Article
Computer Science, Information Systems
Yi Zhu, Lei Li, Xindong Wu
Summary: The research proposes a semi-supervised deep learning framework to address the issue of insufficient labeled image data, utilizing stacked layers, convolutional approach, and sparse auto-encoder to learn feature representations. The framework also includes an algorithm to handle data redundancy and encodes label information using a Softmax regression model.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2021)
Article
Neuroimaging
Qing Li, Qinglin Dong, Fangfei Ge, Ning Qiang, Xia Wu, Tianming Liu
Summary: The study proposed a deep sparse recurrent auto-encoder (DSRAE) for unsupervised learning of spatial patterns and temporal fluctuations of brain networks simultaneously. The proposed model was evaluated on tasks from the HCP fMRI dataset, showing promising evidence of its effectiveness.
BRAIN IMAGING AND BEHAVIOR
(2021)
Article
Engineering, Electrical & Electronic
Yang Liu, Lanxue Dang, Shenshen Li, Kun Cai, Xianyu Zuo
Summary: This article summarizes the data type and processing theory model of RS-STBD, high-performance algorithm design, and architecture design of complex remote sensing application systems. It also analyzes current research problems and prospects the future development trends of RS-STBD.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Computer Science, Information Systems
Wenjuan Wang, Xuehui Du, Dibin Shan, Ruoxi Qin, Na Wang
Summary: This study utilizes deep learning to automatically extract essential feature representations in the cloud computing environment and designs a novel cloud intrusion detection system. By integrating deep learning and shallow learning techniques, it effectively reduces analytical overhead and achieves higher detection performance on intrusion detection evaluation datasets.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Jinyu Cai, Shiping Wang, Wenzhong Guo
Summary: The paper proposes a deep stacked sparse embedded clustering method that considers both local structure preservation and input sparsity. The deep learning approach jointly learns clustering-oriented features and optimizes cluster label assignments by minimizing both the reconstruction and clustering loss. Comprehensive experiments validate the effectiveness of introducing sparsity and preserving local structure in the proposed method.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Rui Fan, Huipeng Li, Tao Zhang, Hong Wang, Linhai Qi, Lina Sun
Summary: This paper proposes a voltage sag identification method that combines sparse auto-encoder and Attention Unet, achieving high accuracy in recognition by performing feature learning and extraction on high-dimensional data. It is of great significance for auxiliary decision-making in power quality management and governance.
Article
Engineering, Electrical & Electronic
Li Liao
Summary: This paper studies the support vector machine (SVM) parallelized remote sensing image classification algorithm based on big data. A method of nesting GPU in MPI multiprocesses within the big data framework is proposed to effectively improve the calculation processing speed and build a high-performance SVM parallel computing framework. The SVM algorithm is optimized by considering both empirical risk and structural risk minimization, and by constructing hyperplane decision boundaries with maximum edge distance. Experimental results show that the SVM classification algorithm achieves speedups of up to 2.55 with different numbers of nodes.
JOURNAL OF ELECTRONIC IMAGING
(2022)
Article
Computer Science, Artificial Intelligence
Yi Zhu, Xindong Wu, Jipeng Qiang, Xuegang Hu, Yuhong Zhang, Peipei Li
Summary: This paper introduces a multi-task learning framework based on DSML and SRICA models, which optimize with unlabeled data to achieve better performance.
PATTERN RECOGNITION
(2022)
Article
Engineering, Multidisciplinary
Zilong Wang, Young-Jin Cha
Summary: This article proposes an unsupervised deep learning-based approach for structural damage detection, which utilizes a carefully designed deep auto-encoder and one-class support vector machine for extracting damage-sensitive features and detecting future damage. Experimental and numerical studies confirm the high accuracy and stability of the method in detecting structural damage.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2021)
Article
Chemistry, Analytical
Peng Liang, Wenzhong Shi, Yixing Ding, Zhiqiang Liu, Haolv Shang
Summary: In this study, vector field learning was used to extract roads from high resolution remote sensing imaging, significantly improving the accuracy of road extraction by constructing vector fields inside or outside road areas, combined with normal road mask learning. The highest F1 score achieved was 0.7618, increased by 0.053 compared to using only mask learning.
Article
Computer Science, Information Systems
Xiaolu Han, Yun Liu, Zhenjiang Zhang, Xin Lu, Yang Li
Summary: This study introduces a sparse auto-encoder combined with kernel for network attack detection to improve network security. By optimizing and reconstructing data features, the model enhances detection efficiency and solves the problems caused by high-dimensional data. The proposed method achieves a recognition rate of 98.68% and an average dimension reduction time of 5.59 seconds, demonstrating better efficiency and computational performance compared to traditional methods.
COMPUTER COMMUNICATIONS
(2021)
Article
Computer Science, Information Systems
Jyostna Devi Bodapati
Summary: This paper proposes a convolutional neural network architecture based on spatial attention for recognizing the severity level of diabetic retinopathy. The experimental results show that combining end-to-end training with attention mechanism can improve the performance of the model.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Chemistry, Multidisciplinary
Kuan-Hsien Liu, Bo-Yen Lin
Summary: Semantic segmentation for high-resolution remote sensing images is challenging due to large image size and complexity of objects and scenes. To address these challenges, we propose a mixed deep learning model that combines local channel spatial attention and multi-scale attention to extract informative features and improve object boundary discrimination. Experimental results demonstrate that our model improves overall accuracy and competes with state-of-the-art methods.
APPLIED SCIENCES-BASEL
(2023)
Article
Geochemistry & Geophysics
Chen Xu, Xiaoping Du, Xiangtao Fan, Zhenzhen Yan, Xujie Kang, Junjie Zhu, Zhongyang Hu
Summary: This research analyzed the processing flow of remote sensing big data from the perspective of computer science and remote sensing science, proposing a modular framework. By introducing computation ready data as a dynamic data type to connect key modules of the framework, it significantly reduces experimental costs for remote sensing researchers.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Remote Sensing
Yongzhi Wang, Wenrui Liao, Xiaoyu Hu, Hua Lv, Qi Huang
Summary: This paper proposes a rooftop extraction method for high spatial resolution remote-sensing images based on sparse representation. The method improves extraction accuracy by determining optimal segmentation parameters and constructing an optimal feature subset. The overall accuracy of the proposed method in two study areas in Zhanggong District is 0.91776 and 0.88313, respectively. This study is of great significance in urban planning, population statistics, and economic forecasting.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2023)
Review
Computer Science, Information Systems
Claudia Greco, Giancarlo Fortino, Bruno Crispo, Kim-Kwang Raymond Choo
Summary: This paper provides a comprehensive review of literature on penetration testing of IoT devices and systems. It identifies existing and potential IoT penetration testing applications and proposed approaches, and highlights recent advances in AI-enabled penetration testing methods at the network edge.
ENTERPRISE INFORMATION SYSTEMS
(2023)
Article
Computer Science, Hardware & Architecture
Junchang Jing, Zhiyong Zhang, Kim-Kwang Raymond Choo, Kefeng Fan, Bin Song, Lili Zhang
Summary: This article investigates the spreading patterns and regularities of disinformation within and across platforms, and proposes a user propagation desire inference model and an optimization algorithm based on deep neural networks. Experimental results demonstrate that users' desire to spread disinformation is related to their interests and topics, and cross-platform dissemination motivation is weak. These findings can inform fine-grained governance and mitigation strategies to minimize disinformation dissemination.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2023)
Article
Business
Gianluca Zanella, Charles Zhechao Liu, Kim-Kwang Raymond Choo
Summary: This article introduces an unsupervised patent analysis framework that aims to improve the identification of novelty in blockchain-related patents. The proposed method helps companies better target their R&D efforts and maximize the return on technology investments. Experimental results show high precision and recall of the proposed method.
IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT
(2023)
Article
Engineering, Civil
Tong Wu, Xinghua Li, Yinbin Miao, Mengfan Xu, Haiyan Zhang, Ximeng Liu, Kim-Kwang Raymond Choo
Summary: Federated learning is beneficial for building better cooperative intelligent transportation systems (C-ITS) with intellectual property protection. Existing research on watermark-based protection in centralized models is not effective in federated learning due to differences in watermark distribution and loss of global model accuracy. To address these issues, we propose a multi-party entangled watermark algorithm in federated learning. Our scheme includes a local watermark enhancement algorithm to solve local watermark failures and a global entanglement aggregation algorithm to mitigate the loss of global model accuracy. Experimental results show significant advantages of our proposal in model accuracy and watermark success rate compared to existing watermark schemes in federated learning.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Yajing Xu, Zhihui Lu, Keke Gai, Qiang Duan, Junxiong Lin, Jie Wu, Kim-Kwang Raymond Choo
Summary: Federated learning (FL) is a promising approach for efficient machine learning with privacy protection in distributed environments such as IoT and MEC. The effectiveness of FL depends on participant nodes contributing their data and computing capacities to collaboratively train a global model. To enhance FL security and performance, this article proposes a blockchain-based secure and incentive FL (BESIFL) paradigm. BESIFL utilizes blockchain to achieve a fully decentralized FL system, integrating effective mechanisms for malicious node detection and incentive management in a unified framework. Experimental results demonstrate the effectiveness of BESIFL in improving FL performance through protection against malicious nodes, incentive management, and selection of credible nodes.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Review
Computer Science, Information Systems
Siva Sai, Vinay Chamola, Kim-Kwang Raymond Choo, Biplab Sikdar, Joel J. P. C. Rodrigues
Summary: Blockchain and AI technologies have independent applications in various industries and can be seamlessly integrated. AI algorithms can optimize the efficiency of medical blockchain storage and serve as knowledgeable gatekeepers. Blockchain can provide secure and diverse healthcare data for AI training. The integration of BC and AI has numerous use cases in healthcare, from disease prediction to pandemic management.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Cybernetics
Junchang Jing, Fei Li, Bin Song, Zhiyong Zhang, Kim-Kwang Raymond Choo
Summary: This study proposes a method for analyzing and identifying the diffusion trends of digital disinformation on online social networks. The method utilizes social situation analytics and a multilevel attention network to accurately identify and predict the spread of disinformation.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Yulin Liu, Debiao He, Zijian Bao, Huaqun Wang, Muhammad Khurram Khan, Kim-Kwang Raymond Choo
Summary: Vehicle-to-Grid (V2G) networks are potential solutions to energy and environmental challenges, but security is a key concern. To address the issue of private information leakage in V2G networks, we propose an efficient multilayered linkable ring signature scheme called Emularis, along with an anonymous payment scheme. Rigorous security analysis proves that Emularis ensures security and privacy requirements, while also outperforming existing schemes in terms of communication and computation costs.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2023)
Article
Geography, Physical
Xiaohan Zhang, Lizhe Wang, Jun Li, Wei Han, Runyu Fan, Sheng Wang
Summary: This study develops a method based on satellite remote sensing and deep learning to identify nearshore sediments using multispectral images and a quasi-analytical algorithm. The experiments demonstrate that the proposed method achieves high accuracy in signal point extraction and sediment classification.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Geography, Physical
Wei Han, Xiaohan Zhang, Yi Wang, Lizhe Wang, Xiaohui Huang, Jun Li, Sheng Wang, Weitao Chen, Xianju Li, Ruyi Feng, Runyu Fan, Xinyu Zhang, Yuewei Wang
Summary: Due to limited resources and environmental pollution, monitoring the geological environment has become essential for sustainable development. Remote sensing of the geological environment (GERS) provides an efficient and low-cost method for identifying geological elements. The integration of advanced machine learning and deep learning methods with multi-source RS images for GERS interpretation has achieved remarkable breakthroughs, but a systematic survey of these advances is lacking.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Computer Science, Information Systems
Yuanyuan Gao, Lei Zhang, Lulu Wang, Kim-Kwang Raymond Choo, Rui Zhang
Summary: In this paper, two new tools, quality-based aggregation method and extended dynamic contribution broadcast encryption (DConBE), are introduced. Based on these tools and local differential privacy, a privacy-preserving and reliable decentralized federated learning (FL) scheme is proposed to support batch joining/leaving of clients with minimal delay and high model accuracy.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2023)
Article
Computer Science, Information Systems
Feng Li, Jianfeng Ma, Yinbin Miao, Zhiquan Liu, Kim-Kwang Raymond Choo, Ximeng Liu, Robert H. Deng
Summary: Symmetric Searchable Encryption (SSE) schemes have been extensively explored for improved function, efficiency, and security. However, in real-world settings, additional functions such as forward and backward privacy and support for boolean search are needed. In this article, we propose the construction of Verifiable Boolean Search (VBS) over encrypted data and enhance it to achieve Forward and Backward privacy (VBS-FB). We also provide a formal proof of security and evaluate the performance using real-world datasets.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2023)
Article
Computer Science, Information Systems
Xinghua Li, Lizhong Bai, Yinbin Miao, Siqi Ma, Jianfeng Ma, Ximeng Liu, Kim-Kwang Raymond Choo
Summary: With the rise in popularity of location-based services, spatial keyword queries have become an important application. To address the issues of privacy leakage and network bandwidth overheads, we propose PSKF, a Privacy-preserving top-k Spatial Keyword query system based on Fog computing. By utilizing IR-tree and distributing subtrees among fog servers, we achieve efficient search and improve search efficiency. Formal security analysis shows that our proposed PSKF scheme achieves Indistinguishability under Known-Plaintext Attacks (IND-KPA), and extensive experiments demonstrate its efficiency and feasibility in practical applications.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2023)
Article
Computer Science, Information Systems
Jun Zhou, Shiying Chen, Kim-Kwang Raymond Choo, Zhenfu Cao, Xiaolei Dong
Summary: Real-time navigation is important in various applications, and preserving location privacy is a concern. Existing approaches use pseudonyms or fully homomorphic encryption (FHE), but they have limitations. This paper proposes an efficient multiparty delegated computation (MPDC) and a lightweight privacy-preserving real-time intelligent traffic navigation scheme (EPNS) to address these issues, providing secure evaluation and accurate prediction.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Engineering, Electrical & Electronic
Haoran Xu, Lizhe Wang, Wei Han, Yixin Yang, Jiabao Li, Yue Lu, Jun Li
Summary: Smart management of urban space is crucial for sustainable urban development, and unmanned aerial vehicles (UAVs) have greatly enhanced this management level. However, there is a lack of systematic investigation on the applications of UAVs in urban spatial management. This article provides a comprehensive review and summary, serving as a valuable reference for researchers and offering insights for future research directions.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
