Applied Mechanics and Materials Vols. 401-403

Abstract: An improved FMCW auto-collision radar system is introduced. The system includes perfect binary sequences pairs theory, the method using auto-correlation functions to get target signal and measure distance, this enables itself to get constant development with theoretical progress. The new system only changes the program of signal generator a little, moreover it can be realized by DSP, which can reduce the false alert notably so as to be applied increasingly widely. Key words: stepped-frequency modulation; multi-target detection; perfect binary sequences pairs

Abstract: This paper Expounds the importance of recoil mechanism in the whole Artillery Systems, and compares three Vibration Signal De-noising based on wavelet analysis. It chooses multi-wavelet to de-noise on the basis of characteristic of recoil mechanism vibration signal, and the result is acceptable. It lays the foundation for fault diagnosis of recoil mechanism.

Abstract: A time sequence clustering algorithm based on edit distance is proposed in the paper, which solves the problem that the existing clustering algorithms for time sequence data is inefficient because of ignorance of different time span of time sequence data. Firstly, the algorithm calculates the distance between time sequences on which a distance matrix is determined. In the second place, for a given time sequence set, a forest with n binary trees is established in terms of the distance matrix and then merge the trees. Finally, a cluster clustering algorithm is called to dynamically adjust the clustering results, and then real-time clustering structure is obtained. Experimental results demonstrated that the algorithm has higher efficiency and clustering quality.

Abstract: Vehicle and pedestrian detection plays a critical role in the intelligent transportation system. The paper proposes an algorithm which can solve the problem effectively by Histograms of Oriented Gradients (HOG) features extraction and Support Vector Machine (SVM). This detection system is based on Histograms of Oriented Gradients features combined with Support Vector Machine for the recognition stage which is insensitive to lightings and noises. We use Kalman filter to track the objects. As shown in experiments, the method has high detection rate and can also satisfy the real-time intelligent transportation system.

Abstract: This paper introduced the system of real-time pulse signal acquisition based on CC2430.the original pulse signal was collected by projected pulse sensor, and then after shaping, filtering and amplification, we can get the pulse wave signal, which was stable and synchronized with the heart. After that this signal was input to the CC2430 chip, and reached the PC by ZigBee wireless communication, therefore the real-time monitoring from doctor to patient could be achieved. There were many advantages, such as simple, low power consumption, real-time coercion, etc. We can also expand the functional modules interfaces ,such as body temperature, ECG, blood pressure, to achieve the real-time monitoring more physiological parameters.

Abstract: Distance choice is an important issue in power load pattern extraction using clustering techniques, so it is necessary to find the influence on clustering result of load curves using different distances in clustering algorithms. In this paper several distances are used in the k-means algorithm for clustering load curves and their influences on the clustering results are analyzed, therefore, the suitable distance for the k-means algorithms is obtained. An example with 147 electricity customers load curves shows distances have different influences on clustering results using the same clustering algorithm. The comparison results indicate that the choice of distances is an important issue in power load pattern extraction using clustering techniques and a suitable distance may improve the accuracy of mining algorithms.

Abstract: The financial world is an uncertain universe where events take place every day, every hour, and every second. Information arrives completely randomly and so do the events. The operations in business activities are continually affected by these events beyond the control of the management. One of the most significant examples in financial economics is the most recent economic-financial crisis of 2008-2009 caused by the collapse of Lehman Brothers Holdings Inc.. The aim of this study is to investigate the statistical properties of the empirical data based on time series of the RFTSE100, RS&P500 and forecast one-step-ahead returns for three months. Additionally, we study the behavior of volatility, which is currently determined as a measure for variation of price or return of a financial instrument over time.

Abstract: the identity authentication is the information society to a commonly used means of information protection, with what kind of identity certification tool is to determine the success or failure of the key authentication, studies show that EEG signal is difficult to counterfeit, therefore the EEG signal is one of the identity certification tool selection. This article uses the wavelet decomposition as data analysis tools, analysis of the EEG signals under normal collected, results show that the acquisition in normal EEG signal, using this method can well identify subjects.

Abstract: With the growing deployment of host and network intrusion detection systems (IDSs), thousands of alerts are generally generated from them per day. Managing these alerts becomes critically important. In this paper, a hybrid alert clustering method based on self-Organizing maps (SOM) and particle swarm optimization (PSO) is presented. We firstly select the important features through binary particle swarm optimization (BPSO) and mutual information (MI) and get a dimension reduced dataset. SOM is used to cluster the dataset. PSO is used to evolve the weights for SOM to improve the clustering result. The algorithm is based on a type of unsupervised machine learning algorithm that infers relationships from data without the need to train the algorithm with expertly labelled data. The approach is validated using the 2000 DARPA intrusion detection datasets and comparative results between the canonical SOM and our scheme are presented.

Abstract: Polysomnogram (PSG) has been the standard of the Sleep Analysis for many years. However it is complicated to operate, and attaches a lot of electrodes on the body. So the development of a non-load sleep architecture stage is necessary. Under the support of non-load detection technique, a new method for sleep architecture which takes advantage of variation of heart beat interval, respiration period body movement and the other physiological parameters during sleep has been studied. Due to sleep architecture it differs person to person, so the result of sleep architecture stage involves great uncertainty, using fuzzy logic theory achieves uncertainty analysis, and it can produce the more accurately result. This method has been tested on with PSG result as contrast, sleep analysis based on non-load detection technique and fuzzy logic has a high compliance rate. The method is qualified as being useful in clinical application.