检索结果-内蒙古大学图书馆

Spatiotemporal synchronous dynamic graph attention network for traffic flow forecasting

Neural Computing and Applications 2024年第22期36卷 13745-13759页

作者： Xia, Dawen Lin, Zhan Chen, Yan Hu, Yang Li, Yantao Li, Huaqing College of Data Science and Information Engineering Guizhou Minzu University Guiyang550025 China Department of Automotive Engineering Guizhou Traffic Technician and Transportation College Guiyang550008 China College of Computer Science Chongqing University Chongqing400044 China College of Electronic and Information Engineering Southwest University Chongqing400715 China

Traffic flow forecasting (TFF) is crucial for effective urban planning and traffic management. Most modeling approaches in TFF ignore the dynamic characteristics of the transportation network topology, which results in an inability to accurately capture the hidden spatiotemporal correlations. To this end, we investigate a Spatiotemporal Synchronous Dynamic Graph Attention Network (STS-DGAT) for TFF. STS-DGAT is composed of three parts: the dynamic feature enhancement (DFE) module, the spatiotemporal coupling (STC) module, and the temporal position embedding (TPE) module. Specifically, we discover the impact of traffic data features on TFF based on the DFE module, assign dynamic weights of various features for time steps, and adjust the intrinsic relevance of traffic data. Then, we propose the STC module to characterize the complex coupling relationships of road network nodes in spatial and temporal dimensions and the dynamic intrinsic interactions of spatiotemporal correlations. The STC module comprises a dynamic graph attention network (DGAT) and an adaptive gated temporal convolutional network (AGTCN). Deep characterization for the dynamic topology of road networks is mined by DGAT, which captures real-time dynamic spatial correlations, and hidden features in the nonlinear temporal dimension are extracted by AGTCN to learn long-term temporal dependency. Finally, we put forward a TPE module to incorporate temporal position information into spatiotemporal relationships and adaptively learn hidden features of individual nodes to understand spatiotemporal variation features effectively. Experimental results from four real-world datasets demonstrate that the STS-DGAT model outperforms other baseline models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： data Analytics

来源：评论

学校读者我要写书评

暂无评论

Bridging Optimal Transport and Jacobian Regularization by Optimal Trajectory for Enhanced Adversarial Defense 17th

Bridging Optimal Transport and Jacobian Regularization by ...

引用

17th Asian Conference on computer Vision, ACCV 2024

作者： M. Le, Binh Tariq, Shahroz S. Woo, Simon Department of Computer Science and Engineering Sungkyunkwan University Suwon Korea Republic of CSIRO’s Data61 Sydney Australia

ISBN: (纸本)9789819609628

Deep neural networks, particularly in vision tasks, are notably susceptible to adversarial perturbations. To overcome this challenge, developing a robust classifier is crucial. In light of the recent advancements in the robustness of classifiers, we delve deep into the intricacies of adversarial training and Jacobian regularization, two pivotal defenses. Our work is the first carefully analyzes and characterizes these two schools of approaches, both theoretically and empirically, to demonstrate how each approach impacts the robust learning of a classifier. Next, we propose our novel Optimal Transport with Jacobian regularization method, dubbed OTJR, bridging the input Jacobian regularization with the a output representation alignment by leveraging the optimal transport theory. In particular, we employ the Sliced Wasserstein distance that can efficiently push the adversarial samples’ representations closer to those of clean samples, regardless of the number of classes within the dataset. The SW distance provides the adversarial samples’ movement directions, which are much more informative and powerful for the Jacobian regularization. Our empirical evaluations set a new standard in the domain, with our method achieving commendable accuracies of 52.57% on CIFAR-10 and 28.36% on CIFAR-100 datasets under the AutoAttack. Further validating our model’s practicality, we conducted real-world tests by subjecting internet-sourced images to online adversarial attacks. These demonstrations highlight our model’s capability to counteract sophisticated adversarial perturbations, affirming its significance and applicability in real-world scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Machine Learning Security: The Role of Quantum-Enhanced Federated Learning 2

Revolutionizing Machine Learning Security: The Role of Quant...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Kannan, E. Ravikumar, S. Carmel Mary Belinda, M.J. Vijay, K. Vathani, Anstey Kannan, Sriram Vel Tech Rangarajan Dr. Sagunthala RD Institute of Science and Technology Department of Computer Science and Engineering Chennai India Saveetha Institute of Medical And Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr Sagunthala RD Institute of Science and Technology Department of Civil Engineering India Fidelity Investments Data Engineering Chennai India

ISBN: (纸本)9798331534950

In today's age of collaborative machine learning where data sharing happens across organizations and privacy becomes a real issue. Old-school methods of securing systems work, but tend to lack against popular new attacks. The research uses a novel approach that uses quantum computing to reimagine what privacy means. An article which deals with the combination of quantum technologies and federated learning systems, specifically discussing how it may set a new standard for data privacy. The plan is to use quantum key distribution and entanglement-based protocols in order to fortify the defences of collaborative machine learning systems against adversarial attacks or unauthorized access, according a consortium statement. The approach to quantum -enhanced federated learning presented provides a solution not only with secure improvements but also implementing more extreme circumstances in decentralised learning scenarios, such as challenges due to different data available and regulatory demands. This paper provides a theoretical benchmark for quantum federated learning and focuses on the underlying concepts leading to excellent security guarantees. Applications and simulations show that this framework can be used in practice with effectiveness. Furthermore, this work benchmarks the scalability of quantum federated learning for different classical and common machine-learning models. The results are a major step towards the goal of making more sophisticated privacy solutions available and allow to create secure, private-first workspace for collaborative machine learning. By leveraging the latest in quantum computing along with specialized tactics designed to combat rapidly evolving data protection threats, this approach will provide a strong foundation for future applications of shared machine learning within distributed quantum environments. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Public Decision-Making Analysis in Urban Heat Islands Based on Socioeconomic Modelling by Deep Learning Techniques

引用

Remote Sensing in Earth Systems sciences 2024年第1期8卷 108-117页

作者： Prakash, S. Wilson Kiruthigha, R. Yadav, Ajay Kumar Kanna, S. K. Rajesh Shaik, Khasimbee Krishna, B. Murali Department of Data Science and Business Systems SRM Institute of Science and Technology Chennai Kattankulathur India Department of Information Technology SRM Institute of Science and Technology Chennai Ramapuram India Department of Computer Application United Institute of Management UP Prayagraj 211010 India Department of Mechanical Engineering Rajalakshmi Institute of Technology Chennai India Department of Computer Science and Engineering Aditya University Andhra Pradesh Surampalem India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Urban heat island (UHI) effects, especially in highly urbanised areas, and greenhouse gas emissions from human activity are two elements that accelerate global climate change (GCC). Sustainable city planning and modification may benefit from the quantification of the surface UHI (SUHI) effect utilising land surface temperature (LST), local climate zones (LCZ), and deep learning methods like convolutional neural networks (CNN) and pix2pix. The findings show that socioeconomic variables account for 12–20% of variability in UHI intensity. In general, the contribution rate of urban economic scale is higher than that of population and industrial structure variables. The increase in urban economic expansion increased summertime heat discomfort. This research propose novel method in socioeconomic analysis based on urban heat pattern analysis with public healthcare system using decision-making with DL (deep learning) model. Input is collected as urban heat pattern dataset and processed for noise removal and normalisation. This data has been features are extracted and classified using convolutional fuzzy Q-Gaussian neural network and variational K-C-means regressive learning. The simulation analysis has been carried out based on training accuracy, average precision, recall, and F-measure. The proposed model attained average precision was 94%, recall was 90%, training accuracy was 97%, and F1-score was 92%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Decision-making Deep learning model Public healthcare system Socioeconomic analysis Urban heat pattern

来源：评论

学校读者我要写书评

暂无评论

Advanced Remote Sensing Techniques for Underwater Fin Whale Detection in the Indian Ocean 16

Advanced Remote Sensing Techniques for Underwater Fin Whale ...

引用

16th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2024

作者： Sanikommu, Vasavi Sura, Akshaya Chimirala, Pranavi Velagapudi Ramakrishna Siddhartha Engineering College Department of Artificial Intelligence and Data Science Andhra Pradesh India Velagapudi Ramakrishna Siddhartha Engineering College Department of Computer Science and Engineering Andhra Pradesh India

ISBN: (纸本)9798331505264

Accurate detection and tracking of cetaceans in the Indian Ocean remain some of the salient issues for marine conservation despite the abundant challenges that accompany the environment underwater. Such realistic avenues can go a long way in bridging the said challenges with advanced remote sensing technologies. In this study, hyperspectral imaging, satellite imagery, and thermal imaging combine to form an integrated system in whale detection. The hyperspectral imaging of whale skin provides spectral reflectance characteristics for detection under different oceanic conditions. Along with these, satellite imaging helps determine subsurface features while thermal imaging determines the thermal characteristics of whales. Machine learning algorithms analyze the data set amalgamation to enhance detection accuracy as well as reliability. The overall system effectively detected whales at the various depths and environmental conditions associated with the Indian Ocean. Hyperspectral imaging was sensitive to the turbidity levels of water and target reflectance, while the coastal blue band showed subsurface features of a whale. Thermal imaging also increased detection abilities in dim light as well. This three-in-one platform approached better than other methods with an accuracy of 0.96 and reliability by real-time whale monitoring. © 2024 IEEE.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Face Forgery Detection Based on Fine-Grained Clues and Noise Inconsistency

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 144-158页

作者： Zhang, Dengyong He, Ruiyi Liao, Xin Li, Feng Chen, Jiaxin Yang, Gaobo Changsha University of Science and Technology Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation the School of Computer and Communication Engineering Changsha410114 China Hunan University Changsha410082 China

Deepfake detection has gained increasing research attention in media forensics, and a variety of works have been produced. However, subtle artifacts might be eliminated by compression, and the convolutional neural networks (CNNs)-based detectors are invalidated for fake face images with compression. In this work, we propose a two-stream network for deepfake detection. We observed that high-frequency noise features and spatial features are inherently complementary to each other. Thus, both spatial features and high-frequency noise features are exploited for face forgery detection. Specifically, we design a double-frequency transformer module (DFTM) to guide the learning of spatial features from local artifact regions. To effectively fuse spatial features and high-frequency noise features, a dual-domain attention fusion module (DDAFM) is designed. We also introduce a local relationship constraint loss, which requires only image-level labels, for model training. We evaluate the proposed approach on five large-scale benchmark datasets, and extensive experimental results demonstrate the proposed approach outperforms most SOTA works. © 2024 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Effort-aware cross-project just-in-time defect prediction framework for mobile apps

引用

Frontiers of computer science 2022年第6期16卷 15-29页

作者： Tian CHENG Kunsong ZHAO Song SUN Muhammad MATEEN Junhao WEN School of Big Data and Software Engineering Chongqing UniversityChongqing401331China School of Computer Science Wuhan UniversityWuhan430072China Department of Computer Science Air University Multan CampusMultan60000Pakistan

As the boom of mobile devices,Android mobile apps play an irreplaceable roles in people’s daily life,which have the characteristics of frequent updates involving in many code commits to meet new ***-in-Time(JIT)defect prediction aims to identify whether the commit instances will bring defects into the new release of apps and provides immediate feedback to developers,which is more suitable to mobile *** the within-app defect prediction needs sufficient historical data to label the commit instances,which is inadequate in practice,one alternative method is to use the cross-project *** this work,we propose a novel method,called KAL,for cross-project JIT defect prediction task in the context of Android mobile *** specifically,KAL first transforms the commit instances into a high-dimensional feature space using kernel-based principal component analysis technique to obtain the representative ***,the adversarial learning technique is used to extract the common feature embedding for the model *** conduct experiments on 14 Android mobile apps and employ four effort-aware indicators for performance *** results on 182 cross-project pairs demonstrate that our proposed KAL method obtains better performance than 20 comparative methods.

关键词： kernel-based principal component analysis adversarial learning just-in-time defect prediction cross-project model

来源：评论

学校读者我要写书评

暂无评论

AI for Smart Agriculture - A Deep Learning Based Turmeric Leaf Disease Detection 9

AI for Smart Agriculture - A Deep Learning Based Turmeric Le...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Selvaraj, R. Devasena, M. S. Geetha Satheesh, T. Sathishkumar, C. Dr.N.G.P. Institute of Technology Department of Computer Science and Engineering Coimbatore India Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India Dr.N.G.P. Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Department of Computer Science and Engineering RVS Technical Campus-Coimbatore Coimbatore India

ISBN: (纸本)9798350377972

Plants is one of the major food sources for world population. In addition to that, some plants and their outcomes are used in food preparation. One of the plants which is widely used in foods and having huge medicinal value is turmeric. Curcuma long the botanically named spice turmeric has large anti-inflammatory properties, antioxidants, etc., the tropical perennial plant is cultivated worldwide. Diseases in plant leaves is one of the serious factors that affects the turmeric cultivation. Leaf disease reduces the production and it requires continuous monitoring to avoid total loss. Manual monitoring is challenging when the crop is planted in large fields. Due to industrial revolution and smart agriculture concepts, artificial intelligence- based disease detection procedure is presented in recent times. Thus, in this research work a deep learning-based turmeric leaf disease detection model is presented using AlexNet. The leaf disease classification model is experimented with our own dataset which includes diseases like Leaf Spot Disease, Leaf Blight, Leaf Rot, and Leaf Curl. The experimentation results provide the maximum accuracy of proposed leaf disease classification model as 95.5% which is better than traditional machine learning models. © 2024 IEEE.

关键词： AlexNet classification Deep learning Turmeric Leaf disease

来源：评论

学校读者我要写书评

暂无评论

Estimating Surface Soil Moisture based on Remote Sensing data and Crop Yield Classification using Machine Learning 9

Estimating Surface Soil Moisture based on Remote Sensing Dat...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Anuradha, G. Susrith, Maddi Siddhardha, Kondreddy Gnana Velagapudi Ramakrishna Siddhartha Engineering College Dept. of computer science and engineering Vijayawada India Velagapudi Ramakrishna Siddhartha Engineering College Dept. of Artificial Intelligence and Data Science Vijayawada India

ISBN: (纸本)9798350377972

Soil moisture plays a critical role in environmental monitoring and sustainable agricultural practices due to its significant impact on crop growth, water availability, and overall ecosystem health. Properly understanding and managing soil moisture is vital for efficient water usage, especially in agriculture. Traditional methods in measuring soil moisture have been confined to ground-based small-scale methods, which are high price due to high labor intensity and limited spatial coverage. This project addresses its limitation in the spatial view by integrating remote sensing data from the Sentinel-1 satellite. Sentinel-1 is particularly effective in monitoring the soil moisture as it captures data in all climate conditions. By combining the satellite data with Google Earth Engine (GEE) we create a soil moisture dataset. For analyzing the joint satellite and ground truth data, the machine learning technique using Random Forest (RF) is applied and classification of crop yield is done. © 2024 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Wild-Animal Detection near Roads using IoT Sensor and Optimization

Machine Learning based Wild-Animal Detection near Roads usin...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Simonthomas, S. Rohith, K. Shalini, K.Shantha Aarupadai Veedu Institute of Technology Department of Computer Science and Engineering Chennai India Aarupadai Veedu Institute of Technology Department of Intelligence and Data Science Chennai India

ISBN: (纸本)9798331539948

The increasing incidence of vehicle-animal collisions poses significant risks to both human and wildlife safety. To address this challenge, the implementation of IoT (Internet of Things) sensor networks for wild-animal detection near roads offers a promising solution. This paper explores the design and deployment of an IoT-based system aimed at detecting the presence of wild animals near roadways, thereby enhancing road safety and wildlife conservation. The proposed system utilizes a network of infrared (IR) sensors, motion detectors, and cameras strategically placed along road sections prone to wildlife crossings. These sensors continuously monitor the area, and upon detecting an animal, they transmit real-time data to a central processing unit via wireless communication protocols. The system then processes this data to generate immediate alerts for drivers through connected road signs or mobile applications, warning them of potential hazards ahead. Additionally, the collected data is stored and analyzed to understand animal movement patterns, which aids in making informed decisions about further preventive measures and the placement of wildlife crossings. The incorporation of machine learning algorithms improves the system's precision in distinguishing between different types of animals and minimizing false alarms. This IoT sensor network not only mitigates the risk of accidents but also contributes to the conservation of wildlife by preventing unnecessary fatalities. This project explores the use of Genetic Algorithms (GA) to optimize a detection system that can identify wild animals near roadsides. The paper summarize with a discussion on the effectiveness of the system, potential challenges in implementation, and outlines future pathways for research and innovation in this domain. © 2024 IEEE.

关键词： Traffic signs

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：