检索结果-内蒙古大学图书馆

First wetland mapping at 10-m spatial resolution in South America using multi-source and multi-feature remote sensing data

引用

Science China Earth Sciences 2024年第10期67卷 3252-3269页

作者： Weiwei SUN Gang YANG Yuling HUANG Dehua MAO Ke HUANG Lin ZHU Xiangchao MENG Tian FENG Chao CHEN Yong GE Department of Geography and Spatial Information Techniques Ningbo UniversityNingbo 315211China State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences&Natural Resources ResearchChinese Academy of SciencesBeijing 100101China Natural Resources and Planning Bureau Shanghai Pudong New DistrictShanghai 200100China Key Laboratory of Wetland Ecology and Environment Northeast Institute of Geography and AgroecologyChinese Academy of SciencesChangchun 130102China Faculty of Electrical Engineering and Computer Science Ningbo UniversityNingbo 315211China School of Geography Science and Geomatics Engineering Suzhou University of Science and TechnologySuzhou 215009China

Wetland degradation has been accelerating in recent years globally. Accurate information on the geographic distribution and categories of wetlands is essential for their conservation and management. Despite being the world′s fourth largest continent, South America has limited research on wetland mapping, and there is currently no available map that provides comprehensive information on wetland distribution and categories in the region. To address this issue, we used Sentinel-1, Sentinel-2 and SRTM data, developed a sample collection method and a wetland mapping method with a collection of multi-source features such as optical features, polarization features and shape features for South American wetlands. We produced a 10-m resolution wetland map based on the Google Earth Engine(GEE) platform. Our Level-1 wetland cover map accurately captured six wetland sub-categories with an overall accuracy of 96.24% and a kappa coefficient of 0.8649, while our Level-2 water cover map included five sub-categories with an overall accuracy of 97.23% and a kappa coefficient of0.9368. The results show that the total area of existing wetlands in South America is approximately 1,737,000 km~2, which is6.8% of the total land area. Among the ten wetland categories, shallow sea had the largest area(960,527.4 km~2), while aquaculture ponds had the smallest area 1513.6 km~2. Swamp had the second largest area(306,240.1 km~2). Brazil, Argentina,Venezuela, Bolivia, and Colombia were found to have the largest wetland areas, with Brazil and Colombia having the most diverse wetland categories. This product can serve as baseline data for subsequent monitoring, management, and conservation of South American wetlands.

关键词： Wetland mapping Google Earth Engine Sentinel imagery South America

来源：评论

学校读者我要写书评

暂无评论

High-Speed Silicon Waveguide 3-to-8 Decoder Based on Electro-Optic Effects 18

High-Speed Silicon Waveguide 3-to-8 Decoder Based on Electro...

引用

Silicon Photonics XVIII 2023

作者： Akhmet, Alisher Gaziz, Almar Alipbayeva, Nazym Nakarmi, Bikash Ukaegbu, Ikechi A. Integrated Device Solutions and Nanophotonics Laboratory Electrical and Computer Engineering Department School of Engineering and Digital Sciences Nazarbayev University Kabanbay batyra prospekt 53 Nur-Sultan010000 Kazakhstan Key Laboratory of RADAR Imaging and Microwave Photonics College of Electronics and Information Engineering Nanjing University of Aeronautics and Astronautics 29 Jiangjun St Jiangning Jiangsu Nanjing211106 China

ISBN: (纸本)9781510659575

A high-performance silicon waveguide-based electro-optical 3-to-8 decoder is proposed in this work. Generic 500x220 nm dimensions of the waveguide provide compatibility with other devices and circuits. The length of the active region is 4.5 microns. The n-to-m electro-optical switching circuits utilize both forward and reversed bias NOT gates with a voltage input of -2.5 V and 2.5 V, for logic zero and logic high, respectively. The 3-to-8 decoder showed an input power of the optical signal of 1.26 mW, which is distributed within the circuit, resulting in the maximum output power of approximately 0.3 mW on each of the 8 terminals. 20000 dB/cm mode loss is achieved with a logic input controlled by ±2.5 V. Results show that a data-rate of up to 100 Gbit/s is achieved. © 2023 SPIE.

关键词： Silicon

来源：评论

学校读者我要写书评

暂无评论

Prior Knowledge-Driven Hybrid Prompter Learning for RGB-Event Tracking

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Wang, Mianzhao Shi, Fan Cheng, Xu Chen, Shengyong Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education Key Laboratory of Computer Vision and System School of Computer Science and Engineering Tianjin300384 China Technical University of Denmark Department of Technology Management and Economics Kongens Lyngby Denmark

Event data can asynchronously capture variations in light intensity, thereby implicitly providing valuable complementary cues for RGB-Event tracking. Existing methods typically employ a direct interaction mechanism to fuse RGB and event data. However, due to differences in imaging mechanisms, the representational disparity between these two data types is not fixed, which can lead to tracking failures in certain challenging scenarios. To address this issue, we propose a novel prior knowledge-driven hybrid prompter learning framework for RGB-Event tracking. Specifically, we develop a frame-event hybrid prompter that leverages prior tracking knowledge from the foundation model as intermediate modal support to mitigate the heterogeneity between RGB and event data. By leveraging its rich prior tracking knowledge, the intermediate modal reduces the gap between the dense RGB and sparse event data interactions, effectively guiding complementary learning between modalities. Meanwhile, to mitigate the internal learning disparities between the lightweight hybrid prompter and the deep transformer model, we introduce a pseudo-prompt learning strategy that lies between full fine-tuning and partial fine-tuning. This strategy adopts a divide-and-conquer approach to assign different learning rates to modules with distinct functions, effectively reducing the dominant influence of RGB information in complex scenarios. Extensive experiments conducted on two public RGB-Event tracking datasets show that the proposed HPL outperforms state-of-the-art tracking methods, achieving exceptional performance. © 1991-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Identity and Modality Attributes Driven Multimodal Fusion Networks for Emotion Recognition in Conversations

引用

IEEE Transactions on Multimedia 2025年

作者： Shi, Wuzhen Chen, Xuping Yao, Biyun Wen, Yang Sheng, Bin Shenzhen University Guangdong Province Engineering Laboratory for Digital Creative Technology Guangdong Provincial Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen518060 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China

Emotion recognition in conversations (ERC) is a crucial aspect of human-computer interaction and plays an important role in various domains, including healthcare, entertainment, and education. Since the conversation data in the form of multimodal sequences is well suited to be constructed into graphs, the methods based on graph convolutional network (GCN) show incomparable advantages. However, existing methods attempt to model the highly uncertain emotional relationships between different speakers, which is not an easy task and may even introduce interference information. Therefore, we propose an identity and modality attributes driven multimodality fusion network (dubbed IMDNet) for emotion recognition in conversations. Specifically, we construct a speaker-centric graph that only connects nodes of the same speaker within modalities to each other, reducing the interference between the emotions of different speakers. We also introduce the attribute embedding mechanism, which facilitates the correct calculation of correlations between nodes for better multimodal feature fusion. Considering that the emotional correlation between utterances will decrease over time, we present an utterance distance attention to make the fusion network pay more attention to the adjacent utterances. Furthermore, we explore the solution to the data imbalance problem suitable for conversation scenarios. Given the presence of possible anomalous samples in the dataset, we opt for the BoundaryFocalLoss. Experiments on the IEMOCAP and MELD datasets show that our IMDNet outperforms the state-of-the-art methods. © 1999-2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Silicon photonics micro-ring resonator-based SR latch for optical memory applications

Silicon photonics micro-ring resonator-based SR latch for op...

引用

Smart Photonic and Optoelectronic Integrated Circuits 2023

作者： Otynshy, Dinmukhammedali Alipbayeva, Nazym Nurgali, Assylkhan Nakarmi, Bikash Ukaegbu, Ikechi A. Integrated Device solutions Laboratory Electrical and Computer Engineering Department School of Engineering and Digital Sciences Nazarbayev University Kabanbay batyra prospekt 53 Nur-Sultan010000 Kazakhstan Key Laboratory of RADAR Imaging and Microwave Photonics College of Electronics and Information Engineering Nanjing University of Aeronautics and Astronautics 29 Jiangjun St Jiangning Jiangsu Nanjing211106 China

ISBN: (纸本)9781510659551

This work proposes the design of optical SR latch. The fundamental component of the latch is a micro-ring resonator (MRR), which utilizes a plasma dispersion effect with an applied reverse bias voltage to tune its resonance wavelength. The proposed SR latch is made up of two identical micro-ring resonators with similar doped regions and the same logic mode of operation. The memory properties are realized by implementing the feedback loop between the input and output of the circuit. A time-varying simulation is carried out by applying two pseudorandom electrical input signals S and R into the circuit at a data rate of 25 Gbps. The work concludes with a comparative analysis between two optical SR latches (NOR-based and NAND-based). © 2023 SPIE.

关键词： Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

Beam Scanning for Integrated Sensing and Communication in IRS-aided mmWave systems 24

Beam Scanning for Integrated Sensing and Communication in IR...

引用

24th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2023

作者： Li, Renwang Shao, Xiaodan Sun, Shu Tao, Meixia Zhang, Rui Shanghai Jiao Tong University Department of Electronic Engineering Shanghai China Shanghai Jiao Tong University Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai China The Chinese University of HongKong School of Science and Engineering Shenzhen Research Institute of Big Data Shenzhen China National University of Singapore Department of Electrical and Computer Engineering Singapore

ISBN: (纸本)9781665496261

This paper investigates an intelligent reflecting surface (IRS) aided millimeter-wave integrated sensing and communication (ISAC) system. Specifically, based on the passive beam scanning in the downlink, the IRS finds the optimal beam for reflecting the signals from the base station to a communication user. Meanwhile, the IRS estimates the angle of a nearby target based on its echo signal received by the sensing elements mounted on the IRS (i.e., semi-passive IRS). We propose an ISAC protocol for achieving the above objective via simultaneous (beam) training and sensing (STAS). Then, we derive the achievable rate of the communication user and the Cramer-Rao bound (CRB) of the angle estimation for the sensing target in closed-form. The achievable rate and CRB exhibit different performance against the duration of beam scanning. Specifically, the average achievable rate initially rises and subsequently declines, while the CRB monotonically decreases. Consequently, the duration of beam scanning should be carefully selected to balance communication and sensing performance. Simulation results have verified our analytical findings and shown that, thanks to the efficient use of downlink beam scanning signal for simultaneous communication and target sensing, the STAS protocol outperforms the benchmark protocol with orthogonal beam training and sensing. © 2023 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Human Expansion-Induced Biodiversity Crisis over Asia from 2000 to 2020

引用

Research 2024年第2期2023卷 647-658页

作者： Chao Yang Qingquan Li Xuqing Wang Aihong Cui Junyi Chen Huizeng Liu Wei Ma Xuanyan Dong Tiezhu Shi Fanyi Meng Xiaohu Yan Kai Ding Guofeng Wu MNR Key Laboratory for Geo-Environmental Monitoring of Great Bay Area&Guangdong Key Laboratory of Urban Informatics&Shenzhen Key Laboratory of Spatial Smart Sensing and Services Shenzhen UniversityShenzhen 518060China School of Architecture and Urban Planning Shenzhen UniversityShenzhen 518060China College of Civil and Transportation Engineering Shenzhen UniversityShenzhen 518060China Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ) Shenzhen 518107China Center for Hydrogeology and Environmental Geology China Geological SurveyBaoding 071051China Department of Geography Hong Kong Baptist UniversityHong Kong Special Administrative Region 999077China Faculty of Land Resource Engineering Kunming University of Science and TechnologyKunming 650093China institute for Advanced Study and Tiandu-Shenzhen University Deep Space Joint Laboratory Shenzhen UniversityShenzhen 518060China School of Civil Engineering Chongqing Jjiaotong UniversityChongging 400074China Department of Cil and Environmental Engineering Tohoku UniversitySendai 980-8579Japan School of Artificial Intelligence Shenzhen PolytechnicShenzhen 518055China School of Computer Science and Technology Dongguan University of TechnologyDongguan 523419China

Asia stands out as a priority for urgent biodiversity conservation due to its large protected areas(PAs)and threatened *** the 21st century,both the highlands and lowlands of Asia have been experiencing the dramatic human ***,the threat degree of human expansion to biodiversity is poorly ***,the threat degree of human expansion to biodiversity over 2000 to 2020 in Asia at the continental(Asia),national(48 Asian countries),and hotspot(6,502 Asian terrestrial PAs established before 2000)scales is investigated by integrating multiple large-scale *** results show that human expansion poses widespread threat to biodiversity in Asia,especially in Southeast Asia,with Malaysia,Cambodia,and Vietnam having the largest threat degrees(~1.5 to 1.7 times of the Asian average level).Human expansion in highlands induces higher threats to biodiversity than that in lowlands in one-third Asian countries(most Southeast Asian countries).The regions with threats to biodiversity are present in~75%terrestrial PAs(including 4,866 PAs in 26 countries),and human expansion in PAs triggers higher threat degrees to biodiversity than that in *** findings provide novel insight for the Sustainable Development Goal 15(SDG-15 Life on Land)and suggest that human expansion in Southeast Asian countries and PAs might hinder the realization of *** reduce the threat degree,Asian developing countries should accelerate economic transformation,and the developed countries in the world should reduce the demands for commodity trade in Southeast Asian countries(i.e.,trade leading to the loss of wildlife habitats)to alleviate human expansion,especially in PAs and highlands.

关键词： Human terrestrial integrating

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Tuned Deep Learning Enabled Intrusion Detection on Internet of Everything Environment

引用

computers, Materials & Continua 2022年第12期73卷 6579-6594页

作者： Manar Ahmed Hamza Aisha Hassan Abdalla Hashim Heba G.Mohamed Saud S.Alotaibi Hany Mahgoub Amal S.Mehanna Abdelwahed Motwakel Department of Electrical and Computer Engineering International Islamic University MalaysiaKuala Lumpur53100Malaysia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Electrical Engineering College of EngineeringPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Faculty of Computers and Information Computer Science DepartmentMenoufia UniversityEgypt Department of Digital Media Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11845Egypt

Internet of Everything(IoE),the recent technological advancement,represents an interconnected network of people,processes,data,and *** recent times,IoE gained significant attention among entrepreneurs,individuals,and communities owing to its realization of intense values from the connected *** the other hand,the massive increase in data generation from IoE applications enables the transmission of big data,from contextawaremachines,into useful *** and privacy pose serious challenges in designing IoE environment which can be addressed by developing effective Intrusion Detection systems(IDS).In this background,the current study develops Intelligent Multiverse Optimization with Deep Learning Enabled Intrusion Detection system(IMVO-DLIDS)for IoT *** presented IMVO-DLIDS model focuses on identification and classification of intrusions in IoT *** proposed IMVO-DLIDS model follows a three-stage *** first,data pre-processing is performed to convert the actual data into useful *** addition,Chaotic Local Search Whale Optimization Algorithm-based Feature Selection(CLSWOA-FS)technique is employed to choose the optimal feature ***,MVO algorithm is exploited with Bidirectional Gated Recurrent Unit(BiGRU)model for ***,the novelty of the work is the application of MVO algorithm in fine-turning the hyperparameters involved in BiGRU *** experimental validation was conducted for the proposed IMVO-DLIDS model on benchmark datasets and the results were assessed under distinct *** extensive comparative study was conducted and the results confirmed the promising outcomes of IMVO-DLIDS approach compared to other approaches.

关键词： Internet of everything deep learning feature selection classification intrusion detection cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Advancing Orchard Fruit Detection: An Innovative Agricultural Foundation Model Approach

Advancing Orchard Fruit Detection: An Innovative Agricultura...

引用

2024 American Society of Agricultural and Biological Engineers Annual International Meeting, ASABE 2024

作者： Li, Jiajia Lammers, Kyle Yin, Xunyuan Yin, Xiang He, Long Lu, Renfu Li, Zhaojian Department of Electrical and Computer Engineering Michigan State University MI United States School of Chemical and Biomedical Engineering Nanyang Technological University Singapore Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China Department of Agricultural and Biological Engineering Pennsylvania State University United States United States Department of Agriculture Agricultural Research Service East LansingMI United States Department of Mechanical Engineering Michigan State University East LansingMI United States

ISBN: (纸本)9798331302214

Fruit harvesting poses a significant labor and financial burden on the fruit industry, which underscore the urgent need for advancements in robotic harvesting solutions. Despite considerable progress in leveraging deep learning and machine learning techniques for fruit detection, a common shortfall is the inability to swiftly extend the developed models across different orchards and/or various fruit species. Additionally, the limited availability of pertinent data further compounds these challenges. In this work, we introduce MetaFruit, the largest publicly available multi-class fruit dataset, comprising 4,248 images and 248,015 manually labeled instances across diverse U.S. orchards. Furthermore, this study proposes an innovative open-set fruit detection system leveraging advanced Vision Foundation Models (VFMs) for fruit detection that can adeptly identify a wide array of fruit types under varying orchard conditions. This system not only demonstrates remarkable adaptability in learning from minimal data through few-shot learning but also shows the ability to interpret human instructions for subtle detection tasks. The performance of the developed foundation model is comprehensively evaluated across several metrics, outperforming existing state-of-the-art algorithms in our MetaFruit, thereby setting a new benchmark in the field of agricultural technology and robotic harvesting. The MetaFruit dataset (https://***/datasets/jiajiali/metafruit) and detection framework (https://***/JiajiaLi04/FMFruit) are open-sourced to foster future research in vision-based fruit harvesting, marking a significant stride toward addressing the urgent needs of the agricultural sector. © 2024 ASABE Annual International Meeting. All rights reserved.

关键词： Orchards

来源：评论

学校读者我要写书评

暂无评论

Gaussian Optimized Deep Learning-based Belief Classification Model for Breast Cancer Detection

引用

computers, Materials & Continua 2022年第11期73卷 4123-4138页

作者： Areej A.Malibari Marwa Obayya Mohamed K.Nour Amal S.Mehanna Manar Ahmed Hamza Abu Sarwar Zamani Ishfaq Yaseen Abdelwahed Motwakel Department of Industrial and Systems Engineering College of EngineeringPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh 11671Saudi Arabia Department of Biomedical Engineering College of EngineeringPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Digital Media Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam Bin Abdulaziz UniversityAlKharjSaudi Arabia

With the rapid increase of new cases with an increased mortality rate,cancer is considered the second and most deadly disease *** cancer is the most widely affected cancer worldwide,with an increased death rate *** to radiologists’processing of mammogram images,many computer-aided diagnoses have been developed to detect breast *** detection of breast cancer will reduce the death rate *** early diagnosis of breast cancer using the developed computer-aided diagnosis(CAD)systems still needed to be enhanced by incorporating innovative deep learning technologies to improve the accuracy and sensitivity of the detection system with a reduced false positive *** paper proposed an efficient and optimized deep learning-based feature selection approach with this *** model selects the relevant features from the mammogram images that can improve the accuracy of malignant detection and reduce the false alarm *** learning is used in the extraction of features *** ext,a convolution neural network,is used to extract the *** two feature vectors are fused and optimized with enhanced Butterfly Optimization with Gaussian function(TL-CNN-EBOG)to select the final most relevant *** optimized features are applied to the classifier called Deep belief network(DBN)to classify the benign and malignant *** feature extraction and classification process used two datasets,breast,and *** to the existing methods,the optimized deep learning-based model secured 98.6%of improved accuracy on the breast dataset and 98.85%of improved accuracy on the MIAS dataset.

关键词： Breast cancer detection computer-aided diagnosis(CAD) deep learning CNN entropy butterfly optimization

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：