检索结果-内蒙古大学图书馆

Flood susceptibility mapping using support vector regression and hyper-parameter optimization

JOURNAL OF FLOOD RISK MANAGEMENT 2023年第4期16卷 e12920-e12920页

作者： Salvati, Aryan Nia, Alireza Moghaddam Salajegheh, Ali Ghaderi, Kayvan Asl, Dawood Talebpour Al-Ansari, Nadhir Solaimani, Feridon Clague, John J. Univ Tehran Fac Nat Resources Dept Arid & Mt Reg Reclamat Karaj Iran Univ Kurdistan Fac Engn Dept Informat Technol & Comp Engn Sanandaj Iran Univ Kurdistan Fac Nat Resources Dept Geomorphol Sanandaj Iran Lulea Univ Technol Dept Civil Environm & Nat Resources Engn Lulea Sweden Khuzestan Agr & Nat Resources Res & Educ Ctr Dept Soil Conservat & Watershed Management Res AREEO Ahvaz Iran Simon Fraser Univ Dept Earth Sci Burnaby BC Canada

Floods are both complex and destructive, and in most parts of the world cause injury, death, loss of agricultural land, and social disruption. Flood susceptibility (FS) maps are used by land-use managers and land owners to identify areas that are at risk from flooding and to plan accordingly. This study uses machine learning ensembles to produce objective and reliable FS maps for the Haraz watershed in northern Iran. Specifically, we test the ability of the support vector regression (SVR), together with linear kernel (LK), base classifier (BC), and hyper-parameter optimization (HPO), to identify flood-prone areas in this watershed. We prepared a map of 201 past floods to predict future floods. Of the 201 flood events, 151 (75%) were used for modeling and 50 (25%) were used for validation. Based on the relevant literature and our field survey of the study area, 10 effective factors were selected and prepared for flood zoning. The results show that three of the 10 factors are most important for predicting flood-sensitive areas, specifically and in order of importance, slope, distance to the river and river. Additionally, the SVR-HPO model, with area under the curve values of 0.986 and 0.951 for the training and testing phases, outperformed the other two tested models.

关键词： flood susceptibility GIS hyper-parameter optimization Iran linear kernel SVR

来源：评论

学校读者我要写书评

暂无评论

Quantum Inspired High Dimensional hyper-parameter optimization of Machine Learning Model

Quantum Inspired High Dimensional Hyper-Parameter Optimizati...

引用

International Smart Cities Conference (ISC2)

作者： Li, Yangyang Lu, Gao Zhou, Linhao Jiao, Licheng Xidian Univ Joint Int Res Lab Intelligent Percept & Computat Int Res Ctr Intelligent Percept & Computat Minist EducKey Lab Intelligent Percept & Image U Xian 710071 Shaanxi Peoples R China

ISBN: (纸本)9781538625248

The hyper-parameter optimization of machine learning model is not a completely solved problem. The exquisite combination of artificial tuning and grid search may be a good choice in the area where the dimension of hyper-parameters is very low. But for high-dimensional hyper-parameter optimization problems, artificial tuning and grid search are obviously helpless. In this paper, we propose a quantum inspired hyper-parameter search method, which employs a quantum inspired evolutionary algorithm integrated with the traditional neural network (NN) training technique to evolve a NN subject to accuracy on test set as the objective. We evaluate the proposed method on MNIST dataset and compare it with random search algorithm. Experimental results demonstrate the superiority of our proposed method.

关键词： quantum inspired evolutionary algorithm hyper-parameter optimization neural networks machine learning

来源：评论

学校读者我要写书评

暂无评论

Prediction Model of Dementia Risk Based on XGBoost Using Derived Variable Extraction and hyper parameter optimization

引用

IEEE ACCESS 2020年 8卷 177708-177720页

作者： Ryu, Seong-Eun Shin, Dong-Hoon Chung, Kyungyong Kyonggi Univ Div Comp Sci & Engn Suwon 16227 South Korea Kyonggi Univ Dept Comp Sci Suwon 16227 South Korea

With the development of healthcare technologies, the elderly population has grown and therefore populating ageing has emerged as a social issue. It is a cause of rise in patients with geriatric disorders, among which dementia is very fatal to the elderly's activities of daily living. In the studies on dementia risk prediction, a method using deep learning was proposed. It requires a lot of image data and much time to learn. Therefore, this study proposes a prediction model of dementia risk based on XGBoost using derived variable extraction from numericalized dementia data and hyper-parameters optimization. The proposed method extracts variable importance from typical independent variables with the use of gradient boosting and then generates derived variables. The generated derived variables are applied to variable importance analysis and thereby a Top-N group is created. Then, for achieving optimal performance in line with the data characteristics of each Top-N group, hyper-parameter tuning is conducted. With the optimized groups, XGBoost model based performance is evaluated. In addition, for the performance evaluation of the proposed model, goodness-of-fit for machine learning classification models is evaluated. According to the Top-N group performance evaluation with different numbers of derived variables, Top-20 model showed the best performance, and the optimized hyper-parameter values were eta = 0.10, gamma = 0, max_depth = 4, and min_child_weight = 1. As a result, the accuracy of the XGBoost model proposed in this study was 85.61%, and its F1-score was 79.28%. When the proposed model is compared with Decision Tree, Random Forest, SVM, and k-NN models, it has the best performance.

关键词： Dementia Predictive models Data models Feature extraction Sociology Statistics optimization Healthcare machine learning dementia extreme gradient boosting hyper-parameter optimization grid search classification parallel processing risk prediction

来源：评论

学校读者我要写书评

暂无评论

Bayesian optimization-Based hyper-parameter-Tuned Neural Network Regression for Smart Home Energy Consumption Modelling Using Weather Information 9th

Bayesian Optimization-Based Hyper-parameter-Tuned Neural Net...

引用

9th International Congress on Information and Communication Technology (ICICT)

作者： Alzimami, Ahmed Das, Saptarshi Mueller, Markus Univ Exeter Fac Environm Sci & Econ Ctr Environm Math Penryn Campus Exeter TR10 9FE Cornwall England Univ Exeter Inst Data Sci & Artificial Intelligence North Pk Rd Exeter EX4 4QE Devon England Univ Exeter Environm & Sustainabil Inst Penryn Campus Exeter TR10 9FE Cornwall England

ISBN: (纸本)9789819754403;9789819754410

This paper presents an illustrative study on the predictive analysis of household energy consumption patterns in the context of hybrid energy-powered smart homes having wide variety of appliances. Leveraging the proliferation of smart sensors and the integration of the Internet of Things (IoTs), our research focuses on the integration of weather information in predicting the user behaviour for different household appliances and the total energy consumption. By employing nonlinear regression modelling using artificial neural networks (ANNs), we develop black-box predictive models aimed at predicting total energy usage given the user behaviour patterns and weather information in order seamlessly design an optimized smart home energy system. We use the adjusted R-2 or the coefficient of determination as the performance metric in deciding the best fitted model. In such data-driven modelling, the regression methods need to be further fine-tuned over a wide choice of hyper-parameters which significantly affect the accuracy, speed, and consistency of the machine learning (ML) models. We here benchmark the hyper-parameter optimized model with a simpler hyper-parameter optimized linear model to show the efficacy of the nonlinear model over the linear counterpart. The reported research endeavours to advance the paradigm of sustainable urban living by leveraging datadrivenMLmodels for hybrid energy-powered smart homes, with the goal of fostering energy-efficient and ecologically responsible urban environments.

关键词： hyper-parameter optimization Bayesian optimization Artificial neural network (ANN) regression Hybrid energy systems Smart homes

来源：评论

学校读者我要写书评

暂无评论

hyper-parameter Selection in Convolutional Neural Networks Using Microcanonical optimization Algorithm

引用

IEEE ACCESS 2020年 8卷 52528-52540页

作者： Gulcu, Ayla Kus, Zeki Fatih Sultan Mehmet Univ Dept Comp Sci TR-34445 Istanbul Turkey

The success of Convolutional Neural Networks is highly dependent on the selected architecture and the hyper-parameters. The need for the automatic design of the networks is especially important for complex architectures where the parameter space is so large that trying all possible combinations is computationally infeasible. In this study, Microcanonical optimization algorithm which is a variant of Simulated Annealing method is used for hyper-parameter optimization and architecture selection for Convolutional Neural Networks. To the best of our knowledge, our study provides a first attempt at applying Microcanonical optimization for this task. The networks generated by the proposed method is compared to the networks generated by Simulated Annealing method in terms of both accuracy and size using six widely-used image recognition datasets. Moreover, a performance comparison using Tree Parzen Estimator which is a Bayesion optimization-based approach is also presented. It is shown that the proposed method is able to achieve competitive classification results with the state-of-the-art architectures. When the size of the networks is also taken into account, one can see that the networks generated by Microcanonical optimization method contain far less parameters than the state-of-the-art architectures. Therefore, the proposed method can be preferred for automatically tuning the networks especially in situations where fast training is as important as the accuracy.

关键词： Convolutional neural networks hyper-parameter optimization microcanonical optimization tree Parzen estimator

来源：评论

学校读者我要写书评

暂无评论

Optimizing the hyper-parameters of deep reinforcement learning for building control

引用

BUILDING SIMULATION 2025年第4期18卷 765-789页

作者： Li, Shuhao Su, Shu Lin, Xiaorui Southeast Univ Dept Civil Engn Nanjing Jiangsu Peoples R China OCT Eastern China Investment Co Ltd Shanghai Peoples R China

Buildings are a major energy consumer and carbon emitter, therefore it is important to improve building energy efficiency to achieve our sustainable development goal. Deep reinforcement learning (DRL), as an advanced building control method, demonstrates great potential for energy efficiency optimization and improved occupant comfort. However, the performance of DRL is highly sensitive to hyper-parameters, and selecting inappropriate hyper-parameters may lead to unstable learning or even failure. This study aims to investigate the design and application of DRL in building energy system control, with a specific focus on improving the performance of DRL controllers through hyper-parameter optimization (HPO) algorithms. It also aims to provide quantitative evaluation and adaptive validation of these optimized controllers. Two widely used algorithms, deep deterministic policy gradient (DDPG) and soft actor-critic (SAC), are used in the study and their performance is evaluated in different building environments based on the BOPTEST virtual testbed. One of the focuses of the study is to compare various HPO techniques, including tree-structured Parzen estimator (TPE), covariance matrix adaptation evolution strategy (CMA-ES), and combinatorial optimization methods, to determine the efficacy of different hyper-parameter optimization methods for DRL. The study enhances HPO efficiency through parallel computation and conducts a comprehensive quantitative assessment of the optimized DRL controllers, considering factors such as reduced energy consumption and improved comfort. The results show that the HPO algorithms significantly improve the performance of the DDPG and SAC controllers. A reduction of 56.94% and 68.74% in thermal discomfort is achieved, respectively. Additionally, the study demonstrates the applicability of the HPO-based approach for enhancing DRL controller performance across diverse building environments, providing valuable insights for the design and optimizat

关键词： hyper-parameter optimization deep reinforcement learning building energy system optimal control BOPTEST parallelization

来源：评论

学校读者我要写书评

暂无评论

A whale optimization algorithm-based ensemble model for power consumption prediction

引用

ELECTRICAL ENGINEERING 2025年第2期107卷 1659-1670页

作者： Weng, Shaoyuan Liu, Zimeng Fan, Zongwen Zhang, Guoliang Xiamen Inst Software Technol Xiamen 361024 Peoples R China Huaqiao Univ Coll Comp Sci & Technol Xiamen 361021 Peoples R China

As one of the indispensable energies, electricity plays an essential role in modern society. Accurate prediction of power consumption is crucial for managing energy generation and purchasing, preventing overloading, and ensuring energy generation and purchase for preventing overloading and having efficient energy storage. In this paper, we propose a whale optimization algorithm-based ensemble learning algorithm (WOA-ELA) for multi-output power consumption prediction using a weighted ensemble approach. Firstly, we optimize the hyper-parameters of the base estimators using the WOA. Each base estimator's performance is evaluated through fivefold cross-validation to mitigate the influence of data splitting during model training. After obtaining the trained estimators, we further optimize the weights that use to ensemble these base estimators for the final prediction. These weights are designed to emphasize the strengths of high-performing estimators while mitigating the impact of weaker ones. Given the three outputs of power consumption, our target is to minimize their mean absolute error (MAE) using the WOA. Experimental results show that our proposed WOA-ELA outperforms the comparative models in predicting the power consumption. The average MAE achieved by our proposed WOA-ELA surpasses the four comparison models by 19.14%, 17.17%, 10.53%, and 2.15%, respectively. Additionally, its average root mean squared error is better by 15.12%, 18.50%, 7.16%, and 1.16% compared to the four models. This indicates that the use of WOA is effective for improving the prediction performance by optimizing the hyper-parameters of each model and the weights for the ensemble operation. With the promising results, our WOA-ELA can be a useful tool for energy management systems in multi-output power control scenarios.

关键词： Whale optimization algorithm Power consumption prediction Weighted ensemble strategy hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT Intrusion Detection Systems Through Horizontal Federated Learning and Optimized WGAN-GP

引用

IEEE ACCESS 2025年 13卷 45059-45076页

作者： Bouzeraib, Wayoud Ghenai, Afifa Zeghib, Nadia Univ Abdelhamid Mehri Constantine 2 NTIC Fac LIRE Lab Constantine 25000 Algeria

The Internet of Things (IoT) ecosystem is fraught with substantial vulnerabilities, particularly in the realm of cybersecurity attacks. Network Intrusion Detection Systems (NIDS) stand as a pivotal element in mitigating these cybersecurity risks. This paper introduces an innovative approach to fortifying IoT security by effectively addressing the data limitations inherent in AI-based NIDS. We present a data generation model that harnesses Generative Adversarial Networks (GANs). Specifically, the GAN variant we employ is Wasserstein GAN with Gradient Penalty (WGAN-GP), which combines the Wasserstein loss formulation with a gradient norm penalty to stabilize training and improve the quality of generated data. The performance is optimized with Genetic Algorithms, focusing on hyper-parameter selection and federated learning for shared model weights. The model's training is conducted on four well-established benchmark datasets: UNSW-NB15, IoT-23, CSE-CIC-IDS2018, and MQTT-IoT-IDS2020. We conduct a comprehensive comparative analysis between the generated synthetic data and real-world datasets, rigorously assessing their impact on training Machine Learning (ML) models. The findings underscore the efficacy of our approach, demonstrating a significant improvement in detection accuracy, achieving a 99% accuracy rate when combining the generated data with real datasets. This study highlights the paramount significance of innovative techniques in enhancing the security of IoT systems. Furthermore, it presents a promising avenue for generating high-quality synthetic tabular data, despite its complexity and time-consuming implementation. Such data can be leveraged across a large spectrum of applications, including training ML models, data augmentation, and privacy-preserving data sharing.

关键词： Training Generative adversarial networks Generators Internet of Things Federated learning Genetic algorithms Data privacy Synthetic data Data models optimization Internet of Things (IoT) network intrusion detection system (NIDS) federated learning (FL) generative adversarial network (GAN) Wasserstein GAN with gradient penalty (WGAN-GP) genetic algorithm (GA) hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Multiple objectives escaping bird search optimization and its application in stock market prediction based on transformer model

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-51页

作者： Wei, Dedai Wang, Zimo Qiu, Minyu Yu, Juntao Yu, Jiaquan Jin, Yurun Sha, Xinye Ouyang, Kaichen Shenyang Univ Coll Econ Shenyang 110000 Peoples R China Nankai Univ Dept Philosophy Tianjin 300381 Peoples R China China Jiliang Univ Coll Informat Engn Hangzhou 310018 Zhejiang Peoples R China Univ Sci & Technol China Dept Math Hefei 230026 Peoples R China Univ Sci & Technol China Sch Comp Sci & Technol Hefei 230026 Peoples R China Columbia Univ Grad Sch Arts & Sci New York NY 10027 USA

Stock market prediction has long attracted the attention of academia and industry due to its potential for substantial financial returns. Despite the availability of various forecasting methods, such as CNN, LSTM, BiLSTM, GRU, and Transformer, the hyperparameter optimization of these models often faces limitations, particularly in single-objective optimization, where they can easily fall into local optima. To address this issue, this paper proposes an innovative multi-objective optimization algorithm-the Multi-Objective Escape Bird Algorithm (MOEBS)-and introduces the MOEBS-Transformer architecture to enhance the efficiency and effectiveness of hyper-parameter optimization for Transformer models. This study first validates the performance of MOEBS through a series of multi-objective benchmark tests on standard problem sets such as ZDT, DTLZ, and WFG, comparing it with other multi-objective optimization algorithms (e.g., MOMVO, MSSA, and MOEAD) using evaluation metrics such as GD, Spacing, IGD, and HV for comprehensive analysis. In the context of stock price prediction, we select the closing price datasets of Amazon, Google, and Uniqlo, using MOEBS to optimize the core hyper parameters of the Transformer while considering multiple objectives, including training set RMSE, testing set RMSE, and testing set error variance. In the experiments, this paper first compares CNN, LSTM, BiLSTM, GRU, and traditional Transformer models to establish the Transformer as the optimal model for stock market prediction. Subsequently, the study compares the MOEBS-Transformer with Transformer models optimized using various hyperparameter optimization methods, including MOMVO-Transformer, MSSA-Transformer, and MOEAD-Transformer. Additionally, it evaluates Transformer models optimized through conventional methods: Random Search (RS-Transformer), Grid Search (GS-Transformer), and Bayesian optimization (BO-Transformer). By assessing the performance of these models using R2, RMSE, and RPD metr

关键词： Stock price prediction Multi-objective optimization Escaping bird search Transformer hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Velocity Paused Particle Swarm optimization-based Intelligent Long Short-Term Memory Framework for Intrusion Detection System in Internet of Medical Things

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2025年 1-31页

作者： Dash, Pandit Byomakesha Behera, H. S. Senapati, Manas Ranjan Nayak, Janmenjoy Maharaja Sriram Chandra Bhanja Deo MSCB Univ Dept Comp Sci Baripada Orissa India Veer Surendra Sai Univ Technol Dept CSE Burla Sambalpur India

The rapid advancement of technology in the domain of Internet of Medical Things (IoMT) necessitates the implementation of stronger safety measures. Intrusion detection system (IDS) is an essential framework on IoMT networks proposed for identifying suspicious activities and detecting abnormal traffics. The implementation of the IDS framework might use either hardware or software solutions. However, traditional IDS frameworks are often inadequate in protecting data privacy and identifying complex and irregular intrusions specifically for IoMT environments. An improved velocity paused particle swarm optimization (VPPSO) methodology combined with long short-term memory (LSTM) has been proposed in this research to improve security in IoMT environment. The improved attack detection performance of proposed VPPSO_LSTM is achieved by the velocity pausing concept's ability of VPPSO algorithm, which efficiently balance both exploration and exploitation. This enables an intelligent choice of hyper-parameter configurations for the LSTM architecture. This research has performed a comparative analysis to highlight the effectiveness of the proposed model with standard machine learning (ML) models including decision trees (DT), random forest (RF), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), gradient boosting (GBoost), and CatBoost, as well as other deep learning (DL) methodologies such as LSTM, PSO_LSTM and Firefly Algorithm (FA)_LSTM. Implementing the ECU-IoHT dataset, the proposed VPPSO_LSTM model has been trained and validated for detecting and categorizing several attack types such as Smurf attack, ARP spoofing attack, Nmap port scans and denial-of-service (DoS) attack. For achieving better attack detection performance, the proposed model has been implemented with an optimal set of hyper-parameters including 64 LSTM cells in each LSTM layer, 32 neurons in each hidden layer, "ReLU" activation function for internal layers, dropout rate of 0.1, optimizer as

关键词： Velocity pausing VPPSO LSTM IDS Security IoMT optimization hyper-parameter optimization Intrusion detection

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：