检索结果-内蒙古大学图书馆

Comparative analysis of preprocessing methods and machine learning models for geographical origin identification in an imbalanced Panax notoginseng dataset with near-infrared spectroscopy

学校读者我要写书评

暂无评论

Comparative analysis of preprocessing methods and machine le...

2024 International Conference on Artificial Intelligence and Machine Learning research, CAIMLR 2024

作者： Cheng, Xuefeng Buhari, Abudhahir Zhu, Hongmei Cheng, Changyin Liu, Juan Faculty of Engineering Science & Technology Infrastructure University Kuala Lumpur Kajang Malaysia School of Big Data and Information Industry Chongqing City Management College Chongqing China School of Artificial Intelligence Chongqing University of Education Chongqing China Chongqing University Chongqing China Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing College University of Chinese Academy of Sciences Chongqing China

ISBN: (纸本)9781510691797

Imbalanced sample distributions pose challenges in accurately identifying the geographical origin of Panax notoginseng (P. Notoginseng), impacting machine learning model performance. This study investigates the efficacy of various data preprocessing methods and machine learning models on geographical origin classification accuracy using near-infrared spectroscopy (NIRS) in imbalanced datasets. Results demonstrate that specific combinations of preprocessing methods and models can significantly improve classification accuracy, bridging the gap between imbalanced and balanced datasets. These findings highlight the importance of tailored approaches to mitigate model and evaluation bias, imbalanced sample weights, and decision boundary shifts in P. Notoginseng datasets. Moreover, the insights gleaned from this study have implications for similar analyses in other traditional Chinese medicinal materials. © 2025 SPIE.

关键词： Near infrared spectroscopy

DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching 39

学校读者我要写书评

暂无评论

DAMPER: A Dual-Stage Medical Report Generation Framework wit...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Huang, Xiaofei Chen, Wenting Liu, Jie Lu, Qisheng Luo, Xiaoling Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)157735897X

Medical report generation is crucial for clinical diagnosis and patient management, summarizing diagnoses and recommendations based on medical imaging. However, existing work often overlook the clinical pipeline involved in report writing, where physicians typically conduct an initial quick review followed by a detailed examination. Moreover, current alignment methods may lead to misaligned relationships. To address these issues, we propose DAMPER, a dual-stage framework for medical report generation that mimics the clinical pipeline of report writing in two stages. In the first stage, a MeSH-Guided Coarse-Grained Alignment (MCG) stage that aligns chest X-ray (CXR) image features with medical subject headings (MeSH) features to generate a rough keyphrase representation of the overall impression. In the second stage, a Hypergraph-Enhanced Fine-Grained Alignment (HFG) stage that constructs hypergraphs for image patches and report annotations, modeling high-order relationships within each modality and performing hypergraph matching to capture semantic correlations between image regions and textual phrases. Finally,the coarse-grained visual features, generated MeSH representations, and visual hypergraph features are fed into a report decoder to produce the final medical report. Extensive experiments on public datasets demonstrate the effectiveness of DAMPER in generating comprehensive and accurate medical reports, outperforming state-of-the-art methods across various evaluation metrics. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Diagnosis

Compressed Sensing Based Channel Estimation for Movable Antenna Communications

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ma, Wenyan Zhu, Lipeng Zhang, Rui The Department of Electrical and Computer Engineering National University of Singapore 117583 Singapore School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Guangdong Shenzhen518172 China

In this letter, we study the channel estimation for wireless communications with movable antenna (MA), which requires to reconstruct the channel response at any location in a given region where the transmitter/receiver is located based on the channel measurements taken at finite locations therein, so as to find the MA's location for optimizing the communication performance. To reduce the pilot overhead and computational complexity for channel estimation, we propose a new successive transmitter-receiver compressed sensing (STRCS) method by exploiting the efficient representation of the channel responses in the given transmitter/receiver region (field) in terms of multi-path components. Specifically, the field-response information (FRI) in the angular domain, including the angles of departure (AoDs)/angles of arrival (AoAs) and complex coefficients of all significant multi-path components are sequentially estimated based on a finite number of channel measurements taken at random/selected locations by the MA at the transmitter and/or receiver. Simulation results demonstrate that the proposed channel reconstruction method outperforms the benchmark schemes in terms of both pilot overhead and channel reconstruction accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Antennas

Tobacco Plant Disease dataset 14

学校读者我要写书评

暂无评论

Tobacco Plant Disease Dataset

14th International Conference on Digital Image Processing, ICDIP 2022

作者： Lin, Hong Tse, Rita Tang, Su-Kit Qiang, Zhenping Ou, Jinliang Pau, Giovanni Faculty of Applied Sciences Macao Polytechnic University China Engineering Research Centre of Applied Technology on Machine Translation and Artificial Intelligence of Ministry of Education Macao Polytechnic University China College of Big Data and Intelligent Engineering Southwest Forestry University KunMing China Department of Computer Science and Engineering-DISI University of Bologna Italy Samueli Computer Science Department University of California Los Angeles United States

ISBN: (纸本)9781510657564

Tobacco is a valuable plant in agricultural and commercial industry. Any disease infection to the plant may lower the harvest and interfere the operation of supply chain in the market. Image-based deep learning methods are cutting-edge technologies that can facilitate the diagnosis of diseases efficiently and effectively when large-scale dataset is available for training. However, there is not a public dataset about tobacco currently. A comprehensive dataset is appealed to take advantage of deep learning methods in tobacco cultivation urgently. In this paper, we propose to create a specific dataset for tobacco diseases, called Tobacco Plant Disease dataset (TPDD). 2721 tobacco leaf images are taken in field. The dataset serves for two purposes: disease classification and leaf detection. For classification, we identify 12 classes and provide two types of disease annotations: 1) Whole Leaf Section;2) Disease Fragment Section. For leaf detection, we provide two kinds of bounding box: rectangle bounding box and polygon bounding box. In addition, we conduct baseline experiments to illustrate the usefulness of TPDD: 1) using deep learning model to detect single disease and multiple diseases;2) using YOLO-v3 and Mask-RCNN to detect leaves. We hope that the dataset could support the tobacco industry, also be a benchmark in fine-grained vision classification. © 2022 SPIE.

关键词： Computer vision

Neural Network-Based Wind Field Reconstruction Method with Limited Measurement Points for Urban Blocks

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Wang, Ranpeng Liu, Yi Li, Congjian Gao, Hang Wang, Gangqiao Institute of Public Safety Research Department of Engineering Physics Tsinghua University Beijng100084 China School of Safety Science Tsinghua University Beijing100084 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China College of Artificial Intelligence Tianjin University of Science and Technology Tianjin300450 China Institute of Big Data intelligent Management and Decision College of Management Shenzhen University Shenzhen518055 China

The rapid reconstruction of wind fields in urban blocks plays a crucial role in retrofitting zero-energy buildings, guiding the selection and placement of wind turbines. Although numerical methods and the Proper Orthogonal Decomposition (POD) method can provide relatively accurate results, their high computational cost and associated discontinuities pose challenges for acquiring high-spatial-resolution data affected by buildings. In this study, we develop a deep learning approach that can reconstruct wind fields affected by complex building layouts using a limited number of measuring points. The model is meticulously crafted with considerations given to model structure, loss function, and point selection method. Extensive analysis and comparisons with conventional designs are conducted to validate the proposed model. The results demonstrate that our model outperforms the conventional methods, achieving a mean absolute error in velocity of only 0.12 m/s over the inlet velocity range of 1 to 20 m/s, with only ten measurement points. Furthermore, a comparison with the POD method reveals that our model excels in extracting and preserving the crucial features of wind fields affected by complex building layouts, enabling higher migration capability. Overall, the proposed method delivers the potential for accurately reconstructing wind fields in urban blocks. © 2024, The Authors. All rights reserved.

关键词： Numerical methods

Two-Stage Incentive Mechanism Based on a Cooperative Mode: A Stackelberg Game Approach

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2025年

作者： Wang, Long Wang, Yingjie Teng, Haojun Jiao, Xiuzhen Sun, Meimei Yang, Jishen Cai, Zhipeng Yantai University School of Computer and Control Engineering Yantai264005 China China Judicial Big Data Research Institute Co. Ltd China Naval Aviation University China Georgia State University Department of Computer Science AtlantaGA30303 United States

With the explosive growth of mobile data, Mobile Crowd Sensing (MCS) has become a popular paradigm for large-scale data collection. The difficulty of data collection and the gaps in workers’ sensing capabilities are key factors to consider in worker recruitment and task assignment. To address these issues, we designed a two-stage cooperative incentive mechanism. In the first stage, a shelving level is introduced to assess task difficulty. Tasks are divided into high-quality and low-quality groups based on quality scores, while workers are categorized into high-ability and low-ability groups based on their historical performance. The Improved Chaotic Particle Swarm Optimization (ICPSO) algorithm is then applied to generate optimal task combinations. In the second stage, we address benefit distribution among cooperating workers by introducing time-dependent rewards and employing Stackelberg game theory to analyze the optimal completion time for both high-ability and low-ability workers. This analysis determines the optimal reward distribution and ability value allocation, with proof of the existence and uniqueness of a Nash equilibrium. Comparative experiments conducted on real-world datasets demonstrate that our cooperative task mechanism outperforms existing task bundling methods, validating its rationality and effectiveness. © 2014 IEEE.

关键词： Nash equilibrium

Urban Water Sprinkler Routing: A Multi-Depot Mixed Capacitated Arc Routing Problem Incorporating Real-Time Demands

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Hongtai Liu, Luna Han, Ke Lei, Boyi School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology National United Engineering Laboratory of Integrated and Intelligent Transportation Institute of System Science and Engineering Southwest Jiaotong University Chengdu611756 China School of Economics and Management Southwest Jiaotong University Chengdu611756 China

Fugitive road dust (FRD), as one of the major pollutants in the city, poses great harm to the environment and the physical health of citizens. A common countermeasure adopted by government agencies is employing on-road water trucks (sprinklers) to spray water (sprinkle) on urban streets to reduce the FRD. Currently, the traveling routes of sprinklers are usually planned based on drivers’ experience, which may lead low operation efficiency and could not respond to the real-time sprinkling demands. To address these issues, this study formulates the routes planning of sprinklers as a multi-depot mixed capacitated arc routing problem with real-time demands with the aim of minimizing the sprinklers’ travel distance. We develop an improved adaptive large neighborhood search (ALNS) algorithm that incorporates a tabu-list and a perturbation mechanism to solve this problem. Furthermore, a problem-specific acceleration mechanism is designed to reduce unnecessary search domains to improve the efficiency of the algorithm. Empirical experiments are conducted based on various scenarios and the results demonstrate that the proposed algorithm generates solutions that are superior or at least comparable to the solutions generated by the traditional ALNS algorithm but with significantly lower computation time. Sensitivity analysis is conducted to explore the effects of relevant parameters on the results. This study is the first to incorporate real-time FRD pollution information, gathered through multiple data sources via IoT technology, into urban sprinkling operations, extending the traditional CARP from a tactical planning to a real-time operational environment. A real-world implementation case is also presented. Copyright © 2024, The Authors. All rights reserved.

关键词： Efficiency

Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Junjia Li, Haofeng Wan, Xiang Li, Guanbin School of Computer Science and Engineering Research Institute of Sun Yat-sen University in Shenzhen Sun Yat-sen University Guangzhou China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China

Multi-class cell nuclei detection is a fundamental prerequisite in the diagnosis of histopathology. It is critical to efficiently locate and identify cells with diverse morphology and distributions in digital pathological images. Most existing methods take complex intermediate representations as learning targets and rely on inflexible post-refinements while paying less attention to various cell density and fields of view. In this paper, we propose a novel Affine-Consistent Transformer (AC-Former), which directly yields a sequence of nucleus positions and is trained collaboratively through two sub-networks, a global and a local network. The local branch learns to infer distorted input images of smaller scales while the global network outputs the large-scale predictions as extra supervision signals. We further introduce an Adaptive Affine Transformer (AAT) module, which can automatically learn the key spatial transformations to warp original images for local network training. The AAT module works by learning to capture the transformed image regions that are more valuable for training the model. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms on various benchmarks. Copyright © 2023, The Authors. All rights reserved.

关键词： Cells

Covariance-Based Device Activity Detection with Massive MIMO for Near-Field Correlated Channels

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Ziyue Li, Yang Liu, Ya-Feng Ma, Junjie The State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China The Shenzhen Research Institute of Big Data Shenzhen518172 China The School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China

This paper studies the device activity detection problem in a massive multiple-input multiple-output (MIMO) system for near-field communications (NFC). In this system, active devices transmit their signature sequences to the base station (BS), which detects the active devices based on the received signal. In this paper, we model the near-field channels as correlated Rician fading channels and formulate the device activity detection problem as a maximum likelihood estimation (MLE) problem. Compared to the traditional uncorrelated channel model, the correlation of channels complicates both algorithm design and theoretical analysis of the MLE problem. On the algorithmic side, we propose two computationally efficient algorithms for solving the MLE problem: an exact coordinate descent (CD) algorithm and an inexact CD algorithm. The exact CD algorithm solves the one-dimensional optimization subproblem exactly using matrix eigenvalue decomposition and polynomial root-finding. By approximating the objective function appropriately, the inexact CD algorithm solves the one-dimensional optimization subproblem inexactly with lower complexity and more robust numerical performance. Additionally, we analyze the detection performance of the MLE problem under correlated channels by comparing it with the case of uncorrelated channels. The analysis shows that when the overall number of devices N is large or the signature sequence length L is small, the detection performance of MLE under correlated channels tends to be better than that under uncorrelated channels. Conversely, when N is small or L is large, MLE performs better under uncorrelated channels than under correlated ones. Simulation results demonstrate the computational efficiency of the proposed algorithms and verify the correctness of the analysis. Copyright © 2024, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions