检索结果-内蒙古大学图书馆

A novel non-destructive technique-based automated classification of construction material using machine learning

Asian Journal of Civil Engineering 2024年第1期25卷 805-810页

作者： Dhingra, Nitika Saluja, Nitin Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

Non-destructive testing (NDT) is helpful to distinguish between healthy and unhealthy buildings or to find faults in dielectric structures. Testing techniques that can be used on dielectrics, such as microwave testing, are necessary for performing structural health tests for dielectric materials. A strategy is needed to reduce the complexity and costs related to microwave NDT procedures. In general, current microwave NDT relies on monitoring changes in the scattering parameter across the operational frequency range of the sensor. The paper focuses on using machine learning algorithms to identify the material constituents using scattering parameters obtained from NDT. The proposed method is validated experimentally using a designed patch sensor on different material compositions. The effectiveness or the proposed method is calculated through K-Nearest Neighbour and tree-based algorithms. Results shows the accuracy of 78.51% using random forest algorithm. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

关键词： machine learning algorithms Material properties Non-destructive testing Sample preparation

来源：评论

学校读者我要写书评

暂无评论

Real-Time Indoor Air Quality Monitoring and Purification System using Sensor Data and machine learning Technique 2

Real-Time Indoor Air Quality Monitoring and Purification Sys...

引用

2nd International Conference on Sustainable Computing and Smart Systems (ICSCSS)

作者： Poulo, Annmaria Manoj, Aswathy Muhsina, V. A. Fathima Titus, E. Gaea Neema, M. Adi Shankara Inst Engn & Technol Elect & Commun Engn Kalady Kerala India

ISBN: (纸本)9798350391558;9798350379990

Air pollution is a serious threat to human health and the environment, and effective monitoring systems need to be developed to assess air quality in real time. Recent advancements in air quality monitoring have hold on Internet of Things (IoT) and machine learning (ML) technologies to increase data collection and predictive capabilities but there are still several challenges like sensor accuracy, data integration, and model optimization. Sensor accuracy is a main issue as low-cost sensors often suffer from calibration drift and environmental interference, leading to unreliable data. Integrating data from various sensors provide a board view of air quality poses significant challenges due to differences in sensor sensitivities and response times and optimizing machine learning models to handle large mixed data while maintaining high predictive accuracy requires continuous refinement. To address these challenges, a real-time indoor air quality monitoring system is proposed using temperature, humidity, dust, methane, carbon monoxide and air quality sensors. Using the Random Forest Master for predictive analysis, the system provides real-time monitoring and daily forecasts. An air filter is installed and automatically activated based on sensor data to immediately respond to poor air quality. The system includes LED indicators, dust purification and air quality classification for accurate data entry. In addition to the disadvantages of air cleaning, it improves environmental monitoring and helps reduce the impact of indoor air pollution on health and well-being.

关键词： IoT Indoor Air Quality Management Air Purifier System Flutter Mobile Application machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Metal-Organic frameworks for optical sensor arrays

引用

PROGRESS IN MATERIALS SCIENCE 2025年 154卷

作者： Zhang, Xin Cui, Yuanjing Qian, Guodong Zhejiang Univ Sch Mat Sci & Engn ZJU Hangzhou Global Sci & Technol Innovat Ctr State Key Lab Silicon & Adv Semicond Mat Hangzhou 310030 Peoples R China

Precisely identifying subtle structural distinctions among various analytes remains a crucial yet difficult endeavor, primarily due to their extensive diversity, structural resemblance, and the potential for mutual interference. Traditional sensors, which operate on the "lock-and-key" principle, offer high selectivity and specificity for detecting particular analytes. However, this design makes them unsuitable for the simultaneous detection of multiple analytes. Metal-organic frameworks (MOFs) have attracted considerable interest in the realm of optical sensor arrays due to their diverse metal nodes and ligands, as well as the guest species that can be encapsulated within their channels or pores. This versatility makes MOFs highly advantageous for developing multi-channel single-sensing-element sensor arrays. The primary emphasis of this comprehensive review is on the intrinsic structure-performance relationship and development status of MOFbased optical sensor arrays. First, this review offers a concise explanation of the underlying theory and operational steps involved in optical sensor arrays. Second, the construction strategies for cross-reactive sensing elements are thoroughly presented. Third, the applications of MOFbased optical sensor arrays in identifying and detecting target analytes are explored comprehensively. This includes their use in environmental monitoring, disease diagnosis, food quality assessment, and the analysis of complex systems. Finally, the existing limitations and future research opportunities concerning MOF-based optical sensor arrays are thoroughly examined.

关键词： Optical sensor arrays Metal-organic frameworks Sensing elements machine learning algorithms Pattern recognition restriction of intramolecular motions PVA poly (vinyl alcohol) PDMS polydimethylsiloxane.

来源：评论

学校读者我要写书评

暂无评论

A Multihead ProbSparse Self-Attention Mechanism-Based High-Precision and High-Robustness Reconstruction Model for Missing Ocean Data

引用

IEEE SENSORS JOURNAL 2025年第8期25卷 13374-13385页

作者： Zhang, Yuxuan Wu, Huafeng Xian, Jiangfeng Mei, Xiaojun Zhang, Kun Zhang, Qiannan Wang, Feng Shanghai Maritime Univ Merchant Marine Coll Shanghai 201306 Peoples R China Shanghai Maritime Univ Inst Logist Sci & Engn Shanghai 201306 Peoples R China Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin 150001 Heilongjiang Peoples R China

Ocean sensor networks (OSNs) can sense long-time series data, which plays a crucial role in tasks that rely on massive sensory data such as ocean ecosystem monitoring and maritime regulation. Unfortunately, ocean nodes are prone to failures, and harsh ocean channels, and natural environments can interfere with the data collection and transmission process, which can lead to large-scale loss of ocean sensory data. Based upon the comprehensive and in-depth analysis of the ocean's time-varying dynamic environment, we proposed a multihead ProbSparse self-attention mechanism (MPSM)-based Model to predict and reconstruct missing ocean data. Specifically, MPSM can learn key features of ocean observation data on both sides of missing gaps with a dual encoder architecture. Subsequently, the MPSM can efficiently capture intersequence dependencies in parallel with lower computational complexity. Moreover, its residual connection will enhance the model's expressive ability and alleviate gradient vanishing. Simulation experiment results demonstrate that the metrics of MPSM are lower than the selected benchmark algorithms on different ocean datasets, which means MPSM has a stronger robust and generalizability. MPSM can provide high-precision, low-latency missing data restoration capabilities for marine monitoring scenarios. It enhances the continuity and reliability of ocean observation systems.

关键词： Oceans Time series analysis Data models Sensors Prediction algorithms Predictive models Imputation machine learning algorithms Accuracy Feature extraction Dual encoder missing data reconstruction multihead ProbSparse self-attention mechanism (MPSM) ocean sensor networks (OSNs) robust and generalization ability

来源：评论

学校读者我要写书评

暂无评论

A Deep learning and Resampling Approach to Credit Card Fraud Detection 11

A Deep Learning and Resampling Approach to Credit Card Fraud...

引用

11th International Conference on Wireless Networks and Mobile Communications (WINCOM) - Inclusive and Intelligent Connectivity

作者： Akouhar, Mohamed Abarda, Abdallah Elfatini, Mohamed Ouhssini, Mohamed Univ IBN Tofail Lab PDEASG Kenitra Morocco Hassan First Univ Lab MMEC Settat Morocco Univ IBN Zohr Lab SIV Agadir Morocco

ISBN: (纸本)9798350377873;9798350377866

Credit card fraud presents a major challenge for both financial institutions and individuals, with fraudsters employing increasingly complex methods. Traditional machine learning methods often fail to accurately identify fraudulent transactions due to the issue of imbalanced datasets in credit card transactions. In response, we introduce an approach that combines deep learning with resampling techniques to improve the detection of credit card fraud. This study evaluates various machine learning models and tests different oversampling methods. Our results show that combining Generative Adversarial Networks (GANs) with the random forest model significantly outperforms other methods in detecting credit card fraud. This method effectively mitigates the problem of class imbalance, thereby increasing both the accuracy and the efficiency of fraud detection systems. This suggests promising enhancements for the application of fraud detection in realworld scenarios.

关键词： Credit card fraud Fraud detection machine learning algorithms GAN

来源：评论

学校读者我要写书评

暂无评论

Toward a Digital Twin: combining sensing, machine learning, and data visualization for the effective management of a coastal lagoon environment 21

Toward a Digital Twin: combining sensing, machine learning, ...

引用

IEEE 21st Consumer Communications and Networking Conference (CCNC)

作者： Delnevo, Giovanni Tumedei, Gianni Ghini, Vittorio Prandi, Catia Univ Bologna Dept Comp Sci & Engn Bologna Italy

ISBN: (纸本)9798350304572

Coastal lagoons serve as highly productive ecosystems, delivering essential ecosystem services contributing to human welfare and well-being. Unfortunately, these intricate systems are particularly vulnerable to climatic and anthropogenic pressures, such as intensive agriculture and extensive urbanization. This paper presents a Digital Twin prototype of the Mar Menor lagoon in Spain, that utilizes environmental data collected from sensors and predicted data generated through machine learning algorithms. It covers the prototype's architecture, the corresponding API layer designed for interoperability with other systems, and its data visualization dashboard aimed at enhancing decision-making processes.

关键词： environmental sensing machine learning algorithms coastal lagoons data visualization digital twin interoperability

来源：评论

学校读者我要写书评

暂无评论

machine learning Based Classification of Coconut Trees Based on Tree Parameters 2

Machine Learning Based Classification of Coconut Trees Based...

引用

2nd IEEE World Conference on Communication and Computing (WCONF)

作者： Manoharan, Sakthiprasad Kuttankulungara Megalingam, Rajesh Kalman Sreeji, Sruthi Padathiparambil Amrita Vishwa Vidyapeetham ACORD Amrita Coconut Res & Dev Ctr Dept Elect & Commun Amritapuri India

ISBN: (纸本)9798350395334;9798350395327

The coconut tree, known as the 'Kalpavriksha,' holds a significant relationship with nature and people in India. For many, it serves as a source of livelihood, either directly or indirectly. The health status of coconut trees is crucial for agricultural productivity and ecosystem conservation. Tree parameters play a vital role in identifying the health conditions and growth of coconut trees, aiding researchers and farmers in cultivation and health prediction. This paper explores various clustering and classification methods to mitigate time consumption, over fitting, and complexity in data classification. This paper proposes a machine learning algorithm for classifying coconut trees based on tree parameters such as Height, Inclination, and Diameter at breast height (DBH). The proposed approach commences with the extraction of tree parameters using an unsupervised learning algorithm. Parameters such as tree height obtained through a mobile application, inclination measured by an inclinometer, and DBH are used as a database for classifying the coconut tree into different classes. These pre-processed parameters serve as inputs to supervised learning models, including Support vector machine, Random Forest, and K-Nearest Neighbor, to classify trees into different categories. This paper endorses K-means clustering followed by the support vector machine (SVM) approach for classification. Evaluation of each algorithm is conducted by calculating accuracy, precision, and F1 score. The dataset comprising 60 sensor data points is utilized for clustering, parameter training, and testing. By implementing machine learning algorithms with real-time morphological data, greater accuracy is achieved for the classification of coconut tree health.

关键词： Coconut Tree Tree parameters Clustering Classification machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Perpendicularly assembled oriented electrospinning nanofibers based piezoresistive pressure sensor with wide measurement range

引用

Nano Research 2024年第7期17卷 6493-6501页

作者： Xiaoxue Bi Zhigang Duan Xiaojuan Hou Shuo Qian Mengjiao Yuan Jiajun Hu Jie Zhang Yuchen Lu Yanli Liu Jian He Zhiling Peng Xiujian Chou School of Mechanical and Electrical Engineering North University of ChinaTaiyuan 030051China Science and Technology on Electronic Test and Measurement Laboratory North University of ChinaTaiyuan 030051China School of Software North University of ChinaTaiyuan 030051China School of Information and Communication Engineering North University of ChinaTaiyuan 030051China

With the rapid development of wearable electronics,flexible pressure sensors have attracted wide attention in human–computer interaction and intelligent ***,it is a challenge to achieve a sensor with high sensitivity,wide measurement range,and wearing ***,we develop an oriented electrospinning thermoplastic polyurethane/polyacrylonitrile(TPU/PAN)nanofibers(OETPN)based piezoresistive pressure sensor(PONPS)in which the active layer and the electrode are assembled *** interdigital electrode is fabricated by spraying silver nanowires(AgNWs)on the OETPN through a mask *** active layer is composed of OETPN coated with MXene,encapsulated on the electrode by polyurethane(PU)*** porous structure of nanofibers membrane broadens the measurement range of the *** oriented nanofibers as active layer can improve the sensitivity in low pressure,because oriented nanofibers without interweaving nanofibers are more compressible than disordered *** prepared using the spraying method creates nanoscale microstructure and increases *** perpendicular assembly has greater response between the active layer and the electrode than the parallel assembly to improve the *** sensor exhibits high sensitivity(6.71 kPa^(−1),0.02–2 kPa)and wide measurement range(0.02–700 kPa).The sensor can detect weak signals such as radial artery.A pressure array constructed precisely represents the distribution of *** intelligent throat is created by combining machine learning algorithms with the *** can detect and recognize subtle throat vibrations while speaking,achieving recognition accuracy up to 100%using support vector machine(SVM)for five words with different *** fabricated sensor shows promising prospects in personal healthcare and intelligent robots.

关键词： oriented nanofibers perpendicular assembly parallel assembly intelligent throat machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Advanced technologies for precision tree fruit disease management: A review

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2025年 229卷

作者： Yang, Yanqiu Mali, Priyanka Arthur, Lawrence Molaei, Faezeh Atsyo, Sena Geng, Jiarui He, Long Ghatrehsamani, Shirin Penn State Univ Agr & Biol Engn Dept University Pk PA 16803 USA Penn State Univ Fruit Res & Extens Ctr Agr & Biol Engn Dept 290 Univ Dr Biglerville PA 17307 USA

Effective disease management in tree fruit cultivation is essential for ensuring crop health, improving yield, and minimizing economic losses. In recent years, the adoption of advanced technologies has revolutionized the approach to managing tree fruit diseases. This review explores the integration of precision agriculture tools, such as Unmanned Aerial Vehicles (UAVs), Unmanned Ground Vehicles (UGVs), and various sensor technologies, alongside sophisticated machine learning algorithms and predictive models. The effectiveness of these technologies in disease scouting, monitoring, detection, and prediction is evaluated, emphasizing their potential to enhance crop health, reduce economic losses, and minimize environmental impacts. Despite the promising advancements, challenges such as data quality, computational demands, and the need for robust, generalizable models persist. This review underscores the transformative potential of these technologies in promoting a resilient, efficient, and sustainable tree fruit industry, highlighting the need for continued research and development to fully realize their benefits.

关键词： Precision agriculture Tree fruit disease management Remote sensing machine learning algorithms Unmanned vehicles GIS Disease diagnostic

来源：评论

学校读者我要写书评

暂无评论

Firm-level climate change risk and adoption of ESG practices: a machine learning prediction

引用

BUSINESS PROCESS MANAGEMENT JOURNAL 2024年第6期30卷 1741-1763页

作者： Khan, Mushtaq Hussain Alabdeen, Zaid Zein Anupam, Angesh Cardiff Metropolitan Univ Cardiff Sch Management Dept Accounting Econ & Finance Llandaff Campus Cardiff Wales Cardiff Metropolitan Univ Cardiff Sch Technol Dept Data Sci Llandaff Campus Cardiff Wales

PurposeBy combining the notion of prospect theory with advanced machine learning algorithms, this study aims to predict whether financial institutions (FIs) adopt a reactive stance when they perceive climate change as a risk, consequently leading to the adoption of environmental, social and governance (ESG) practices to avoid this risk. Prospect theory assumes that decision-makers react quickly when decisions are framed as a risk or threat rather than as an ***/methodology/approachWe used a sample of 168 FIs across 27 countries and seven regions over the period 2003-2020. To conduct our empirical investigation, we compared the prediction accuracy of various machine learning *** findings suggest that out of 12 machine learning algorithms, AdaBoost, Gradient Boosting and XGBoost have the most precision in predicting whether FIs react to climate change risk in adopting ESG practices. This study also tested the overall climate change risk and risks associated with physical, opportunity and regulatory shocks of climate change. We observed that risks associated with physical and regulatory shocks significantly impact the adoption of ESG practices, supporting prospect theory *** implicationsThe insights of this study provide important implications for policymakers. Specifically, policymakers must take into account the risk posed by climate change in the corporate decision-making process, as it directly influences a firm's adoption of corporate actions (ESG practices).Originality/valueTo the best of our knowledge, this is the first study to investigate the firm-level climate change risk and adoption of ESG practices from a prospect theory perspective using novel machine learning algorithms.

关键词： Adoption of ESG practices Climate change risk machine learning algorithms Prospect theory

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：