In open environment, an effective trust mechanism should be built to ensure transaction safety. But current trust evaluation approaches solely based on the certificate or feedback are inaccurate and ineffective. Thus,...
详细信息
In open environment, an effective trust mechanism should be built to ensure transaction safety. But current trust evaluation approaches solely based on the certificate or feedback are inaccurate and ineffective. Thus, referring to the social trust models, this paper presents a capability enhanced method to improve the accuracy of evaluating trustworthiness. Based on it, this paper also designs a trust evaluation model ServTrust that naturally provides a solution to the trust problem. Compared with current feedback based approaches, simulation experimental results show the effectiveness of the proposed model in trust evaluating.
Hyperspectral image super resolution aims to improve the spatial resolution of given hyperspectral images, which has become a highly attractive topic in the field of image processing. Existing techniques typically foc...
Hyperspectral image super resolution aims to improve the spatial resolution of given hyperspectral images, which has become a highly attractive topic in the field of image processing. Existing techniques typically focus on super resolution with sufficient training data. However, restricted by data acquisition conditions, certain hyperspectral images or band images are very different to obtain, resulted in insufficient training data. In order to solve this problem, a new hyperspectral image super resolution method is proposed in this paper in an effort to conduct the super resolution task over insufficient (sparse) training data, by applying the recently introduced ANFIS (Adaptive Network-based Fuzzy Inference System) interpolation method. Particularly, the training dataset is divided into several subsets. For the subsets with sufficient training data, the relevant ANFIS models are trained using standard ANFIS learning algorithm, while for the subsets with sparse training data, the corresponding ANFIS models are interpolated through the use of ANFIS interpolation. Experimental results indicate that compared with the methods using sufficient training data, the proposed method can achieve very similar result, showing its effectiveness for situations where only sparse training data is available.
Local causal discovery aims to learn and distinguish the direct causes and effects of a target variable from observed data. Existing constraint-based local causal discovery methods use AND or OR rules in constructing ...
In the Internet of things (IoT) era, vehicles and other intelligent components in an intelligent transportation system (ITS) are connected, forming vehicular networks (VNs) that provide efficient and safe traffic and ...
详细信息
Compared with the flat multi-label image classification, the hierarchical structure reserves a richer source of structural information to represent complicated relationships between labels in the real world. However, ...
详细信息
It is well-known that deep learning models are vulnerable to adversarial examples. Existing studies of adversarial training have made great progress against this challenge. As a typical trait, they often assume that t...
详细信息
Automatic optimization algorithms are crucial for vehicle body lightweight design;however, existing methods remain inefficient leading to excessive iterations that increase both time and costs. Current interactive opt...
详细信息
Real-world data in emerging applications may suffer from highly-skewed class imbalanced distribution, however how to deal with this kind of problem appropriately through deep learning needs further investigation. In t...
详细信息
ISBN:
(纸本)9781665423991
Real-world data in emerging applications may suffer from highly-skewed class imbalanced distribution, however how to deal with this kind of problem appropriately through deep learning needs further investigation. In this paper, we mainly propose a novel cross-entropy based loss function, referred to as Additive Scale Loss (ASL), for deep representation learning and imbalanced classification. To deal with the class imbalanced problem, ASL aims at increasing the loss in case of misclassification, which can avoid the superimposed loss values caused by the large amount of easily classified data in the unbalanced database to dominate the loss value of misclassified data. Moreover, in real-world applications, one data source may be used for multiple scenarios, such as classification and embedding learning, however training two separable models to handle these problems is costly, especially in deep learning area. To tackle this issue, we present and integrate a discriminative inter-class separation term into ASL, and propose a discriminative ASL (D-ASL), which can not only improve the classification performance, but also obtain discriminative representations simultaneously. The discriminative inter-class separation term is general, and can be easily integrated to other loss functions, such as CE and FL, as the byproducts. Finally, a new deep convolutional neural network equipped with D-ASL and a fully-connected (FC) layer is proposed, which can classify the imbalanced image data and obtain the discriminative representations at the same time. Extensive experimental results verified the superior performance of our method.
This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the ...
详细信息
The matrix-based Rényi’s entropy allows us to directly quantify information measures from given data, without explicit estimation of the underlying probability distribution. This intriguing property makes it wid...
详细信息
暂无评论