{"title":"Unsupervised Image Classification Using Multi-Autoencoder and K-means++","authors":"S. Mabu, K. Kobayashi, M. Obayashi, T. Kuremoto","doi":"10.2991/jrnal.2018.5.1.17","DOIUrl":"https://doi.org/10.2991/jrnal.2018.5.1.17","url":null,"abstract":"Supervised learning algorithms such as deep neural networks have been actively applied to various problems. However, in image classification problem, for example, supervised learning needs a large number of data with correct labels. In fact, the cost of giving correct labels to the training data is large; therefore, this paper proposes an unsupervised image classification system with Multi-Autoencoder and K-means++ and evaluates its performance using benchmark image datasets.","PeriodicalId":157035,"journal":{"name":"J. Robotics Netw. Artif. Life","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116767157","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":"Improving EEG-based BCI Neural Networks for Mobile Robot Control by Bayesian Optimization","authors":"T. Hayakawa, Jun Kobayashi","doi":"10.2991/jrnal.2018.5.1.10","DOIUrl":"https://doi.org/10.2991/jrnal.2018.5.1.10","url":null,"abstract":"The aim of this study is to improve classification performance of neural networks as an EEG-based BCI for mobile robot control by means of hyperparameter optimization in training the neural networks. The hyperparameters were intuitively decided in our preceding study. It is expected that the classification performance will improve if you determine the hyperparameters in a more appropriate way. Therefore, the authors have applied Bayesian optimization to training the EEG-based BCI neural networks and achieved the performance improvement.","PeriodicalId":157035,"journal":{"name":"J. Robotics Netw. Artif. Life","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114832691","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":"Integrated Optimization of Differential Evolution with Grasshopper Optimization Algorithm","authors":"Duangjai Jitkongchuen, Udomlux Ampant","doi":"10.5954/ICAROB.2018.GS3-2","DOIUrl":"https://doi.org/10.5954/ICAROB.2018.GS3-2","url":null,"abstract":"This paper proposes a scheme to improve the differential evolution (DE) algorithm performance with integrated the grasshopper optimization algorithm (GOA). The grasshopper optimization algorithm mimics the behavior of grasshopper. The characteristic of grasshoppers is slow movement in the larval stage but sudden movement in the adulthood which seem as exploration and exploitation. The grasshopper optimization algorithm concept is added to DE to guide the search process for potential solutions. The efficiency of the DE/GOA is validated by testing on unimodal and multimodal benchmarks optimization problems. The results prove that the DE/GOA algorithm is competitive compared to the other meta-heuristic algorithms.","PeriodicalId":157035,"journal":{"name":"J. Robotics Netw. Artif. Life","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116643427","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":"Toward Artificial Intelligence by using DNA molecules","authors":"Yasuhiro Suzuki, R. Taniguchi","doi":"10.2991/jrnal.2018.5.2.12","DOIUrl":"https://doi.org/10.2991/jrnal.2018.5.2.12","url":null,"abstract":"Molecule Robotics have been realized by using bio molecules such as DNA, proteins, for example in Molecular Robotics Research Project [2012-17, JSPS]; bio molecules, such as DNA or proteins are highly structured and they already have a kind of “intelligence” and adapt to environment change. Hence, we have tried to extract their “ability” and induce Intelligence artificially. We have used well-known DNA reactions, Seesaw gate reaction and we found that DNA molecule can sense concentration of single strand input sequence or quasi-input (including mismatched base pairs and point mutations in the sequence) and chooses higher concentration one; this result shows DNA molecule (short DNA sequence) can adapt to its environment.","PeriodicalId":157035,"journal":{"name":"J. Robotics Netw. Artif. Life","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132800491","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 Haiku Generation from a Narrative","authors":"Takuya Ito, Takashi Ogata","doi":"10.2991/JRNAL.K.190531.005","DOIUrl":"https://doi.org/10.2991/JRNAL.K.190531.005","url":null,"abstract":"The primary goal of this study, which is related to the generation of narratives and haikus, is to create a mutual transformation mechanism between a narrative and a haiku [1]. Previously, the authors had developed an Integrated Narrative Generation System (INGS) [2], and the concept of mutual transformation is based on this background. INGS automatically generates narratives. This system produces a cyclical generation of stories or expressions. The authors have previously presented a method for generating a narrative from a haiku [3]. By analyzing the relationships between a haiku and the interpreted sentences of a haiku, these relationships can be used to obtain new interpreted sentences. We approach haiku generation from two aspects. One is a quantitative method, and the other is a method that uses the structure of a narrative.","PeriodicalId":157035,"journal":{"name":"J. Robotics Netw. Artif. Life","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134161437","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":"Design and Development of Three Arms Transmission Line Inspection Robot","authors":"M. F. A. Jalal, K. Sahari, HongMin Fei, J. Leong","doi":"10.5954/ICAROB.2018.GS9-11","DOIUrl":"https://doi.org/10.5954/ICAROB.2018.GS9-11","url":null,"abstract":"High-voltage transmission lines is one of the main elements in power distribution from the power plant or power station to the customer. However, the transmissions line is exposed to various environment conditions namely thermo-mechanical loading, mechanical tension, material degradation and material corrosion. The transmissions lines undergoing such circumstances eventually lead to many problems such as electrical breakdown or even major accident if transmissions lines were not being inspect, fixed and replaced in appropriate time [1].","PeriodicalId":157035,"journal":{"name":"J. Robotics Netw. Artif. Life","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116269797","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":"Technique of Recovery Process and Application of AI in Error Recovery Using Task Stratification and Error Classification","authors":"Akira Nakamura, K. Nagata, K. Harada, N. Yamanobe","doi":"10.2991/jrnal.2018.5.1.13","DOIUrl":"https://doi.org/10.2991/jrnal.2018.5.1.13","url":null,"abstract":"We have proposed an error recovery method using the concepts of task stratification and error classification. In this paper, the recovery process after the judgment of error is described in detail. In particular, we explain how to change the parameters of planning, modeling, and sensing when error recovery is performed. Furthermore, we apply artificial intelligence (AI) techniques, such as deep learning, to error recovery.","PeriodicalId":157035,"journal":{"name":"J. Robotics Netw. Artif. Life","volume":"57 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116313803","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}
F. Dai, Yuxing Ouyang, Runhua Mao, Ce Bian, Baochang Wei, Yiqiao Qin, Shengbiao Chang, Qijia Kang
{"title":"Development of NC Power Based on Buck Circuit","authors":"F. Dai, Yuxing Ouyang, Runhua Mao, Ce Bian, Baochang Wei, Yiqiao Qin, Shengbiao Chang, Qijia Kang","doi":"10.2991/jrnal.2018.4.4.15","DOIUrl":"https://doi.org/10.2991/jrnal.2018.4.4.15","url":null,"abstract":"This paper develops a kind of power-supply module that uses digital control and buck circuit. The module can convert 220V alternating current into 0-30V direct current. In the aspect of circuit design, it is mainly AC-DC, DC-DC conversion circuit and SCM minimum system circuit. In the aspect of control circuit, for feedback signal of current sensor, the power-supply module can obtain average value by multiple methods and remove the mutation value.","PeriodicalId":157035,"journal":{"name":"J. Robotics Netw. Artif. Life","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116506025","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. Khalid, W. S. Liew, Voong Bin Sheng, M. Helander
{"title":"Trust of Virtual Agent in Multi Actor Interactions","authors":"H. Khalid, W. S. Liew, Voong Bin Sheng, M. Helander","doi":"10.2991/jrnal.2018.4.4.8","DOIUrl":"https://doi.org/10.2991/jrnal.2018.4.4.8","url":null,"abstract":"Trust is crucial when integrating virtual agents in human teams. Our study investigated the combined use of psychological and physiological measures in predicting human trust of agents undertaking social tasks. The psychological measures comprised trust scores on ability, benevolence and integrity. The physiological measures included facial expressions, voice, heart rate and gestural postures. Subjects interacted with two avatars. A neurofuzzy algorithm extracted rules from the psychophysiological data to predict trust. Results revealed that trust can be predicted with 88% accuracy.","PeriodicalId":157035,"journal":{"name":"J. Robotics Netw. Artif. Life","volume":"2017 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134360535","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}