2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)最新文献

{"title":"Evolving time-series based prediction models for quality criteria in a multi-stage production process","authors":"E. Lughofer, R. Pollak, Pauline Meyer-Heye, Helmut Zörrer, C. Eitzinger, J. Lehner, Thomas Radauer, Mahardhika Pratama","doi":"10.1109/EAIS.2018.8397186","DOIUrl":"https://doi.org/10.1109/EAIS.2018.8397186","url":null,"abstract":"We address the problem of predicting product quality for a latter stage in a production process already at an early stage. Thereby, the idea is to use time-series of process values, recorded during the on-line production process of the early stage and containing possible system dynamics and variations according to parameter settings or different environmental conditions, as input to predict the final quality criteria in the latter stage. We apply a non-linear partial least squares (PLS) variant for reducing the high input dimensionality of time-series batch-process problems, by combining PLS with generalized Takagi-Sugeno fuzzy systems, a new extended variant of classical TS fuzzy system (thus termed as PLS-Fuzzy). This combination opens the possibility to resolve non-linearities in the PLS score space without requiring extra pre-tuning parameters (as is the case in other non-linear PLS variants). The models are trained by an evolving and iterative vector quantization approach to find the optimal number of rules and their ideal positioning and shape, combined with a fuzzily weighted version of elastic net regu-larization for robust estimation of the consequent parameters. The adaptation algorithm of the models (termed as IPLS-GEFS) includes an on-the-fly evolving rule learning concept (GEFS), a forgetting strategy with dynamically varying forgetting factor in case of drifts (to increase flexibility by outweighing older samples) as well as a new variant for an incremental single-pass update of the latent variable space (IPLS). The latter can be seen as a new variant for incremental dimension reduction and subspace update and is necessary when the covariance characteristics between input and output changes. Results on a real-world data set from microfluidic chip production show a comparable performance of PLS-Fuzzy with random forests, extreme learning machines and deep learning with MLP neural networks, achieving low prediction errors (below 10%) with low model complexity. Updating the models with new on-line data — only achievable with our method, as the others are batch off-line methods (with mostly slow re-training phases) — decreased the model errors, at most when including incremental latent variable space update.","PeriodicalId":368737,"journal":{"name":"2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132060476","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":"Swarm communication by evolutionary algorithms","authors":"N. Vaughan","doi":"10.1109/EAIS.2018.8397189","DOIUrl":"https://doi.org/10.1109/EAIS.2018.8397189","url":null,"abstract":"This research has applied evolutionary algorithms to evolve swarm communication. Controllers were evolved for colonies of artificial simulated ants during a food foriaging task which communicate using pheromone. Neuroevolution enables both weights and the topology of the artificial neural networks to be optimized for food foriaging. The developed model results in evolution of ants which communicate using pheromone trails. The ants successfully collect and return food to the nest. The controller has evolved to adjust the strength of pheromone which provides a signal to guide the direction of other ants in the colony by hill climbing strategy. A single ANN controller for ant direction successfully evolved which exhibits many separate skills including food search, pheromone following, food collection and retrieval to the nest.","PeriodicalId":368737,"journal":{"name":"2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129371233","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-objective optimization of charging infrastructure to improve suitability of commercial drivers for electric vehicles using real travel data","authors":"Timo Krallmann, M. Döring, Marek Stess, Timo Graen, Michael Nolting","doi":"10.1109/EAIS.2018.8397185","DOIUrl":"https://doi.org/10.1109/EAIS.2018.8397185","url":null,"abstract":"Electric mobility has gained much interest in the automotive industry and with commercial customers. A well-developed charging infrastructure is necessary to meet the rising customer demand for electricity. The aim of this paper is to evaluate how the suitability of commercial customers for the conversion to electric vehicles (EVs) is improved by the expansion of new charging stations. Here, the impact of an expanded charging infrastructure is measured by a multi-objective genetic algorithm. The location and type of charging stations is optimized with respect to the number of failed trips, due to empty batteries, and the total cost of infrastructure. Travel data from commercial vehicle fleets is approximated to EVs and discloses a pareto front to support decision makers in placing optimal public charging stations.","PeriodicalId":368737,"journal":{"name":"2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122828928","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":"Predicting changes in quality of life for patients in vocational rehabilitation","authors":"Saemundur O. Haraldsson, Ragnheidur D. Brynjolfsdottir, V. Gudnason, K. Tomasson, K. Siggeirsdottir","doi":"10.1109/EAIS.2018.8397182","DOIUrl":"https://doi.org/10.1109/EAIS.2018.8397182","url":null,"abstract":"Adaptive systems will become increasingly important for health care in coming years as costs and workload grow. The need for efficient rehabilitation will expand which will be fulfilled by information technologies. This paper presents a novel implementation and application of a dynamic prediction software in vocational rehabilitation. The software is made adaptable with a Genetic Improvement of software methodology and utilised to predict fluctuations in patient's perceived quality of life. Results of accuracy, recall and precision were better than 90% for the classification of the shifts and the mean absolute error in predictions of the quantity of the shifts was low. The findings of the present study support that it is possible to predict fluctuations in quality of life on average based on the status six months prior. Professionals could therefore intervene accordingly and increase the possibility of successful rehabilitation. The significant long term effect on health care from applying the prediction tool might be reduced cost and overall improved quality of life.","PeriodicalId":368737,"journal":{"name":"2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131217118","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 adaptable deep learning system for optical character verification in retail food packaging","authors":"Fabio De Sousa Ribeiro, Francesco Calivá, M. Swainson, Kjartan Gudmundsson, G. Leontidis, S. Kollias","doi":"10.1109/EAIS.2018.8397178","DOIUrl":"https://doi.org/10.1109/EAIS.2018.8397178","url":null,"abstract":"Retail food packages contain various types of information such as food name, ingredients list and use by dates. Such information is critical to ensure proper distribution of products to the market and eliminate health risks due to erroneous mislabelling. The latter is considerably detrimental to both consumers and suppliers alike. In this paper, an adaptable deep learning based system is proposed and tested across various possible scenarios: a) for the identification of blurry images and/or missing information from food packaging photos. These were captured during the validation process in supply chains; b) for deep neural network adaptation. This was achieved through a novel methodology that utilises facets of the same convolutional neural network architecture. Latent variables were extracted from different datasets and used as input into a Λ-means clustering and Λ-nearest neighbour classification algorithm, to compute a new set of centroids which better adapts to the target dataset's distribution. Furthermore, visualisation and analysis of network adaptation provides insight into how higher accuracy was achieved when compared to the original deep neural network. The proposed system performed very well in the conducted experiments, showing that it can be deployed in real-world supply chains, for automating the verification process, cutting down costs and eliminating errors that could prove risky for public health.","PeriodicalId":368737,"journal":{"name":"2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)","volume":"14 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124190341","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":"Embedded vision system with hardware acceleration","authors":"O. Elgawi, A. Mutawa","doi":"10.1109/EAIS.2018.8397187","DOIUrl":"https://doi.org/10.1109/EAIS.2018.8397187","url":null,"abstract":"This paper presents an efficient architecture of low power embedded vision system based on dynamically pro-grammable logic acceleration. This approach is based on param-eterised architecture designed for a machine supervised learning classifier. We test and verified the model functionality by experiments on benchmark datasets including case study on object recognition. Evaluation shows that the proposed architecture gained speedups and high performance.","PeriodicalId":368737,"journal":{"name":"2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126262796","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":"Uninorm based regularized fuzzy neural networks","authors":"P. V. C. Souza, G. R. L. Silva, L. Torres","doi":"10.1109/EAIS.2018.8397176","DOIUrl":"https://doi.org/10.1109/EAIS.2018.8397176","url":null,"abstract":"This paper proposes a training algorithm for fuzzy neural networks that can generate consistent and accurate models while adding some level of interpretation to applied problems. Learning is achieved through extreme learning machine concepts, allowing the adjustment of parameters during the training phase using a fast and straightforward approach. The use of the regularization in the inner layers of the model will enable it to be more precise and selfish since a reduced set of fuzzy rules can be extracted from the final result of the network. The proposed approach was evaluated through pattern classification problems using real datasets of large and small sizes. The achieved results were compared to the results obtained using another state of the art classifiers. Statistical analysis of the results suggests the proposed approach as a promising alternative to performing classification with some level of model interpretability.","PeriodicalId":368737,"journal":{"name":"2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126860081","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":"Incremental adaptive semi-supervised fuzzy clustering for data stream classification","authors":"Gabriella Casalino, G. Castellano, Corrado Mencar","doi":"10.1109/EAIS.2018.8397172","DOIUrl":"https://doi.org/10.1109/EAIS.2018.8397172","url":null,"abstract":"Data stream mining refers to methods able to mine continuously arriving and evolving data sequences or even large scale static databases. Most of data stream classification methods are supervised, hence they require labeled samples that are more difficult and expensive to obtain than unlabeled ones. Semi-supervised learning algorithms can solve this problem by using unlabeled samples together with a few labeled ones to build classification models. Recently we introduced a method for data stream classification based on an incremental semi-supervised fuzzy clustering algorithm. This method processes data belonging to different classes assuming that they are available during time as chunks. It creates a fixed number of clusters that is set equal to the number of classes. In real-world contexts a fixed number of clusters may not capture adequately the evolving structure of streaming data. To overcome this limitation in this work we extend our method by introducing a dynamic component that is able to adapt dynamically the number of clusters. Preliminary experimental results on a real-world benchmark dataset show the effectiveness of the dynamic mechanism introduced in the method.","PeriodicalId":368737,"journal":{"name":"2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122032521","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":"Initial study on evolving state space neural networks (eSSNN)","authors":"G. Černe, I. Škrjanc","doi":"10.1109/EAIS.2018.8397188","DOIUrl":"https://doi.org/10.1109/EAIS.2018.8397188","url":null,"abstract":"This paper presents initial research on the novel neural network evolution algorithm for modelling dynamic systems called evolving state space neural network (eSSNN) algorithm. It also introduces a state space neural network (SSNN) for modelling non-linear dynamic systems using neural network, derived from state space representation. The evolution is done by inserting influence signal polynomial to the evolution edge in the SSNN in order to reduce state estimation error. The inserting is done automatically, where every combination of influence signal and potential evolution edge are tested in order to find the combination with largest error reduction. SSNN Model was created for 3 synthetic systems, where model simulations showed promising results for further research, including control design based on SSNN.","PeriodicalId":368737,"journal":{"name":"2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)","volume":"100 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123892865","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":"EDUC8: Self-evolving and personalized learning pathways utilizing semantics","authors":"Omiros Iatrellis, A. Kameas, P. Fitsilis","doi":"10.1109/EAIS.2018.8397179","DOIUrl":"https://doi.org/10.1109/EAIS.2018.8397179","url":null,"abstract":"During the last decade, educational institutions are implementing reforms geared towards improving student outcomes and quality of studies. Personalization of education services is one of the challenges to be confronted. However, personalization requires continuous reconfiguration of the learning schemes since the academic status of each student, program studies and circumstances inside an educational institution constantly change. In this paper, we present EDUC8 (EDUCATE) prototype that provides an information technology solution concerning the dynamic recommendation and execution of personalized education processes. The EDUC8 prototype comprises an educational process execution engine based on a semantic infrastructure for reconfiguring the learning pathways for each student. The semantic infrastructure consists of an ontological framework enclosing the required knowledge and a semantic rule-set. During the execution of learning pathways, the system reasons over the rules and reconfigures the next steps of the learning process. The rule-base is able to create new facts and update the EDUC8 ontology accordingly, thus creating new knowledge as each learning pathway evolves.","PeriodicalId":368737,"journal":{"name":"2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132934466","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}