{"title":"An improved K-means clustering algorithm for sleep stages classification","authors":"Shuyuan Xiao, Wang Bei, Zhang Jian, Qunfeng Zhang, Junzhong Zou, Masatoshi Nakamura","doi":"10.1109/SICE.2015.7285326","DOIUrl":"https://doi.org/10.1109/SICE.2015.7285326","url":null,"abstract":"Sleep stage scoring is used to evaluate one's overnight sleep process, which is important for clinical diagnosis. However, the visual inspection of sleep data is a laborious task and the scoring results may be subjective to different clinicians. The purpose of this paper is to develop an automatic sleep stage classification algorithm to reduce the artificial workload. The overnight sleep data are represented by the extracted features from time domain and frequency domain of EEG. An improved k-means clustering algorithm is proposed to classify overnight sleep data into five stages including awake (W), NREM (Non-Rapid Eye Movement) stage 1 (S1), NREM stage 2 (S2), slow-wave sleep (SS) and REM (Rapid Eye Movement). In the improved k-means clustering algorithm, the points with dense surrounding are selected as the original centers by using the concept of density for reference. Additionally, the cluster centers are updated according to ‘Three-Sigma Rule’ during the iteration. The determination of cluster center selection was developed which can be adaptive to the actual cases and abate the singular points effect. The obtained results showed that the accuracy of proposed algorithm was satisfied; especially it can distinguish W, SS and REM effectively. Furthermore, the improved k-means algorithm had less number of misclassification and higher accuracy than the original algorithm.","PeriodicalId":405766,"journal":{"name":"Annual Conference of the Society of Instrument and Control Engineers of Japan","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115173771","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":"Proposal of a neural controller able to compensate neurological time delay for stance postural control","authors":"Ping Jiang, R. Chiba, K. Takakusaki, J. Ota","doi":"10.1109/SICE.2015.7285391","DOIUrl":"https://doi.org/10.1109/SICE.2015.7285391","url":null,"abstract":"In order to understand insights into the postural control mechanism, realization of biped stance motion in consideration of both muscles and neurological time delay (NTD) is important. In this paper, we proposed a neural controller composed of feed-forward (FF) and feedback (FB) control to keep a musculoskeletal model with 70 muscles standing stably when NTD was 100ms. FF control is modelled as a set of constant activations necessary to keep musculoskele-tal model standing in objective posture. FB control is modelled as a PD control based on muscular-tendon length and lengtening velocity. Parameter tuning was conducted to search feed-forward controls and feedback gains of PD control to keep musculoskeletal model standing. As a result, we successfully found the suitable parameters to keep musculoskeletal model standing when NTD was 100ms. We found FF control contribute more to compensate disturbances caused by NTD.","PeriodicalId":405766,"journal":{"name":"Annual Conference of the Society of Instrument and Control Engineers of Japan","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124206724","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":"Wearable EEG-based human intention detection and its application in human care-robot systems","authors":"Shota Terada, Zhiwei Luo","doi":"10.1109/SICE.2015.7285441","DOIUrl":"https://doi.org/10.1109/SICE.2015.7285441","url":null,"abstract":"This research developed a wearable EEG-based brain robot interface (WE-BRI) which detects the human subject's intention using steady-state visual evoked potential (SSVEP) and is applied in the food care tasks of robots. In detail, five types of visual stimuli with different frequencies are displayed on the different locations of a PC monitor. The human subject can select his/her intended food by focusing on a related specific visual stimulus for several seconds. A wearable EEG sensor then measures the subject's EEG and followed by on line frequency analysis. From the frequency analysis, the robot can detect the human subject's intention within limited time and can perform the task to move the related food to the subject. In this research, 5 health subjects are tested using this WE-BRI. It is found that in order to increase the success rate of intention detection, the subject should focus on a specific visual stimulus for more than 4 seconds. The highest success rate of the detection can reach to 92%. The developed WE-BRI is also expected to be applied in wider range of robotic human care tasks.","PeriodicalId":405766,"journal":{"name":"Annual Conference of the Society of Instrument and Control Engineers of Japan","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124947388","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":"Contouring control of multi-axis machine tools with iterative learning control","authors":"Shyh‐Leh Chen, Yu-chi Chang","doi":"10.1109/SICE.2015.7285423","DOIUrl":"https://doi.org/10.1109/SICE.2015.7285423","url":null,"abstract":"The accuracy of machine tools can be improved through using the learning control algorithm which can provide a better input command toward the closed-loop system. Due to the complexity of actual contour error model, the equivalent contour error is introduced. In this study, the target of the learning control is to reduce the equivalent contour error which the actual contour error will also be reduced. The iterative learning control algorithms were verified through the experiments which were done on x-y axis system of five-axis milling machine and controlled by PC-based controller. The results from the experiments show that the actual contour error can be reduced by 80% within five times of learning.","PeriodicalId":405766,"journal":{"name":"Annual Conference of the Society of Instrument and Control Engineers of Japan","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130806853","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":"Inertia compensasion control of engine test bench","authors":"T. Akiyama, Y. Sawada","doi":"10.1109/SICE.2015.7285581","DOIUrl":"https://doi.org/10.1109/SICE.2015.7285581","url":null,"abstract":"An engine test bench is utiliezed to execute a performance test, durability test and etc. of a vehicle engine. In these tests, there is a process that the engine must become an idling state. Figure 1 shows a typical mechanical configuration of the engine test bench. To make the engine an idling state, a dynamometer must be controlled so that the engine becomes no-load state. Only by controlling a measured value of a torque meter (shaft torque) to 0Nm, the engine carries shaft inertia. So, to make the engine no-load state, it is necessary to compensate the inertia of the coupling shaft by dynamometer control.","PeriodicalId":405766,"journal":{"name":"Annual Conference of the Society of Instrument and Control Engineers of Japan","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133935283","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":"Self-identification of mentality and self-control through indirect biofeedback","authors":"M. Takahara, I. Tanev, K. Shimohara","doi":"10.1109/SICE.2015.7285373","DOIUrl":"https://doi.org/10.1109/SICE.2015.7285373","url":null,"abstract":"This paper describes a possibility of a new scheme for a user with mental health problems so that the user can identify his/her own mentality and self-control it by proactively confronting his/her symptoms, different from the usual passive role of visiting specialists. For that purpose, the scheme should provide the user with functions not only to externalize and objectify the user's mental state but also for the user itself to self-control the mental state. Here, we propose an indirect biofeedback system which represents a user's mental state with color and shape, and which enables the user to grasp his/her mental state and to proactively change and control it through methods of breathing.","PeriodicalId":405766,"journal":{"name":"Annual Conference of the Society of Instrument and Control Engineers of Japan","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130121921","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":"Robust path tracking control using model predictive control and sliding mode control — Application to the JSAE-SICE benchmark problem","authors":"Takatsugu Oda, K. Nonaka, K. Sekiguchi","doi":"10.1109/SICE.2015.7285448","DOIUrl":"https://doi.org/10.1109/SICE.2015.7285448","url":null,"abstract":"In this paper, we cope with the JSAE-SICE benchmark study which demands recovering disadvantage of micro electric vehicles. To enhance the stability of micro cars, we apply the robust path tracking control combining Model Predictive Control and Sliding Mode Control. In this controller, the friction circles are considered using the approximated tire force usage rate to balance the path following performance and the robustness. The enhancement of the vehicle stability using the robust path tracking controller through the numerical simulations is shown. The controller are applied to the all scenarios of the JSAE-SICE benchmark study.","PeriodicalId":405766,"journal":{"name":"Annual Conference of the Society of Instrument and Control Engineers of Japan","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133446829","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":"Evaluation of Oxide Dispersion Strengthened Palladium for Platinum/Palladium thermocouples","authors":"T. Shinohara, Junpei Koyama, T. Kodama, T. Hamada","doi":"10.1109/SICE.2015.7285299","DOIUrl":"https://doi.org/10.1109/SICE.2015.7285299","url":null,"abstract":"Type R and S thermocouples are widely used not only for industrial temperature measurement but also for temperature standards. These types of thermocouples contain rhodium in the positive branch, so it is commonly known that oxidation occurs during high temperature operation and causes thermal electromotive force (E.M.F.) drift. In these days, Platinum/Palladium(Pt/Pd) thermocouple is occasionally substituted for type R and S because those are made of pure metals only and show more stability of thermal E.M.F. However, metal grain growth occurs on pure metals at high temperature operation, and creep rupture occurs even with relatively lower stress. Especially, the melting point of palladium is lower than that of platinum, thus palladium has a tendency to creep easily at high temperature rather than platinum. We applied the Oxide Dispersion Strengthened (O.D.S.) technique on palladium in the negative branch of Pt/Pd thermocouples for further product improvements.","PeriodicalId":405766,"journal":{"name":"Annual Conference of the Society of Instrument and Control Engineers of Japan","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124478065","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":"Prototyping of ultrasonic crank angle sensor and its application to torque estimation","authors":"T. Mogi, S. Oho, T. Aono","doi":"10.1109/SICE.2015.7285585","DOIUrl":"https://doi.org/10.1109/SICE.2015.7285585","url":null,"abstract":"Torque information is valuable for automotive engine control and diagnosis, and there is a growing demand for on-line torque sensors. In this research, we propose an ultrasonic crank angle sensor and its application to simultaneous measurement of engine rotation speed and output torque.","PeriodicalId":405766,"journal":{"name":"Annual Conference of the Society of Instrument and Control Engineers of Japan","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115616120","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":"Model of important user determination in OSN by genetic programming","authors":"Chi Pong Chan, I. Tanev, K. Shimohara","doi":"10.1109/SICE.2015.7285344","DOIUrl":"https://doi.org/10.1109/SICE.2015.7285344","url":null,"abstract":"Online social network (OSN) has become a popular platform of information sharing and communication in the past decade. Regarding the trend, identification of influential spreaders or important users inside OSN is a common approach of improving the message diffusion efficiency. In this research, the objective is to develop a model of simulating the determination of influential spreaders with respect to a special user in OSN. The model would be a multi agent system. It consists of an environment which demonstrates an OSN and each agent inside the model represents a user in OSN. In order to simulate the identification of important users, understanding the way that OSN users estimate important users is essential because the determination task in the model has to been simulate with this strategy. A trial experiment was performed for investigating the possibility for using genetic programming to obtain the strategy of determining important users in OSN. The result shows that the strategy can be achieved by genetic programming and the research can be continued with further extensions.","PeriodicalId":405766,"journal":{"name":"Annual Conference of the Society of Instrument and Control Engineers of Japan","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115701487","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}