检索结果-内蒙古大学图书馆

Super-resolution GANs for upscaling unplanned urban settlements from remote sensing satellite imagery - the case of Chinese urban village detection

引用

International Journal of Digital Earth 2023年第1期16卷 2623-2643页

作者： Alessandro Crivellari Hong Wei Chunzhu Wei Yuhui Shi Department of Computer Science and Engineering SouthernUniversity of Science and TechnologyShenzhenPeople’s Republic of China Ministry of Education Ecological Field Station for East Asian Migratory Birds Department of Earth System ScienceInstitute for Global Change StudiesTsinghua UniversityBeijingPeople’s Republic of China School of Geography and Planning Sun Yat-sen UniversityGuangzhouPeople’s Republic of China Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai) ZhuhaiPeople’s Republic of China

The semantic segmentation of informal urban settlements represents an essential contribution towards renovation strategies and reconstruction *** this context,however,a big challenge remains unsolved when dealing with incomplete data acquisitions from multiple sensing devices,especially when study areas are depicted by images of different *** practice,traditional methodologies are directed to downgrade the higher-resolution data to the lowest-resolution measure,to define an overall homogeneous dataset,which is however ineffective in downstream segmentation activities of such crowded unplanned urban *** this purpose,we hereby tackle the problem in the opposite direction,namely upscaling the lower-resolution data to the highest-resolution measure,contributing to assess the use of cutting-edge super-resolution generative adversarial network(SR-GAN)*** experimental novelty targets the particular case involving the automatic detection of‘urban villages’,sign of the quick transformation of Chinese urban *** aligning image resolutions from two different data sources(Gaofen-2 and Sentinel-2 data),we evaluated the degree of improvement with regard to pixel-based landcover segmentation,achieving,on a 1 m resolution target,classification accuracies up to 83%,67%and 56%for 4x,8x,and 10x resolution upgrades respectively,disclosing the advantages of artificially-upscaled images for segmenting detailed characteristics of informal settlements.

关键词： SR-GAN resolution upscaling informal settlements urban villages cross-sensor analytics

来源：评论

学校读者我要写书评

暂无评论

Explainable Session-based Recommendation via Path Reasoning

arXiv

引用

arXiv 2024年

作者： Cao, Yang Shang, Shuo Wang, Jun Zhang, Wei The School of Computer Science and Technology East China Normal University Shanghai China School of Computer Science and Engineering Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Chengdu China

This paper explores providing explainability for session-based recommendation (SR) by path reasoning. Current SR models emphasize accuracy but lack explainability, while traditional path reasoning prioritizes knowledge graph exploration, ignoring sequential patterns present in the session history. Therefore, we propose a generalized hierarchical reinforcement learning framework for SR, which improves the explainability of existing SR models via Path Reasoning, namely PR4SR. Considering the different importance of items to the session, we design the session-level agent to select the items in the session as the starting point for path reasoning and the path-level agent to perform path reasoning. In particular, we design a multi-target reward mechanism to adapt to the skip behaviors of sequential patterns in SR, and introduce path midpoint reward to enhance the exploration efficiency in knowledge graphs. To improve the completeness of the knowledge graph and to diversify the paths of explanation, we incorporate extracted feature information from images into the knowledge graph. We instantiate PR4SR in five state-of-the-art SR models (i.e., GRU4REC, NARM, GCSAN, SR-GNN, SASRec) and compare it with other explainable SR frameworks, to demonstrate the effectiveness of PR4SR for recommendation and explanation tasks through extensive experiments with these approaches on four datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Clustering Model-based Analysis of Sales in Vegetable Categories for Supermarkets

Clustering Model-based Analysis of Sales in Vegetable Catego...

引用

Signal, Information and Data Processing (ICSIDP), IEEE International Conference on

作者： Jiana Liao Jiajun Chen Wenxu Zheng Yazhou Ren School of Automation Guangdong University of Technology Guangzhou China School of Computer Science and Engineering Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

The development of effective vegetable sales strategies is crucial for enhancing supermarket profitability, and these strategies are heavily reliant on a nuanced understanding of the sales volume distribution patterns across different vegetable categories. However, most existing studies fail to thoroughly analyze these distribution patterns, often neglecting factors such as sales volume magnitude and fluctuations. To address this gap, we first propose a comprehensive framework based on a K-means++ clustering model and Spearman correlation coefficient to analyze the sales data. Firstly, we normalize the data to eliminate the impact of differing dimensions across vegetable categories. Next, we analyze the sales data from both quarterly and daily perspectives. Data visualization is performed utilizing line charts, followed by a descriptive analysis of the sales volume distribution considering both magnitude and fluctuation. Furthermore, we utilize a K-means++ clustering model and the Spearman correlation coefficient to further explore the distribution patterns and interrelationships among different vegetable categories. The results of the experiments reveal the daily and quarterly sales distribution patterns of various vegetable categories, providing valuable insights to support the development of effective vegetable sales strategies for supermarkets.

关键词： Correlation coefficient Analytical models Fluctuations Correlation Profitability Data visualization Data processing Data models Numerical models Meteorology

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of Sparrow Search Algorithm based on multi-strategy fusion 10

Design and implementation of Sparrow Search Algorithm based ...

引用

10th Symposium on Novel Optoelectronic Detection technology and Applications

作者： Dai, Zhijian Li, Chengjie Li, Xin Wang, Shuo Li, Cong Yue, Xiuquan Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Guangdong Shenzhen518110 China National Key Laboratory of Wireless Communication University of Electronic Science and Technology of China Sichuan Chengdu611731 China Institute of Telecommunication and Navigation Satellites China Academy of Space Technology Beijing100094 China School of Computer Science and Engineering Southwest Minzu University Sichuan Chengdu610225 China

ISBN: (数字)9781510688155

ISBN: (纸本)9781510688148

In recent years, swarm intelligence algorithms have been widely used in image classification, image recognition and optimization problems. However, swarm intelligence algorithms are also faced with problems such as local optimization, loss of population diversity, slow convergence and stagnation of convergence in the later period. In this paper, a sparrow search algorithm based on multi-strategy fusion is proposed to solve the problem of local optimization. Firstly, the population is initialized by reverse elite learning to increase species diversity. Secondly, the sine-cosine algorithm and the adaptive weight formula are fused in the discoverer position, and the Gaussian mutation operator is introduced in the follower position update to update the global optimal solution perturbation process. The above processing can effectively improve the global optimization ability of the algorithm and prevent the algorithm from falling into local optimization. Finally, 7 test functions are used to evaluate the convergence speed, convergence accuracy, average value and standard difference of the algorithm. The experiment proves that the multi-strategy fusion sparrow search algorithm has obvious improvement in the convergence speed and the precision of the overall optimal value compared with the traditional sparrow search algorithm. © 2025 SPIE.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Self-Paced Neutral Expression-Disentangled Learning for Facial Expression Recognition

Self-Paced Neutral Expression-Disentangled Learning for Faci...

引用

Artificial Intelligence technology (ACAIT), Asian Conference on

作者： Zhenqian Wu Xiaoyuan Li Yazhou Ren Xiaorong Pu Xiaofeng Zhu Lifang He School of Computer Science and Engineering University of Electronic Science and Technology of China School of Computer Science and Engineering Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Department of Computer Science and Engineering Lehigh University

ISBN: (数字)9798350359145

ISBN: (纸本)9798350359152

The accuracy of facial expression recognition is typically influenced by the following factors: high similarities across different expressions, disturbing factors, and the subtle and rapid micro-movements of the face. One potential solution to overcome these obstacles is to leverage the hidden neutral information present in neutral expression images. In this paper, we propose a Self-Paced Neutral Expression-Disentangled Learning (SPNDL) model, which aims to disentangle the neutral information from facial expressions, facilitating the extraction of crucial features and variations. This approach enables the capture of discriminative details within similar expressions and the detection of micro-facial movements. To enhance the learning of these neutral expression-disentangled features (NDFs) and mitigate the challenges posed by non-convex optimization, we propose a self-paced learning (SPL) strategy based on NDFs during the training phase. SPL learns samples from easy to complex by increasing the number of samples selected into the training process, which enables to effectively suppress the negative impacts caused by low-quality samples and inconsistently distributed NDFs. Experiments on three popular databases (i.e., CK+, Oulu-CASIA, and RAF-DB) show the effectiveness of our proposed method.

关键词： Training Databases Face recognition Learning (artificial intelligence) Feature extraction Data mining Optimization

来源：评论

学校读者我要写书评

暂无评论

Parallel Repetition of k-Player Projection Games 27

Parallel Repetition of k-Player Projection Games

引用

27th International Conference on Approximation Algorithms for Combinatorial Optimization Problems, APPROX 2024 and the 28th International Conference on Randomization and Computation, RANDOM 2024

作者： Bhangale, Amey Braverman, Mark Khot, Subhash Liu, Yang P. Minzer, Dor Department of Computer Science and Engineering University of California RiversideCA United States Department of Computer Science Princeton University NJ United States Department of Computer Science Courant Institute of Mathematical Sciences New York University NY United States School of Mathematics Institute for Advanced Study PrincetonNJ United States Department of Mathematics Massachusetts Institute of Technology CambridgeMA United States

We study parallel repetition of k-player games where the constraints satisfy the projection property. We prove exponential decay in the value of a parallel repetition of projection games with a value less than 1. ... 详细信息

ISBN: (纸本)9783959773485

关键词： Multiplayer games Parallel Repetition Projection games

来源：评论

学校读者我要写书评

暂无评论

RF-PSSM:A Combination of Rotation Forest Algorithm and Position-Specific Scoring Matrix for Improved Prediction of Protein-Protein Interactions Between Hepatitis C Virus and Human

引用

Big Data Mining and Analytics 2023年第1期6卷 21-31页

作者： Xin Liu Yaping Lu Liang Wang Wei Geng Xinyi Shi Xiao Zhang School of Medical Informatics and Engineering Xuzhou Medical UniversityXuzhou 221000China College of Computer Science and Technology China University of Mining and TechnologyXuzhou 221116China Laboratory Medicine Guangdong Provincial People’s HospitalGuangdong Academy of Medical SciencesGuangzhou 510080China Hangzhou Institute for Advanced Study University of Chinese Academy of SciencesHangzhou 310005China

The identification of hepatitis C virus(HCV)virus-human protein interactions will not only help us understand the molecular mechanisms of related diseases but also be conductive to discovering new drug *** increasing number of clinically and experimentally validated interactions between HCV and human proteins have been documented in public databases,facilitating studies based on computational *** this study,we proposed a new computational approach,rotation forest position-specific scoring matrix(RF-PSSM),to predict the interactions among HCV and human *** particular,PSSM was used to characterize each protein,two-dimensional principal component analysis(2DPCA)was then adopted for feature extraction of ***,rotation forest(RF)was used to implement *** results of various ablation experiments show that on independent datasets,the accuracy and area under curve(AUC)value of RF-PSSM can reach 93.74% and 94.29%,respectively,outperforming almost all cutting-edge *** addition,we used RF-PSSM to predict 9 human proteins that may interact with HCV protein E1,which can provide theoretical guidance for future experimental studies.

关键词： protein-protein interactions hepatitis C virus position specific scoring matrix two-dimensional principal component analysis rotation forest

来源：评论

学校读者我要写书评

暂无评论

Blockchain for IoT Scenarios: Lightweight Three-Tier Architecture with GH-PBFT Consensus 23

Blockchain for IoT Scenarios: Lightweight Three-Tier Archite...

引用

Proceedings of the 2023 6th International Conference on Blockchain technology and Applications

作者： Ziwen Dai Qi Xia School of Computer Science and Engineering (School of Cyber Security) Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China (UESTC) China

ISBN: (纸本)9798400708671

Blockchain technology holds the potential to address security issues in the Internet of Things (IoT). However, its integration with IoT systems necessitates addressing substantial challenges related to lightweighting and scalability. This research introduces a novel architecture that seamlessly integrates IoT and blockchain technologies. A three-tier system design is proposed, enabling resource-constrained IoT devices to function as lightweight nodes. Integral to this architecture is the incorporation of certificate-less encryption, significantly reducing redundancy and resource overhead associated with certificate distribution and management. This approach simplifies the authentication and management processes for both nodes and end devices. Furthermore, the study introduces the GH-PBFT consensus algorithm, strategically optimizing system scalability and security. These pioneering solutions offer unprecedented possibilities for advancing blockchain applications within the intricate landscape of the Internet of Things.

关键词： Consensus algorithm Federated Blockchain IOT System architecture

来源：评论

学校读者我要写书评

暂无评论

Polaron mobility modulation by bandgap engineering in black phaseα-FAPbI_(3)

引用

Journal of Energy Chemistry 2023年第1期76卷 175-180,I0005页

作者： Chunwei Wang Zeyu Zhang Zhuang Xiong Xingyu Yue Bo Zhang Tingyuan jia Zhengzheng Liu Juan Du Yuxin Leng Kuan Sun Ruxin Li State Key Laboratory of High Field Laser Physics and CAS Center for Excellence in Ultra-intense Laser Science Shanghai Institute of Optics and Fine Mechanics(SIOM)Chinese Academy of Sciences(CAS)Shanghai 201800China School of Physical Science and Technology ShanghaiTech UniversityShanghai 201210China School of Physics and Optoelectronic Engineering Hangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesHangzhou 310024ZhejiangChina MOE Key Laboratory of Low-grade Energy Utilization Technologies and Systems CQU-NUS Renewable Energy Materials&Devices Joint LaboratorySchool of Energy&Power EngineeringChongqing UniversityChongqing 400044China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijing 100049China

Lead halide hybrid perovskites(LHP)have emerged as one of the most promising photovoltaic materials for their remarkable solar energy conversion *** transportation of the photoinduced carriers in LHP could screen the defect recombination with the help of the large polaron ***,the physical insight of the relationship between the superior optical-electronic performance of perovskite and its polaron dynamics related to the electron-lattice strong coupling induced by the substitution engineering is still lack of ***,the bandgap modulated thin films ofα-FAPbI_(3)with different element substitution is investigated by the time resolved Terahertz *** find the polaron recombination dynamics could be prolonged in LHP with a relatively smaller bandgap,even though the formation of polaron will not be affected ***,the large polaron mobility in(FAPb I_(3))0.95(MAPbI_(3))0.05thin film is~30%larger than that in(FAPb I_(3))0.85(MAPbBr_(3))*** larger mobility in(FAPb I_(3))0.95(MAPb I_(3))0.05could be assigned to the slowing down of the carrier scattering ***,the physical origin of the higher carrier mobility in the(FAPb I_(3))0.95(MAPbI_(3))0.05should be related with the lattice distortion and enhanced electron–phonon coupling induced by the *** addition,(FAPbI_(3))0.95(MAPbI_(3))0.05will lose fewer active carriers during the polaron cooling process than that in(FAPb I_(3))0.85(MAPbBr_(3)),indicating lower thermal dissipation in(FAPbI_(3))0.95(MAPbI_(3))*** results suggest that besides the smaller bandgap,the higher polaron mobility improved by the substitution engineering inα-FAPbI_(3)can also be an important factor for the high PCE of the black phaseα-FAPbI_(3)based solar cell devices.

关键词： Perovskites Polaron Mobility Terahertz spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction

arXiv

引用

arXiv 2024年

作者： Xu, Guowei Tao, Jiale Li, Wen Duan, Lixin Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China China School of Computer Science and Engineering University of Electronic Science and Technology of China China

In the realm of stochastic human motion prediction (SHMP), researchers have often turned to generative models like GANS, VAEs and diffusion models. However, most previous approaches have struggled to accurately predict motions that are both realistic and coherent with past motion due to a lack of guidance on the latent distribution. In this paper, we introduce Semantic Latent Directions (SLD) as a solution to this challenge, aiming to constrain the latent space to learn meaningful motion semantics and enhance the accuracy of SHMP. SLD defines a series of orthogonal latent directions and represents the hypothesis of future motion as a linear combination of these directions. By creating such an information bottleneck, SLD excels in capturing meaningful motion semantics, thereby improving the precision of motion predictions. Moreover, SLD offers controllable prediction capabilities by adjusting the coefficients of the latent directions during the inference phase. Expanding on SLD, we introduce a set of motion queries to enhance the diversity of predictions. By aligning these motion queries with the SLD space, SLD is further promoted to more accurate and coherent motion predictions. Through extensive experiments conducted on widely used benchmarks, we showcase the superiority of our method in accurately predicting motions while maintaining a balance of realism and diversity. Our code and pretrained models are available at https://***/GuoweiXu368/SLD-HMP. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

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：