Genetic algorithms have been used successfully to solve continuous optimization problems. However, an early convergence to low-quality solutions is one of the most common difficulties encountered when using these strategies. In this paper, a method that combines multiple auxiliary populations with the main population of the algorithm is proposed. The role of the auxiliary populations is dual: to prevent or hinder the early convergence to local suboptimal solutions, and to provide a local search mechanism for a greater exploitation of the most promising regions within the search space.
{"title":"GAAP. genetic algorithm with auxiliary populations applied to continuous optimization problems","authors":"Leonardo Corbalán, W. Hasperué, L. Lanzarini","doi":"10.2498/iti.2012.0382","DOIUrl":"https://doi.org/10.2498/iti.2012.0382","url":null,"abstract":"Genetic algorithms have been used successfully to solve continuous optimization problems. However, an early convergence to low-quality solutions is one of the most common difficulties encountered when using these strategies. In this paper, a method that combines multiple auxiliary populations with the main population of the algorithm is proposed. The role of the auxiliary populations is dual: to prevent or hinder the early convergence to local suboptimal solutions, and to provide a local search mechanism for a greater exploitation of the most promising regions within the search space.","PeriodicalId":135105,"journal":{"name":"Proceedings of the ITI 2012 34th International Conference on Information Technology Interfaces","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126560143","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}
Risk management is focused on preventing the losses and protecting the company's asset base. Banks are most exposed to credit risk, so their goal is to minimize the losses that occur as a result of default or insolvency. Business credit scoring models are designed to estimate the probability of corporate default. In this paper we presented the business credit scoring model based on a decision tree analysis. The emphasis in the research is on the selection of the variables that are relevant for the business credit scoring model applicable to the Croatian financial system. In order to reduce the number of variables included in the analysis, we suggest the use of the Information Value and inferential statistical methods.
{"title":"Risk management and business credit scoring","authors":"Ljiljanka Kvesić, G. Dukic","doi":"10.2498/iti.2012.0478","DOIUrl":"https://doi.org/10.2498/iti.2012.0478","url":null,"abstract":"Risk management is focused on preventing the losses and protecting the company's asset base. Banks are most exposed to credit risk, so their goal is to minimize the losses that occur as a result of default or insolvency. Business credit scoring models are designed to estimate the probability of corporate default. In this paper we presented the business credit scoring model based on a decision tree analysis. The emphasis in the research is on the selection of the variables that are relevant for the business credit scoring model applicable to the Croatian financial system. In order to reduce the number of variables included in the analysis, we suggest the use of the Information Value and inferential statistical methods.","PeriodicalId":135105,"journal":{"name":"Proceedings of the ITI 2012 34th International Conference on Information Technology Interfaces","volume":"218 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122397202","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}
The paper describes an approach to environmental data mining on a problem of public bicycle system. Environmental infromation including weather information and the bicycle station location is considered, as well as the time of the day and the number of bicycles at each hour at each station. Data mining methods are applied to predict the number of available bicycles at a certain time at a given station, to describe situations of empty and full stations and, to estimate the most common paths and usage patterns. The experiemntal evaluation of the proposed approach on real-world data gives promissing results, with machine learning mehtods achieving significantely lower error on predicting the number of bicycles compared to a baseline method.
{"title":"BICIKELJ: Environmental data mining on the bicycle","authors":"Lorand Dali, D. Mladenić","doi":"10.2498/iti.2012.0391","DOIUrl":"https://doi.org/10.2498/iti.2012.0391","url":null,"abstract":"The paper describes an approach to environmental data mining on a problem of public bicycle system. Environmental infromation including weather information and the bicycle station location is considered, as well as the time of the day and the number of bicycles at each hour at each station. Data mining methods are applied to predict the number of available bicycles at a certain time at a given station, to describe situations of empty and full stations and, to estimate the most common paths and usage patterns. The experiemntal evaluation of the proposed approach on real-world data gives promissing results, with machine learning mehtods achieving significantely lower error on predicting the number of bicycles compared to a baseline method.","PeriodicalId":135105,"journal":{"name":"Proceedings of the ITI 2012 34th International Conference on Information Technology Interfaces","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127998657","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}
Amdahl has shown that multiprocessor execution performance is not proportional to the number of processors. Gustafson has found a way to show that there are algorithms which can have almost linear speedup. In this article we have found algorithms which can achieve a superlinear speedup. The idea is not based on changing the algorithm or executing smaller number of operations like in the parallel search. It is based on characteristics of using an structure persistent algorithm which efficiently exploits the cache in a shared multiprocessor and avoids cache misses as much as possible. Our experimental research shows results of superlinear speedup for algorithms which run on modern multicore and multi-chip architectures and perform beyond expectations of maximum linear speedup.
{"title":"Superlinear speedup for matrix multiplication","authors":"S. Ristov, M. Gusev","doi":"10.2498/iti.2012.0376","DOIUrl":"https://doi.org/10.2498/iti.2012.0376","url":null,"abstract":"Amdahl has shown that multiprocessor execution performance is not proportional to the number of processors. Gustafson has found a way to show that there are algorithms which can have almost linear speedup. In this article we have found algorithms which can achieve a superlinear speedup. The idea is not based on changing the algorithm or executing smaller number of operations like in the parallel search. It is based on characteristics of using an structure persistent algorithm which efficiently exploits the cache in a shared multiprocessor and avoids cache misses as much as possible. Our experimental research shows results of superlinear speedup for algorithms which run on modern multicore and multi-chip architectures and perform beyond expectations of maximum linear speedup.","PeriodicalId":135105,"journal":{"name":"Proceedings of the ITI 2012 34th International Conference on Information Technology Interfaces","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114666652","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}
For the past few years in the face recognition research area are made very progressive improvements. This is because of the high level and versatile technologies in use nowadays, and high level of processors running on our machines and mobile phones. Available technologies provide mechanisms which use face recognition for security identification (user face) and authentication purposes. The aim of this paper is to present and propose client - server model and to compare it with the most recent client - server models for face recognition with a GPG infrastructure which uses security private key (symmetric encryption) with main purpose to securely transmit image (user face) over the network. Moreover in the face recognition algorithm is implemented Principle Component Analysis (PCA) algorithm for face recognition. Proposed system has been tested on the mobile phone with Android OS platform, using previous research experiences where system was initially developed for DROID emulator. The implementation of the PCA is done on the MATLAB side.
{"title":"Face recognition implementation for client server mobile application using PCA","authors":"Emir Kremic, A. Subasi, Kemal Hajdarevic","doi":"10.2498/iti.2012.0455","DOIUrl":"https://doi.org/10.2498/iti.2012.0455","url":null,"abstract":"For the past few years in the face recognition research area are made very progressive improvements. This is because of the high level and versatile technologies in use nowadays, and high level of processors running on our machines and mobile phones. Available technologies provide mechanisms which use face recognition for security identification (user face) and authentication purposes. The aim of this paper is to present and propose client - server model and to compare it with the most recent client - server models for face recognition with a GPG infrastructure which uses security private key (symmetric encryption) with main purpose to securely transmit image (user face) over the network. Moreover in the face recognition algorithm is implemented Principle Component Analysis (PCA) algorithm for face recognition. Proposed system has been tested on the mobile phone with Android OS platform, using previous research experiences where system was initially developed for DROID emulator. The implementation of the PCA is done on the MATLAB side.","PeriodicalId":135105,"journal":{"name":"Proceedings of the ITI 2012 34th International Conference on Information Technology Interfaces","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116079461","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}
Concerning the needs of today's university oriented to virtual university development, aim of this paper is to explore convergence of academic libraries' e-services and learning management system in regards to quality assurance in higher education. A special attention in this research is given to students. Namely, research results based on exploring students' attitudes towards libraries' e-services integrated in the subject contents within learning management system revealed four educational benefit factors of convergence of academic libraries' e-services and learning management systems which are presented in this paper.
{"title":"Educational benefit factors of convergence of academic libraries' e-services and learning management system","authors":"Anita Papic, Boris Badurina","doi":"10.2498/iti.2012.0418","DOIUrl":"https://doi.org/10.2498/iti.2012.0418","url":null,"abstract":"Concerning the needs of today's university oriented to virtual university development, aim of this paper is to explore convergence of academic libraries' e-services and learning management system in regards to quality assurance in higher education. A special attention in this research is given to students. Namely, research results based on exploring students' attitudes towards libraries' e-services integrated in the subject contents within learning management system revealed four educational benefit factors of convergence of academic libraries' e-services and learning management systems which are presented in this paper.","PeriodicalId":135105,"journal":{"name":"Proceedings of the ITI 2012 34th International Conference on Information Technology Interfaces","volume":"220 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130519552","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}
The cloud computing paradigm includes a spectrum of many models, developers and reference designs. This paper proposes information model for further taxonomy or classification and comparison of the fundamental cloud technology implementations that cover most common practical installations of the service and deployment models within the “private” or “community” branches of cloud computing infrastructures, which are not so clearly distinguished within the industry.
{"title":"Comparison of private cloud infrastructure implementation models","authors":"Ivor Milosevic, V. Simovíc","doi":"10.2498/iti.2012.0439","DOIUrl":"https://doi.org/10.2498/iti.2012.0439","url":null,"abstract":"The cloud computing paradigm includes a spectrum of many models, developers and reference designs. This paper proposes information model for further taxonomy or classification and comparison of the fundamental cloud technology implementations that cover most common practical installations of the service and deployment models within the “private” or “community” branches of cloud computing infrastructures, which are not so clearly distinguished within the industry.","PeriodicalId":135105,"journal":{"name":"Proceedings of the ITI 2012 34th International Conference on Information Technology Interfaces","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130663441","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 discusses the identity crisis in the Information Systems (I.S.) academic discipline. It reviews how Kuhn's concepts of paradigm and (normal) science apply to I.S. and argues that I.S.'s scope is too broad and too disconnected from practice. The paper proposes that I.S. become a professional discipline, guided by issues faced by practitioners, e.g., Chief Innovation Officers. I.S. research would center around the management of provisioning, operation and maintenance of I.T. Similar to other professional fields (e.g., medicine), I.S. researchers would be practitioners. The paper concludes with a sample of important research questions for I.S. as a professional discipline.
{"title":"I.S. research of business practices: Many, one or zero academic disciplines?","authors":"G. J. Hidding","doi":"10.2498/iti.2012.0483","DOIUrl":"https://doi.org/10.2498/iti.2012.0483","url":null,"abstract":"This paper discusses the identity crisis in the Information Systems (I.S.) academic discipline. It reviews how Kuhn's concepts of paradigm and (normal) science apply to I.S. and argues that I.S.'s scope is too broad and too disconnected from practice. The paper proposes that I.S. become a professional discipline, guided by issues faced by practitioners, e.g., Chief Innovation Officers. I.S. research would center around the management of provisioning, operation and maintenance of I.T. Similar to other professional fields (e.g., medicine), I.S. researchers would be practitioners. The paper concludes with a sample of important research questions for I.S. as a professional discipline.","PeriodicalId":135105,"journal":{"name":"Proceedings of the ITI 2012 34th International Conference on Information Technology Interfaces","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114524050","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}
A key step in recommendation systems is to estimate if a user would likely enjoy an item who has not considered yet. In this study, a new framework is defined to predict user ratings on new items from previously given ratings by other users. The systems has two major steps: (1) Enhancing available data based on semantic content to get a full item-user matrix, and (2) Predicting the unknown rating using an integrated feature set of “other ratings given by the same user” and “other ratings given to the same item”. This allows the classifier to consider both user similarities and item similarities simultaneously. The system is shown to outperform existing methods in terms of prediction accuracy on a benchmark movie dataset.
{"title":"Two-way collaborative filtering on semantically enhanced movie ratings","authors":"H. Oğul, Emrah Ekmekciler","doi":"10.2498/iti.2012.0404","DOIUrl":"https://doi.org/10.2498/iti.2012.0404","url":null,"abstract":"A key step in recommendation systems is to estimate if a user would likely enjoy an item who has not considered yet. In this study, a new framework is defined to predict user ratings on new items from previously given ratings by other users. The systems has two major steps: (1) Enhancing available data based on semantic content to get a full item-user matrix, and (2) Predicting the unknown rating using an integrated feature set of “other ratings given by the same user” and “other ratings given to the same item”. This allows the classifier to consider both user similarities and item similarities simultaneously. The system is shown to outperform existing methods in terms of prediction accuracy on a benchmark movie dataset.","PeriodicalId":135105,"journal":{"name":"Proceedings of the ITI 2012 34th International Conference on Information Technology Interfaces","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121556794","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}
The research presented in this paper shows a study into the training online in large organizations in Australia. In particular, this research is focused on comparing the enablers of online training in Australia's large corporation as a whole and Recreation and other services industry in Australia. It was accomplished through a survey of 500 large organizations. On-line training is gaining momentum in many countries and is used by many types of businesses [4]. The research reported in this paper is looking at the enablers of online training in very diverse organizations ranging from Communications industry to wholesale/retail trade in Australia. This research has found that many of the enablers identified in the literature are also identified in large organizations in Australia. These include: top management support, skilled work force [14]; financial support, crossfunctional team, alignment of the software and organizational standards [6]; just in time training [4]; usability and transferability [18] etc.
{"title":"Enablers of online training (OT) In Australia's recreation and other services industry","authors":"J. Kuzic, J. Mesaric","doi":"10.2498/iti.2012.0393","DOIUrl":"https://doi.org/10.2498/iti.2012.0393","url":null,"abstract":"The research presented in this paper shows a study into the training online in large organizations in Australia. In particular, this research is focused on comparing the enablers of online training in Australia's large corporation as a whole and Recreation and other services industry in Australia. It was accomplished through a survey of 500 large organizations. On-line training is gaining momentum in many countries and is used by many types of businesses [4]. The research reported in this paper is looking at the enablers of online training in very diverse organizations ranging from Communications industry to wholesale/retail trade in Australia. This research has found that many of the enablers identified in the literature are also identified in large organizations in Australia. These include: top management support, skilled work force [14]; financial support, crossfunctional team, alignment of the software and organizational standards [6]; just in time training [4]; usability and transferability [18] etc.","PeriodicalId":135105,"journal":{"name":"Proceedings of the ITI 2012 34th International Conference on Information Technology Interfaces","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125764720","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：