检索结果-内蒙古大学图书馆

FireXnet: an explainable AI-based tailored deep learning model for wildfire detection on resource-constrained devices

引用

Fire Ecology 2023年第1期19卷 1-19页

作者： Ahmad, Khubab Khan, Muhammad Shahbaz Ahmed, Fawad Driss, Maha Boulila, Wadii Alazeb, Abdulwahab Alsulami, Mohammad Alshehri, Mohammed S. Ghadi, Yazeed Yasin Ahmad, Jawad Faculty of Engineering and Technology Multimedia University Melaka Malaysia School of Computing Engineering and the Built Environment Edinburgh Napier University Edinburgh UK Department of Cyber Security Pakistan Navy Engineering College NUST Karachi Pakistan Robotics and Internet of Things Laboratory Prince Sultan University Riyadh Saudi Arabia RIADI Laboratory National School of Computer Sciences University of Manouba Manouba Tunisia Department of Computer Science College of Computer Science and Information Systems Najran University Najran Saudi Arabia Department of Software Engineering Computer Science Al Ain University Abu Dhabi United Arab Emirates

Forests cover nearly one-third of the Earth’s land and are some of our most biodiverse ecosystems. Due to climate change, these essential habitats are endangered by increasing wildfires. Wildfires are not just a risk to the environment, but they also pose public health risks. Given these issues, there is an indispensable need for efficient and early detection methods. Conventional detection approaches fall short due to spatial limitations and manual feature engineering, which calls for the exploration and development of data-driven deep learning solutions. This paper, in this regard, proposes 'FireXnet', a tailored deep learning model designed for improved efficiency and accuracy in wildfire detection. FireXnet is tailored to have a lightweight architecture that exhibits high accuracy with significantly less training and testing time. It contains considerably reduced trainable and non-trainable parameters, which makes it suitable for resource-constrained devices. To make the FireXnet model visually explainable and trustable, a powerful explainable artificial intelligence (AI) tool, SHAP (SHapley Additive exPlanations) has been incorporated. It interprets FireXnet’s decisions by computing the contribution of each feature to the prediction. Furthermore, the performance of FireXnet is compared against five pre-trained models — VGG16, InceptionResNetV2, InceptionV3, DenseNet201, and MobileNetV2 — to benchmark its efficiency. For a fair comparison, transfer learning and fine-tuning have been applied to the aforementioned models to retrain the models on our dataset. The test accuracy of the proposed FireXnet model is 98.42%, which is greater than all other models used for comparison. Furthermore, results of reliability parameters confirm the model’s reliability, i.e., a confidence interval of [0.97, 1.00] validates the certainty of the proposed model’s estimates and a Cohen’s kappa coefficient of 0.98 proves that decisions of FireXnet are in considerable accordance with t

关键词：

来源：评论

学校读者我要写书评

暂无评论

Clustering-Based Resource Management for Consumer Cost Optimization in IoT Edge computing Environments

引用

IEEE Transactions on Consumer Electronics 2024年 1-1页

作者： Denden, Mohsen Jemmali, Mahdi Boulila, Wadii Soni, Mukesh Khan, Faheem Ahmad, Jawad Department of Computer and Information Technologies College of Telecommunication and Information CTI Riyadh Saudi Arabia Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah UAE Robotics and Internet-of-Things Laboratory Prince Sultan University Riyadh Saudi Arabia Department of CSE University Centre for Research and Development Chandigarh University Mohali Punjab- India Department of Computer Engineering Gachon University Seongnam-si South Korea School of Computing Engineering and the Built Environment Edinburgh Napier University U.K

Edge computing emerges as a pivotal model in the era of next-generation consumer electronics and the emerging challenges of multimodal data-driven decision-making. Specifically, edge computing offers an open computing architecture for the vast and diverse consumer multimodal data generated by mobile computing and internet of Things (IoT) technologies. While edge computing is instrumental in optimizing latency and bandwidth control in processing consumer multimodal data, the viability of employing edge resources is complicated by high service costs and the complexities of managing multimodal data diversity. This study introduces an innovative optimization method for distributing multimodal data on edge storage, considering both the I/O (input/output) speed and the overall distribution cost. The core part of our approach is the deployment of intelligent algorithms that ensure equitable data distribution across storage servers, thus eliminating unused space and reducing extra costs. Given the complexity of this NP-hard (non-deterministic polynomial-time) challenge, our study reveals a unique model incorporating an edge-broker component in combination with novel algorithms. The proposed algorithms aim to harmonize data distribution and reduce resource allocation expenses in a multimodal edge environment. Our proposed approach achieves excellent results, highlighting the efficacy of the proposed algorithms in several parameters such as makespan, cost, multimodal data security, and total processing time. Empirical tests reveal that the BCA (Best Clustering Algorithm) performs best, achieving a minimum load balancing rate of 92.2%, an average variance of 0.04, and an average run time of 0.56 seconds. IEEE

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Achieving Distributed and Privacy-Preserving Cross-Chain Transactions in Account-Model Blockchain Systems

Achieving Distributed and Privacy-Preserving Cross-Chain Tra...

引用

2023 IEEE International Conference on Metaverse computing, Networking and Applications, MetaCom 2023

作者： Zhang, Chuan Wang, Weijie Zhang, Weiting Nie, Jiangtian Liang, Jinwen Zhu, Liehuang Beijing Institute of Technology School of Cyberspace Science and Technology Beijing China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Guangdong China Beijing Institute of Technology School of Computer Science & Technology Beijing China Beijing Jiaotong University School of Electronic and Information Engineering Beijing China Nanyang Technological University School of Computer Science and Engineering Singapore Hong Kong Polytechnic University Department of Computing Hong Kong

ISBN: (纸本)9798350333336

Cross-Chain is an emerging technology to enable transaction circulation across different blockchain systems, breaking down transaction isolation among decentralized ecosystems. Existing cross-chain solutions are often constructed based on centralized trusted third parties, which introduce additional threats to users' identities due to potentially compromised risks on the centralized third parties. To exclude the single-point compromised risk in centralized systems, this paper focuses on a fully decentralized scenario and develops a distributed cross-chain transaction scheme, which enables cross-chain transaction exchanges while ensuring the unlinkability between payees and payers. Specifically, we first propose a cross-chain cryptocurrency exchange scheme by leveraging Ethereum's smart contracts, which achieves transaction exchanges in decentralized settings. Then, we leverage zero-knowledge succinct non-interactive argument of knowledge (i.e., zk-SNARKs) to explore a privacy-preserving method for cross-chain transactions in account-model blockchain systems, such that the unlinkability between payees and payers and the privacy of cross-chain participants can be guaranteed. security analysis and experimental evaluations demonstrate that the proposed scheme achieves the security goal at acceptable costs. © 2023 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Solving partial differential equations based on preconditioning-pretraining physics-informed neural network

引用

computer Physics Communications 2025年 312卷

作者： Wang, Zihan Hu, Ziyue Yang, Mingwei Dong, Yalin Huang, Wenlong Ren, Haijun School of Computer Science and Technology Anhui Engineering Laboratory for Industrial Internet Intelligent Applications and Security Anhui University of Technology Anhui Ma'anshan243002 China Department of Mechanical Engineering The University of Akron AkronOH44325 United States CAS Key Laboratory of Geospace Environment Department of Engineering and Applied Physics School of Physical Sciences University of Science and Technology of China Anhui Hefei230026 China

Physics-Informed Neural Network (PINN) is a deep learning framework that has been widely employed to solve spatial-temporal partial differential equations (PDEs) across various fields. However, recent numerical experiments indicate that the vanilla-PINN often struggles with PDEs featuring high-frequency solutions or strong nonlinearity. To enhance PINN's performance, we propose a novel strategy called the Preconditioning-Pretraining Physics-Informed Neural Network (PP-PINN). This approach involves transforming the original task into a new system characterized by low frequency and weak nonlinearity over an extended time scale. The transformed PDEs are then solved using a pretraining approach. Additionally, we introduce a new constraint termed "fixed point", which is beneficial for scenarios with extremely high frequency or strong nonlinearity. To demonstrate the efficacy of our method, we apply the newly developed strategy to three different equations, achieving improved accuracy and reduced computational costs compared to previous approaches which incorporate the pretraining technique. The effectiveness and interpretability of our PP-PINN are also discussed, emphasizing its advantages in tackling high-frequency solutions and strong nonlinearity, thereby offering insights into its broader applicability in complex mathematical modeling. © 2025 Elsevier B.V.

关键词： High frequency solution Physics informed neural network Preconditioning-pretraining Strong nonlinearity

来源：评论

学校读者我要写书评

暂无评论

A BTN-Based Method for Multi-Entity Bitcoin Transaction Analysis and Influence Assessment

引用

Distributed Ledger Technologies: Research and Practice 2024年第4期3卷 1-23页

作者： Yan Wu Liuyang Zhao Jia Zhang Leilei Shi Lu Liu John Panneerselvam Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace Jiangsu University Zhengjiang Jiangsu China and School of Computer Science and Communication Engineering Jiangsu University Zhengjiang Jiangsu China School of Computer Science and Communication Engineering Jiangsu University Zhengjiang Jiangsu China Department of Computer Science University of Exeter Exeter UK School of Computing and Mathematic Sciences University of Leicester Leicester UK

Bitcoin transaction analysis is valuable for examining Bitcoin events. However, most of the existing methods are inadequate for dealing with transactions involving multiple entities. Furthermore, existing Bitcoin transaction analysis methods neglect to evaluate the influence of different entities on a Bitcoin event. This article aims to overcome such limitations by introducing a novel method for multi-entity Bitcoin transaction analysis along with proposing a method for multi-entity influence assessment based on the Bitcoin transaction network (BTN) model. To overcome the loss of tracking information, a Bitcoin gene operation named compound dyeing is devised and incorporated into the BTN simulation. After obtaining the simulation results, a method for multi-entity transaction behavior analysis is presented to identify and visualize the interactions among entities precisely and effectively. Furthermore, four influence indices with suitable visualization methods are proposed based on the features of the BTN to measure the business and trading influences of different entities. A real-world case study, the *** coin loss event, is analyzed to demonstrate the effectiveness and efficiency of the proposed methods.

关键词： Blockchain computer forensics Bitcoin

来源：评论

学校读者我要写书评

暂无评论

Event-Guided Attention Network for Low Light Image Enhancement

Event-Guided Attention Network for Low Light Image Enhanceme...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Qiaobin Wang Haiyan Jin Haonan Su Zhaolin Xiao Department of Computer Science and Engineering Engineering Research Center Shaanxi Key Laboratory for Network Computing and Security Technology Human-Machine Integration Intelligent Robot Shaanxi University Xi'an University of Technology

In the low-light conditions, images are corrupted by low contrast and severe noise, but event cameras can capture event streams with clear edge structures. Therefore, we propose an Event-Guided Attention Network for Low-light Image Enhancement (EGAN) using a dual branch Network and recover clear structure with the guide of events. To overcome the lack of paired training datasets, we first synthesize the dataset containing low-light event streams, low-light images, and the ground truth (GT) normal-light images. Then, we develop an end-to-end dual branch network consisting of a Image Enhancement Branch (IEB) and a Gradient Reconstruction Branch (GRB). The GRB branch reconstructs image gradients using events, and the IEB enhances low-light images using reconstructed gradients. Moreover, we develops the Attention based Event-Image Feature Fusion Module (AEIFFM) which selectively fuses the event and low-light image features using the spatial and channel attention mechanism, and the fused features are concatenated into the IEB and GRB, which respectively generate the enhanced images with clear structure and more accurate gradient images. Extensive experiments on synthetic and real datasets demonstrate that the proposed EGAN produces visually more appealing enhancement images, and achieves a good performance in structure preservation and denoising over state-of-the-arts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network

arXiv

引用

arXiv 2024年

作者： Zhang, Quan Wang, Lei Patel, Vishal M. Xie, Xiaohua Lai, Jianhuang School of Computer Science and Engineering Sun Yat-Sen University China Guangdong China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Department of Electrical and Computer Engineering Johns Hopkins University United States

Existing person re-identification methods have achieved remarkable advances in appearance-based identity association across homogeneous cameras, such as ground-ground matching. However, as a more practical scenario, aerial-ground person re-identification (AGPReID) among heterogeneous cameras has received minimal attention. To alleviate the disruption of discriminative identity representation by dramatic view discrepancy as the most significant challenge in AGPReID, the view-decoupled transformer (VDT) is proposed as a simple yet effective framework. Two major components are designed in VDT to decouple view-related and view-unrelated features, namely hierarchical subtractive separation and orthogonal loss, where the former separates these two features inside the VDT, and the latter constrains these two to be independent. In addition, we contribute a large-scale AGPReID dataset called CARGO, consisting of five/eight aerial/ground cameras, 5,000 identities, and 108,563 images. Experiments on two datasets show that VDT is a feasible and effective solution for AGPReID, surpassing the previous method on mAP/Rank1 by up to 5.0%/2.7% on CARGO and 3.7%/5.2% on AG-ReID, keeping the same magnitude of computational complexity. Our project is available at https://***/LinlyAC/VDT-AGPReID. © 2024, CC BY.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Risk Assessment for Nonlinear Cyber-Physical Systems under Stealth Attacks

arXiv

引用

arXiv 2024年

作者： Chen, Guang Sun, Zhicong Ding, Yulong Yang, Shuang-Hua Department of Mechanical and Energy Engineering Southern University of Science and Technology China Department of Civil and Environmental Engineering Hong Kong Polytechnic University Hong Kong Institute of Advanced Computing and Digital Engineering Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet SUSTech Shenzhen518055 China Department of Computer Science and Engineering SUSTech Shenzhen518055 China Department of Computer Science University of Reading United Kingdom

Stealth attacks pose potential risks to cyber-physical systems because they are difficult to detect. Assessing the risk of systems under stealth attacks remains an open challenge, especially in nonlinear systems. To comprehensively quantify these risks, we propose a framework that considers both the reachability of a system and the risk distribution of a scenario. We propose an algorithm to approximate the reachability of a nonlinear system under stealth attacks with a union of standard sets. Meanwhile, we present a method to construct a risk field to formally describe the risk distribution in a given scenario. The intersection relationships of system reachability and risk regions in the risk field indicate that attackers can cause corresponding risks without being detected. Based on this, we introduce a metric to dynamically quantify the risk. Compared to traditional methods, our framework predicts the risk value in an explainable way and provides early warnings for safety control. We demonstrate the effectiveness of our framework through a case study of an automated warehouse. Copyright © 2024, The Authors. All rights reserved.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Prediction of exosomal piRNAs based on deep learning for sequence embedding with attention mechanism

Prediction of exosomal piRNAs based on deep learning for seq...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Liu, Yajun Ding, Yulian Li, Aimin Fei, Rong Guo, Xie Wu, Fangxiang Xi'an University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China University of Saskatchewan Division of Biomedical Engineering Saskatoon Canada Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an China University of Saskatchewan Division of Biomedical Engineering Department of Computer Science Department of Mechanical Engineering Saskatoon Canada

ISBN: (纸本)9781665468190

PIWI-interacting RNAs (piRNAs) are a type of small non-coding RNAs which bind with the PIWI proteins to exert biological effects in various regulatory mechanisms. A growing amount of evidence reveals that exosomal piRNAs are potential biomarkers for diagnosis and treatment of complex diseases. Effective methods for the prediction of exosomal piRNAs are the foundation of piRNA functional research. In this study, we propose an end-to-end deep network for identifying exosomal piRNAs based on features learned from natural language processing (NLP) models for sequence embedding with attention mechanism. First, a benchmark dataset is constructed by processing piRNA subcellular localization annotated data and sequence data. Moreover, bagging positive unlabeled learning is applied to get the reliable negative set. Finally, we treat a piRNA sequence as a sentence and its k-mer subsequence as a token. Sequence embedding models with self-attention mechanism is designed to extract features from exosome piRNA sequences, which are used for the prediction task. Compared with three competing methods, our model achieves the best performance and reveals the key factors of exosomal piRNA sequences by the attention mechanism. Our model characterizes exosomal piRNAs and could be beneficial for researchers to investigate exosomal piRNAs' functions. © 2022 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning

arXiv

引用

arXiv 2025年

作者： Li, Ziang Zhang, Hongguang Wang, Juan Chen, Meihui Hu, Hongxin Yi, Wenzhe Xu, Xiaoyang Yang, Mengda Ma, Chenjun Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China Shanghai Innovation Institute China Ant Group China Department of Computer Science and Engineering University at Buffalo SUNY United States

Model Inversion Attacks (MIAs) aim to reconstruct private training data from models, leading to privacy leakage, particularly in facial recognition systems. Although many studies have enhanced the effectiveness of white-box MIAs, less attention has been paid to improving efficiency and utility under limited attacker capabilities. Existing black-box MIAs necessitate an impractical number of queries, incurring significant overhead. Therefore, we analyze the limitations of existing MIAs and introduce Surrogate Model-based Inversion with Long-tailed Enhancement (SMILE), a high-resolution oriented and query-efficient MIA for the black-box setting. We begin by analyzing the initialization of MIAs from a data distribution perspective and propose a long-tailed surrogate training method to obtain high-quality initial points. We then enhance the attack’s effectiveness by employing the gradient-free black-box optimization algorithm selected by NGOpt. Our experiments show that SMILE outperforms existing state-of-the-art black-box MIAs while requiring only about 5% of the query overhead. Our code is available at https://***/L1ziang/SMILE. Copyright © 2025, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：