检索结果-内蒙古大学图书馆

Fundus Image Quality Assessment and Enhancement: a Systematic Review

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Heng Li, Haojin Ou, Mingyang Yu, Xiangyang Zhang, Xiaoqing Niu, Ke Fu, Huazhu Liu, Jiang Research Institute of Trustworthy Autonomous Systems SUSTech Shenzhen China Department of Computer Science and Engineering SUSTech Shenzhen China Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Computer School Beijing Information Science and Technology University Beijing China Singapore

As an affordable and convenient eye scan, fundus photography holds the potential for preventing vision impairment, especially in resource-limited regions. However, fundus image degradation is common under intricate imaging environments, impacting following diagnosis and treatment. Consequently, image quality assessment (IQA) and enhancement (IQE) are essential for ensuring the clinical value and reliability of fundus images. While existing reviews offer some overview of this field, a comprehensive analysis of the interplay between IQA and IQE, along with their clinical deployment challenges, is lacking. This paper addresses this gap by providing a thorough review of fundus IQA and IQE algorithms, research advancements, and practical applications. We outline the fundamentals of the fundus photography imaging system and the associated interferences, and then systematically summarize the paradigms in fundus IQA and IQE. Furthermore, we discuss the practical challenges and solutions in deploying IQA and IQE, as well as offer insights into potential future research directions. Copyright © 2025, The Authors. All rights reserved.

关键词： Photography

Symbolic Execution of MPI Programs with One-Sided Communications

学校读者我要写书评

暂无评论

Symbolic Execution of MPI Programs with One-Sided Communicat...

Asia-Pacific Conference on Software engineering

作者： Nenghui Hu Zheng Bian Ziqi Shuai Zhenbang Chen Yufeng Zhang College of Computer National University of Defense Technology China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology China State Key Laboratory of High Performance Computing National University of Defense Technology China College of Computer Science and Electronic Engineering Hunan University Changsha China

Message-passing interface (MPI) programs are non-deterministic and challenging to ensure correctness. The introduction of one-sided communications makes the problem of non-determinism more severe for MPI programs. This paper reports our in-progress work of symbolic execution for the MPI programs with one-sided communications. Our approach can cover the non-determinism caused by the inputs, one-sided communication, and message- passing operations of MPI programs. The preliminary evaluation's results indicate the promising of our approach.

关键词：

Deep Reinforcement Learning Empowered Activity-Aware Dynamic Health Monitoring systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ye, Ziqiaing Gao, Yulan Xiao, Yue Xiong, Zehui Niyato, Dusit National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China Chengdu611731 China School of Computer Science and Engineering Nanyang Technological University 639798 Singapore Information Systems Technology and Design Pillar Singapore University of Technology and Design 487372 Singapore

In smart healthcare, health monitoring utilizes diverse tools and technologies to analyze patients' real-time biosignal data, enabling immediate actions and interventions. Existing monitoring approaches were designed on the premise that medical devices track several health metrics concurrently, tailored to their designated functional scope. This means that they report all relevant health values within that scope, which can result in excess resource use and the gathering of extraneous data due to monitoring irrelevant health metrics. In this context, we propose Dynamic Activity-Aware Health Monitoring strategy (DActAHM) for striking a balance between optimal monitoring performance and cost efficiency, a novel framework based on Deep Reinforcement Learning (DRL) and SlowFast Model to ensure precise monitoring based on users' activities. Specifically, with the SlowFast Model, DActAHM efficiently identifies individual activities and captures these results for enhanced processing. Subsequently, DActAHM refines health metric monitoring in response to the identified activity by incorporating a DRL framework. Extensive experiments comparing DActAHM against three state-of-the-art approaches demonstrate it achieves 27.3% higher gain than the best-performing baseline that fixes monitoring actions over timeline. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

A Unified Modeling Framework for Automated Penetration Testing

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Yunfei Liu, Shixuan Wang, Wenhao Zhou, Changling Zhang, Chao Jin, Jiandong Zhu, Cheng National Key Laboratory of Information Systems Engineering National University of Defense Technology Hunan China Department of Intelligent Data Science College of Computer Science and Technology National University of Defense Technology Hunan China National University of Defense Technology Hunan China Tsinghua University Beijing China Computer Center Peking University Beijing China

The integration of artificial intelligence into automated penetration testing (AutoPT) has highlighted the necessity of simulation modeling for the training of intelligent agents, due to its cost-efficiency and swift feedback capabilities. Despite the proliferation of AutoPT research, there is a recognized gap in the availability of a unified framework for simulation modeling methods. This paper presents a systematic review and synthesis of existing techniques, introducing MDCPM to categorize studies based on literature objectives, network simulation complexity, dependency of technical and tactical operations, and scenario feedback and variation. To bridge the gap in unified method for multi-dimensional and multi-level simulation modeling, dynamic environment modeling, and the scarcity of public datasets, we introduce AutoPT-Sim, a novel modeling framework that based on policy automation and encompasses the combination of all sub dimensions. AutoPT-Sim offers a comprehensive approach to modeling network environments, attackers, and defenders, transcending the constraints of static modeling and accommodating networks of diverse scales. We publicly release a generated standard network environment dataset and the code of Network Generator. By integrating publicly available datasets flexibly, support is offered for various simulation modeling levels focused on policy automation in MDCPM and the network generator help researchers output customized target network data by adjusting parameters or fine-tuning the network generator. Copyright © 2025, The Authors. All rights reserved.

关键词： Intelligent agents

Unsatisfiable Core Based Constraint Solving Cache in Symbolic Execution

学校读者我要写书评

暂无评论

Unsatisfiable Core Based Constraint Solving Cache in Symboli...

Asia-Pacific Conference on Software engineering

作者： Ziqi Shuai Zhenbang Chen Yufeng Zhang Hengbiao Yu Ji Wang College of Computer National University of Defense Technology China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology China State Key Laboratory of High Performance Computing National University of Defense Technology China College of Computer Science and Electronic Engineering Hunan University Changsha China

Constraint solving stands out as a significant bot-tleneck in symbolic execution. Caching is a commonly adopted approach to alleviate this bottleneck. However, the cutting-edge caching technique targeting unsatisfiable constraints, known as unsatisfiable core caching, primarily involves checking whether the constraint being solved contains an unsatisfiable core that has been previously collected. Such straightforward reuse frequently proves less effective in numerous scenarios. In this paper, we present a novel method to enhance the utilization of unsatisfiable cores. By excavating unsatisfiable cores, our method can compute an easily solvable over-approximation that tends to be unsatis-fiable for each constraint, which facilitates the determination of the satisfiability of the original constraint. We implemented our method on KLEE symbolic executor. The evaluation results on 27 real-world programs are encouraging.

关键词：

Hidden high-risky states identification from routine urban traffic

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Shiyan Bai, Mingyang Guo, Shengmin Gao, Jianxi Sun, Huijun Gao, Ziyou Li, Daqing School of Reliability and Systems Engineering Beihang University Beijing100191 China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China Department of Computer Science Rensselaer Polytechnic Institute TroyNY12180 United States School of Systems Science Beijing Jiaotong University Beijing100044 China

One of the core risk management tasks is to identify hidden high-risky states that may lead to system breakdown, which can provide valuable early warning knowledge. However, due to high dimensionality and nonlinear interaction embedded in large-scale complex systems like urban traffic, it remains challenging to identify hidden high-risky states from huge system state space where over 99% of possible system states are not yet visited in empirical data. Based on maximum entropy model, we infer the underlying interaction network from complicated dynamical processes of urban traffic, and construct system energy landscape. In this way, we can locate hidden high-risky states that have never been observed from real data. These states can serve as risk signals with high probability of entering hazardous minima in energy landscape, which lead to huge recovery cost. Our finding might provide insights for complex system risk management. Significance Statement Hidden high-risky states are lethal system states with catastrophic consequences for large-scale complex systems. Existing methods for identifying hidden high-risky states face challenges in routine urban traffic, where over 99% of possible system states are not yet visited in empirical data. Based on large-scale traffic-speed data, we build a least-structured network entropy model that captures intricate traffic interactions. This model can generate the entire state space and help the identification of hidden high-risky states that may lead to extreme events. Our results suggest a new way to provide reliable early warning signals for system breakdown based on critical risk scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Large scale systems

LCINet: Local Cross-position Interaction Network for Oracle Bone Inscriptions Recognition

学校读者我要写书评

暂无评论

LCINet: Local Cross-position Interaction Network for Oracle ...

International Joint Conference on Neural Networks (IJCNN)

作者： Qingyang Sun Xiaoqing Zhang Chenlu Gui Hanxi Sun Tingsheng Cai Yan Hu Jigen Tang Jiang Liu Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China School of Humanities and Social Sciences Southern University of Science and Technology Shenzhen China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Oracle Bone Inscriptions (OBIs) are a type of ancient Chinese hieroglyphs, which are precursors of many Asian characters. Automatic OBIs recognition can assist archaeologists in understanding the history and evolution of hieroglyphs. Recently, deep learning methods have been gradually applied to OBIs recognition, but these methods often fail to leverage the glyphological feature information of oracle bone characters. In this paper, we propose a novel Local Cross-position Interaction (LCI) module, which dynamically adjusts the relative importance of feature maps in convolutional neural networks (CNNs) by exploiting the potential of the glyphological information. LCI extracts the glyphological context information by orientation pooling, then constructs the local dependencies between glyphological context features via a cross-position interaction. Subsequently, we combine the LCI module with the residual module to form the Residual-LCI module and then build an LCINet for automatic OBIs recognition by stacking multiple Residual-LCI modules. In addition, we construct an OBIs dataset named OBI316 to verify the effectiveness of LCINet, which will be released soon. The comprehensive experiments on the OBI316 dataset demonstrate that our LCINet outperforms baselines and state-of-the-art attention-based networks. The CIFAR datasets are used to further demonstrate the generalization ability of our method.

关键词： Deep learning Stacking Neural networks Bones Feature extraction Complexity theory Character recognition

Direct Truncation and Routh Approximation Assisted Reduced Order Modelling of Islanded Microgrid

学校读者我要写书评

暂无评论

Direct Truncation and Routh Approximation Assisted Reduced O...

IEEE Industry Applications Society Annual Meeting (IAS)

作者： Richa Chaudhary V. P. Singh Akhilesh Mathur U. K. Yadav Krishna Murari Sukumar Kamalasadan Department of Electrical Engineering Malaviya National Institute of Technology Jaipur Rajasthan India Electrical Engineering and Computer Science Department The University of Toledo Toledo Ohio USA Department of Electrical Engineering Power Energy and Intelligent Systems Laboratory EPIC University of North Carolina at Charlotte Charlotte NC USA

ISBN: (数字)9798350372717

ISBN: (纸本)9798350372724

Microgrid (MG) networks, with their diverse energy sources and storage systems, represent complex higher-order systems (HOS). Analyzing such networks is challenging due to the uncertainty associated with energy sources like solar and wind power. To address this complexity, reduced-order models (ROMs) are essential, achieved through order reduction techniques. This article presents a method to reduce the eighth-order transfer function of an islanded microgrid to a second-order model. The reduction involves truncation reduction technique (TRT) for the numerator and Routh approximation reduction technique (RART) for the denominator. A comparative analysis is conducted between the original higher-order islanded microgrid system and its ROM. The comparison includes various error indices to determine the effectiveness of the ROM. Graphical representations of impulse, Nichols, step, Nyquist, and Bode responses are provided for both the original system and the ROM to visually compare their performances. This study demonstrates the practical application of mixed reduction techniques to simplify complex microgrid models, making them more manageable for analysis and design purposes.

关键词： Uncertainty Industry applications Transfer functions Microgrids Wind power generation Reduced order systems Complexity theory Time-domain analysis Read only memory Energy storage

Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Li, Ping Zhang, Yu Yuan, Li Xiao, Huaxin Lin, Binbin Xu, Xianghua School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Electrical and Computer Engineering Peking University Beijing China College of Systems Engineering National University of Defense Technology Changsha China College of Computer Science Zhejiang University Hangzhou China

Unsupervised Video Object Segmentation (VOS) aims at identifying the contours of primary foreground objects in videos without any prior knowledge. However, previous methods do not fully use spatial-temporal context and fail to tackle this challenging task in real-time. This motivates us to develop an efficient Long-Short Temporal Attention network (termed LSTA) for unsupervised VOS task from a holistic view. Specifically, LSTA consists of two dominant modules, i.e., Long Temporal Memory and Short Temporal Attention. The former captures the long-term global pixel relations of the past frames and the current frame, which models constantly present objects by encoding appearance pattern. Meanwhile, the latter reveals the short-term local pixel relations of one nearby frame and the current frame, which models moving objects by encoding motion pattern. To speedup the inference, the efficient projection and the locality-based sliding window are adopted to achieve nearly linear time complexity for the two light modules, respectively. Extensive empirical studies on several benchmarks have demonstrated promising performances of the proposed method with high © 2023, The Authors. All rights reserved.

关键词： Pixels