检索结果-内蒙古大学图书馆

Comparative Study on Evaluating the Performance of Automated Bacterial Colony Counting with Available APP and Software on Generated Image Dataset

学校读者我要写书评

暂无评论

SN Computer Science 2025年第4期6卷 1-16页

作者： Arora, Prachi Tewary, Suman Krishnamurthi, Srinivasan Kumari, Neelam School of Computing Indian Institute of Information Technology Una (IIIT-Una) Una 177209 India Academy of Scientific and Innovative Research (AcSIR) Ghaziabad 201002 India Thin Film Coating Facility CSIR-Central Scientific Instruments Organisation (CSIR-CSIO) Sector 30-C Chandigarh 160030 India Materials Science and Sensor Applications CSIR-Central Scientific Instruments Organisation (CSIR-CSIO) Sector 30-C Chandigarh 160030 India Advanced Materials and Processes Division CSIR-National Metallurgical Laboratory (CSIR-NML) Jamshedpur 831007 India MTCC-Gene bank CSIR-Institute of Microbial Technology (CSIR-IMTECH) Sector 39-A Chandigarh 160039 India

Recent developments in image analysis and interpretation using computer vision techniques have shown potential for novel applications in microbiology laboratories to support the task of automation, aiming for faster and more reliable detection. Image processing techniques and machine learning models can be valuable tools in the screening process, helping technicians spend less time classifying no-growth results and quickly separating the categories for further analysis. In this context, creating a dataset of different bacterial strain images is a fundamental objective for developing and improving the accuracy of image processing models. Therefore, this manuscript acquired a dataset of water samples with different bacterial strain images on a petri dish following a standardized process with controlled conditions of positioning and lighting. The image acquisition device was also developed with a light-emitting diode (LED) and diffuser as a lighting source and a smartphone camera with 16 MP resolution. In addition, the present manuscript also focuses on comparing the accuracy of the proposed algorithm with the available apps and software using the custom-built imaging device. Hence, the resulting dataset consists of 100 images, which is helpful for researchers working in image processing to develop an algorithm for automated counting of bacterial colonies on petri dishes. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bacterial colonies Image datasets Image processing Imaging device Segmentation Water samples

FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Jian Lin, Zehui Lin, Wanyu Shi, Wenlong Yin, Xiaoyan Wang, Di Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong Department of Data Science and Artificial Intelligence The Department of Computing The Hong Kong Polytechnic University Hong Kong School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan430074 China School of Information Science and Technology Northwest University Xi’an China Division of Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology Saudi Arabia

Recently, the practical needs of "the right to be forgotten" in federated learning gave birth to a paradigm known as federated unlearning, which enables the server to forget personal data upon the client’s removal request. Existing studies on federated unlearning have primarily focused on efficiently eliminating the influence of requested data from the client’s model without retraining from scratch, however, they have rarely doubted the reliability of the global model posed by the discrepancy between its prediction performance before and after unlearning. To bridge this gap, we take the first step by introducing a novel malicious unlearning attack dubbed FedMUA, aiming to unveil potential vulnerabilities emerging from federated learning during the unlearning process. Specifically, clients may act as attackers by crafting malicious unlearning requests to manipulate the prediction behavior of the global model. The crux of FedMUA is to mislead the global model into unlearning more information associated with the influential samples for the target sample than anticipated, thus inducing adverse effects on target samples from other clients. To achieve this, we design a novel two-step method, known as Influential Sample Identification and Malicious Unlearning Generation, to identify and subsequently generate malicious feature unlearning requests within the influential samples. By doing so, we can significantly alter the predictions pertaining to the target sample by initiating the malicious feature unlearning requests, leading to the deliberate manipulation for the user adversely. Additionally, we design a new defense mechanism that is highly resilient against malicious unlearning attacks. Extensive experiments on three realistic datasets reveal that FedMUA effectively induces misclassification on target samples and can achieve an 80% attack success rate by triggering only 0.3% malicious unlearning requests. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

A Multi-Agent DRL-Based Framework for Optimal Resource Allocation and Twin Migration in the Multi-Tier Vehicular Metaverse

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Abishu, Hayla Nahom Seid, A. Mohammed Erbad, Aiman Getu, Tilahun M. Al-Fuqaha, Ala Guizani, Mohsen Division of Information and Computing Technology College of Science and Engineering Hamad Bin Khalifa University Doha Qatar College of Engineering Qatar University Doha Qatar MontréalQCH3C 1K3 Canada Abu Dhabi United Arab Emirates

Although multi-tier vehicular Metaverse promises to transform vehicles into essential nodes – within an interconnected digital ecosystem – using efficient resource allocation and seamless vehicular twin (VT) migration, this can hardly be achieved by the existing techniques operating in a highly dynamic vehicular environment, since they can hardly balance multi-objective optimization problems such as latency reduction, resource utilization, and user experience (UX). To address these challenges, we introduce a novel multi-tier resource allocation and VT migration framework that integrates Graph Convolutional Networks (GCNs), a hierarchical Stackelberg game-based incentive mechanism, and Multi-Agent Deep Reinforcement Learning (MADRL). The GCN-based model captures both spatial and temporal dependencies within the vehicular network;the Stackelberg game-based incentive mechanism fosters cooperation between vehicles and infrastructure;and the MADRL algorithm jointly optimizes resource allocation and VT migration in real time. By modeling this dynamic and multi-tier vehicular Metaverse as a Markov Decision Process (MDP), we develop a MADRL-based algorithm dubbed the Multi-Objective Multi-Agent Deep Deterministic Policy Gradient (MO-MADDPG), which can effectively balances the various conflicting objectives. Extensive simulations validate the effectiveness of this algorithm that is demonstrated to enhance scalability, reliability, and efficiency while considerably improving latency, resource utilization, migration cost, and overall UX by 12.8%, 9.7%, 14.2%, and 16.1%, respectively. © 2025, CC BY-NC-SA.

关键词： Markov processes

SELF-SUPERVISED DIFFUSION MRI DENOISING VIA ITERATIVE AND STABLE REFINEMENT

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Chenxu Kong, Qingpeng Jiang, Zihang Kevin Zhou, S. School of Biomedical Engineering Division of Life Sciences and Medicine USTC China MIRACLE Center Suzhou Institute for Advance Research USTC China State Key Laboratory of Precision and Intelligent Chemistry USTC China Key Laboratory of Intelligent Information Processing of CAS Institute of Computing Technology CAS China

Magnetic Resonance Imaging (MRI), including diffusion MRI (dMRI), serves as a "microscope" for anatomical structures and routinely mitigates the influence of low signal-to-noise ratio scans by compromising temporal or spatial resolution. However, these compromises fail to meet clinical demands for both efficiency and precision. Consequently, denoising is a vital preprocessing step, particularly for dMRI, where clean data is unavailable. In this paper, we introduce Di-Fusion, a fully self-supervised denoising method that leverages the latter diffusion steps and an adaptive sampling process. Unlike previous approaches, our single-stage framework achieves efficient and stable training without extra noise model training and offers adaptive and controllable results in the sampling process. Our thorough experiments on real and simulated data demonstrate that Di-Fusion achieves state-of-the-art performance in microstructure modeling, tractography tracking, and other downstream tasks. Code is available at https://***/FouierL/Di-Fusion. Copyright © 2025, The Authors. All rights reserved.

关键词： Signal to noise ratio

Beyond Radio: Het-Medium Networks and Its Cross-Medium Communication Paradigms for 6G

学校读者我要写书评

暂无评论

IEEE Network 2025年

作者： Wu, Mingming Han, Yufeng Xiao, Yue Gao, Yulan Li, Shiying Niyato, Dusit Karagiannidis, George K. University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China QianYuan National Laboratory Hangzhou310024 China KTH Royal Institute of Technology Division of Information Science and Engineering Stockholm100 44 Sweden Nanyang Technological University College of Computing and Data Science Singapore639798 Singapore Group Electrical and Computer Engineering Dept Thessaloniki54 124 Greece

In the evolving landscape of communication technologies, the integration of Heterogeneous Medium Networks (HetMNets) has emerged as a pivotal progression, signaling a departure from traditional, radio-centric paradigms. As we edge closer to the realization of 6G networks, understanding the intricate dynamics of cross-medium communication (CMC) becomes imperative. This article indicates the multifaceted nature of HetMNets and explores the transformative CMC paradigms shaping the roadmap toward 6G. First, we outline the key performance indicators (KPIs), potential scenarios, and the emerging technologies and applications of 6G wireless systems, which serve as the driving forces behind the development of HetMNets. Subsequently, various communication media are introduced, contrasting their propagation characteristics to underscore the indispensability of HetMNets for the 6G landscape. We then enumerate the general issues involving challenges/problems and potential technical solutions in HetMNets. Moreover, we present an air-sea coordinated CMC system model, serving as an example of HetMNets built upon CMC paradigms. Specifically, we tackle a power allocation challenge, optimizing the transmit power of both underwater acoustic and radio frequency (RF) communication media at the cross-medium bidirectional relay to curtail the outage probability. The corresponding solution highlights the efficacy of the proposed CMC paradigm in supporting the reliability and resource efficiency of HetMNets. © 1986-2012 IEEE.

关键词： Radio communication

Rapid quantum ground state preparation via dissipative dynamics

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhan, Yongtao Ding, Zhiyan Huhn, Jakob Gray, Johnnie Preskill, John Chan, Garnet Kin-Lic Lin, Lin Institute for Quantum Information and Matter California Institute of Technology United States Division of Physics Mathematics and Astronomy California Institute of Technology United States Department of Mathematics University of California Berkeley United States Department of Physics Arnold Sommerfeld Center for Theoretical Physics Ludwig-Maximilians-Universität München Germany Division of Chemistry and Chemical Engineering California Institute of Technology United States Department of Physics California Institute of Technology United States AWS Center for Quantum Computing United States Applied Mathematics and Computational Research Division Lawrence Berkeley National Laboratory United States

Inspired by natural cooling processes, dissipation has become a promising approach for preparing low-energy states of quantum systems. However, the potential of dissipative protocols remains unclear beyond certain commuting Hamiltonians. This work provides significant analytical and numerical insights into the power of dissipation for preparing the ground state of non-commuting Hamiltonians. For quasi-free dissipative dynamics, including certain 1D spin systems with boundary dissipation, our results reveal a new connection between the mixing time in trace distance and the spectral properties of a non-Hermitian Hamiltonian, leading to an explicit and sharp bound on the mixing time that scales polynomially with system size. For more general spin systems, we develop a tensor network-based algorithm for constructing the Lindblad jump operator and for simulating the dynamics. Using this algorithm, we demonstrate numerically that dissipative ground state preparation protocols can achieve rapid mixing for certain 1D local Hamiltonians under bulk dissipation, with a mixing time that scales logarithmically with the system size. We then prove the rapid mixing result for certain weakly interacting spin and fermionic systems in arbitrary dimensions, extending recent results for high-temperature quantum Gibbs samplers to the zero-temperature regime. Our theoretical approaches are applicable to systems with singular stationary states, and are thus expected to have applications beyond the specific systems considered in this study. © 2025, CC BY.

关键词： Hamiltonians

Multiple Deep-Belief-Network-Based Spectral-Spatial Classification of Hyperspectral Images

学校读者我要写书评

暂无评论

Tsinghua Science and technology 2019年第2期24卷 183-194页

作者： Atif Mughees Linmi Tao Pervasive Computing Division Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University

A deep-learning-based feature extraction has recently been proposed for HyperSpectral Images(HSI)classification. A Deep Belief Network(DBN), as part of deep learning, has been used in HSI classification for deep and abstract feature extraction. However, DBN has to simultaneously deal with hundreds of features from the HSI hyper-cube, which results into complexity and leads to limited feature abstraction and performance in the presence of limited training data. Moreover, a dimensional-reduction-based solution to this issue results in the loss of valuable spectral information, thereby affecting classification performance. To address the issue, this paper presents a Spectral-Adaptive Segmented DBN(SAS-DBN) for spectral-spatial HSI classification that exploits the deep abstract features by segmenting the original spectral bands into small sets/groups of related spectral bands and processing each group separately by using local DBNs. Furthermore, spatial features are also incorporated by first applying hyper-segmentation on the HSI. These results improved data abstraction with reduced complexity and enhanced the performance of HSI classification. Local application of DBN-based feature extraction to each group of bands reduces the computational complexity and results in better feature extraction improving classification accuracy. In general, exploiting spectral features effectively through a segmented-DBN process and spatial features through hyper-segmentation and integration of spectral and spatial features for HSI classification has a major effect on the performance of HSI classification. Experimental evaluation of the proposed technique on well-known HSI standard data sets with different contexts and resolutions establishes the efficacy of the proposed techniques,wherein the results are comparable to several recently proposed HSI classification techniques.

关键词： hyperspectral image classification segmentation deep belief network support vector machine

MS-Glance: Bio-Inspired Non-Semantic Context Vectors and Their Applications in Supervising Image Reconstruction

学校读者我要写书评

暂无评论

MS-Glance: Bio-Inspired Non-Semantic Context Vectors and The...

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Ziqi Gao Wendi Yang Yujia Li Lei Xing S. Kevin Zhou Division of Life Sciences and Medicine School of Biomedical Engineering University of Science and Technology of China (USTC) Hefei Anhui China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advance Research USTC Suzhou Jiangsu China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology China Department of Radiation Oncology Stanford University Stanford CA USA Key Laboratory of Precision and Intelligent Chemistry USTC CAS Hefei Anhui

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Non-semantic context information is crucial for visual recognition, as the human visual perception system first uses global statistics to process scenes rapidly before identifying specific objects. However, while semantic information is increasingly incorporated into computer vision tasks such as image reconstruction, non-semantic information, such as global spatial structures, is often overlooked. To bridge the gap, we propose a biologically informed non-semantic context descriptor, MS-Glance, along with the Glance Index Measure for comparing two images. A Global Glance vector is formulated by randomly retrieving pixels based on a perception-driven rule from an image to form a vector representing non-semantic global context, while a local Glance vector is a flattened local image window, mimicking a zoom in observation. The Glance Index is defined as the inner product of two standardized sets of Glance vectors. We evaluate the effectiveness of incorporating Glance supervision in two reconstruction tasks: image fitting with implicit neural representation (INR) and undersampled MRI reconstruction. Extensive experimental results show that MS-Glance outperforms existing image restoration losses across both natural and medical images. The code is available at https://***/Z7Gao/MSGlance.

关键词： Computer vision Visualization Magnetic resonance imaging Fitting Vectors Image restoration Indexes Image reconstruction Biomedical imaging Visual perception

Invoking an Efficient Deep Learning Approach for Real-Time Detection of False Data Injection Attacks

学校读者我要写书评

暂无评论

Invoking an Efficient Deep Learning Approach for Real-Time D...

IEEE Texas Power and Energy Conference (TPEC)

作者： Maymouna Ez Eddin Mohamed Massaoudi Haitham Abu-Rub Mohammad Shadmand Mohamed Abdallah Miroslav Bcgovic Ali Ghrayeb Department of Electrical and Computer Engineering Texas A&M University at Qatar Doha Qatar Department of Electrical and Computer Engineering Texas A&M University College Station USA Information and Computing Technology Division Hamad Bin Khalifa University Doha Qatar Department of Electrical and Computer Engineering University of Illinois at Chicago Chicago USA

ISBN: (数字)9798331541125

ISBN: (纸本)9798331541132

With the increasing complexity of power systems and their vulnerability to cyber-attacks, robust detection mechanisms are crucial for ensuring the grid's transient and steady-state stability and resiliency. This study introduces an efficient deep learning framework to detect false data injection attacks (FDIAs) in power systems. Leveraging the MATPOWER environment, we simulate a realistic power grid scenario to generate datasets comprising normal operations and various FDIA scenarios. Utilizing advanced deep learning techniques, including convolutional neural networks enhanced with channel attention mechanisms and transformer encoders, our model processes sequential power system data to discern subtle attack signatures from normal fluctuations. The proposed methodology employs a stratified k-fold cross-validation approach on resampled datasets to address class imbalance, ensuring robust model evaluation. The model's performance is meticulously assessed using accuracy metrics and confusion matrices, demonstrating its capability to effectively identify and differentiate between normal and compromised states in power systems. Results on the IEEE 39-bus and 300-bus systems highlight that this approach significantly enhances detection capabilities, achieving high accuracy and practical detection times of less than 2 milliseconds for the IEEE 39-bus system, which addresses the real-time requirements. These promising results suggest that such models can be pivotal for preemptive security measures and real-time monitoring of power grids.

关键词： Deep learning Attention mechanisms Accuracy Power system stability Transformers Real-time systems Power grids Data models Convolutional neural networks Cyberattack