Pub Date : 2011-06-15DOI: 10.1109/INISTA.2011.5946082
M. Arabaci, Armagan Aktug, Gürdal Ertek
Association mining is the methodology within data mining that researches associations among the elements of a given set, based on how they appear together in multiple subsets of that set. Extensive literature exists on the development of efficient algorithms for association mining computations, and the fundamental motivation for this literature is that association mining reveals actionable insights and enables better policies. This motivation is proven valid for domains such as retailing, healthcare and software engineering, where elements of the analyzed set are physical or virtual items that appear in transactions. However, the literature does not prove this motivation for databases where items are “derived items”, rather than actual items. This study investigates the association patterns in changes of exchange rates of US Dollar, Euro and Gold in the Turkish economy, by representing the percentage changes as “derived items” that appear in “derived market baskets”, the day on which the observations are made. The study is one of the few in literature that applies such a mapping and applies association mining in exchange rate analysis, and the first one that considers the Turkish case. Actionable insights, along with their policy implications, demonstrate the usability of the developed analysis approach.
{"title":"Actionable insights through association mining of exchange rates: A case study","authors":"M. Arabaci, Armagan Aktug, Gürdal Ertek","doi":"10.1109/INISTA.2011.5946082","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946082","url":null,"abstract":"Association mining is the methodology within data mining that researches associations among the elements of a given set, based on how they appear together in multiple subsets of that set. Extensive literature exists on the development of efficient algorithms for association mining computations, and the fundamental motivation for this literature is that association mining reveals actionable insights and enables better policies. This motivation is proven valid for domains such as retailing, healthcare and software engineering, where elements of the analyzed set are physical or virtual items that appear in transactions. However, the literature does not prove this motivation for databases where items are “derived items”, rather than actual items. This study investigates the association patterns in changes of exchange rates of US Dollar, Euro and Gold in the Turkish economy, by representing the percentage changes as “derived items” that appear in “derived market baskets”, the day on which the observations are made. The study is one of the few in literature that applies such a mapping and applies association mining in exchange rate analysis, and the first one that considers the Turkish case. Actionable insights, along with their policy implications, demonstrate the usability of the developed analysis approach.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125836000","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946112
O. Mengi, I. Altas
In this paper, a smart energy management consist of Photovoltaic/Wind (PV/W) renewable energy resources is studied. Since the operation performances of such sources are not the same for different hours of a day as well as different seasons of a year, an Energy Management System is required to a sustainable energy supply for users. An EMS using a Fuzzy Decision Making (FDM) process is proposed in this study in order to manage the supply power from PV/W to loads. The proposed FDM based Smart Management System (SMS) determines the switching sequences of the PV/W system considering both the environmental conditions and power demands by loads. In order to prevent power supply discontinuity to loads during the switching from one source to another, an algorithm is included in the SMS. The proposed FDM based SMS is modeled in Matlab/Simulink and tested on real time in a laboratory environment in order to validate the operating performances.
{"title":"A fuzzy decision making energy management system for a PV/Wind renewable energy system","authors":"O. Mengi, I. Altas","doi":"10.1109/INISTA.2011.5946112","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946112","url":null,"abstract":"In this paper, a smart energy management consist of Photovoltaic/Wind (PV/W) renewable energy resources is studied. Since the operation performances of such sources are not the same for different hours of a day as well as different seasons of a year, an Energy Management System is required to a sustainable energy supply for users. An EMS using a Fuzzy Decision Making (FDM) process is proposed in this study in order to manage the supply power from PV/W to loads. The proposed FDM based Smart Management System (SMS) determines the switching sequences of the PV/W system considering both the environmental conditions and power demands by loads. In order to prevent power supply discontinuity to loads during the switching from one source to another, an algorithm is included in the SMS. The proposed FDM based SMS is modeled in Matlab/Simulink and tested on real time in a laboratory environment in order to validate the operating performances.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123748094","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946130
S. Dib, M. Barkat, M. Grimes
In this paper, we investigate the use of two iterative algorithms for the suppression of interferences and thus, the detection of slow targets in monostatic airborne radar. The conventional space-time adaptive processing (STAP) such as the sample matrix inversion (SMI) or the Principal Components (PC) methods are computationally costly and require the estimation of the clutter covariance matrix from secondary data, which are assumed to be independent and identically distributed. However, in monostatic airborne radar, because of the platform motion and the inclination of the array, the data are not stationary. Consequently, to circumvent such a problem, we propose to investigate the performances of adaptive recursive subspace-based algorithms of linear complexity using projection approximation subspace tracking (PAST) and orthonormal PAST (OPAST) algorithms. Simulation results are presented and the performance of STAP is discussed with a comparative study to PC and SINR metric methods justifying the use of those algorithms in radar signal processing. Performance curves show that PAST and OPAST algorithms allow good indeed detection of slow moving targets even with a low rank covariance matrix and in a Doppler ambiguous environment.
{"title":"PAST and OPAST algorithms for STAP in monostatic airborne radar","authors":"S. Dib, M. Barkat, M. Grimes","doi":"10.1109/INISTA.2011.5946130","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946130","url":null,"abstract":"In this paper, we investigate the use of two iterative algorithms for the suppression of interferences and thus, the detection of slow targets in monostatic airborne radar. The conventional space-time adaptive processing (STAP) such as the sample matrix inversion (SMI) or the Principal Components (PC) methods are computationally costly and require the estimation of the clutter covariance matrix from secondary data, which are assumed to be independent and identically distributed. However, in monostatic airborne radar, because of the platform motion and the inclination of the array, the data are not stationary. Consequently, to circumvent such a problem, we propose to investigate the performances of adaptive recursive subspace-based algorithms of linear complexity using projection approximation subspace tracking (PAST) and orthonormal PAST (OPAST) algorithms. Simulation results are presented and the performance of STAP is discussed with a comparative study to PC and SINR metric methods justifying the use of those algorithms in radar signal processing. Performance curves show that PAST and OPAST algorithms allow good indeed detection of slow moving targets even with a low rank covariance matrix and in a Doppler ambiguous environment.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126603556","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946160
F. S. Gharehchopogh
One of the topics during the last 30 years much research has been allocated to cost estimation for software projects. Important issues in the field of software engineering capabilities estimate size and effort required for development of software projects. Cost estimates must be made at the beginning of the project, and principally at the beginning of projects through cost and set new work requirements will be done. In this paper, we describe new case study for estimate software cost and will be presented new Neural Network (NN) architecture for prediction necessary effort for new software. The results indicate that the NN model that we offer the very best of algorithmic methods to predict and estimate software costs as smart deals. NN training results by NN indicating, that the test results indicate that over 90% of cases give much better estimates of NN algorithm model.
{"title":"Neural networks application in software cost estimation: A case study","authors":"F. S. Gharehchopogh","doi":"10.1109/INISTA.2011.5946160","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946160","url":null,"abstract":"One of the topics during the last 30 years much research has been allocated to cost estimation for software projects. Important issues in the field of software engineering capabilities estimate size and effort required for development of software projects. Cost estimates must be made at the beginning of the project, and principally at the beginning of projects through cost and set new work requirements will be done. In this paper, we describe new case study for estimate software cost and will be presented new Neural Network (NN) architecture for prediction necessary effort for new software. The results indicate that the NN model that we offer the very best of algorithmic methods to predict and estimate software costs as smart deals. NN training results by NN indicating, that the test results indicate that over 90% of cases give much better estimates of NN algorithm model.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114603515","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946057
S. Guney, A. Atasoy
Electronic nose (e-nose) is a machine used for sensing and recognizing odors by using chemical sensors. E-nose has wide fields of applications and it is used for sensing special odors. Also performance of e-nose depends on choosing correct sensor and choosing correct pattern recognition algorithm according to field of application and kinds of odors. In this study, different n-butanol concentrations sensed by 12 metal oxide gas sensors are classified by using artificial neural network (ANN) and k-nearest neighbor (k-NN) algorithm. 100 % success rate is obtained with k-NN classifier for this application. Simultaneously results of k-NN classifier are compared with ANN results. To recognize the different concentrations of n-butanol sample which is component of farm odors is first stage of the study. Advanced stage of the study recognizes the farm odors.
{"title":"Classification of n-butanol concentrations with k-NN algorithm and ANN in electronic nose","authors":"S. Guney, A. Atasoy","doi":"10.1109/INISTA.2011.5946057","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946057","url":null,"abstract":"Electronic nose (e-nose) is a machine used for sensing and recognizing odors by using chemical sensors. E-nose has wide fields of applications and it is used for sensing special odors. Also performance of e-nose depends on choosing correct sensor and choosing correct pattern recognition algorithm according to field of application and kinds of odors. In this study, different n-butanol concentrations sensed by 12 metal oxide gas sensors are classified by using artificial neural network (ANN) and k-nearest neighbor (k-NN) algorithm. 100 % success rate is obtained with k-NN classifier for this application. Simultaneously results of k-NN classifier are compared with ANN results. To recognize the different concentrations of n-butanol sample which is component of farm odors is first stage of the study. Advanced stage of the study recognizes the farm odors.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"183 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128664872","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946065
Suhail M. Odeh, Manal Khalil
This paper discusses signature verification and recognition using a new approach that depends on a neural network which enables the user to recognize whether a signature is original or a fraud. The user introduces into the computer the scanned images, modifies their quality by image enhancement and noise reduction techniques, to be followed by feature extraction and neural network training, and finally verifies the authenticity of the signature. The paper discusses the different stages of the process including: image pre-processing, feature extraction and pattern recognition through neural networks.
{"title":"Off-line signature verification and recognition: Neural network approach","authors":"Suhail M. Odeh, Manal Khalil","doi":"10.1109/INISTA.2011.5946065","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946065","url":null,"abstract":"This paper discusses signature verification and recognition using a new approach that depends on a neural network which enables the user to recognize whether a signature is original or a fraud. The user introduces into the computer the scanned images, modifies their quality by image enhancement and noise reduction techniques, to be followed by feature extraction and neural network training, and finally verifies the authenticity of the signature. The paper discusses the different stages of the process including: image pre-processing, feature extraction and pattern recognition through neural networks.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129173097","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946148
Hasna Boumechaal, Z. Boufaida
Most existing systems of information retrieval are limited to a search by keywords, based on the syntactic content of documents. The absence of semantics conducts to a very complex formulation of queries which generates the problem of access to relevant information on the web. In this paper, we implement a conversion tool which takes queries expressed in natural language and an ontology as input and returns the appropriate formal queries. The generated queries are then sent to the reasoner for querying the knowledge bases.
{"title":"Formalization of natural language queries","authors":"Hasna Boumechaal, Z. Boufaida","doi":"10.1109/INISTA.2011.5946148","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946148","url":null,"abstract":"Most existing systems of information retrieval are limited to a search by keywords, based on the syntactic content of documents. The absence of semantics conducts to a very complex formulation of queries which generates the problem of access to relevant information on the web. In this paper, we implement a conversion tool which takes queries expressed in natural language and an ontology as input and returns the appropriate formal queries. The generated queries are then sent to the reasoner for querying the knowledge bases.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123486116","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946070
J. Szymański, Kamil Węgrzynowicz
This article describes an improvement for K-means algorithm and its application in the form of a system that clusters search results retrieved from Wikipedia. The proposed algorithm eliminates K-means disadvantages and allows one to create a cluster hierarchy. The main contributions of this paper include the following: (1) The concept of an improved K-means algorithm and its application for hierarchical clustering. (2) Description of the WikiClusterSearch system that employs the proposed algorithm to organize Wikipedia search results into clusters.
{"title":"0-Step K-means for clustering Wikipedia search results","authors":"J. Szymański, Kamil Węgrzynowicz","doi":"10.1109/INISTA.2011.5946070","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946070","url":null,"abstract":"This article describes an improvement for K-means algorithm and its application in the form of a system that clusters search results retrieved from Wikipedia. The proposed algorithm eliminates K-means disadvantages and allows one to create a cluster hierarchy. The main contributions of this paper include the following: (1) The concept of an improved K-means algorithm and its application for hierarchical clustering. (2) Description of the WikiClusterSearch system that employs the proposed algorithm to organize Wikipedia search results into clusters.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121305939","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946106
A. Yardimci
Portable nebulizers are increasingly being used by asthmatics and patients with chronic obstructive airway disease as part of their domiciliary treatment using inhaled β2-agonist and anticholinergic drugs. According to recent studies correct matching of the nebulizer/compressor is seen to be important to ensure optimum performance. In order to make produced aerosols reach to target field adequately, it is notable that compressor power is important in jet nebulizers. In this paper we are going to present a new effective jet nebulizer design. Developed system has two major intelligent controls; control of compressor power and treatment time period control function. With this study we tried to improve design of commercially available jet nebulizers. The test results also have proven that we have achieved our goal.
{"title":"Microcontroller based jet nebulizer design with ANFIS compessor control for domiciliary use","authors":"A. Yardimci","doi":"10.1109/INISTA.2011.5946106","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946106","url":null,"abstract":"Portable nebulizers are increasingly being used by asthmatics and patients with chronic obstructive airway disease as part of their domiciliary treatment using inhaled β2-agonist and anticholinergic drugs. According to recent studies correct matching of the nebulizer/compressor is seen to be important to ensure optimum performance. In order to make produced aerosols reach to target field adequately, it is notable that compressor power is important in jet nebulizers. In this paper we are going to present a new effective jet nebulizer design. Developed system has two major intelligent controls; control of compressor power and treatment time period control function. With this study we tried to improve design of commercially available jet nebulizers. The test results also have proven that we have achieved our goal.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133430823","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946061
P. Govender, D. A. Kyereahene-Mensah
Modern manufacturing techniques depend upon systems that produce high volumes with consistent quality in order to ensure maximum productivity. One source of reduced productivity is equipment failure. To minimize these production losses, we propose an intelligent system that is incorporated into the architecture of a machine for detecting the onset of equipment malfunctioning, and to generate corrective action. The intelligent diagnostic system is based upon the artificial immune algorithm and the technique of negative selection. The proposed immune based system monitors a machine's transition states during an operating cycle and immediately detects the occurrence of an anomaly.
{"title":"Artificial immune systems and negative selection for fault diagnosis","authors":"P. Govender, D. A. Kyereahene-Mensah","doi":"10.1109/INISTA.2011.5946061","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946061","url":null,"abstract":"Modern manufacturing techniques depend upon systems that produce high volumes with consistent quality in order to ensure maximum productivity. One source of reduced productivity is equipment failure. To minimize these production losses, we propose an intelligent system that is incorporated into the architecture of a machine for detecting the onset of equipment malfunctioning, and to generate corrective action. The intelligent diagnostic system is based upon the artificial immune algorithm and the technique of negative selection. The proposed immune based system monitors a machine's transition states during an operating cycle and immediately detects the occurrence of an anomaly.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"15 22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115737000","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：