• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.82-89
• /
• 2023

Various machine-learning models may yield high predictive power for massive time series for time series prediction. However, these models are prone to instability in terms of computational cost because of the high dimensionality of the feature space and nonoptimized hyperparameter settings. Considering the potential risk that model training with a high-dimensional feature set can be time-consuming, we evaluate a feature-importance-based feature selection method to derive a tradeoff between predictive power and computational cost for time series prediction. We used two machine learning techniques for performance evaluation to generate prediction models from a retail sales dataset. First, we ranked the features using impurity- and Local Interpretable Model-agnostic Explanations (LIME) -based feature importance measures in the prediction models. Then, the recursive feature elimination method was applied to eliminate unimportant features sequentially. Consequently, we obtained a subset of features that could lead to reduced model training time while preserving acceptable model performance.

• Korean Management Science Review
• /
• v.13 no.3
• /
• pp.173-186
• /
• 1996

This paper presents an approach for classifying scheduling problems and selecting a heuristic rule to yield best solution in terms of certain performance measure(s). Classification parameters are employed from previous studies on job shop scheduling and project scheduling. Neural network is used for learning and estimating the performance of heuristic rules. In addition, multi-criteria decision making techniques are employed to combine the preferences for each performance measure and heuristic rule for the problems with multi-objectives.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1197-1205
• /
• 2018

In this paper, we perform Single Image Super Resolution(SISR) for acquired images of EOTS or IRST from naval combat system. In order to conduct super resolution, we use Generative Adversarial Networks(GANs), which consists of a generative model to create a super-resolution image from the given low-resolution image and a discriminative model to determine whether the generated super-resolution image is qualified as a high-resolution image by adjusting various learning parameters. The learning parameters consist of a crop size of input image, the depth of sub-pixel layer, and the types of training images. Regarding evaluation method, we apply not only general image quality metrics, but feature descriptor methods. As a result, a larger crop size, a deeper sub-pixel layer, and high-resolution training images yield good performance.

• Journal of Digital Contents Society
• /
• v.6 no.4
• /
• pp.209-216
• /
• 2005

The aim of this study is to examine the effects of web-based cyber instruction on EFL learning from the viewpoint of learners` perceptions and needs. Data was collected through a questionnaire survey that was carried out with 709 undergraduate student enrolled in three cyber English courses offered at N university during the secind semester in 2004. The results of the study indicated that the learners exhibited a positive attitude towards web-based cyber instruction and considered it a paper educational method in the cyber age. However, the students perceived that web-based cyber instruction was not greatly satisfactory in terms of cultivating their English communicative competence or improving the language skills they needed. It was also found that cyber instruction was still teacher-dominant, lacking in interaction, which made the students passive recipients of informaton presented. In comparison with off-line instruction, cyber instruction was not particularly better in enhancing their motivation interest or concentration on class. To be more effective, cyber instruction needs to be equipped not only with a large variety of contents and class activities, but also with more exposure to authentic language by native English speakers. The finding of the investigation yield some implications for the design and development of web-based cyber EFL programs.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.1
• /
• pp.49-59
• /
• 2019

Generative adversarial networks(GANs) have received great attention in the machine learning field for their capacity to model high-dimensional and complex data distribution implicitly and generate new data samples from the model distribution. This paper investigates the model training methodology, architecture, and various applications of generative adversarial networks. Experimental evaluation is also conducted for generating synthetic image dataset for defense using two types of GANs. The first one is for military image generation utilizing the deep convolutional generative adversarial networks(DCGAN). The other is for visible-to-infrared image translation utilizing the cycle-consistent generative adversarial networks(CycleGAN). Each model can yield a great diversity of high-fidelity synthetic images compared to training ones. This result opens up the possibility of using inexpensive synthetic images for training neural networks while avoiding the enormous expense of collecting large amounts of hand-annotated real dataset.

• Journal of Information Processing Systems
• /
• v.17 no.6
• /
• pp.1115-1126
• /
• 2021

Plant disease is one of the most irritating problems for agriculture growers. Thus, timely detection of plant diseases is of high importance to practical value, and corresponding measures can be taken at the early stage of plant diseases. Therefore, numerous researchers have made unremitting efforts in plant disease identification. However, this problem was not solved effectively until the development of artificial intelligence and big data technologies, especially the wide application of deep learning models in different fields. Since the symptoms of plant diseases mainly appear visually on leaves, computer vision and machine learning technologies are effective and rapid methods for identifying various kinds of plant diseases. As one of the fruits with the highest nutritional value, apple production directly affects the quality of life, and it is important to prevent disease intrusion in advance for yield and taste. In this study, an improved deep residual network is proposed for apple leaf disease identification in a novel way, a global residual connection is added to the original residual network, and the local residual connection architecture is optimized. Including that 1,977 apple leaf disease images with three categories that are collected in this study, experimental results show that the proposed method has achieved 98.74% top-1 accuracy on the test set, outperforming the existing state-of-the-art models in apple leaf disease identification tasks, and proving the effectiveness of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.2018-2043
• /
• 2022

Nowadays, COVID-19 infections are influencing our daily lives which have spread globally. The major symptoms' of COVID-19 are dry cough, sore throat, and fever which in turn to critical complications like multi organs failure, acute respiratory distress syndrome, etc. Therefore, to hinder the spread of COVID-19, a Computerized Doughty Predictor Framework (CDPF) is developed to yield benefits in monitoring the progression of disease from Chest CT images which will reduce the mortality rates significantly. The proposed framework CDPF employs Convolutional Neural Network (CNN) as a feature extractor to extract the features from CT images. Subsequently, the extracted features are fed into the Adaptive Dragonfly Algorithm (ADA) to extract the most significant features which will smoothly drive the diagnosing of the COVID and Non-COVID cases with the support of Doughty Learners (DL). This paper uses the publicly available SARS-CoV-2 and Github COVID CT dataset which contains 2482 and 812 CT images with two class labels COVID⁺ and COVI^-. The performance of CDPF is evaluated against existing state of art approaches, which shows the superiority of CDPF with the diagnosis accuracy of about 99.76%.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.966-977
• /
• 2021

Filterbank multicarrier with offset quadrature amplitude modulation (FBMC-OQAM) is an attractive alternative to the orthogonal frequency division multiplexing (OFDM) modulation technique. In comparison with OFDM, the FBMC-OQAM signal has better spectral confinement and higher spectral efficiency and tolerance to synchronization errors, primarily due to per-subcarrier filtering using a frequency-time localized prototype filter. However, the filtering process introduces intrinsic interference among the symbols and complicates channel estimation (CE). An efficient way to improve the CE in FBMC-OQAM is using a technique known as windowed frequency domain averaging (FDA); however, it requires a priori knowledge of the window length parameter which is set based on the channel's frequency selectivity (FS). As the channel's FS is not fixed and not a priori known, we propose a k-nearest neighbor-based machine learning algorithm to classify the FS and decide on the FDA's window length. A comparative theoretical analysis of the mean-squared error (MSE) is performed to prove the proposed CE scheme's effectiveness, validated through extensive simulations. The adaptive CE scheme is shown to yield a reduction in CE-MSE and improved bit error rates compared with the popular preamble-based CE schemes for FBMC-OQAM, without a priori knowledge of channel's frequency selectivity.

• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.28 no.3
• /
• pp.237-244
• /
• 2022

Onions are a significant crop in Korea, and cultivation is increasing every year along with high demand. Onions are planted in the fall and mainly harvested in June, the rainy season, therefore, physiological changes in onion bulbs during long-term storage might have happened. Onions are stored in cold room and at adequate relative humidity to avoid quality loss. In this study, bio-yield stress and weight loss were measured as the quality parameters of net packaged onions during 10 weeks of storage, and the storage environmental conditions are monitored using sensor networks systems. Quality estimation of net packaged onion during storage was performed using the storage environmental condition data through machine learning approaches. Among the suggested estimation models, support vector regression method showed the best accuracy for the quality estimation of net packaged onions.

• Computers and Concrete
• /
• v.31 no.4
• /
• pp.307-314
• /
• 2023

In this paper we back-analyze a failure event of a 9 m high concrete cantilever wall subjected to earth loading. Granular soil was deposited into the space between the wall and a nearby rock slope. The wall segments were not designed to carry lateral earth loading and collapsed due to excessive bending. As many geotechnical programs rely on the Mohr-Coulomb (MC) criterion for elastoplastic analysis, it is useful to apply this failure criterion to the concrete material. Accordingly, the back-analysis is aimed to search for the suitable MC parameters of the concrete. For this study, we propose a methodology for accelerating the back-analysis task by automating the numerical modeling procedure and applying a machine-learning (ML) analysis on FE model results. Through this analysis it is found that the residual cohesion and friction angle have a highly significant impact on model results. Compared to traditional back-analysis studies where good agreement between model and reality are deemed successful based on a limited number of models, the current ML analysis demonstrate that a range of possible combinations of parameters can yield similar results. The proposed methodology can be modified for similar calibration and back-analysis tasks.