|
Automatic Calibration of Bed-Leaving Sensor Signals Based on Genetic Evolutionary Learning |
|
Daiju Hiramatsu, Hirokazu Madokoro, Kazuhito Sato(Akita Prefectural University, Japan), Kazuhisa Nakasho(Yamaguchi University, Japan), Nobuhiro Shimoi(Akita Prefectural University, Japan) |
| This paper presents a method to generate filters for shaping sensor signals using genetic network programming (GNP) for automatic calibration to absorb individual differences. In our previous study, we developed a prototype that incorporates bed-leaving detection sensors using piezoelectric films and a machine-learning-based behavior recognition method using counter-propagation networks (CPNs). For the preliminary experiment, we optimized the original sensor signals to approximate high-accuracy ideal sensor signals using generated filters. |
|
|
Automatic Building and Floor Classification using Two Consecutive Multi-layer Perceptron |
|
Jaehoon Cha, Sanghyuk Lee, Kyeongsoo Kim(Xian Jiaotong Liverpool University, China) |
| Key issues of indoor localization is taking full advantages and overcoming its disadvantages. Indoor localization
based on Wi-Fi fingerprinting attracts researchers’ attentions since it does not require new infrastructure and devices.
Many devices such as smart phones and laptops, which have a function to capture Wi-Fi signals, can be used for Wi-Fi
fingerprinting. However, due to unreliable Wi-Fi signals, there are still difficulty to achieve high positioning accuracy.
The unreliable signal disturbs devices to find their locations. As a result, getting localization with devices sometimes
make |
|
|
Research on stock trading strategy based on deep neural network |
|
Yilin Ma, Ruizhu Han(Southeast University, China) |
| This paper studies 7 trading strategies based on a deep neural network, and uses the 2009-2015 years historical data of Shanghai Composite Index for experiments through sliding window approach, and adopts the accuracy, rate of excess return, volatility of yield and information ratio to measure the advantages and disadvantages of different trading strategies. According to the experimental results, a trading strategy suitable for the deep neural network is found. This trading strategy can not only achieve a high predictive accuracy but also have a low volatility. |
|
|
Synchronization for complex networks with interval delay via Finsler’s Lemma |
|
Dawei Gong, Anxu Li(University of Electronic Science and Technology of China, China) |
| By using an new inequality from Newton-Leibniz formula, and introducing Finsler's Lemma, a new synchronization analysis method is obtained. Different from existing results, Finsler's Lemma with variable subintervals are firstly used to introduce more free weighting matrices in synchronization criteria.
Finally, numerical example proved the proposed result. |
|
|
The development of a web application for the automatic analysis of the tonality of texts based on machine learning methods |
|
Gulnara Bektemyssova, Zhuanyshev Orazgaliyevic Ilyas(International Information Technologies University, Kazakhstan), Gulnara Zakirova(International Information Technolodgy University, Kazakhstan) |
| The work is devoted to the study of the existing methods of analyzing the sentimentality of the text, development and realization of web application for determining the key of the text in commentaries and paragraphs in social networks. Experiment is based on data sets from the social media portals like «Tengrinews», «Nur.kz» and «Zakon.kz», which analyzes the tone of message entered by user. We developed a software to determine the tone of text data, according to the problem of the system for analyzing the emotional coloring of messages. |
| |