With the increase in popularity of Portable Document Format(PDF) documents and increasing vulnerability of PDF users, effective detection of malicious PDF documents has become as a more and more significant issue. In ...
详细信息
With the increase in popularity of Portable Document Format(PDF) documents and increasing vulnerability of PDF users, effective detection of malicious PDF documents has become as a more and more significant issue. In this paper, we proposed a way to detect malicious PDF files by using semi-supervise learning method. Compare with previous studies, this method not only improve detection accuracy and generalization ability by combining with three different classifiers, but also effectively utilize the abundant unlabeled PDF files to retrain classifiers and update module by selecting the "useful" files from unlabeled test set.
Recently, deep convolutional neural networks(CNNs) have made great achievements, whether taken as features extractor or classifier, in particular for very high resolution(VHR) images classification task which is a key...
详细信息
Recently, deep convolutional neural networks(CNNs) have made great achievements, whether taken as features extractor or classifier, in particular for very high resolution(VHR) images classification task which is a key point in the remote sensing field. This work aims to improve the VHR image classification accuracy by exploiting the fusion of two pre-trained deep convolutional neural network models. In this paper, we propose to concatenate the features extracted from the last convolutional layer of each pre-trained deep convolutional neural network to get a long features vector which is fed into a fullyconnected layer and then perform a fine-tuning for a VHR image dataset classification. The experimental results are promising since they show that the fusion of two deep CNNs achieves better accuracy for the classification compared to the individual CNN models on the same dataset.
This paper focuses on the task of searching a stationary target using a team of multiple unmanned aerial vehicles(UAV) with limited communication ranges and sensing capabilities. It is based on a probabilistic represe...
详细信息
This paper focuses on the task of searching a stationary target using a team of multiple unmanned aerial vehicles(UAV) with limited communication ranges and sensing capabilities. It is based on a probabilistic representation model of the search environment, in which each UAV keeps a probability map on the presence of the target for each cell. The UAVs make observations and update the map for multiple rounds according to the Bayesian rule. In this process, each UAV can exchange data with its neighbors who are in its communication range. The decision of finding the target can be made once its probability of presence in any cell reaches a threshold. In this work, we design an efficient framework to decide the movement of each UAV at each time step, and propose a novel data fusion strategy among UAVs. The simulation result shows that our framework achieves improvements on both the success rate and the time taken to complete the searching task. We also explore the impact of different parameters, like the sensor model, moving mobility model of each UAV, and the data fusion strategies associated with the moving patterns. The simulation results show that the correct rate on target identification can vary greatly under different parameter settings, indicating the importance of the selection of UAV searching components such as the sensor model and the mobility model.
Frequent sequential pattern mining is an important field in data mining. Compared with the static data, the stream data is a single scan data obtained in a continuous and real-time way. The frequent pattern mining alg...
详细信息
Frequent sequential pattern mining is an important field in data mining. Compared with the static data, the stream data is a single scan data obtained in a continuous and real-time way. The frequent pattern mining algorithm of traditional static sequence database has been difficult to meet the frequent pattern mining requirements for streaming data. The traditional serial processing method is time-consuming and cannot meet the requirements of high performance processing. Based on the existing Pisa algorithm, this paper presents a parallel algorithm named Parallel-Pisa, it can adjust the parallel strategy according to the different velocity of the stream data to improve the efficiency of the algorithm so that it can be better applied to frequent sequence pattern mining of stream data.
暂无评论