检索结果-内蒙古大学图书馆

2023 1st DMIHER International Conference on Artificial Intelligence in Education and Industry 4.0, IDICAIEI 2023

作者： Tiwari, Shivam Sharma, Vikrant Rathore, Yogesh Singh Gandhi, Parul Srivastava, Durgesh Sharda University Department of Computer Science & Engineering Greater Noida India Graphic Era Hill University Computer Science and Engineering Dehradun India Sharda University Computer Science and Application UP Greater Noida India Manav Rachna International Institute of Research and Studies Department of Computer Applications Haryana Faridabad India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

ISBN: (纸本)9798350338423

The vast variety of floral species present on Earth poses a considerable challenge in memorizing their individual names. Acquiring knowledge about specific flower types inhabiting diverse environments like forests, mountains, and dense regions becomes crucial for their recognition and differentiation. Consequently, the development of a technique for accurately determining flower categories becomes imperative. The task of distinguishing and categorizing a particular blossom amidst the extensive array of floral species presents a formidable task. Hence, the automation of flower species identification has been a subject of extensive research interest. This research domain is characterized by the utilization of features extracted from floral images in conjunction with specialized algorithms aimed at classifying flower species. A prominent aspect of these endeavors is the employment of three widely recognized flower image datasets. The present study constitutes a comprehensive survey of various methodologies proposed by diverse researchers with the objective of accomplishing precise identification of flower species. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Texture-Based Garments Defect Detection Method Using Machine Learning 2nd

Texture-Based Garments Defect Detection Method Using Machine...

引用

2nd International Conference on Cyber Intelligence and Information Retrieval, CIIR 2023

作者： Rahul, Mayur Verma, Shekhar Singh, Akhilesh Verma, Sarvachan Yadav, Vikash Department of Computer Application School of Engineering & Technology CSJM University Uttar Pradesh Kanpur India Ajay Kumar Garg Engineering College Uttar Pradesh Ghaziabad India Department of Technical Education Government Polytechnic Bighapur Unnao Uttar Pradesh Manpur India

ISBN: (纸本)9789819735938

Fabric defects identification is significantly important in textile industry. Various activities are involved in detecting fabric quality. The total profits of the industries depend on the defects on the quality of fabrics that produces loss. Existing defect identification methods are conducting in different organizations with the help of human defect inspectors who draw manually defect pattern. However, these detection techniques have few drawbacks like complication, inaccuracy, negligence, tediousness, and exhaustion in addition to time-consuming which causes decrease performance in failure finding. For the sake of overcoming these problems, a framework that depends on processing of image has been introduced to efficiently and effectively identify the defects of fabrics. The given introduced work consists of image segmentation, morphological methods, feature extraction, and classification. We have used edge detection for image segmentation, ICA for feature extraction, and SVM for image classification. The results achieved from the given framework are superior than existing framework. The experiments have been conducted in Python environment using TILDA datasets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

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

Deep Learning-Based Diagnostic Tool for Brain Tumours 3

Deep Learning-Based Diagnostic Tool for Brain Tumours

引用

3rd International Conference on Innovative Sustainable Computational Technologies, CISCT 2023

作者： Singh, Arun Rakhra, Manik Singh, Dalwinder Sharma, Arvind Kumar, Rakesh Lovely Professional University Department of Computer Science & Engineering Jalandhar Phagwara India School of Computer Application Lovely Professional University Punjab Phagwara India Lovely Professional University Department of Mathematics Punjab Phagwara144411 India

ISBN: (纸本)9798350303360

In this work, we provide the results of our experiments on Brain Tumour Classification and explore their implications. MRI, short for magnetic resonance imaging, is a crucial piece of medical imaging technology that creates high-resolution pictures of the inside of a human body by combining radio waves, a strong magnetic field, and a computer. In this study, we employ a CNN-based Deep learning model to categorise cases of brain tumours. Common applications for CNNs (Convolutional Neural Networks) include video and image analysis. It processes images by first ingesting them and then convoluting them into smaller and smaller pieces. The convolutional layer analyses the input picture using a series of filters designed to identify elements like edges, curves, and patterns. Here, we constructed the CNN using data obtained from Kaggle. It contains roughly 3300 MRI scans of the brain, split into 4 groups (no tumours, meningioma tumours, glioma tumours, and pituitary tumours) and a total of 384 testing pictures. We used Keras to construct the model. The accuracy of the suggested project is quite high, coming in at 97.142%. The Confusion matrix is used to evaluate the precision. It is a data table for measuring the efficacy of an ML system. This provides the results of a comparison between the actual values in a dataset and the model's projected values in an easy-to-understand format. © 2023 IEEE.

关键词： Neuroimaging

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

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

Optimizing Type-2 Diabetes Mellitus Early Detection using ML Techniques 8

Optimizing Type-2 Diabetes Mellitus Early Detection using ML...

引用

8th International Conference on Inventive Computation Technologies, ICICT 2025

作者： Mishra, Debaswapna Behera, Bichitrananda Pattnayak, Parthasarathi Mohanty, Arpeeta Patnaik, Sanghamitra Department of Computer Science and Application OUAT Bhubaneswar India Department of Computer Science and Engineering C.V. Raman Global University Bhubaneswar India School of Computer Applications KIIT Deemed to be University Bhubaneswar India School of Computer Engineering KIIT Deemed to be University Bhubaneswar India School of Law KIIT Deemed to be University Bhubaneswar India

ISBN: (纸本)9798331512248

A major global health concern, T2DM (type 2 diabetes mellitus) has a substantial impact on people's longevity and general well-being. In order to avoid or postpone difficulties, early detection is essential. To diagnose type 2 diabetes at an earlier stage, the usefulness of machine learning techniques is assessed in this work. Using a dataset that included both healthy controls and patients having type 2 diabetes, a classification model was created, utilising sophisticated feature selection approaches to improve performance. K-Nearest Neighbours, support vector machines, random forests, logistic regression, and decision trees are just a few of the machine learning algorithms that have undergone extensive training and testing. Of these, the Random Forest method demonstrated the promise of machine learning in T2DM detection with an exceptional 98% accuracy rate. The study emphasises how crucial it is to include these cutting-edge techniques into clinical decision-making procedures. In order to improve patient outcomes and lessen the disease's worldwide impact, the findings help build precision medicine screening technologies that allow healthcare practitioners to identify type 2 diabetes in its earliest stages. © 2025 IEEE.

关键词： ML models precision medicine SVM T2DM

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

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

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：