Display Method:
Research Article
Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients
Cheng-Cheng Ma, Bao-Yuan Wu, Yan-Bo Fan, Yong Zhang, Zhi-Feng Li
doi: 10.1007/s11633-022-1328-1
Abstract PDF SpringerLink
Adversarial example has been well known as a serious threat to deep neural networks (DNNs). In this work, we study the detection of adversarial examples based on the assumption that the output and internal responses of one DNN model for both adversarial and benign examples follow the generalized Gaussian distribution (GGD) but with different parameters (i.e., shape factor, mean, and variance). GGD is a general distribution family that covers many popular distributions (e.g., Laplacian, Gaussian, or uniform). Therefore, it is more likely to approximate the intrinsic distributions of internal responses than any specific distribution. Besides, since the shape factor is more robust to different databases rather than the other two parameters, we propose to construct discriminative features via the shape factor for adversarial detection, employing the magnitude of Benford-Fourier (MBF) coefficients, which can be easily estimated using responses. Finally, a support vector machine is trained as an adversarial detector leveraging the MBF features. Extensive experiments in terms of image classification demonstrate that the proposed detector is much more effective and robust in detecting adversarial examples of different crafting methods and sources compared to state-of-the-art adversarial detection methods.
Dense Face Network: A Dense Face Detector Based on Global Context and Visual Attention Mechanism
Lin Song, Jin-Fu Yang, Qing-Zhen Shang, Ming-Ai Li
doi: 10.1007/s11633-022-1327-2
Abstract PDF SpringerLink
Face detection has achieved tremendous strides thanks to convolutional neural networks. However, dense face detection remains an open challenge due to large face scale variation, tiny faces, and serious occlusion. This paper presents a robust, dense face detector using global context and visual attention mechanisms which can significantly improve detection accuracy. Specifically, a global context fusion module with top-down feedback is proposed to improve the ability to identify tiny faces. Moreover, a visual attention mechanism is employed to solve the problem of occlusion. Experimental results on the public face datasets WIDER FACE and FDDB demonstrate the effectiveness of the proposed method.
Display Method:
Knowledge Mining: A Cross-disciplinary Survey
Yong Rui, Vicente Ivan Sanchez Carmona, Mohsen Pourvali, Yun Xing, Wei-Wen Yi, Hui-Bin Ruan, Yu Zhang
2022,  vol. 19,  no. 2, pp. 89-114,  doi: 10.1007/s11633-022-1323-6
Abstract PDF SpringerLink
Knowledge mining is a widely active research area across disciplines such as natural language processing (NLP), data mining (DM), and machine learning (ML). The overall objective of extracting knowledge from data source is to create a structured representation that allows researchers to better understand such data and operate upon it to build applications. Each mentioned discipline has come up with an ample body of research, proposing different methods that can be applied to different data types. A significant number of surveys have been carried out to summarize research works in each discipline. However, no survey has presented a cross-disciplinary review where traits from different fields were exposed to further stimulate research ideas and to try to build bridges among these fields. In this work, we present such a survey.
Research Article
Sharing Weights in Shallow Layers via Rotation Group Equivariant Convolutions
Zhiqiang Chen, Ting-Bing Xu, Jinpeng Li, Huiguang He
2022,  vol. 19,  no. 2, pp. 115-126,  doi: 10.1007/s11633-022-1324-5
Abstract PDF SpringerLink
The convolution operation possesses the characteristic of translation group equivariance. To achieve more group equivariances, rotation group equivariant convolutions (RGEC) are proposed to acquire both translation and rotation group equivariances. However, previous work paid more attention to the number of parameters and usually ignored other resource costs. In this paper, we construct our networks without introducing extra resource costs. Specifically, a convolution kernel is rotated to different orientations for feature extractions of multiple channels. Meanwhile, much fewer kernels than previous works are used to ensure that the output channel does not increase. To further enhance the orthogonality of kernels in different orientations, we construct the non-maximum-suppression loss on the rotation dimension to suppress the other directions except the most activated one. Considering that the low-level-features benefit more from the rotational symmetry, we only share weights in the shallow layers (SWSL) via RGEC. Extensive experiments on multiple datasets (i.e., ImageNet, CIFAR, and MNIST) demonstrate that SWSL can effectively benefit from the higher-degree weight sharing and improve the performances of various networks, including plain and ResNet architectures. Meanwhile, the convolutional kernels and parameters are much fewer (e.g., 75%, 87.5% fewer) in the shallow layers, and no extra computation costs are introduced.
Satellite Integration into 5G: Deep Reinforcement Learning for Network Selection
Emanuele De Santis, Alessandro Giuseppi, Antonio Pietrabissa, Michael Capponi, Francesco Delli Priscoli
2022,  vol. 19,  no. 2, pp. 127-137,  doi: 10.1007/s11633-022-1326-3
Abstract PDF SpringerLink
This paper proposes a deep-Q-network (DQN) controller for network selection and adaptive resource allocation in heterogeneous networks, developed on the ground of a Markov decision process (MDP) model of the problem. Network selection is an enabling technology for multi-connectivity, one of the core functionalities of 5G. For this reason, the present work considers a realistic network model that takes into account path-loss models and intra-RAT (radio access technology) interference. Numerical simulations validate the proposed approach and show the improvements achieved in terms of connection acceptance, resource allocation, and load balancing. In particular, the DQN algorithm has been tested against classic reinforcement learning one and other baseline approaches.
A Dynamic Resource Allocation Strategy with Reinforcement Learning for Multimodal Multi-objective Optimization
Qian-Long Dang, Wei Xu, Yang-Fei Yuan
2022,  vol. 19,  no. 2, pp. 138-152,  doi: 10.1007/s11633-022-1314-7
Abstract PDF SpringerLink
Many isolation approaches, such as zoning search, have been proposed to preserve the diversity in the decision space of multimodal multi-objective optimization (MMO). However, these approaches allocate the same computing resources for subspaces with different difficulties and evolution states. In order to solve this issue, this paper proposes a dynamic resource allocation strategy (DRAS) with reinforcement learning for multimodal multi-objective optimization problems (MMOPs). In DRAS, relative contribution and improvement are utilized to define the aptitude of subspaces, which can capture the potentials of subspaces accurately. Moreover, the reinforcement learning method is used to dynamically allocate computing resources for each subspace. In addition, the proposed DRAS is applied to zoning searches. Experimental results demonstrate that DRAS can effectively assist zoning search in finding more and better distributed equivalent Pareto optimal solutions in the decision space.
Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization
Wei-Chen Chen, Xin-Yi Yu, Lin-Lin Ou
2022,  vol. 19,  no. 2, pp. 153-168,  doi: 10.1007/s11633-022-1321-8
Abstract PDF SpringerLink
Pedestrian attribute recognition in surveillance scenarios is still a challenging task due to the inaccurate localization of specific attributes. In this paper, we propose a novel view-attribute localization method based on attention (VALA), which utilizes view information to guide the recognition process to focus on specific attributes and attention mechanism to localize specific attribute-corresponding areas. Concretely, view information is leveraged by the view prediction branch to generate four view weights that represent the confidences for attributes from different views. View weights are then delivered back to compose specific view-attributes, which will participate and supervise deep feature extraction. In order to explore the spatial location of a view-attribute, regional attention is introduced to aggregate spatial information and encode inter-channel dependencies of the view feature. Subsequently, a fine attentive attribute-specific region is localized, and regional weights for the view-attribute from different spatial locations are gained by the regional attention. The final view-attribute recognition outcome is obtained by combining the view weights with the regional weights. Experiments on three wide datasets (richly annotated pedestrian (RAP), annotated pedestrian v2 (RAPv2), and PA-100K) demonstrate the effectiveness of our approach compared with state-of-the-art methods.
Feature Selection and Feature Learning for High-dimensional Batch Reinforcement Learning: A Survey
De-Rong Liu, Hong-Liang, Li Ding Wang
2015,  vol. 12,  no. 3, pp. 229-242,  doi: 10.1007/s11633-015-0893-y
Abstract PDF SpringerLink
Second-order Sliding Mode Approaches for the Control of a Class of Underactuated Systems
Sonia Mahjoub, Faiçal Mnif, Nabil Derbel
2015,  vol. 12,  no. 2, pp. 134-141,  doi: 10.1007/s11633-015-0880-3
Abstract PDF SpringerLink
Genetic Algorithm with Variable Length Chromosomes for Network Intrusion Detection
Sunil Nilkanth Pawar, Rajankumar Sadashivrao Bichkar
2015,  vol. 12,  no. 3, pp. 337-342,  doi: 10.1007/s11633-014-0870-x
Abstract PDF SpringerLink
Grey Qualitative Modeling and Control Method for Subjective Uncertain Systems
Peng Wang, Shu-Jie Li, Yan Lv, Zong-Hai Chen
2015,  vol. 12,  no. 1, pp. 70-76,  doi: 10.1007/s11633-014-0820-7
Abstract PDF SpringerLink
Recent Progress in Networked Control Systems-A Survey
Yuan-Qing Xia, Yu-Long Gao, Li-Ping Yan, Meng-Yin Fu
2015,  vol. 12,  no. 4, pp. 343-367,  doi: 10.1007/s11633-015-0894-x
Abstract PDF SpringerLink
Cooperative Formation Control of Autonomous Underwater Vehicles: An Overview
Bikramaditya Das, Bidyadhar Subudhi, Bibhuti Bhusan Pati
2016,  vol. 13,  no. 3, pp. 199-225,  doi: 10.1007/s11633-016-1004-4
Abstract PDF SpringerLink
A Wavelet Neural Network Based Non-linear Model Predictive Controller for a Multi-variable Coupled Tank System
Kayode Owa, Sanjay Sharma, Robert Sutton
2015,  vol. 12,  no. 2, pp. 156-170,  doi: 10.1007/s11633-014-0825-2
Abstract PDF SpringerLink
An Unsupervised Feature Selection Algorithm with Feature Ranking for Maximizing Performance of the Classifiers
Danasingh Asir Antony Gnana Singh, Subramanian Appavu Alias Balamurugan, Epiphany Jebamalar Leavline
2015,  vol. 12,  no. 5, pp. 511-517,  doi: 10.1007/s11633-014-0859-5
Abstract PDF SpringerLink
Bounded Real Lemmas for Fractional Order Systems
Shu Liang, Yi-Heng Wei, Jin-Wen Pan, Qing Gao, Yong Wang
2015,  vol. 12,  no. 2, pp. 192-198,  doi: 10.1007/s11633-014-0868-4
Abstract PDF SpringerLink
Sliding Mode and PI Controllers for Uncertain Flexible Joint Manipulator
Lilia Zouari, Hafedh Abid, Mohamed Abid
2015,  vol. 12,  no. 2, pp. 117-124,  doi: 10.1007/s11633-015-0878-x
Abstract PDF SpringerLink
Robust Face Recognition via Low-rank Sparse Representation-based Classification
Hai-Shun Du, Qing-Pu Hu, Dian-Feng Qiao, Ioannis Pitas
2015,  vol. 12,  no. 6, pp. 579-587,  doi: 10.1007/s11633-015-0901-2
Abstract PDF SpringerLink
Advances in Vehicular Ad-hoc Networks (VANETs): Challenges and Road-map for Future Development
Elias C. Eze, Si-Jing Zhang, En-Jie Liu, Joy C. Eze
2016,  vol. 13,  no. 1, pp. 1-18,  doi: 10.1007/s11633-015-0913-y
Abstract PDF SpringerLink
Distributed Control of Chemical Process Networks
Michael J. Tippett, Jie Bao
2015,  vol. 12,  no. 4, pp. 368-381,  doi: 10.1007/s11633-015-0895-9
Abstract PDF SpringerLink
Appropriate Sub-band Selection in Wavelet Packet Decomposition for Automated Glaucoma Diagnoses
Chandrasekaran Raja, Narayanan Gangatharan
2015,  vol. 12,  no. 4, pp. 393-401,  doi: 10.1007/s11633-014-0858-6
Abstract PDF SpringerLink
Analysis of Fractional-order Linear Systems with Saturation Using Lyapunov s Second Method and Convex Optimization
Esmat Sadat Alaviyan Shahri, Saeed Balochian
2015,  vol. 12,  no. 4, pp. 440-447,  doi: 10.1007/s11633-014-0856-8
Abstract PDF SpringerLink
Extracting Parameters of OFET Before and After Threshold Voltage Using Genetic Algorithms
Imad Benacer, Zohir Dibi
2016,  vol. 13,  no. 4, pp. 382-391,  doi: 10.1007/s11633-015-0918-6
Abstract PDF SpringerLink
Generalized Norm Optimal Iterative Learning Control with Intermediate Point and Sub-interval Tracking
David H. Owens, Chris T. Freeman, Bing Chu
2015,  vol. 12,  no. 3, pp. 243-253,  doi: 10.1007/s11633-015-0888-8
Abstract PDF SpringerLink
Backstepping Control of Speed Sensorless Permanent Magnet Synchronous Motor Based on Slide Model Observer
Cai-Xue Chen, Yun-Xiang Xie, Yong-Hong Lan
2015,  vol. 12,  no. 2, pp. 149-155,  doi: 10.1007/s11633-015-0881-2
Abstract PDF SpringerLink
Flexible Strip Supercapacitors for Future Energy Storage
Rui-Rong Zhang, Yan-Meng Xu, David Harrison, John Fyson, Fu-Lian Qiu, Darren Southee
2015,  vol. 12,  no. 1, pp. 43-49,  doi: 10.1007/s11633-014-0866-6
Abstract PDF SpringerLink
A High-order Internal Model Based Iterative Learning Control Scheme for Discrete Linear Time-varying Systems
Wei Zhou, Miao Yu, De-Qing Huang
2015,  vol. 12,  no. 3, pp. 330-336,  doi: 10.1007/s11633-015-0886-x
Abstract PDF SpringerLink
Finite-time Control for a Class of Networked Control Systems with Short Time-varying Delays and Sampling Jitter
Chang-Chun Hua, Shao-Chong Yu, Xin-Ping Guan
2015,  vol. 12,  no. 4, pp. 448-454,  doi: 10.1007/s11633-014-0849-7
Abstract PDF SpringerLink
Machine Learning for Cataract Classification/Grading on Ophthalmic Imaging Modalities: A Survey
Xiaoqing Zhang, Yan Hu, Zunjie Xiao, Jiansheng Fang, Risa Higashita, Jiang Liu
Abstract PDF
Cataracts are the leading cause of visual impairment and blindness globally. Over the years, researchers have achieved significant progress in developing state-of-the-art machine learning techniques for automatic cataract classification and grading, aiming to prevent cataracts early and improve clinicians′ diagnosis efficiency. This survey provides a comprehensive survey of recent advances in machine learning techniques for cataract classification/grading based on ophthalmic images. We summarize existing literature from two research directions: conventional machine learning methods and deep learning methods. This survey also provides insights into existing works of both merits and limitations. In addition, we discuss several challenges of automatic cataract classification/grading based on machine learning techniques and present possible solutions to these challenges for future research.

2022 Vol.19 No. 2

Tieniu TAN

ISSN 2731-538X

Global Visitors