检索结果-内蒙古大学图书馆

machine learning analysis of cervical balance in early-onset scoliosis post-growing rod surgery: a case-control study

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-11页

作者： Han, Bo Hai, Junrui Jonathan Pan, Aixing Wang, Yingjie Hai, Yong Capital Med Univ Beijing Jishuitan Hosp Beijing Peoples R China Princeton Int Sch Math & Sci 19 Lambert Dr Princeton NJ 08540 USA Capital Med Univ Beijing Chao Yang Hosp Dept Orthoped Surg GongTiNanLu 8 Beijing 100020 Peoples R China China Univ Petr East China Coll Control Sci & Engn Qingdao 266580 Peoples R China Capital Med Univ Joint Lab Res & Treatment Spinal Cord Injury Spina Beijing Peoples R China Capital Med Univ Clin Ctr Spinal Deform Beijing Peoples R China

We aimed to analyze the cervical sagittal alignment change following the growing rod treatment in early-onset scoliosis (EOS) and identify the risk factors of sagittal cervical imbalance after growing-rod surgery of machine learning. EOS patients from our centre between 2007 and 2019 were retrospectively reviewed. Radiographic parameters include the cervical lordosis (CL), T1 slope, C2-C7 sagittal vertical axis (C2-7 SVA), primary curve Cobb angle, thoracic kyphosis (TK), C7-S1 sagittal vertical axis (C7-S1 SVA) and proximal junctional angle (PJA) were evaluated preoperatively, postoperatively and at the final follow-up. The parameters were analyzed using a t-test and chi 2 test. The machine learning methodology of a sparse additive machine (SAM) was applied to identify the risk factors that caused the cervical imbalance. 138 patients were enrolled in this study (96 male and 42 female). The mean thoracic curve Cobb angle was 67.00 +/- 22.74 degrees. The mean age at the first operation was 8.5 +/- 2.6yrs. The mean follow-up was 38.48 +/- 10.87 months. CL, T1 slope, and C2-7 SVA increased significantly in the final follow-up compared with the pre-operative data. (P < 0.05). The CL and T1 slope increased more significantly in the group of patients who had proximal junctional kyphosis (PJK) compared with the patients without PJK (P < 0.05). The location of the upper instrumented vertebrae (UIV) and single/dual growing rod had no significant influence on the sagittal cervical parameters (P > 0.05). According to the SAM analysis of machine learning algorithms, Postoperative PJK, more improvement of kyphosis, and T1 slope angle were identified as the risk factors of cervical sagittal imbalance during the treatment of growing rod surgery. The growing rod surgery in EOS significantly affected the cervical sagittal alignment. Postoperative PJK and more improvement of kyphosis and T1 slope angle would lead to a higher incidence of cervical sagittal imbalance.

关键词： Cervical alignment Early-Onset Scoliosis Growing rod Proximal junctional kyphosis machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Integrating Vision Localization and Deep Reinforcement learning for High-Precision, Low-Cost Peg-in-Hole Assembly 11

Integrating Vision Localization and Deep Reinforcement Learn...

引用

11th IEEE international conference on Cybernetics and Intelligent Systems (CIS) / 11th IEEE international conference on Robotics, Automation and Mechatronics (RAM)

作者： Lin, Ze Wang, Chuang Xie, Longhan Zeng, Miaosheng Wu, Sihan South China Univ Technol Shien Ming Wu Sch Intelligent Engn Guangzhou Peoples R China

ISBN: (纸本)9798350364200;9798350364194

Combining vision and force assembly strategies constitutes a crucial component of industrial automation production. However, there are two challenges. First, the positioning error of existing vision systems often fails to meet the demands of precision assembly, necessitating the design of assembly strategies based on force sensors tailored to the characteristics of the assembly process. Second, the extensive data required to train vision positioning systems represents a significant burden. Therefore, we propose an assembly method based on object location with a relatively low deployment cost and fine-tuning with reinforcement learning. This method reduces the training cost with few training samples through data augmentation and the incorporation of attention modules. Furthermore, by integrating a deep reinforcement learning module, it performs high-precision hole searching and insertion operations learned by itself, mitigating the impact of visual positioning errors. The experimental results indicate that by improving the vision model, the required labeled samples for training can be reduced to 10. Furthermore, the method proposed in this paper achieves a faster average assembly time by 7.8 seconds and reduces the average number of assembly steps by 28 compared to traditional methods.

关键词： Reinforcement learning Attention mechanism data augmentation Peg-in-hole assembly

来源：评论

学校读者我要写书评

暂无评论

Helping the Oracle: Vector Sign Constraints for Model Shrinkage Methodologies 8th

Helping the Oracle: Vector Sign Constraints for Model Shrink...

引用

8th Annual international conference on machine learning, Optimization and data science (LOD)

作者： Boskovic, Ana Gross, Marco Swiss Fed Inst Technol Ramistr 92 CH-8092 Zurich Switzerland European Commiss Joint Res Ctr Via Enrico Fermi 2749 I-21027 Ispra VA Italy Int Monetary Fund 700 19th St NW Washington DC 20431 USA

ISBN: (纸本)9783031255984;9783031255991

Motivated by the need for obtaining econometric models with theory-conform signs of long-run multipliers or other groups of predictor variables for numerous purposes in economics and other scientific disciplines, we develop a vector sign constrained variant of existing model shrinkage methodologies, such as (Adaptive) Lasso and (Adaptive) Elastic Net. A battery of Monte Carlo experiments is used to illustrate that the addition of such constraints "helps the Oracle property" (the ability to identify the true model) for those methods that do not initially carry it, such as Lasso. For methods that possess it already (the adaptive variants), the constraints help increase efficiency in finite data samples. An application of the methods to empirical default rate data and their macro-financial drivers for 16 countries from Europe and the U.S. corroborates the avail of the sign constrained methodology in empirical applications for obtaining more robust economic models.

关键词： machine learning Model selection Oracle property

来源：评论

学校读者我要写书评

暂无评论

Breaking Isometric Ties and Introducing Priors in Gromov-Wasserstein Distances 27

Breaking Isometric Ties and Introducing Priors in Gromov-Was...

引用

27th international conference on Artificial Intelligence and Statistics, AISTATS 2024

作者： Demetci, Pinar Tran, Quang Huy Redko, Ievgen Singh, Ritambhara Eric and Wendy Schmidt Center 1 Broad Institute of MIT and Harvard United States Université Bretagne-Sud IRISA CMAP Ecole Polytechnique IP Paris France Paris Noah’s Ark Lab Huawei Technologies France Department of Computer Science Center for Computational Molecular Biology Brown University United States

Gromov-Wasserstein distance has many applications in machine learning due to its ability to compare measures across metric spaces and its invariance to isometric transformations. However, in certain applications, this invariant property can be too flexible, thus undesirable. Moreover, the Gromov-Wasserstein distance solely considers pairwise sample similarities in input datasets, disregarding the raw feature representations. We propose a new optimal transport formulation, called Augmented Gromov-Wasserstein (AGW), that allows for some control over the level of rigidity to transformations. It also incorporates feature alignments, enabling us to better leverage prior knowledge on the input data for improved performance. We first present theoretical insights into the proposed method. We then demonstrate its usefulness for single-cell multi-omic alignment tasks and heterogeneous domain adaptation in machine learning. Copyright 2024 by the author(s).

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Hypergraph Joint Representation learning for Hypervertices and Hyperedges via Cross Expansion 38

Hypergraph Joint Representation Learning for Hypervertices a...

引用

38th AAAI conference on Artificial Intelligence (AAAI) / 36th conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence

作者： Yan, Yuguang Chen, Yuanlin Wang, Shibo Wu, Hanrui Cai, Ruichu Guangdong Univ Technol Sch Comp Sci Guangzhou Peoples R China Jinan Univ Coll Informat Sci & Technol Guangzhou Peoples R China Guangdong Prov Key Lab Publ Finance & Taxat Big D Guangzhou Peoples R China

ISBN: (纸本)1577358872

Hypergraph captures high-order information in structured data and obtains much attention in machine learning and data mining. Existing approaches mainly learn representations for hypervertices by transforming a hypergraph to a standard graph, or learn representations for hypervertices and hyperedges in separate spaces. In this paper, we propose a hypergraph expansion method to transform a hypergraph to a standard graph while preserving high-order information. Different from previous hypergraph expansion approaches like clique expansion and star expansion, we transform both hypervertices and hyperedges in the hypergraph to vertices in the expanded graph, and construct connections between hypervertices or hyperedges, so that richer relationships can be used in graph learning. Based on the expanded graph, we propose a learning model to embed hypervertices and hyperedges in a joint representation space. Compared with the method of learning separate spaces for hypervertices and hyperedges, our method is able to capture common knowledge involved in hypervertices and hyperedges, and also improve the data efficiency and computational efficiency. To better leverage structure information, we minimize the graph reconstruction loss to preserve the structure information in the model. We perform experiments on both hypervertex classification and hyperedge classification tasks to demonstrate the effectiveness of our proposed method.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Early Detection and Severity Classification of Diabetic Retinopathy Through Image Processing and Deep learning

Early Detection and Severity Classification of Diabetic Reti...

引用

2024 IEEE international conference on Future machine learning and data science, FMLDS 2024

作者： Nishio, Nelson Nishio, Jason Nishio, Alexander Basis Independent Silicon Valley San Jose United States Purdue University Department of Computer Science West Lafayette United States

ISBN: (纸本)9798350391213

Diabetic retinopathy (DR) remains a leading cause of blindness among individuals with diabetes, making early detection crucial to mitigate vision deterioration and prevent vision loss. However, the current manual DR diagnosis by ophthalmologists in clinics is labor-intensive, particularly due to challenges in identifying subtle retinal lesions. Hence, there is a need to develop an automated detection framework. This study leveraged the two pre-trained ResNet50 and VGG19 models for detecting DR in retinal fundus images from the APTOS 2019 dataset. The advanced image preprocessing techniques such as the Graham method, Contrast Limited Adaptive Histogram Equalization (CLAHE), and Enhanced Super-Resolution Generative Adversarial Networks (ESRGAN) were explored. The results demonstrate that combining these preprocessing methods with optimized parameters significantly enhances performance. For binary classification, the pretrained VGG19 model, combined with the proposed CLAHE + ESRGAN preprocessing method, achieved an accuracy of 98.91%. For multi-class classification, the pre-trained ResNet50 model, combined with the proposed Graham20 + CLAHE and ESRGAN + CLAHE preprocessing methods, attained accuracies of 86.07% and 84.15%, respectively. This study is the first systematic study of deep learning architectures with various combinations of DR image preprocessing methods, offering a significant step forward in automated DR detection and severity classification. © 2024 IEEE.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

DPFL-AES: Differential Privacy Federated learning Based on Adam Early Stopping 29th

DPFL-AES: Differential Privacy Federated Learning Based on A...

引用

29th international conference on Computational and Experimental Engineering and sciences, ICCES 2023

作者： Qian, Jiaqing Chen, Yanan Jiao, Sanxiu Business School of Jiangxi University of Science and Technology 1180 Shuanggang East Street Qingshanhu District Nanchang330013 China College of Automation and Information Engineering Sichuan University of Science and Engineering Yibin644000 China

ISBN: (纸本)9783031425141

Federated learning (FL) is a distributed machine learning framework that protects data privacy on the premise that the data does not leave the local area, and can effectively solve the data islands and data privacy security issues faced by artificial intelligence. However, attackers can launch attribute inference attacks or membership inference attacks on customers by analyzing the parameters in shared model training. To solve this problem, we combine the concepts of differential privacy (DP) and federated learning, and propose a differentially private federated learning scheme based on the Adam Early Stopping algorithm (DPFL-AES). The algorithm inherits the advantages of differential privacy and federated learning, and hides the basic parameters uploaded by the client during the training process. Furthermore, as the model converges, the noise should be reduced accordingly later in the federated learning training process. We added an early stopping (ES) mechanism to the algorithm. In the later stage of federated learning training, as the model converges, the number of communication rounds and the addition of noise are reduced, thereby improving the performance of the model. The algorithm balances data security and availability under a shared model. Finally, we verified the feasibility and practicability of the algorithm through theoretical analysis and experimental simulation on the real MNIST dataset. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

Diabetes prediction models based on intrinsic explainable machine learning

Diabetes prediction models based on intrinsic explainable ma...

引用

2024 international conference on Algorithms, High Performance Computing, and Artificial Intelligence, AHPCAI 2024

作者： Huang, Xiangtong Zhang, Jing Chen, Qi He, Jia School of Health Sciences and Engineering University of Shanghai for Science and Technology Shanghai China Department of Health Statistics Naval Medical University Shanghai China

ISBN: (纸本)9781510685840

With the sharp increase in the global prevalence of diabetes, early diagnosis and prediction have become key to improving patient management and reducing the disease burden. This study investigates the use of explainable machine learning models for diabetes prediction, specifically employing the Pima Indian Diabetes dataset to develop a model that integrates explainability. Several advanced machine learning models—including the Bayesian classifier, Decision Tree, XGBoost, LightGBM, Random Forest, K-Nearest Neighbors (KNN), and CatBoost—were assessed using the 2019 Diabetics dataset. Notably, the SHAP framework was applied to the Pima Indian dataset to enhance the transparency and interpretability of the models. Through a comprehensive evaluation of different models, we found that the CatBoost model performed excellently across multiple performance metrics, particularly achieving an AUC value of 0.867, indicating superior sensitivity and specificity compared to other models. Additionally, the application of the SHAP framework revealed that glucose levels and BMI are the main factors influencing diabetes prediction, providing valuable insights for medical professionals to better understand and explain the prediction results. This study confirms the effectiveness of explainable machine learning methods in improving the accuracy of early diabetes prediction and model transparency. Our results offer new perspectives and approaches for applying machine learning technologies to diabetes and other chronic diseases in clinical practice, promoting the development of personalized and precision medicine. © 2024 SPIE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Detection Based on Chest X-Rays and CT Scans Using Inception v3 Deep learning Algorithm

COVID-19 Detection Based on Chest X-Rays and CT Scans Using ...

引用

2023 international conference on Engineering, science and Advanced Technology, ICESAT 2023

作者： Raheem, Ali K. Abdul Zuhair, Mays Ameri, Hajer.A. Al University of Warith Al-Anbiyaa Karbala Iraq Al-Zahraa University for Women Karbala Iraq

ISBN: (纸本)9798350344400

In December 2019, a number of acute atypical respiratory ailment cases were recorded in Wuhan, China. This swiftly swept throughout China from Wuhan. It wasn't long before a novel coronavirus was identified as the culprit. Among the types of machine learning is deep learning, Deep learning algorithms are designed to automatically learn from large amounts of data, by iteratively improving their ability to identify and extract meaningful features from input data. The majority of COVID-19 symptoms include indicators of respiratory infections and lung abnormalities that radiologists may identify. As a result, Deep learning algorithms may be used to diagnose illness from pictures of the CT scan and the chest X-ray. To assist radiologists, automated programs might be designed. This article is an effort to diagnose the sickness using the Deep learning algorithm Inception V3. The method was tested on two types of databases: X-rays of the chest and CT scans. The results demonstrated that the procedure was successful and that the results were improved when applied to the Chest X-ray datasets. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

SwinMixer Detector: A Two-Level Traffic Flow Detection System Based on Swin Transformer and MLP-Mixer 24th

SwinMixer Detector: A Two-Level Traffic Flow Detection Syste...

引用

24th international conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Lu, Lu Fang, Menghao Li, Xia Li, Minghui Lei, Tianwei Kong, Zixiao School of Cyber Science and Engineering University of International Relations Beijing100091 China Institute of Disaster and Emergency Medicine Tianjin University Tianjin300072 China Marine Engineering of College Dalian Maritime University Dalian116026 China School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9789819615414

This paper explores the problem of boundary data classification ambiguity that arises when machine learning techniques are applied in the field of intrusion detection. The features and attributes of the boundary data place them in the boundaries or boundaries between different categories in the classification decision, and these data points may be close to the decision boundaries of different categories in the feature space, resulting in relative uncertainty or some ambiguity in their classification. To address this problem, this study innovatively proposes a secondary detection system called the SwinMixer Detector, which utilises the Swin Transformer and MLP-Mixer architecture. The system consists of a primary triage detection platform utilizing Swin Transformer classifier and a secondary detection platform utilizing MLP-Mixer, which can effectively solve the problem of fuzzy classification of boundary data. By validating on the SR-BH2020 dataset and the CIC-DDOS2019 dataset, the method in this paper achieves a precision of 96.40% and 95.81%, respectively, which provides a new research idea and solution for the field of intrusion detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Mixers (machinery)

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：