检索结果-内蒙古大学图书馆

Integrative Predictive Models of Computed Tomography Texture Parameters and Hematological Parameters for Lymph Node Metastasis in Lung Adenocarcinomas

引用

JOURNAL OF COMPUTER ASSISTED TOMOGRAPHY 2022年第2期46卷 315-324页

作者： Chen, Wenping Xu, Mengying Sun, Yiwen Ji, Changfeng Chen, Ling Liu, Song Zhou, Kefeng Zhou, Zhengyang Nanjing Med Univ Nanjing DrumTower Hosp Dept Radiol Clin Coll Nanjing Peoples R China Nanjing Univ Dept Radiol Affiliated Hosp Med Sch Nanjing Peoples R China Nanjing Med Univ Nucl Med Clin Coll Nanjing Drum Tower Hosp Nanjing Peoples R China Nanjing Med Univ Pathol Clin Coll Nanjing Drum Tower Hosp Nanjing Peoples R China

Objectives The aims of the study were to integrate characteristics of computed tomography (CT), texture, and hematological parameters and to establish predictive models for lymph node (LN) metastasis in lung adenocarcinoma. Methods A total of 207 lung adenocarcinoma cases with confirmed postoperative pathology and preoperative CT scans between February 2017 and April 2019 were included in this retrospective study. All patients were divided into training and 2 validation cohorts chronologically in the ratio of 3:1:1. The chi(2) test or Fisher exact test were used for categorical variables. The Shapiro-Wilk test and Mann-Whitney U test were used for continuous variables. Logistic regression and machine learning algorithm models based on CT characteristics, texture, and hematological parameters were used to predict LN metastasis. The performance of the multivariate models was evaluated using a receiver operating characteristic curve;prediction performance was evaluated in the validation cohorts. Decision curve analysis confirmed its clinical utility. Results Logistic regression analysis demonstrated that pleural thickening (P = 0.013), percentile 25th (P = 0.033), entropy gray-level co-occurrence matrix 10 (P = 0.019), red blood cell distribution width (P = 0.012), and lymphocyte-to-monocyte ratio (P = 0.049) were independent risk factors associated with LN metastasis. The area under the curve of the predictive model established using the previously mentioned 5 independent risk factors was 0.929 in the receiver operating characteristic analysis. The highest area under the curve was obtained in the training cohort (0.777 using Naive Bayes algorithm). Conclusions Integrative predictive models of CT characteristics, texture, and hematological parameters could predict LN metastasis in lung adenocarcinomas. These findings may provide a reference for clinical decision making.

关键词： lung adenocarcinoma computed tomography texture analysis machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Significant full reference image segmentation evaluation: a survey in remote sensing field

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第13期81卷 17959-17987页

作者： Pugazhenthi, A. Sebastian, Sruthy Rohith, G. Kumar, Lakshmi Sutha Natl Inst Technol Puducherry Dept Elect & Commun Engn Pondicherry India

Image segmentation is a crucial step in remote sensing application, as it breaks down a larger image into smaller chunks, which contains useful information. Although there are several image segmentation algorithms available, evaluation of the algorithms is challenging. Furthermore, the evaluation of image segmentation can elucidate the best image segmentation algorithm for a single image or a group of image or a whole class of image. This paper explores and evaluates the benefits and the drawbacks of various qualitative and quantitative image segmentation evaluation metrics used in remote sensing applications. For all the metrics, a quantitative set of values for good and bad segmentation is provided. In addition, some image segmentation algorithms such as Multi Otsu Threshold, K Means clustering, Fuzzy C Means clustering, Improved K Means clustering (IFCM), Improved Fuzzy C Means clustering, Naive Bayes classifier, K Nearest Neighbor, Decision Tree (DT) and Random Forest classifier are used in the experimental comparison of metrics. The qualitative and quantitative satellite image segmentation evaluation using the mentioned algorithms is measured. The results are analyzed to strengthen the impact of different metrics on the segmentation algorithms. In both qualitative and quantitative analysis, the IFCM outperformed the other unsupervised machine learning algorithms and the DT outperformed the other supervised machine learning algorithms. The effectiveness of the provided metrics in the remote sensing field is validated.

关键词： Image segmentation INSAT-3D Evaluation metrics Clustering algorithm Qualitative evolution Quantitative evolution machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction model of crash severity in imbalanced dataset using data leveling methods and metaheuristic optimization algorithms

引用

INTERNATIONAL JOURNAL OF CRASHWORTHINESS 2022年第6期27卷 1869-1882页

作者： Danesh, Akbar Ehsani, Mehrdad Nejad, Fereidoon Moghadas Zakeri, Hamzeh Amirkabir Univ Technol Dept Civil & Environm Engn Tehran Iran

Road accident is one of the important problems in the world which caused large number of deaths. In a road crash dataset, the fatal crash samples, often constitute very small proportion in comparison with non-fatal crash samples. Accurate prediction of fatal crashes, as a minority class, is one of the important challenges in such imbalanced sample distribution in the most of machine learning algorithms. This study introduced data leveling methods based on two metaheuristic optimization algorithms (biogeography-based optimization and invasive weed optimization) to obtain more balanced data. Then, three machine learning algorithms including decision tree, support vector machine (SVM) and k-nearest neighbor were applied for obtained balanced dataset. Performances of the prepared models were evaluated by improving the accuracy of the models in detecting the fatal crashes. It is found that data leveling methods of imbalanced dataset with metaheuristic algorithms improve the performance of crash prediction models in detecting fatal crashes especially in SVM algorithm up to 100% compared to previous studies. Also, results of sensitivity analysis on the developed model represented that head-on crashes, curved roads, and large type vehicles can increase the probability of fatal crashes up to 27.2%, 29%, and 36.8% at high posted speed limit, respectively. Also, two-vehicle crashes are much more likely to be involved in fatal crashes than single-vehicle crashes.

关键词： Crash injury severity imbalanced dataset machine learning algorithm prediction model sensitivity analysis data leveling methods

来源：评论

学校读者我要写书评

暂无评论

Combined Random Forest and NSGA-II for Optimal Design of Permanent Magnet Arc Motor

引用

IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN POWER ELECTRONICS 2022年第2期10卷 1800-1812页

作者： Pan, Zhenbao Fang, Shuhua Southeast Univ Sch Elect Engn Nanjing 210096 Peoples R China

This article presents an optimization design method for a double-stator hybrid excited permanent magnet arc motor (DS-HE-PMAM). The proposed optimization method combining the machine learning algorithm random forest (RF) and the nondominated sorting genetic algorithm-II (NSGA-II) contributes to achieving high average torque, low torque ripple, high back electromotive force (EMF), and low total harmonic distortion of the back EMF. First, the motor structure and working principle of the DS-HE-PMAM are illustrated. The selection of parameters to be optimized is determined based on an analytical model. Then, a variable importance measure-based new sensitivity analysis method is implemented to evaluate the influence of each structural parameter on the selected design objectives. The finite-element analysis (FEA)-based DS-HE-PMAM model is developed to obtain the sample data regarding input structural parameters and output design objectives. Based on the sample data, a powerful machine learning algorithm called RF is employed to fit the function relationship between output design objectives and input structural parameters. After that, an intelligent search algorithm named NSGA-II is introduced to search for the optimal solution to the structural parameters combination and obtain the optimal motor performances. Finally, the electromagnetic characteristics of the initial and optimized models of the DS-HE-PMAM are compared and analyzed, and both FEA and prototype experiments verify the feasibility and superiority of the proposed optimization method.

关键词： Stator windings Structural engineering Analytical models Radio frequency Rotors Data models Sensitivity analysis machine learning algorithm nondominated sorting genetic algorithm (GA) optimization design permanent magnet arc motor (PMAM) random forest (RF)

来源：评论

学校读者我要写书评

暂无评论

Feature Selection Strategies for Accurate Crop Yield Prediction in Heterogeneous Datasets 3rd

Feature Selection Strategies for Accurate Crop Yield Predict...

引用

3rd International Conference on Emerging Electronics and Automation, E2A 2023

作者： Ramani, R. Maheswari, M. Uma Kayathri, S. P.S.R Engineering College Sivakasi India

ISBN: (纸本)9789819768011

A key element of life for humans is agriculture. Not only is it essential, but it contributes to the development of a nation. For a substantial percentage of Indians, agriculture is a significant source of income. Agriculture and Rural Development provide a substantial amount of Indians’ principal revenue source income. In recent years, ecological damage has become an important concern for people all around the world. It has been found that ecological change has a consequence on farming quality and quantity. Crop yield forecasts would help producers make informed marketing and storage decisions well before harvest. Many landowners anticipate using old-fashioned agricultural methods, which produce little profit in today's competitive marketplace. Agricultural forecasting of yields is critical for quick decision-making both on the national and regional levels. An accurate crop production forecasting model could help in deciding which to plant and how much yield can be produced. The implementation of machine learning (ML) is an important aspect to consider when trying to find a useful and efficient solution to the crop yield problem. Crop yield can be predicted by analyzing different datasets given and various ML algorithms like Linear Regression, Random Forest (RF) Regression, Support Vector Regression (SVR), Decision Tree (DT) Regression and Extreme Gradient Boosting (XGBoost) Regression. The feature selection methods include ANOVA, the correlation-based threshold value method, the Mutual information method, and the Pearson correlation methods used for three different datasets. The accuracy of the DT algorithm in the agricultural yield prediction dataset has a highest accuracy of 97.25% after different feature selection techniques are used. With a 99.2% accuracy rate in the dataset used to forecast wild blueberry yield, the Linear Regression approach is the most accurate. The highest precision of the RF algorithm is 93.53%, and that of the XGBoost technique is 94.28%

关键词： Decision making system Feature selection Inter crop machine learning algorithm Prediction Techniques

来源：评论

学校读者我要写书评

暂无评论

Power optimization of 1:2 and 1:4 photonic crystal based optical power splitters/combiners using machine learning algorithms

引用

Results in Optics 2025年 21卷

作者： Ghosh, Kalyan Kumar Mondal, Haraprasad Das, Himanshu Ranjan Soroosh, Mohammad Majumder, Sudipta Saikia, Bhargabjyoti Dibrugarh University Institute of Engineering and Technology Dibrugarh University Assam India Department of Electronics and Communication Engineering School of Engineering Central University of Karnataka Karnataka Kalaburagi 585367 India Department of Electrical Engineering Shahid Chamran University of Ahvaz Ahvaz Iraq

Optical power splitters play a vital role in signal distribution, network expansion, and both balanced and unbalanced power splitting in cost-efficient fiber optic systems. Similarly, optical power combiners are essential for signal aggregation, upstream transmission, and balanced network design. In this article, we propose the design of two power splitters—3 dB and 6 dB Y-shaped configurations—that also function as power combiners using two-dimensional photonic crystal waveguides. The performance of these devices has been analyzed using the finite difference time domain (FDTD) algorithm, and their operational parameters have been optimized through the K-means clustering and Particle Swarm Optimization algorithms. As a result of this optimization, the devices achieve precise 3 dB and 6 dB power splitting across all output ports with an efficiency of 99 %. Their fast response time (0.4 and 0.5 picoseconds for 3 dB and 6 dB respectively), high power delivery efficiency, precise power splitting/combining capabilities, and machine Learming (ML) – driven optimization make these splitters/combiners highly suitable for advanced fiber optic networks. © 2025 The Author(s)

关键词： Fiber optic networks Finite difference time domain machine learning algorithm Optical waveguides Power splitter

来源：评论

学校读者我要写书评

暂无评论

Time and Accuracy based impact analysis of Poisoning Attack on Support Vector machine algorithm 2

Time and Accuracy based impact analysis of Poisoning Attack ...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Ponsuresh, M. Rajkumar, T.Dhiliphan Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Virudhunagar Krishnankoil India

ISBN: (纸本)9798350306415

The security concerns in the digital world are rapidly evolving. Artificial intelligence and machine learning (AI&ML) techniques are not an exception from this concern. None of us wants to stay away from the comforts by avoiding the luxury provided by AI&ML technology-based products. As these are being widely adopted, the risk involved with the weak security posture is a big threat to our community. This paper provides insight to the attacks and their categorization. The work investigates how volatile the ML algorithms are against the cyber-attack by examining the Support Vector machine (SVM) algorithm against the poisoning attack. The significance is given to the accuracy and time of execution factors among many. Exploring the volatility of ML algorithms against the poisoning attack is a step towards understanding the weakness of ML algorithms, which further allows to explore the various ways to develop the defense mechanisms that prevent such attacks. © 2024 IEEE.

关键词： machine learning algorithm Poisoning Attack Support Vector machine

来源：评论

学校读者我要写书评

暂无评论

Collusion Strategy Investigation and Detection for Generation Units in Electricity Market Using Supervised learning Paradigm

引用

IEEE SYSTEMS JOURNAL 2021年第1期15卷 146-157页

作者： Razmi, Peyman Buygi, Majid Oloomi Esmalifalak, Mohammad Ferdowsi Univ Mashhad Fac Engn Mashhad *** Razavi Khorasan Iran McMaster Univ Hamilton ON L8S 4L8 Canada

In an oligopoly market, producers compete together to seize the electricity market share. Since they cannot obtain their desired profits through fair competition, they may collude to set their bid prices illegally higher than the oligopoly level. Manipulation and increasing market price decrease social welfare and then market efficiency. This article intends to provide independent system operators (ISOs) with a tool to analyze day-ahead market data so as to identify generator units who intend to exercise collusion and raise the market prices. Toward this goal, all possible collusion and competition scenarios are simulated and then the generated data are used to train a supervised learning algorithm. By applying the proposed approach to the IEEE 57 and 30 bus test systems, the efficiency of the proposed approach was assessed. Furthermore, it is demonstrated how colluding generators choose between maximizing their colluded profit and reducing the risk of being detected by ISO. The results show machine learning is capable of identifying colluding companies with accuracy of 95%. Also, it was rightly obvious that the closer the bidding price of companies is to competitive level, the more downward the efficiency of the machine is.

关键词： Electricity supply industry machine learning algorithms Generators machine learning Companies Supervised learning Oligopoly Collusion equilibrium point machine learning algorithm nonoptimal strategy

来源：评论

学校读者我要写书评

暂无评论

Early Detection and Analysis of Anxiety in Adolescents

引用

Mathematical Models and Computer Simulations 2023年第5期15卷 956-967页

作者： Jyothirmayi, M. Sidharth, M. Vijay, B. Khandelwal, Ritik Raju, K. Dinesh, P.A. Department of Electronics and Instrumentation Engineering Ramaiah Institute of Technology Karnataka Bangalore India Department of Mathematics Ramaiah Institute of Technology Karnataka Bangalore India

Abstract: Mental health has become one of the most important topics in today’s world and has been included in WHO’s World Sustainable Development goals. Significant breakthrough made in diagnosis and treatment has reduced the mortality caused by various diseases, however depression and suicide caused by mental health disorders has become the leading cause of death in the world. Though mental health treatment is easily available and inexpensive, social stigma prevents people from coming forward for detection and treatment. To combat this growing epidemic, this paper describes an effective noninvasive two-step method which helps in early detection of anxiety in children below age of 19. This involves cognitive behavioral analysis from the data taken from both the child and parent. The score derived from the above is used to decide the requirement for further analysis. EEG is used to check the brain state. A machine learning classifier algorithm is used to classify the EEG data and determine anxiety. This helps in confirming anxiety in children who need psychiatrist support for further treatment. © 2023, Pleiades Publishing, Ltd.

关键词： anxiety cognitive behavioral therapy EEG machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A self-assessment framework for initial screening of human monkeypox 5

A self-assessment framework for initial screening of human m...

引用

5th International Conference on Control and Robotics (ICCR)

作者： Gupta, Kapil Bajaj, Varun PDPM IIITDM Dept ECE Jabalpur 482005 MP India

ISBN: (纸本)9798350307627

Human monkeypox (MPX) is the deadliest infection that transmits from person to person by direct interaction with animals, bodily fluids, coughing or sneezing, and infected things such as bedding. Due to the symptoms of MPX infections being similar to measles and chickenpox, manual screening of MPX virus at an early stage is time-consuming, prone to community spread, and subject to human error. Computer-assisted detection of human MPX using skin lesion images may improve clinical efficiency and decrease the workload of health staff. The objective of this work is to develop a reliable system for self-diagnostic of MPX infection employing a cloud-based diagnosis system. In this paper, a publicly available MPX skin lesion database and a convolutional neural network (CNN) are used to detect MPX-infected subjects automatically. Two pre-trained CNNs, and a newly-developed less-complex CNN, are used to diagnose MPX infection. Benchmarked models are trained using a transfer-learning strategy. A 10-fold holdout cross-validation scheme with a data augmentation strategy is employed to design a more robust network. Transfer learned DarkNet19 has attained a maximum classification accuracy of 96.74%. The efficiency of the presented work is demonstrated by the simulation results using the publicly accessible dataset. The experimental results demonstrate that CNN shows potential in the screening of MPX-infected subjects from skin lesion images. The presented framework can be an interface unit for cloud-based disease diagnostic systems.

关键词： Monkeypox infection skin lesion images convolutional neural network machine learning algorithm biomedical image classification

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：