Journal of Robotics, Networking and Artificial Life
Volume 2, Issue 2, September 2015
Chao Yang, Yingmin Jia
Pages: 69 - 72
In this paper, an adaptive multiple-model controller is developed for nonlinear systems in parametric-strict-feedback form. Unlike the previous results, a switching scheme is not required here to switch the most appropriate model into the controller design. The new scheme reduces the number of identification...
Wirarama Wedashwara, Shingo Mabu, Masanao Obayashi, Takashi Kuremoto
Pages: 73 - 78
This research proposes a decision support system of database cluster optimization using genetic network programming (GNP) with on-line rule based clustering. GNP optimizes cluster quality by reanalyzing weak points of each cluster and maintaining rules stored in each cluster. The maintenance of rules...
3. Facial Expression Recognition Using Thermal Image Processing and Efficient Preparation of Training-data
Yuu Nakanishi, Yasunari Yoshitomi, Taro Asada, Masayoshi Tabuse
Pages: 79 - 84
Using our previously developed system, we investigated the influence of training data on the facial expression accuracy using the training data of “taro” for the intentional facial expressions of “angry,” “sad,” and “surprised,” and the training data of respective pronunciation for the intentional facial...
Yuanyuan Shang, Yue Meng
Pages: 85 - 88
Image dehazing utilizes a very complex algorithm that requires intensive filtering and floating-point arithmetic operations. Consequently, processing speed is the most significant bottleneck in its application in some vision tasks such as mobile platforms. In this paper, we propose an optimized single...
Mochamad Chandra Saputra, Tetsuro Katayama
Pages: 89 - 93
The visualization of statement coverage (C0) and branch coverage (C1) measurement output can be used in several ways to improve the verification and validation process. The result displays are percentage of a successful tested code and visual information with highlighted in bright green as information...
6. Deep Feedback GMDH-Type Neural Network Using Principal Component-Regression Analysis and Its Application to Medical Image Recognition of Abdominal Multi-Organs
Tadashi Kondo, Junji Ueno, Shoichiro Takao
Pages: 94 - 99
The deep feedback Group Method of Data Handling (GMDH)-type neural network is proposed and applied to the medical image recognition of abdominal organs such as the liver and spleen. In this algorithm, the principal component-regression analysis is used for the learning calculation of the neural network,...
Jiwu Wang, Huazhe Dou, Shunkai Zheng, Masanori Sugisaka
Pages: 100 - 102
In order to improve the applications for an industrial sorting robot, it is necessary to increase its flexibility and control accuracy. Here an industrial robot arm is designed and set up for experiment simulation with machine vision. Some target recognition experiments are designed for vision recognition....
Taiki Taniguchi, Yasunari Yoshitomi
Pages: 103 - 106
There has been an increase in the number of images on the Internet that contain private information and/or the URL of an illegal Web site. This information could result in a violation of human rights and/or a crime. We present a method for extracting from an image the region(s) that contain characters....
9. On the Effects of Epigenetic Programming on the Efficiency of Incremental Evolution of the Simulated Khepera Robot
Yasuto Nishiwaki, Naoki Mukosaka, Ivan Tanev, Katsunori Shimohara
Pages: 107 - 110
We present the results of our work on epigenetic programming (EP) and its application to navigation of mobile cleaning robot. We verify the effect of genetic switches and the feasibility of incorporating histones. The results show individuals applying Lamarckian EP have better quality and evolve faster...
Taro Asada, Yasunari Yoshitomi, Ryota Kato, Masayoshi Tabuse, Jin Narumoto
Pages: 111 - 114
A video is analyzed by image processing and the feature parameters of facial expressions and movements, which are extracted in the mouth area. The feature parameter for expressing facial expressions is defined as the average of the facial expression intensity. The parameter for expressing movement of...
Kenji Aoki, Makoto Sakamoto, Hiroshi Furutani
Pages: 115 - 119
Haemophilia A is a genetic disease resulting from deficiency of factor VIII. The database of mutations causing haemophilia A has been developed by the world wide collaboration. In this study, we examined the relation between activity of factor VIII and the missense mutation by using machine learning....
Kentaro Aburada, Hisaaki Yamaba, Shinichiro Kubota, Tetsuro Katayama, Mirang Park, Naonobu Okazaki
Pages: 120 - 124
In ad hoc networks, due to the mobility of nodes, communication links are unstable and restricted. As such, an efficient routing protocol is needed in order to solve these problems. In the present paper, we propose a neighbors based routing (NBR) protocol by constructing paths in an area in which a large...
Takao Ito, Tsutomu Ito, Katsuhiko Takahashi, Makoto Sakamoto, Satoshi Ikeda, Rajiv Mehta
Pages: 125 - 130
This paper introduces recent fundamental modifications to the Japanese alliance system known as the keiretsu, and analyses how these changes have affected corporate performance. More specially, the performance of Japanese auto manufacturers, such as Toyota, Nissan and others, has significantly improved...
Yifei Du, QinLian Ma, Kenji Aoki, Makoto Sakamoto, Hiroshi Furutani, Yu-an Zhang
Pages: 131 - 134
Genetic algorithms (GAs) are stochastic optimization techniques, and we have studied the effects of stochastic fluctuation in the process of GA evolution. A mathematical study was carried out for GA on OneMax function within the framework of Markov chain model. We treated the task of estimating convergence...
Tetsuro Katayama, Yuuki Kikkawa, Yoshihiro Kita, Hisaaki Yamaba, Kentaro Aburada, Naonobu Okazaki
Pages: 135 - 139
This paper proposes a modification method of a source code to correspond with a modified model in MDA. The proposed method generates, translates, and modifies EAD (Extended Activity Diagram). Also, it generates a source code from the activity diagram. We use a simple ATM example to confirm availability...