检索结果-内蒙古大学图书馆

Predictive modeling for concrete properties under variable curing conditions using advanced machine learning approaches

引用

Asian Journal of Civil engineering 2024年第8期25卷 6249-6265页

作者： Mungle, Nischal P. Mate, Dnyaneshwar M. Mankar, Sham H. Tale, Vithoba T. Mehta, Ankita Dhale, Shrikrishna A. Vairagade, Vikrant S. Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Maharashtra Nagpur 441110 India Department of Mechanical Engineering JSPM’s Rajarshi Shahu College of Engineering Maharashtra Pune 440033 India Department of Mechanical Engineering PCET’s Pimpri Chinchwad College of Engineering and Research Ravet Maharashtra Pune 412101 India Department of Computer Science and Application Ramdeobaba University Maharashtra Nagpur 440013 India Department of Civil Engineering Priyadarshini College of Engineering Maharashtra Nagpur 440019 India

Such is the need for this work, since accurate concrete strength prediction at different curing conditions is critical to having structures that are both strong and long-lasting. Traditional methods for the prediction of concrete strength often lack the complexity that occurs in the interaction of the different environmental factors involved, hence leading to suboptimal practices in curing with potential structural weaknesses. Current research into this area has typically focused on disparate data sources and rather naïve modeling methods, further limiting predictive accuracy and creating a general lack of comprehensive knowledge of curing dynamics. Such limitations bring out the need for a more integrated, sophisticated predictive modeling approach to explain variability in concrete strength levels. This paper proposes a novel predictive modeling framework that will be powered by advanced machine learning techniques to take up these challenges. It will adopt a multimodal data integration approach driven by a combination of sensor data related to temperature, humidity, and strain gauges;environmental data related to weather conditions and atmospheric pressure;and historical records, such as mix design and curing duration, further leveraging techniques from data fusion, including the Kalman filter and Bayesian networks. This will be further integrated into a unified, enriched dataset, encapsulating the complex interaction of factors influencing concrete strength. In the present work, this is a chosen approach: hybrid modeling with ensemble learning using XGBoost for the prediction of static features, and Long Short-Term Memory (LSTM) networks for capturing temporal dependencies. In this case, a combination of these models via weighted averaging or stacking improves the accuracy of the predictions to a very great extent: the R² increased from 0.85 to 0.92, and MAE levels by 10–15%. In addition to that, AutoML with Feature Tools implements advanced feature engineering

关键词： Concrete strength Data fusion Ensemble learning Machine learning Predictive modeling

来源：评论

学校读者我要写书评

暂无评论

Despeckling Algorithm for Ultrasound Images based on Variation filter in Wavelet Domain 8

Despeckling Algorithm for Ultrasound Images based on Variati...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Wang, Cai Yadav, Amit Khan, Asif Yadav, Dakshina Chengdu Neusoft University Department of Software Engineering Chengdu China Charles Darwin University College of Engineering It and Environment NT Australia Integral University Department of Computer Application Lucknow India Plant Industry Department of Industry Tourism and Trade Line Darwin Australia

ISBN: (纸本)9798350376425

Ultrasonic imaging technology is widely used in clinical medicine. It is very challenging to remove speckle noise in ultrasonic images because it is not easy to model accurately and it is dependent on the amplitude of the tissue object. To effectively remove the speckle noise of ultrasound images, a despeckling algorithm based on the variational filter in wavelet domain is proposed. The wavelet transform with time-frequency characteristic is used to decompose the ultrasound image firstly, and the variational filter based on BMAPE (Bayesian Maximum A Posteriori Estimation) is applied to filter the coefficients of the low frequency part in wavelet domain. The speckle noise in wavelet is modeled as Laplace distribution, then the coefficients of high frequency part is shrinkaged by a new adaptive wavelet threshold function. Compared with the wavelet soft-threshold filter and variational filter, results show that the proposed filter performs better despeckling ability while preserving the edge information. © 2024 IEEE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Routing Protocols for FANETs

Performance Analysis of Routing Protocols for FANETs

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Anita Rani Vinay Bhardwaj Computer Application Lovely Professional University Phagwara INDIA Computer Science and Engineering Lovely Professional University Phagwara INDIA

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Routing protocols play an important role in unmanned aerial vehicle (UAV) communication networks. When transferring information in low-altitude environments, UAVs confront difficulties in ensuring efficient and reliable packet transmission between nodes. To address this scientific challenge, a routing protocol needs to be developed that can meet these requirements. In this paper, we have created a more realistic simulation environment based on NS-3 and conducted performance tests and comparisons on four classic routing protocols: Ad Hoc on-demand distance vector (AODV), Destination-Sequenced Distance-Vector Routing (DSDV), Dynamic Source routing (DSR) and optimized link state routing (OLSR). We have analyzed performance parameters such as packet delivery and throughput. Our findings demonstrate that alternative routing strategies may function effectively in several UAV communication network circumstances. These experiments generate quantitative data that determines the optimum pathways in every specific scenario. According to the data analysis, while utilized on networks of 50,100,200, and 250, the AODV protocol has an accuracy of 96%. The DSR protocol achieves 90% accuracy, the DSDV protocol 87% accuracy, and the OLSR protocol 80%. The results show that AODV outperforms other traditional approaches, resulting in a considerable improvement in network efficacy.

关键词： Technological innovation Accuracy Routing Autonomous aerial vehicles Throughput Routing protocols Vectors Communication networks Vehicle dynamics AODV

来源：评论

学校读者我要写书评

暂无评论

Novel Robust Span-based Model for Event Detection 3

Novel Robust Span-based Model for Event Detection

引用

3rd International conference on computer, Big Data and Artificial Intelligence, ICCBDAI 2022

作者： Zhang, Hang Yuan, Xiaoguang Song, Yingyi Yang, Yuting Wang, Rui Liu, Bing Han, Cuihong Beijing Institute of Computer Technology and Application Yongding Road Beijing100854 China College of Systems Engineering National University of Defense Technology Sifangping Street Changsha410073 China

Event detection (ED) aims to identify events and their types from the given text, which is the vital subtask of event extraction. However, poor quality training corpus can seriously affect the validity of current dominating deep learning-based techniques. In order to improve the robustness of the model, this paper converts the ED task into the named entity recognition (NER) task, and uses the span-based NER framework to identify and classify event triggers. In addition, we ameliorate the framework through data cleaning strategy, hierarchical learning rate strategy, sentence-level loss function and model ensemble strategy. The experimental results suggest that our approach achieves state-of-the-art performance on the widely used Chinese dataset. Moreover, the deep analysis has confirmed the effectiveness of the improvement strategy in resisting data pollution. © Published under licence by IOP Publishing Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Driven Economic Modeling for Enhanced Unemployment Rate Prediction and Analysis

Machine Learning-Driven Economic Modeling for Enhanced Unemp...

引用

International Conference on Computational Intelligence and Communication Networks (CICN)

作者： Rakhi Arora Nitin Dixit Muskan Sihare Shreshtha Kinger Sneha Shivhare Komal Kulshreshtha Computer Science and engineering Institute of technology & Management Gwalior India Masters of Computer Application Vikrant University Gwalior India

ISBN: (数字)9798331505264

ISBN: (纸本)9798331505271

This study presents a comprehensive analysis of economic modeling using Python, specifically focusing on the prediction of unemployment rates. In response to the growing significance of data-driven decision-making in economics, our research explores the application of logistic regression and random forest classification models to comprehend and forecast unemployment status. The dataset utilized in this analysis encompasses historical unemployment rate data, serving as a valuable source for our modeling endeavors. Our methodology begins with logistic regression, establishing a baseline model to scrutinize the relationship between diverse economic indicators and the binary classification of unemployment status (above or below 10%). We evaluate the model's efficacy in capturing trends over time and identifying influential factors in determining unemployment status. Subsequently, we advance our approach by employing random forest classification, a sophisticated machine learning technique adept at capturing non-linear relationships and interactions within the data. Our investigation shows that both random forest classification and logistic regression are good at predicting jobless status. We conduct a comparative evaluation of these models, shedding light on their respective strengths and limitations. Additionally, we delve into the significance of feature selection, hyperparameter tuning, and model evaluation within the realm of economic modeling using Python.

关键词： Logistic regression Analytical models Accuracy Biological system modeling Computational modeling Predictive models Market research Unemployment Random forests Tuning

来源：评论

学校读者我要写书评

暂无评论

Exploring Research Opportunities to Apply Data Mining Techniques in Software engineering Lifecycle 1

Exploring Research Opportunities to Apply Data Mining Techni...

引用

1st International Conference on Advances in Electrical, Electronics and Computational Intelligence, ICAEECI 2023

作者： Anitha Gracy, J. Parthasarathy, S. Bagavathilaksmi, R. Thiagarajar College of Engineering Applied Mathametics and Computational Science Madurai India VELS Institute of Science Technology and Advanced Studies Department of Computer Application/Information Technology Chennai India

ISBN: (纸本)9798350342796

This Software engineering (SE) is the core research area of the software industry, and numerous algorithms and frameworks are proposed every day. Software engineering is the discipline that keeps up with recent developments in fields and techniques such as data mining, machine learning, natural language processing, and artificial intelligence. It is difficult to manage such a massive amount of data in a software engineering repository if data processing and big data analytics are not available. This paper provides an in-depth study of data mining techniques that to improve the efficiency of the software development lifecycle. The study emphasizes the practical applications and discoveries made by text mining, clustering, classification, and other methods. © 2023 IEEE.

关键词： Classification Clustering Data Mining SDLC Software engineering Text Mining

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Bearing Fault Diagnosis Method for Complex Electromechanical Hydraulic System

Unsupervised Bearing Fault Diagnosis Method for Complex Elec...

引用

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Zizhou He Wenwen Shen Suicheng Li Tianyou Yuan Xiaowei Zhou Zhigao Ni Department of Computer Engineering and Science Institute of Computer Application CAEP Sichuan Province China

Finding the optimal combination of feature extraction and classifier has always been a hot issue in intelligent health monitoring. Traditional artificial features are difficult to achieve the ability of deep learning to mine deep abstract features of signals. However, compared with ensemble learning models, deep learning classifiers have the problems of easy overfitting, poor generalization performance, and the need for a large number of labeled samples. Autoencoder has the advantage of unsupervised feature extraction, LightGBM has the advantage of feature selection, so this paper proposes a fault diagnosis method combining deep convolutional sparse autoencoder with LightGBM, which has the advantages of unsupervised feature extraction and distributed gradient boosting. Experiments are carried out on the CWRU bearing dataset to verify the superiority of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deploying Reinforcement Learning Approaches for Smart Home Automation 15

Deploying Reinforcement Learning Approaches for Smart Home A...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Sen, Amit Prakash Goyal, Manish Kumar Shalini Arka Jain University Department of Electrical & Electronics Engineering Jharkhand Jamshedpur India Vivekananda Global University Department of Computer Science & Application Jaipur India Department of Management School of Mangement - Pg Karnataka Bangalore India

ISBN: (纸本)9798350370249

Reinforcement mastering is an area of synthetic intelligence that enables machines to adopt actions that optimize their environment or maximize a pre-defined reward. This paper investigates the potential makes use of reinforcement studying for clever domestic automation. Some of distinctive algorithms had been advanced that leverage reinforcement getting to know strategies for clever houses. The paper discusses the advantages of using reinforcement learning for optimizing electricity consumption, increasing comfort, and presenting protection as well as the potential challenges of such deployment. The paper also evaluations several present reinforcement studying-based totally methods applicable for smart domestic automation and highlights ability studies possibilities to address present methodological gaps in an effort to enable the reliable deployment of reinforcement getting to know for clever domestic automation. © 2024 IEEE.

关键词： Deployment Distinctive Domestic Methodological Potential Protection Reinforcement

来源：评论

学校读者我要写书评

暂无评论

The development of a new edge computing device based on deep learning YOLOv8 algorithm for diabetic retinopathy Detection 5

The development of a new edge computing device based on deep...

引用

5th IEEE International Conference on Advances in Computing, Communication Control and Networking, ICAC3N 2023

作者： Singh, Devendra Mohan, Lalit Pant, Janmejay Mittal, Amit Dobhal, Dinesh C. Graphic Era Deemed To Be University Department Of Computer Science And Engineering Dehradun India Graphic Era Hill University Department Of Computer Science And Engineering Bhimtal India Graphic Era Hill University Department Of Allied Science Bhimtal India Graphic Era Deemed To Be University Department Of Computer Science Application Dehradun India

ISBN: (纸本)9798350330861

Diabetic retinopathy is a prevalent eye disorder that occurs in individuals with diabetes. The condition is caused by damage to the retinal blood vessels caused by elevated blood sugar levels. The retina is the tissue behind the eye that is sensitive to light. Among the leading causes of blindness worldwide is diabetic retinopathy. However, early detection and prompt treatment can effectively prevent or minimize vision loss. Deep learning algorithms, such as 'You Only Look Once' (YOLO) Convolutional Neural Networks (CNNs), have demonstrated state-of-the-art performance on benchmark datasets and computer vision competitions. YOLO is a single end-to-end model that enables real-time object identification with high accuracy. Our proposed YOLOv8-based model integrated with Jetson Nano Developer Kit with CSI camera module shows the highest top1 accuracy of 93.77 on the training dataset and validation dataset with all given classes its measured accuracy top1 accuracy is 72.6 with 2.6ms inference time. © 2023 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Filtering of Spurious Sonar Signals 14

Filtering of Spurious Sonar Signals

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Srutheeshna, U. Ashraf, Sharik Koshy, Litty Department of Master of Computer Application SCMS School of Engineering &Technology VidyaNagar Karukutty Ernakulam India Naval Physical and Oceanographic Laboratory P.B.NO.6 NGO Quarters Thrikkara Vazhakkala Kochi India Department of computer science & Engineering SCMS School of Engineering & Technology VidyaNagar Karukutty Ernakulam India

Navy uses a harmonic filter to extract the propel sounds in ships. Usually, Sonar processing uses the harmonic filter to remove unwanted harmonics. The proposed system is used for filtering unwanted noise from lower frequency noise using the machine learning technique. Some sonar may have higher frequency sounds, which can be difficult to hear. Using this sound frequency humans can identify their target by experience. Automate these sounds and using a trained neural network, Classify the sounds. Retrieve non-frequency voice and avoid harmonics using a neural network. © Grenze Scientific Society, 2023.

关键词： High pass filters

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：