. Soeprijanto, A. Musyafa
Solar radiation is a source of alternative energy that is very influential on the photovoltaic performance in generating energy. The need for solar radiation estimation has become a significant feature in the design of photovoltaic (PV) systems. Recently, the most popular method used to estimate solar radiation is artificial neural network (ANN). However, a new approach, called the extreme learning machine (ELM) algorithm is a new learning method of feed forward neural network with one hidden layer or known as Single Hidden Layer Feed Forward Neural Network (SLFN). In this research, ELM and a multilayer feed-forward network with back propagation are implemented to estimate hourly solar radiation on horizontal surface in Surabaya. In contrast to previous researches, this study has emphasized the use of meteorological data such as temperature, humidity, wind speed, and direction of speed as inputs for ANN and ELM model in estimating solar radiation. The MSE and learning rate has been used to measure the performance of two methods. The simulation results showed that the ELM model built had best performance for 400 nodes in which MSE and learning rate achieved were 5,88e-14 and 0,0156 second, respectively. The values were much smaller compared with the results of ANN. Overall, the ELM provided a better performance.
{"title":"Extreme learning machine approach to estimate hourly solar radiation on horizontal surface (PV) in Surabaya -East java","authors":"I. Abadi, A. Soeprijanto, A. Musyafa","doi":"10.1109/ICITACEE.2014.7065774","DOIUrl":"https://doi.org/10.1109/ICITACEE.2014.7065774","url":null,"abstract":"Solar radiation is a source of alternative energy that is very influential on the photovoltaic performance in generating energy. The need for solar radiation estimation has become a significant feature in the design of photovoltaic (PV) systems. Recently, the most popular method used to estimate solar radiation is artificial neural network (ANN). However, a new approach, called the extreme learning machine (ELM) algorithm is a new learning method of feed forward neural network with one hidden layer or known as Single Hidden Layer Feed Forward Neural Network (SLFN). In this research, ELM and a multilayer feed-forward network with back propagation are implemented to estimate hourly solar radiation on horizontal surface in Surabaya. In contrast to previous researches, this study has emphasized the use of meteorological data such as temperature, humidity, wind speed, and direction of speed as inputs for ANN and ELM model in estimating solar radiation. The MSE and learning rate has been used to measure the performance of two methods. The simulation results showed that the ELM model built had best performance for 400 nodes in which MSE and learning rate achieved were 5,88e-14 and 0,0156 second, respectively. The values were much smaller compared with the results of ANN. Overall, the ELM provided a better performance.","PeriodicalId":404830,"journal":{"name":"2014 The 1st International Conference on Information Technology, Computer, and Electrical Engineering","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126967701","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 : 2014-10-20DOI: 10.1109/ICITACEE.2014.7065726
Harindra Wisnu Pradhana
Computer vision been used to estimate object location relatively from observer on many applications. High definition sensor often used to gain accuracy of the object tracking which resulting high processing complexity. Lower resolution sensor simplifies the process with significant accuracy lost. Particle clustering method estimates the object location by grouping several detection data with certain similarity. Instead of detecting edges and corner on the visual data, this paper uses clustering method to group pixels with certain similarity and measure its element. The cluster measured both height and width to estimate the distance of the object from the observer. New color features introduced in this research promising a better detection approach even with low resolution sensor. The proposed approach successfully provides 30fps image analysis with significant color extraction improvement.
{"title":"Visual object tracking using particle clustering","authors":"Harindra Wisnu Pradhana","doi":"10.1109/ICITACEE.2014.7065726","DOIUrl":"https://doi.org/10.1109/ICITACEE.2014.7065726","url":null,"abstract":"Computer vision been used to estimate object location relatively from observer on many applications. High definition sensor often used to gain accuracy of the object tracking which resulting high processing complexity. Lower resolution sensor simplifies the process with significant accuracy lost. Particle clustering method estimates the object location by grouping several detection data with certain similarity. Instead of detecting edges and corner on the visual data, this paper uses clustering method to group pixels with certain similarity and measure its element. The cluster measured both height and width to estimate the distance of the object from the observer. New color features introduced in this research promising a better detection approach even with low resolution sensor. The proposed approach successfully provides 30fps image analysis with significant color extraction improvement.","PeriodicalId":404830,"journal":{"name":"2014 The 1st International Conference on Information Technology, Computer, and Electrical Engineering","volume":"75 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113982881","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 : 2014-10-20DOI: 10.1109/ICITACEE.2014.7065733
Bagas Sakamulia Prakoso, Ivanna K. Timotius, Iwan Setyawan
Human palmprints contain biometric features that can be used to identify an individual. These features can be used for example in user verification applications. This paper presents a user verification system using palmprint identification. The image of the palm is captured using a web camera. Then the features used for palmprint identification is extracted using line detection and local standard deviation. The proposed system is evaluated by asking 40 subjects to act as users (10 subject as registered users and 30 non-registered users). Our experiments show that the system can achieve accuracy rate of up to 98% with no false acceptance and 2% false rejection rate. The average time required to perform a user verification is 340 ms.
{"title":"Palmprint identification for user verification based on line detection and local standard deviation","authors":"Bagas Sakamulia Prakoso, Ivanna K. Timotius, Iwan Setyawan","doi":"10.1109/ICITACEE.2014.7065733","DOIUrl":"https://doi.org/10.1109/ICITACEE.2014.7065733","url":null,"abstract":"Human palmprints contain biometric features that can be used to identify an individual. These features can be used for example in user verification applications. This paper presents a user verification system using palmprint identification. The image of the palm is captured using a web camera. Then the features used for palmprint identification is extracted using line detection and local standard deviation. The proposed system is evaluated by asking 40 subjects to act as users (10 subject as registered users and 30 non-registered users). Our experiments show that the system can achieve accuracy rate of up to 98% with no false acceptance and 2% false rejection rate. The average time required to perform a user verification is 340 ms.","PeriodicalId":404830,"journal":{"name":"2014 The 1st International Conference on Information Technology, Computer, and Electrical Engineering","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114602900","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 : 2014-10-20DOI: 10.1109/ICITACEE.2014.7065777
R. Syahputra, I. Robandi, M. Ashari
This paper presents an optimal distribution network reconfiguration with penetration of distributed energy resources (DER). The reconfiguration is done to achieve the minimum active power loss of radial distribution networks with DER penetration. As a further matter, the presence of DER to the distribution systems has become some problems such the increase of the voltage at which there are many DER. In this study, the technique of network reconfiguration is based on an extended fuzzy multi-objective. Multi-objective function are considered for the power loss minimization, deviation of bus voltage, and load balancing among the feeders, while subject to a radial network structure in which all loads must be energized. The extended fuzzy multi-objective for reconfiguration of distribution network has been tested on Yogyakarta 60-bus distribution network data. The test results show that a 3.83% of Yogyakarta 60-bus network power loss reduction is achieved by the method. Also, the improvement of the voltage profile at each bus is also achieved with this method.
{"title":"Optimal distribution network reconfiguration with penetration of distributed energy resources","authors":"R. Syahputra, I. Robandi, M. Ashari","doi":"10.1109/ICITACEE.2014.7065777","DOIUrl":"https://doi.org/10.1109/ICITACEE.2014.7065777","url":null,"abstract":"This paper presents an optimal distribution network reconfiguration with penetration of distributed energy resources (DER). The reconfiguration is done to achieve the minimum active power loss of radial distribution networks with DER penetration. As a further matter, the presence of DER to the distribution systems has become some problems such the increase of the voltage at which there are many DER. In this study, the technique of network reconfiguration is based on an extended fuzzy multi-objective. Multi-objective function are considered for the power loss minimization, deviation of bus voltage, and load balancing among the feeders, while subject to a radial network structure in which all loads must be energized. The extended fuzzy multi-objective for reconfiguration of distribution network has been tested on Yogyakarta 60-bus distribution network data. The test results show that a 3.83% of Yogyakarta 60-bus network power loss reduction is achieved by the method. Also, the improvement of the voltage profile at each bus is also achieved with this method.","PeriodicalId":404830,"journal":{"name":"2014 The 1st International Conference on Information Technology, Computer, and Electrical Engineering","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129278935","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 : 2014-10-20DOI: 10.1109/ICITACEE.2014.7065747
S. Mardiana
This paper aims to propose a framework for assessing information system (IS) success considering the impact of culture. Previous frameworks for assessing information system (IS) success, such as DeLone and McLean model, only concern about the status of IS implementation itself. But none of the models have included the dimensions for assessing culture even though researchers have shown the strong relationship between culture and the success (or failure) of the IS. The inclusion of culture in the IS success model is very important, especially in Indonesia, since culture plays as a dominant part in almost all aspects of citizen's lives. This paper is expected to make a contribution on providing a framework for assessing IS success considering the impact of culture. To validate the proposed model, a mixed-method research design is proposed.
{"title":"An integrated framework for measuring information system success considering the impact of culture in Indonesia","authors":"S. Mardiana","doi":"10.1109/ICITACEE.2014.7065747","DOIUrl":"https://doi.org/10.1109/ICITACEE.2014.7065747","url":null,"abstract":"This paper aims to propose a framework for assessing information system (IS) success considering the impact of culture. Previous frameworks for assessing information system (IS) success, such as DeLone and McLean model, only concern about the status of IS implementation itself. But none of the models have included the dimensions for assessing culture even though researchers have shown the strong relationship between culture and the success (or failure) of the IS. The inclusion of culture in the IS success model is very important, especially in Indonesia, since culture plays as a dominant part in almost all aspects of citizen's lives. This paper is expected to make a contribution on providing a framework for assessing IS success considering the impact of culture. To validate the proposed model, a mixed-method research design is proposed.","PeriodicalId":404830,"journal":{"name":"2014 The 1st International Conference on Information Technology, Computer, and Electrical Engineering","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132499258","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 : 2014-10-20DOI: 10.1109/ICITACEE.2014.7065719
Vipin Gemini
Decimal floating point arithmetic is gaining importance because of its higher accuracy for financial, commercial and Web based applications. However, the binary floating point arithmetic is needed for scientific applications. Both these applications require general purpose processors (GPPs) for their execution. GPPs have separate hardware for decimal and binary floating point operations and therefore need a large area for their implementation. In this paper, we present a runtime reconfigurable floating point adder which targets both decimal and binary floating point addition on same hardware. The proposed design is 24.53% area efficient and approximately 7.6% faster than the previously reported designs. However, it is 6.3% slower for binary inputs.
{"title":"Reconfigurable floating point adder","authors":"Vipin Gemini","doi":"10.1109/ICITACEE.2014.7065719","DOIUrl":"https://doi.org/10.1109/ICITACEE.2014.7065719","url":null,"abstract":"Decimal floating point arithmetic is gaining importance because of its higher accuracy for financial, commercial and Web based applications. However, the binary floating point arithmetic is needed for scientific applications. Both these applications require general purpose processors (GPPs) for their execution. GPPs have separate hardware for decimal and binary floating point operations and therefore need a large area for their implementation. In this paper, we present a runtime reconfigurable floating point adder which targets both decimal and binary floating point addition on same hardware. The proposed design is 24.53% area efficient and approximately 7.6% faster than the previously reported designs. However, it is 6.3% slower for binary inputs.","PeriodicalId":404830,"journal":{"name":"2014 The 1st International Conference on Information Technology, Computer, and Electrical Engineering","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114316732","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 : 2014-10-20DOI: 10.1109/ICITACEE.2014.7065727
Prati Hutari Gani, M. Abdurohman
Selective encryption is a technique to encrypt a portion of the video data. In this case, it is encrypted by RSA algorithm. It is one of the public - key cryptosystem that is used to provide privacy and authentication of digital data. Security of this algorithm lies in the difficulty of factoring very large modulus n. In this project, the video format are MPEG - 1 and MPEG - 2, because they have almost the same bit stream structure, so the processing by using an algorithm. In this final project will be built a software using the Java platform. Testing on this project to encrypt and decrypt video formats, MPEG-1 and MPEG-2, so the security of video can be realized by using the method of selective encryption. Other parameters are the key length in the RSA algorithm which has been adapted and Brute Force Attacks.
{"title":"Selective encryption of video MPEG use RSA algorithm","authors":"Prati Hutari Gani, M. Abdurohman","doi":"10.1109/ICITACEE.2014.7065727","DOIUrl":"https://doi.org/10.1109/ICITACEE.2014.7065727","url":null,"abstract":"Selective encryption is a technique to encrypt a portion of the video data. In this case, it is encrypted by RSA algorithm. It is one of the public - key cryptosystem that is used to provide privacy and authentication of digital data. Security of this algorithm lies in the difficulty of factoring very large modulus n. In this project, the video format are MPEG - 1 and MPEG - 2, because they have almost the same bit stream structure, so the processing by using an algorithm. In this final project will be built a software using the Java platform. Testing on this project to encrypt and decrypt video formats, MPEG-1 and MPEG-2, so the security of video can be realized by using the method of selective encryption. Other parameters are the key length in the RSA algorithm which has been adapted and Brute Force Attacks.","PeriodicalId":404830,"journal":{"name":"2014 The 1st International Conference on Information Technology, Computer, and Electrical Engineering","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114495559","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 : 2014-10-20DOI: 10.1109/ICITACEE.2014.7065757
Evi Triandini, A. Djunaidy, D. Siahaan
Small and Medium Enterprises (SMEs) in Indonesia need to enhance their ability to face a global market. E-commerce provides potential benefits for SMEs. This study proposed a number of Indonesian SMEs' e-commerce adoption levels and their ranks based on customer-oriented benefits. The levels and ranks are determined based k-means clustering. Analysis result shows that Indonesian SMEs can be classified into four levels of e-commerce adoption based on customer-oriented benefits. The result of this study will be used as a metric in Indonesian SMEs' e-commerce adoption framework.
{"title":"Determining e-commerce adoption level by SMEs in Indonesia based on customer-oriented benefits","authors":"Evi Triandini, A. Djunaidy, D. Siahaan","doi":"10.1109/ICITACEE.2014.7065757","DOIUrl":"https://doi.org/10.1109/ICITACEE.2014.7065757","url":null,"abstract":"Small and Medium Enterprises (SMEs) in Indonesia need to enhance their ability to face a global market. E-commerce provides potential benefits for SMEs. This study proposed a number of Indonesian SMEs' e-commerce adoption levels and their ranks based on customer-oriented benefits. The levels and ranks are determined based k-means clustering. Analysis result shows that Indonesian SMEs can be classified into four levels of e-commerce adoption based on customer-oriented benefits. The result of this study will be used as a metric in Indonesian SMEs' e-commerce adoption framework.","PeriodicalId":404830,"journal":{"name":"2014 The 1st International Conference on Information Technology, Computer, and Electrical Engineering","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129263407","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 : 2014-10-19DOI: 10.1109/ICITACEE.2014.7065738
R. Isnanto
Human iris has a very unique pattern which is possible to be used as a biometric recognition. To identify texture in an image, texture analysis method can be used. One of method is wavelet that extract the image feature based on energy. Wavelet transforms used are biothogonal types, i.e. Haar and Daubechies. In this research, iris recognition based on Haar and Daubechies was done and then comparison analysis was conducted for which some conclusions taken. Some steps have to be done in the research. First, the iris image is segmented from eye image then enhanced with histogram equalization. The method used for extracting features are Haar and Daubechies (i.e. db5) wavelets transform. The features obtained is energy value. The next step is recognition using normalized Euclidean distance. Comparison analysis is done based on recognition rate percentage with two samples stored in database for reference images. As the result, the highest recognition rate is achieved using Haar with decomposition level 3 i.e. 84.375%, for which the highest recognition rate of db5 is 68.75% with decomposition level 2. The lowest recognition is achieved when db5 used with decomposition level 1, i.e. 38.231%, whereas the lowest recognition rate using Haar is 68.75% with decomposition level 1.
{"title":"Iris recognition analysis using biorthogonal wavelets tranform for feature extraction","authors":"R. Isnanto","doi":"10.1109/ICITACEE.2014.7065738","DOIUrl":"https://doi.org/10.1109/ICITACEE.2014.7065738","url":null,"abstract":"Human iris has a very unique pattern which is possible to be used as a biometric recognition. To identify texture in an image, texture analysis method can be used. One of method is wavelet that extract the image feature based on energy. Wavelet transforms used are biothogonal types, i.e. Haar and Daubechies. In this research, iris recognition based on Haar and Daubechies was done and then comparison analysis was conducted for which some conclusions taken. Some steps have to be done in the research. First, the iris image is segmented from eye image then enhanced with histogram equalization. The method used for extracting features are Haar and Daubechies (i.e. db5) wavelets transform. The features obtained is energy value. The next step is recognition using normalized Euclidean distance. Comparison analysis is done based on recognition rate percentage with two samples stored in database for reference images. As the result, the highest recognition rate is achieved using Haar with decomposition level 3 i.e. 84.375%, for which the highest recognition rate of db5 is 68.75% with decomposition level 2. The lowest recognition is achieved when db5 used with decomposition level 1, i.e. 38.231%, whereas the lowest recognition rate using Haar is 68.75% with decomposition level 1.","PeriodicalId":404830,"journal":{"name":"2014 The 1st International Conference on Information Technology, Computer, and Electrical Engineering","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130072799","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：