{"title":"Algorithms for direct L2 support vector machines","authors":"V. Kecman, Ljiljana Zigic","doi":"10.1109/INISTA.2014.6873654","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873654","url":null,"abstract":"Paper introduces a novel Direct L2 Support Vector Machine (DL2 SVM) and compares the performances of its three learning algorithms on 12 `small' and 4 `medium' real binary and multi-class datasets. The DL2 SVM model is posed as solving a NonNegative (NN) Least Squares (LS) problem. This leads to a solution in much less CPU time than what the SVMs based on quadratic programming (QP) problem need. Three techniques for solving DL2 SVM's problem are the NNLS using Cholesky decomposition with an update, NN Conjugate Gradient method and a new NN Iterative Single Data Algorithm (ISDA). All 3 methods produce both high and similar classification accuracy within the very strict nested crossvalidation (a.k.a. double resampling) experimental environment, but they do significantly differ in terms of speed. Paper presents the performances of three different algorithms in terms of accuracy, model size (percentage of support vectors obtained) and CPU time used.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134376614","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":"FPGA implementation of Differential Evaluation Algorithm for MLP training","authors":"Ali Riza Yilmaz, B. Erkmen, O. Yavuz","doi":"10.1109/INISTA.2014.6873655","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873655","url":null,"abstract":"In this work, Differential Evolution Algorithm (DEA) is implemented on an embedded systems based on FPGA for the training of multi-layer perceptron (MLP). The classification performance of the MLP trained by DEA on FPGA has been analyzed by using a non-linear database. The MLP performance on FPGA has been compared with that on MATLAB in terms of computational performance and test accuracy. It is proved that DEA is suitable for realizing on FPGA considering simplicity of the algorithm. Simulation results of each component for DEA on FPGA are demonstrated in this paper.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126702693","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}
Mehmet Karaköse, M. Baygin, Nursena Baygin, Kagan Murat, E. Akin
{"title":"An intelligent reconfiguration approach based on fuzzy partitioning in PV arrays","authors":"Mehmet Karaköse, M. Baygin, Nursena Baygin, Kagan Murat, E. Akin","doi":"10.1109/INISTA.2014.6873644","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873644","url":null,"abstract":"The reconfiguration process in photovoltaic (PV) arrays is very important to obtain maximum power under partial shading conditions. Connection architecture of array for this process is changed according to status of non-uniform shadows. However, finding of best connection in big PV arrays is hard in real-time. In this paper, a new efficient and intelligent reconfiguration approach based on partitioning of array is proposed. The proposed approach is aimed to search best connection from possible connections in several small-sized array partitions obtained with decomposing according to location of shadows to carry out control task. Thus, search space of possible connections is considerably reduced for using in real time implementation of reconfiguration process in big size PV arrays. Efficiency, accuracy, and performance proposed reconfiguration approach has been verified for different size and shading conditions with comparative simulation results.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132361701","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":"Tracking a single node's availability for communication by means of observing local system resources","authors":"S. Eken, F. K. Gülagiz, A. Sayar, A. Kavak","doi":"10.1109/INISTA.2014.6873595","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873595","url":null,"abstract":"“Movement of Enhancing Opportunities and Improving Technology”, abbreviated as Fatih, is among the most important educational projects in Turkey, in which students and teachers can use their tablet PCs to obtain educational data (text, images, media, etc.) stored in cloud services. However, the limited network bandwidth and increase in both the number of users and their educational data sizes degrade the system performance and even negatively affect the overall usability of the system. Using proxy server is an approach to both decreasing network traffic and increasing the efficiency in data transfers between end users and cloud services. In this approach, it is critical that when synchronization process will be performed. In this paper, bandwidth utilization, CPU and memory usage information have been examined for obtaining accurate synchronization time for this school level proxy server based distributed systems architecture. In order to minimize effect of too large and too small CPU and memory usage data, we use min-max normalization. Also, multiple linear regression is used to estimate a node's availability for communication. Experimental results show that proposed technique is feasible not only for school level proxy server based systems but also for other systems.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131798165","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":"Evolving look ahead controllers for energy optimal driving and path planning","authors":"A. Gaier, A. Asteroth","doi":"10.1109/INISTA.2014.6873610","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873610","url":null,"abstract":"An evolved neural network controller is presented to solve the optimal control problem for energy optimal driving. A controller is produced which computes equivalent control commands to traditional graph searching approaches, while able to adapt to varied constraints and conditions. Furthermore, after training, trivial amounts of computation time and memory are required, making the approach applicable for embedded systems and path planning applications.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132613010","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":"Defocussing estimation for obstacle detection on single camera smartphone Assisted navigation for vision impaired people","authors":"Alessandro Grassi, C. Guaragnella","doi":"10.1109/INISTA.2014.6873636","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873636","url":null,"abstract":"An efficient application has been developed to detect close obstacles using a single smartphone camera and give speech information to vision impaired people. The proposed algorithm uses a simple technique aimed at measuring the local estimated image defocussing to roughly estimate its closeness to the camera. Preliminary results of the developing system are presented.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126626721","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}
V. D. Lecce, D. Soldo, Alessandro Quarto, A. Giove, F. D. Lecce
{"title":"Dialogue disambiguation in Living Labs experience the Puglia Tremor system","authors":"V. D. Lecce, D. Soldo, Alessandro Quarto, A. Giove, F. D. Lecce","doi":"10.1109/INISTA.2014.6873615","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873615","url":null,"abstract":"The Living Lab idea was conceived by William Mitchell at MIT and since 2006 also Europe Union has been joining the living lab experience. In August 2011, the Regional Government of Apulia included Living Labs and Pre-commercial public procurement in their existing Operational Program of European Regional Development Fund. Hereinafter the project called “Puglia Tremor” is presented by focusing the attention on web based dialogue among living labs actors. This project represents one possible answer to the regional call and a proposal to future experience and further development of best practices. An innovative text disambiguation system is presented in order to overcome the well-known gap in human-computer interaction. Thanks to the proposed system the unskilled-user and public operators will be able to communicate using a web 2.0 approach.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114992241","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}
Vitoantonio Bevilacqua, Nicola Nuzzolese, D. Barone, M. Pantaleo, M. Suma, Dario D'Ambruoso, A. Volpe, C. Loconsole, F. Stroppa
{"title":"Fall detection in indoor environment with kinect sensor","authors":"Vitoantonio Bevilacqua, Nicola Nuzzolese, D. Barone, M. Pantaleo, M. Suma, Dario D'Ambruoso, A. Volpe, C. Loconsole, F. Stroppa","doi":"10.1109/INISTA.2014.6873638","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873638","url":null,"abstract":"Falls are one of the major risks of injury for elderly living alone at home. Computer vision-based systems offer a new, low-cost and promising solution for fall detection. This paper presents a new fall-detection tool, based on a commercial RGB-D camera. The proposed system is capable of accurately detecting several types of falls, performing a real time algorithm in order to determine whether a fall has occurred. The proposed approach is based on evaluating the contraction and the expansion speed of the width, height and depth of the 3D human bounding box, as well as its position in the space. Our solution requires no pre-knowledge of the scene (i.e. the recognition of the floor in the virtual environment) with the only constraint about the knowledge of the RGB-D camera position in the room. Moreover, the proposed approach is able to avoid false positive as: sitting, lying down, retrieve something from the floor. Experimental results qualitatively and quantitatively show the quality of the proposed approach in terms of both robustness and background and speed independence.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124907980","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}
Taqdir Ali, Maqbool Hussain, W. A. Khan, Muhammad Afzal, B. Kang, Sungyoung Lee
{"title":"Arden syntax studio: Creating medical logic module as shareable knowledge","authors":"Taqdir Ali, Maqbool Hussain, W. A. Khan, Muhammad Afzal, B. Kang, Sungyoung Lee","doi":"10.1109/INISTA.2014.6873629","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873629","url":null,"abstract":"Clinical Decision Support Systems assist the physicians to make critical decisions during the diagnosis and treatment of the patients. CDSS envisions an extendable, shareable and reusable knowledge base to generate shareable guidelines and recommendations. Existing systems utilize HL7 standard Arden Syntax MLM and data model vMR schema for shareability and interoperability purpose. Understanding the Arden Syntax and vMR schema classes is tedious task for physicians, therefore an easy to use knowledge authoring environment is required to overcome the barrier of acquiring clinical knowledge. We are presenting Arden Syntax based authoring environment called Arden Syntax Studio that provides an easy to use interface to the physicians for creating shareable MLM without understanding the HL7 standard Arden Syntax. The created MLM can easily integrate with other healthcare systems by using HL7 standard data model vMR. The system hides the vMR layer from physicians by replacing vMR schema class's layer with corresponding understandable healthcare system's concepts. Therefore, the physician does not need to learn and understand complete Arden Syntax and vMR data model to create shareable rules in form of MLM. The system also provides the Intelli-sense functionality to enhance the knowledge rule creation process and reduce the possibilities of physician's errors. Furthermore, to enhance the interoperability feature our system capitalizes standard terminologies of the SNOMED CT concepts. The terminologies that are specific to organization, environment or region are handled with localized concepts in addition to SNOMED CT concepts.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131670624","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":"Plain objects detection in image based on a contour tracing algorithm in a binary image","authors":"A. Kazlouski, R. Sadykhov","doi":"10.1109/INISTA.2014.6873624","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873624","url":null,"abstract":"Objects detection in image is a central problem to many tasks in digital image processing and therefore it has a vast range of applications. An algorithm for plain objects detection in image based on a contour tracing algorithm in a binary image is presented in this paper. The detection of plain object in image relates to the decomposition of a binary image contour into contours and closed contours and is based on the developed by the author algorithms for: an applicant for the vertex detection in a binary image, a closed contour detection in a binary image. The algorithm for an applicant for the vertex detection in a binary image allows performing the decomposition of a binary image contour into contours and closed contours. The problem of the determination of the starting point for contour tracing algorithm in a binary image is considered. The experiments show the robustness and the efficiency of the algorithm.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124743316","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}