检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zou, Xuechao Zhang, Shun Li, Kai Wang, Shiying Xing, Junliang Jin, Lei Lang, Congyan Tao, Pin School of Computer Science & Technology Beijing Jiaotong University Beijing China The Department of Computer Science and Technology Tsinghua University Beijing China The Key Laboratory of Pervasive Computing Ministry of Education China The School of Computer Technology and Application Qinghai University Xining China The School of Electronic Engineering Beijing University of Posts and Telecommunications Beijing China

Cloud segmentation is a critical challenge in remote sensing image interpretation, as its accuracy directly impacts the effectiveness of subsequent data processing and analysis. Recently, vision foundation models (VFM) have demonstrated powerful generalization capabilities across various visual tasks. In this paper, we present a parameter-efficient adaptive approach, termed Cloud-Adapter, designed to enhance the accuracy and robustness of cloud segmentation. Our method leverages a VFM pretrained on general domain data, which remains frozen, eliminating the need for additional training. Cloud-Adapter incorporates a lightweight spatial perception module that initially utilizes a convolutional neural network (ConvNet) to extract dense spatial representations. These multi-scale features are then aggregated and serve as contextual inputs to an adapting module, which modulates the frozen transformer layers within the VFM. Experimental results demonstrate that the Cloud-Adapter approach, utilizing only 0.6% of the trainable parameters of the frozen backbone, achieves substantial performance gains. Cloud-Adapter consistently achieves state-of-the-art performance across various cloud segmentation datasets from multiple satellite sources, sensor series, data processing levels, land cover scenarios, and annotation granularities. We have released the code and model checkpoints at https://***/Cloud-Adapter/ to support further research. Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Time Expression Normalization with Meta Time Information

Time Expression Normalization with Meta Time Information

引用

International Conference on Computational science and Computational Intelligence (CSCI)

作者： Mengyu An Chenyu Jin Xiaoshi Zhong Erik Cambria School of Computer Science and Technology Beijing Institute of Technology China NORINCO Group Co. Ltd. China North Industries Computer Application Technology Institute China School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (数字)9798350361513

ISBN: (纸本)9798350372304

Time expression (a.k.a., timex) normalization is a fundamental task for many downstream researches and applications. Previous researches mainly developed deterministic rules and machine-learning methods for the end-to-end task of timex recognition and normalization (TERN). However, deterministic rules heavily depend on specific domains while machine-learning methods are somewhat unexplainable. To better understand the task, we analyze three diverse benchmark datasets for the characteristics of timex types and values. According to these characteristics, we propose a rule-based method termed MetaTime 1 with three kinds of meta time information to normalize timexes into standard type and value formats. MetaTime is independent of specific domains and textual types. Experimental results on three diverse benchmark datasets demonstrate that MetaTime outperforms four representative state-of-the-art methods.

关键词： Scientific computing Computational modeling Machine learning Benchmark testing Linguistics Real-time systems Task analysis

来源：评论

学校读者我要写书评

暂无评论

Advancing Data science Using AI-Driven Processes

Advancing Data Science Using AI-Driven Processes

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Jahir Pasha, M. Gaurav, Kumar Bhanja, Amit Kumar Shamout, Mohamed Dawood Mupparaju, Chinna Babu Manohar Bhanushali, Mahesh G.Pullaiah College of Engineering and Technology Computer Science and Engineering Kurnool India Lovely Professional University Phagwara India School of Management Sciences Department of Management Varanasi India College of Business Administration University of Sharjah Department of Management Sharjah United Arab Emirates University of Central Missouri Masters in Computer Science warrensburg United States Management Studies University of Mumbai VPM's Dr.V.N.Bedekar Institute of Management Studies Thane India

ISBN: (纸本)9798350357769

Advances in AI-pushed facts technological know-how can be seen in an expansion of different regions. Examples of those consist of herbal Language Processing (NLP), machine learning (ML), Deep gaining knowledge of (DL), pc vision (CV), computerized data evaluation, and plenty *** technology is used to technique and extract significant records from textual content-based totally datasets. This era uses semantic algorithms, natural language processing tools, and rule-based totally era to apprehend and interpret textual content information. machine studying (ML) is now being used to automate positive obligations such as predicting monetary trends, figuring out consumer styles, and greater. ML technology can be used to identify relationships among facts points that have been previously no longer seen. Deep gaining knowledge of (DL) is a sub field of the device getting to know that applies layers of neural networks to identify patterns inside facts units. This generation gives an exceptionally powerful manner of analyzing records, allowing machines to stumble on complicated relationships that may have previously been too hard to come *** imaginative and prescient (CV) is another region in which advances in AI-pushed information science are being visible. CV generation lets in for computerized evaluation of snap shots and movies, making it viable to become aware of gadgets, come across tendencies, and discover anomalies. computerized facts analysis is one of the maximum powerful approaches. © 2023 IEEE.

关键词： Analyzing Records computerized Data Evaluation Semantic Algorithms

来源：评论

学校读者我要写书评

暂无评论

PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learning

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5690-5704页

作者： Hou, Sizai Li, Songze Jahani-Nezhad, Tayyebeh Caire, Giuseppe Hong Kong University of Science and Technology Hong Kong Southeast University School of Cyber Science and Engineering Nanjing China Supervision and Management (Southeast University) Ministry of Education Engineering Research Center of Blockchain Application China Technische Universität Berlin Department of Electrical Engineering and Computer Science Berlin 10587 Germany

Federated learning (FL), as a promising machine learning paradigm for large-scale distributed data, faces two security challenges of privacy and robustness: the transmitted model updates potentially leak sensitive user information, and the lack of central control over local model updates leaves the global model susceptible to malicious attacks. Current solutions attempting to address both problems under the one-server FL setting fall short in the following aspects: 1) design for simple validity checks that are insufficient against advanced attacks (e.g., checking norm of individual update);and 2) have partial privacy leakage for more complicated robust aggregation algorithms (e.g., distances between model updates are leaked for multi-Krum). In this work, we formalize a novel security notion of aggregated privacy that characterizes the minimum amount of user information, in the form of aggregated statistics of users’ updates, that is necessary to be revealed to accomplish more advanced robust aggregation. We develop a general framework PriRoAgg, utilizing Lagrange coded computing and distributed zero-knowledge proof, to execute a wide range of robust aggregation algorithms while satisfying aggregated privacy. As concrete instantiations of PriRoAgg, we construct two secure and robust protocols based on state-of-the-art robust algorithms, for which we provide full theoretical analyses on security and complexity. Extensive experiments are conducted for these protocols, demonstrating their robustness against various model integrity attacks, and their efficiency advantages over baselines. © 2005-2012 IEEE.

关键词： Byzantine Resilience Federated Learning Privacy Preservation Secure and Robust Aggregation

来源：评论

学校读者我要写书评

暂无评论

Denoised Internal Models:A Brain-inspired Autoencoder Against Adversarial Attacks

引用

Machine Intelligence Research 2022年第5期19卷 456-471页

作者： Kai-Yuan Liu Xing-Yu Li Yu-Rui Lai Hang Su Jia-Chen Wang Chun-Xu Guo Hong Xie Ji-Song Guan Yi Zhou School of Life Sciences and Technology ShanghaiTech UniversityShanghai 201210China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai 201602China School of Life Sciences Tsinghua UniversityBeijing 100084China National Engineering Laboratory for Brain-inspired Intelligence Technology and Application School of Information Science and TechnologyUniversity of Science and Technology of ChinaHefei 230026China Institute of Photonic Chips University of Shanghai for Science and TechnologyShanghai 200093China Centre for Artificial-intelligence Nanophotonics School of Optical-electrical and Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China

Despite its great success,deep learning severely suffers from robustness;i.e.,deep neural networks are very vulnerable to adversarial attacks,even the simplest *** by recent advances in brain science,we propose the denoised internal models(DIM),a novel generative autoencoder-based model to tackle this *** the pipeline in the human brain for visual signal processing,DIM adopts a two-stage *** the first stage,DIM uses a denoiser to reduce the noise and the dimensions of inputs,reflecting the information pre-processing in the *** by the sparse coding of memory-related traces in the primary visual cortex,the second stage produces a set of internal models,one for each *** evaluate DIM over 42 adversarial attacks,showing that DIM effectively defenses against all the attacks and outperforms the SOTA on the overall robustness on the MNIST(Modified National Institute of Standards and Technology)dataset.

关键词： Brain-inspired learning autoencoder robustness adversarial attack generative model

来源：评论

学校读者我要写书评

暂无评论

Optimizing Resource Efficiency in Smart Greenhouses Through IoT

Optimizing Resource Efficiency in Smart Greenhouses Through ...

引用

Emerging Technology (INCET), International Conference for

作者： Subhra Debdas Shikhar Pandey Shivam Gupta Ranjan Kumar Dash Manik Chand Patnaik Anusthan Ajay Singh School of Electrical Engineering KIIT Deemed to Be University Bhubaneswar India School of Computer Engineering KIIT Deemed to Be University Bhubaneswar India Computer Science and Application Odisha University of Technology and Research Bhubaneswar India Department of CSE Roland Institute of Technology Brahmapur India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

In the pursuit of sustainable agriculture, smart greenhouses have emerged as a vital solution, enhancing crop productivity while assuring resource conservation. This research delves into the optimization of resource efficiency in smart greenhouses by leveraging the Internet of Things (IoT). Through a comprehensive review of current technologies and methods, the study identifies key challenges and opportunities within the domain. A novel framework is proposed, integrating IoT sensors and actuators to monitor and control the microclimate, ensuring optimal growth conditions while minimizing resource usage. Data from sensor networks are analyzed to predict resource needs, enabling precision farming practices. The framework emphasizes the use of Machine Learning algorithms to enable predictive analytics for resource allocation, ensuring that water, nutrients, and energy are distributed more efficiently. The potential of Lightweight Resource Allocation (LaRA) algorithms is also explored to maintain the delicate balance between maximizing yield and minimizing environmental impact. Ultimately, this research highlights the transformational potential of IoT in creating green, efficient, and productive agricultural practices within smart greenhouses.

关键词： Temperature measurement Temperature sensors Machine learning algorithms Green products Greenhouses Internet of Things Resource management

来源：评论

学校读者我要写书评

暂无评论

Hybrid CNN-RNN Models for Multimodal Analysis of Autism Spectrum Disorder Neuroimaging

Hybrid CNN-RNN Models for Multimodal Analysis of Autism Spec...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Rajat Kishor Varshney Alok Katiyar Prashant Johri School of Computing Science & Engineering Research Scholar Galgotias University Greater Noida India School of Computing Science & Engineering Professor Galgotias University Greater Noida India School of Computer Application & Technology Professor Galgotias University Greater Noida India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

ASD is a developmental disorder in the neurological category and has numerous and diverse symptoms. Diagnosis is still problematic because symptoms of parkinsonism are diverse, and the dimensionality of the neuroimaging data is high. This paper presents a combination of CNN and RNN for classifying the ASD by analyzing multimodal neuroimaging data such as fMRI data, MRI data, and DTI data. The CNN component analyzes spatial characteristics of the neuroimaging data, and the RNN learns temporal patterns in fMRI series. Enhancements include a novel preprocessing step called 3D Brain Region Alignment (3D-BRA) as well as the 3D version of Adaptive Temporal, minimizing dimensionality through an innovative feature selection technique employing EN-CC. Predictive analysis with the hybrid model utilizes standard benchmark datasets such as ABIDE I, ABIDE II, HCP, and SFARI and records classification performances over 95 percentage. To enhance the interpretability of the model, the Grad-CAM algorithm is used, which marks specific regions of the brain important in the context of ASD. The proposed framework seems to possess considerable feasibility for enhancing the diagnosis of ASD and improving the understanding of its neural substrates, making the developed method highly advantageous for applications in neuroinformatics and clinical utility.

关键词： Neuroimaging Adaptation models Analytical models Three-dimensional displays Accuracy Functional magnetic resonance imaging Predictive models Brain modeling Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Towards Transparent Intelligence: A Comprehensive Review of Explainable AI Methods and applications

Towards Transparent Intelligence: A Comprehensive Review of ...

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： Bhupesh Rawat Nitin Pandey Ankur Bist Yogesh Joshi School of Computing Graphic Era Hill University Bhimtal India Department of Computer Science and Application Amrapali University Haldwani India Department of Computer Science and Engineering Graphic Era Hill University Bhimtal India School of Computing Amrapali University Haldwani India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

As artificial intelligence (AI) continues to advance, the need for transparency and accountability in AI systems becomes increasingly critical. Explainable AI (XAI) emerges as a promising approach to address the inherent opacity of many AI models, enabling humans to understand and trust AI-driven decisions. This paper provides a comprehensive review of the state-of-the-art explainable AI methods and their applications across diverse domains. We delve into various techniques for achieving explainability in AI, including interpretable models, post-hoc explanation methods, and human-AI collaboration approaches. Through a thorough examination of recent research and real-world applications, this review aims to elucidate the importance of transparent intelligence and provide insights into the future directions of explainable AI research.

关键词： Ethics Explainable AI Reviews Computational modeling Decision making Medical services Predictive models Energy efficiency Telecommunication computing Decision trees

来源：评论

学校读者我要写书评

暂无评论

Microgrid Recent Innovations & Uses

Microgrid Recent Innovations & Uses

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Neeraj Kaushik Shubhashis Goswami Keerti Sachan V.J. Vijayalakshmi P. Gajendran V.A. Mishra Department of ECE TMU School of Engineering and Computer Dev Bhoomi Uttarakhand University Uttarakhand School of computer science and application IIMT University meerut Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore Department of Electrical and Electronics Engineering Karpagam College of Engineering Coimbatore Computer Engg Vishwakarma Institute of Information Technology Pune

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Concerns about global warming brought on by increasing carbon dioxide levels in the environment have sped up technological development in the sustainable energy sector over the past few years. The advancement in science while the shift to less polluting materials sources possesses increased the appeal for DG, subsequent generations distributed generation, using renewable supplies. Nevertheless, it has become widely recognized that increasing DG entry can negatively affect the matrix’s layout and operations. A suggestion made to reduce the effect about DG while improve the suitability of traditional grids over massive DG installation involves the Located concept. encompassing a variety of electrical devices’, the elements and Micro-grids and related power gadgets fields are now very well-liked research areas. This essay examines the history and theory behind microgrids, as well as the present situation regarding the writing, active research initiatives, and pertinent requirements. It additionally provides a more thorough analysis of the numerous Located pilot initiatives which have been implemented surrounding the globe and addresses possible directions for future study.

关键词： Technological innovation Layout Hydroelectric power generation Microgrids Carbon dioxide Production Writing Inverters Research initiatives Standards

来源：评论

学校读者我要写书评

暂无评论

Modality-Independent Regression and Training for Improving Multispectral Pedestrian Detection 7

Modality-Independent Regression and Training for Improving M...

引用

7th International Conference on Image, Vision and Computing, ICIVC 2022

作者： Ni, Han Wang, Wenna Yun, Shuai Zhao, Zixu Zhang, Xiuwei Big Data Application Technology National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Xi'an710072 China Northwestern Polytechnical University School of Computer Science Xi'an710072 China

ISBN: (数字)9781665467346

ISBN: (纸本)9781665467346

Multispectral pedestrian detection enables an all-weather detector by fusing the complementary information of RGB and thermal images. However, due to the modality difference and the spatial misalignment between RGB and thermal sensors, the positions of the same pedestrian in two different sensors may be different and some pedestrians may only be visible in one sensor. The existing methods mostly adopt unified annotations to supervise different modalities, this is not conducive to the learning of different modal features. Therefore, we propose a multispectral pedestrian detector based on MBNet with modality-independent regression modules, named MBPNet. It adopts the corresponding modality-independent annotation to train the regression branch for different modalities, separately. Then, a decision-level fusion strategy is introduced to fuse the regression results from different branches. Experiments show that the proposed method outperforms the state-of-the-art methods on the KAIST pedestrian detection dataset. © 2022 IEEE.

关键词： Regression analysis

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：