2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)最新文献

{"title":"Three-term relation neuro-fuzzy cognitive maps","authors":"Michal Puheim, J. Vaščák, L. Madarász","doi":"10.1109/CINTI.2014.7028723","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028723","url":null,"abstract":"In this paper, we propose a novel approach to modeling using fuzzy cognitive maps, which we refer to as the Three-Term Relation Neuro-Fuzzy Cognitive Map or simply the TTR NFCM. The proposed method is mostly suited to model complex nonlinear technical systems with dynamic internal characteristics. With this method we aim to solve some of the most critical problems of the conventional fuzzy cognitive maps. We target two of these problems by hybridization with artificial neural networks. First of them is a linear nature of relations between the concepts. The second is a lack of mutual dependence between the relations connecting to the same concept. Finally, we tackle a problem of relation dynamics using an inspiration from the control engineering. While focusing on bringing these advanced additional methods to the design of cognitive maps, we also aim to keep the degree of dependency on expert knowledge on the same level as with the conventional fuzzy cognitive maps. We achieve this by utilizing the machine learning methods. However, since the proposed method is heavily dependent on automated data-driven learning, it is suitable mainly for systems which are well observable and can produce sufficient training datasets.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125304553","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 sharpness metrics for HE stained blood cell images","authors":"G. Windisch, M. Kozlovszky","doi":"10.1109/CINTI.2014.7028679","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028679","url":null,"abstract":"Image sharpness is a feature that has great influence on image quality. In this paper we present methods to evaluate the sharpness of images, that can be used to select the best image in a sequence of images taken of the same scene using different focus settings. We then execute measurements on 1195 image sets using two sharpness metrics - one based on image gradient sums and one based on the edges found in the images. The metrics are evaluated on original noise free images, different amount of noise is added to the images and the metrics are reevaluated in those circumstances as well. Two additional evaluation properties are proposed in this article: roboustness and position of the sharpest image in a miss.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129472439","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":"Environment and situation monitoring for firefighter teams","authors":"M. Kozlovszky, D. Pavlinic","doi":"10.1109/CINTI.2014.7028715","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028715","url":null,"abstract":"Environment and situation awareness are key factors to effectively work or even to survive in harsh environment. Over recent decades, the need to adequately protect the human in various dangerous situations has forced the development of clothing industry in the direction to provide high innovative products, and equip their products with sensors or other means of smart technologies. Besides basic functions of protection, thermal and ergonomic comfort, these new generation protective garments have served also functions like monitoring and/or protection. Heat injury is a major issue for firefighters as they wear insulated clothing and cannot shed the heat generated from physical exertion. Early detection of heat issues is critical to stop dehydration and heat stress becoming fatal. Early onset of heat stress affects cognitive function which combined with operating in dangerous environment makes heat stress and dehydration a critical issue to monitor. Physiological status monitors measure firefighter's vital sign status, fatigue and exertion levels. This allows a Fire Chief to call in additional personnel before the crew gets exhausted and also gives an early warning to firemen before they run out of energy, as they may not be able to make voice calls over their radio. However early solutions have been only partly accepted by the professional end users. Design requirements such as cost, bulkiness, accuracy, independency, scalability, robustness are key parameters, which can cause high acceptance or usage prevention rapidly. We approached the development of intelligent fire suits integrated with a data acquisition (DAQ) system and we are using enabling technologies to collect measured physiological and environment information about the firefighter(s) remotely. In our first prototype we are monitoring basic physiological parameters as well the microenvironment temperature. With our DAQ solution we measure, combine, transfer physiological and environmental signals collected from and within the firefighter's suit to monitor and visualize whole firefighter platoons remotely.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121347501","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":"Improving classification accuracy using Fuzzy Clustering Coefficients of Variations (FCCV) feature selection algorithm","authors":"S. Fong, Justin Liang, Zhuang Yan","doi":"10.1109/CINTI.2014.7028666","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028666","url":null,"abstract":"One of the challenges in inferring a classification model with good prediction accuracy is to select the relevant features that contribute to maximum predictive power. Many feature selection techniques have been proposed and studied in the past, but none so far claimed to be the best. In this paper, a novel and efficient feature selection method called Fuzzy Clustering Coefficients of Variation (FCCV) is proposed. FCCV is based on a very simple principle of variance-basis which finds an optimal balance between generalization and over-fitting. Through a computer simulation experiment, 44 datasets with substantially large number of features are tested by FCCV in comparison to four popular feature selection techniques. Results show that FCCV outperformed them in all aspects of averaged performances and speed. By the simplicity of design it is anticipated that FCCV will be a useful alternative of preprocessing method for classification especially with those datasets that are characterized by many features.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"301 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121461423","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":"An efficient framework for distributed computing in heterogeneous Beowulf clusters and cluster-management","authors":"Darius Malysiak, U. Handmann","doi":"10.1109/CINTI.2014.7028670","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028670","url":null,"abstract":"In the context of existing approaches to cluster computing we present a newly developed modular framework `SimpleHydra' for rapid deployment and management of Beowulf clusters. Instead of focusing only the pure computation tasks on homogeneous clusters (i.e. clusters with identically set up nodes), this framework aims to ease the configuration of heterogeneous clusters and to provide a low-level / high-level object-oriented API for low-latency distributed computing. Our framework does not make any restrictions regarding the hardware and minimizes the use of external libraries to the case of special modules. In addition to that our framework enables the user to develop highly dynamic cluster topologies. We describe the framework's general structure as well as time critical elements, give application examples in the `Big-Data' context during a research project and briefly discuss additional features. Furthermore we give a thorough theoretical time/space complexity analysis of our implemented methods and general approaches.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124351442","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":"Link prediction in weighted symptom networks","authors":"Buket Kaya, M. Poyraz","doi":"10.1109/CINTI.2014.7028688","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028688","url":null,"abstract":"The saying “treat the disease, not the symptoms” is widespread, a cliche for eliminating or repairing the root of a problem rather than mitigating the negative effects. It is taken for granted that prevention is the best course of action. It is ironic, then, that many of today's best “disease treatments” are actually symptom suppressors. This paper predicts the onset of future symptoms on the base of the current health status of patients. The problem of predicting the relations between symptoms (abnormal parameters in this paper) which can be shown as the reason of a disease in the future is a really difficult and, at the same time, an important task. For this purpose, the present paper first constructs a weighted symptom networks considering the relations between abnormal parameters. Then, it proposes a link prediction method to identify the connections between parameters, building the evolving structure of symptom network with respect to patients' ages. To the best of our knowledge, this is the first attempt in predicting the connections between the results of laboratory tests. Experiments on a real network demonstrate that the proposed approach can reveal new abnormal parameter correlations accurately and perform well at capturing future disease risks.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124118697","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":"Low consumption and high performance intel, AMD and ARM based Mini PCs","authors":"P. Dukan, A. Kovari, J. Katona","doi":"10.1109/CINTI.2014.7028662","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028662","url":null,"abstract":"Earlier we have already tested an ARM-based SBC (Single Board Computer) solution, which cannot keep up with the performance of a Mini PC, but we achieved nearly the same functionality in its installed Linux system, while consumption outpaced its rival. Since then, the ARM has undergone a huge development; though, Intel and AMD have taken steps to reduce their consumption and AMD has launched their APU solution. We will try to present that development in this paper and find the answer where the ARM-producers are in comparison with Intel and AMD, regarding performance, consumption and price.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131158070","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":"Belief influence diagrams","authors":"Rahma Ferjani, I. Boukhris, Zied Elouedi","doi":"10.1109/CINTI.2014.7028652","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028652","url":null,"abstract":"Influence diagrams are one of the most effective representational tools for decision analysis. However, probabilistic influence diagrams require the availability of probability distributions for all problem's uncertain variables which is not always typical to most real world applications. This paper presents a new approach which adapts these models to real world problems by extending classical influence diagrams within the belief function theory. Hence, we define new graphical decision models called belief influence diagrams which overcome some of the classical influence diagrams limitations such as the necessity of the entire probability distributions. This paper proposes belief evaluation method. It is an adaptation of Shachter method based on arc reversal and nodes removal operations by adding more assumptions specific to belief influence diagrams.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134495519","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":"Double field oriented sensorless control of cage induction motor","authors":"E. Szoke, C. Szabo, M. Imecs, I. Incze","doi":"10.1109/CINTI.2014.7028708","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028708","url":null,"abstract":"The paper presents a vector control strategy for induction motor without mechanical sensor using double field-orientation procedure. It combines the advantages of both, rotor-and stator-field orientation. As a consequence the computation of control variables and also the speed identification calculus is independent of the rotor resistance, which improves the performance/robustness of the system.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"210 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133452973","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":"Achieving DDoS resiliency in a software defined network by intelligent risk assessment based on neural networks and danger theory","authors":"Ionita Mihai-Gabriel, Patriciu Victor-Valeriu","doi":"10.1109/CINTI.2014.7028696","DOIUrl":"https://doi.org/10.1109/CINTI.2014.7028696","url":null,"abstract":"Distributed Denial of Service (DDoS) attacks are becoming a very versatile weapon. Unfortunately, they are becoming very popular amongst cyber criminals, and they are also getting cheaper. As the interest grows for such weapons on the black market, their scale reaches unimaginable proportions. As is the case of the Spamhaus attack, which was mitigated by CloudFlare through null-routing techniques. This paper presents a way of mitigating DDoS attacks in a Software Defined Network (SDN) environment, by assessing risk through the means of a cyber-defense system based on neural networks and the biological danger theory. In addition to mitigating attacks the demo platform can also perform full packet capture in the SDN, if the central command component deems it necessary. These packet captures can be used later for forensic analysis and identification of the attacker.","PeriodicalId":435053,"journal":{"name":"2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132728549","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}