2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY)最新文献

{"title":"Uniform dispersal of silent oblivious robots","authors":"Attila Hideg, Tamás Lukovszki, B. Forstner","doi":"10.1109/SISY.2017.8080548","DOIUrl":"https://doi.org/10.1109/SISY.2017.8080548","url":null,"abstract":"Consider the Filling problem, in which a set of mobile robots enter an unknown area and have to disperse in that area. The robots are homogeneous, anonymous, autonomous, have limited visibility radius, and do not use explicit communication. Moreover, these robots are oblivious, i.e. they do not have any bits of persistent memory. It is already known that these limitations prevent the creation of a deterministic algorithm to solve the Filling problem. In this paper an algorithm is presented, which is the first to overcome those limitations, to fill the area with oblivious robots. The algorithm is collision-free, has an expected termination time of O(n3) rounds, where n is the number of robots (and the number of cells in the area).","PeriodicalId":352891,"journal":{"name":"2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125248441","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 time- and frequency-domain features for movement classification using data from wrist-worn sensors","authors":"Peter Sarcevic, Szilveszter Pletl, Zoltán Kincses","doi":"10.1109/SISY.2017.8080564","DOIUrl":"https://doi.org/10.1109/SISY.2017.8080564","url":null,"abstract":"Inertial and magnetic sensors are widely used for different pattern recognition applications. In this paper, features extracted using time- and frequency-domain analysis are compared for human movement classification. Applied data were collected using wrist-mounted Wireless Sensor Network (WSN) motes equipped with 9 degree of freedom (9DOF) sensor boards. Data acquisition was done with the help of multiple subjects. To explore the capabilities of the used sensor types, different feature sets were generated and tested using multiple sensor combinations, and the feature extraction was tested utilizing raw sensor signals and computed magnitudes. The classification was done using MultiLayer Perceptron (MLP) neural networks. The obtained results show that the time-domain features (TDFs) provide higher classification efficiencies than frequency-domain features (FDFs). The highest obtained classification rate on unknown data was 91.74% using TDFs, and 88.51% applying FDFs.","PeriodicalId":352891,"journal":{"name":"2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY)","volume":" 46","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120834280","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":"Labor market risks of industry 4.0, digitization, robots and AI","authors":"Zóltan Rajnai, István Kocsis","doi":"10.1109/SISY.2017.8080580","DOIUrl":"https://doi.org/10.1109/SISY.2017.8080580","url":null,"abstract":"Digitization changes our world. Industry 4.0, the digital transformation of manufacturing changes the labor market. The impacts of rapid technology development of the fourth industrial revolution present huge challenges for the society and for policy makers. Are we facing reduction of employment by automation rendering human work force uncompetitive with machines? Can creation of new fields of employment, new types of jobs compensate for the loss of traditional labor market requirements?","PeriodicalId":352891,"journal":{"name":"2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123947604","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":"LPV-based control of nonlinear compartmental model with input uncertainty","authors":"G. Eigner, Á. Varga, Miklos Mezei, L. Kovács","doi":"10.1109/SISY.2017.8080538","DOIUrl":"https://doi.org/10.1109/SISY.2017.8080538","url":null,"abstract":"In this study we introduce a Linear Parameter Varying (LPV) based controller design possibility for LPV systems with state and input uncertainties. Through the LPV framework the developed method can be used for the nonlinear system belongs to the given LPV system. The controller design approach effectively exploits the combination of the classical state feedback and matrix similarity theorems in order to realize a complementary LPV controller. By using this controller the necessary control action will be determined via a comparison to a given reference Linear Time Invariant (LTI) system which is given by the fixation of the parameter vectors in the parameter space. We proven the usability of the developed method on a highly nonlinear compartmental model. The results showed that the developed complementary controller structure performed well. We compared the dynamics of the reference LTI system, the LPV system and the original nonlinear system to each other by using a norm based error of the states. The magnitude of the error signals were small and acceptable in all cases. Moreover, the deviation between the LPV system and the original nonlinear system was negligible (only numerical error occurred), namely, the developed control structure can be used directly for the nonlinear system as well.","PeriodicalId":352891,"journal":{"name":"2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"236 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122620501","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":"FaceTime — Deep learning based face recognition attendance system","authors":"M. Arsenovic, S. Sladojevic, A. Anderla, Darko Stefanović","doi":"10.1109/SISY.2017.8080587","DOIUrl":"https://doi.org/10.1109/SISY.2017.8080587","url":null,"abstract":"In the interest of recent accomplishments in the development of deep convolutional neural networks (CNNs) for face detection and recognition tasks, a new deep learning based face recognition attendance system is proposed in this paper. The entire process of developing a face recognition model is described in detail. This model is composed of several essential steps developed using today's most advanced techniques: CNN cascade for face detection and CNN for generating face embeddings. The primary goal of this research was the practical employment of these state-of-the-art deep learning approaches for face recognition tasks. Due to the fact that CNNs achieve the best results for larger datasets, which is not the case in production environment, the main challenge was applying these methods on smaller datasets. A new approach for image augmentation for face recognition tasks is proposed. The overall accuracy was 95.02% on a small dataset of the original face images of employees in the real-time environment. The proposed face recognition model could be integrated in another system with or without some minor alternations as a supporting or a main component for monitoring purposes.","PeriodicalId":352891,"journal":{"name":"2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130181159","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":"Data analytics for clouds health-care and risk predictions based on ensemble classifiers and subjective projection","authors":"H. Fujita","doi":"10.1109/SISY.2017.8080525","DOIUrl":"https://doi.org/10.1109/SISY.2017.8080525","url":null,"abstract":"Discovering patterns from big data attracts a lot of attention due to its importance in discovering accurate patterns and features that are used in predictions of decision making. The challenges in big data analytics are the high dimensionality and complexity in data representation. Granular computing and feature selection are among the challenge to deal with big data analytics that is used for Decision making. We will discuss these challenges in this talk and provide new projection on ensemble learning for health care risk prediction. In decision making most approaches are taking into account objective criteria, however the subjective correlation among different ensembles provided as preference utility is necessary to be presented to provide confidence preference additive among it reducing ambiguity and produce better utility preferences measurement for good quality predictions. Most models in Decision support systems are assuming criteria as independent. Different type of data (time series, linguistic values, interval data, etc.) imposes some difficulties to data analytics due to preprocessing and normalization processes which are expensive and difficult when data sets are raw and imbalanced. We will highlight these issues though project applied to health-care for elderly, by merging heterogeneous metrics for providing health care predictions for elderly at home. We have utilized ensemble learning as multi-classification techniques on multi-data streams that collected from multi-sensing devices. Subjectivity (i.e., service personalization) would be examined based on correlations between different contextual structures that are reflecting the framework of personal context, for example in nearest neighbor based correlation analysis fashion. Some of the attributes incompleteness also may lead to affect the approximation accuracy. Attributes with preference-ordered domain relations properties become one aspect in ordering properties in rough approximations. We outline issues on Virtual Doctor Systems, and highlights its innovation in interactions with elderly patients, also discuss these challenges in granular computing and decision support systems research domains. In this talk I will present the current state of art and focus it on health care risk analysis with examples from our experiments.","PeriodicalId":352891,"journal":{"name":"2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126499245","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 prescription-based automatic medical diagnosis system using a stacking method","authors":"Shiva Kazempour Dehkordi, H. Sajedi","doi":"10.1109/SISY.2017.8080550","DOIUrl":"https://doi.org/10.1109/SISY.2017.8080550","url":null,"abstract":"The amount of data being collected and stored is huge and is expanding at a vivid pace at both the national and international level. Health care organizations correspondingly generate a large volume of information every day. The health care industry is rich in information but it needs to discover hidden relationships and patterns in this data. This paper intends to use data mining techniques to discover knowledge in a dataset that was provided by a research center in Tehran. By analyzing the drugs that were bought by each patient, this paper aims to predict what kind of physician each patient has referred to and what kind of disease they are suffering from. The dataset includes details such as sex, age and the names of the drugs prescribed for each patient. For labeling the instances, a group of pharmacy students and professors has determined each patient's disease. A number of experiments have been performed to compare the performance of different data mining techniques for predicting the diseases and the results illustrate that the proposed Stacking Model has higher accuracy compared to other techniques such as k-Nearest Neighbor (kNN), Naïve Bayes, Decision Tree etc.","PeriodicalId":352891,"journal":{"name":"2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131274359","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":"Computational relaxations for affine tensor product model transformation","authors":"József Kuti, P. Galambos","doi":"10.1109/SISY.2017.8080577","DOIUrl":"https://doi.org/10.1109/SISY.2017.8080577","url":null,"abstract":"The paper introduces methods that decrease the computational and memory burden of discretisation based affine tensor product model transformation. Their importance comes from the fact, that the computational cost of multi-variate functions' orthonormalization and the amount of accessible memory bound the applicable discretisation density and the number of parameters. The proposed methods can overwhelm these limitations and allow to apply the methodology on LPV/qLPV models of complex, practically relevant systems.","PeriodicalId":352891,"journal":{"name":"2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114778688","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":"Human action recognition with hidden Markov models and neural network derived poses","authors":"E. Gedat, Pascal Fechner, Richard Fiebelkorn, R. Vandenhouten","doi":"10.1109/SISY.2017.8080544","DOIUrl":"https://doi.org/10.1109/SISY.2017.8080544","url":null,"abstract":"A human action recognition method is introduced that detects a set of actions in videos by a temporal expansion with hidden Markov models of a pose detection with an artificial neural network. The method was set-up and tested using eleven actions from the MOCAP motion capture database comprising 3,947 frames. A poses alphabet of fourteen relevant poses was defined to be learned by an artificial neural network. It was trained with the skeletons and a manual pose classification of 370 key frame images from the motions resulting in an accuracy of 83.5 %. Three actions prevalent in the used motions were chosen to be recognized with the interplay of one separate hidden Markov model for each action. From the output of the trained artificial neural network for all 1,891 frames of seven of the eleven motions together with a manual pose and action classification the matrices of the hidden Markov models for the four actions were calculated. A tailored maximum likelihood estimation based on the Viterbi algorithm generated an action proposal for each frame. The resulting overall accuracy was 83.2 % precision and 83.7 % recall for recognition of the actions.","PeriodicalId":352891,"journal":{"name":"2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124120758","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":"Recognition of the stomach cancer images with probabilistic HOG feature vector histograms by using HOG features","authors":"S. A. Korkmaz, Aysegul Akcicek, Hamidullah Binol, M. Korkmaz","doi":"10.1109/SISY.2017.8080578","DOIUrl":"https://doi.org/10.1109/SISY.2017.8080578","url":null,"abstract":"In this study, normal (n), benign (b), and malign (m) stomach image cells have taken from faculty of Medicine the Fırat University with Light Microscope help. Total number of stomach images are 180 which be 60 n, 60 b, and 60 m. 90 of these 180 stomach images have been used for testing purposes and 90 have been used for training purposes. The histograms of oriented gradient (HOG) feature extraction method were used for these images. HOG feature vectors were obtained by plotting HOG features on normal, benign, and malign original stomach images. Using these HOG property vectors, histograms of normal, benign, and malignant stomach images were plotted. Bins and h histogram values were obtained from these drawn histograms. A bandwidth range that can be distinguished between normal, benign, and malignant stomach images was calculated by comparing the bins and h values obtained for normal (n), benign (b) and malign (m) images. This bandwidth range was found to be 0.09–0.22. According to this bandwidth range, the accuracy result of stomach cancer images is found as 100%. When the h values of the HOG feature vector between these bandwidths are examined, the h values of normal and benign stomach images are found to be higher than those of a malignant stomach image. Between this bandwidth, the h value of the normal stomach image was found to be higher than the benign stomach image.","PeriodicalId":352891,"journal":{"name":"2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134445460","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}