检索结果-内蒙古大学图书馆

Transfer learning Based Recurrent Neural Network algorithm for Linguistic Analysis

ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING 2021年第3期20卷 1–16页

作者： Jiang, Peipei Chen, Liailun Wang, Min-Feng West Anhui Univ Fac Foreign Languages Luan 237012 Anhui Peoples R China Wuhan Tech Coll Commun Sch Publ Teaching & Practice Wuhan 430065 Peoples R China Zheng Zhou Sheng Da Univ Econ Business & Manageme Sch Arts & Law Zhengzhou 451191 Peoples R China

Each language is a system of understanding and skills that allows language users to interact, express thoughts, hypotheses, feelings, wishes, and all that needs to be expressed. Linguistics is the research of these structures in all respects: the composition, usage, and sociology of language, in particular, are the core of linguistics. machine learning is the research area that allows machines to learn without being specifically scheduled. In linguistics, the design of writing is understood to be a foundation for many distinct company apps and probably the most useful if incorporated with machine learning methods. Research shows that besides text tagging and algorithm training, there are major problems in the field of Big Data. This article provides a collaborative effort (transfer learning integrated into Recurrent Neural Network) to analyze the distinct kinds of writing between the language's linear and non-computational sides, and to enhance granularity. The outcome demonstrates stronger incorporation of granularity into the language from both sides. Comparative results of machine learning algorithms are used to determine the best way to analyze and interpret the structure of the language.

关键词： Linguistics machine learning algorithm text analytics part-of-speech sentence analysis

来源：评论

学校读者我要写书评

暂无评论

Assessment of landslide susceptibility using DBSCAN-AHD and LD-EV methods

引用

Journal of Mountain Science 2022年第1期19卷 184-197页

作者： MAO Yi-min MWAKAPESA Deborah S LI Yi-can XU Kai-bin NANEHKARAN Yaser A ZHANG Mao-sheng School of Information Engineering Jiangxi University of Science and TechnologyGanzhou 341000China Key Laboratory for Geo-hazards in Loess Area Xi’an 710054China Northwest Nonferrous Geological Mining Group Limited Company Xi’an 710054China

Landslide susceptibility assessment plays a vital role in understanding landslide information in advance and taking preventive as well as control measures. The need to initially specify the number of clusters, difficulty in handling noise and quantifying rainfall data, limits the application of traditional clustering models in landslide susceptibility assessment which then lowers their performance accuracy. Thus, to overcome these limitations, this study proposed an improved clustering algorithm titled the DBSCAN-AHD algorithm, which combines the traditional DBSCAN(Density Based Spatial Clustering of Application with Noise) algorithm and an Adaptive Hausdorff Distance(AHD) for landslide susceptibility modeling. Firstly, AHD was introduced to the traditional DBSCAN to quantify rainfall. Then,the DBSCAN-AHD grouped the mapping units with similar topology and geology characteristics into subclasses without specifying the number of clusters in advance for its ability to handle noise in the ***, the LD-EV(landslide density or eigenvalues) approach was introduced to obtain the susceptibility levels using K-means algorithm. Finally,to verify the model’s performance, statistical indices and the area under the curve(AUC) were applied and compared to the traditional DBSCAN, KPSO, Kmeans and Hierarchical Clustering algorithms,whereby, the proposed model outperformed the others. Also, the obtained susceptibility map can provide references in taking relevant preventive and control measures.

关键词： Landslide susceptibility DBSCAN machine learning algorithm Uncertain data Clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Buckling Load Estimation for Sandwich Plates with Innovative Circular Cell Cores via Nondestructive Vibration Correlation Technique and machine learning

引用

JOURNAL OF ENGINEERING MECHANICS 2025年第7期151卷

作者： Zeinali, Mohammadjavad Rahimi, Gholamhossein Hosseini, Shahram Tarbiat Modares Univ Mech Engn Dept Composite Lab Tehran Iran Tarbiat Modares Univ Mech Engn Dept Composite Lab Sch Mech Engn Tehran Iran

The vibration correlation technique (VCT) has emerged as an advanced and nondestructive approach for structural buckling analysis, offering substantial potential for high-level engineering applications. This study aims to estimate the buckling load of a sandwich plate with a novel circular cell core using VCT. The sandwich plate is designed based on a unit cell characterized by three adjustable parameters. machine learning algorithms (MLAs) are initially employed to model the relationship between these design parameters (inputs) and key performance indicators (outputs), namely, the specific buckling load to weight ratio (p0/m=pc) and the first specific natural frequency to weight ratio (f0/m=fc). The resulting predictive models are integrated into a genetic algorithm (GA) as an objective function to maximize both (pc) and (fc) simultaneously, enabling the identification of optimal design parameters. Subsequently, a homogenization method is applied to determine the equivalent mechanical properties of the circular cell core. The structural behavior is further analyzed using first-order shear deformation theory, with buckling and free vibration equations solved through a meshless numerical method. The VCT is then implemented to estimate the buckling load, and its predictions are validated against experimental results. Among the three VCT variants, the third method demonstrates superior accuracy, achieving a prediction error of less than 6.2%, thereby proving its efficiency over alternative approaches. This integrated framework highlights the synergy of machine learning, optimization algorithms, and advanced structural theories in achieving robust and efficient structural designs.

关键词： Vibration correlation technique (VCT) Circular cell core machine learning algorithm Buckling Meshless method

来源：评论

学校读者我要写书评

暂无评论

machine learning-Enhanced Dual-Band Plasmonic Sensing for Simultaneous Qualitative and Quantitative Detection of Biomolecules in the Mid-Infrared Region

引用

SENSORS 2025年第10期25卷 3135-3135页

作者： Chang, Yunwei Bian, Ang Jiangsu Univ Sci & Technol Sch Sci Dept Optoelect Informat Sci & Engn Zhenjiang 212100 Peoples R China

Recently, sensing for biomolecules has become increasingly popular in the fields of environmental monitoring, personal health, and food safety. Plasmonic biosensors have been a powerful tool due to their high sensitivity and label-free operation. However, when it comes to molecules with different kinds and concentrations, detection technology and data processing remain a challenging task. In this study, we investigate the qualitative and quantitative detection of two kinds of biomolecules in the mid-infrared region simultaneously by the utilization of a plasmonic sensor. The strong coupling between each plasmonic resonance and the corresponding molecular vibration is found to significantly enhance the absorption signal of molecules, and the obtained Rabi splitting is not only a proof of molecular existence but also an indicator of molecular concentration. However, the amount of the molecular solution with a background refractive index in turn affects the plasmonic resonance position. In more general situations, it is not easy to achieve the match between plasmonic resonance and molecular resonance, and thus the quantitative detection by the Rabi splitting depth is not always feasible. Hence, we propose a machine learning algorithm called principal component analysis (PCA), providing a versatile approach for analyzing the proportion of each molecule in the mixture. Our work opens up new routes in noninvasive optical sensing and the integration of AI-driven data analysis further strengthens its potential for real-world applications.

关键词： plasmon molecular sensing machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Fine-tune BERT based on machine learning Models For Sentiment Analysis

引用

Procedia Computer Science 2024年 246卷 2390-2399页

作者： Nadia Smairi Houda Abadlia Hajer Brahim Wided Lejouad Chaari National School of Computer Science LARIA UR22ES01 Campus Universitaire Manouba 2010 Tunisia College of Science Department of Computer Science and Information in Majmaah University Az Zulf 15941 Saudi Arabia

Sentiments Analysis is a technique applied to examine emotions expressed by the users of social networks where they massively convey their opinions and permanently share their feelings. Therefore, its main objective is to determine the emotional attitude of a discourse by classifying it into different categories as positive, negative or neutral. However, in some research works, the authors failed to accurately specify the sentiments from the context due to the varying text lengths and the presence of equivocal emotional cues. This paper sets forth the deployment and assessment of the capabilities of applying machine learning sentiment analysis techniques using a publicly available IMDB dataset. Notably, this dataset encompasses numerous instances of irony and sarcasm. Lately, the Bidirectional Encoder Representations from Transformers model (BERT) has showcased its efficacy in the domain of text sentiment analysis classification. However, there remains a scope for enhancing the accuracy of SA. In the current study, BERT, and Word2vec are utilized to extract contextual sentences embeddings, while Support Vector machine (SVM) is used to classify the emotions of the social networks users. To enhance SVM accuracy, the genetic algorithm is integrated to optimize its hyper-parameters. The comparative study revealed that the developed technique applied on IMDB dataset outperforms other baseline machine learning techniques.

关键词： Emotion classification BERT transformer machine learning algorithm SVM Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Maximum Power Point Tracking During Partial Shading Effect in PV System Using machine learning Regression Controller

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2021年第2期16卷 737-748页

作者： Padmavathi, N. Chilambuchelvan, A. Shanker, N. R. RMD Engn Coll Thiruvallur India Aalim Muhammed Salegh Coll Engn Dept Comp Sci & Engn Chennai Tamil Nadu India

Maximum Power Point Tracking (MPPT) algorithm performs for maximizing the efficiency of solar Photo Voltaic (PV) system. The solar photovoltaic system efficiency reduces due to partial shading and ambient atmospheric condition, which varies with geographic locations. Traditional MPPT systems solve the above problem through different soft computing algorithms such as Perturb and observe (P&O), Flower pollination algorithm (FPA) and Particle swarm optimization (PSO). In P&O, FPA and PSO algorithms, duty cycle of boost converter varies to attain MPPT. The soft computing algorithms in MPPT perform less during the partial shading effect or rapid insolation, fluctuation condition of solar energy. The performance of MPPT with traditional algorithms is reduced due to slow convergence speed and oscillations in tracking by computing algorithms. In this paper, Regression controller based MPPT achieve maximum peak voltage during partial shading effect is developed. The regression controller predicts the duty cycle for boost converter based on stored dataset of PV system output voltage and load, during partial shading effect or rapid isolation for that particular geographic location. The regression based duty cycle prediction controller is programmed in MATLAB R2018a Simulink. Furthermore, Regression controller is implemented in PV system test bed. The simulation and hardware results of Regression controller based MPPT perform more of about 20%, 16.96% and 15% in efficiency respectively than PSO, FPA and P&O algorithms during partial shading condition in PV.

关键词： Energy harvesting machine learning algorithm Maximum power point tracking Microcontroller based system design Regression controller

来源：评论

学校读者我要写书评

暂无评论

Selective Thermophotovoltaic Emitter with Aperiodic Multilayer Structures Designed by machine learning

引用

ACS APPLIED ENERGY MATERIALS 2021年第2期4卷 2004-2013页

作者： Zhang, Wenbin Wang, Boxiang Zhao, Changying Shanghai Jiao Tong Univ Inst Engn Thermophys Sch Mech Engn Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ MOE Key Lab Power Machinery & Engn Shanghai 200240 Peoples R China

Controlling the thermal emission characteristics of a thermophotovoltaic (TPV) emitter can effectively reduce the thermal losses in a photovoltaic cell. Moreover, selective TPV emitters can facilitate the generation of electricity from a variety of high-temperature waste heat sources. To overcome the challenge of achieving perfect spectral selectivity of TPV emitters, the development of artificial intelligence provides a vision for the optimization of selective TPV emitters beyond the conventional paradigm. In this work, we demonstrate that a highly selective, aperiodic TPV emitter with a high figure of merit (FOM) can be achieved with the help of Bayesian optimization. The design of the selective TPV emitter is optimized over 5.23 x 10(9) candidate structures in multilayers consisting of multiple components to maximize the FOM. The maximum FOM could be realized within calculations for less than 0.67% of the total candidate structures, which is much better than other machine learning algorithms. As for the gallium antimonide photovoltaic cell, the resulting optimal structure is an aperiodic multilayer structure with an FOM of 82.16%. The optimal structure is then fabricated by a multi-target sputtering system, and the experimental result of the emission characteristics is achieved with an FOM of 81.35%, which is significantly better than those of multilayers with similar material designed and fabricated based on previous studies. What is more, we have analyzed the efficiency of the TPV system and measured the thermal stability of the fabricated samples. The results demonstrate that Bayesian optimization is efficient in designing selective TPV emitters, and the machine-learning-based design of metamaterials can be extended for the expensive black-box global optimization problems in other field applications.

关键词： machine learning algorithm selective TPV emitter Bayesian optimization aperiodic multilayer metamaterials thermal stability

来源：评论

学校读者我要写书评

暂无评论

Prediction models for macro shrinkage of aluminum alloys based on machine learning algorithms

引用

MATERIALS TODAY COMMUNICATIONS 2019年 21卷

作者： Liao, Hengcheng Zhao, Baojun Suo, Xiaojin Wang, Qigui Southeast Univ Sch Mat Sci & Engn Jiangsu Key Lab Adv Metall Mat Nanjing 211189 Jiangsu Peoples R China GM Global Prod Grp Mat Technol 800 North Glenwood Ave Pontiac MI 48340 USA

Macro shrinkage percentage is one of the most important measures of the castability of alloys. To quickly and accurately predict the macro shrinkage of aluminum alloys is greatly meaningful before developing new components or new alloys. In this study, based on the dataset of macro shrinkage percentage of aluminum alloys obtained by our experiments, three algorithms, Support Vector Regression (SVR), General Regression Neural Network (GRNN) and Random Forest (RF), were adopted to construct the prediction models for macro shrinkage, respectively. K-fold cross-validation and analysis on stability and reliability of models indicate the RF model is the best one. Compared the prediction values of macro shrinkage percentage in binary, ternary and multicomponent aluminum alloys by RF model with the experiment data of this study and the data from literatures, the constructed model has been verified to have high prediction accuracy and reliability.

关键词： Aluminum alloys Macro shrinkage machine learning algorithm Prediction model

来源：评论

学校读者我要写书评

暂无评论

Safety of Glecaprevir/Pibrentasvir for hepatitis C in patients with posttraumatic stress disorder: A post-marketing surveillance study

引用

GENERAL HOSPITAL PSYCHIATRY 2023年 84卷 268-270页

作者： Shiner, Brian Park, Jenna A. Rozema, Luke Hoyt, Jessica E. Watts, Bradley, V Gradus, Jaimie L. Vet Affairs Med Ctr White River Jct VT USA Natl Ctr Posttraumat Stress Disorder White River Jct VT USA Geisel Sch Med Dartmouth Hanover NH USA Boston Univ Sch Publ Hlth Boston MA USA Boston Univ Sch Med Boston MA USA Vet Affairs Med Ctr 215 North Main St206 245-6361 White River Jct VT 05009 USA

来源：评论

学校读者我要写书评

暂无评论

Using pXRF and vis-NIR spectra for predicting properties of soils developed in loess

引用

Pedosphere 2022年第4期32卷 602-615页

作者： Gafur GOZUKARA Yakun ZHANG Alfred E.HARTEMINK University of Wisconsin-Madison Department of Soil ScienceFD Hole Soils Lab1525 Observatory DriveMadison WI 53706USA Eskisehir Osmangazi University Department of Soil Science and Plant NutritionEskisehir 26160Turkey

Visible near-infrared (vis-NIR) and portable X-ray fluorescence (pXRF) spectrometers have been increasingly utilized for predicting soil properties worldwide. However, only a few studies have focused on splitting the predictive models by horizons to evaluate prediction performance and systematically compare prediction performance for A, B, and combined A+B horizons. Therefore, we investigated the performance of pXRF and vis-NIR spectra, as individual or combined, for predicting the clay, silt, sand, total carbon (TC), and pH of soils developed in loess, and compared their prediction performance for A, B, and A+B horizons. Soil samples (176 in A horizon and 172 in B horizon) were taken from Mollisols and Alfisols in 136 pedons in Wisconsin, USA and analyzed for clay, silt, sand, pH, and TC. The pXRF and vis-NIR spectrometers were used to measure the pXRF and vis-NIR soil spectra. Data were separated into calibration (n = 244, 70%) and validation (n = 104, 30%) datasets. The Savitzky-Golay filter was applied to preprocess the pXRF and vis-NIR spectra, and the first 10 principal components (PCs) were selected through principal component analysis (PCA). Five types of predictor, i.e., PCs from vis-NIR spectra, pXRF of beams at 0–40 and 0–10 keV (XRF40 and XRF10, respectively) spectra, combined XRF40 and XRF10 (XRF40+XRF10) spectra, and combined XRF40, XRF10, and vis-NIR (XRF40+XRF10+vis-NIR) spectra, were compared for predicting soil properties using a machine learning algorithm (Cubist model). A multiple linear regression (MLR) model was applied to predict clay, silt, sand, pH, and TC using pXRF elements. The results suggested that pXRF spectra had better prediction performance for clay, silt, and sand, whereas vis-NIR spectra produced better TC and pH predictions. The best prediction performance for sand (R2= 0.97), silt (R2= 0.95), and clay (R2= 0.84) was achieved using vis-NIR+XRF40+XRF10 spectra in B horizon, whereas the best prediction performance for TC (R2= 0.93)

关键词： Cubist model machine learning algorithm portable X-ray fluorescence spectra soil elements visible near-infrared spectra

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：