检索结果-内蒙古大学图书馆

Retrieval and validation of long-term aerosol optical depth from AVHRR data over China

International Journal of Digital Earth 2022年第1期15卷 1817-1832页

作者： Chunlin Jin Yong Xue Xingxing Jiang Shuhui Wu Yuxin Sun School of Environment and Spatial Informatics China University of Mining and TechnologyXuzhouPeople’s Republic of China School of Computing and Engineering College of Science and EngineeringUniversity of DerbyDerbyUK

Advanced Very High Resolution Radiometer(AVHRR)onboard National Oceanic and Atmospheric Administration(NOAA)satellites can provide over 40 years of global remote sensing observations,which can be used to retrieve long-term aerosol optical depth(AOD).This is of great significance to the study of global climate *** this paper,we proposed an algorithm to jointly calculate AOD and land surface properties from AVHRR *** assumptions that AOD doesn’t vary in adjacent space and earth surface property doesn’t vary in two days,the algorithm considered non-Lambertian surface reflection based on the shape of bidirectional reflectance distribution function(BRDF shape)and obtained AOD and surface property by optimal estimation(OE)*** algorithm has been applied to NOAA-7,9,11,14,16,18,and 19 satellites and AVHRR-retrieved AOD with 5×10 km over China(15°–60°N,70°–140°E)has been obtained from 1982 to *** of AVHRR-retrieved AOD against AErosol RObotic NETwork(AERONET)(in and around China)and China Aerosol Remote Sensing Network(CARSNET)AOD show good consistency with 62.62%points within the uncertainty ofΔτ=±(0.05+0.25τ)and root-mean-square error(RMSE)of *** comparison of the monthly mean AOD of multiple AOD datasets in the‘Beijing’,‘Dalanzadgad’,‘NCU_Taiwan’and‘Kanpur’stations shows that the results of the algorithm are *** yearly averaged AOD data also has similar agreements with MERRA-2(The Modern-Era Retrospective analysis for Research and Applications,Version 2)and AVHRRDB data(AVHRR‘Deep Blue’aerosol data set).The multi-year mean correlation coefficient is 0.70 and 0.61 and the percentages within the uncertainty are 80.01%and 67.29%compared with MERRA-2 AOD and AVHRRDB AOD respectively.

关键词： Long-term AOD AVHRR joint retrieval BRDF shape

来源：评论

学校读者我要写书评

暂无评论

Incipient Fault Detection with Jointly Optimized Health Indicators and Fault Thresholds via Convex-Optimization 5

Incipient Fault Detection with Jointly Optimized Health Indi...

引用

5th International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2024

作者： Li, Xiaochuan Zhen, Shengbing Mba, David School of Electrical Engineering and Automation Hefei University of Technology Hefei China Birmingham City University Faculty of Computing Engineering and the Build Environment United Kingdom

ISBN: (纸本)9798331529192

Machine health monitoring plays a key role in the reliable and efficient operation of industrial processes by the provision of timely fault detection and prognostic supports for maintenance decisions. Health indicator (HI) construction provides a simple way to realize machine health monitoring. In recent years, convex weight learning data fusion methods have been preferred for incipient fault detection. However, the existing weight learning approaches treat HI construction and fault threshold determination as two separate tasks in that a HI is firstly established through optimizing an objective function and a HI threshold is then determined statistically. Without the joint determination of a HI and its detection threshold, these methods may not be sensitive enough for incipient faults. To solve this problem, this study proposes a new convex weight learning data fusion model that realizes the joint assessment of a HI and its fault threshold, providing a more sensitive interpretable-HI for incipient faults. To form a sensitive yet stable HI, a novel objective function and its constraints are put forward, and the optimized model weights are used to construct a monitoring HI and its threshold simultaneously. Besides, to handle non-Gaussian distributed data and improve model explainability, kernel density estimation (KDE) was adopted for computing detection thresholds. The proposed fault detection method requires no prior knowledge about the time of fault initiation and can be implemented online to localize informative frequency bands. Benchmarking against state-of-the-art methods, we used the proposed weight learning model to analyze both process and vibration data sets. We show that the proposed method greatly improves fault detection in terms of sensitivity and achieves a satisfactory rate of false alarms. We also show that the introduced model possesses interpretability when it is employed for fault detection based on vibration signals. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Dynamic Surface-enabled Air Quality Evaluation 7

Dynamic Surface-enabled Air Quality Evaluation

引用

7th International Conference on Contemporary computing and Informatics, IC3I 2024

作者： Gurupriya, M. Rahul Karthikeyan, B. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Cse Karnataka Bengaluru India Vellore Institute of Technology School of Electronics Engineering Vellore India

ISBN: (纸本)9798350350067

The current generation of 5G technology has reached its limitations in terms of both frequency and wavelength. There is no room for further increasing the frequency, nor can we decrease the wavelength any further. In light of this challenge, alternative solutions for signal transmission must be explored. One such promising avenue is the utilization of Reconfigurable Intelligent Surfaces (RIS). RIS refers to a meta surface with the capability to dynamically alter its impedance, enabling efficient manipulation of signal reflection and steering. It holds significant potential for advancing beyond 5G towards the envisioned 6G era. This paper endeavours to delve into the behaviour of RIS through modelling, with a specific focus on its application in Remote Air Quality Monitoring. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

HECNNet: Hybrid Ensemble Convolutional Neural Network Model with Multi-Backbone Feature Extractors for Soybean Disease Classification 2

HECNNet: Hybrid Ensemble Convolutional Neural Network Model ...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Tiwari, Raj Gaurang Maheshwari, Himani Agarwal, Ambuj Kumar Jain, Vishal Chitkara University Institute of Engineering and Technology Chitkara University Punjab India School of Computing Graphic Era Hill University Uttrakhand Dehradun India School of Engineering and Technology Sharda University Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350327533

The purpose of this study is to classify soybean plant diseases using a new method called Hybrid Ensemble Convolutional Neural Networks (HECNNet). To effectively extract unique characteristics and categorize pictures, the proposed approach makes use of convolutional neural networks. The suggested approach is organized around three main phases: data collection, preprocessing, and classification. The novel component of this study is the hybrid ensemble model, which consists of ResNeXt, SqueezeNet, and SegNet, three strong backbone networks. With convolutional layers, dropouts, and max-pooling layers carefully adjusted to match the needs of the dataset, these backbone networks function as feature extractors and classifiers. HECNNet is the product of the interplay between these three extractors. Notably, the prediction scores from each sub-network are combined using a weighted sum operation in HECNNet, which significantly improves the final recognition rate compared to a single network method. The proposed algorithm tackles the complexity of soybean disease categorization and obtains an amazing accuracy rate of 91.7%. This study is a major advance in agricultural disease diagnosis since it provides a reliable and effective method for diagnosing ailments affecting soybean plants. © 2024 IEEE.

关键词： Agricultural disease identification Disease classification Feature extraction Hybrid model Soybean plant

来源：评论

学校读者我要写书评

暂无评论

MedLeafNet: A Feature Fusion Network Integrating Transformer and CNN Modules for Indian Medical Leaf Classification 2

MedLeafNet: A Feature Fusion Network Integrating Transformer...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Tiwari, Raj Gaurang Maheshwari, Himani Gautam, Vinay Agarwal, Ambuj Kumar Trivedi, Naresh Kumar Jain, Vishal Chitkara University Institute of Engineering and Technology Chitkara University Punjab India School of Computing Graphic Era Hill University Uttrakhand Dehradun India School of Engineering and Technology Department of Computer Science and Engineering Sharda University Greater Noida India

ISBN: (纸本)9798350327533

A new feature fusion network called 'MedLeafNet' is presented in this study specifically for the categorization of Indian medicinal leaves. Using a hybrid architecture, MedLeafNet integrates the best features of Convolutional Neural Network (CNN) modules for spatial feature extraction and Transformer modules for sequence modeling. Because of the complexity of classifying Indian medicinal leaves-which are famous for their varied and powerful medicinal properties-the suggested methodology is well suited to the task. For this research, 80 different types of Indian leaves were analyzed, each with its well-known therapeutic properties. To improve its capacity to detect complex patterns in leaves, Me dLeafNet incorporates Transformer and CNN modules to efficiently gather both global and local information. The suggested model was optimized using several different optimizers, such as Adam, Adadelta, Gradient Descent, AdaGrad, RMSProp, Adamax, Momentum, and Adaptive Moment Estimation. When trained with the Adam optimizer, MedLeafNet attained its maximum accuracy of 98.97%, as shown by extensive testing. MedLeafNet is also compared against some of the most well-known deep learning architectures, such as ResNet, Inception, VGG, Xception, and MobileNet. In terms of classification accuracy, the findings show that it is superior to these architectures, proving that it is effective for the difficult job of classifying Indian medicinal leaves. © 2024 IEEE.

关键词： Automated Plant Identification Deep Architectures Deep Learning Feature Fusion Network Medicinal Properties Optimizer Diversity Transformer Module

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Enabled Green Edge computing System for IIoT Applications 20th

Federated Learning Enabled Green Edge Computing System for ...

引用

20th International Conference on Mobile Web and Intelligent Information Systems, MobiWIS 2024

作者： Grønli, Tor Morten Lakhan, Abdullah Younas, Muhammad School of Economics Innovations and Technology Kristiania University College Oslo Norway School of Engineering Computing and Mathematics Oxford Brookes University Oxford United Kingdom

ISBN: (纸本)9783031680045

These days, the usage of industrial Internet of Things (IIoT), such as industrial robotics, smart homes, and electric, has been growing progressively. The IIoT applications consisted of different sensors and generated huge amounts of data. Due to resource issues of local devices, generally, IIoT workloads offload to a centralized cloud for execution. However, centralized power consumption is much higher, which is not optimal in a green environment. Green edge nodes are an extended version of cloud computing that brings computing devices and infrastructure to the network’s edge. They are designed to be environmentally friendly and energy-efficient. However, edge node-enabled green systems still have many issues. This paper presents a novel conceptual federated Learning Enabled Green Edge computing system for IIoT Applications. The paper aims to reduce the power consumption of computing nodes such as local devices, edge nodes, and cloud nodes during data training and analysis of IIoT applications. The proposed system offers green data training and analysis services at the edge nodes and offloads the data to the cloud for storage. The paper presents energy-green efficient federated learning deep convolutional neural network scheduling (FL-DCNNS) algorithm methodology to schedule all workloads of IIoT applications with minimum power consumption. Simulation results show that FL-DCNNS meets the requirements of a green computing environment on edge nodes during the execution of IIoT applications as compared to existing methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Secure communication routing and attack detection in UAV networks using Gannet Walruses optimization algorithm and Sheppard Convolutional Spinal Network

引用

Peer-to-Peer Networking and Applications 2024年第5期17卷 3269-3285页

作者： Renu, Yuvaraj Sarveshwaran, Velliangiri Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Campus Chengalpattu India Department of Computer Science and Information Engineering National Chung Cheng University Minxiong Chiayi Taiwan

Unmanned Aerial vehicles (UAV) are high-speed moving machines that attained rapid growth in various activities and are considered an integral component in the Satellite-Air -Ground-Sea (SAGS) incorporated network. However, UAVs are affected by communication delays and malicious attacks. Therefore, an adequate and secure communication routing and attack detection model is necessary for UAV communication networks. This research described a novel approach for initiating secure communication in UAV networks namely Gannet Walruses Optimization Algorithm + Sheppard Convolutional Spinal Network (GWOA + ShCSpinalNet). Initially, the UAV network is simulated, and the data packets are transmitted among the nodes using optimal routing paths. An optimal routing path is computed using the Gannet Walruses Optimization Algorithm (GWOA) by considering some multi-objective functions through the Deep Recurrent Neural Network (DRNN). The developed GWAO integrates Gannet Optimization (GOA) and Walruses Optimization (WaOA). The data communication is done through monitoring agents. The newly devised Sheppard Convolutional Spinal Network (ShCSpinalNet) is utilized as a decision-making agent for malicious attack detection. The attributes considered for decision-making are round trip time, packet delivery ratio, the strength of the signal, the size of the packet, and the number of incoming packets. Once the SpinalNet categorizes the normal and attacked nodes the defense agent is implemented for attack migration. The ShCSpinalNet is devised by the combination of the Sheppard Convolutional Neural Network and Spinal Network. The GWOA + ShCSpinalNet accomplishes a diminished delay of 0.614 s, an increased detection rate of 0.930%, an energy of 0.439 J, and a Packet Delivery Ratio (PDR) of 0.749. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Algorithmic Trading Strategies with Sentiment Analysis: A Reinforcement Learning Approach 3

Enhancing Algorithmic Trading Strategies with Sentiment Anal...

引用

3rd IEEE World Conference on Applied Intelligence and computing, AIC 2024

作者： Bharathi Mohan, G. Prasanna Kumar, R. Vifert Jenuben Daniel, V. Praghaadeesh, R. Maniappan, Varun Doss, Srinath Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India University Botswana Faculty of Engineering and Technology Botho Botswana

ISBN: (纸本)9798350384598

This paper discusses the application of deep reinforcement learning algorithms in stock trading, where the stock market environment is highly dynamic in nature. To represent the dynamics of the stock market, news headlines are a key factor in order to predict whether the market direction is bullish (upward) or bearish (downward). So we use different sentiment analysis models like Finbert and Roberta to see how the sentiment scores given by these models affect our trading agent's strategy. These sentiment scores are added to our custom trading environment, where we combine these scores as part of the state along with other parameters like open, high, low, close prices and trading *** for the reinforcement learning part, we used various policy gradient methods like Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Deep Q-Network (DQN) to train our agent in this custom environment. These models were then back-tested on historic data, where the trading strategies devised by these deep RL agents during the training phase were applied. The results provided by these models were very promising. The evaluation metrics used were the Sharpe score and Sortino score. The highest Sharpe ratio was given by the PPO agent, which was 3.0 for Facebook data and 2.834 for Goldman Sachs data, using the Roberta sentiment model. Whereas for the Finbert model, PPO got 3.24 for Facebook data and 3.03 for Goldman Sachs data. This explains that the trading portfolio is performing really well. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

ChainPIM: A ReRAM-Based Processing-in-Memory Accelerator for HGNNs via Chain Structure

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年第7期44卷 2516-2529页

作者： Xiao, Wenjing Wang, Jianyu Chen, Dan Shi, Chenglong Ling, Xin Chen, Min Wu, Thomas School of Computer Electronics and Information Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning530004 China School of Computer Electronics and Information Guangxi University Nanning530004 China School of Computing National University of Singapore 119077 Singapore School of Computer Science and Engineering South China University of Technology Guangzhou510006 China Pazhou Laboratory Guangzhou510330 China School of Electrical Engineering Guangxi University Nanning530004 China

Heterogeneous graph neural networks (HGNNs) have recently demonstrated significant advantages of capturing powerful structural and semantic information in heterogeneous graphs. Different from homogeneous graph neural networks directly aggregating information based on neighbors, HGNNs aggregate information based on complex metapaths. ReRAM-based processing-in-memory (PIM) architecture can reduce data movement and compute matrix-vector multiplication (MVM) in analog. It can be well used to accelerate HGNNs. However, the complex metapath-based aggregation of HGNNs makes it challenging to efficiently utilize the parallelism of ReRAM and vertices data reuse. To this end, we propose ChainPIM, the first ReRAM-based processing-in-memory accelerator for HGNNs featuring high computing parallelism and vertices data reuse. Specifically, we introduce R-Chain, which is based on a chain structure to build related metapath instances together. We can efficiently reuse vertices through R-Chain and process different R-Chains in parallel. Then, we further design an efficient storage format for storing R-Chains, which reduces a lot of repeated vertices storage. Finally, a specialized ReRAM-based architecture is developed to pipeline different types of aggregations in HGNNs, fully exploiting the huge potential of multi-level parallelism in HGNNs. Our experiments show that ChainPIM achieves an average memory space reduction of 47.86% and performance improvement by 128.29× compared to NVIDIA Tesla V100 GPU. © 1982-2012 IEEE.

关键词： Random access storage

来源：评论

学校读者我要写书评

暂无评论

From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos

引用

IEEE Transactions on Affective computing 2025年第2期16卷 624-638页

作者： Chen, Yin Li, Jia Shan, Shiguang Wang, Meng Hong, Richang Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Dynamic facial expression recognition (DFER) in the wild is still hindered by data limitations, e.g., insufficient quantity and diversity of pose, occlusion and illumination, as well as the inherent ambiguity of facial expressions. In contrast, static facial expression recognition (SFER) currently shows much higher performance and can benefit from more abundant high-quality training data. Moreover, the appearance features and dynamic dependencies of DFER remain largely unexplored. Recognizing the potential in leveraging SFER knowledge for DFER, we introduce a novel Static-to-Dynamic model (S2D) that leverages existing SFER knowledge and dynamic information implicitly encoded in extracted facial landmark-aware features, thereby significantly improving DFER performance. First, we build and train an image model for SFER, which incorporates a standard Vision Transformer (ViT) and Multi-View Complementary Prompters (MCPs) only. Then, we obtain our video model (i.e., S2D), for DFER, by inserting Temporal-Modeling Adapters (TMAs) into the image model. MCPs enhance facial expression features with landmark-aware features inferred by an off-the-shelf facial landmark detector. And the TMAs capture and model the relationships of dynamic changes in facial expressions, effectively extending the pre-trained image model for videos. Notably, MCPs and TMAs only increase a fraction of trainable parameters (less than +10%) to the original image model. Moreover, we present a novel Emotion-Anchors (i.e., reference samples for each emotion category) based Self-Distillation Loss to reduce the detrimental influence of ambiguous emotion labels, further enhancing our S2D. Experiments conducted on popular SFER and DFER datasets show that we have achieved a new state of the art. 2010-2012 IEEE.

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：