关键词： 大数据   网络安全   模式识别   机器学习  

摘要： 大数据是一种非常先迚的模式识别技术,兵可以仍海量的网络数据资源中収现潜在的病毒或木马,这样就可以及时启动杀毒防御软件,将病毒或木马清除出网络,确保网络能够正常运行。本文详细地描述大数据的基本理论,分析兵在网络安全中的应用流程,极建了一个先迚的网络安全防御模型,提高网络安全防御水平。

关键词： Partial discharges   pattern recognition   grayscale image   sub-PRPD pattern   LBP features   HOG features   PCA transform   SVM classifier and DBSCAN  

摘要： Partial discharge (PD) measurement and identification have great importance to condition monitoring of power transformers. In this paper, a new method for recognition of single and multi-source of PD based on extraction of high level image features has been introduced. A database, involving 365 samples of phase-resolved PD (PRPD) data, is developed by measurement carried out on transformer artificial defect models (having different sizes of defect) under a specific applied voltage, to be used for proposed algorithm validation. In the first step, each set of PRPD data is converted into grayscale images to represent different PD defects. Two "image feature extraction" methods, the Local Binary Pattern (LBP), and the Histogram of Oriented Gradient (HOG), are employed to extract features from the obtained gray scale images. Different variants of Support Vector Machine (SVM) are adjusted for optimal classification of PD sources in this process. Impact of the employed parameters in the image processing such as image resolution, random noise, and phase shift, on identification accuracy is investigated and addressed. It is shown that by using HOG-SVM method 99.3% accuracy can be achieved. This is hardly affected by various external factors. Two case studies have been conducted on multi-source PD for evaluating the performance of the proposed algorithm. Avoid defect is implemented into the transformer model and the resultant recorded signal is used for the study. The DBSCAN algorithm is used as the mean of PD source clustering and sub-PRPD pattern development. It is shown that HOG-SVM method has superior performance in identifying active sources, under sub-PRPD pattern application.

关键词： Anomaly detection   Intrusion detection   Intrusion Detection System   Neural Networks   NSL-KDD   Security  

摘要： Network security is an essential element in the day-to-day IT operations of nearly every organization in business. Securing a computer network means considering the threats and vulnerabilities and arrange the countermeasures. Network security threats are increasing rapidly and making wireless network and internet services unreliable and insecure. Intrusion Detection System plays a protective role in shielding a network from potential intrusions. In this research paper, Feed Forward Neural Network and Pattern Recognition Neural Network are designed and tested for the detection of various attacks by using modified KDD Cup99 dataset. In our proposed models, Bayesian Regularization and Scaled Conjugate Gradient, training functions are used to train the Artificial Neural Networks. Various performance measures such as Accuracy, MCC, R-squared, MSE, DR, FAR and AROC are used to evaluate the performance of proposed Neural Network Models. The results have shown that both the models have outperformed each other in different performance measures on different attack detections. © 2019 MECS.

关键词： k-means clustering   Hierarchical clustering   Similarity measures   Traffic simulation   Scenarios-based approach   Travel time reliability analysis  

摘要： This paper is intended to mine historical data by presenting a scenario clustering approach to identify appropriate scenarios for mesoscopic simulation as a part of the evaluation of transportation projects or operational measures. It provides a systematic and efficient approach to select and prepare effective input scenarios for a given traffic simulation model. The scenario clustering procedure has two primary applications: travel time reliability analysis, and traffic estimation and prediction systems. The ability to systematically identify similarity and dissimilarity among weather scenarios can facilitate the selection of critical scenarios for reliability studies. It can also support real-time weather-responsive traffic management (WRTM) by quickly classifying a current or predicted weather condition into predefined categories and suggesting relevant WRTM strategies that can be tested via real-time traffic simulation before deployment. A detailed method for clustering weather time series data is presented and demonstrated using historical data. Two clustering algorithms with different similarity measures are compared. Clustering results using a k-means clustering algorithm with squared Euclidean distance are illustrated in the travel time reliability application.

关键词： Atmosphere   Asia   Rainfall   Classification   Pattern detection   Statistical forecasting  

摘要： In this study, self-organizing maps in combination with K-means clustering are used to objectively classify the anomalous weather patterns (WPs) associated with the summertime [May-June (MJ) and July-August-September (JAS)] heavy rainfall days during 1979-2007 over the Upper Nan River basin, northwestern Thailand. The results show that in MJ, intensive rains are mainly brought by the remarkable enhancement of the westerly summer monsoon. Meanwhile, westward-propagating tropical disturbances including tropical cyclones are the primary factors that reproduce heavy rainfall over the Upper Nan in JAS. These results also suggest that the occurrence time of local heavy rainfall is strongly related to the seasonal transition of the summer monsoon over the Indochina Peninsula. The classification results are then implemented with the perfect prognosis and analog method to predict the occurrence (yes/no) of heavy rainfall days over the studied basin in summer 2008-17 using prognostic WPs from the operational Japan Meteorological Agency Global Spectral Model (GSM). In general, the forecast skill of this approach up to 3-day lead times is significantly improved, in which the method not only outperforms GSM with the same forecast ranges, but also its 3-day forecast is better than the 1-2-day forecasts from GSM. However, the false alarms ratio is still high, particularly in JAS. Nevertheless, it is expected that the new approach will provide warning and useful guidance for decision-making by forecasters or end-users engaging in water management and disaster prevention activities.

关键词： C1q-domain-containing protein   Sebastes schlegelii   Immune defense   Pattern recognition receptor   Antibacterial activity  

摘要： C1q-domain-containing (C1qDC) proteins, which are involved in a series of immune responses, are important pattern recognition receptors in innate immunity in vertebrates and invertebrates. Functional studies of C1qDC proteins in vertebrates are scarce. In the present study, a C1qDC protein (SsC1qDC) from the teleost black rockfish (Sebastes schlegelii) was identified and examined at expression and functional levels. The open reading frame of SsC1qDC is 636 bp, and the predicted amino acid sequence of SsC1qDC shares 62%-69% overall identity with the C1qDC proteins of several fish species. SsC1qDC possesses conserved C1qDC features, including a signal sequence and a C1q domain. SsClqDC was expressed in different tissues and its expression was upregulated by bacterial and viral infection. Recombinant SsC1qDC (rSsC1qDC) exhibited apparent binding activities against PAMPs including LPS and PGN. rSsC1qDC had antibacterial activity against Vibrio parehaemolyticus, and was able to enhance the phagocytic activity of macrophages towards Vibrio anguillarwn. rSsC1qDC interacted with human heat-aggregated IgG. Furthermore, in the presence of rSsC1qDC, fish exhibited enhanced resistance against bacterial infection. Collectively, these results indicated that SsC1qDC serves as a pattern recognition receptor and plays a vital role in the defense system of black rockfish.

关键词： Active fingerprinting   Round-trip time   Data mining   Correlations   Cybersecurity  

摘要： Active fingerprinting is an effective penetration testing technique to know about vulnerability of hosts against security threats and network as a whole. Sometimes firewalls may block fingerprinting packets, hence making the probes infeasible. Measured Round Trip Time (RTTm) is a benign number that can be obtained from communication based on legitimate non malicious packets. In this paper, RTTm has been used along with other timers namely Smoothened Round-trip Time (SRTT), Round-trip Time Variance (RTTVar), Retransmission Time Out (RTO) and Scantime for pattern recognition and association analysis with the aid of cross-correlations. Experimental relationship among these timers are derived to back-up existing theoretical knowledge. A novel method to estimate IP-ID Sequence classes and network-traffic intensity based on these timers has been proposed. Results show that the model can be used to accurately derive (about 100% accuracy) active fingerprinting components IP-ID sequences and link traffic estimation. Analytical results obtained by this study can helpin designing high-performance realistic networks and dynamic congestion control techniques.

关键词： Mixture model   Mixed feature   Cluster analysis   Comorbidity   Generalised Bernoulli distribution  

摘要： In the present era of "Big Data", data collection involving massive amount of features with a mix of variable types is commonplace. Mixture model-based techniques for statistical cluster analysis of mixed numerical and categorical feature data have their limitations, due to the difficulty in specifying appropriate component-densities when common multivariate distributions become invalid. This problem is particularly apparent in applications where the outcome feature variables are in a categorical form. An example of such an application is the analysis of binary morbidity data in national health survey, where the aims are to quantify heterogeneous comorbidity patterns of health conditions and identify (risk)-features of individuals that explain the heterogeneity. In this paper, we propose an unsupervised mixture regression model of multivariate generalised Bernoulli distributions for cluster analysis on the basis of categorical outcome features and mixed risk features. The proposed method is illustrated using simulated data and two real data sets concerning comorbidity patterns among 20,788 Australians who participated in the 2007-2008 National Health Survey (NHS) and among 470 patients who were recruited in a randomised controlled trial of a health intervention about in-patient detoxification from alcohol, heroin or cocaine in Boston. The method is also readily applicable to cluster more general mixed-feature data via the framework of consensus clustering. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： temporal patterns   pattern recognition   DNA strand displacement   analog   molecular computing   transients  

摘要： Living cells communicate information about physiological conditions by producing signaling molecules in a specific timed manner. Different conditions can result in the same total amount of a signaling molecule, differing only in the pattern of the molecular concentration over time. Such temporally coded information can be completely invisible to even state-of-the-art molecular sensors with high chemical specificity that respond only to the total amount of the signaling molecule. Here, we demonstrate design principles for circuits with temporal specificity, that is, molecular circuits that respond to specific temporal patterns in a molecular concentration. We consider pulsatile patterns in a molecular concentration characterized by three fundamental temporal features: time period, duty fraction, and number of pulses. We develop circuits that respond to each one of these features while being insensitive to the others. We demonstrate our design principles using general chemical reaction networks and with explicit simulations of DNA strand displacement reactions. In this way, our work develops building blocks for temporal pattern recognition through molecular computation.

关键词： Two dimensional displays   Feature extraction   Pattern recognition   Additives   Sensors   Databases   Reliability  

摘要： A novel star pattern recognition technique for a "Lost-in-space" mode star tracker is presented in this paper. First, the two-dimensional (2-D) vectors connecting the stars are constructed in a rotationinvariant frame. Later, the additive property of 2-D vectors is integrated with the rotation-invariant frame to build a vector sequence for star identification. The proposed technique achieves an identification accuracy of 98.7% and has a run-time of only 12 ms for real-time testing on star images.