检索结果-内蒙古大学图书馆

Conference on Satellite Data Compression, Communications, and Processing X

作者： Alissou, Simplice A. Zhang, Ye Harbin Inst Technol Harbin 150001 Peoples R China

ISBN: (纸本)9781628410617

Among discrete orthogonal transforms, Karhunen-Loeve transform (KLT) achieves the most optimal spectral decorrelation for hyperspectral data compression with minimum mean square error. A common approach for those spectral decorrelation transform techniques such as KLT is to select m coefficient using some threshold value and then treating the rest of the coefficients as zero, this will result in loss of information. In order to preserve more information on small target data, this paper focused on a new technique called joint KLT-lasso. The lasso was applied to KLT coefficient. Sparse loadings were obtained using the lasso constraint on KLT regression coefficients and more coefficients were shrunk to exact zero. The goal of our new method is to introduce a limit on the sum of the absolute values of the KLT coefficients and in which some coefficients consequently become zero without using any threshold value. A simulation on different hyperspectral data showed encouraging results.

关键词： Hyperspectral data Information preserving Karhunen-Loeve transform lasso algorithm mean square error small target data sparse loadings spectral decorrelation

来源：评论

学校读者我要写书评

暂无评论

Analysis of Mixed Pulping Raw Materials of Eucalyptus globulus and Acacia mangium by Near Infrared Spectroscopy Technique Combined with lasso algorithm

引用

BIORESOURCES 2018年第1期13卷 1348-1359页

作者： Wu, Ting Fang, Guigan Liang, Long Deng, Yongjun Lin, Yan Xiong, Zhixin Chinese Acad Forestry Inst Chem Ind Forest Prod Nanjing 210042 Jiangsu Peoples R China Nanjing Forestry Univ Collaborat Innovat Ctr High Efficient Proc & Util Nanjing 210037 Jiangsu Peoples R China Nanjing Forestry Univ Coll Light Ind Sci & Engn Nanjing 210037 Jiangsu Peoples R China

To meet the current demand in China for Eucalyptus globulus and Acacia mangium mixed pulping, a study was conducted to collect the near infrared (NIR) spectra of 150 mixed samples of E. globulus and A. mangium in which the content of E. globulus was manually controlled. After the original spectra were pretreated by first derivative and standard normal variate (SNV), the least absolute shrinkage and selection operator (lasso) algorithm and cross-validation were used to calculate the optimal adjustment parameters of 14.30, 19.16, 12.10, and 9.74, respectively. The optimal calibration models for the content of E. globulus, holocellulose, pentosan, and acid insoluble lignin were generated. An independent verification of the calibration models showed that the root mean square error of prediction (RMSEP) for these models was 1.59%, 0.54%, 0.66%, and 0.40%, respectively. The absolute deviation (AD) was -2.58% to 2.73%, -0.91% to 0.84%, -1.19% to 1.06%, and -0.61% to 0.64%, respectively. The prediction performance of the four models was sufficient for real-time analysis in the pulping production line. The lasso algorithm was judged to be efficient for the prediction and analysis of mixed raw materials in pulping industry.

关键词： Near-infrared spectroscopy lasso algorithm Real-time analysis Pulpwood quality Chemical composition

来源：评论

学校读者我要写书评

暂无评论

Unraveling the water quality-ecosystem nexus using Kalman filter-driven models and feature analysis under uncertainty

引用

JOURNAL OF HYDROLOGY 2025年 657卷

作者： Poursaeid, Mojtaba Payame Noor Univ Dept Civil Engn Khorramabad Lorestan Iran

Many factors impact water quality (WQ), such as climate change and population growth. Thus, the present work aims to propose an accurate and potent solution for the WQ instabilities challenge in the South Platte River in United States. The data driven model based on the machine learning model tuned with Kalman filter (KF) was considered to reduce input data noise. The least absolute shrinkage and selection operator (lasso) algorithm were used to analyze the importance of features and select the best inputs. The US Geological Survey (USGS) archive provided the primary database related to 2023-2024, with over 38,000 samples. The random forest (RF) was combined with KF and lasso to reduce noise and analyze the importance of features due to the high number of samples. Artificial neural network (ANN), linear regression (LR), and support vector machine (SVM) were developed to compare the accuracy of the proposed model. The proposed model had the highest coefficient of determination values, which were between 0.95 and 0.99. Modeling the indicators revealed that some WQ variations could negatively affect aquatic ecosystems.

关键词： Water Quality Machine learning Feature analysis Kalman filter lasso algorithm South Platte river

来源：评论

学校读者我要写书评

暂无评论

A novel 5-differentially expressed gene (DEG) signature predicting the prognosis in patients with metastatic liver malignancies and the prognostic and therapeutic potential of SPP1

引用

INTERNATIONAL JOURNAL OF CLINICAL ONCOLOGY 2025年第5期30卷 956-973页

作者： Liu, Jing Yu, Zijian Liu, Qiong Dou, Chengyun Cao, Peng Xie, Xia Univ South China Affiliated Hosp 1 Hengyang Med Sch Dept Infect Dis Hengyang 421001 Hunan Peoples R China Univ South China Affiliated Hosp 1 Hengyang Med Sch Dept Hepatopancreatobiliary Surg Hengyang 421001 Hunan Peoples R China

Background This study aimed to identify differentially expressed genes (DEGs) that are associated with hepatocarcinogenesis and metastasis in hepatocellular carcinoma (HCC) and to explore their value in predicting overall survival (OS). The methods used included bioinformatics analysis of gene expression datasets and in vitro experiments using HCC cell lines. Methods Gene expression profiles from metastatic and non-metastatic liver cancer specimens were analyzed using the limma R package. Functional enrichment was performed using Metascape. A prognostic 5-gene signature was constructed using the lasso algorithm based on TCGA-LIHC data. Kaplan-Meier survival analysis assessed the association of these genes with clinical outcomes (DFI, DSS, OS, and PFS). In vitro, Huh7 and Hep3B cells were transfected with shRNA for SPP1 knockdown. Cell viability was measured with CCK-8 assays, and migration was assessed with Transwell and wound-healing assays. Protein expression was evaluated via western blotting. Results The analysis of gene expression profiles led to the identification of 11 DEGs associated with immune response, phagocytosis, and cell migration. From these DEGs, the lasso algorithm identified a 5-DEG signature (MASP1, MASP2, MUC1, TREM1, and SPP1) that was predictive of OS in liver cancer patients. Among the five genes, SPP1 was the most upregulated in cancer samples and was significantly associated with poorer outcomes, including DFI, DSS, OS, and PFS. In vitro experiments confirmed that SPP1 knockdown in Huh7 and Hep3B cells significantly inhibited cancer cell viability and migration. Western blot analysis showed alterations in key proteins, with a reduction in vimentin and Ki-67 and an increase in E-cadherin following SPP1 knockdown. Conclusion This study highlights the pivotal effect of SPP1 on HCC development and underscores its potential as a biomarker for the OS of liver cancer patients. The identified DEGs may serve as predictive markers for OS and potentia

关键词： Liver cancer Metastasis Integrative bioinformatics analyses lasso algorithm 5-DEG signature Secreted phosphoprotein 1 (SPP1)

来源：评论

学校读者我要写书评

暂无评论

Improving prediction efficiency of Chinese stock index futures intraday price by VIX-lasso-GRU Model

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartC期238卷

作者： Fang, Wen Zhang, Shuwen Xu, Chang Beijing Jiaotong Univ Sch Econ & Management Dept Finance Beijing 100044 Peoples R China

With T + 0 and short selling mechanism, the stock index futures are attractive to short-term traders in China, where stocks cannot be liquidated within the day and are difficult to short. So in terms of futures, how to improve the accuracy and speed of intraday price forecasting always fascinates short-term traders and researchers. Here we propose a novel forecasting model, VIX-lasso-GRU Model, which based on the gated recurrent unit (GRU) by adding VIX information and a method called Least absolute shrinkage and selection operator (lasso). The volatility index (VIX) can reduce the prediction errors and the lasso algorithm significantly improve the training speed of the model. We predict the 5-minute closing prices of three datasets of index futures by VIX-lasso-GRU Model. Comparing to the pure GRU and LSTM, we find that this new prediction model can improve the prediction efficiency with faster speed and higher accuracy.

关键词： Stock index future price Prediction VIX GRU lasso algorithm

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral estimation of petroleum hydrocarbon content in soil using ensemble learning method and lasso feature extraction

引用

ENVIRONMENTAL POLLUTANTS AND BIOAVAILABILITY 2022年第1期34卷 308-320页

作者： Wu, Menghong Lin, Nan Li, Genjun Liu, Hanlin Li, Delin Jilin Agr Univ Coll Resources & Environm Changchun Jilin Peoples R China Jilin Jianzhu Univ Coll Surveying & Explorat Engn Changchun Jilin Peoples R China Kuntuo Remote Sensing Serv Co Ltd Xining Qinghai Peoples R China Qinghai Geol Survey Inst Xining Qinghai Peoples R China Northern Qinghai Tibet Plateau Key Lab Geol Proc & Mineral Resources Xining Qinghai Peoples R China

Rapid and accurate estimation of soil petroleum hydrocarbon content is crucial for analyzing the degree of soil pollution and evaluating pollution status. Surface soil samples and hyperspectral measurements in the reservoir area in Lenghu Town, Qinghai Province, China, were viewed as research objects, and the correlation between different spectral forms of original data and petroleum hydrocarbon content in soil was analyzed. To improve the estimation accuracy, we proposed a solution that introduces least absolute shrinkage and selection operator (lasso) combined with extremely randomized trees (ERT) and gradient boosting decision tree (GBDT) ensemble learning for constructing hyperspectral estimation model. The results show: lasso algorithm can not only solve the spectral multicollinearity problem effectively but also reduce the number and calculation complexity of soil hyperspectral variables to a great extent. Compared with traditional machine learning, ERT and GBDT perform superior. In particular, the estimation accuracy of the lasso-GBDT model is the highest.

关键词： Hyperspectral remote sensing petroleum hydrocarbon content lasso algorithm ERT GBDT

来源：评论

学校读者我要写书评

暂无评论

Determinants of household waste separation in rural China

引用

JOURNAL OF MATERIAL CYCLES AND WASTE MANAGEMENT 2024年第6期26卷 3446-3459页

作者： Qiu, Xiuhong Zou, Baoling Southwest Univ Coll Econ & Management Chongqing 400715 Peoples R China Southwest Univ Rural Econ & Management Res Ctr 2 Tiansheng Rd Chongqing 400715 Peoples R China

It is crucial for rural residents to consciously separate their domestic waste to improve their living environment and build beautiful villages. Exploring the decisive factors of household waste separation in rural China can offer more precise guidance for waste segregation, thereby contributing to the establishment of a more efficient and sustainable waste management system. Using the 2022 China rural revitalization comprehensive survey data (CRRS), this paper combined the least absolute shrinkage and selection operator (lasso) algorithm with the Logit model to identify the determinants of waste separation in rural China from multiple aspects. It was found that families with better internet conditions, more equipment, and online training are more willing to participate in waste separation. Families who are more satisfied with the various tasks of the village committee are more willing to separate waste. Additionally, greater concern about food safety, and active learning of health knowledge are more inclined to engage in waste separation. Thus, this paper proposes improving internet conditions, enhancing satisfaction with village cadre work and promoting health awareness education.

关键词： Waste separation Determinants lasso algorithm Logit model

来源：评论

学校读者我要写书评

暂无评论

Effect of Spatial Filtering on Characterizing Soil Properties From Imaging Spectrometer Data

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2017年第9期10卷 4149-4170页

作者： Dutta, Debsunder Kumar, Praveen Greenberg, Jonathan A. Univ Illinois Dept Civil & Environm Engn Urbana IL 61801 USA Univ Nevada Dept Nat Resources & Environm Sci Reno NV 89557 USA

Airborne imaging spectroscopy covering wavelength range of 0.35-2.5 mu m can be used to quantify soil textural properties and chemical constituents. In this paper, we evaluate the effects of spatial resolution on the quantification of soil constituents using a lasso algorithm-based ensemble bootstrapping framework. Airborne visible infrared imaging spectrometer data collected at 7.6m resolution over Bird's Point New Madrid (BPNM) floodway in Missouri, USA, is upscaled using a spatial filter to simulate a satellite-based sensor and generate multiple coarser resolution datasets, including the originally proposed 60.8 m hyperspectral infrared imager like data. The simulated data at multiple spatial resolutions are used in an ensemble lasso algorithm-based modeling framework for developing quantitative prediction models and spatial mapping of the soil constituents. We outline an evaluation framework with a set of metrics that considers the point-scale model performance as well as the consistency of cross-scale spatial predictions. The model results demonstrate that the ensemble quantification method is scalable, and further the model structure indicates the persistence of important spectral features across spatial resolutions. The probability density functions of the constituents over the BPNM landscape show that it is similar for multiple spatial resolutions. Finally, a comparison of the model predictions with statistical central values together with the within pixel variance across fine to coarse resolutions indicate that the model accurately captures the median values of the fine subgrid that the coarse-resolution data is composed of. This study establishes the feasibility for quantifying soil constituents from space-borne hyperspectral sensors.

关键词： Hyperspectral HyspIRI lasso algorithm multiresolution remote sensing soil properties

来源：评论

学校读者我要写书评

暂无评论

On the Feasibility of Characterizing Soil Properties From AVIRIS Data

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2015年第9期53卷 5133-5147页

作者： Dutta, Debsunder Goodwell, Allison E. Kumar, Praveen Garvey, James E. Darmody, Robert G. Berretta, David P. Greenberg, Jonathan A. Univ Illinois Dept Civil & Environm Engn Urbana IL 61801 USA So Illinois Univ Dept Zool Carbondale IL 62901 USA Univ Illinois Dept Nat Resources & Environm Sci Urbana IL 61801 USA Memphis Dist US Army Corps Engineers Hydraul & Hydrol Branch Memphis TN 38103 USA Univ Illinois Dept Geog & Geog Informat Sci Urbana IL 61801 USA

We evaluate the feasibility of quantifying surface soil properties over large areas and at a fine spatial resolution using high-resolution airborne imaging spectroscopy. Airborne Visible Infrared Imaging Spectrometer (AVIRIS) data collected by the National Aeronautics and Space Administration immediately after the large 2011 Mississippi River flood at the Birds Point New Madrid (BPNM, approximate to 700 km(2)) floodway in Missouri, USA, was used in a data mining lasso framework for mapping of soil textural properties such as percentages of sand, silt, clay, soil-organic matter, and many other soil chemicals constituents. The modeling results show that the approach is feasible and provide insights in the accuracy and uncertainty of the approach for both soil textural properties and chemical constituents. These models were further used for a pixel-by-pixel prediction of each the soil constituent, resulting in high-resolution (7.6 m) quantitative spatial maps in the entire floodway. These maps reveal coherent spatial correlations with historical meander patterns of Mississippi River and fine-scale features such as erosional gullies, represented by difference in constituent concentration, e. g., low soil organic matter, with the underlying topography immediately disturbed by the large flooding event. Further, we have argued and established that the independent validation results are better represented as a probability density function as compared with a single calibration-validation set. It is also found that modeled soil constituents are sensitive to NDVI and the calibration sample sizes, and the results improve with stricter (lower) NDVI thresholds and larger calibration sets.

关键词： Floods hyperspectral lasso algorithm remote sensing soil properties

来源：评论

学校读者我要写书评

暂无评论

COPD stage detection: leveraging the auto-metric graph neural network with inspiratory and expiratory chest CT images

引用

MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING 2024年第6期62卷 1733-1749页

作者： Deng, Xingguang Li, Wei Yang, Yingjian Wang, Shicong Zeng, Nanrong Xu, Jiaxuan Hassan, Haseeb Chen, Ziran Liu, Yang Miao, Xiaoqiang Guo, Yingwei Chen, Rongchang Kang, Yan Northeastern Univ Coll Med & Biol Informat Engn Shenyang 110169 Peoples R China Shenzhen Technol Univ Coll Hlth Sci & Environm Engn Shenzhen 518118 Peoples R China Shenzhen Lanmage Med Technol Co Ltd Dept Radiol 103 Baguang Serv Ctr Shenzhen 518119 Guangdong Peoples R China Shenzhen Univ Sch Appl Technol Shenzhen 518060 Peoples R China Guangzhou Med Univ Affiliated Hosp 1 Natl Ctr Resp Med Guangzhou Inst Resp HlthState Key Lab Resp DisNa Guangzhou 510120 Peoples R China Northeast Petr Univ Sch Elect & Informat Engn Daqing 163318 Peoples R China Jinan Univ Southern Univ Sci & Technol Affiliated Hosp 1 Shenzhen Peoples HospClin Med CollShenzhen Inst Shenzhen 518001 Peoples R China Minist Educ Engn Res Ctr Med Imaging & Intelligent Anal Shenyang 110169 Peoples R China

Chronic obstructive pulmonary disease (COPD) is a common lung disease that can lead to restricted airflow and respiratory problems, causing a significant health, economic, and social burden. Detecting the COPD stage can provide a timely warning for prompt intervention in COPD patients. However, existing methods based on inspiratory (IN) and expiratory (EX) chest CT images are not sufficiently accurate and efficient in COPD stage detection. The lung region images are autonomously segmented from IN and EX chest CT images to extract the 1, 781 x 2 lung radiomics and 13, 824 x 2 3D CNN features. Furthermore, a strategy for concatenating and selecting features was employed in COPD stage detection based on radiomics and 3D CNN features. Finally, we combine all the radiomics, 3D CNN features, and factor risks (age, gender, and smoking history) to detect the COPD stage based on the Auto-Metric Graph Neural Network (AMGNN). The AMGNN with radiomics and 3D CNN features achieves the best performance at 89.7% of accuracy, 90.9% of precision, 89.5% of F1-score, and 95.8% of AUC compared to six classic machine learning (ML) classifiers. Our proposed approach demonstrates high accuracy in detecting the stage of COPD using both IN and EX chest CT images. This method can potentially establish an efficient diagnostic tool for patients with COPD. Additionally, we have identified radiomics and 3D CNN as more appropriate biomarkers than Parametric Response Mapping (PRM). Moreover, our findings indicate that expiration yields better results than inspiration in detecting the stage of COPD.

关键词： Biphasic CT Images COPD stage detection Auto-metric graph neural network Machine learning lasso algorithm Radiomics

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：