Search

Recent state-of-the-art semi-supervised learning (SSL) methods usually use data augmentations as core components. Such methods, however, are limited to simple transformations such as the augmentations under the instance's naive representations or the augmentations under the instance's semantic representations. To tackle this problem, we offer a unique insight into data augmentations and propose a novel data-augmentation-based semisupervised learning method, called Attentive Neighborhood Feature Augmentation (ANFA). The motivation of our method lies in the observation that the relationship between the given feature and its neighborhood may contribute to constructing more reliable transformations for the data, and further facilitating the classifier to distinguish the ambiguous features from the low-dense regions. Specially, we first project the labeled and unlabeled data points into an embedding space and then construct a neighbor graph that serves as a similarity measure based on the similar representations in the embedding space. Then, we employ an attention mechanism to transform the target features into augmented ones based on the neighbor graph. Finally, we formulate a novel semi-supervised loss by encouraging the predictions of the interpolations of augmented features to be consistent with the corresponding interpolations of the predictions of the target features. We carried out experiments on SVHN and CIFAR-10 benchmark datasets and the experimental results demonstrate that our method outperforms the state-of-the-artmethods when the number of labeled examples is limited. [ABSTRACT FROM AUTHOR]

Reweighting adversarial examples during training plays an essential role in improving the robustness of neural networks, which lies in the fact that examples closer to the decision boundaries aremuchmore vulnerable to being attacked and should be given larger weights. The probability margin (PM) method is a promising approach to continuously and path-independently measuring such closeness between the example and decision boundary. However, the performance of PM is limited due to the fact that PM fails to effectively distinguish the examples having only one misclassified category and the ones with multiple misclassified categories, where the latter is closer to multiclassification decision boundaries and is supported to be more critical in our observation. To tackle this problem, this paper proposed an improved PM criterion, called confused-label-based PM (CL-PM), to measure the closeness mentioned above and reweight adversarial examples during training. Specifically, a confused label (CL) is defined as the label whose prediction probability is greater than that of the ground truth label given a specific adversarial example. Instead of considering the discrepancy between the probability of the true label and the probability of the most misclassified label as thePMmethod does, we evaluate the closeness by accumulating the probability differences of all the CLs and ground truth label. CL-PM shares a negative correlation with data vulnerability: data with larger/smaller CL-PM is safer/riskier and should have a smaller/larger weight. Experiments demonstrated that CL-PM is more reliable in indicating the closeness regarding multiple misclassified categories, and reweighting adversarial training based on CL-PM outperformed state-ofthe- art counterparts. [ABSTRACT FROM AUTHOR]

Copyright of INMATEH - Agricultural Engineering is the property of INMATEH - Agricultural Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The Three Gorges is a region with a very high landslide distribution density and a concentrated population. In Three Gorges there are often landslide disasters, and the potential risk of landslides is tremendous. In this paper, focusing on Three Gorges, which has a complicated landform, spatial forecasting of landslides is studied by establishing 20 forecast factors (spectra, texture, vegetation coverage, water level of reservoir, slope structure, engineering rock group, elevation, slope, aspect, etc). China-Brazil Earth Resources Satellite (Cbers) images were adopted based on C4.5 decision tree to mine spatial forecast landslide criteria in Guojiaba Town (Zhigui County) in Three Gorges and based on this knowledge, perform intelligent spatial landslide forecasts for Guojiaba Town. All landslides lie in the dangerous and unstable regions, so the forecast result is good. The method proposed in the paper is compared with seven other methods: IsoData, K-Means, Mahalanobis Distance, Maximum Likelihood, Minimum Distance, Parallelepiped and Information Content Model. The experimental results show that the method proposed in this paper has a high forecast precision, noticeably higher than that of the other seven methods. [ABSTRACT FROM AUTHOR]

A fast optimal algorithm for solving radio resource allocation (RRA) problems in orthogonal frequency division multiple access (OFDMA) systems is proposed based on branch- and-bound (BnB) approach. The proposed algorithm offers the same performance as that achieved by some other existing optimal algorithms but with much reduced average computational complexity. As an effort in providing trade-off between performance and computational complexity, two suboptimal algorithms are also developed. Simulation results are shown to compare the performance and complexity of the proposed suboptimal algorithms with several existing algorithms. [ABSTRACT FROM PUBLISHER]

A semidefinite programming (SDP) relaxation approach is proposed to solve multiuser detection problems in systems with M-ary quadrature amplitude modulation (M-QAM). In the proposed approach, the optimal M-ary maximum likelihood (ML) detection is carried out by converting the associated M-ary integer programming problem into a binary integer programming problem. Then a relaxation approach is adopted to convert the binary integer programming problem into an SDP problem. This relaxation process leads to a detector of much reduced complexity. A multistage approach is then proposed to improve the performance of the SDP relaxation based detectors. Computer simulations demonstrate that the symbol-error rate (SER) performance offered by the proposed multistage SDP relaxation based detectors outperforms that of several existing suboptimal detectors. [ABSTRACT FROM PUBLISHER]