• Journal of the Korean Society of Industry Convergence
• /
• v.18 no.4
• /
• pp.191-196
• /
• 2015

In this paper, we present a path-smoothing algorithm for a robot arm manipulator that finds the path using a joint space-based rapidly-exploring random tree. Unlike other smoothing algorithms which require complex mathematical computation, the proposed path-smoothing algorithm is done using a Gaussian process. To find the optimal hyperparameters of the Gaussian process, we use differential evolution hybridized with opposition-based learning. The simulation result indicates that the Gaussian process whose hyperparameters were optimized by hybrid differential evolution successfully smoothed the path generated by the joint space-based rapidly-exploring random tree.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.32-42
• /
• 2019

The performance of machine learning algorithms significantly depends on how a configuration of hyperparameters is identified and how a neural network architecture is designed. However, this requires expert knowledge of relevant task domains and a prohibitive computation time. To optimize these two processes using minimal effort, many studies have investigated automated machine learning in recent years. This paper reviews the conventional random, grid, and Bayesian methods for hyperparameter optimization (HPO) and addresses its recent approaches, which speeds up the identification of the best set of hyperparameters. We further investigate existing neural architecture search (NAS) techniques based on evolutionary algorithms, reinforcement learning, and gradient derivatives and analyze their theoretical characteristics and performance results. Moreover, future research directions and challenges in HPO and NAS are described.

• Journal of Korea Multimedia Society
• /
• v.24 no.4
• /
• pp.519-527
• /
• 2021

Alzheimer's disease is one of the challenges to tackle in the coming aging era and is attempting to diagnose and predict through various biomarkers. While the application of various deep learning-based technologies as powerful imaging technologies has recently expanded across the medical industry, empirical design is not easy because there are various deep earning neural networks architecture and categorical hyperparameters that rely on problems and data to solve. In this paper, we show the possibility of optimizing a deep learning neural network structure and hyperparameters for Alzheimer's disease classification in amyloid brain images in a representative deep earning neural networks architecture using genetic algorithms. It was observed that the optimal deep learning neural network structure and hyperparameter were chosen as the values of the experiment were converging.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.446-448
• /
• 2021

In training a deep learning model, it is crucial to tune various hyperparameters and gain speed and accuracy. While hyperparameters that mathematically induce convergence impact training speed, system parameters that affect host-to-device transfer are also crucial. Therefore, it is important to properly tune and select parameters that influence the data loader as a system parameter in overall time acceleration. We propose an automated framework called Num Worker Tuner (NWT) to address this problem. This method finds the appropriate number of multi-processing subprocesses through the search space and accelerates the learning through the number of subprocesses. Furthermore, this method allows memory efficiency and speed-up by tuning the system-dependent parameter, the number of multi-process spawns.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.48.1-48.1
• /
• 2021

Gaussian process regression (GPR) is a powerful method used for model-independent analysis of cosmological observations. In GPR, it is important to decide an input mean function and hyperparameters that affect the reconstruction results. Depending on how the input mean function and hyperparameters are determined in the literature, I divide into four main applications for GPR and compare their results. In particular, a zero mean function is commonly used as an input mean function, which may be inappropriate for reconstructing cosmological observations such as the distance modulus. Using mock data based on Pantheon compilation of type Ia supernovae, I will point out the problem of using a zero input and suggest a new way to deal with the input mean function.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.3
• /
• pp.148-153
• /
• 2020

In order to obtain high accuracy with an convolutional neural network(CNN), it is necessary to set the optimal hyperparameters. However, the exact value of the hyperparameter that can make high performance is not known, and the optimal hyperparameter value is different based on the type of the dataset, therefore, it is necessary to find it through various experiments. In addition, since the range of hyperparameter values is wide and the number of combinations is large, it is necessary to find the optimal values of the hyperparameters after the experimental design in order to save time and computational costs. In this paper, we suggest an algorithm that use the design of experiments and grid search algorithm to determine the optimal hyperparameters for a classification problem. This algorithm determines the optima values of the hyperparameters that yields high performance using the factorial design of experiments. It is shown that the amount of computational time can be efficiently reduced and the accuracy can be improved by performing a grid search after reducing the search range of each hyperparameter through the experimental design. Moreover, Based on the experimental results, it was shown that the learning rate is the only hyperparameter that has the greatest effect on the performance of the model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2806-2825
• /
• 2018

Unsupervised learning has shown good performance on image, video and audio classification tasks, and much progress has been made so far. It studies how systems can learn to represent particular input patterns in a way that reflects the statistical structure of the overall collection of input patterns. Many promising deep learning systems are commonly trained by the greedy layerwise unsupervised learning manner. The performance of these deep learning architectures benefits from the unsupervised learning ability to disentangling the abstractions and picking out the useful features. However, the existing unsupervised learning algorithms are often difficult to train partly because of the requirement of extensive hyperparameters. The tuning of these hyperparameters is a laborious task that requires expert knowledge, rules of thumb or extensive search. In this paper, we propose a simple and effective unsupervised feature learning algorithm for image classification, which exploits an explicit optimizing way for population and lifetime sparsity. Firstly, a sparse target matrix is built by the competitive rules. Then, the sparse features are optimized by means of minimizing the Euclidean norm ($L_2$) error between the sparse target and the competitive layer outputs. Finally, a classifier is trained using the obtained sparse features. Experimental results show that the proposed method achieves good performance for image classification, and provides discriminative features that generalize well.

• Advances in concrete construction
• /
• v.1 no.1
• /
• pp.85-102
• /
• 2013

Prior concrete strength distributions can be updated by using direct information from test results as well as by taking into account indirect information due to conformity control. Due to the filtering effect of conformity control, the distribution of the material property in the accepted inspected lots will have lower fraction defectives in comparison to the distribution of the entire production (before or without inspection). A methodology is presented to quantify this influence in a Bayesian framework based on prior knowledge with respect to the hyperparameters of concrete strength distributions. An algorithm is presented in order to update prior distributions through numerical integration, taking into account the operating characteristic of the applied conformity criteria, calculated based on Monte Carlo simulations. Different examples are given to derive suitable hyperparameters for incoming strength distributions of concrete offered for conformity assessment, using updated available prior information, maximum-likelihood estimators or a bootstrap procedure. Furthermore, the updating procedure based on direct as well as indirect information obtained by conformity assessment is illustrated and used to quantify the filtering effect of conformity criteria on concrete strength distributions in case of a specific set of conformity criteria.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.4
• /
• pp.1128-1145
• /
• 2022

Owing to the rapid development of information science, data analysis based on machine learning has become an interdisciplinary and strategic area. Marine predators algorithm (MPA) is a novel metaheuristic algorithm inspired by the foraging strategies of marine organisms. Considering the randomness of these strategies, an improved algorithm called co-evolutionary cultural mechanism-based marine predators algorithm (CECMPA) is proposed. Through this mechanism, search agents in different spaces can share knowledge and experience to improve the performance of the native algorithm. More specifically, CECMPA has a higher probability of avoiding local optimum and can search the global optimum quickly. In this paper, it is the first to use CECMPA to perform feature subset selection and optimize hyperparameters in support vector machine (SVM) simultaneously. For performance evaluation the proposed method, it is tested on twelve datasets from the university of California Irvine (UCI) repository. Moreover, the coronavirus disease 2019 (COVID-19) can be a real-world application and is spreading in many countries. CECMPA is also applied to a COVID-19 dataset. The experimental results and statistical analysis demonstrate that CECMPA is superior to other compared methods in the literature in terms of several evaluation metrics. The proposed method has strong competitive abilities and promising prospects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.755-778
• /
• 2024

In recent years, the number of devices being connected to the internet has grown enormously, as has the intrusive behavior in the network. Thus, it is important for intrusion detection systems to report all intrusive behavior. Using deep learning and machine learning algorithms, intrusion detection systems are able to perform well in identifying attacks. However, the concern with these deep learning algorithms is their inability to identify a suitable network based on traffic volume, which requires manual changing of hyperparameters, which consumes a lot of time and effort. So, to address this, this paper offers a solution using the extended compact genetic algorithm for the automatic tuning of the hyperparameters. The novelty in this work comes in the form of modeling the problem of identifying attacks as a multi-objective optimization problem and the usage of linkage learning for solving the optimization problem. The solution is obtained using the feature map-based Convolutional Neural Network that gets encoded into genes, and using the extended compact genetic algorithm the model is optimized for the detection accuracy and latency. The CIC-IDS-2017 and 2018 datasets are used to verify the hypothesis, and the most recent analysis yielded a substantial F1 score of 99.23%. Response time, CPU, and memory consumption evaluations are done to demonstrate the suitability of this model in a fog environment.