检索结果-内蒙古大学图书馆

A Knowledge-graph based Method for Datum Reference Frame Reasoning

Procedia CIRP 2024年 129卷 7-12页

作者： Hongsheng Fu Chao Kong Yanlong Cao Yuanping Xu Jin Jin Tukun Li Junding Luo Zongzheng Zhang School of Mechanical Engineering Zhejiang University Zhejiang China NIO Automobile Technology (Anhui) CO. Ltd China School of Computing and Engineering University of Huddersfield Queensgate Huddersfield UK School of Software Engineering Chengdu University of Information Technology Chengdu China Shandong Industrial Technology Research Institute of Zhejiang University Shandong China

In mechanical engineering, the datum is essential in the tolerance specification, which impacts assembly and functional requirements. The standard mechanical parts, such as shaft and gear, already have a formalized datum reference frame (DRF) design process. However, non-standard parts still mainly rely on manual design. To this end, a knowledge-graph-based DRF reasoning method for non-standard parts is proposed. In this paper, an OWL 2-based knowledge model is constructed according to industrial practice. It combines empirical knowledge, knowledge graphs, and ontology reasoning methods to perform DRF generation automatically and precisely. The finite element method is introduced into this work to evaluate reasoned DRF. The effectiveness and feasibility of the method are demonstrated via a case study.

关键词： DRF knowledge reasoning ontology non-standard part evaluation

来源：评论

学校读者我要写书评

暂无评论

Evaluation of machine learning-based regression techniques for prediction of diabetes levels fluctuations

引用

Heliyon 2025年第1期11卷 e41199页

作者： Alkalifah, Badriah Shaheen, Muhammad Tariq Alotibi, Johrah Alsubait, Tahani Alhakami, Hosam Department of Computer Science and Artificial Intelligence College of Computing Umm Al-Qura University Makkah Saudi Arabia School of Electrical Engineering and Computer Science NUST Islamabad Pakistan Department of Software Engineering College of Computing Umm Al-Qura University Makkah Saudi Arabia

Middle-Aged and Elderly people today face a variety of health problems as a result of their modern lifestyle, which includes increased work stress, less physical activity, and altered food habits. Because of Complications arising, diabetes has become one of the most frequent, severe, and fatal illnesses around the world. Therefore, inaccurate measurements of blood glucose levels can seriously damage vital organs. Several strategies for long-term glucose prediction have been proposed in the literature. Unfortunately, these methods require the patient to identify their daily activities, which can be error-prone, such as meal intake, insulin injection, and emotional aspects. This paper suggests using continuous glucose monitoring (CGM) of 14733 patients, with three assistance factors to predict blood glucose levels independently of other parameters, hence reducing the burden on the patients. To support this an Artificial Neural Network (ANN), Binary Decision Tree (BDT), Linear Regression (LR), Boosting Regression Tree Ensemble (BSTE), Linear Regression with Stochastic Gradient Descent (LRSGD), Stepwise (SW), Support Vector Machine (SVM), and Gaussian process regression (GPR) were investigated. The result indicated that The highest classification accuracy of (92.58%) has been achieved by BDT followed by BSTE (92.04%) and GPR (88.59%). The obtained average of root means square error (MSE) was 1.64, 1.67, 1.69, mg/dL for prediction horizon (PH) respectively to GPR, BSTE, and ANN. © 2024 The Author(s)

关键词： Continuous glucose monitoring (CGM) Diabetic Hyperglycemia Hypoglycemia Machine learning (ML) Regression

来源：评论

学校读者我要写书评

暂无评论

An Efficient Classification Techniques for Brain Tumor Using Features Extraction and Statistic Methods, with Machine Learning Algorithms

An Efficient Classification Techniques for Brain Tumor Using...

引用

作者： Badshah, Shah Hussain Farhatullah khan, Gul Zaman Hassan, Muhammad Abul Junaid, Hazrat Sohail, Muhammad Mahbob, Muhammad Awais Ahamad, Izaz Ullah, Nadeem Department of Computing and Technology Abasyn University Peshawar Pakistan School of Automation China University of Geosciences Wuhan430074 China Department of Computer Software Engineering University of Engineering and Technology Mardan Pakistan Department of Computer Science and Information Technology University of Malakand Dir Lower Pakistan Department of Computer Science Bahria University Islamabad Pakistan Department of Computer Science University of Engineering and Technology Taxila Pakistan Department of Information Engineering and Computer Science University of Trento Trento38122 Italy

Today, brain tumor is a very dangerous disease that can even cause death. There are many ways to classify Brain MRI images of tumors. Various aspects of current research have limitations;some methods are accurate but take a long time to compute while some algorithms are fast, but with low accuracy. Consequently, a lot of effort is needed in this area. In this paper, our major goal is to reduce computation time and improve the classification accuracy for brain MRI images. This research proposes four phases: preprocessing, feature extraction, feature selection, and classification. During pre-processing, the median filter was used to reduce noise in the images, and the grayscale image size was reduced to further limit the image for efficient use. After that the Gray images are then given as inputs to the Feature extraction phase to select a limited feature from the image namely, texture features, shape features, smoothing features. The images features obtained in the feature’s extraction phase are still large, and we cannot simply feed them to machine learning models for processing due to computational constraints. So, we need to analyze it and pick out some interesting elements from the images. The statistical features namely, variances, mean, correlation are used in the feature selection phase to select more significant features to reduce the size of the features and reduce computational time. These features are combined and labeled in a file to train Machine Learning (ML) algorithms. We used two types of machine learning algorithms in the classification phase: classifier and evolutionary algorithm. The selected classifier algorithms results are combined in a file and we named it S-K-E-L Classifier and it gives us acceptable results in terms of accuracy and time. Similarly, an evolutionary algorithm named P-S-D-G Classifier also gives us acceptable results in terms of accuracy and time. Lastly, we combine both S-K-E-L Classifier and P-S-D-G Classifier in a file with

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Bilinear Graph Neural Network-Enhanced Web Services Classification 23

Bilinear Graph Neural Network-Enhanced Web Services Classifi...

引用

23rd IEEE International Conference on High Performance computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Zhang, Lulu Cao, Buqing Peng, Mi Qing, Yueying Kang, Guosheng Liu, Jianxun Fletcher, Kenneth K. School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory of Service Computing and New Software Service Technology Xiangtan China University of Massachusetts Boston Department of Computer Science Boston United States

ISBN: (纸本)9781665494571

With the growing number of Web services, classifying Web services accurately and efficiently has become a challenging problem. Effective service classification is conducive to improving the quality of service discovery and the efficiency of service composition. Existing graph neural network methods represent the target service node by a weighted sum of the features of the neighbor service nodes, and have achieved remarkable results in service classification. However, these methods ignore the impact of possible interactions between neighbor service nodes on the target service node. To address this problem, we propose a Web services classification method based on bilinear graph neural network. Our proposed method can model the bilinear interactions between neighbor service nodes and effectively improve the accuracy of service classification. First, our proposed model uses the Word2Vec model to extract the latent semantic vectors from service description documents. We then construct the service relationship network according to tags and shared annotation relationships of Web services. Next, a bilinear aggregator is used to model the pairwise interactions between neighbor service nodes, highlighting the local common attributes. Finally, the bilinear aggregator is combined with the weighted sum aggregator to construct a bilinear graph neural network, which can learn more comprehensive representations of services. The experimental results on the real dataset from ProgrammableWeb show that the classification accuracy of the proposed method is greatly improved compared with DeepWalk, Node2Vec, GCN, and GAT. © 2021 IEEE.

关键词： Smart cities Annotations Mashups Semantics Quality of service Feature extraction Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Local Information Guided Global Integration for Infrared Small Target Detection

Local Information Guided Global Integration for Infrared Sma...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qiang Li Qianchen Mao Wenjie Liu Jinbao Wang Wenmin Wang Bingshu Wang School of Software Northwestern Polytechnical University Xi’an China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Faculty of Innovation Engineering Macau University of Science and Technology Macau China

Infrared small targets often exhibit small scale and weak semantic features, which makes it a great challenge to their detection. To address this situation, we propose a novel network for infrared small target detection that combines local details information and global contextual information. To preserve the local and high-frequency details present in infrared images, we introduce a High-frequency Aware Encoder. To extract contextual information from multi-scale feature maps, we propose a Multi-scale Context Learning Bottleneck that incorporates contextual information repeatedly and performs cross-level fusion, which enables the recognition of small targets based on their surroundings. Finally, a lightweight Transformer Decoder is employed to restore the feature map, while placing attention on the target pixels. Experimental results on the IRSTD-1k dataset demonstrate that our method outperforms other state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Algorithm for the Laser Stripe Centreline Extraction 17

A Hybrid Algorithm for the Laser Stripe Centreline Extractio...

引用

17th CIRP Conference on Computer Aided Tolerancing, CAT 2022

作者： Mao, Zirui Xu, Yuanping Guo, Benjun Li, Tukun Jiang, Xiangqian Shi, Yajing Cao, Yanlong Xu, Zhijie Zhang, Chaolong Huang, Jian School of Software Engineering Chengdu University of Information Technology Chengdu China School of Computing and Engineering University of Huddersfield HuddersfieldHD1 3DH United Kingdom Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province College of Mechanical Engineering Zhejiang University Hangzhou310027 China

Centreline extraction is one of the critical processes of structured light systems that play an increasingly important role in industry 4.0. This paper proposes a novel algorithm to extract the centreline by combining an improved skeleton thinning algorithm to extract the initial centreline and an improved grey centroid algorithm to establish the final centreline. It consists of several steps: Firstly, an image difference operation and a thresholding operation are undertaken, and the Canny edge detection algorithm is applied to locate the approximate position of the laser stripe to reduce the image matrix calculation cost;Secondly, an initial centreline is extracted via the use of an image morphology operation and a skeleton thinning algorithm;Finally, a high-power grey centroid method is employed to acquire the centreline at the sub-pixel level. Experiments together with a comparison with other mainstream methods is conducted to test the validity and practicability of the proposed hybrid algorithm. The experimental results show that the speed of the proposed algorithm is 50% faster than the Steger algorithm, and the root-mean-square error is 40% lower than the grey centroid method. © 2022 The Author(s).

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

p-Norm Broad Learning for Negative Emotion Classification in Social Networks

引用

Big Data Mining and Analytics 2022年第3期5卷 245-256页

作者： Guanghao Chen Sancheng Peng Rong Zeng Zhongwang Hu Lihong Cao Yongmei Zhou Zhouhao Ouyang Xiangyu Nie Laboratory of Language Engineering and Computing Guangdong University of Foreign StudiesGuangzhou 510006China Guangdong Provincial Key Laboratory of Nanophotonic Functional Materials and Devices South China Normal UniversityGuangzhou 511400China School of Computer Science and Software Zhaoqing UniversityZhaoqing 526000China School of Information Science and Technology Guangdong University of Foreign StudiesGuangzhou 510006China School of Computing University of LeedsLeeds LS29JTUnited Kingdom

Negative emotion classification refers to the automatic classification of negative emotion of texts in social *** existing methods are based on deep learning models,facing challenges such as complex structures and too many *** meet these challenges,in this paper,we propose a method for negative emotion classification utilizing a Robustly Optimized BERT Pretraining Approach(RoBERTa)and p-norm Broad Learning(p-BL).Specifically,there are mainly three contributions in this ***,we fine-tune the RoBERTa to adapt it to the task of negative emotion ***,we employ the fine-tuned RoBERTa to extract features of original texts and generate sentence ***,we adopt p-BL to construct a classifier and then predict negative emotions of texts using the *** with deep learning models,p-BL has advantages such as a simple structure that is only 3-layer and fewer parameters to be ***,it can suppress the adverse effects of more outliers and noise in data by flexibly changing the value of ***,we conduct extensive experiments on the public datasets,and the experimental results show that our proposed method outperforms the baseline methods on the tested datasets.

关键词： social networks negative emotion RoBERTa broad learning p-norm

来源：评论

学校读者我要写书评

暂无评论

Online Course Recommendation by Exploring User Interaction and Course Description

Online Course Recommendation by Exploring User Interaction a...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Weike Zhou Xiaokang Zhou Jing He Yamei Nie Qiqi Chen Guosheng Kang School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Hunan Provincial Key Lab. for Services Computing and Novel Software Technology HNUST Xiangtan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

With the wide use of Massive Open Online Courses (MOOCs) and online education, the large number and variety of educational resources on the online course open platform make it difficult for users to choose, and the requirements for course recommendation algorithms and model performance are getting higher and higher. The existing course recommendation algorithms often ignore the interactive information between n learners and courses and the course descriptions, resulting in poor recommendation performance. To solve the problems above, our work proposes an online course recommendation approach via exploring user interactions and course description documents. Specifically, LightGCN model is used to represent the user-course interaction graph to derive the structural embeddings of users and courses. Moreover, BERT model is used to represent the course description documents to derive the description embeddings of courses. Based on the three embeddings, ANFM (Attention Neural Factorization Machine) model is applied to perform online course recommendation by modeling low-order and high-order feature interactions, and learning the weights of the feature interactions through the attention mechanism. Finally, solid experiments are conducted over a real-world public dataset. Experimental results show that the proposed approach outperforms the baseline methods under NDCG, Recall and Precision.

关键词： Electronic learning Attention mechanisms Federated learning Education Solids

来源：评论

学校读者我要写书评

暂无评论

An AI-Based Chicken Disease Management System 1st

An AI-Based Chicken Disease Management System

引用

1st International Conference on Artificial Intelligence for Smart Community, AISC 2020

作者： Quach, Luyl-Da Quoc, Nghi Pham Thi, Nhien Huynh Le Thanh, Nhan Thanh, Xuan Truong Thi Tran, Duc Chung Hassan, Mohd Fadzil Software Engineering Department FPT University Cantho city Viet Nam Computing Fundamental Department FPT University Hanoi Viet Nam Department of Computer and Information Sciences Universiti Teknologi PETRONAS Seri Iskandar Perak Malaysia

ISBN: (纸本)9789811621826

Food stability has always received worldwide attention, especially in the development of the poultry industry. However, the poultry’s diseases have caused the loss of the poultry population and direct income of the owners. In this work, a system comprising of a website and a mobile application has been developed to support disease identification in chickens;the disease spread locations can be managed and traced with maps. In addition, the system allows farmers to make contact and get support from experts through chat, voice calls, and video calls. It also has some e-commerce functions for improving sales of poultry’s owners. The system uses the improved ResNet-50 model, with an accuracy of about 93.56%. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

TSCA: Enhancing Smartphone Security with a Touchpoints-Sensitive and Context-Aware Model for Touchscreen-Based Authentication

TSCA: Enhancing Smartphone Security with a Touchpoints-Sensi...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Yingjie Wang Ruimin Hu National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Whuhan China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Whuhan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

With the widespread use of smartphones, more and more private information is stored on them, which requires a more secure authentication method. Continuous authentication methods show potential for privacy protection due to their continuous and transparent nature, as opposed to the entry-point authentication methods like PIN codes and facial recognition. Users' touchscreen behavior, being both common and unique, has been widely studied in the field. However, previous methods based on manual features and deep learning have certain shortcomings when mining patterns from touchscreen behaviors that are beneficial for authentication. First, the operating habits of different users lead to different importance of touch points in a single touchscreen swipe. Second, extracting features from each touchscreen swipe independently ignores useful information from the context. To address this problem, we propose a novel Touchpoints-Sensitive and Context-Aware model called TSCA, which is able to adaptively assign weights to different touch points in a touchscreen swipe while also taking into account information from the context of the touchscreen swipe. We evaluate the TSCA model on two publicly available datasets and show that the TSCA is able to deliver significant performance gains compared to baseline methods while reducing model complexity.

关键词： Deep learning Adaptation models Privacy Computational modeling Authentication Touch sensitive screens Feature extraction Complexity theory Smart phones Context modeling

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：