检索结果-内蒙古大学图书馆

IEEE International Conference on Communication, Networks and Satellite (ComNetSat)

作者： Rangga Dipta Azhari Muljono Faculty of Computer Science Dian Nuswantoro University Semarang Central Java Indonesia

ISBN: (数字)9798350368086

ISBN: (纸本)9798350368093

The development of Indonesia’s New Capital (IKN) is a national strategic project of Indonesia that has sparked various discussions and debates in society. Sentiment analysis of Twitter data can provide a more comprehensive overview of public perception towards this project. Studies on sentiment analysis of IKN are still relatively limited, particularly concerning the optimization of hyperparameters in machine learning models. There is still research that has not applied hyperparameter optimization in the sentiment analysis process. The objectives of this research are to investigate how hyperparameter optimization affects the effectiveness of different machine learning algorithms when analyzing sentiment in Indonesian text data, and enhance the precision of sentiment analysis in machine learning models. The researchers used Random Search, Bayesian optimization, and PSO to optimize the hyperparameter in machine learning models. Among the four tested models (SVM, KNN, Random Forest, and Logistic Regression), the most significant impact of hyperparameter optimization was observed in the KNN model. hyperparameter optimization has a significant impact on improving the performance of KNN, as indicated by the highest accuracy increase of 0.0763 (7.63%) using Bayesian optimization. Additionally, the SVM algorithm optimized using Random Search, combined with data balancing using SMOTE, achieved the highest accuracy of 0.7859 (78.59%) in the sentiment analysis process in this study.

关键词： Support vector machines Sentiment analysis Analytical models Machine learning algorithms Nearest neighbor methods hyperparameter optimization Data models Bayes methods optimization Context modeling

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithms and Parallel Distributed Computing Techniques for High-Resolution Load Forecasting Applying hyperparameter optimization

引用

IEEE SYSTEMS JOURNAL 2022年第3期16卷 3758-3769页

作者： Parizad, Ali Hatziadoniu, Constantine Southern Illinois Univ Dept Elect & Comp Engn Carbondale IL 62901 USA Virginia Tech Natl Capital Region Adv Res Inst ARI 900 North Glebe Rd Arlington VA 22203 USA

Electrical load forecasting is one of the critical tasks that helps power utility companies in planning and operation as well as the energy management system (EMS) in controlling and optimizing the power grid's performance. It guarantees system adequacy and reliability by reducing the gap between supply and demand, and it bolsters cybersecurity by enabling false data detection and system security by predicting system peak load. This article aims to build an accurate long-term load forecasting model based on deep learning (DL) algorithms. Initially, big-data analytics and feature engineering are applied to the power load and weather historical data. Next, three different load forecasting models a re developed based on three corresponding deep neural network models (DNN): the simple RNN, the long short term memory (LSTM), and the gated recurrent unit (GRU), respectively. To find an accurate DNN model, a two-step hyperparameter optimization is performed consisting of cross-validation. In the first step, the random search (RS) algorithm is employed to narrow the parameter search space to a smaller local one. In the second step, the grid search (GS) algorithm is used to find the best hyperparameters in the local area located by RS. However, the computational burden of the DNN training process is too high and may lead to out-of-memory (OOM) issues, especially when we are dealing with a big volume of data. To overcome this problem, we developed our Python program based on Tensorflow framework and implemented the framework on a high-performance computer cluster (HPCC). Then, different jobs are defined to employ parallel distributed computing (PDC) capability on the SIU BigDawg HPCC. To this end, all DNN hyperparameters (e.g., number of layers, neurons, dropout, batch size, epoch, learning rate, etc.) can be optimized and result in a comprehensive and accurate load forecasting model. Our proposed method, along with the programming framework, is evaluated on a real-world data

关键词： Big data analytics deep learning (DL) algorithms gated recurrent unit (GRU) hyperparameter optimization load forecasting long short term memory (LSTM) parallel distributed computing (PDC) sequence prediction

来源：评论

学校读者我要写书评

暂无评论

hyperparameter optimization in Deep Learning-Based Object Detection of Branching and Endpoints on 2D Brain Vessel Images

Hyperparameter Optimization in Deep Learning-Based Object De...

引用

Innovations in Intelligent Systems and Applications Conference

作者： Samet Kaya Berna Kiraz Ali Yılmaz Çamurcu Department of Software Engineering Fatih Sultan Mehmet Vakif University Istanbul Turkiye Department of Computer Engineering Fatih Sultan Mehmet Vakif University Istanbul Turkiye

ISBN: (数字)9798350379433

ISBN: (纸本)9798350379440

This work presents a deep learning-based object detection technique for identifying branches and endpoints in two-dimensional brain vessel images alongside its hyperparame- ter optimization. Although traditional image processing methods are feasible and successful, their algorithm complexity increases exponentially with the size of the image and the filters to be applied. In contrast, our deep learning approach has shown significant improvements in accuracy and efficiency, independent of image size and number of filters. We preprocess our dataset of raw mouse brain slices from laboratory environments to remove noise from images and then extract a binary vein network using image processing methods. Finally, we labeled vessel branching and endpoints in 5x5 pixel bounding boxes. All labeled objects on images were converted to COCO format for training and testing to ensure compatibility with deep learning algorithms. Our research focused on using the Faster R-CNN method in the Detectron2 framework, which has been successful in our previous work. Evaluation using the intersection over union (IoU) metric underscores the robustness of our approach, and we achieved a success rate of over 90%. We employed Optuna for hyperparameter optimization to further enhance our model, focusing on three key hyperparameters: base learning rate, maximum iterations, and batch size per image. We systematically refined these hyperparameters by running 50 training and test runs separately, significantly improving model performance to over 98%. Our findings highlight the transformative potential of deep learning in neuroimaging analysis and promise significant advances in diagnostic and research applications in neurovascular studies.

关键词： Deep learning Training Neuroimaging Measurement Accuracy Image processing Object detection hyperparameter optimization Robustness optimization

来源：评论

学校读者我要写书评

暂无评论

SMAC3: A Versatile Bayesian optimization Package for hyperparameter optimization

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2022年第1期23卷 1-9页

作者： Lindauer, Marius Eggensperger, Katharina Feurer, Matthias Biedenkapp, Andre Deng, Difan Benjamins, Carolin Ruhkopf, Tim Sass, Rene Hutter, Frank Leibniz Univ Hannover Hannover Germany Univ Freiburg Freiburg Germany Bosch Ctr Artificial Intelligence Renningen Germany

Algorithm parameters, in particular hyperparameters of machine learning algorithms, can substantially impact their performance. To support users in determining well-performing hyperparameter configurations for their algorithms, datasets and applications at hand, SMAC3 offers a robust and flexible framework for Bayesian optimization, which can improve performance within a few evaluations. It offers several facades and pre-sets for typical use cases, such as optimizing hyperparameters, solving low dimensional continuous (artificial) global optimization problems and configuring algorithms to perform well across multiple problem instances. The SMAC3 package is available under a permissive BSD-license at https://***/automl/SMAC3.

关键词： Bayesian optimization hyperparameter optimization Multi-Fidelity optimization Automated Machine Learning Algorithm Configuration

来源：评论

学校读者我要写书评

暂无评论

An automatic hyperparameter optimization DNN model for precipitation prediction

引用

APPLIED INTELLIGENCE 2022年第3期52卷 2703-2719页

作者： Peng, Yuzhong Gong, Daoqing Deng, Chuyan Li, Hongya Cai, Hongguo Zhang, Hao Nanning Normal Univ Sch Comp & Informat Engn Nanning 530001 Peoples R China Fudan Univ Coll Comp Sci & Technol Shanghai 200433 Peoples R China Shangqiu Univ Appl Sci & Technol Coll Dept Sci Kaifeng 475000 Peoples R China Guangxi Coll Educ Dept Math & Comp Sci Nanning 530023 Peoples R China

Deep neural networks (DNN) have gained remarkable success on many rainfall predictions tasks in recent years. However, the performance of DNN highly relies upon the hyperparameter setting. In order to design DNNs with the best performance, extensive expertise in both the DNN and the problem domain under investigation is required. But many DNN users have not met this requirement. Therefore, it is difficult for the users who have no extensive expertise in DNN to design optimal DNN architectures for their rainfall prediction problems that is to solve. In this paper, we proposed a novel automatic hyperparameters optimization method for DNN by using an improved Gene Expression Programming. The proposed method can automatically optimize the hyperparameters of DNN for precipitation modeling and prediction. Extensive experiments are conducted with three real precipitation datasets to verify the performance of the proposed algorithm in terms of four metrics, including MAE, MSE, RMSE, and R-Squared. The results show that: 1) the DNN optimized by the proposed method outperforms the existing precipitation prediction methods including Multiple Linear Regression (MLR), Back Propagation (BP), Support Vector Machine (SVM), Random Forest (RF) and DNN;2) the proposed DNN hyperparameter optimization method outperforms state-of-the-art DNN hyperparameter optimization methods, including Genetic Algorithm, Bayes Search, Grid Search, Randomized Search, and Quasi Random Search.

关键词： Deep neural networks Precipitation prediction Neural structure optimization Neural architecture search hyperparameter optimization Gene expression programming

来源：评论

学校读者我要写书评

暂无评论

DeepQGHO: Quantized Greedy hyperparameter optimization in Deep Neural Networks for on-the-Fly Learning

引用

IEEE ACCESS 2022年 10卷 6407-6416页

作者： Chowdhury, Anjir Ahmed Hossen, Md Abir Azam, Md Ali Rahman, Md Hafizur Amer Int Univ Bangladesh Dept Comp Sci Dhaka 1229 Bangladesh Univ South Carolina Comp Sci & Engn Dept Columbia SC 29208 USA South Dakota Sch Mines & Technol Dept Elect Engn Rapid City SD 57701 USA

On-the-fly learning is unavoidable for applications that demand instantaneous deep neural network (DNN) training or where transferring data to the central system for training is costly. hyperparameter optimization plays a significant role in the performance and reliability in deep learning. Many hyperparameter optimization algorithms have been developed for obtaining better validation accuracy in DNNs. Most state-of-the-art hyperparameter optimization techniques are computationally expensive due to the focus on validation accuracy. Therefore, they are unsuitable for on-the-fly learning applications that require faster computation on resource constraint devices (e.g., edge devices). In this paper, we develop a novel greedy approach-based hyperparameter optimization (GHO) algorithm enabling faster computing on edge devices for on-the-fly learning applications. In GHO, we obtain the validation accuracy locally for each of the hyperparameter configurations. The GHO algorithm optimizes each hyperparameter while keeping the others constant in order to converge to the locally optimal solution in the expectation that this choice will lead to a globally optimal solution. We perform an empirical study to compute the performance such as computation time and energy consumption of the GHO and compare it with two state-of-the-art hyperparameter optimization algorithms. We also deploy the GHO algorithm in an edge device to validate the performance of our algorithm. We perform post-training quantization on the GHO algorithm to reduce the inference time. Our GHO algorithm is more than 3x energy efficient and 2x faster than two state-of-the-art hyperparameter optimization techniques on both DNNs and datasets studied in this paper.

关键词： Greedy algorithm deep learning neural networks online learning hyperparameter optimization TinyML quantization

来源：评论

学校读者我要写书评

暂无评论

SASHA: hyperparameter optimization by Simulated Annealing and Successive Halving 19th

SASHA: Hyperparameter Optimization by Simulated Annealing an...

引用

19th International Conference on Artificial Intelligence Applications and Innovations (AIAI)

作者： Triepels, Ron Maastricht Univ Tongersestr 53 NL-6211 LM Maastricht Netherlands

ISBN: (纸本)9783031341090;9783031341076;9783031341069

Successive halving (SHA) has become popular for hyperparameter optimization since it often yields good results while consuming a considerably lower training budget than traditional brute-force algorithms. Nevertheless, SHA is known to suffer from the crossing curves problem. A configuration that performs poorly at the start may perform very well with more budget in later rounds, causing its loss curve to cross that of competing configurations. When this happens, there is a risk that promising configurations are discarded prematurely. In this paper, we propose a new variant of SHA which we name SASHA, that combines Simulated Annealing (SA) with SHA. SASHA discards configurations stochastically based on their performance relative to the best-performing configuration. This property allows the algorithm to make more informed decisions about the configurations to be discarded each round. We study the behavior of SASHA when optimizing a simple test function and a logistic regression model. Our results indicate that SASHA can effectively deal with the crossing curves problem.

关键词： hyperparameter optimization Simulated Annealing Successive Halving Machine Learning Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

Battery SOH Estimation Using LSTM with Genetic Algorithm-Based hyperparameter optimization

Battery SOH Estimation Using LSTM with Genetic Algorithm-Bas...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Ponnambalam, Karthickumar Sivaneasan, B. Sharma, A. Lee, S.S. Chakrabarti, Prasun Newcastle University Singapore Singapore Institute of Technology Singapore Sir Padampat Singhania University India

ISBN: (纸本)9798350350821

The effective operation and management of battery-based energy storage devices hinge upon timely assessment of battery health. This paper introduces an optimized deep learning approach utilizing Artificial Neural Networks (ANN) for assessing the State of Health (SoH) of lithium-ion batteries, leveraging on battery aging datasets from NASA's Open Data Portal. An innovative methodology for optimizing Long Short-Term Memory (LSTM) hyperparameters using Genetic Algorithm (GA) is also proposed. Traditional approaches rely heavily on trial and error for hyperparameter determination, facing challenges in selecting optimal parameters due to an expansive search space. The proposed systematic methodology not only identifies the best architecture but also introduces novel criteria for evaluating ANN performance and complexity. The novel optimized GA-LSTM model is trained using the curated NASA data, and its accuracy evaluated by fine-tuning its parameters such as batch size, unit size, activation and loss functions. The results demonstrate that the proposed optimized GA-LSTM model exhibits better performance in estimating battery State of Health (SoH) across diverse conditions, achieving significantly improved Root Mean Square Error (RMSE) values compared to the Particle Swarm optimization algorithm aided LSTM model, namely PA-LSTM, introduced in recent research. The improvement in RMSE ranges from 12.4% to 76.79% when trained with 70% of discharge cycle data. This represents a notable enhancement over previous methods, highlighting its efficacy as a more accurate prediction model for battery health assessment. © 2024 IEEE.

关键词： Battery energy storage genetic algorithm hyperparameter optimization LSTM prediction state-of-health

来源：评论

学校读者我要写书评

暂无评论

hyperparameter optimization Using Successive Halving with Greedy Cross Validation

引用

ALGORITHMS 2023年第1期16卷 17-17页

作者： Soper, Daniel S. Calif State Univ Informat Syst & Decis Sci Dept Fullerton CA 92831 USA

Training and evaluating the performance of many competing Artificial Intelligence (AI)/Machine Learning (ML) models can be very time-consuming and expensive. Furthermore, the costs associated with this hyperparameter optimization task grow exponentially when cross validation is used during the model selection process. Finding ways of quickly identifying high-performing models when conducting hyperparameter optimization with cross validation is hence an important problem in AI/ML research. Among the proposed methods of accelerating hyperparameter optimization, successive halving has emerged as a popular, state-of-the-art early stopping algorithm. Concurrently, recent work on cross validation has yielded a greedy cross validation algorithm that prioritizes the most promising candidate AI/ML models during the early stages of the model selection process. The current paper proposes a greedy successive halving algorithm in which greedy cross validation is integrated into successive halving. An extensive series of experiments is then conducted to evaluate the comparative performance of the proposed greedy successive halving algorithm. The results show that the quality of the AI/ML models selected by the greedy successive halving algorithm is statistically identical to those selected by standard successive halving, but that greedy successive halving is typically more than 3.5 times faster than standard successive halving.

关键词： hyperparameter optimization successive halving greedy cross validation machine learning artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

TextBrew: Automated Model Selection and hyperparameter optimization for Text Classification

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2022年第9期13卷 748-754页

作者： Desai, Rushil Shah, Aditya Kothari, Shourya Surve, Aishwarya Shekokar, Narendra Dwarkadas J Coll Engn Dept Comp Engn Mumbai India

In building a machine learning solution, algorithm selection and hyperparameter tuning is the most time-consuming task. Automated Machine Learning is a solution to fully automate the process of finding the best model for a given task without actually having to try various models. This paper introduces a new AutoML system, TextBrew, explicitly built for the NLP task of text classification. Our system provides an automated method for selecting transformer models, tuning hyperparameters, and combining the best models into one by ensembling. Keeping in mind that new state-of-the-art models are being constantly introduced, TextBrew has been designed to be highly flexible and thus can support additional models easily. In our work, we experiment with multiple transformer models, each with numerous different hyperparameter settings, and select the most robust models. These models are then trained on multiple datasets to obtain accuracy scores, which are then used to build the meta-dataset to train the meta-model. Since text classification datasets are not as abundant, our system generates synthetic data to augment the meta-dataset using CopulaGAN, a deep generative model. The meta-model is an ensemble of five models, which predicts the best candidate model with an accuracy of 78.75%. The final model returned to the user is an ensemble of all the best models that can be trained under the given time constraint. Experiments on various datasets and comparisons with existing systems demonstrate the effectiveness of our system.

关键词： Automated machine learning AutoML NLP trans-former models hyperparameter optimization CopulaGAN gener-ative model meta-learning

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：