Journal of Robotics, Networking and Artificial Life
Volume 3, Issue 1, June 2016
Tong Wu, Weicun Zhang
Pages: 1 - 4
Undershoot phenomena caused by unstable zeros of non-minimum-phase (NMP) plant is difficult to deal with in active disturbance rejection control (ADRC). This paper proposes a new method to reduce undershoot by optimizing the controller parameters of discrete-time ADRC system. Simulation results are given...
Masao Kubo, Viet Chau Dan, Hiroshi Sato, Akira Namatame
Pages: 5 - 8
In this paper, a method to generate traffic safety maps automatically from a collection of GPS logs of a drivers' smartphone. So far methods that residents can update their traffic environment better by their opinion are required for. The proposed method which uses a collection of individual summary...
Taiki Nishime, Satoshi Endo, Koji Yamada, Naruaki Toma, Yuhei Akamine
Pages: 9 - 12
In this study, we carried out the facial expression recognition from facial expression dataset using Convolutional Neural Networks (CNN). In addition, we analyzed intermediate outputs of CNN. As a result, we have obtained a emotion recognition score of about 58%; two emotions (Happiness, Surprise) recognition...
Henrik Hautop Lund
Pages: 13 - 16
Decades of research into intelligent, playful technology and user-friendly man-machine interfaces has provided important insight into the creation of robotic systems and intelligent interactive systems which are much more user-friendly, safer and cheaper than what appeared possible merely a decade or...
Tadashi Kondo, Junji Ueno, Shoichiro Takao
Pages: 17 - 23
The deep Group Method of Data Handling (GMDH)-type neural network is applied to the medical image analysis of brain X-ray CT image. In this algorithm, the deep neural network architectures which have many hidden layers and fit the complexity of the nonlinear systems, are automatically organized using...
Tatsuyuki Iju, Satoshi Endo, Koji Yamada, Naruaki Toma, Yuhei Akamine
Pages: 24 - 27
The estimation methods for Twitter user’s attributes typically require a vast amount of labeled data. Therefore, an efficient way is to tag the unlabeled data and add it to the set. We applied the self-training SVM as a semi-supervised method for age estimation and introduced Plat scaling as the unlabeled...
Luigi Pagliarini, Henrik Hautop Lund
Pages: 28 - 32
We analyse the state of the art of hi-tech and robot based technologies in terms of Assistive Technology for all patients and, in particular, elderly people assistance and everyday activities aid. We focus on different aspects and characteristics of these tools, such as playfulness, invasiveness, learning-speed,...
8. Clinical Evaluation of UR-System 2 for Recovery of Motor Function of Plegic Upper Limb after Stroke
Hirofumi Tanabe, Masahiro Mitsukane, Norihiro Toya, Ryosuke Takeichi, Hitomi Hattori, Yoshifumi Morita, Yoshiaki Takagi, Norio Hasegawa
Pages: 33 - 36
We developed a new training system UR-System 2 for restoring motor function of the upper limb after stroke in patients with hemiplegia. And then, we conducted clinical evaluation of the therapeutic effect of training with the UR-System 2 in six patients. The UR-System uses Proprioceptive Neuromuscular...
Taro Asada, Yasunari Yoshitomi, Ryota Kato, Masayoshi Tabuse, Jin Narumoto
Pages: 37 - 40
We developed a method for analyzing the facial expressions of a person having a conversation on a videophone. This was implemented on a wireless local area network, consisting of two personal computers and a router; the subject and the operator are placed in front of each computer. The module contains...
Pages: 41 - 44
The concept of “Building Type Control” was employed to establish hierarchical design guidelines for the urban regeneration process. GIS was used to manage and map environmental database as visual reference tool. Existing building regulations and urban design policies were reviewed to set out limitation...
Shingo Mabu, Masanao Obayashi, Takashi Kuremoto
Pages: 45 - 49
As the exponential increase of data in the world, machine learning, pattern recognition, data mining etc. are attracting more attentions recently. Classification is one of the major research in pattern recognition and a large number of methods have been proposed such as decision trees, neural networks...
12. Self-identification of Mental State and Self-control through Indirect Biofeedback – Indirect Representation and Placebo Effect
Madoka Takahara, Jilin Huang, Ivan Tanev, Katsunori Shimohara
Pages: 50 - 54
This paper describes a possible new scheme for a user with mental health problems to identify his/her own mental state and control it. For that purpose, we propose an indirect biofeedback system which represents physiological information with color and shape, and enables the user to grasp his/her inner...
13. Automated Processing of Multiple-Brightness Peak Histogram Image Using Curvature and Variance Estimation
Yusuke Kawakami, Tetsuo Hattori, Yoshiro Imai, Yo Horikawa, Kazuaki Ando, R. P. C. Janaka Rajapakse
Pages: 55 - 60
Previously, we have illustrated that the Histogram Matching based on Gaussian Distribution (HMGD) is an effective automated image processing method for obtaining a better feeling impression image. However, the simple HMGD works only for the image whose histogram has just one peak. For the image whose...
Hidehiko Yamamoto, Takayoshi Yamada, Shizuka Tanaka
Pages: 61 - 64
According to the previous study of a decentralized autonomous FMS using a mind, it is found that the production outputs decreased because an agent sometimes lies. To solve this problem, we study an AGV’s lie. The study is that AGVs recognize the lie that each AGV sends. To do this, we propose to give...
Sho Yamauchi, Keiji Suzuki
Pages: 65 - 68
Robot is designed for achieving specific task. However, robot is able to do much more things than it is expected by its own hardware. In this paper, concept of conquest oriented robot is proposed to know its availability systemati-cally and autonomously. Algorithm of conquest oriented robot and its experimental...