检索结果-内蒙古大学图书馆

hyper-parameter optimization-based multi-source fusion for remote sensing inversion of non-photosensitive water quality parameters

引用

INTERNATIONAL JOURNAL OF REMOTE SENSING 2024年第18期45卷 6838-6859页

作者： Yuan, Yuhao Lin, Zhiping Jiang, Xinhao Fan, Zhongmou Fujian Agr & Forestry Univ Sch Transportat & Civil Engn Comprehens Bldg 50763 Xiyuangong Rd Fuzhou 350100 Fujian Peoples R China

The constraints of spatiotemporal heterogeneity and spatial resolution constitute two crucial challenges in the establishment of remote sensing inversion models. Spatiotemporal heterogeneity gives rise to an inadequate generalization capacity of remote sensing models, demanding extensive manual parameter adjustment for each model construction. This not only escalates the task's work intensity but also leads to unstable performance. The limited spatial resolution of remote sensing images leads to suboptimal inversion accuracy for sampling points influenced by mixed pixel effects. To tackle these problems, we take the case of non-photosensitive water quality parameter inversion in the narrow rivers of Longnan area. By integrating advanced hyper-parameter optimization (HPO) techniques, such as Optuna from machine learning, an inversion model was developed, incorporating the bands of Sentinel-2 and Sentinel-3 as model features. Among these features, bands with lower spatial resolution are employed to furnish surrounding information, thereby enhancing the inversion accuracy. The research outcomes demonstrate that: 1) The model constructed based on the HPO method, Optuna, attained favourable inversion results, with R2 values of 0.68, 0.77, 0.35, and 0.60 for Total Nitrogen (TN), Total Phosphorus (TP), Ammonia Nitrogen (NH3-N), and Chemical Oxygen Demand (COD), respectively. 2) The fusion of Sentinel-2 and Sentinel-3 data enhanced the inversion accuracy compared to using them separately, highlighting the considerable significance of multi-source data fusion methods in improving inversion accuracy. This research fills a void in the remote sensing inversion domain and lays the groundwork for future endeavours.

关键词： Remote sensing inverse problems hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

hyper-parameter optimization of deep learning architectures using artificial bee colony (ABC) algorithm for high performance real-time automatic colorectal cancer (CRC) polyp detection

引用

APPLIED INTELLIGENCE 2023年第12期53卷 15603-15620页

作者： Karaman, Ahmet Karaboga, Dervis Pacal, Ishak Akay, Bahriye Basturk, Alper Nalbantoglu, Ufuk Coskun, Seymanur Sahin, Omur Acibadem Hosp Dept Gastroenterol Kayseri Turkey Erciyes Univ Engn Fac Dept Comp Engn Kayseri Turkey Erciyes Univ Artificial Intelligence & Big Data Applicat & Res Kayseri Turkey Igdir Univ Engn Fac Dept Comp Engn Igdir Turkey

Colorectal cancer (CRC) is one of the most common and malignant types of cancer worldwide. Colonoscopy, considered the gold standard for CRC screening, allows immediate removal of polyps, which are precursors to CRC. Many computer-aided diagnosis systems (CADs) have been proposed for automatic polyp detection. Most of these systems are based on traditional machine learning algorithms and their generalization ability, sensitivity and specificity are limited. On the other hand, with the widespread use of deep learning algorithms in medical image analysis and the successful results in the analysis of colonoscopy images, especially in the early and accurate detection of polyps, these problems are eliminated in recent years. In short, deep learning algorithms and applications have gained a critical role in CAD systems for real-time autonomous polyp detection. Here, we make significant improvements to object detection algorithms to improve the performance of CAD-based real-time polyp detection systems. We integrate the artificial bee colony algorithm (ABC) into the YOLO algorithm to optimize the hyper-parameters of YOLO-based algorithms. The proposed method can be easily integrated into all YOLO algorithms such as YOLOv3, YOLOv4, Scaled-YOLOv4, YOLOv5, YOLOR and YOLOv7. The proposed method improves the performance of the Scaled-YOLOv4 algorithm with an average of more than 3% increase in mAP and a more than 2% improvement in F1 value. In addition, the most comprehensive study is conducted by evaluating the performance of all existing models in the Scaled-YOLOv4 algorithm (YOLOv4s, YOLOv4m, YOLOV4-CSP, YOLOv4-P5, YOLOV4-P6 and YOLOv4-P7) on the novel SUN and PICCOLO polyp datasets. The proposed method is the first study for the optimization of YOLO-based algorithms in the literature and makes a significant contribution to the detection accuracy.

关键词： Colorectal cancer Deep learning hyper-parameter optimization Artificial bee colony Real-time polyp detection YOLOv4

来源：评论

学校读者我要写书评

暂无评论

hyper-parameter optimization of multiple machine learning algorithms for molecular property prediction using hyperopt library

引用

Chinese Journal of Chemical Engineering 2022年第12期52卷 115-125页

作者： Jun Zhang Qin Wang Weifeng Shen School of Chemistry and Chemical Engineering Chongqing UniversityChongqing 401331China School of Chemistry and Chemical Engineering Chongqing University of Science&TechnologyChongqing 401331China Chongqing Key Laboratory of Theoretical and Computational Chemistry Chongqing 400044China

Due to outstanding performance in cheminformatics,machine learning algorithms have been increasingly used to mine molecular properties and biomedical big *** performance of machine learning models is known to critically depend on the selection of the hyper-parameter ***,many studies either explored the optimal hyper-parameters per the grid searching method or employed arbitrarily selected hyper-parameters,which can easily lead to achieving a suboptimal hyper-parameter *** this study,hyperopt library embedding with the Bayesian optimization is employed to find optimal hyper-parameters for different machine learning *** drug discovery datasets,including solubility,probe-likeness,h ERG,Chagas disease,tuberculosis,and malaria,are used to compare different machine learning algorithms with ECFP6 *** contribution aims to evaluate whether the Bernoulli Na?ve Bayes,logistic linear regression,Ada Boost decision tree,random forest,support vector machine,and deep neural networks algorithms with optimized hyper-parameters can offer any improvement in testing as compared with the referenced models assessed by an array of metrics including AUC,F1-score,Cohen’s kappa,Matthews correlation coefficient,recall,precision,and *** on the rank normalized score approach,the hyperopt models achieve better or comparable performance on 33 out 36 models for different drug discovery datasets,showing significant improvement achieved by employing the hyperopt *** open-source code of all the 6 machine learning frameworks employed in the hyperopt python package is provided to make this approach accessible to more scientists,who are not familiar with writing code.

关键词： Machine learning Prediction Optimal design hyper-parameter optimization hyperopt library

来源：评论

学校读者我要写书评

暂无评论

hyper-parameter optimization of Stacked Asymmetric Auto-Encoders for Automatic Personality Traits Perception

引用

SENSORS 2022年第16期22卷 6206页

作者： Zaferani, Effat Jalaeian Teshnehlab, Mohammad Khodadadian, Amirreza Heitzinger, Clemens Vali, Mansour Noii, Nima Wick, Thomas KN Toosi Univ Technol Elect & Comp Engn Fac Tehran *** Iran Leibniz Univ Hannover Inst Appl Math D-30167 Hannover Germany TU Wien Inst Anal & Sci Comp A-1040 Vienna Austria TU Wien Ctr Artificial Intelligence & Machine Learning CA A-1040 Vienna Austria Leibniz Univ Hannover Inst Continuum Mech D-30823 Hannover Germany

In this work, a method for automatic hyper-parameter tuning of the stacked asymmetric auto-encoder is proposed. In previous work, the deep learning ability to extract personality perception from speech was shown, but hyper-parameter tuning was attained by trial-and-error, which is time-consuming and requires machine learning knowledge. Therefore, obtaining hyper-parameter values is challenging and places limits on deep learning usage. To address this challenge, researchers have applied optimization methods. Although there were successes, the search space is very large due to the large number of deep learning hyper-parameters, which increases the probability of getting stuck in local optima. Researchers have also focused on improving global optimization methods. In this regard, we suggest a novel global optimization method based on the cultural algorithm, multi-island and the concept of parallelism to search this large space smartly. At first, we evaluated our method on three well-known optimization benchmarks and compared the results with recently published papers. Results indicate that the convergence of the proposed method speeds up due to the ability to escape from local optima, and the precision of the results improves dramatically. Afterward, we applied our method to optimize five hyper-parameters of an asymmetric auto-encoder for automatic personality perception. Since inappropriate hyper-parameters lead the network to over-fitting and under-fitting, we used a novel cost function to prevent over-fitting and under-fitting. As observed, the unweighted average recall (accuracy) was improved by 6.52% (9.54%) compared to our previous work and had remarkable outcomes compared to other published personality perception works.

关键词： big five personality traits cultural algorithm deep learning hyper-parameter optimization personality perception

来源：评论

学校读者我要写书评

暂无评论

Rethinking density ratio estimation based hyper-parameter optimization

引用

NEURAL NETWORKS 2025年 182卷 106917页

作者： Fan, Zi-En Lian, Feng Li, Xin-Ran Xi An Jiao Tong Univ Sch Automat Sci & Technol 28 West Xianning Rd Xian 710049 Shaanxi Peoples R China

hyper-parameter optimization (HPO) aims to improve the performance of machine learning algorithms by identifying appropriate hyper-parameters. By converting the computation of expected improvement into density-ratio estimation problems, existing works use binary classifiers to estimate these ratio and determine the next point by maximizing the class posterior probabilities. However, these methods tend to treat different points equally and ignore some important regions, because binary classifiers are unable to capture more information about search spaces and highlight important regions. In this work, we propose a hyper-parameter optimization method by estimating ratios and selecting the next point using multi-class classifiers. First, we divide all samples into multiple classes and train multi-class classifiers. The decision boundaries of the trained classifiers allow fora finer partitioning of search spaces, offering richer insights into the distribution of hyper- parameters within search spaces. We then define an acquisition function as a weighted sum of multi-class classifiers' outputs, with these weights determined by samples in each class. By assigning different weights to each class posterior probability in our acquisition function, points within search spaces are no longer treated equally. Experimental results on three representative tasks demonstrate that our method achieves a significant improvement in immediate regrets and convergence speed.

关键词： hyper-parameter optimization Density ratio estimation Neural architecture search

来源：评论

学校读者我要写书评

暂无评论

A new hyper-parameter optimization method for machine learning in fault classification

引用

APPLIED INTELLIGENCE 2023年第11期53卷 14182-14200页

作者： Ye, Xingchen Gao, Liang Li, Xinyu Wen, Long Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol 1037 Luoyu Rd Wuhan 430074 Peoples R China China Univ Geosci Sch Mech Engn & Elect Informat 388 Lumo Rd Wuhan 430074 Peoples R China

Accurate bearing fault classification is essential for the safe and stable operation of rotating machinery. The success of Machine Learning (ML) in fault classification is mainly dependent on efficient features and the optimal pre-defined hyper-parameters. Various hyper-parameter optimization (HPO) methods have been proposed to tune the ML algorithms' hyper-parameters in low dimensions but ignore the hyper-parameters of Feature Engineering (FE). The hyper-parameter dimension is high because both FE and the ML algorithm contain many hyper-parameters. This paper proposed a new HPO method for high dimensions based on dimension reduction and partial dependencies. Firstly, the whole hyper-parameter space is separated into two subspaces of FE and the ML algorithm to reduce time consumption. Secondly, the sensitive intervals of hyperparameters can be recognized by partial dependencies due to the nonlinearity of the relationship between the hyperparameters. Then HPO is conducted in intervals to acquire more satisfactory accuracy. The proposed method is verified on three OpenML datasets and the CWRU bearing dataset. The results show that it can automatically construct efficient domain features and outperforms traditional HPO methods and famous ML algorithms. The proposed method is also very time efficient.

关键词： hyper-parameter optimization Fault classification Dimension reduction Partial dependencies

来源：评论

学校读者我要写书评

暂无评论

hyper-parameter optimization OF DEEP LEARNING MODELS FOR COMPRESSOR AIR LEAK PREDICTION IN A GAS TURBINE

HYPER-PARAMETER OPTIMIZATION OF DEEP LEARNING MODELS FOR COM...

引用

ASME Power Conference (Power)

作者： Nogueras-Rivera, Diego I. Mojica-Vazquez, Lemuel Bonilla-Alvarado, Harry Bryden, Kenneth M. Tucker, David Traverso-Aviles, Luis M. Aponte-Roa, Diego A. Univ Ana G Mendez Elect & Comp Engn Dept San Juan PR 00926 USA Ames Lab Decis Sci Program Ames IA USA US DOE Natl Energy Technol Lab Washington DC USA Univ Ana G Mendez Mech Engn Dept San Juan PR USA

ISBN: (纸本)9780791885826

Gas turbine systems are widely used in the power industry because they provide continuous and reliable power to the electrical grid. One of the main concerns for implementing gas turbine systems is the maintenance costs. Therefore, predictive maintenance methods driven by Deep Learning (DL) models present an opportunity to extract important information and knowledge from the process data to minimize maintenance costs and reduce equipment failure rates. A previous study aimed to benchmark various state-of-the-art DL models for predicting compressor air leak with multivariate time-series data from a modified recuperated gas turbine system. However, the brute-force approach used to select the hyper-parameters of the DL models could be improved. This paper aims to address the hyper-parameter optimization process of the best performers for predicting the next future time-step: GRU-LSTM, Sequential CNNLSTM, and BI-LSTM. In addition, a BI-GRU model was implemented and a common grid search algorithm was combined with proposed algorithms for automating the selection of hyper-parameter values to build the DL models. The datasets were provided from experiments conducted at the U.S. Department of Energy's National Energy Technology Laboratory (NETL) Hybrid Performance (hyper) Facility. Results suggest better performance can be obtained from the already good performing benchmarked models;however, reproducing the best results for some models may take more training cycles. The BI-GRU model exhibited the most reproducible results across all tests.

关键词： Deep Learning Failure Prediction Gas Turbines hyper-parameter optimization Time Series

来源：评论

学校读者我要写书评

暂无评论

A lightweight intrusion detection system for internet of vehicles based on transfer learning and MobileNetV2 with hyper-parameter optimization

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第8期83卷 22347-22369页

作者： Wang, Yingqing Qin, Guihe Zou, Mi Liang, Yanhua Wang, Guofeng Wang, Kunpeng Feng, Yao Zhang, Zizhan Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Changchun 130012 Peoples R China Jilin Univ Publ Comp Educ & Res Ctr Changchun 130012 Peoples R China

With the rapid development of Internet of Vehicles (IoV) technology, Intelligent Connected Vehicles (ICVs) have richer vehicle information functions and applications. In recent years, as ICVs have become more complex and intelligent, vehicle information security is facing great threats and challenges. Therefore, it is of great significance to develop efficient intrusion detection methods to protect the information security of IoV. In this paper, after analyzing the vulnerability of intra-vehicle networks (IVNs) and external vehicle networks (EVNs), we propose a lightweight intrusion detection method, which uses MobileNetv2 as the backbone, combines transfer learning (TL) techniques and the hyper-parameter optimization (HPO) method. The proposed method can detect various types of attacks, and the Accuracy, Precision, and Recall on the Car-Hacking dataset representing IVNs data are all 100 %. The Accuracy, Precision, and Recall on the CICIDS2017 dataset representing EVNs data are all 99.93 %. The average processing time of each packet tested is about 0.75 ms, and the model space is 23 M. Experimental results demonstrate that the proposed intrusion detection method is effective and lightweight.

关键词： Intrusion Detection System Transfer Learning Internet of Vehicles MobileNetV2 Lightweight Networks hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

hyper-parameter optimization by Using the Genetic Algorithm for Upper Limb Activities Recognition Based on Neural Networks

引用

IEEE SENSORS JOURNAL 2021年第2期21卷 1877-1884页

作者： Zhang, Junjie Sun, Guangmin Sun, Yuge Dou, Huijing Bilal, Anas Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Univ Manchester Sch Elect & Elect Engn Manchester M13 9PL Lancs England

A method of Upper Limb Activities Recognition (UPLA) based on Neural Networks is presented. The accuracy of activity recognition will be influenced by the size of sliding window, the overlapping of adjacent sequences and the number of neurons for neural networks. Whereas, there is less work in hyper parameters optimization of neural networks automatically. It is very time-consuming to optimize hyper parameters by experts through an experience and error approach. In the paper, Genetic algorithm is used to find the best hyper parameters automatically: the size of sliding window, the overlapping of adjacent sequences and the number of neurons for neural networks. The basic genetic algorithm has a slow convergence problem and it is very easy to fall into a local optimum. To solve the problem, the population selection mechanism is improved. A comparison is made for the improving method with seven traditional classification algorithms and convolutional neural network, an accuracy of 97.9% is reached by using the new method. Finally, an App is developed that can collect and recognize upper limb activity in real time.

关键词： Sensors Activity recognition Accelerometers Gyroscopes Feature extraction Real-time systems Elbow Activity recognition neural networks genetic algorithm hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

The future looks dark: improving high contrast imaging with hyper-parameter optimization for data-driven predictive wavefront control 9

The future looks dark: improving high contrast imaging with ...

引用

Conference on Adaptive Optics Systems IX

作者： Fowler, J. Jensen-Clemens, Rebecca van Kooten, Maaike A. M. Chamboulery, Vincent Cetre, Sylvain Univ Calif Santa Cruz Dept Astron & Astrophys Santa Cruz CA 95064 USA Natl Res Council Canada Herzberg Astron & Astrophys Res Ctr Victoria BC Canada WM Keck Observ Waimea HI 96743 USA

ISBN: (纸本)9781510675186;9781510675179

The direct imaging and characterization of exoplanets requires extreme adaptive optics (XAO), achieving exquisite wavefront correction (upwards of 90% Strehl) over a narrow field of view (a few arcseconds). For these XAO systems the temporal error is often a leading term in the error budget, wherein the wavefront evolves faster than the lag between wavefront sensing and control. For atmospheres with high-velocity wind layers, this can result in a wind-driven halo in the coronagraphic dark-zone, limiting sensitivity to faint, close-in companions. The AO system's lag-time is often limited by the wavefront sensor exposure time, especially in the case of fainter guidestars. Predictive control mitigates the temporal error by predicting the shape of the wavefront by time the system correction is applied. One such method of prediction is empirical orthogonal functions (EOF), wherein previous states in the wavefront sensor history are used to learn linear correlations with a minimization problem. This method has been demonstrated on-sky at Subaru/SCExAO and Keck/NIRC2, but has yet to be optimized. With this work as a starting point, we explore the optimal filter hyper-parameter space for implementing EOF on-sky, study its stability under varying atmospheric parameters, and discuss future paths for facilitization of predictive control. This work not only offers a pathway to optimize Keck and Subaru observing, but also acts as a pathfinder for predictive control methods with extremely large telescopes.

关键词： predictive control temporal error empirical orthogonal functions (EOF) hyper-parameter optimization simulated annealing Keck Subaru

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

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

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：