2017 Intelligent Systems Conference (IntelliSys)最新文献

{"title":"iSAFETY — Integrated system for an automatic support to fishing vessel security","authors":"S. Aronica, I. Fontana, G. Giacalone, G. Basilone, Laura La Gattuta, M. Pulizzi, S. Genovese, S. Mangano, P. Calandrino, S. Mazzola, A. Bonanno, A. Langiu","doi":"10.1109/INTELLISYS.2017.8324305","DOIUrl":"https://doi.org/10.1109/INTELLISYS.2017.8324305","url":null,"abstract":"Fishing is one of the most dangerous sectors in which the number of accidents occurs with a high probability. The response times for rescue at sea are often worsened by the boat's accessibility, as well as the isolation in which it is located. The knowledge of the entire ship system behaviour, in real time, is very important and can allow the crew to take immediate corrective actions to prevent accidents and incidents. In this paper, we present an integrated system with an ad-hoc developed software that aims to supervise and control the behaviour of fishing nets in the water, their loads and the vessel movement response in order to give a digital support able to increase on-board security and providing early warning messages in the presence of possible situations of risk.","PeriodicalId":131825,"journal":{"name":"2017 Intelligent Systems Conference (IntelliSys)","volume":"15 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":"128054381","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":"Algorithms and approaches to mathematical modeling of conflict in a complex social system","authors":"A. Petukhov, V. M. Sandalov, A. Malhanov, Y. Petukhov","doi":"10.1109/INTELLISYS.2017.8324307","DOIUrl":"https://doi.org/10.1109/INTELLISYS.2017.8324307","url":null,"abstract":"The issue of modeling various kinds of social conflicts using diffusion equations is discussed. The main approaches are the methods of mathematical modeling in contemporary humanitarian sciences. The main concepts of social conflicts, ways of their classification, interpretation, including ethnic-social, religious and other conflicts are considered. The notion of a conflict in a social system is defined in terms of mathematical modeling. A model based on Langevin diffusion equation is introduced. The model is based on the idea that all individuals in a society interact by means of a communication field — h. This field is induced by each individual in the society, and modeling informational interaction between individuals. An analytical solution of the system of thus obtained equations in the first approximation for a diverging type of diffusion is given. It is shown that even analyzing a simple example of the interaction of two groups of individuals the developed model makes it possible to discover characteristic laws of a conflict in a social system, to determine the effect of social distance in a society on the conditions of generation of such processes, like accounting for external effects or a random factor. Based on the analysis of the phase portraits obtained by modeling, it is concluded that there exists a stability region within which the social system is stable and non-conflictive.","PeriodicalId":131825,"journal":{"name":"2017 Intelligent Systems Conference (IntelliSys)","volume":"5 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":"114176146","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":"Phased array antenna for the application of device free localization in indoor environments","authors":"Zeeshan Ellahi, Ata ur Rehman","doi":"10.1109/INTELLISYS.2017.8324261","DOIUrl":"https://doi.org/10.1109/INTELLISYS.2017.8324261","url":null,"abstract":"In an era of technological advancement, device free localization (DFL) is one of the most widely researched area. In this paper, we present a cost effective RF based device free localization technique in indoor environments. Focus of this work is to design a low cost antenna for indoor localization and also to improve localization accuracy. For this purpose microstrip patch antenna phased array is designed, which is capable to exploit angle of arrival (AOA) and received single strength (RSS) measurement to localize the target in an indoor environment. Phased array is designed using the concept of delay transmission line to radiate in ±30° in the ISM band (2.4GHz to 2.5GHz). Phased array is consisting of 4 rectangular microstrip patch antennas which are fed by a T-junction power divider. A scenario is being proposed which shows the use of phased array for the application of device free localization. It is expected that by augmenting AOA with RSS, performance of the proposed system will be more reliable than the traditional RSS based systems. To reduce the cost of antenna FR-4 laminate is used. CST is used for the simulation purpose and results are shown and discussed.","PeriodicalId":131825,"journal":{"name":"2017 Intelligent Systems Conference (IntelliSys)","volume":"45 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":"115729001","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":"Discrimination of Grey Cast Iron morphology using integrated SVM and ANN approaches","authors":"A. Khaled, M. Atia, T. Moussa","doi":"10.1109/INTELLISYS.2017.8324301","DOIUrl":"https://doi.org/10.1109/INTELLISYS.2017.8324301","url":null,"abstract":"The internal structure of Grey Cast Iron (GCI) and its microstructure determines the acceptance or rejection of several mechanical parts in the inspection process. This is based on the change of GCI mechanical properties due to the variation of its cooling rate. Visual inspection by metallurgical experts has been the approved method to assess GCI types. However, such method has always been subject to human error, biased categorization, lack of experience and variations in performance level. Even though several commercial software is available for such discrimination approaches, multiple flaws and defects are detected in the way it assesses samples. This research introduces a new software that is capable of distinguishing between GCI and other types of cast irons based on Support Vector Machines (SVM). Moreover, the software can identify the GCI types according to international standards using a well-trained Artificial Neural Network (ANN).","PeriodicalId":131825,"journal":{"name":"2017 Intelligent Systems Conference (IntelliSys)","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":"130785514","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":"Visualizing positive and negative affordances in infancy using mobile augmented reality","authors":"Miho Nishizaki","doi":"10.1109/INTELLISYS.2017.8324272","DOIUrl":"https://doi.org/10.1109/INTELLISYS.2017.8324272","url":null,"abstract":"This study proposed a prototype Augmented Reality (AR) application aimed at visualizing infants' affordances in their natural settings for prevention of accidents and promoting development. To visualize how infants perceive and acts toward everyday objects in their home environment, we (1) conducted longitudinal observations of 15 infants from 4 to 12 months of age at their homes in Japan and Portugal. (2) Developed AR application for iPhone and iPad with two types of vision-based markers. All AR contents are converted to line drawings for considering privacy based on the actual recording data. (3) Conducted informal user interviews and a user test to confirm validity and technical problems. The results demonstrated that the prototype could partially represent what the environment affords infants, and how infants interact with it using AR. The prototype will benefit from a possible future and widespread everyday use.","PeriodicalId":131825,"journal":{"name":"2017 Intelligent Systems Conference (IntelliSys)","volume":"7 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":"130821319","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":"Question answer system for online feedable new born Chatbot","authors":"S. Abdul-Kader, John Woods","doi":"10.1109/INTELLISYS.2017.8324231","DOIUrl":"https://doi.org/10.1109/INTELLISYS.2017.8324231","url":null,"abstract":"Designing a new born Chatbot and feeding it from the web with specific areas of interest is a new research field. Few researchers have investigated empty database Chatbots and populating it from web pages or plain text corpora. Extracting data from web pages needs considerable processing before the response sentences are ready for the Chatbot. Feature extraction is also needed in order to filter and quantify the extracted plain text. In addition, ranking and classification are also required. This paper presents a new method that employs multiple feature extraction methods to quantify text responses for a new born (uneducated) Chatbot. Multiple measurement metrics are examined simultaneously in order to find the nearest match to a query. The nearest matches with the highest score have been obtained by re-ranking the scores of extracted features for text responses. The results show that the highest scored sentences have subjectively a good match to the query. The evaluation results indicate that the performance of the system increases significantly by using cosine similarity to find lexical match between the query and the response sentence rather than Jaccard's coefficient.","PeriodicalId":131825,"journal":{"name":"2017 Intelligent Systems Conference (IntelliSys)","volume":"03 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":"131635356","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":"Contagion: Optimizing foodborne outbreak analysis with automatic suggestions","authors":"Dan Guo","doi":"10.1109/INTELLISYS.2017.8324348","DOIUrl":"https://doi.org/10.1109/INTELLISYS.2017.8324348","url":null,"abstract":"Contagion is a web-based foodborne outbreak analysis tool that suggests users the most pertinent views of their data. Contagion is a proposed solution to the case when there are many ways to filter, view, and analyze a given data set and there are distinct segments of the population interested in the data set for different reasons. Contagion is unique for its ability to learn analysis patterns of previous users to suggest popular views for new users. It tailors the data viewing and analysis experience to each user. More broadly, Contagion looks at the human-computer interface and seeks to delineate which aspects of user interface design can be automated. It takes a data-driven approach to suggest views for users, reducing the influence of the user interface designer. Contagion lays the groundwork for future user interfaces to be learned, decoupling the designer from the design decisions.","PeriodicalId":131825,"journal":{"name":"2017 Intelligent Systems Conference (IntelliSys)","volume":"5 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":"123742699","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":"Survey on a neural network for non linear estimation of aerodynamic angles","authors":"A. Lerro, M. Battipede, P. Gili, A. Brandl","doi":"10.1109/INTELLISYS.2017.8324240","DOIUrl":"https://doi.org/10.1109/INTELLISYS.2017.8324240","url":null,"abstract":"Unmanned Aerial Vehicles (UAV) design may involve issues on redundancy of the systems due to restricted available space and allowable weight. Virtual sensors offer great advantages from this point of view and several research projects carry out more or less complicated solutions in order to estimate a signal without applying a physical sensor. This approach brings to a reduction of the overall cost and to improve the Reliability, Availability, Maintainability and Safety (RAMS) performance. The patented technology named Smart-ADAHRS (Smart — Attitude and Heading Reference System) is a powerful technique presented during previous research for estimation of the aerodynamic angles. This algorithm is based on Artificial Neural Network (ANN) and receive inputs from on-board sensors only. Whereas previous studies considered also the signals coming from the Flight Control System (FCS), this work presents the important simplification of not considering them in the input vector. This paper resumes the previous results obtained in simulated environment with former neural network-based estimators. Then, a comparison of the results obtained by the new estimator, applying the reduced input vector in different environments, is carried out. Moreover, it re-discusses accuracy by means of a new test case that consider simulated realistic faults and noise. Eventually, a first analysis around performance in operative environment is conducted using data obtained from flight test campaigns. Results show how accuracy is preserved both in realistic situation and critical circumstances.","PeriodicalId":131825,"journal":{"name":"2017 Intelligent Systems Conference (IntelliSys)","volume":"10 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":"126774708","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 framework for pattern based melody matching for Content Based Music Information Retrieval","authors":"D. Vikram, M. Shashi","doi":"10.1109/INTELLISYS.2017.8324335","DOIUrl":"https://doi.org/10.1109/INTELLISYS.2017.8324335","url":null,"abstract":"Content Based Music Information Retrieval (CBMIR) Systems help the users to find the interesting musical object from a vast collection of musical objects based on the content expressed in terms of musical phrases referred to as repeating patterns in response to query often expressed as a smaller fragment of note sequence. It is crucial to identify repeating patterns, indexing the musical objects based on the patterns and estimate the relevance of music objects to the given query for preparing the ranked list of music objects. This paper discusses development of a framework for pattern based melody matching used to build CBMIR systems. The framework consists of five modules to support the content processing of music objects for multiple tasks. Module-1 deals with extraction of melody track from the music object and representing it as a symbolic note sequence. Alternative representational strategies and their suitability to different scenarios are discussed. Module-2 deals with extraction of approximate repeating patterns from the note sequences representing the music objects to identify semantic features of music object. Module-3 applies document retrieval techniques to transform the music objects into semantic feature space using the approximate patterns identified by the previous module. A pattern base is created to maintain the inverted list of music objects (along with the prominence scores) corresponding to each pattern. Query preprocessing to transform it into a set of query terms followed by query pattern matching with candidate patterns available in the pattern base is implemented in Module-4 of the framework. Finally the Module-5 estimates the matching scores of the music objects/songs if they contain some/all of the query patterns and sort the music objects in the order of their matching scores. Experimentation is conducted on two real world dataset of musical objects: one containing South Indian classical music and the other containing popular movie songs of India. The performance of the framework is estimated in terms of Mean Reciprocal Ranking (MRR) and is found to be satisfactory even for short queries.","PeriodicalId":131825,"journal":{"name":"2017 Intelligent Systems Conference (IntelliSys)","volume":"62 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":"128147485","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":"Bio-inspired meta-learning for active exploration during non-stationary multi-armed bandit tasks","authors":"G. Velentzas, C. Tzafestas, M. Khamassi","doi":"10.1109/INTELLISYS.2017.8324365","DOIUrl":"https://doi.org/10.1109/INTELLISYS.2017.8324365","url":null,"abstract":"Fast adaptation to changes in the environment requires agents (animals, robots and simulated artefacts) to be able to dynamically tune an exploration-exploitation trade-off during learning. This trade-off usually determines a fixed proportion of exploitative choices (i.e. choice of the action that subjectively appears as best at a given moment) relative to exploratory choices (i.e. testing other actions that now appear worst but may turn out promising later). Rather than using a fixed proportion, non-stationary multi-armed bandit methods in the field of machine learning have proven that principles such as exploring actions that have not been tested for a long time can lead to performance closer to optimal — bounded regret. In parallel, researches in active exploration in the fields of robot learning and computational neuroscience of learning and decision-making have proposed alternative solutions such as transiently increasing exploration in response to drops in average performance, or attributing exploration bonuses specifically to actions associated with high uncertainty in order to gain information when choosing them. In this work, we compare different methods from machine learning, computational neuroscience and robot learning on a set of non-stationary stochastic multi-armed bandit tasks: abrupt shifts; best bandit becomes worst one and vice versa; multiple shifting frequencies. We find that different methods are appropriate in different scenarios. We propose a new hybrid method combining bio-inspired meta-learning, kalman filter and exploration bonuses and show that it outperforms other methods in these scenarios.","PeriodicalId":131825,"journal":{"name":"2017 Intelligent Systems Conference (IntelliSys)","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":"114221594","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}