Applied Mechanics and Materials Vols. 556-562

Abstract: In order to solve the problem that traditional intelligent surveillance is easily influenced by blocking and the capture views is limited, this paper presents a new method with 3 Kinects. Kinects are used to capture the human skeleton data and extract motion features. Principle component of raw data is extracted by using improved KPCA. Classifier is generated by using spatial-temporal Hidden Markov Model. A set of specific motions is analyzed in monitoring area. Experimental results show that this method can efficiently solve the problems that blocking and skeleton data is incomplete. It can also improve the recognition accuracy. The improved KPCA can improve the cumulative contribution rate and reduce the motion recognition time.

Abstract: This paper proposes a novel non-contact single point ranging method in which the laser light source is replaced by the white light in the projector. It will project the blank points on the standard plate. With the videos by CCD camera, the advanced image processing technology will be applied to correct the image accuracy and remove the exterior interference to finish the ranging optimization. The experiment results illustrate the method is accessible and the measurement errors are acceptable.

Abstract: The reliability detection method for the traditional large-scale automation software is based on the module design principle of the automation software which detects the reliability features one by one. It does not consider the concurrent reliable chain problems for the automation software which cause the low detection accuracy. The paper proposes a novel automation software system reliability detection method based on the path-based interfaces. The detection model integrates the features of the automation software. The established stochastic points process and state probability transition diagram overcome the shortcomings of the traditional large-scale automation software reliability detection methods. The experiment results illustrate the improved methods can increase the detection accuracy of the large-scale automation software which can be widely applied.

Abstract: Traditional single-packet inspection can only detect isolated intrusion. To detect intrusion of network feed-forward and multi-packet collaboration, a lot of prior knowledge or historical knowledge is required. There are many drawbacks of the traditional methods, such as low detection rates and high missing rate. The paper proposes a detection model considering classification intrusion identification, which builds the detection model by analyzing the intrusion feature. The experiment results show that the proposed method effectively solves the problems of intrusion of network feed-forward and multi-packet, and reduces missing rate, of which the detection speed and accuracy are much higher compared to traditional methods.

Abstract: Objective: Based on the problem of aging population, increasing heart disease prevalence and the difficulty of seeing a doctor in hospital, the paper studies on the long-term continuous changes of heart sounds to implement real-time monitoring and remote diagnosis at home. Method: by use of wireless sensor technology, signal processing technology and network transmission technology, the paper designs a remote heart sound detection and analysis system based on internet of things. Results: this method can detect the heart sound, transmit the data and diagnose remotely on real-time. Conclusion: according to the patient information and heart rhythm index storage of hospital database, doctors can make the medical scheme in time to prevent and treat, which has a wide commercialization prospect.

Abstract: The gas alarms based on sensors are widely used, but there are still some limitations. By design a gas real time monitoring system, the gas alarms within a certain range transport collected data to a remote computer via wired or wireless method. Remote computer can monitoring the gas environment by receiving and monitoring alarms’ collected data. In order to ensure system’s reliability, transmission mechanism based on handshake is used. Data compression technology also included to reduce the storage space required by data store.

Abstract: With the rapid development of motion capture technology, large motion capture databases are established. How to effectively retrieve the motions from huge amounts of motion data has become a hot topic in computer animation. In this paper, we give a survey on current motion capture data retrieval methods and point out some still existing problems at the end.

Abstract: As the purpose of environmental protection, NO_x sensor is driven to develop. It is built to detect the concentration of nitrogen oxides in the exhaust emissions of motor vehicles. During the development of sensor, the automatic test for the sensor ́s output message is a significant procedure. This article is aimed to design a user friendly test tool based on LabVIEW for real time testing, evaluating and error detecting of sensor data transmitted via CAN bus. Controller area network (CAN) is one of the most widely and frequently used communication protocols in automotive applications. LabVIEW (Laboratory Virtual Instrument Engineering Workbench) is a system-design platform and development environment for a visual programming language from National Instruments. NI Company provides flexible and diverse CAN bus interface hardware and software drivers which is useful and necessary for building an automatic test system. It contains the features of configuration, displaying and decoding CAN data frames, checking CAN bus errors, testing and evaluating decoded messages, report generation, signal setting and validation.

Abstract: Aiming to solve the difficulty of recognize corrosion types for complex CO₂ corrosion process with data, this paper presents a recognition method of CO₂ corrosion types using SVM as recognizer. Surface morphology images of N8 steel corroded by CO₂ are decomposed into sub-images by wavelet after gray processing and gray enhancement, and energy information of sub-images is extracted as eigenvector. SVM classifier is constructed based on the three sample sets of no corrosion, pitting corrosion and uniform corrosion, which can recognize CO₂ corrosion types accurately. Superiority of this method is verified by comparison with recognition result of neural network.

Abstract: The failure of hydraulic pump as a power unit in hydraulic systems affects directly the proper performance of the systems. Therefore, the monitoring of the pump performance and diagnosis of pump faults are urgent problems in want of solution. The principle of RBF algorithm is described. Study on fault diagnosis based on RBF for hydraulic pump. The test and analysis results indicate that the method is simple and efficient.