Pub Date : 2012-07-02DOI: 10.1109/INISTA.2012.6246999
H. Cataloluk, M. Kesler
In the field of dermatology, to able to make differential diagnosis of erythemato-squamous diseases between each other accurately, is quite significant for the treatment of the disease. Especially the symptoms seen in the early stages of diseases in this group, may be very similar to each other. And this situation makes it difficult to determine accurate diagnosis for patients. Hence this study presents a data mining application for this problem in the medical field. Mentioned software tool in this study is trying to obtain correct diagnosis of erythemato-squamous diseases by using the basic and weighted K-NN algorithms on medical data. In this way, this paper presents a comparison between these two methods by evaluating and presenting the performances of them. Furthermore there is also a comparison between the Euclidean and Manhattan distance measures.
{"title":"A diagnostic software tool for skin diseases with basic and weighted K-NN","authors":"H. Cataloluk, M. Kesler","doi":"10.1109/INISTA.2012.6246999","DOIUrl":"https://doi.org/10.1109/INISTA.2012.6246999","url":null,"abstract":"In the field of dermatology, to able to make differential diagnosis of erythemato-squamous diseases between each other accurately, is quite significant for the treatment of the disease. Especially the symptoms seen in the early stages of diseases in this group, may be very similar to each other. And this situation makes it difficult to determine accurate diagnosis for patients. Hence this study presents a data mining application for this problem in the medical field. Mentioned software tool in this study is trying to obtain correct diagnosis of erythemato-squamous diseases by using the basic and weighted K-NN algorithms on medical data. In this way, this paper presents a comparison between these two methods by evaluating and presenting the performances of them. Furthermore there is also a comparison between the Euclidean and Manhattan distance measures.","PeriodicalId":305858,"journal":{"name":"2012 International Symposium on Innovations in Intelligent Systems and Applications","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127340729","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 : 2012-07-02DOI: 10.1109/INISTA.2012.6247034
E. Yesil, M. Kaya, S. Siradag
In this study, a combiner method is developed to create weekly demand forecasts for a fast-fashion apparel company. The combiner generates forecasts by combining the forecasts of three different methods through fuzzy logic. The combination weights are adaptive in the sense that the weights of the better-performing methods are increased over time. One of the three methods, which is based on product lifecycle, is relatively novel. This method is observed to be quite successful in forecasts as it can reflect the inherent regular seasonality of demand, and it allows the input of expert knowledge. The approach is illustrated through a simulation study that uses real (distorted) data from a Turkish apparel company. The combined forecast method is shown to be better than any of the methods alone.
{"title":"Fuzzy forecast combiner design for fast fashion demand forecasting","authors":"E. Yesil, M. Kaya, S. Siradag","doi":"10.1109/INISTA.2012.6247034","DOIUrl":"https://doi.org/10.1109/INISTA.2012.6247034","url":null,"abstract":"In this study, a combiner method is developed to create weekly demand forecasts for a fast-fashion apparel company. The combiner generates forecasts by combining the forecasts of three different methods through fuzzy logic. The combination weights are adaptive in the sense that the weights of the better-performing methods are increased over time. One of the three methods, which is based on product lifecycle, is relatively novel. This method is observed to be quite successful in forecasts as it can reflect the inherent regular seasonality of demand, and it allows the input of expert knowledge. The approach is illustrated through a simulation study that uses real (distorted) data from a Turkish apparel company. The combined forecast method is shown to be better than any of the methods alone.","PeriodicalId":305858,"journal":{"name":"2012 International Symposium on Innovations in Intelligent Systems and Applications","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122904961","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 : 2012-07-02DOI: 10.1109/INISTA.2012.6246964
H. Kawasaki, S. Koide, T. Endo, T. Mouri
This paper presents a concept for a hand haptic interface for use in a virtual reality environment and describes its basic experimental evaluation. The haptic interface consists of one-dimensional (1D) force display devices for each finger pad and the palm and a 3D fingertip haptic display device. The 1D force display devices are closed-loop controlled by the use of tactile sensors. The specifications of the 1D force display and experiment results at passive touch and active touch when subjects use the hand haptic interface in a virtual reality environment are presented.
{"title":"Development of a hand haptic interface and its basic experimental evaluation","authors":"H. Kawasaki, S. Koide, T. Endo, T. Mouri","doi":"10.1109/INISTA.2012.6246964","DOIUrl":"https://doi.org/10.1109/INISTA.2012.6246964","url":null,"abstract":"This paper presents a concept for a hand haptic interface for use in a virtual reality environment and describes its basic experimental evaluation. The haptic interface consists of one-dimensional (1D) force display devices for each finger pad and the palm and a 3D fingertip haptic display device. The 1D force display devices are closed-loop controlled by the use of tactile sensors. The specifications of the 1D force display and experiment results at passive touch and active touch when subjects use the hand haptic interface in a virtual reality environment are presented.","PeriodicalId":305858,"journal":{"name":"2012 International Symposium on Innovations in Intelligent Systems and Applications","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114168127","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 : 2012-07-02DOI: 10.1504/IJRIS.2013.057269
F. Benhamida, R. Belhachem, S. Slimane, Y. Ramdani
The combined economic/emission dispatch (CEED) problem is obtained by considering both the economy and emission objectives with required constraints. Many optimization techniques are slow for such complex optimization tasks and are not suitable for online use. This paper presents an optimization algorithm for solving constrained CEED, through the application of a flexible Hopfield neural network (HNN). The constrained CEED must satisfy the system load demand and practical operation constraints of generators. The feasibility of the proposed HNN using to solve CEED is demonstrated using a 3-unit test system and it is compared with the other methods in terms of solution quality and computation efficiency. The simulation results showed that the proposed HNN method was indeed capable of obtaining higher quality solutions efficiently in CEED problems with a much shorter computation time compared to other methods.
{"title":"A fast solver for combined emission and generation allocation using a Hopfield neural network","authors":"F. Benhamida, R. Belhachem, S. Slimane, Y. Ramdani","doi":"10.1504/IJRIS.2013.057269","DOIUrl":"https://doi.org/10.1504/IJRIS.2013.057269","url":null,"abstract":"The combined economic/emission dispatch (CEED) problem is obtained by considering both the economy and emission objectives with required constraints. Many optimization techniques are slow for such complex optimization tasks and are not suitable for online use. This paper presents an optimization algorithm for solving constrained CEED, through the application of a flexible Hopfield neural network (HNN). The constrained CEED must satisfy the system load demand and practical operation constraints of generators. The feasibility of the proposed HNN using to solve CEED is demonstrated using a 3-unit test system and it is compared with the other methods in terms of solution quality and computation efficiency. The simulation results showed that the proposed HNN method was indeed capable of obtaining higher quality solutions efficiently in CEED problems with a much shorter computation time compared to other methods.","PeriodicalId":305858,"journal":{"name":"2012 International Symposium on Innovations in Intelligent Systems and Applications","volume":"365 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124581532","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 : 2012-07-02DOI: 10.1109/INISTA.2012.6246946
N. Morova, Ş. Sargın, S. Terzi, M. Saltan, S. Serin
In this study, an Artificial Neural Network (ANN) model has been developed to estimate Marshall Stability (MS) of lightweight asphalt concrete containing expanded clay. In the model, amount of bitumen (%), transition speed of ultrasound (μs), unit weight (gr/cm3) were used as inputs and Marshall Stability (kg) was used as output. Developed ANN model results and the experimental results were compared and good relationship was found.
{"title":"Modeling Marshall Stability of light asphalt concretes fabricated using expanded clay aggregate with Artificial Neural Networks","authors":"N. Morova, Ş. Sargın, S. Terzi, M. Saltan, S. Serin","doi":"10.1109/INISTA.2012.6246946","DOIUrl":"https://doi.org/10.1109/INISTA.2012.6246946","url":null,"abstract":"In this study, an Artificial Neural Network (ANN) model has been developed to estimate Marshall Stability (MS) of lightweight asphalt concrete containing expanded clay. In the model, amount of bitumen (%), transition speed of ultrasound (μs), unit weight (gr/cm3) were used as inputs and Marshall Stability (kg) was used as output. Developed ANN model results and the experimental results were compared and good relationship was found.","PeriodicalId":305858,"journal":{"name":"2012 International Symposium on Innovations in Intelligent Systems and Applications","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114716661","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 : 2012-07-02DOI: 10.1109/INISTA.2012.6246967
M. Ozturk, Z. Hasirci
In this paper, we propose a method to determine the best regression axis to order the noisy points for curve reconstruction. The fundamental problem of the curve reconstruction is to order the data in most suitable way. We suggested a histogram based feature to be able to determine the goodness of the order for a regression line. The method developed by using the proposed feature tested on the some synesthetic data with different noise levels. This data was selected due to the eigenvector approach gave wrong results when obtaining regression line. The results showed that the proposed method is encouraging.
{"title":"A novel method for determination of best ordering direction for noisy point clouds","authors":"M. Ozturk, Z. Hasirci","doi":"10.1109/INISTA.2012.6246967","DOIUrl":"https://doi.org/10.1109/INISTA.2012.6246967","url":null,"abstract":"In this paper, we propose a method to determine the best regression axis to order the noisy points for curve reconstruction. The fundamental problem of the curve reconstruction is to order the data in most suitable way. We suggested a histogram based feature to be able to determine the goodness of the order for a regression line. The method developed by using the proposed feature tested on the some synesthetic data with different noise levels. This data was selected due to the eigenvector approach gave wrong results when obtaining regression line. The results showed that the proposed method is encouraging.","PeriodicalId":305858,"journal":{"name":"2012 International Symposium on Innovations in Intelligent Systems and Applications","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127757492","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 : 2012-07-02DOI: 10.1109/INISTA.2012.6247001
I. Gumus, O. Abul
Human computation is a promising approach at solving computation tasks for which humans currently perform better than computers. Archive digitization is such a task. In this paper, we present our reCAPTCHA like archive digitization system, called trCAPTCHA, mainly targeting old Turkish archives and hence Turkish speaking audience. trCAPTCHA differs from reCAPTCHA that it uses no global dictionary but constructs a local dictionary for each scanned word from alternative texts generated through OCR readings.
{"title":"Turkish archive digitization by human computation approach","authors":"I. Gumus, O. Abul","doi":"10.1109/INISTA.2012.6247001","DOIUrl":"https://doi.org/10.1109/INISTA.2012.6247001","url":null,"abstract":"Human computation is a promising approach at solving computation tasks for which humans currently perform better than computers. Archive digitization is such a task. In this paper, we present our reCAPTCHA like archive digitization system, called trCAPTCHA, mainly targeting old Turkish archives and hence Turkish speaking audience. trCAPTCHA differs from reCAPTCHA that it uses no global dictionary but constructs a local dictionary for each scanned word from alternative texts generated through OCR readings.","PeriodicalId":305858,"journal":{"name":"2012 International Symposium on Innovations in Intelligent Systems and Applications","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127951154","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 : 2012-07-02DOI: 10.1109/INISTA.2012.6246972
B. Ergen, A. Cinar, G. Aydin
It is well known that the Gabor wavelet transform (GWT) provides directional information for the analysis of an image. In this paper, we proposed an approach based on the GWT by combining unsupervised Fuzzy c-means (FCM) clustering which provides plays an important role in recognition as a classifier. After enhancing the edge of the input image using GWT, the binary image showing the edge is obtained using FCM clustering and morphological skeletonization. When compared to the Canny method and other conventional method, the proposed method has showed a better performance in terms of detection accuracy for noisy medical images.
{"title":"Gabor wavelet and unsupervised Fuzzy C-means clustering for edge detection of medical images","authors":"B. Ergen, A. Cinar, G. Aydin","doi":"10.1109/INISTA.2012.6246972","DOIUrl":"https://doi.org/10.1109/INISTA.2012.6246972","url":null,"abstract":"It is well known that the Gabor wavelet transform (GWT) provides directional information for the analysis of an image. In this paper, we proposed an approach based on the GWT by combining unsupervised Fuzzy c-means (FCM) clustering which provides plays an important role in recognition as a classifier. After enhancing the edge of the input image using GWT, the binary image showing the edge is obtained using FCM clustering and morphological skeletonization. When compared to the Canny method and other conventional method, the proposed method has showed a better performance in terms of detection accuracy for noisy medical images.","PeriodicalId":305858,"journal":{"name":"2012 International Symposium on Innovations in Intelligent Systems and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130445614","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 : 2012-07-02DOI: 10.1109/INISTA.2012.6247015
Z. Ahmed, A. Hussain, D. Al-Jumeily
This paper presents a new technique called edge detection for fast block-matching motion estimation. In order to find the matching macroblock for the current macroblock from previous frame, this technique classifies the current macroblock into shade and edge. The shade macroblock has a high probability to move in the same direction as its neighbouring macroblocks. This property has been used to decrease the computations of Mean Predictive Block Matching algorithm. The proposed technique used only the motion vectors of the neighbouring macroblocks and ignore other motion vectors that were utilized in the first search step of Mean Predictive Block Matching algorithm. Experimental results of various video sequences types showed that the proposed technique reduces the average number of search points required per macroblock for the videos, as well as keeps or enhances the resolution of some decompressed videos in comparison to the Mean Predictive Block Matching algorithm and the standard block matching algorithms.
{"title":"Edge detection for fast block-matching motion estimation to enhance Mean Predictive Block Matching algorithm","authors":"Z. Ahmed, A. Hussain, D. Al-Jumeily","doi":"10.1109/INISTA.2012.6247015","DOIUrl":"https://doi.org/10.1109/INISTA.2012.6247015","url":null,"abstract":"This paper presents a new technique called edge detection for fast block-matching motion estimation. In order to find the matching macroblock for the current macroblock from previous frame, this technique classifies the current macroblock into shade and edge. The shade macroblock has a high probability to move in the same direction as its neighbouring macroblocks. This property has been used to decrease the computations of Mean Predictive Block Matching algorithm. The proposed technique used only the motion vectors of the neighbouring macroblocks and ignore other motion vectors that were utilized in the first search step of Mean Predictive Block Matching algorithm. Experimental results of various video sequences types showed that the proposed technique reduces the average number of search points required per macroblock for the videos, as well as keeps or enhances the resolution of some decompressed videos in comparison to the Mean Predictive Block Matching algorithm and the standard block matching algorithms.","PeriodicalId":305858,"journal":{"name":"2012 International Symposium on Innovations in Intelligent Systems and Applications","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134639607","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 : 2012-07-02DOI: 10.1109/INISTA.2012.6247044
Mete Celik, N. Azginoglu, Ramazan Terzi
Periodic spatio-temporal co-occurrence patterns (PECOPs) represent subsets of object-types that are often periodically located together in space and time. Discovering PECOPs is an important problem with many applications such as discovering interactions between animals and identifying tactics in games. However, mining PECOPs is computationally very expensive because the interest measures are computationally complex, databases are larger due to the archival history, and the set of candidate patterns is exponential in the number of object-types. In this paper, we define the problem of mining PECOPs, and propose a novel PECOP mining algorithm. The experimental results show that the proposed algorithm is computationally more efficient than the naïve alternatives.
{"title":"Mining periodic spatio-temporal co-occurrence patterns: A summary of results","authors":"Mete Celik, N. Azginoglu, Ramazan Terzi","doi":"10.1109/INISTA.2012.6247044","DOIUrl":"https://doi.org/10.1109/INISTA.2012.6247044","url":null,"abstract":"Periodic spatio-temporal co-occurrence patterns (PECOPs) represent subsets of object-types that are often periodically located together in space and time. Discovering PECOPs is an important problem with many applications such as discovering interactions between animals and identifying tactics in games. However, mining PECOPs is computationally very expensive because the interest measures are computationally complex, databases are larger due to the archival history, and the set of candidate patterns is exponential in the number of object-types. In this paper, we define the problem of mining PECOPs, and propose a novel PECOP mining algorithm. The experimental results show that the proposed algorithm is computationally more efficient than the naïve alternatives.","PeriodicalId":305858,"journal":{"name":"2012 International Symposium on Innovations in Intelligent Systems and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115071981","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：