检索结果-内蒙古大学图书馆

Sustainable Agriculture-Based Climate Change Training Models using Remote Hyperspectral Image with Machine Learning Model

引用

Remote Sensing in Earth Systems Sciences 2024年第4期7卷 261-270页

作者： Durairaj, M. Rubenraju, Kasapaka Krishna, B. V. Rama Yajid, Mohd Shukri Ab Jackson, Beulah Babu, Jampani Satish Padmavathi, Kodali Lakshmi Department of ECE Saveetha School of Engineering SIMATS Chennai India Department of Data Science & amp IT Malla Reddy University Telangana Hyderabad 500100 India Department of CSE Aditya College of Engineering and Technology Andhra PradeshSurampalem India Management and Science University Selangor Shah Alam Malaysia Department of ECE Vel Tech Rangarajan Dr. Sagunthala R & amp D Institute of Science and Technology Chennai India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram A.P. Guntur 522302 India Department of Artificial Intelligence and Data Science Lakireddy Bali Reddy College of Engineering Andhra Pradesh India

In order to help farmers and crop managers better understand the elements influencing crop status and growth, hyperspectral and multispectral data processing methods have shown to be beneficial. Utilising advanced computational methods via machine learning is one strategy that has been in use recently. This method can forecast satellite image data based on the circumstances of mapping different types of land and vegetation in the field. This research proposes novel technique in sustainable agriculture-based climate change detection using hyperspectral image analysis with machine learning model. Here, the hyperspectral image of agricultural field is collected as input and processed for smoothening with normalisation. The proposed image analysis model is carried out in two stages which is feature extraction and classification. In stage 1, the feature extraction of processed input hyperspectral image is carried out using multilayer Bayesian encoder vector model (MBEV). The second stage of this proposed model is to classify the extracted image using deep convolutional belief neural networks (DCBNN). The experimental analysis has been carried out for various agriculture-based hyperspectral image datasets in terms of training accuracy, sensitivity, specificity, and AUC. The experimental findings demonstrate that, when compared to other ways, the suggested strategy performed exceptionally well. Proposed technique attained training accuracy of 97%, AUC of 85%, sensitivity of 96%, and specificity of 93%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Classification Climate change Hyperspectral image analysis Machine learning Sustainable agriculture

来源：评论

学校读者我要写书评

暂无评论

Optimal Privacy Preserving for Federated Learning in Mobile Edge Computing

arXiv

引用

arXiv 2022年

作者： Nguyen, Hai M. Chu, Nam H. Nguyen, Diep N. Hoang, Dinh Thai Nguyen, Van-Dinh Hà, Minh Hoàng Dutkiewicz, Eryk Krunz, Marwan The School of Electrical and Data Engineering University of Technology Sydney Australia The College of Engineering and Computer Science VinUniversity Hanoi Viet Nam The ORLab Faculty of Computer Science Phenikaa University Hanoi Viet Nam The Department of Electrical and Computer Engineering University of Arizona United States

Federated Learning (FL) with quantization and deliberately added noise over wireless networks is a promising approach to preserve user differential privacy while reducing wireless resources. Specifically, an FL learning process can be fused with quantized Binomial mechanism-based updates contributed by multiple users to reduce the communication overhead/cost and to protect the privacy of participating users. However, optimizing quantization parameters, communication resources (e.g., transmit power, bandwidth, and quantization bits), and the added noise to guarantee the differential privacy requirement and performance of the learned FL model remains an open and challenging problem. This article aims to jointly optimize the level of quantization, parameters of the Binomial mechanism, and communication resources so as to maximize the convergence rate under the constraints of the wireless network and differential privacy (DP) requirement. To that end, we first derive a novel DP budget estimation of the FL with quantization and Binomial noise that is tighter than the state-of-the-art bound. We then analyze the relationship between the convergence rate and the transmit power, the bandwidth, the transmission time, and the quantization/noise parameters and provide a theoretical bound on the convergence rate. This theoretical bound is decomposed into two components, including the variance of the global gradient and an upper bound on the quadratic bias that can be minimized by optimizing the communication resources, quantization, and added noise parameters. The resulting optimization turns out to be a Mixed-Integer Non-linear Programming (MINLP) problem. To tackle it, we first transform this MINLP problem into a new problem whose solutions are proved to be the optimal solutions of the original one. We then propose an approximate algorithm to solve the transformed problem with an arbitrary relative error guarantee. Extensive simulations show that under the same wireless resour

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Modeling and performances assessments of PV/T bifluid hybrid collector: Three cooling modes operation case 4

Modeling and performances assessments of PV/T bifluid hybrid...

引用

4th International Conference on Electrical and Information Technologies, ICEIT 2020

作者： El Manssouri, Oussama El Fouas, Chaimae Hajji, Bekkay Rabhi, Abdelhamid Tina, Giuseppe Marco Gagliano, Antonio Mohamed First University Renewable Energy Embedded System and Data Processing Laboratory National School of Applied Sciences Oujda Morocco Picardie Jules Verne University Modelization Information and Systems Laboratory Amiens France University of Catania DIEEI: Department of Electric Electronic and Computer Engineering Catania Italy

ISBN: (数字)9781728143415

ISBN: (纸本)9781728143415

The objective of the present work is the performance assessments of a bi-fluid photovoltaic/thermal solar collector (PV/T). Based on energy-balance equations, a mathematical model of PV/T hybrid collector has been developed and simulated using Matlab Software. This model takes into account the effect of the three modes of fluid operation under the same PV/T system, namely: the air mode, the water mode, and the simultaneous mode of water and air. The results show that the lowest PV module temperature is observed in the simultaneous mode (air water) compared to others modes. It's maximum value achieved is around 62°C in the bi-fluid mode against 80°C and 73°C respectively in the air mode and the water mode. The maximum efficiencies of 66.97 % (thermal efficiency) and 10.1% (electrical efficiency) are also observed, when both fluids are operated simultaneously compared to others modes. Finally, the working in simultaneous mode is beneficial to transmit more heat, produce more thermal energy and consequently improve the electrical and thermal performances of the PV/T hybrid collector. Moreover, the theoretical model developed is validated, evidencing a good fit between simulation results and the experimental data available in literature. The PV/T collector designed in this study has a variety of applications, as solar drying in agriculture, air conditioning, space heating and hot water supply for domestic applications. © 2020 IEEE.

关键词： Air

来源：评论

学校读者我要写书评

暂无评论

Learning to transfer graph embeddings for inductive graph based recommendation

arXiv

引用

arXiv 2020年

作者： Wu, Le Yang, Yonghui Chen, Lei Lian, Defu Hong, Richang Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology University of Science and Technology of China

With the increasing availability of videos, how to edit them and present the most interesting parts to users, i.e., video highlight, has become an urgent need with many broad applications. As users’ visual preferences are subjective and vary from person to person, previous generalized video highlight extraction models fail to tailor to users’ unique preferences. In this paper, we study the problem of personalized video highlight recommendation with rich visual content. By dividing each video into non-overlapping segments, we formulate the problem as a personalized segment recommendation task with many new segments in the test stage. The key challenges of this problem lie in: the cold-start users with limited video highlight records in the training data and new segments without any user ratings at the test stage. To tackle these challenges, an intuitive idea is to formulate a user-item interaction graph and perform inductive graph neural network based models for better user and item embedding learning. However, the graph embedding models fail to generalize to unseen items as these models rely on the item content feature and item link information for item embedding calculation. To this end, we propose an inductive Graph based Transfer learning framework for personalized video highlight Recommendation (TransGRec). TransGRec is composed of two parts: a graph neural network followed by an item embedding transfer network. Specifically, the graph neural network part exploits the higher-order proximity between users and segments to alleviate the user cold-start problem. The transfer network is designed to approximate the learned item embeddings from graph neural networks by taking each item’s visual content as input, in order to tackle the new segment problem in the test phase. We design two detailed implementations of the transfer learning optimization function, and we show how the two parts of TransGRec can be efficiently optimized with different transfer learning optimiz

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Parameter-Saving Adversarial Training: Reinforcing Multi-Perturbation Robustness via Hypernetworks

arXiv

引用

arXiv 2023年

作者： Gong, Huihui Dong, Minjing Ma, Siqi Camtepe, Seyit Nepal, Surya Xu, Chang School of Computer Science University of Sydney Australia School of Engineering and Information Technology University of New South Wales Canberra Australia CISRO Data61 Australia

Adversarial training serves as one of the most popular and effective methods to defend against adversarial perturbations. However, most defense mechanisms only consider a single type of perturbation while various attack methods might be adopted to perform stronger adversarial attacks against the deployed model in real-world scenarios, e.g., 2 or ∞. Defending against various attacks can be a challenging problem since multi-perturbation adversarial training and its variants only achieve suboptimal robustness trade-offs, due to the theoretical limit to multi-perturbation robustness for a single model. Besides, it is impractical to deploy large models in some storage-efficient scenarios. To settle down these drawbacks, in this paper we propose a novel multi-perturbation adversarial training framework, parameter-saving adversarial training (PSAT), to reinforce multi-perturbation robustness with an advantageous side effect of saving parameters, which leverages hypernetworks to train specialized models against a single perturbation and aggregate these specialized models to defend against multiple perturbations. Eventually, we extensively evaluate and compare our proposed method with state-of-the-art single/multi-perturbation robust methods against various latest attack methods on different datasets, showing the robustness superiority and parameter efficiency of our proposed method, e.g., for the CIFAR-10 dataset with ResNet-50 as the backbone, PSAT saves approximately 80% of parameters with achieving the state-of-the-art robustness trade-off accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Optimal Encoding and Decoding Algorithms for the RAID-6 Liberation Codes

Optimal Encoding and Decoding Algorithms for the RAID-6 Libe...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Zhijie Huang Hong Jiang Zhirong Shen Hao Che Nong Xiao Ning Li Dept. of Computer Science and Engineering University of Texas at Arlington Arlington USA School of Informatics Xiamen University Xiamen China School of Data and Computer Science Sun Yat-Sen University Guangzhou China

ISBN: (数字)9781728168760

ISBN: (纸本)9781728168777

RAID-6 is gradually replacing RAID-5 as the dominant form of disk arrays due to its capability of tolerating concurrent failures of any two disks, as well as the case of encountering an uncorrectable read error during recovery. Implementing a RAID-6 system relies on some erasure coding schemes, and so far the most representative solutions are EVENODD codes [1], RDP codes [2] and Liberation codes [3], none of which has emerged as a clear "all-around" winner. In this paper, we are interested in revealing the undiscovered potential of the Liberation codes, since these codes have the following attractive features: (a) they have the best update performance, (b) they have better scalability, and (c) they are open-sourced and publicly available, as well as the following drawbacks: fair encoding performance and, more importantly, relatively poor decoding performance. Specificly, we present novel optimal encoding and decoding algorithms for the Liberation codes by introducing an alternative, geometric presentation of these codes. The proposed algorithms completely eliminate redundant computations during the encoding and decoding procedures by extracting and reusing common expressions between the two types of parity constraints, and do not involve any matrix operations on which the original algorithms are based. Our experiment results show that compared with the original solution, the proposed encoding and decoding algorithms reduce the number of XOR's by up to 16 percent and 15 ~20 percent respectively, and the encoding and decoding throughputs are increased by 22.3 percent and at most 155 percent respectively. Moreover, the encoding complexity reaches the theoretical lower bound, while the decoding complexity is also very close to the theoretical lower bound.

关键词： Encoding Decoding Arrays Complexity theory Measurement Standards Reed-Solomon codes

来源：评论

学校读者我要写书评

暂无评论

Imitation Learning from Purified Demonstrations

arXiv

引用

arXiv 2023年

作者： Wang, Yunke Dong, Minjing Zhao, Yukun Du, Bo Xu, Chang School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan Institute of Data Intelligence Wuhan University China Department of Computer Science City University of Hong Kong China School of Computer Science Faculty of Engineering The University of Sydney Australia

Imitation learning has emerged as a promising approach for addressing sequential decision-making problems, with the assumption that expert demonstrations are optimal. However, in real-world scenarios, most demonstrations are often imperfect, leading to challenges in the effectiveness of imitation learning. While existing research has focused on optimizing with imperfect demonstrations, the training typically requires a certain proportion of optimal demonstrations to guarantee performance. To tackle these problems, we propose to purify the potential noises in imperfect demonstrations first, and subsequently conduct imitation learning from these purified demonstrations. Motivated by the success of diffusion model, we introduce a two-step purification via diffusion process. In the first step, we apply a forward diffusion process to smooth potential noises in imperfect demonstrations by introducing additional noise. Subsequently, a reverse generative process is utilized to recover the optimal demonstration from the diffused ones. We provide theoretical evidence supporting our approach, demonstrating that the distance between the purified and optimal demonstration can be bounded. Empirical results on MuJoCo and RoboSuite demonstrate the effectiveness of our method from different aspects. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Visual Analytics for Temporal and Spatial Feature of TV Drama Viewing data

引用

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of computer-Aided Design and computer Graphics 2018年第5期30卷 816-823页

作者： Chen, Hongqian Yang, Qianyu Wen, Yulin Li, Hui Chen, Yi Beijing Key Laboratory of Big Data Technology for Food Safety School of Computer and Information Engineering Beijing Technology and Business University Beijing100048 China College of Management Beijing Union University Beijing100101 China

To analysis the influence factors of the TV drama view ratings, we proposed a visual analytic method for the temporal and spatial feature of broadcasting. Heat map was adopted firstly to show the temporal features of the ratings of different TV drama themes. Bar graph was used to compare the average ratings of each category. The location offset mapping was introduced to display different TV stations' spatial characteristics such as broadcast volume, average ratings, gender, age and occupational distribution of viewers. We selected the representative TV stations' drama ratings data from March 2015 to December 2015 as an example. The experimental results show that the method can assist efficiently to visual comparison of ratings and viewers for different TV stations and TV drama categories. The method can help making decisions in TV drama making, buying and arranging for TV stations. © 2018, Beijing China Science Journal Publishing Co. Ltd. All right reserved.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Pruning Self-attentions into Convolutional Layers in Single Path

arXiv

引用

arXiv 2021年

作者： He, Haoyu Cai, Jianfei Liu, Jing Pan, Zizheng Zhang, Jing Tao, Dacheng Zhuang, Bohan Department of Data Science and AI Faculty of IT Monash University Australia Faculty of Engineering The University of Sydney Australia School of Computer Science and Engineering Nanyang Technological University Singapore

Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. However, modeling global correlations with multi-head self-attention (MSA) layers leads to two widely recognized issues: the massive computational resource consumption and the lack of intrinsic inductive bias for modeling local visual patterns. To solve both issues, we devise a simple yet effective method named Single-Path Vision Transformer pruning (SPViT), to efficiently and automatically compress the pre-trained ViTs into compact models with proper locality added. Specifically, we first propose a novel weight-sharing scheme between MSA and convolutional operations, delivering a single-path space to encode all candidate operations. In this way, we cast the operation search problem as finding which subset of parameters to use in each MSA layer, which significantly reduces the computational cost and optimization difficulty, and the convolution kernels can be well initialized using pre-trained MSA parameters. Relying on the single-path space, we introduce learnable binary gates to encode the operation choices in MSA layers. Similarly, we further employ learnable gates to encode the fine-grained MLP expansion ratios of FFN layers. In this way, our SPViT optimizes the learnable gates to automatically explore from a vast and unified search space and flexibly adjust the MSA-FFN pruning proportions for each individual dense model. We conduct extensive experiments on two representative ViTs showing that our SPViT achieves a new SOTA for pruning on ImageNet-1k. For example, our SPViT can trim 52.0% FLOPs for DeiT-B and get an impressive 0.6% top-1 accuracy gain simultaneously. The source code is available at https://***/ziplab/SPViT. © 2021, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： He, Weizhao Zhang, Yang Zhuo, Wei Shen, Linlin Yang, Jiaqi Deng, Songhe Sun, Liang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China School of Computer Science University of Nottingham China

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and their performances degrade significantly while applied to a distinct domain. To this end, we propose to leverage the cutting-edge foundation model, the Segment Anything Model (SAM), for generalization enhancement. The SAM however performs unsatisfactorily on domains that are distinct from its training data, which primarily comprise natural scene images, and it does not support automatic segmentation of specific semantics due to its interactive prompting mechanism. In our work, we introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS), which is designed to be auto-prompted for guiding cross-domain segmentation. Specifically, we propose a Dual Prototype Anchor Transformation (DPAT) module that fuses pseudo query prototypes extracted based on cycle-consistency with support prototypes, allowing features to be transformed into a more stable domain-agnostic space. Additionally, a Meta Prompt Generator (MPG) module is introduced to automatically generate prompt embeddings, eliminating the need for manual visual prompts. We build an efficient model which can be applied directly to target domains without fine-tuning. Extensive experiments on four cross-domain datasets show that our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

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：