检索结果-内蒙古大学图书馆

Advancing Hyperdimensional Computing Based on Trainable Encoding and Adaptive Training for Efficient and Accurate learning

引用

ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS 2024年第5期29卷 1-25页

作者： Kim, Jiseung Lee, Hyunsei Imani, Mohsen Kim, Yeseong DGIST Dept Elect Engn & Comp Sci Daegu South Korea UC Irvine Irvine CA USA DGIST Daegu South Korea

Hyperdimensional computing (HDC) is a computing paradigm inspired by the mechanisms of human memory, characterizing data through high-dimensional vector representations, known as hypervectors. Recent advancements in HDC have explored its potential as a learning model, leveraging its straightforward arithmetic and high efficiency. The traditional HDC frameworks are hampered by two primary static elements: randomly generated encoders and fixed learning rates. These static components significantly limit model adaptability and accuracy. The static, randomly generated encoders, while ensuring high-dimensional representation, fail to adapt to evolving data relationships, thereby constraining the model's ability to accurately capture and learn from complex patterns. Similarly, the fixed nature of the learning rate does not account for the varying needs of the training process over time, hindering efficient convergence and optimal performance. This article introduces TrainableHD, a novel HDC framework that enables dynamic training of the randomly generated encoder depending on the feedback of the learning data, thereby addressing the static nature of conventional HDC encoders. TrainableHD also enhances the training performance by incorporating adaptive optimizer algorithms in learning the hypervectors. We further refine TrainableHD with effective quantization to enhance efficiency, allowing the execution of the inference phase in low-precision accelerators. Our evaluations demonstrate that TrainableHD significantly improves HDC accuracy by up to 27.99% (averaging 7.02%) without additional computational costs during inference, achieving a performance level comparable to state-of-the-art deep learning models. Furthermore, TrainableHD is optimized for execution speed and energy efficiency. Compared to deep learning on a low-power GPU platform like NVIDIA Jetson Xavier, TrainableHD is 56.4 times faster and 73 times more energy efficient. This efficiency is further augmented thr

关键词： Theory of computation Random projections and metric embeddings Computing methodologies machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Prediction of Multidimensional Poverty Status With machine learning Classification at Household Level: Empirical Evidence From Tanzania

引用

IEEE ACCESS 2025年 13卷 23461-23471页

作者： Bujiku Sende, Ngong'Ho Saha, Snehanshu Ruganzu, Leon Kar, Saibal Univ Rwanda African Ctr Excellence Data Sci Kigali Rwanda Birla Inst Technol & Sci Pilani CSIS Goa Campus Zuarinagar 403726 Goa India Birla Inst Technol & Sci Pilani APPCAIR Goa Campus Zuarinagar 403726 Goa India Ctr Studies Social Sci Kolkata India IZA Bonn Germany

Over fifty percent of the population in Tanzania suffers from multidimensional poverty. Because of the high poverty rate and slow improvement, ending poverty by the year 2030 remains challenging and empirically testable proposition and part of a shared challenge. The main purpose of this study is to predict multidimensional poverty status with the help of best performance-supervised machine-learning algorithms. To achieve this objective, longitudinal data from the 2014/15 and 2020/21 surveys, sourced from the Tanzania National Bureau of Statistics (NBS) were analyzed. A variety of supervised machine-learning algorithms such as RBF Kernel in SVM, Linear Kernel in SVM, Polynomial Kernel in SVM, Random Forest, Logistic regression classifier, Decision tree, Gradient Boosting, K-Nearest Neighbours Classifier, Na & iuml;ve Bayes Classifier, Artificial Neuron Network and Ensemble learning Model were implemented to predict multidimensional poverty status for each dataset. This captured the dynamic changes from 2014 to 2021 at the national level. The study employed data pre-processing techniques and adjusted imbalance through weighted categorical cross entropy and 5-Fold Cross Validation to mitigate the inefficiencies due to overfitting and under-fitting of the algorithms. Additionally, dimensionality data reduction was performed using Principal Component Analysis (PCA). With regard to the evaluation metrics, we show that the Ensemble learning Model has achieved the best performance modelling both balanced and unbalanced datasets. Our policy recommendations draw on the results of the algorithmic predictions.

关键词： Prediction algorithms Classification algorithms Predictive models machine learning Surveys Decision trees Support vector machines machine learning algorithms Indexes Data models Multidimensional poverty machine learning zones

来源：评论

学校读者我要写书评

暂无评论

Enhancing E-Commerce Warehouse Order Fulfillment Through Predictive Order Reservation Using machine learning

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 5700-5713页

作者： Kang, Yuexin Qu, Zhiqiang Yang, Peng Tsinghua Univ Shenzhen Int Grad Sch Div Logist & Transportat Shenzhen 518055 Peoples R China Tsinghua Univ Inst Data & Informat Shenzhen Int Grad Sch Shenzhen 518055 Peoples R China

Order batching plays a pivotal role in enhancing order fulfillment efficiency within both manual and robotic warehousing systems. Rare attention has been devoted to the impact of future incoming orders on online order batching. This study addresses this gap by exploring the potential benefits of reserving suitable orders when upcoming orders share similarities with existing orders in the order pool. Specifically, we investigate the online order batching problem with predictive order reservation, employing the Ensemble learning method, to predict similarities between current and future orders. Our proposed approach involves deliberate reservation of certain orders upon arrival, deferring their batching to a subsequent period for additional efficiency gains. To operationalize this predictive order reservation, we develop an algorithmic framework that comprehensively addresses online order batching, encompassing batching, sequencing, and assignment. Experimental results, conducted on real data from an e-commerce warehouse, demonstrate the superiority of our proposed approach over fixed and variable time-window online batching algorithms in terms of order turnover time, with improvements of up to 6.1%. Notably, the benefits are more pronounced when the order arrival rate aligns with the available picking resources.

关键词： Heuristic algorithms Electronic commerce machine learning algorithms Robots Sequential analysis Predictive models Prediction algorithms machine learning online order batching order picking logistics

来源：评论

学校读者我要写书评

暂无评论

machine learning in GNSS Multipath/NLOS Mitigation: Review and Benchmark

引用

IEEE AEROSPACE AND ELECTRONIC SYSTEMS MAGAZINE 2024年第9期39卷 35-44页

作者： Xu, Penghui Zhang, Guohao Yang, Bo Hsu, Li-Ta Hong Kong Polytech Univ Dept Aeronaut & Aviat Engn Hong Kong Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China

Global navigation satellite system (GNSS) positioning accuracy is degraded in urban canyons due to signal blockages and reflections, which is still a major challenge. Recently, using machine learning to improve the accuracy of GNSS positioning in urban areas has become a new trend. This article summarizes the works focused on GNSS multipath/non-light-of-sight (NLOS) mitigation using machine learning. The review of the studies is categorized based on the input features, algorithms, and outputs. The categorization shows that the received signal strength, elevation angle, and receiver correlator outputs from a single channel of satellite signal are the most popular input features. For the algorithm selection, the support vector machine and fully connected neural network are the algorithms most widely used. In terms of the outputs, most of the works made improvements in measurement status prediction, namely, LOS, multipath, and NLOS. Besides, this article also provides an open-source dataset with four scenarios for machine learning algorithms for the GNSS multipath/NLOS mitigation. Finally, the benchmarks are established based on the proposed dataset and the FCNN and least-squares estimation to enable performance evaluation in Kaggle.

关键词： Global navigation satellite system machine learning Satellites Receivers machine learning algorithms Measurement uncertainty Urban areas Prediction algorithms Support vector machines Accuracy Prevention and mitigation GNSS multipath NLOS machine learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Semi-Supervised learning With Concept Drift Detection and Self-Training: A Study on Classifier Diversity and Performance

引用

IEEE ACCESS 2025年 13卷 24681-24697页

作者： Perez, Jose L. M. Barros, Roberto S. M. Santos, Silas G. T. C. Univ Fed Pernambuco Ctr Informat Cidade Univ BR-50740560 Recife Brazil SiDi Inst BR-51110160 Recife Brazil

machine learning algorithms that assist in decision-making are becoming crucial in several areas, such as healthcare, finance, marketing, etc. algorithms exposed to a larger and more relevant amount of training data tend to perform better. However, the availability of labeled data without human expert intervention is a challenging task, especially in data stream learning with concept drifts, where data is generated rapidly, in real-time, with the possibility of changes in the data distribution. Concept drift occurs in supervised, semi-supervised and unsupervised learning environments, and is addressed through different approaches such as statistics, machine learning, among others. Currently, the use of drift detectors with base classifiers in semi-supervised learning is uncommon. Semi-supervised classifiers often consume a lot of memory and run-time, and the addition of a detection mechanism increases the computational cost. Furthermore, classification in semi-supervised environments can lead to problems related to labeling data to training: an error in this process can negatively impact model performance. This article investigates the use of supervised concept drift detectors in semi-supervised learning problems, highlighting how the detectors can improve the performance of classification. It also explores the influence of diversity in classifier ensembles, showing that increased diversity contributes to enhanced accuracy and robustness of models in concept drift scenarios. Additionally, it introduces a self-training approach to provide more labels and optimize model learning and adaptation. This research also details updates in the Massive Online Analysis (MOA) framework, that supports the simulation of semi-supervised scenarios. The experiments conducted to test the proposed approach used Hoeffding Tree (HT) and Naive Bayes (NB) as base classifiers, which were also employed as members of the ensembles used in this research. These classifiers were combined with se

关键词： Concept drift Detectors Training Semisupervised learning Classification algorithms machine learning algorithms Adaptation models Accuracy Stacking Predictive models Data stream concept drift detectors semi-supervised learning ensembles self-training

来源：评论

学校读者我要写书评

暂无评论

Comparison of Classical and machine learning Methods in Estimation of Missing Streamflow Data

引用

WATER RESOURCES MANAGEMENT 2024年第4期38卷 1453-1478页

作者： Dariane, A. B. Borhan, M. I. KN Toosi Univ Technol Dept Civil Engn Tehran Iran

Recovering missing data and access to a complete and accurate streamflow data is of great importance in water resources management. This article aims to comparatively investigate the application of different classical and machine learning-based methods in recovering missing streamflow data in three mountainous basins in northern Iran using 26 years of data duration extending from 1991 to 2017. These include Taleghan, Karaj, and Latyan basins that provide municipal water for the capital Tehran. Two periods of artificial gaps of data were considered to avoid possible duration-based impacts that may affect the results. For this purpose, several methods are investigated including simple and multiple linear regressions (LR & MLR), artificial neural network (ANN) with five different structures, support vector regression (SVR), M5 tree and two Adaptive Neuro-Fuzzy Inference System (ANFIS) comprising Subtractive (Sub-ANFIS) and fuzzy C-means (FCM-ANFIS) classification. Although these methods have been used in different problems in the past, but the comparison of all these methods and the application of ANFIS using two clustering methods in missing data is new. Overall, it was noticed that machine learning-based methods yield better outputs. For instance, in the Taleghan basin and in the gap during 2014-2017 period it shows that the evaluation criteria of Root Mean Square Error (RMSE), Nash-Sutcliffe Index (NSE) and Coefficient of Determination (R2)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${({\text{R}}}<^>{2})$$\end{document} for the Sub-ANFIS method are 1.67 m3/s\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${

关键词： Missing data Streamflow Recovering methods Classical methods machine learning algorithms Social choice

来源：评论

学校读者我要写书评

暂无评论

Enhancing solar irradiance forecasting for hydrogen production: The MEMD-ALO-BiLSTM hybrid machine learning model

引用

COMPUTERS & ELECTRICAL ENGINEERING 2024年 120卷

作者： Zhu, Chaoyang Wang, Mengxia Guo, Mengxing Deng, Jinxin Du, Qipei Wei, Wei Zhang, Yuxiang Commun Univ China Inst Social Innovat & Publ Culture Beijing 100000 Peoples R China Int Engn Psychol Inst US Denver CO 80201 USA Univ Illinois Champaign IL 61801 USA Hainan Vocat Univ Sci & Technol Haikou 570100 Peoples R China Shenzhen High Level Talents Dev Promot Assoc Shenzhen 518000 Peoples R China CDA Int Accelerator Shenzhen 518000 Peoples R China Beijing Inst Technol Shenzhen Res Inst Shenzhen 518000 Peoples R China Univ Wollongong Wollongong 2223 Australia Xian Univ Technol Sch Comp Sci & Engn Xian 710048 Peoples R China Shandong Open Univ Jinan 250000 Peoples R China Zhejiang Univ Technol Sch Management Hangzhou 310000 Peoples R China

This study focuses on an innovative hybrid machine-learning model for solar irradiance forecasting, targeting the integration of solar power into hydrogen production systems. Addressing the urgent need for sustainable energy transitions, the paper introduces the MEMD-ALO-BiLSTM model, designed to enhance solar irradiance prediction accuracy. This model uniquely combines Multivariate Empirical Mode Decomposition (MEMD), Ant Lion Optimizer (ALO), and Bidirectional Long Short-Term Memory (BiLSTM) techniques, setting a new benchmark in forecast precision across various seasonal datasets from Jiangsu Province, China. Demonstrating superior performance to traditional models, it achieves an exceptional coefficient of determination, averaging 0.99 for all seasons. Additionally, to prove the efficiency of the model three statistical tests were used, namely Wilcoxon, Friedman, and P-value. The research highlights the model's potential in optimizing photovoltaic systems and hydrogen production, thus contributing to carbon dioxide emission mitigation. Through comprehensive simulations of a residential system encompassing photovoltaic cells, compressors, and electrolyzers, the study underscores the practical feasibility and significant advancements the MEMD-ALO-BiLSTM model offers in the renewable energy sector, promoting a shift toward more reliable and efficient solar-powered hydrogen generation systems. Accordingly, the day-ahead values of photovoltaic-generated power and hydrogen production through the electrolyzer reached peak values at 1:00PM with approximately 75 kW and 1.4 kg, respectively.

关键词： Direct normal irradiance Carbon dioxide emissions Hydrogen production Photovoltaic system machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

machine learning-powered modelling of creep strain in shape-memory Nitinol alloys at different combination points of stress and temperature

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART E-JOURNAL OF PROCESS MECHANICAL ENGINEERING 2025年

作者： Mekky, Abdel-baset H. Qassim Univ Coll Sci Phys Dept Buraydah 51452 Saudi Arabia

An integrated machine learning system has been developed to make creep strain predictions on shape-memory Nitinol alloys subjected to different stress ranging from 0 to 500 MPa and temperature ranges from 25 degrees C to 80 degrees C. Our work used experimental data from 35 strain-controlled tests through which we evaluated four machine learning approaches, including linear regression and k-nearest neighbours along with decision Tree and Random Forest because traditional methods showed insufficient capabilities for analysing stress/temperature/creep deformation relationships. The evaluation of the models occurred through the mean absolute error(MAE) along with the root mean square error (RMSE) and the coefficient of determination (R-2). The Random Forest Ensemble Method exceeded the performance of linear models and Decision Tree models by providing near-perfect predictive power with R-2 = 1.000 while maintaining a zero MAE = 0.000 and RMSE = 3.93 x 10(9). This matched better than linear models (e.g. linear regression: R-2 = 0.708, MAE = 0.009) and decision tree (R-2 = 0.999, MAE = 0.000). Stress exists as the main cause of creep strain based on observation because there is a positive correlation (r > 0.95) while temperature maintains a non-linear effect that hastens deformation rates to 40% at 80 degrees C when compared to 25 degrees C. This study leads the field by merging machine learning algorithms with thermomechanical Nitinol data to build a comprehensive predictive system that increases material reliability and optimisation potential for biomedical and aerospace and energy sectors.

关键词： Shape memory Nitinol alloys working temperatures machine learning algorithms creep strain curves stress

来源：评论

学校读者我要写书评

暂无评论

machine learning models for prediction of nutrient concentrations in surface water in an agricultural watershed

引用

JOURNAL OF ENVIRONMENTAL MANAGEMENT 2024年 372卷 123305页

作者： Elsayed, Ahmed Rixon, Sarah Levison, Jana Binns, Andrew Goel, Pradeep Univ Guelph Morwick G360 Groundwater Res Inst Sch Engn Guelph ON Canada Cairo Univ Fac Engn Irrigat & Hydraul Dept Giza Egypt Minist Environm Conservat & Pk Etobicoke ON Canada

Prediction and quantification of nutrient concentrations in surface water has gained substantial attention during recent decades because excess nutrients released from agricultural and urban watersheds can significantly deteriorate surface water quality. machine learning (ML) models are considered an effective tool for better understanding and characterization of nutrient release from agricultural fields to surface water. However, to date, no systematic investigations have examined the implementation of different classification and regression ML models in agricultural settings to predict nutrient concentrations in surface water using a group of input variables including climatological (e.g., precipitation), hydrological (e.g., stream flow) and field characteristics (i.e., land and crop use). In the current study, multiple classification (e.g., decision trees) and regression (e.g., regression trees) ML models were applied on a dataset pertaining to surface water quality in an agricultural watershed in southern Ontario, Canada (i.e., Upper Parkhill watershed). The target variables of these models were the nutrient concentrations in surface water including nitrate, total phosphorus, soluble reactive phosphorus, and total dissolved phosphorus. These target variables were predicted using physical and chemical water parameters of surface water (e.g., temperature and DO), climatological, hydrological, and field conditions as the input variables. The performance of these different models was assessed using various evaluation metrics such as classification accuracy (CA) and coefficient of determination (R-2) for classification and regression models, respectively. In general, both the ensemble bagged trees and logistic regression (CA >= 0.72), and exponential Gaussian process regression (R-2 >= 0.93) models were the optimal classification and regression ML algorithms, respectively, where they resulted in the highest prediction accuracy of the target variables. The insights an

关键词： machine learning algorithms Nutrient concentrations Surface water Water quality Agricultural watershed Model predictions

来源：评论

学校读者我要写书评

暂无评论

Experimental investigation and machine learning modeling of diethylenetriaminepentaacetic acid agents in sandstone rock wettability alteration: Implications for enhanced oil recovery processes

引用

JOURNAL OF MOLECULAR LIQUIDS 2024年 404卷

作者： Keradeh, Mahsa Parhizgar Khanghah, Amir Mohammadi Sahand Univ Technol Fac Petr & Nat Gas Engn Tabriz Iran

Chelating agents have garnered increasing attention due to their unique capabilities in addressing challenges associated with chemical enhanced oil recovery (CEOR) materials. This research investigates the transformative potential of diethylenetriaminepentaacetic acid (DTPA) chelating agent in altering sandstone rock wettability. Wettability and zeta potential measurements were used to assess the impact of crucial factors including DTPA concentration, salinity, and potential determining ions (PDIs) on contact angle and rock surface charges. The findings revealed that there is an optimal level for DTPA concentration and salinity that can shift rock wettability from an oil -wet to strongly water -wet state. Moreover, while PDIs in their natural concentrations had no significant impact on DTPA performance, a threefold increase in their concentration was found to adversely affect DTPA efficacy. After conducting rock wettability tests, two advanced machine learning (ML) techniques, namely Random Forest (RF) and Boosted Regression Tree (BRT), were employed to assess rock/oil contact angle based on the aforementioned factors. Data were collected from 240 experimental datasets of contact angles. The findings indicated that both models performed well, but BRT exhibited exceptional performance. Sensitivity analysis, conducted using the Jackknife method, revealed the order of importance for parameters affecting wettability as follows: PDIs > salinity > time > DTPA concentration.

关键词： Wettability Alteration Chelating agent Zeta Potential machine learning algorithms

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：