检索结果-内蒙古大学图书馆

GeoAgriGuard: AI-Driven Pest and Disease Management with Remote Sensing for Global Food Security

Remote Sensing in Earth Systems sciences 2025年第2期8卷 409-422页

作者： Sharada, K. Choudhary, Shailee Lohmor Harikrishna, T. Dixit, Rinku Sharma Suman, Sanjay Kumar Ayyappa Chakravarthi, M. Bhagyalakshmi, L. Department of Computer Science and Engineering GITAM (Deemed to Be University) AP Visakhapatnam India Department of Artificial Intelligence and Machine Learning New Delhi Institute of Management Delhi India Department of AIML Annamacharya University Andhra Pradesh Rajampet India Department of ECE St. Martin’s Engineering College Telangana Secunderabad India Departmentt of CSE-Data Science KSR Institute of Technology and Science KKR & AP Guntur India Department of ECE Rajalakshmi Engineering College TN Chennai India

Agricultural productivity is increasingly threatened by the growing frequency and severity of pest and disease outbreaks, exacerbated by climate change and evolving environmental conditions. The GeoAgriGuard AI-Driven Pest and Disease Management System integrates remote sensing technologies with advanced AI models to address pest and disease outbreaks in agriculture. Utilizing multi-spectral and hyper-spectral satellite and drone imagery, the system processes crop health data through comprehensive preprocessing steps, including radiometric, geometric, and atmospheric corrections. Vegetation indices such as NDVI and NDWI further enhance the data quality, ensuring accurate detection of crop stress. A hybrid deep learning ensemble, combining models like ResNet, Transformer, DenseNet, and AutoEncoders, processes this data to predict and classify pest and disease occurrences. The proposed model achieved a remarkable accuracy of 97.81%, significantly outperforming existing models such as SVM (82.45%) and CNN (90.12%). By integrating these AI predictions with GIS-based spatial analysis, the system generates real-time risk maps, enabling farmers to take timely and localized actions. Performance metrics, including precision (96.72%), recall (95.83%), and F1-score (96.27%), demonstrate the system’s reliability in real-world applications. GeoAgriGuard provides a scalable, data-driven solution for enhancing crop protection and improving global food security. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： AI-driven agriculture Crop disease Deep learning Food security GIS NDVI Pest detection Precision agriculture Remote sensing Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

ENHANCING ZEROTH-ORDER FINE-TUNING FOR LANGUAGE MODELS WITH LOW-RANK STRUCTURES

arXiv

引用

arXiv 2024年

作者： Chen, Yiming Zhang, Yuan Cao, Liyuan Yuan, Kun Wen, Zaiwen Beijing International Center for Mathematical Research Peking University Beijing China Center for Data Science Peking University Beijing China Center for Machine Learning Research Peking University Beijing China

Parameter-efficient fine-tuning (PEFT) significantly reduces memory costs when adapting large language models (LLMs) for downstream applications. However, traditional first-order (FO) fine-tuning algorithms incur substantial memory overhead due to the need to store activation values for back-propagation during gradient computation, particularly in long-context fine-tuning tasks. Zeroth-order (ZO) algorithms offer a promising alternative by approximating gradients using finite differences of function values, thus eliminating the need for activation storage. Nevertheless, existing ZO methods struggle to capture the low-rank gradient structure common in LLM fine-tuning, leading to suboptimal performance. This paper proposes a low-rank ZO gradient estimator and introduces a novel low-rank ZO algorithm (LOZO) that effectively captures this structure in LLMs. We provide convergence guarantees for LOZO by framing it as a subspace optimization method. Additionally, its low-rank nature enables LOZO to integrate with momentum techniques while incurring negligible extra memory costs. Extensive experiments across various model sizes and downstream tasks demonstrate that LOZO and its momentum-based variant outperform existing ZO methods and closely approach the performance of FO algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Identification Fingerprint Based on machine learning Method

引用

Journal of the Operations Research Society of China 2022年第4期10卷 849-860页

作者： Long The Nguyen Huong Thu Nguyen Alexander Diomidovich Afanasiev Tao Van Nguyen Laboratory of Artificial Intelligence and Machine Learning Institute of Information Technology and Data ScienceIrkutsk National Research Technical UniversityIrkutskRussia Baikal School of BRICS Irkutsk National Research Technical UniversityIrkutskRussia University of Information and Communication Technology Thai Nguyen UniversityThai NguyenViet Nam

The fingerprint identification technology has been developed and applied effectively to security systems in financial transactions,personal information security,national security,and other *** this paper,we proposed the development of a fingerprint identification system based on image processing methods that clarify fingerprint contours,using machine learning methods to increase processing speed and increase the accuracy of the fingerprint identification *** identification system consists of the following main steps:improving image quality and image segmentation to identify the fingerprint area,extracting features,and matching the *** accuracy of the system reached 97.75%on the mixed high-and low-quality fingerprint database.

关键词： Fingerprint identification Feature extraction Image segmentation Wavelet transform Neural network algorithm machine learning

来源：评论

学校读者我要写书评

暂无评论

BIM: Improving Graph Neural Networks with Balanced Influence Maximization 40

BIM: Improving Graph Neural Networks with Balanced Influence...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Zhang, Wentao Gao, Xinyi Yang, Ling Cao, Meng Huang, Ping Shan, Jiulong Yin, Hongzhi Cui, Bin Peking University Center for Machine Learning Research China Institute of Advanced Algorithms Research Shanghai China National Engineering Labratory for Big Data Analytics and Applications The University of Queensland Australia Peking University Key Lab of High Confidence Software Technologies China Apple Inc. Institute of Computational Social Science Peking University Qingdao China

ISBN: (纸本)9798350317152

The imbalanced data classification problem has aroused lots of concerns from both academia and industry since data imbalance is a widespread phenomenon in many real-world scenarios. Although this problem has been well researched from the view of imbalanced class samples, we further argue that graph neural networks (GNNs) expose a unique source of imbalance from the influenced nodes of different classes of labeled nodes, i.e., labeled nodes are imbalanced in terms of the number of nodes they influenced during the influence propagation in GNNs. To tackle this previously unexplored influence-imbalance issue, we connect social influence maximization with the imbalanced node classification problem and propose balanced influence maximization (BIM). Specifically, BIM greedily assigns the pseudo label to the node which can maximize the number of influenced nodes in GNN training while making the influence of each class more balance. Experimental results on five public datasets demonstrate the effectiveness of our method in relieving the influence-imbalance issue. For example, when training a GCN with an imbalance ratio of 0.1, BIM significantly outperforms the most competitive baseline by 0.6% -9.8% in five public datasets in terms of the F1 score. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Sustainable Urban Street Lighting through Predictive Maintenance using IoT and AI

Sustainable Urban Street Lighting through Predictive Mainten...

引用

Emerging Research in Computational science (ICERCS), International Conference on

作者： Sudharson D Jananiksha P Mukilarasu R Sushmita V Vaishali V Rini Vaishnavi R S Artificial Intelligence and Data Science Kumaraguru College of Technology Coimbatore India CSE – Artificial Intelligence and Machine Learning Vellore Institute of Technology Vellore India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534974

The potential for transformative urban management is enhanced through the integration of IoT and AI, creating smart ecosystems that revolutionize intelligent lighting systems. This paper explores predictive maintenance solutions for urban street lighting, leveraging advanced machine learning models such as Temporal Fusion Transformer (TFT), Temporal Aggregation and Decomposition-based Attention (TADA), and Graph Neural Networks (GNNs). By analyzing historical operational data, these models detect subtle fault patterns and predict failures, improving system reliability, reducing maintenance costs, and optimizing energy use. The work contributes to United Nations SDGs 11 and 9 by promoting sustainable urban infrastructure and smart city development, fostering a future where IoT and AI systems enhance sustainability and resilience.

关键词： Smart cities Scientific computing Biological system modeling Lighting Predictive models Transformers Thin film transistors Sustainable development Predictive maintenance Resilience

来源：评论

学校读者我要写书评

暂无评论

Attention based 1-D CNN system for detection of Freezing of gait (FOG) in Parkinsons Patients

Attention based 1-D CNN system for detection of Freezing of ...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： D Pradeep Kumar B J Sowmya Ashvin Vincent Aravindh Pandiyan Department of Computer Science and Engineering Ramaiah Institute of Technology Bangalore India Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Bangalore India Machine Learning Engineer Bangalore India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

One common clinical symptom seen in Parkinson’s disease (PD) patients is freezing of gait (FOG). It manifests as an irregular gait, marked by abrupt, involuntary stopping of movement during gait episodes. FOG entails a major negative effect on PD patients’ quality of life. In this work, we analyze the movement data that is collected using the lower-back 3D accelerometer worn by the patients during FOG episodes. By employing machine learning methods to classify this data, we aim to accurately detect FOG trends. In particular, we focus on Deep learning-based techniques, specifically an attention-based 1D Convolutional Neural Network (1D-CNN), due to their capacity to extract intricate features from unprocessed sensor input. Our results indicate that the proposed model achieves AUC scores of 0.9032 with respect to the TDCSFOG dataset and 0.8682 for the DeFOG dataset, for a combined average AUC of 0.8857. Mean Average Precision (mAP) scores for TDCSFOG and DeFOG reach 0.8388 and 0.779, respectively, for an average of 0.8089, showing the ability of the model to predict FOG occurrences over time. These findings suggest techniques based on Deep learning enhance FOG detection, allowing clinicians to more effectively tailor treatments and care strategies for Parkinson’s patients, thus enhancing their ability to move and overall well-being.

关键词： Deep learning Accelerometers Three-dimensional displays Accuracy Predictive models Feature extraction Transformers Convolutional neural networks Forecasting Diseases

来源：评论

学校读者我要写书评

暂无评论

SMOOTHNESS SPACES FOR WARPED TIME-FREQUENCY REPRESENTATIONS - DECOMPOSITION SPACES AND EMBEDDING RELATIONS

arXiv

引用

arXiv 2024年

作者： Holighaus, Nicki Voigtlaender, Felix Acoustics Research Institute Austrian Academy of Sciences Wohllebengasse 12–14 ViennaA-1040 Austria Mathematical Institute for Machine Learning and Data Science Katholische Universität Eichstätt-Ingolstadt Auf der Schanz 49 Ingolstadt85049 Germany

In a recent paper, we have shown that warped time-frequency representations provide a rich framework for the construction and study of smoothness spaces matched to very general phase space geometries obtained by diffeomorphic deformations of Rd. Here, we study these spaces, obtained through the application of general coorbit theory, using the framework of decomposition spaces. This allows us to derive embedding relations between coorbit spaces associated to different warping functions, and relate them to established, important smothness spaces. In particular, we show that we obtain α-modulation spaces and spaces of dominating mixed smoothness as special cases and, in contrast, that this is only possible for Besov spaces if d = *** Codes 42B35, 46E35, 46F05, 46F12 © 2024, CC BY.

关键词： Phase space methods

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Task Modelling for Meta-learning 37

Probabilistic Task Modelling for Meta-Learning

引用

37th Conference on Uncertainty in Artificial Intelligence, UAI 2021

作者： Nguyen, Cuong C. Do, Thanh-Toan Carneiro, Gustavo Australian Institute for Machine Learning University of Adelaide Australia Department of Data Science and AI Monash University Australia

We propose probabilistic task modelling - a generative probabilistic model for collections of tasks used in meta-learning. The proposed model combines variational auto-encoding and latent Dirichlet allocation to model each task as a mixture of Gaussian distribution in an embedding space. Such modelling provides an explicit representation of a task through its task-theme mixture. We present an efficient approximation inference technique based on variational inference method for empirical Bayes parameter estimation. We perform empirical evaluations to validate the task uncertainty and task distance produced by the proposed method through correlation diagrams of the prediction accuracy on testing tasks. We also carry out experiments of task selection in meta-learning to demonstrate how the task relatedness inferred from the proposed model help to facilitate meta-learning algorithms. © 2021 37th Conference on Uncertainty in Artificial Intelligence, UAI 2021. All Rights Reserved.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Big data in Social Media: Analyzing Trends, Patterns and Challenges 2

Big Data in Social Media: Analyzing Trends, Patterns and Cha...

引用

2nd International Conference on machine learning and Autonomous Systems, ICMLAS 2025

作者： Jikar, Nayan Tale, Yash Tale, Abhay Barhate, Aditya Verma, Prateek Jikar, Aman Datta Meghe Institute of Higher Education and Research Sawangi Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Sawangi Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

The huge volumes of data produced in social media provide both new possibilities and challenges to analytics. The present paper emphasizes Big data analytics and machine learning (ML) methods to uncover trends, patterns, and user behavior from social media-related data. Such vital concepts, like the 'Four Vs' of Big data: Volume, Velocity, Variety, and Veracity, and innovative tools for datacollection, storage, and preprocessing are covered here as well. Sentiment analysis, trend forecasting, and user behaviormodeling are some of the examples of what is possible using ML and Artificial Intelligence (AI) for deriving actionable insights. Marketing campaigns, crisis communications, and political campaigns are some of the scenarios that are covered to bring out real world applications of such technologies, along with their transformative effects. Lastly, data privacy, quality, and scalability issues are noted, along with ethical concerns and biases. Directions for the future point to developments in real-time data analysis, anonymization, and the changing role of AI in social media platforms. This research emphasizes the significance of Big data and machine learning in driving innovation and decision-making in the digital era. © 2025 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Diffusion-Based Method with TTS Guidance for Foreign Accent Conversion

Diffusion-Based Method with TTS Guidance for Foreign Accent ...

引用

International Symposium on Chinese Spoken Language Processing

作者： Qibing Bai Shuai Wang Zhijun Liu Mingyang Zhang Wei Rao Yannan Wang Haizhou Li School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen Tencent Ethereal Audio Lab Tencent Machine Learning Lab (MLL) University of Bremen

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

Accent conversion (AC) aims to alter the accent of spoken language while preserving the original content and speaker characteristics. While any accent can be selected as a target, foreign accent conversion (FAC) that focuses on L2 speakers is particularly noteworthy due to its wide-ranging applications. Compared to general voice conversion tasks, which focus on speaker conversion, research related to accent conversion is relatively scarce, and the audio quality is often limited. In this article, we introduce a diffusion decoder into the conventional TTS-guided accent conversion framework and propose a phoneme-level acoustic-linguistic alignment strategy. Subjective evaluations on the Chinese-accent source speech confirm that the proposed method outperforms the baseline in terms of speech naturalness, accentedness, and speaker similarity 1 1 Audio samples are available at ***..

关键词： Decoding

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：