Abstract ：

Deep clustering outperforms conventional clustering by mutually promoting representation learning and cluster assignment. However, most existing deep clustering methods suffer from two major drawbacks. Firstly, most cluster assignment methods are highly dependent on the intermediate target distribution generated by a handcrafted nonlinear mapping function. Secondly, the clustering results can be easily guided towards wrong direction by the misassigned samples in each cluster. The existing deep clustering methods are incapable of discriminating such samples. These facts largely limit the possible performance that deep clustering methods can reach. To address these issues, a novel Self-Supervised Clustering (SSC) framework is constructed, which boosts the clustering performance by classification in an unsupervised manner. Fuzzy theory is used to score the membership of each sample to the clusters in terms of probability in each training epoch, which evaluates the intermediate clustering result certainty of each sample. The most reliable samples can be selected with the help of a sample selection method according to the membership and enhanced by data augmentation method. These augmented data are employed to fine-tune an off-the-shelf deep network classifier with the labels provided by the clustering in a self-supervised way. The classification results of the original dataset are used as the target distribution to guide the training process of the deep clustering model. The proposed framework can efficiently discriminate sample outliers and generate better target distribution with the assistance of the powerful classifier. Extensive experiments indicate that the proposed framework remarkably outperforms state-of-the-art deep clustering methods on four benchmark datasets. © 2023

Keyword ：

Classification; Deep clustering; Sample selection; Self-supervised

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Evolutionary multi-tasking optimization (EMTO) aims to boost the overall efficiency of optimizing multiple tasks by triggering knowledge transfer among them. Unfortunately, it may suffer from negative transfer on heterogeneous composite tasks that have low similarity. Some studies try to learn an intertask alignment transformation based on the paired samples from the involved tasks, but risk a failed alignment with improper pairwise methods. To solve this issue, this study proposes an optimal correspondence assisted affine transformation (OCAT) algorithm. OCAT explicitly constructs a mathematical model for the intertask alignment problem and theoretically deduces its optimal solution in an iterative method. As a result, the sample correspondences that enable the learned transformation to achieve the maximum intertask similarity can be located. Besides, a novel approach to deriving the affine transformation formula is also developed for OCAT. The resulting affine alignment transformation will not impair the knowledge contained in the tasks during the alignment process. By integrating OCAT with the estimation of distribution algorithm, this study finally develops a many-tasking optimization algorithm named MaT-EDA, where the solutions from other tasks are explicitly transferred as the samples for estimating the current distribution model. Extensive simulation studies have indicated that OCAT can significantly enhance the performance of EMTO, and MaT-EDA also achieves impressive many-tasking optimization performance. © 2023 Elsevier B.V.

Keyword ：

Affine transformation; Estimation of distribution algorithm; Evolutionary multi-tasking; Intertask alignment; Many-tasking optimization

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Financial Technology have revolutionized the delivery and usage of the autonomous operations and processes to improve the financial services. However, the massive amount of data (often called as big data) generated seamlessly across different geographic locations can end up as a bottleneck for the underlying network infrastructure. To mitigate this challenge, software-defined network (SDN) has been leveraged in the proposed approach to provide scalability and resilience in multicontroller environment. However, in case if one of these controllers fail or cannot work as per desired requirements, then either the network load of that controller has to be migrated to another suitable controller or it has to be divided or balanced among other available controllers. For this purpose, the proposed approach provides an adaptive recovery mechanism in a multicontroller SDN setup using support vector machine-based classification approach. The proposed work defines a recovery pool based on the three vital parameters, reliability, energy, and latency. A utility matrix is then computed based on these parameters, on the basis of which the recovery controllers are selected. The results obtained prove that it is able to perform well in terms of considered evaluation parameters. © 2014 IEEE.

Keyword ：

Classification; controller recovery; financial technology (FinTech); software-defined networks (SDNs); support vector machine

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Background: Accurate segmentation of organs has a great significance for clinical diagnosis, but it is still hard work due to the obscure imaging boundaries caused by tissue adhesion on medical images. Based on the image continuity in medical image volumes, segmentation on these slices could be inferred from adjacent slices with a clear organ boundary. Radiologists can delineate a clear organ boundary by observing adjacent slices. Purpose: Inspired by the radiologists' delineating procedure, we design an organ segmentation model based on boundary information of adjacent slices and a human–machine interactive learning strategy to introduce clinical experience. Methods: We propose an interactive organ segmentation method for medical image volume based on Graph Convolution Network (GCN) called Surface-GCN. First, we propose a Surface Feature Extraction Network (SFE-Net) to capture surface features of a target organ, and supervise it by a Mini-batch Adaptive Surface Matching (MBASM) module. Then, to predict organ boundaries precisely, we design an automatic segmentation module based on a Surface Convolution Unit (SCU), which propagates information on organ surfaces to refine the generated boundaries. In addition, an interactive segmentation module is proposed to learn radiologists' experience of interactive corrections on organ surfaces to reduce interaction clicks. Results: We evaluate the proposed method on one prostate MR image dataset and two abdominal multi-organ CT datasets. The experimental results show that our method outperforms other state-of-the-art methods. For prostate segmentation, the proposed method conducts a DSC score of 94.49% on PROMISE12 test dataset. For abdominal multi-organ segmentation, the proposed method achieves DSC scores of 95, 91, 95, and 88% for the left kidney, gallbladder, spleen, and esophagus, respectively. For interactive segmentation, the proposed method reduces 5–10 interaction clicks to reach the same accuracy. Conclusions: To overcome the medical organ segmentation challenge, we propose a Graph Convolutional Network called Surface-GCN by imitating radiologist interactions and learning clinical experience. On single and multiple organ segmentation tasks, the proposed method could obtain more accurate segmentation boundaries compared with other state-of-the-art methods. © 2023 American Association of Physicists in Medicine.

Keyword ：

Graph Convolutional Network; interactive segmentation; organ segmentation

Cite：

Copy from the list or Export to your reference management。

Abstract ：

The IPT system has been studied for underwater applications such as autonomous underwater vehicles (AUVs) and subsea sensors. However, it rarely comparatively shows the performance of the IPT system in air, freshwater, and seawater. Based on the fore-mentioned research background, this paper presents a survey of the properties of the IPT system in different mediums. Here, a 100 W power-level experimental IPT prototype is built and tested. The resonant frequency is set at 300 kHz with a gap range from 10 to 190 mm. The comparison is focused on the efficiency, mutual inductance, coupling coefficient, coil resistance, and quality factor of the IPT system. The IPT system is placed in air, freshwater, and seawater with the same settings. What's more, the magnetic fields of coupling coils in air, freshwater, and seawater are presented in this paper. This paper could be acted as a reference to optimize the IPT system and facilitate future IPT research for underwater applications by analysing the performance of the IPT system in different mediums. The 3D Ansys Maxwell simulation of the IPT system is also given here to study the magnetic fields. © 2023 The Authors. IET Power Electronics published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

Keyword ：

DC–AC power convertors; energy conservation; power conversion

Cite：

Copy from the list or Export to your reference management。

Abstract ：

The smart grid, as a cyber-physical system, is vulnerable to attacks due to the diversified and open environment. The false data injection attack (FDIA) can threaten the grid security by constructing and injecting the falsified attack vector to bypass the system detection. Due to the diversity of attacks, it is impractical to detect FDIAs by fixed methods. This paper proposed a false data injection attack model and countering detection methods based on deep reinforcement learning (DRL). First, we studied an attack model under the assumption of unlimited attack resources and information of complete topology. Different types of FDIAs are also enumerated. Then, we formulated the attack detection problem as a Markov decision process (MDP). A deep reinforcement learning-based method is proposed to detect FDIAs with a combined dynamic-static detection mechanism. To address the sparse reward problem, experiences with discrepant rewards are stored in different replay buffers to achieve efficiency. Moreover, the state space is extended by considering the most recent states to improve the perception capability. Simulations were performed on IEEE 9,14,30, and 57-bus systems, proving the validation of attack model and efficiency of detection method. Results proved efficacy of the detection method in different scenarios. Copyright © 2023 Lin, An, Cui and Zhang.

Keyword ：

attack detection; deep reinforcement learning; false data injection attack; smart grid; state estimation

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Determining the attitude of a non-cooperative target in space is an important frontier issue in the aerospace field, and has important application value in the fields of malfunctioning satellite state assessment and non-cooperative target detection in space. This paper proposes a non-cooperative target attitude estimation method based on the deep learning of ground and space access (GSA) scene radar images to solve this problem. In GSA scenes, the observed target satellite can be imaged not only by inverse synthetic-aperture radar (ISAR), but also by space-based optical satellites, with space-based optical images providing more accurate attitude estimates for the target. The spatial orientation of the intersection of the orbital planes of the target and observation satellites can be changed by fine tuning the orbit of the observation satellite. The intersection of the orbital planes is controlled to ensure that it is collinear with the position vector of the target satellite when it is accessible to the radar. Thus, a series of GSA scenes are generated. In these GSA scenes, the high-precision attitude values of the target satellite can be estimated from the space-based optical images obtained by the observation satellite. Thus, the corresponding relationship between a series of ISAR images and the attitude estimation of the target at this moment can be obtained. Because the target attitude can be accurately estimated from the GSA scenes obtained by a space-based optical telescope, these attitude estimation values can be used as training datasets of ISAR images, and deep learning training can be performed on ISAR images of GSA scenes. This paper proposes an instantaneous attitude estimation method based on a deep network, which can achieve robust attitude estimation under different signal-to-noise ratio conditions. First, ISAR observation and imaging models were created, and the theoretical projection relationship from the three-dimensional point cloud to the ISAR imaging plane was constructed based on the radar line of sight. Under the premise that the ISAR imaging plane was fixed, the ISAR imaging results, theoretical projection map, and target attitude were in a one-to-one correspondence, which meant that the mapping relationship could be learned using a deep network. Specifically, in order to suppress noise interference, a UNet++ network with strong feature extraction ability was used to learn the mapping relationship between the ISAR imaging results and the theoretical projection map to achieve ISAR image enhancement. The shifted window (swin) transformer was then used to learn the mapping relationship between the enhanced ISAR images and target attitude to achieve instantaneous attitude estimation. Finally, the effectiveness of the proposed method was verified using electromagnetic simulation data, and it was found that the average attitude estimation error of the proposed method was less than 1°. © 2023 by the authors.

Keyword ：

attitude estimation; deep learning; non-collaborate target; radar image

Cite：

Copy from the list or Export to your reference management。

Abstract ：

The authors would like to provide the updated acknowledgement for the article: Acknowledgements: This work was supported in part by the National Natural Science Foundation of China (Grant No. 12002254), the Natural Science Basic Research Plan in Shaanxi Province of China (Grant No. 2020JQ-013). The authors would like to apologize for any inconvenience caused. © 2023 Elsevier B.V.

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Various deep transfer learning solutions have been developed for machine fault diagnosis. The existing solutions mainly focus on domain adaptation by minimizing the data distribution discrepancy with certain metric, which emphasize the common features embedded in the data cross domains and neglect the unique features toward health condition classification in one specific domain. In these solutions, all the data for training have been forced to align in a common feature space and all the features for domain adaptation have been treated equally. However, there might exist domain specific features which are not appropriate for transfer but may contain essential information for classification in specific domain. In addition, due to the difficulty of collecting machine fault data, the number of machine fault samples is usually quite small or even zero. The traditional deep network structures and the training strategy are not the optimal choice in this occasion. To address these problems, a novel multi-view and multi-level network (MMNet) for fault diagnosis is developed. In MMNet, two network channels have been respectively constructed for cross domain common feature and domain specific feature learning to provide multi-view features. This architecture could implicitly differentiate the common features cross domains and the specific features only in one domain. In the channel of domain specific feature, a domain classifier and fault classifier are combined to learn the domain specific features. Multiple kernel maximum mean discrepancy (MK-MMD) is imposed on multiple layers of the common feature channel to implement domain adaptation and extract cross domain common features. The domain classification and fault classification together form a multi-level classification scheme. A classic few shot learning architecture with two modules respectively for feature extraction and relation computation is adopted as the backbone network. The relation score based classification mechanism enables zero shot fault classification in the target domain. Episode based few shot training strategy is employed to enhance the performance of MMNet with few labeled training data. Extensive experiments have demonstrated the state-of-the-art performance of MMNet on the involved transfer tasks. © 2022 Elsevier Ltd

Keyword ：

Fault diagnosis; Feature transferability; Few shot learning; Transfer learning

Cite：

Copy from the list or Export to your reference management。

Abstract ：

In information fusion, the uncertain information from different sources might be modeled with different theoretical frameworks. When one needs to fuse the uncertain information represented by different uncertainty theories, constructing the transformation between different frameworks is crucial. Various transformations of a Fuzzy Membership Function (FMF) into a Basic Belief Assignment (BBA) have been proposed, where the transformations based on uncertainty maximization and minimization can determine the BBA without preselecting the focal elements. However, these two transformations that based on uncertainty optimization emphasize the extreme cases of uncertainty. To avoid extreme attitudinal bias, a trade-off or moderate BBA with the uncertainty degree between the minimal and maximal ones is more preferred. In this paper, two moderate transformations of an FMF into a trade-off BBA are proposed. One is the weighted average based transformation and the other is the optimization-based transformation with weighting mechanism, where the weighting factor can be user-specified or determined with some prior information. The rationality and effectiveness of our transformations are verified through numerical examples and classification examples. © 2022 Chinese Society of Aeronautics and Astronautics

Keyword ：

Economic and social effects Information fusion Membership functions Uncertainty analysis

Cite：

Copy from the list or Export to your reference management。