• Corrosion Science and Technology
• /
• v.20 no.2
• /
• pp.62-68
• /
• 2021

Artificial neural network techniques show an excellent ability to predict the data (output) for various complex characteristics (input). It is primarily specialized to solve nonlinear relationship problems. This study is an experimental investigation that applies artificial neural network techniques and an experimental design to predict the cyclic polarization curves of the super-austenitic stainless steel AL-6XN alloy with sensitization. A cyclic polarization test was conducted in a 3.5% NaCl solution based on an experimental design matrix with various factors (degree of sensitization, temperature, pH) and their levels, and a total of 36 cyclic polarization data were acquired. The 36 cyclic polarization patterns were used as training data for the artificial neural network model. As a result, the supervised learning algorithms with back-propagation showed high learning and prediction performances. The model showed an excellent training performance (R²=0.998) and a considerable prediction performance (R²=0.812) for the conditions that were not included in the training data.

• Journal of Korea Multimedia Society
• /
• v.22 no.1
• /
• pp.1-9
• /
• 2019

Single image rain removal is a typical inverse problem which decomposes the image into a background scene and a rain streak. Recent works have witnessed a substantial progress on the task due to the development of convolutional neural network (CNN). However, existing CNN-based approaches train the network with synthetically generated training examples. These data tend to make the network bias to the synthetic scenes. In this paper, we present an unsupervised framework for removing rain streaks from real-world rainy images. We focus on the natural phenomena that static rainy scenes capture a common background but different rain streak. From this observation, we train siamese network with the real rain image pairs, which outputs identical backgrounds from the pairs. To train our network, a real rainy dataset is constructed via web-crawling. We show that our unsupervised framework outperforms the recent CNN-based approaches, which are trained by supervised manner. Experimental results demonstrate that the effectiveness of our framework on both synthetic and real-world datasets, showing improved performance over previous approaches.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1778-1799
• /
• 2022

Automatic text summarization is a procedure that packs enormous content into a more limited book that incorporates significant data. Malayalam is one of the toughest languages utilized in certain areas of India, most normally in Kerala and in Lakshadweep. Natural language processing in the Malayalam language is relatively low due to the complexity of the language as well as the scarcity of available resources. In this paper, a way is proposed to deal with the text summarization process in Malayalam documents by training a model based on the Support Vector Machine classification algorithm. Different features of the text are taken into account for training the machine so that the system can output the most important data from the input text. The classifier can classify the most important, important, average, and least significant sentences into separate classes and based on this, the machine will be able to create a summary of the input document. The user can select a compression ratio so that the system will output that much fraction of the summary. The model performance is measured by using different genres of Malayalam documents as well as documents from the same domain. The model is evaluated by considering content evaluation measures precision, recall, F score, and relative utility. Obtained precision and recall value shows that the model is trustable and found to be more relevant compared to the other summarizers.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.47 no.4
• /
• pp.666-683
• /
• 2023

This research aims to develop based clothing design process tailored to the industry-university collaborative setting and apply it in a fashion design class. into three distinct phases: designing and organizing our fashion design class, conducting our class at a university, and gathering student feedback. First, we conducted a literature review on employing new technologies in traditional clothing design processes. We consulted with industry professionals from the Samsung C&T Fashion Group to develop an AI-based clothing design process. We then developed in-class learning activities that leveraged fashion brand product databases, a supervised learning AI model, and operating an AI-based Creativity Support Tool (CST). Next, we setup an industry-university fashion design class at a university in South Korea. Finally, we obtained feedback from undergraduate students who participated in the class. The survey results showed a satisfaction level of 4.7 out of 5. The evaluations confirmed that the instructional methods, communication, faculty, and student interactions within the class were both adequate and appropriate. These research findings highlighted that our AI-based clothing design process applied within the fashion design class led to valuable data-driven convergent thinking and technical experience beyond that of traditional clothing design processes.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.443-452
• /
• 2020

Worker's awkward postures and unreasonable physical load can be corrected by monitoring construction activities, thereby increasing the safety and productivity of construction workers and projects. However, manual identification is time-consuming and contains high human variance. In this regard, an automated activity recognition system based on inertial measurement unit can help in rapidly and precisely collecting motion data. With the acceleration data, the machine learning algorithm will be used to train classifiers for automatically categorizing activities. However, input acceleration data are extracted either from designed experiments or simple construction work in previous studies. Thus, collected data series are discontinuous and activity categories are insufficient for real construction circumstances. This study aims to collect acceleration data during long-term continuous work in a construction project and validate the feasibility of activity recognition algorithm with the continuous motion data. The data collection covers two different workers performing formwork at the same site. An accelerator, as well as portable camera, is attached to the worker during the entire working session for simultaneously recording motion data and working activity. The supervised machine learning-based models are trained to classify activity in hierarchical levels, which reaches a 96.9% testing accuracy of recognizing rest and work and 85.6% testing accuracy of identifying stationary, traveling, and rebar installation actions.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.31-34
• /
• 2023

주택 매매에 있어서 가격에 대한 예측은 매우 중요하지만, 실거래 발생 전까지는 정확한 가격을 알 수 없다. 그렇기에 주택가격을 예측하는 많은 연구가 진행되어왔다. 주택가격을 결정하는 영향요인은 크게 주택의 내부요인과 주택의 외부 요인으로 구분되는데, 내부적인 요인 (공급면적, 전용면적, 층, 방 개수 등)에 대한 연구가 많이 진행되었다. 하지만 외부적인 요인 (위치 요인, 금융요인 등)에 대한 연구는 미비하였다. 본 연구는 주택 매수자 관점에서 가격 예측 시 외부적인 요인 역시 중요하다고 판단하여 외부요인을 적용하고자 한다. 본 논문에서 제안하는 방법은 다양한 외부요인 중 주택의 위치 정보를 활용하여, 해당 정보 기반으로 도출 가능한 데이터를 추가한다. 또한 이용량에 따른 지하철역 데이터를 추가하여 관련된 여러 영향요인들을 분석 및 적용 후 머신러닝 기반 예측 모델을 생성한다. 생성된 모델들에 주택매매 실거래 데이터를 적용하여 예측 정확도를 비교 후 높은 정확성을 보이는 모델 결과에 주요하게 영향을 끼치는 요인에 관하여 기술한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2883-2902
• /
• 2023

Since the existing anti-jamming methods, including intelligent methods, have difficulty against high-speed reactive jamming, we studied a new methodology for jamming utilization instead of avoiding jamming. Different from the existing jamming utilization techniques that harvest energy from the jamming signal as a power supply, our proposed method can take the jamming signal as a favorable factor for frequency detection. Specifically, we design an intelligent differential frequency hopping communication framework (IDFH), which contains two stages of training and communication. We first adopt supervised learning to get the jamming rule during the training stage when the synchronizing sequence is sent. And then, we utilize the jamming rule to improve the frequency detection during the communication stage when the real payload is sent. Simulation results show that the proposed method successfully combated high-speed reactive jamming with different parameters. And the communication performance increases as the power of the jamming signal increase, hence the jamming signal can help users communicate in a low signal-to-noise ratio (SNR) environment.

• The Journal of Korean Association of Computer Education
• /
• v.20 no.1
• /
• pp.87-97
• /
• 2017

Recently, much research has been done on the turnover and retirement intentions of the organization members as many companies recognize the negative impact of the human resource outflow on the organization. However, most of the studies are conducted in the form of questionnaires, and there is still a lack of studies on the turnover and retirement intentions based on the work life data. In this study, we analyzed the factors affecting the retirement of employees based on the work life profile, and created a retirement prediction model using the machine learning method. As a result, we could identify various factors that were not covered in previous researches. In addition, we have established a basis for research that can provide a solution for the problem of human resource outflow by generating a good performance retirement prediction model.

• Journal of KIISE:Software and Applications
• /
• v.34 no.2
• /
• pp.160-168
• /
• 2007

For developing a text classifier using supervised learning, a manually labeled corpus of large size is required. However, it takes a lot of time and human effort. Recently a research paradigm was proposed to use a raw corpus and a small amount of seed information instead of manually labeled corpus. In this paper we introduce an unsupervised learning method that makes it possible to achieve better performance than other related works. The characteristics of our approach is that average mutual information is used to learn representative words and their weights and then update of the weights is done using a technique inspired by the works in information retrieval. By iterating this teaming process it was shown that a high performance system can be developed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.11
• /
• pp.2037-2042
• /
• 2017

The manufacturing facility is generally operated by a pre-set program under the existing factory automation system. On the other hand, the manufacturing facility must decide how to operate autonomously in Industry 4.0. Determining the operation mode of the production facility itself means, for example, that it detects the abnormality such as the deterioration of the facility at the shop-floor, prediction of the occurrence of the problem, detection of the defect of the product, In this paper, we propose a manufacturing process modeling using a queue for detection of manufacturing process abnormalities at the shop-floor, and detect abnormalities in the modeling using SVM, one of the machine learning techniques. The queue was used for M / D / 1 and the conveyor belt manufacturing system was modeled based on ${\mu}$, ${\lambda}$, and ${\rho}$. SVM was used to detect anomalous signs through changes in ${\rho}$.