Konstantinos Demertzis, L. Iliadis, Vardis-Dimitris Anezakis
{"title":"A deep spiking machine-hearing system for the case of invasive fish species","authors":"Konstantinos Demertzis, L. Iliadis, Vardis-Dimitris Anezakis","doi":"10.1109/INISTA.2017.8001126","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001126","url":null,"abstract":"Prolonged and sustained warming of the sea, acidification of surface water and rising of sea levels, creates significant habitat losses, resulting in the proliferation and spread of invasive species which immigrate to foreign regions seeking colder climate conditions. This is happening either because their natural habitat does not satisfy the temperature range in which they can survive, or because they are just following their food. This has negative consequences not only for the environment and biodiversity but for the socioeconomic status of the areas and for the human health. This research aims in the development of an advanced Machine Hearing system towards the automated recognition of invasive fish species based on their sounds. The proposed system uses the Spiking Convolutional Neural Network algorithm which cooperates with Geo Location Based Services. It is capable to correctly classify the typical local fish inhabitants from the invasive ones.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125140326","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}
{"title":"Comparison of convolutional neural network models for food image classification","authors":"Gozde Ozsert Yigit, Buse Melis Özyildirim","doi":"10.1080/24751839.2018.1446236","DOIUrl":"https://doi.org/10.1080/24751839.2018.1446236","url":null,"abstract":"According to some estimates of World Health Organization (WHO), in 2014, more than 1.9 billion adults aged 18 years and older were overweight. Overall, about 13% of the world's adult population (11% of men and 15% of women) were obese. 39% of adults aged 18 years and over (38% of men and 40% of women) were overweight. The worldwide prevalence of obesity more than doubled between 1980 and 2014. The purpose of this study is to design a convolutional neural network model and provide a food dataset collection to distinguish the nutrition groups which people take in daily life. For this aim, both two pretrained models Alexnet and Caffenet were finetuned and a similar structure was trained with dataset. Food images were generated from Food-11, FooDD, Food100 datasets and web archives. According to the test results, finetuned models provided better results than trained structure as expected. However, trained model can be improved by using more training examples and can be used as specific structure for classification of nutrition groups.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115782746","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}
{"title":"Multi-criteria trajectory base path planning algorithm for a moving object in a dynamic environment","authors":"A. Lazarowska","doi":"10.1109/INISTA.2017.8001136","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001136","url":null,"abstract":"The paper introduces a new, original approach for the application in robotics and automation. The application concerns a path planning module of an intelligent control system. The marine environment was chosen as an exemplary application area, but the method can also be applied for mobile robots. The presented approach calculates a safe, optimal path for a ship in a dynamic environment, where static and dynamic obstacles occur. The paper includes the background of the presented research, the description of a new method and results of simulation studies. Simulation tests covered simple and more complex scenarios with a few static and dynamic obstacles in the environment. The results proof the problem solving capability of the proposed approach and the potential of its applicability in commercial systems due to short computational time and satisfactory solutions.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121512977","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}
{"title":"A hybrid Latent Dirichlet Allocation approach for topic classification","authors":"Chi-I Hsu, C. Chiu","doi":"10.1109/INISTA.2017.8001177","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001177","url":null,"abstract":"Many classification techniques can automatically summarize text into topics and accordingly identify topic terms from the online reviews. Among these techniques Latent Dirichlet Allocation (LDA) and Latent Semantic Analysis (LSA) are some of the most often employed approaches. LDA is a probability generated model that projects a document into the topic space using Dirichlet Distribution, and each topic is a collection of words of the probability distribution. As the LDA extracted topics are often implicit, this study first applies LDA to examine the topics of online reviews for game apps in a supervised way. To improve the topic classification performance for LDA, this study proposes a hybrid LDA approach to use Genetic Algorithm (GA) in discovering optimal weights for LDA topics.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116756512","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}
{"title":"Distributed image retrieval with color and keypoint features","authors":"M. Lagiewka, M. Korytkowski, R. Scherer","doi":"10.1109/INISTA.2017.8001130","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001130","url":null,"abstract":"Big data term refers to different variations of large datasets to complex to be processed by traditional computing methods. The paper presents a system for retrieving images in relational databases in a distributed environment. Content of the query image and images in the database is compared using global color information and local image keypoints. Image keypoints are indexed by fuzzy sets directly in a relational database. To distribute the process to several machines we use the Apache Hadoop software framework with HDFS.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127270979","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}
{"title":"Ensemble approach for time series analysis in demand forecasting: Ensemble learning","authors":"A. Akyuz, M. Uysal, B. Bulbul, M. Uysal","doi":"10.1109/INISTA.2017.8001123","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001123","url":null,"abstract":"Demand forecasting for replenishment is one of the main issue for retail industry in terms of optimizing stocks, minimizing costs and also for reducing stock out problem. Better forecasting for demands, means maximizing sales and result with more revenue and profit for retailers. An other critical result of the stock out problem is of course dissatisfied customers and customer churn effect to retailers as well. Customers, in general do not wish to buy an equivalent product from different brands instead of their routine selections. There are of course many parameters which affect very seriously forecasting accuracy of consumer demands. For instance; seasonality, promotional effects, social events, new trends, unexpected crisis, terrorism, changes on weather conditions, commercial behavior of competitors at the market etc. In this study, new heuristic approach for ensemble methodology has been proved. It has been implemented in SOK Market. It is one of Turkey's hard discount retail chain with 4000 stores and replenishes 1500 SKUs to stores via 22 regional distribution centers. The results of this approach and how to take benefits of the powerful common minded demand forecasting in time series forecasting analysis have been showed.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130270428","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}
{"title":"Ranking nodes by silentness","authors":"Soheil Ghanbari, Hasan Heydari, A. Moeini","doi":"10.1109/INISTA.2017.8001205","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001205","url":null,"abstract":"Silentness in networks refers to the behavior that a node receives lots of information from other nodes but share nothing or little information with them. We can rank people in social networks by silentness. In this paper we present an algorithm based on random walks for ranking nodes by silentness. The time complexity of the proposed algorithm in a network with n nodes is O(log2n) with high probability, while the state-of-the-art algorithm does not specified time complexity and runs until holds convergence conditions and we show it does not converge in all cases by a counterexample. We assess the proposed algorithm with Fagin's intersection metric and Bperef methods and compare the implementation results of the algorithm on GPlus and Twitter datasets with PageRank and I/O ranking methods. We implement our algorithm on Hadoop framework, as well and in compare of the state-of-the-art algorithm reduces 64.48% of the disk I/O.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132198059","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}
{"title":"Basic clustering algorithms used for monitoring the processes of the ATM's OS","authors":"Michal Maliszewski, U. Boryczka","doi":"10.1109/INISTA.2017.8001128","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001128","url":null,"abstract":"The number of highly sophisticated software-based attacks on ATMs is growing these days. New types of threats require new ways of system protection. Most secure solutions are based on whitelists and sandboxes, which unlike antivirus solutions are able to protect the system against any new threat. Sadly, they are hard to configure therefore require an expert-level knowledge of operating system mechanisms and software security techniques. The main purpose of this article is to present the possibilities of using clustering algorithms in a configuration process of a sandbox-based security solution. Results of the experimental studies show that even basic clustering algorithms can be used as a part of the configuration process. Achieved results were deemed promising by the control algorithm and thus can be used as a base for future research.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132366483","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}
{"title":"Evaluating the effect of voting methods on ensemble-based classification","authors":"Florin Leon, S. Floria, C. Bǎdicǎ","doi":"10.1109/INISTA.2017.8001122","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001122","url":null,"abstract":"Bagging is a popular method used to increase the accuracy of classification, by training a set of classifiers on slightly different datasets and aggregating their output by voting. Usually, the majority voting is used for this purpose, or the plurality voting, when the problem has multiple class values. In this study, we analyze the influence of several voting methods on the performance of two classification algorithms used for datasets with different levels of difficulty. The results reveal that the single transferable vote can be a good alternative to plurality voting, although it has the drawback of a higher computational cost related to the calculation of preference ordering.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129616629","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}
{"title":"Monthly car sales prediction using Internet Word-of-Mouth (eWOM)","authors":"C. Chiu, Chia-Houng Shu","doi":"10.1109/INISTA.2017.8001183","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001183","url":null,"abstract":"Internet's mature has changed the behavior of consumers. Most of consumers before purchase will queries opinion on the Internet. Vehicle is high priced and durable merchandise, so consumer would be more prudent to view Internet opinion before they buy. Past research has pointed out eWOM (electronic Word-of-Mouth) and customer satisfaction will influence purchasing decision, 70% of consumers believe eWOM. In this study, we utilizes economic indexes, Internet “word of mouth”, and Google Trends variables created by key word searches to forecast the monthly sales volumes of a given model of car. The experiment results demonstrate that the proposed GA/KNN model has the highest predictive power in terms of Mean Absolute Percentage Error (MAPE).","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116734003","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}