首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 234 毫秒
1.
Semi-supervised anomaly detection methods leverage a few anomaly examples to yield drastically improved performance compared to unsupervised models. However, they still suffer from two limitations: 1) unlabeled anomalies (i.e., anomaly contamination) may mislead the learning process when all the unlabeled data are employed as inliers for model training; 2) only discrete supervision information (such as binary or ordinal data labels) is exploited, which leads to suboptimal learning of anomaly scores that essentially take on a continuous distribution. Therefore, this paper proposes a novel semi-supervised anomaly detection method, which devises contamination-resilient continuous supervisory signals. Specifically, we propose a mass interpolation method to diffuse the abnormality of labeled anomalies, thereby creating new data samples labeled with continuous abnormal degrees. Meanwhile, the contaminated area can be covered by new data samples generated via combinations of data with correct labels. A feature learning-based objective is added to serve as an optimization constraint to regularize the network and further enhance the robustness w.r.t. anomaly contamination. Extensive experiments on 11 real-world datasets show that our approach significantly outperforms state-of-the-art competitors by 20%–30% in AUC-PR and obtains more robust and superior performance in settings with different anomaly contamination levels and varying numbers of labeled anomalies.  相似文献   

2.
In synthetic aperture radar (SAR) image change detection, the deep learning has attracted increasingly more attention because the difference images (DIs) of traditional unsupervised technology are vulnerable to speckle noise. However, most of the existing deep networks do not constrain the distributional characteristics of the hidden space, which may affect the feature representation performance. This paper proposes a variational autoencoder (VAE) network with the siamese structure to detect changes in SAR images. The VAE encodes the input as a probability distribution in the hidden space to obtain regular hidden layer features with a good representation ability. Furthermore, subnetworks with the same parameters and structure can extract the spatial consistency features of the original image, which is conducive to the subsequent classification. The proposed method includes three main steps. First, the training samples are selected based on the false labels generated by a clustering algorithm. Then, we train the proposed model with the semisupervised learning strategy, including unsupervised feature learning and supervised network fine-tuning. Finally, input the original data instead of the DIs in the trained network to obtain the change detection results. The experimental results on four real SAR datasets show the effectiveness and robustness of the proposed method.  相似文献   

3.
Anomalous data are such data that deviate from a large number of normal data points, which often have negative impacts on various systems. Current anomaly detection technology suffers from low detection accuracy, high false alarm rate and lack of labeled data. Anomaly detection is of great practical importance as an effective means to detect anomalies in the data and provide important support for the normal operation of various systems. In this paper, we propose an anomaly detection classification model that incorporates federated learning and mixed Gaussian variational self-encoding networks, namely MGVN. The proposed MGVN network model first constructs a variational self-encoder using a mixed Gaussian prior to extracting features from the input data, and then constructs a deep support vector network with the mixed Gaussian variational self-encoder to compress the feature space. The MGVN finds the minimum hypersphere to separate the normal and abnormal data and measures the abnormal fraction by calculating the Euclidean distance between the data features and the hypersphere center. Federated learning is finally incorporated with MGVN (FL-MGVN) to effectively address the problems that multiple participants collaboratively train a global model without sharing private data. The experiments are conducted on the benchmark datasets such as NSL-KDD, MNIST and Fashion-MNIST, which demonstrate that the proposed FL-MGVN has higher recognition performance and classification accuracy than other methods. The average AUC on MNIST and Fashion-MNIST reached 0.954 and 0.937, respectively.  相似文献   

4.
With the widespread application of 3D capture devices, diverse 3D object datasets from different domains have emerged recently. Consequently, how to obtain the 3D objects from different domains is becoming a significant and challenging task. The existing approaches mainly focus on the task of retrieval from the identical dataset, which significantly constrains their implementation in real-world applications. This paper addresses the cross-domain object retrieval in an unsupervised manner, where the labels of samples from source domain are provided while the labels of samples from target domain are unknown. We propose a joint deep feature learning and visual domain adaptation method (Deep-VDA) to solve the cross-domain 3D object retrieval problem by the end-to-end learning. Specifically, benefiting from the advantages of deep learning networks, Deep-VDA employs MVCNN for deep feature extraction and domain alignment for unsupervised domain adaptation. The framework can enable the statistical and geometric shift between domains to be minimized in an unsupervised manner, which is accomplished by preserving both common and unique characteristics of each domain. Deep-VDA can improve the robustness of object features from different domains, which is important to maintain remarkable retrieval performance.  相似文献   

5.
Ranking is a central component in information retrieval systems; as such, many machine learning methods for building rankers have been developed in recent years. An open problem is transfer learning, i.e. how labeled training data from one domain/market can be used to build rankers for another. We propose a flexible transfer learning strategy based on sample selection. Source domain training samples are selected if the functional relationship between features and labels do not deviate much from that of the target domain. This is achieved through a novel application of recent advances from density ratio estimation. The approach is flexible, scalable, and modular. It allows many existing supervised rankers to be adapted to the transfer learning setting. Results on two datasets (Yahoo’s Learning to Rank Challenge and Microsoft’s LETOR data) show that the proposed method gives robust improvements.  相似文献   

6.
High-resolution probabilistic load forecasting can comprehensively characterize both the uncertainties and the dynamic trends of the future load. Such information is key to the reliable operation of the future power grid with a high penetration of renewables. To this end, various high-resolution probabilistic load forecasting models have been proposed in recent decades. Compared with a single model, it is widely acknowledged that combining different models can further enhance the prediction performance, which is called the model ensemble. However, existing model ensemble approaches for load forecasting are linear combination-based, like mean value ensemble, weighted average ensemble, and quantile regression, and linear combinations may not fully utilize the advantages of different models, seriously limiting the performance of the model ensemble. We propose a learning ensemble approach that adopts the machine learning model to directly learn the optimal nonlinear combination from data. We theoretically demonstrate that the proposed learning ensemble approach can outperform conventional ensemble approaches. Based on the proposed learning ensemble model, we also introduce a Shapley value-based method to evaluate the contributions of each model to the model ensemble. The numerical studies on field load data verify the remarkable performance of our proposed approach.  相似文献   

7.
The advent of connected devices and omnipresence of Internet have paved way for intruders to attack networks, which leads to cyber-attack, financial loss, information theft in healthcare, and cyber war. Hence, network security analytics has become an important area of concern and has gained intensive attention among researchers, off late, specifically in the domain of anomaly detection in network, which is considered crucial for network security. However, preliminary investigations have revealed that the existing approaches to detect anomalies in network are not effective enough, particularly to detect them in real time. The reason for the inefficacy of current approaches is mainly due the amassment of massive volumes of data though the connected devices. Therefore, it is crucial to propose a framework that effectively handles real time big data processing and detect anomalies in networks. In this regard, this paper attempts to address the issue of detecting anomalies in real time. Respectively, this paper has surveyed the state-of-the-art real-time big data processing technologies related to anomaly detection and the vital characteristics of associated machine learning algorithms. This paper begins with the explanation of essential contexts and taxonomy of real-time big data processing, anomalous detection, and machine learning algorithms, followed by the review of big data processing technologies. Finally, the identified research challenges of real-time big data processing in anomaly detection are discussed.  相似文献   

8.
The study of query performance prediction (QPP) in information retrieval (IR) aims to predict retrieval effectiveness. The specificity of the underlying information need of a query often determines how effectively can a search engine retrieve relevant documents at top ranks. The presence of ambiguous terms makes a query less specific to the sought information need, which in turn may degrade IR effectiveness. In this paper, we propose a novel word embedding based pre-retrieval feature which measures the ambiguity of each query term by estimating how many ‘senses’ each word is associated with. Assuming each sense roughly corresponds to a Gaussian mixture component, our proposed generative model first estimates a Gaussian mixture model (GMM) from the word vectors that are most similar to the given query terms. We then use the posterior probabilities of generating the query terms themselves from this estimated GMM in order to quantify the ambiguity of the query. Previous studies have shown that post-retrieval QPP approaches often outperform pre-retrieval ones because they use additional information from the top ranked documents. To achieve the best of both worlds, we formalize a linear combination of our proposed GMM based pre-retrieval predictor with NQC, a state-of-the-art post-retrieval QPP. Our experiments on the TREC benchmark news and web collections demonstrate that our proposed hybrid QPP approach (in linear combination with NQC) significantly outperforms a range of other existing pre-retrieval approaches in combination with NQC used as baselines.  相似文献   

9.
Detecting collusive spammers who collaboratively post fake reviews is extremely important to guarantee the reliability of review information on e-commerce platforms. In this research, we formulate the collusive spammer detection as an anomaly detection problem and propose a novel detection approach based on heterogeneous graph attention network. First, we analyze the review dataset from different perspectives and use the statistical distribution to model each user's review behavior. By introducing the Bhattacharyya distance, we calculate the user-user and product-product correlation degrees to construct a multi-relation heterogeneous graph. Second, we combine the biased random walk strategy and multi-head self-attention mechanism to propose a model of heterogeneous graph attention network to learn the node embeddings from the multi-relation heterogeneous graph. Finally, we propose an improved community detection algorithm to acquire candidate spamming groups and employ an anomaly detection model based on the autoencoder to identify collusive spammers. Experiments show that the average improvements of precision@k and recall@k of the proposed approach over the best baseline method on the Amazon, Yelp_Miami, Yelp_New York, Yelp_San Francisco, and YelpChi datasets are [13%, 3%], [32%, 12%], [37%, 7%], [42%, 10%], and [18%, 1%], respectively.  相似文献   

10.
Imbalanced sample distribution is usually the main reason for the performance degradation of machine learning algorithms. Based on this, this study proposes a hybrid framework (RGAN-EL) combining generative adversarial networks and ensemble learning method to improve the classification performance of imbalanced data. Firstly, we propose a training sample selection strategy based on roulette wheel selection method to make GAN pay more attention to the class overlapping area when fitting the sample distribution. Secondly, we design two kinds of generator training loss, and propose a noise sample filtering method to improve the quality of generated samples. Then, minority class samples are oversampled using the improved RGAN to obtain a balanced training sample set. Finally, combined with the ensemble learning strategy, the final training and prediction are carried out. We conducted experiments on 41 real imbalanced data sets using two evaluation indexes: F1-score and AUC. Specifically, we compare RGAN-EL with six typical ensemble learning; RGAN is compared with three typical GAN models. The experimental results show that RGAN-EL is significantly better than the other six ensemble learning methods, and RGAN is greatly improved compared with three classical GAN models.  相似文献   

11.
介绍了集成学习入侵检测系统设计的总体思路、总体结构和各模块功能,重点研究了基于遗传算法的集成学习分类引擎工作原理,通过仿真试验说明集成神经网络能克服单个神经网络的缺陷,具有高速数据处理与自学习功能.  相似文献   

12.
We present a 3-staged method for automated learning of the spatial density function of the mass of all gravitating matter in a real galaxy, for which, data exist on the observable phase space coordinates of a sample of resident galactic particles that trace the galactic gravitational potential. We learn this gravitational mass density function, by embedding it in the domain of the probability density function (pdf) of the phase space vector variable, where we learn this pdfas well, given the data. We generate values of each sought function, at a design value of its input, to learn vectorised versions of each function; this creates the training data, using which we undertake supervised learning of each function, to thereafter undertake predictions and forecasting of the functional value, at test inputs. We assume that the phase space that a kinematic data set is sampled from, is isotropic, and we quantify the relative violation of this assumption, in a given data set. Illustration of the method is made to the real elliptical galaxy NGC4649. The purpose of this learning is to produce a data-driven protocol that allows for computation of dark matter content in any example real galaxy, without relying on system- specific astronomical details, while undertaking objective quantification of support in the data for undertaken model assumptions.  相似文献   

13.
Fault or anomaly detection is one of the key problems faced by the chemical process industry for achieving safe and reliable operation. In this study, a novel methodology, spectral weighted graph autoencoder (SWGAE) is proposed, wherein, the problem of anomaly detection is addressed with the help of graphs. The proposed approach entails the following key steps. Firstly, constructing a spectral weighted graph, where each time step of a process variable in the multivariate time series dataset is modelled as a node in an appropriately tuned moving window. Subsequently, we propose to monitor the weights of the edges between two nodes that make a connection. The faulty instances are identified based on the discrepancy in the weight pattern compared to normal operating data. To this end, once the weights are determined, they are fed to the auto-encoder network, where reconstruction loss is calculated, and faults are identified if the reconstruction loss exceeds a threshold. Further, to make the proposed approach comprehensive, a fault isolation methodology is also proposed to identify the faulty nodes once the faulty variables are identified. The proposed approach is validated using Tennessee-Eastman benchmark data and pressurized heavy water nuclear reactor real-time plant data. The results indicate that the SWGAE method, when compared to the other state-of-the-art methods, yielded more accurate results in correctly detecting faulty nodes and isolating them.  相似文献   

14.
The wide spread of false information has detrimental effects on society, and false information detection has received wide attention. When new domains appear, the relevant labeled data is scarce, which brings severe challenges to the detection. Previous work mainly leverages additional data or domain adaptation technology to assist detection. The former would lead to a severe data burden; the latter underutilizes the pre-trained language model because there is a gap between the downstream task and the pre-training task, which is also inefficient for model storage because it needs to store a set of parameters for each domain. To this end, we propose a meta-prompt based learning (MAP) framework for low-resource false information detection. We excavate the potential of pre-trained language models by transforming the detection tasks into pre-training tasks by constructing template. To solve the problem of the randomly initialized template hindering excavation performance, we learn optimal initialized parameters by borrowing the benefit of meta learning in fast parameter training. The combination of meta learning and prompt learning for the detection is non-trivial: Constructing meta tasks to get initialized parameters suitable for different domains and setting up the prompt model’s verbalizer for classification in the noisy low-resource scenario are challenging. For the former, we propose a multi-domain meta task construction method to learn domain-invariant meta knowledge. For the latter, we propose a prototype verbalizer to summarize category information and design a noise-resistant prototyping strategy to reduce the influence of noise data. Extensive experiments on real-world data demonstrate the superiority of the MAP in new domains of false information detection.  相似文献   

15.
  相似文献   

16.
Textual entailment is a task for which the application of supervised learning mechanisms has received considerable attention as driven by successive Recognizing Data Entailment data challenges. We developed a linguistic analysis framework in which a number of similarity/dissimilarity features are extracted for each entailment pair in a data set and various classifier methods are evaluated based on the instance data derived from the extracted features. The focus of the paper is to compare and contrast the performance of single and ensemble based learning algorithms for a number of data sets. We showed that there is some benefit to the use of ensemble approaches but, based on the extracted features, Naïve Bayes proved to be the strongest learning mechanism. Only one ensemble approach demonstrated a slight improvement over the technique of Naïve Bayes.  相似文献   

17.
针对高斯混合模型算法（GMM）对初始参数敏感、易陷入局部最优的问题,本文提出一种基于改进海洋捕食者算法优化的GMM算法（MMPA-GMM）。首先基于混沌序列和伪对立学习策略初始化种群,引入非线性收敛因子平衡MPA算法的全局与局部搜索,同时提出融入社会等级制度的位置更新策略;然后从搜索能力和收敛速度对改进的MPA进行分析;最后以S_Dbw指标作为算法的适应度函数,利用改进的MPA优化GMM算法的初始参数。实验结果表明,改进的MPA在4种测试函数上表现良好,并且MMPA-GMM算法对4个数据集的聚类效果均有改善,有效避免了GMM算法陷入局部最优的问题。  相似文献   

18.
林萍  吕健超 《情报科学》2023,41(2):135-142
【目的/意义】提出基于Stacking集成学习的问答信息采纳行为识别策略,促进在线健康社区问答的精准化推送、助推数字化医疗服务高质量发展。【方法/过程】构建以集成学习方法和非集成学习方法为基学习器、以逻辑回归算法（LR）为元学习器的Stacking集成学习模型,比较单预测模型、同类预测模型组合、不同类预测模型组合的Stacking集成学习模型预测精度,选取“寻医问药”平台的慢性病问答构建数据集验证模型的优越性,并选取“快速问医生有问必答120”平台数据验证模型的可移植性。【结果/结论】Stacking集成模型相比于单预测模型能够更精准识别被采纳问答信息,模型具有较强的泛化性,可以适用于不同的在线健康社区。【创新/局限】本文基于Stacking集成思想构建两阶段预测模型,并借助机器学习构建最佳预测模型组合,显著提高在线健康社区问答信息采纳识别精度,但伴随问答信息积累,在线健康社区问答模式不断发展变化,考虑结合历史数据和每日更新数据的动态预测方法是未来研究工作重点。  相似文献   

19.
The stacked extreme learning machine (S-ELM) is an advanced framework of deep learning. It passes the ‘reduced’ outputs of the previous layer to the current layer, instead of directly propagating the previous outputs to the next layer in traditional deep learning. The S-ELM could address some large and complex data problems with a high accuracy and a relatively low requirement for memory. However, there is still room for improvement of the time complexity as well as robustness while using S-ELM. In this article, we propose an enhanced S-ELM by replacing the original principle component analysis (PCA) technique used in this algorithm with the correntropy-optimized temporal PCA (CTPCA), which is robust for outliers rejection and significantly improves the training speed. Then, the CTPCA-based S-ELM performs better than S-ELM in both accuracy and learning speed, when dealing with dataset disturbed by outliers. Furthermore, after integrating the extreme learning machine (ELM) sparse autoencoder (AE) method into the CTPCA-based S-ELM, the learning accuracy is further improved while spending a little more training time. Meanwhile, the sparser and more compact feature information are available by using the ELM sparse AE with more computational efforts. The simulation results on some benchmark datasets verify the effectiveness of our proposed methods.  相似文献   

20.
Most of the existing large-scale high-dimensional streaming anomaly detection methods suffer from extremely high time and space complexity. Moreover, these models are very sensitive to parameters,make their generalization ability very low, can also be merely applied to very few specific application scenarios. This paper proposes a three-layer structure high-dimensional streaming anomaly detection model, which is called the double locality sensitive hashing Bloom filter, namely dLSHBF. We first build the former two layers that is double locality sensitive hashing (dLSH), proving that the dLSH method reduces the hash coding length of the data, and it ensures that the projected data still has a favorable mapping distance-preserving property after projection. Second, we use a Bloom filter to build the third layer of dLSHBF model, which used to improve the efficiency of anomaly detection. Six large-scale high-dimensional data stream datasets in different IIoT anomaly detection domains were selected for comparison experiments. First, extensive experiments show that the distance-preserving performance of the former dLSH algorithm proposed in this paper is significantly better than the existing LSH algorithms. Second, we verify the dLSHBF model more efficient than the other existing advanced Bloom filter model (for example Robust Bloom Filter, Fly Bloom Filter, Sandwich Learned Bloom Filter, Adaptive Learned Bloom Filters). Compared with the state of the art, dLSHBF can perform with the detection rate (DR) and false alarm rate (FAR) of anomaly detection more than 97%, and less than 2.2% respectively. Its effectiveness and generalization ability outperform other existing streaming anomaly detection methods.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号