Yao Minghai

An improved combination method of multiple classifiers based on fuzzy integrals

Combination of multiple classifiers is a powerful solution to difficult pattern recognition problems. Fuzzy integral is one of the many effective ways to combine classifiers, but how to calculate the fuzzy integral density with fuzzy integrals remains an unsolved problem. A combination method based on the fuzzy integral and Bayes method is presented to obtain the fuzzy integral density function, and then combines the output information of all classifiers with the fuzzy integral. Experiments show that this method achieves a very promising performance and outperforms other combining approaches.

Study and Transplant of Operating System for Wireless Sensor Network Node

This paper studies the embedded operating system TinyOS, including its event-driven mechanism, schedule strategy mechanics, power management mechanism, and etc. Then, the component-based architecture of TinyOS is analyzed. Based on these, the transplant scheme, the design principle of the layer of hardware description and the selection principle of processor are provided. Finally, this paper gives some conclusions and foresight.

Study and application of SQLite embedded database system based on Windows cE

The SQLite is an open source embedded database engine. For its advantages of small core, fast and high efficiency, stability and reliability, portability and so on, SQLite is widely applied in the data management of embedded environment, such as mobile phone, PDA, industrial control, etc. In this study, the features, architecture and development technology of SQLite are discussed. We proposed a detailed porting process for SQLite to Windows CE platform, and we also introduced an C++ unicode encapsulation for SQLite. In the end, we presented an application of SQLite in embedded system that is about the data recording system which based on ARM and Windows CE 5.0. The experiment shows that it is high performance embedded database and is suitable for embedded system.

An Incremental and Autonomous Visual Learning Algorithm Based on Internally Motivated Q Learning

The traditional machine learning paradigm is commonly used for intelligent robot design, which causes problems of low learning initiative, lack of adaptability with uncertainty and bad expansibility of knowledge and ability. According to the new research direction called cognitive development learning, an incremental and autonomous visual learning algorithm based on internally motivated Q learning is proposed. The visual novelty is calculated by online PCA. The active learning and accumulation of knowledge is implemented in the form of updating PCA subspace, which is guided by internally motivated Q learning. By equipped with the proposed algorithm, robot makes next learning decision by judging the novelty between learned knowledge and what is seen now. Experimental results show that the algorithm has the ability of autonomous exploring and learning, actively guiding robot to learning new knowledge, acquiring knowledge and developing intelligence in an online and incremental manner.

Design of physiotherapy monitor and control system based on embedded system

For the problems of present physiotherapy system, the paper presents a system framework of physiotherapy monitor and control system which using embedded system as hardware platform that based on high performance ARM processor AT91SAM9263, and Windows CE 5.0 as embedded operating system. Embedded Visual C++ 4.0 is used as software development environment for physiotherapy monitor and control system. Some techniques of Windows CE are employed, such as multi-threading technique, that is used for serial communication with physiotherapy controller and the message and event driven mechanism, that is used for real-time state display of physiotherapy controller. The system also has good scalability, supporting for remote authorization access and charging function and be able to meet different requirements of users.

Study on configurable computer-aided turbocharger assemble system to order

Assemble to order is a method to realize the idea of the customization. Under the analysis of the disadvantages of the traditional turbocharger assemble systems, this paper introduces a configurable computer-aided turbocharger assemble system to order. This system proposed uses Siemens S7-200 PLC as controller, and PC Access as OPC Server. Siemens S7-200 PLC can establish different types of turbocharger assemble process control module. PC Access can realize assemble software communication with PLC controller. The computer-aided software is designed under Visual Basic development environment and realizes seamless integration with enterprise management system. The application result indicates that the proposed system can improve the quality and efficiency of turbocharger assemble.

On Integrated System for Commercial Concrete Enterprise

Aiming to solve the prevalent problems such as the manufacture breaks away seriously from the management, resources not fully effective used, low production batching accuracy in the typical process industry commercial concrete enterprise. This paper presents a systematic approach to develop the QMS based on the three-layer Enterprise Resource Planning(ERP)/Manufacturing Executive System(MES)/Process Control System(PCS) architecture for the Concrete-Mixing station enterprise. Based on the deeply analysis of the production , control and the administration pattern of the current Commercial Concrete, We designed and realized the CIMS in commercial concrete industry, Followed by the detailed statements of the system intelligent,system Internet-based and the System Integrated.