Papers by Author: Wen Tsai Sung

Abstract: This paper improve the original particle swarm optimization (PSO) algorithm in the fixed inertia weight, this study analyzed the value of inertia weight factor in (PSO) algorithm, and proposed a non-linear weights with decreasing strategy to implement the Improvement PSO (IPSO) algorithm and estimate the weighted factor in the data fusion of multi-sensors network. This FLAG Programmable System On Chip (SoC) Developing System 1605A (FLAG-the PSoC-1605A) as an experimental platform, using various types of sensors, combined with ZigBee wireless sensor networks, the TCP / IP network and the GPRS / SMS long-range wireless network will sense the measured data analysis and evaluation, to create a more effective monitoring and observing regional environment to achieve a things and things, and automated exchange of information between persons and things, processing an intelligent network. Finally, the IPSO applied the IOT system in monitoring environment is better than other existing PSO method in computing precise and convergence rate for excellent fusion result.

Abstract: The thesis proposes to construct a small vertical axis wind turbine monitoring system by the wireless sensor measuring network. This paper uses a small vertical axis wind turbine to generate electricity, and then provide to the parking lot and street lights, but also practical to monitor the entire system. Our monitoring system is constructed by the module. This paper proposes the small vertical axis wind turbine with the blade structure can be adjusted the angle with mechanical means, which is the most important improvement. Monitoring system to monitor real-time status of the communication part of the ZigBee and Ethernet established in the remote monitoring platform and the establishment of an Access database. Our research will be expected to improve the efficiency of wind turbine power generation, increase the stability of the monitoring system and the overall cost of power generation to reduce the effect.

Abstract: Wireless Sensor Networks have recently been used for environmental monitoring and real time event detection because of their low implementation costs and distributed sensing and processing capabilities. Event detection is a critical issue in wireless sensor networks. Fire detection is used as an example in our event detection system. Algorithms are required to detect fire sensors and measure the environmental parameters (temperature, humidity, light intensity, and Carbon Monoxide) to determine if a fire is present or not. It is urgent to research fire detection techniques that are efficient, convenient and practical. Although there are several works on fire detection using WSNs, sufficient attention has rarely been paid to using fuzzy logic methods. We present a novel approach based on fuzzy logic for multi-sensors data fusion in a wireless sensor network system with a node-sink mobile network structure to detect fire. Through simulation results, it is shown that the proposed innovative fuzzy logic algorithm can improve the reliability and accuracy of sensed information and reduce the rate of false alarm.

Abstract: This paper mainly in combination with RFID to construct a set of power system equipment remote control, first on the tags reader received after the use of Visual Basic to determine the signal and transmits the signal via the RS232 cable to the control circuit 8051 to control the instrument power switch. The topic written in Visual Basic RFID, using features such as: personnel control systems, access control systems are derived from the time of access control systems, many instrument control systems, and use the records stored in the form of the function, the other circuit is transmit signals to Visual Basic 8051, then by 8051 to control the instrument power switch.

Abstract: Undertake the study of the topic home monitoring system, the wisdom of building the health care environment monitoring and automation control systems, sensor signal is transmitted through ZigBee wireless technology and NI data acquisition card to do transfer cable transmission technology. In addition, an infrared remote control technology for automation and control for air conditioning. Improvements in the system developed sensors were temperature, humidity, carbon monoxide, illumination, and sensor signal transmission through wireless technology and cable transmission technology, to the terminal for processing, record, query and other features, then the terminal through RS -232 assigned for IR control module control packets, and output through PPM IR code to the IR receiver, and thus control of indoor air conditioning.

Abstract: For factory automation, devices and machine make a lot of space has become crowded and full of workers makes the operation of the pipeline space is limited, the problem of accidents become more frequent as the frequency will gradually floating surface have to seriously. The combination of embedded systems based on ZigBee technology to enhance the quality of research objectives of industrial safety, in addition to the general control inherent in using the system outside the ZigBee wireless technology to a remote control. Industrial application platform measurements have the thickness of the degree of screening, vibration sensor, weight classification, current sensing, energy monitoring, load switching, temperature monitoring, and carbon dioxide concentration. From the existing literature found in this study combined with embedded ZigBee for industrial real-time measurement system is an innovative technology. In this study, in addition to the discussion platform, the data for statistical measurement and analysis are also discussed in detail, through wired and wireless synchronization of the system measurement and monitoring, will be able to reach a real-time and can improve the safety of plant safety monitoring.

Abstract: This system was composed of independently developed ECG Signal Acquisition Model, DAQ Signal Acquisition Card, and the LabVIEW Graphics System. Regarding the ECG Signal Acquisition Model, this system uses the TL082 Operational Amplifier to realize the amplification, and uses the Filter Circuits along with the ISO122 to isolate IC. Regarding the ECG oscillogram display and ECG Signal Acquisition, the LabVIEW Graphics System developed by the American company “National Instruments” (NI) was adopted. Also, the LabVIEW system and the DAQ signal acquisition card of the Data Acquisition Package developed by the NI Company was adopted as well.The DAQ signal acquisition card can engage in A/D, DI/O, number counting and time counting applications. At last, it can use the TCP/IP Protocol to send the ECG waveform data by the internet to the computers with remote surveillance monitors. The remote surveillance computers can be installed in the hospital. Professional doctors in the hospital can observe the patient’s ECG waveform data and statistics, and engage in the job of remote care.

Abstract: Artificial neural networks (ANNs) are one of the most recently explored advanced technologies which show promise in the factory monitoring area. This paper focuses on two particular network models, back-propagation network (BPN) and general regression neural network (GRNN). The prediction accuracy of these two models is evaluated using a practical application situation in a monitor factory. GRNN emerged as a variant of the artificial neural network. Its principal advantages are that it can quickly learn and rapidly converge to the optimal regression surface with large number of data sets. According the simulation results we can show that GRNN is an effective way to considerably improve the predictive ability of BPN.