检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Han, Keji Li, Yun Long, Xianzhong Ge, Yao Nanjing University of Posts and Telecommunications China Jiangsu Key Laboratory of Big Data Security & Intelligent Processing

Many works demonstrate that deep learning system is vulnerable to adversarial attack. A deep learning system consists of two parts: the deep learning task and the deep model. Nowadays, most existing works investigate the impact of the deep model on robustness of deep learning systems, ignoring the impact of the learning task. In this paper, we adopt the binary and interval label encoding strategy to redefine the classification task and design corresponding loss to improve robustness of the deep learning system. Our method can be viewed as improving the robustness of deep learning systems from both the learning task and deep model. Experimental results demonstrate that our learning task-aware method is much more robust than traditional classification while retaining the accuracy. © 2020, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

HAM:a deep collaborative ranking method incorporating textual information

引用

Frontiers of Information Technology & Electronic Engineering 2020年第8期21卷 1206-1216页

作者： Cheng-wei WANG Teng-fei ZHOU Chen CHEN Tian-lei HU Gang CHEN The Key Laboratory of Big Data Intelligent Computing of Zhejiang Province Hangzhou 310027China State Key Lab of CAD&CG Zhejiang UniversityHangzhou 310027China College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China

The recommendation task with a textual corpus aims to model customer preferences from both user feedback and item textual *** is highly desirable to explore a very deep neural network to capture the complicated nonlinear ***,training a deeper recommender is not as effortless as simply adding layers.A deeper recommender suffers from the gradient vanishing/exploding issue and cannot be easily trained by gradient-based ***,textual descriptions probably contain noisy word *** extracting feature vectors from them can harm the recommender’s *** overcome these difficulties,we propose a new recommendation method named the HighwAy reco Mmender(HAM).HAM explores a highway mechanism to make gradient-based training methods stable.A multi-head attention mechanism is devised to automatically denoise textual ***,a block coordinate descent method is devised to train a deep neural *** studies show that the proposed method outperforms state-of-the-art methods significantly in terms of accuracy.

关键词： Deep learning Recommendation system Highway network Block coordinate descent

来源：评论

学校读者我要写书评

暂无评论

Building Cooling load prediction based on LightGBM

引用

IFAC-PapersOnLine 2022年第11期55卷 114-119页

作者： RuoChen Zhao Dong Wei YiBing Ran Guang Zhou YuChen Jia ShiLun Zhu YouQuan He School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Xicheng District Beijing 100032 China Beijing Municipal Science and Technology Commission Key Laboratory of Intelligent Processing for Building Big Data Xicheng District Beijing 100032 China Siemens Ltd. China 100020 China Zhongkai University of Agriculture and Engineering Guangzhou Tevo Energy Management Co. Ltd.

In building Heating Ventilation and Air Conditioning (HVAC) control systems, the HVAC must be controlled in real-time according to the actual building cooling load demand while minimizing energy consumption. Given that the building cooling load is affected by several factors and that historical data are sparse and have outliers due to sensor errors, existing prediction methods cannot accurately calculate the building's cooling load demand. Therefore, this paper first pre-processes the historical building cooling load data, fills in the missing data utilizing the KNNImputer algorithm, and then locates and replaces the outlier data through the 3-sigma method, solving the poor data availability problem. Moreover, to address the problem of small feature variety in historical data, this paper analyzes the time features and the climatic features separately. Specifically, our method splits the time features into several independent features for describing the impact of pedestrian flow on the building cooling load and expands the climatic features to increase the variety of the features that can be used for training and improving the model's prediction accuracy. Finally, the LightGBM algorithm is exploited to train the processed data and build a building cooling load prediction model. The proposed data pre-processing method and model training algorithm are validated through Python programming, with the results highlighting that the proposed method effectively improves the prediction accuracy of building cooling loads.

关键词： Building cooling load prediction LightGBM data pre-processing KNN 3Sigma

来源：评论

学校读者我要写书评

暂无评论

An Orbital Angular Momentum Mode Estimation Method with an Unknown Beam Axis

An Orbital Angular Momentum Mode Estimation Method with an U...

引用

IEEE SENSORS

作者： Gaofeng Shu Bingxu Chen Ning Li School of Computer and Information Engineering Henan University Henan Engineering Research Center of Intelligent Technology and Application Henan University Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

Orbital angular momentum (OAM) beam is very difficult to receive due to the divergence of the beam. The position of the beam axis must be known by the existing receiving methods, including the single point method and the phase gradient method. This article proposes an OAM mode estimation method with an unknown beam axis. This method first estimates the position of the beam axis according to the phase characteristics and then uses the phase gradient method to estimate the OAM mode. The simulation results verify the effectiveness of the method.

关键词： Gradient methods Simulation Estimation Orbits Sensors

来源：评论

学校读者我要写书评

暂无评论

Three-way conflict analysis model via the best-worst method: Balancing subjective preferences and objective data on incomplete and dispersed systems

引用

International Journal of Approximate Reasoning 2025年 186卷

作者： Zhu, Junjie Zhang, Qinghua Luo, Nanfang Liu, Fan Yin, Longjun School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing400065 China Tourism Multi-source Data Perception and Decision Technology Key Laboratory of the Ministry of Culture and Tourism Chongqing400065 China

In real-world environments, different issues contribute to conflicts with varying weights. However, current conflict analysis weighting models face significant limitations when dealing with incomplete data and dispersed knowledge. Objective methods are sensitive to missing values and struggle to accurately capture authentic preferences, while subjective approaches lack systematic evaluation criteria, leading to substantial randomness in weight assignments. Therefore, a three-way conflict analysis model via the best-worst method is proposed, which is combined with a correlation coefficient method to balance subjective preferences and objective data. First, the trisection of agent pairs is derived through Bayesian minimum risk. Subsequently, a new conflict distance function is defined on the incomplete information system to provide a more precise measurement of conflict degrees. Then, for incomplete and dispersed information systems, a maximal coalition-based agent partitioning algorithm is designed, along with a new weighted voting mechanism to aggregate dispersed knowledge. Finally, the scientific transparency of the weighting process, as well as the robustness and feasibility of the model, are demonstrated through experimental analysis. © 2025 Elsevier Inc.

关键词： Distributed database systems

来源：评论

学校读者我要写书评

暂无评论

Reconstructing Missing Modalities in Multi-Modal Endoscopic Ultrasound Via Cross-Modal Feature Replacement Representation

SSRN

引用

SSRN 2024年

作者： Zheng, Cenyang Gong, Xun Fan, Lin Li, Jiao School of Computing and Artificial Intelligence Southwest Jiaotong University Sichuan Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China Department of Gastroenterology The Third People’s Hospital of Chendu Affiliated Hospital of Southwest Jiaotong University Chengdu610031 China

Endoscopic ultrasound (EUS) is the primary diagnostic imaging technique for gastrointestinal stromal tumors. However, accurately identifying these tumors through EUS imaging alone remains challenging, even for experienced clinicians. They often rely on additional data, such as white light endoscopy (WLE) and EUS text reports, to aid in the diagnosis. Unfortunately, in practice, these supplementary modalities are sometimes overlooked during patient evaluation. To address these issues, we propose the Cross-modal Feature Reconstruction Network (CFRN), which integrates multimodal data modeling for medical diagnostic processes and performs specific learning for different modalities with missing data. The network fuses the multi-modal features based on the clinical medical process, realizes the feature-level missing modality reconstruction, and learns the refined features of different modal true cases by decoding the mode-specific missing. We trained and tested the model on two publicly available datasets, Audiovision-MNIST, MM-IMDb, and data sets collected from real clinical scenarios at three hospitals. Our results show that CFRN outperforms state-of-the-art methods, achieving higher prediction accuracy than using EUS alone. By simultaneously incorporating multimodal or reconstructed modal data for disease diagnosis, our single-modal EUS model proves to be more suitable for clinical scenarios. © 2024, The Authors. All rights reserved.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Research on Crop Disaster Stress Risk Mapping System Based on Agriculture big data

Research on Crop Disaster Stress Risk Mapping System Based o...

引用

Electronic Information Technology and Smart Agriculture (ICEITSA), International Conference on

作者： Chunqiao Mi Xiaoning Peng Ling Peng Changhua Zhao Xiaowu Deng School of Computer Science and Engineering Huaihua University Huaihua Hunan China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture Huaihua University Huaihua Hunan China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application Hunan Province Universities Huaihua University Huaihua Hunan China

ISBN: (纸本)9781665413015

At present, the research on crop disaster risk is mostly carried out from the perspective of numerical simulation in one factor aspect, and there is a lack of information system practice that can integrate disaster spatio-temporal analysis technologies such as environment characteristic information extraction, geographic data scale transformation, spatial analysis and map visualization. Based on agriculture big data and highlighting the spatial characteristics of crop disasters, in this study a method of crop disaster risk mapping is designed and a prototype system is implemented, which function is composed of agriculture big data cleaning, scale conversion, multi-source data fusion, feature information extraction, risk probability prediction and map visualization. A specific application of the system is also demonstrated by taking the production of thematic map of wind-induced lodging risk probability distribution during maize jointing and tasseling stage as an example, which shows great help for avoiding maize lodging risk in agriculture practice. The research results have a good role in improving the technical level of agriculture disaster mapping and analysis, and improving the efficiency and effect of disaster prevention and reduction in agriculture production. It has important academic significance for promoting the application of big data in agriculture disaster management and establishing a new perspective of crop disaster mapping, and has important practice application value for optimizing the fine zoning of crop planting area and strengthening the accurate management of agriculture disaster risk.

关键词： Crops data visualization Prototypes Production big data Information retrieval Agriculture

来源：评论

学校读者我要写书评

暂无评论

LungX-Net: Lung Cancer Diagnosis from CT and Histopathological Images via Attention Based Multi-Level Feature Fusion Network

LungX-Net: Lung Cancer Diagnosis from CT and Histopathologic...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Sohaib Asif Vicky Yang Wang Dong Xu Taizhou Campus of Zhejiang Cancer Hospital (Taizhou Cancer Hospital) Taizhou Key Laboratory of Minimally Invasive Interventional Therapy & Artificial Intelligence Taizhou China Center of Intelligent Diagnosis and Therapy (Taizhou) Hangzhou Institute of Medicine (HIM) Chinese Academy of Sciences Taizhou China Wenling Institute of Big Data and Artificial Intelligence in Medicine Taizhou China Department of Diagnostic Ultrasound Imaging & Interventional Therapy Zhejiang Cancer Hospital Hangzhou Institute of Medicine (HIM) Chinese Academy of Sciences Hangzhou China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Lung cancer ranks among the top causes of cancer mortality worldwide. However, early detection can significantly boost survival rates, potentially increasing them by as much as 70%. While deep learning algorithms have shown promise in detecting lung cancer from CT scans, current methods are often inefficient, and single-model approaches struggle with complex medical images. Leveraging diverse model features can enhance accuracy and simplify detection. This paper introduces LungX-Net, an innovative and cost-effective deep learning model aimed at improving lung cancer diagnostic accuracy using CT and histopathological images. The proposed model unifies two networks into a unified, trainable feature extraction architecture, employing model compression to preserve essential core blocks. This approach enhances the model’s ability to propagate strong and robust features while significantly reducing computational resource requirements. The model also integrates a Convolutional Block Attention Module (CBAM) to enhance feature extraction by emphasizing the most important regions, which further improves overall accuracy. The integration of these techniques optimizes diagnostic performance while strategically minimizing complexity, making LungX-Net a powerful tool for efficient and precise lung cancer diagnosis. The proposed LungX-Net was evaluated on both CT and histopathological datasets, achieving a recognition accuracy of 99.09% on the CT dataset and 99.30% on the histopathological dataset. LungX-Net demonstrated superior performance compared to previous approaches, achieving greater accuracy with fewer parameters and faster testing times, highlighting its efficiency and cost-effectiveness.

关键词： Deep learning Accuracy Computed tomography Computational modeling Lungs Lung cancer Mortality Feature extraction Medical diagnostic imaging Testing

来源：评论

学校读者我要写书评

暂无评论

Multi-label Contrastive Focal Loss for Pedestrian Attribute Recognition

Multi-label Contrastive Focal Loss for Pedestrian Attribute ...

引用

International Conference on Pattern Recognition

作者： Xiaoqiang Zheng Zhenxia Yu Lin Chen Fan Zhu Shilong Wang Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China School of computer science Chengdu University Of Information Technology Chengdu China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China

Pedestrian Attribute Recognition (PAR) has received extensive attention during the past few years. With the advances of deep convolutional neural networks (CNNs), the performance of PAR has been significantly improved. Existing methods tend to acquire attribute-specific features by designing various complex network structures with additional modules. Such additional modules, however, dramatically increase the number of network parameters. Meanwhile, the problems of class imbalance and hard attribute retrieving remain underestimated in PAR. In this paper, we explore the optimization mechanism of the training processing to account for these problems and propose a new loss function called Multi-label Contrastive Focal Loss (MCFL). This proposed MCFL emphasizes the hard and minority attributes by using a separated re-weighting mechanism for different positive and negative classes to alleviate the impact of the imbalance. MCFL is also able to enlarge the gaps between the intra-class of multi-label attributes, to force CNNs to extract more subtle discriminative features. We evaluate the proposed MCFL on three large public pedestrian datasets, including RAP, PA-100K, and PETA. The experimental results indicate that the proposed MCFL with the ResNet-50 backbone is able to outperform other state-of-the-art approaches in term of mean accuracy.

关键词： Training Visualization Force Complex networks Feature extraction Pattern recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Random Forest-Based Ensemble Estimator for Concrete Compressive Strength Prediction via AdaBoost Method 15th

Random Forest-Based Ensemble Estimator for Concrete Compress...

引用

15th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2019, co-located with the 5th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2019

作者： Lv, Yuanxin Shi, Xiaoyu Ran, Longyu Shang, Mingsheng College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9783030325909

As one of the most important building materials, the quality of concrete directly affects the safety of buildings. Hence, it is an important and hot issue to predict the compressive strength of concrete with highly accuracy. Most of existing methods heavily depend on building a single model to predict the compressive strength of concrete. However, the proposed single models are not one-size-fits-all, different model have different limitations, making them a better or worse fit for different situation. To address this issue, this paper proposes a novel predict model for concrete compressive strength based on ensemble learning method. In detail, we build our ensemble framework via using the AdaBoost method, while the random forests methods as weak classifier are integrated to the AdaBoost framework. For dealing with the noisy and missing value problems, a set of statistical methods are employed. Furthermore, we utilize the Pearson correlation coefficient to analysis the relationship between different input materials, which can effectively drop out the irrelevant and redundant features. Experimental results on two industrial data sets show that proposed ensemble estimator can significantly improve the prediction accuracy in comparing with other five state-of-the-art methods. © 2020, Springer Nature Switzerland AG.

关键词： Forecasting

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：