{"title":"Learning the optimal state-feedback using deep networks","authors":"Carlos Sánchez-Sánchez, D. Izzo, Daniel Hennes","doi":"10.1109/SSCI.2016.7850105","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850105","url":null,"abstract":"We investigate the use of deep artificial neural networks to approximate the optimal state-feedback control of continuous time, deterministic, non-linear systems. The networks are trained in a supervised manner using trajectories generated by solving the optimal control problem via the Hermite-Simpson transcription method. We find that deep networks are able to represent the optimal state-feedback with high accuracy and precision well outside the training area. We consider non-linear dynamical models under different cost functions that result in both smooth and discontinuous (bang-bang) optimal control solutions. In particular, we investigate the inverted pendulum swing-up and stabilization, a multicopter pin-point landing and a spacecraft free landing problem. Across all domains, we find that deep networks significantly outperform shallow networks in the ability to build an accurate functional representation of the optimal control. In the case of spacecraft and multicopter landing, deep networks are able to achieve safe landings consistently even when starting well outside of the training area.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122128539","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}
Dyego de Campos, E. A. C. Neto, R. Fernandes, I. Hauer, A. Richter
{"title":"Optimal tariff system for integration of distributed resources based on a comparison of Brazil's and Germany's system","authors":"Dyego de Campos, E. A. C. Neto, R. Fernandes, I. Hauer, A. Richter","doi":"10.1109/SSCI.2016.7849854","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7849854","url":null,"abstract":"The energy trading in Brazil is conducted in two different environments: the Free Market (ACL) and the Regulated Market (ACR). In ACL, the free and specials consumers can freely negotiate their own energy. In contrast, the captive consumers belong to ACR, and do not have the option to choose their energy supplier. Germany also has a similar system, where the big consumers (industrial) can freely negotiate their energy and the small consumers (residential) must choose a provider and pay a fixed price for the energy, where prices vary very little from one provider to another. Recently in Brazil, it was created the white tariff providing conditions that stimulate some consumers to shift consumption from peak periods to those periods that the distribution network has idle capacity. Regarding distributed energy resources (DER), there are also some peculiarities between the two countries. The objective of this paper is to verify the impacts that German residential consumers and the distribution network would have with the implementation of an hourly tariff equivalent to the white tariff of Brazil. The tariff structure and energy market regulation from both countries are compared and several simulations considering real data from German consumers and tariffs are done.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124020257","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}
H. Masuta, T. Motoyoshi, K. Koyanagi, K. Sawai, T. Oshima
{"title":"Plane extraction using Point Cloud data for service robot","authors":"H. Masuta, T. Motoyoshi, K. Koyanagi, K. Sawai, T. Oshima","doi":"10.1109/SSCI.2016.7850239","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850239","url":null,"abstract":"This paper describes an plane extraction method using point cloud data to perceive an unknown object for a service robot. Recently, depth sensors are used to perceive 3D space for a robot. A depth sensor have been used to recognize unknown environment, such as surface reconstruction, model fitting and so on. Point Cloud Library is typical open source library to deal with 3D point cloud data. However, robot perception for grasping have limitations with high computational costs and low-accuracy for perceiving small objects. Therefore, we propose the PSO-based plane detection method with RG to reconstruct an object from a combination of detected planes. To verify accuracy and computational cost for the plane detection of unknown object, we show that the proposed method has higher accuracy and less computational cost for the proposed method.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124972035","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":"Automated classification for pathological prostate images using AdaBoost-based Ensemble Learning","authors":"Chao-Hui Huang, E. Kalaw","doi":"10.1109/SSCI.2016.7849887","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7849887","url":null,"abstract":"We present an AdaBoost-based Ensemble Learning for supporting automated Gleason grading of prostate adenocarcinoma (PRCA). The method is able to differentiate Gleason patterns 4–5 from patterns 1–3 as the patterns 4–5 are correlated to more aggressive disease while patterns 1–3 tend to reflect more favorable patient outcome. This method is based on various feature descriptors and classifiers for multiple color channels, including color channels of red, green and blue, as well as the optical intensity of hematoxylin and eosin stainings. The AdaBoost-based Ensemble Learning method integrates the color channels, feature descriptors and classifiers, and finally constructs a strong classifier. We tested our method on the histopathological images and the corresponding medical reports obtained from The Cancer Genome Atlas (TCGA) using 10-fold cross validation, the accuracy achieved 97.8%. As a result, this method can be used to support the diagnosis on prostate cancer.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"180 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128356118","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 incremental learning mechanism for human activity recognition","authors":"S. Ntalampiras, M. Roveri","doi":"10.1109/SSCI.2016.7850188","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850188","url":null,"abstract":"This paper proposes an incremental mechanism for the automatic recognition of physical activities performed by humans. The specific research field has become quite relevant as it may offer important information to areas such as ambient intelligence, pervasive computing, and assistive technologies. The works in the related literature so far assume the a-priori availability of the dictionary of activities to be recognised. This work is focused on relaxing that assumption by learning and recognizing the human activities in an incremental manner based on the acquired datastreams. To this end, we designed a learning mechanism based on hidden Markov models for recognising human activities among those of a dictionary. The major novelty of the proposed mechanism is its ability to detect the occurrence of new activities and update the dictionary accordingly. We conducted experiments on a publicly available dataset of six human activities, i.e. walking, walking upstairs, walking downstairs, sitting, standing, and laying, where the efficiency of the proposed algorithm is demonstrated.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128369742","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":"Dimension reduction in classification using particle swarm optimisation and statistical variable grouping information","authors":"Bing Xue, M. C. Lane, Ivy Liu, Mengjie Zhang","doi":"10.1109/SSCI.2016.7850126","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850126","url":null,"abstract":"Dimension reduction is a preprocessing step in many classification tasks, but reducing dimensionality and finding the optimal set of features or attributes are challenging because of the big search space and interactions between attributes. This paper proposes a new dimension reduction method by using a statistical variable grouping method that groups similar attributes into a group by considering interaction between attributes and using particle swarm optimisation as a search technique to adopt the discovered statistical grouping information to search optimal attribute subsets. Two types of approaches are developed, where the first aims to select one attribute from each group to reduce the dimensionality, and the second allows the selection of multiple attributes from one group to further improve the classification performance. Experiments on ten datasets of varying difficulties show that all the two approaches can successfully address dimension reduction tasks to decrease the number of attributes, and achieve the similar of better classification performance. The first approach selects a smaller number of attributes than the second approach while the second approach achieves better classification performance. The proposed new algorithms outperform other recent dimension reduction algorithms in terms of the classification performance, or further reduce the number of attributes while maintaining the classification performance.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128710969","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":"Estimating force mix lower bounds using a multi-objective evolutionary algorithm","authors":"Fred Ma, S. Wesolkowski","doi":"10.1109/SSCI.2016.7850071","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850071","url":null,"abstract":"Nations will always experience conflicting pressures to reduce both (i) the funding of militaries and (ii) the probability that they will not be able to respond to scenarios that may arise. We develop a multiobjective evolutionary algorithm (MOEA) to generate force mix options that trade-off between lower bounds for objective (i) versus objective (ii). A set of military assets or force mix is evaluated against multiple instances of the future, each composed of a mix of stochastically generated realistic scenarios based on historically derived parameters. Scenario success is evaluated by matching each occurrence with a course of action (CoA) whose force element (FE) demands can be met. The lower bound on (i) comes from the assumption that a nation has complete flexibility to engage in scenarios at times that minimize simultaneous demand on FEs. The results are compared with the results from Tyche, a discrete event Simulator, which provides an more realistic, though pessimistic, point estimate of objective (ii). Results confirm the expected relative behavior of both models.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128604100","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}
D. Kapsoulis, K. Tsiakas, V. Asouti, K. Giannakoglou
{"title":"The use of Kernel PCA in evolutionary optimization for computationally demanding engineering applications","authors":"D. Kapsoulis, K. Tsiakas, V. Asouti, K. Giannakoglou","doi":"10.1109/SSCI.2016.7850203","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850203","url":null,"abstract":"Two techniques to further enhance the efficiency of Evolutionary Algorithms (EAs), even those which have already been accelerated by implementing surrogate evaluation models or metamodels to overcome a great amount of costly evaluations, are presented. Both rely upon the use of a Kernel Principal Component Analysis (Kernel PCA or KPCA) of the design space, as this reflects upon the offspring population in each generation. The PCA determines a feature space where the evolution operators should preferably be applied. In addition, in Metamodel-Assisted EA (MAEAs), the PCA can reduce the number of sensory units of metamodels. Due to the latter, the metamodels yield better approximations to the objective function value. This paper extends previous work by the authors which was based on Linear PCA, used for the same purposes. In the present paper, the superiority of using the Kernel (rather than the Linear) PCA, especially in real-world applications, is demonstrated. The proposed methods are assessed in single- and two-objective mathematical optimization problems and, finally, showcased in aerodynamic shape optimization problems with computationally expensive evaluation software.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127186492","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}
A. M. Durán-Rosal, J. C. Fernández, Pedro Antonio Gutiérrez, C. Hervás‐Martínez
{"title":"Hybridization of neural network models for the prediction of Extreme Significant Wave Height segments","authors":"A. M. Durán-Rosal, J. C. Fernández, Pedro Antonio Gutiérrez, C. Hervás‐Martínez","doi":"10.1109/SSCI.2016.7850144","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850144","url":null,"abstract":"This work proposes a hybrid methodology for the detection and prediction of Extreme Significant Wave Height (ESWH) periods in oceans. In a first step, wave height time series is approximated by a labeled sequence of segments, which is obtained using a genetic algorithm in combination with a likelihood-based segmentation (GA+LS). Then, an artificial neural network classifier with hybrid basis functions is trained with a multiobjetive evolutionary algorithm (MOEA) in order to predict the occurrence of future ESWH segments based on past values. The methodology is applied to a buoy in the Gulf of Alaska and another one in Puerto Rico. The results show that the GA+LS is able to segment and group the ESWH values, and the neural network models, obtained by the MOEA, make good predictions maintaining a balance between global accuracy and minimum sensitivity for the detection of ESWH events. Moreover, hybrid neural networks are shown to lead to better results than pure models.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129989223","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 Fuzzy Analogy on incomplete software projects data","authors":"Ibtissam Abnane, A. Idri","doi":"10.1109/SSCI.2016.7849922","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7849922","url":null,"abstract":"Missing Data (MD) is a widespread problem that can affect the ability to use data to construct effective software development effort prediction systems. This paper investigates the use of missing data (MD) techniques with Fuzzy Analogy. More specifically, this study analyze the predictive performance of this analogy-based technique when using toleration, deletion or k-nearest neighbors (KNN) imputation techniques using the Pred(0.25) accuracy criterion and thereafter compares the results with the findings when using the Standardized Accuracy (SA) measure. A total of 756 experiments were conducted involving seven data sets, three MD techniques (toleration, deletion and KNN imputation), three missingness mechanisms (MCAR: missing completely at random, MAR: missing at random, NIM: non-ignorable missing), and MD percentages from 10 percent to 90 percent. The results of accuracy measured in terms of Pred(0.25) confirm the findings of a study which used the SA measure. Moreover, we found that SA and Pred(0.25) measure different aspects of technique performance. Hence, SA is not sufficient to conclude about the technique accuracy and it should be used with other metrics, especially Pred(0.25).","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130160192","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}