Tech Science Press
Not a member yet
3972 research outputs found
Sort by
An Abnormal Network Flow Feature Sequence Prediction Approach for DDoS Attacks Detection in Big Data Environment
Get PDFDistributed denial-of-service (DDoS) is a rapidly growing problem with the fast development of the Internet. There are multitude DDoS detection approaches, however, three major problems about DDoS attack detection appear in the big data environment. Firstly, to shorten the respond time of the DDoS attack detector; secondly, to reduce the required compute resources; lastly, to achieve a high detection rate with low false alarm rate. In the paper, we propose an abnormal network flow feature sequence prediction approach which could fit to be used as a DDoS attack detector in the big data environment and solve aforementioned problems. We define a network flow abnormal index as PDRA with the percentage of old IP addresses, the increment of the new IP addresses, the ratio of new IP addresses to the old IP addresses and average accessing rate of each new IP address. We design an IP address database using sequential storage model which has a constant time complexity. The autoregressive integrated moving average (ARIMA) trending prediction module will be started if and only if the number of continuous PDRA sequence value, which all exceed an PDRA abnormal threshold (PAT), reaches a certain preset threshold. And then calculate the probability that is the percentage of forecasting PDRA sequence value which exceed the PAT. Finally we identify the DDoS attack based on the abnormal probability of the forecasting PDRA sequence. Both theorem and experiment show that the method we proposed can effectively reduce the compute resources consumption, identify DDoS attack at its initial stage with higher detection rate and lower false alarm rate
Paragraph Vector Representation Based on Word to Vector and CNN Learning
Get PDFDocument processing in natural language includes retrieval, sentiment analysis, theme extraction, etc. Classical methods for handling these tasks are based on models of probability, semantics and networks for machine learning. The probability model is loss of semantic information in essential, and it influences the processing accuracy. Machine learning approaches include supervised, unsupervised, and semi-supervised approaches, labeled corpora is necessary for semantics model and supervised learning. The method for achieving a reliably labeled corpus is done manually, it is costly and time-consuming because people have to read each document and annotate the label of each document. Recently, the continuous CBOW model is efficient for learning high-quality distributed vector representations, and it can capture a large number of precise syntactic and semantic word relationships, this model can be easily extended to learn paragraph vector, but it is not precise. Towards these problems, this paper is devoted to developing a new model for learning paragraph vector, we combine the CBOW model and CNNs to establish a new deep learning model. Experimental results show that paragraph vector generated by the new model is better than the paragraph vector generated by CBOW model in semantic relativeness and accuracy
Inverted XML Access Control Model Based on Ontology Semantic Dependency
Get PDFIn the era of big data, the conflict between data mining and data privacy protection is increasing day by day. Traditional information security focuses on protecting the security of attribute values without semantic association. The data privacy of big data is mainly reflected in the effective use of data without exposing the user’s sensitive information. Considering the semantic association, reasonable security access for privacy protect is required. Semi-structured and self-descriptive XML (eXtensible Markup Language) has become a common form of data organization for database management in big data environments. Based on the semantic integration nature of XML data, this paper proposes a data access control model for individual users. Through the semantic dependency between data and the integration process from bottom to top, the global visual range of inverted XML structure is realized. Experimental results show that the model effectively protects the privacy and has high access efficiency
Full-Blind Delegating Private Quantum Computation
Get PDFThe delegating private quantum computation (DQC) protocol with the universal quantum gate set {X,Z,H,P,R,CNOT} was firstly proposed by Broadbent et al. [Broadbent (2015)], and then Tan et al. [Tan and Zhou (2017)] tried to put forward a half-blind DQC protocol (HDQC) with another universal set {H,P,CNOT,T}. However, the decryption circuit of Toffoli gate (i.e. T) is a little redundant, and Tan et al.’s protocol [Tan and Zhou (2017)] exists the information leak. In addition, both of these two protocols just focus on the blindness of data (i.e. the client’s input and output), but do not consider the blindness of computation (i.e. the delegated quantum operation). For solving these problems, we propose a full-blind DQC protocol (FDQC) with quantum gate set {H,P,CNOT,T}, where the desirable delegated quantum operation, one of {H,P,CNOT,T}, is replaced by a fixed sequence (H,P,CZ,CNOT,T) to make the computation blind, and the decryption circuit of Toffoli gate is also optimized. Analysis shows that our protocol can not only correctly perform any delegated quantum computation, but also holds the characteristics of data blindness and computation blindness
Snow Cover Mapping for Mountainous Areas by Fusion of MODIS L1B and Geographic Data Based on Stacked Denoising Auto-Encoders
Get PDFSnow cover plays an important role in meteorological and hydrological researches. However, the accuracies of currently available snow cover products are significantly lower in mountainous areas than in plains, due to the serious snow/cloud confusion problem caused by high altitude and complex topography. Aiming at this problem, an improved snow cover mapping approach for mountainous areas was proposed and applied in Qinghai-Tibetan Plateau. In this work, a deep learning framework named Stacked Denoising Auto-Encoders (SDAE) was employed to fuse the MODIS multispectral images and various geographic datasets, which are then classified into three categories: Snow, cloud and snow-free land. Moreover, two independent SDAE models were trained for snow mapping in snow and snow-free seasons respectively in response to the seasonal variations of meteorological conditions. The proposed approach was verified using in-situ snow depth records, and compared to the most widely used snow products MOD10A1 and MYD10A1. The comparison results show that our method got the best performance: Overall accuracy of 98.95% and F-measure of 73.84%. The results indicated that our method can effectively improve the snow recognition accuracy, and it can be further extended to other multi-source remote sensing image classification issues
Research on Operation of UAVs in Non-isolated Airspace
Get PDFIn order to explore the safe operation of UAVs in non-segregated airspace, a collision risk model for cylindrical UAVs based on conflict areas was constructed and the risk of conflict between manned and unmanned aerial vehicles was researched. According to the results of risk analysis, a strategy for solving the conflict of aircraft is proposed, and the risk assessment experiment of unmanned aerial vehicle (UAV) in non-isolated airspace conflict is carried out. The results show that under the experimental conditions, large unmanned aerial vehicles equipped with ADS-B, TCAS and other airborne sensing systems will indeed interfere with other aircraft in airspace when they enter non-isolated airspace. Especially when the number of aircraft in airspace is large, the automatic avoidance system of UAV will increase the avoidance time and trigger the safety alarm, but the safety level is still acceptable. This indicates that it is relatively safe for UAVs to enter non-isolated airspace under limited conditions. The results can be used as a reference for the safe operation of unmanned aerial vehicle (UAV) in non-isolated airspace
A Memory-efficient Simulation Method of Grover's Search Algorithm
Get PDFGrover's search algorithm is one of the most significant quantum algorithms, which can obtain quadratic speedup of the extensive search problems. Since Grover's search algorithm cannot be implemented on a real quantum computer at present, its quantum simulation is regarded as an effective method to study the search performance. When simulating the Grover's algorithm, the storage space required is exponential, which makes it difficult to simulate the high-qubit Grover's algorithm. To this end, we deeply study the storage problem of probability amplitude, which is the core of the Grover simulation algorithm. We propose a novel memory-efficient method via amplitudes compression, and validate the effectiveness of the method by theoretical analysis and simulation experimentation. The results demonstrate that our compressed simulation search algorithm can help to save nearly 87.5% of the storage space than the uncompressed one. Thus under the same hardware conditions, our method can dramatically reduce the required computing nodes, and at the same time, it can simulate at least 3 qubits more than the uncompressed one. Particularly, our memory-efficient simulation method can also be used to simulate other quantum algorithms to effectively reduce the storage costs required in simulation
Dynamic Proofs of Retrievability Based on Partitioning-Based Square Root Oblivious RAM
Get PDFWith the development of cloud storage, the problem of efficiently checking and proving data integrity needs more consideration. Therefore, much of growing interest has been pursed in the context of the integrity verification of cloud storage. Provable data possession (PDP) and Proofs of retrievablity (POR) are two kinds of important scheme which can guarantee the data integrity in the cloud storage environments. The main difference between them is that POR schemes store a redundant encoding of the client data on the server so as to she has the ability of retrievablity while PDP does not have. Unfortunately, most of POR schemes support only static data. Stefanov et al. proposed a dynamic POR, but their scheme need a large of amount of client storage and has a large audit cost. Cash et al. use Oblivious RAM (ORAM) to construct a fully dynamic POR scheme, but the cost of their scheme is also very heavy. Based on the idea which proposed by Cash, we propose dynamic proofs of retrievability via Partitioning-Based Square Root Oblivious RAM (DPoR-PSR-ORAM). Firstly, the notions used in our scheme are defined. The Partitioning-Based Square Root Oblivious RAM (PSR-ORAM) protocol is also proposed. The DPOR-PSR-ORAM Model which includes the formal definitions, security definitions and model construction methods are described in the paper. Finally, we give the security analysis and efficiency analysis. The analysis results show that our scheme not only has the property of correctness, authenticity, next-read pattern hiding and retrievabiltiy, but also has the high efficiency
Automatic Delineation of Lung Parenchyma Based on Multilevel Thresholding and Gaussian Mixture Modelling
Get PDFDelineation of the lung parenchyma in the thoracic Computed Tomography (CT) is an important processing step for most of the pulmonary image analysis such as lung volume extraction, lung nodule detection and pulmonary vessel segmentation. An automatic method for accurate delineation of lung parenchyma in thoracic Computed Tomography images is presented in this paper. The proposed method involves a segmentation phase followed by a lung boundary correction technique. The tissues in the thoracic Computed Tomography can be represented by a number of Gaussians. We propose a histogram utilized Adaptive Multilevel Thresholding (AMT) for estimating the total number of Gaussians and their initial parameters. The parameters of Gaussian components are updated by Expectation Maximization (EM) algorithm. The segmented lung parenchyma from the Gaussian Mixture model (GMM) undergoes an Adaptive Morphological Filtering (AMF) to reduce the boundary errors. The proposed method has been tested on 70 diseased and 119 normal lung images from 28 cases obtained from Lung Image Database Consortium (LIDC). The performance of the proposed system has been validated
Grey Wolf Optimizer to Real Power Dispatch with Non-Linear Constraints
Get PDFA new and efficient Grey Wolf Optimization (GWO) algorithm is implemented to solve real power economic dispatch (RPED) problems in this paper. The nonlinear RPED problem is one the most important and fundamental optimization problem which reduces the total cost in generating real power without violating the constraints. Conventional methods can solve the ELD problem with good solution quality with assumptions assigned to fuel cost curves without which these methods lead to suboptimal or infeasible solutions. The behavior of grey wolves which is mimicked in the GWO algorithm are leadership hierarchy and hunting mechanism. The leadership hierarchy is simulated using four types of grey wolves. In addition, searching, encircling and attacking of prey are the social behaviors implemented in the hunting mechanism. The GWO algorithm has been applied to solve convex RPED problems considering the all possible constraints. The results obtained from GWO algorithm are compared with other state-of-the-art algorithms available in the recent literatures. It is found that the GWO algorithm is able to provide better solution quality in terms of cost, convergence and robustness for the considered ELD problems