• ETRI Journal
• /
• v.43 no.2
• /
• pp.288-298
• /
• 2021

Abstractive text summarization is a process of making a summary of a given text by paraphrasing the facts of the text while keeping the meaning intact. The manmade summary generation process is laborious and time-consuming. We present here a summary generation model that is based on multilayered attentional peephole convolutional long short-term memory (MAPCoL; LSTM) in order to extract abstractive summaries of large text in an automated manner. We added the concept of attention in a peephole convolutional LSTM to improve the overall quality of a summary by giving weights to important parts of the source text during training. We evaluated the performance with regard to semantic coherence of our MAPCoL model over a popular dataset named CNN/Daily Mail, and found that MAPCoL outperformed other traditional LSTM-based models. We found improvements in the performance of MAPCoL in different internal settings when compared to state-of-the-art models of abstractive text summarization.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.4
• /
• pp.126-129
• /
• 2020

We introduce a lifetime assessment technique using deep learning algorithm with complex electrical parameters such as resistivity, permittivity, impedance parameters as integrated indicators for predicting the degradation of the organic molecules. The evaluation system consists of fully automated in-situ measurement system and multiple layer perceptron learning system with five hidden layers and 1011 perceptra in each layer. Prediction accuracies are calculated and compared depending on the physical feature, learning hyperparameters. 62.5% of full time-series data are used for training and its prediction accuracy is estimated as r-square value of 0.99. Remaining 37.5% of the data are used for testing with prediction accuracy of 0.95. With k-fold cross-validation, the stability to the instantaneous changes in the measured data is also improved.

• Journal of the Korean Society of Systems Engineering
• /
• v.17 no.2
• /
• pp.91-97
• /
• 2021

User interface for cancer classification system is a software application with clinician's friendly tools and functions to diagnose cancer from pathology images. Pathology evolved from manual diagnosis to computer-aided diagnosis with the help of Artificial Intelligence tools and algorithms. In this paper, we explained each block of the project life cycle for the implementation of automated breast cancer classification software using AI and machine learning algorithms to classify normal and invasive breast histology images. The system was designed to help the pathologists in an automatic and efficient diagnosis of breast cancer. To design the classification model, Hematoxylin and Eosin (H&E) stained breast histology images were obtained from the ICIAR Breast Cancer challenge. These images are stain normalized to minimize the error that can occur during model training due to pathological stains. The normalized dataset was fed into the ResNet-34 for the classification of normal and invasive breast cancer images. ResNet-34 gave 94% accuracy, 93% F Score, 95% of model Recall, and 91% precision.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.168-174
• /
• 2022

The article defines the organizational conditions for effective management, the actions of the team to implement the concept of marketing management using the tools of pedagogical and strategic management. Due to this, results are achieved - indicators, since in our study they will be indicators of managerial efficiency: improving the "organization" function through the construction of new organizational structures; improving the functions of "analytical activity and planning" through enriching managerial work with economic and gnostic methods, analytical activities with the mandatory inclusion of financial activities, introspection of all participants, widespread use of licensed automated systems; synthesis of educational, economic, social results.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.627-630
• /
• 2022

Over the past few years, fake news has become one of the most significant problems. Since it is impossible to prevent people from spreading misinformation, people should analyze the news themselves. However, this process takes some time and effort, so the routine part of this analysis should be automated. There are many different approaches to this problem, but they only analyze the text and messages, ignoring the images. The fake news problem should be solved using a complex analysis tool to reach better performance. In this paper, we propose the approach of training an Artificial Intelligence using an unsupervised learning algorithm, combined with online data parsing tools, providing independence from subjective data set. Therefore it will be more difficult to spread fake news since people could quickly check if the news or article is trustworthy.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.248-251
• /
• 2015

High injury and fatality rates remain a serious problem in the construction industry. Many construction injuries and fatalities can be prevented if workers can recognize potential hazards and take actions in time. Many efforts have been devoted in improving workers' ability of hazard recognition through various safety training and education methods. However, a reliable approach for evaluating this ability is missing. Previous studies in the field of human behavior and phycology indicate that the visual focus of attention (VFOA) is a good indicator of worker's actual focus. Towards this direction, this study introduces an automated approach for estimating the VFOA of equipment operators using a head orientation-based VFOA estimation method. The proposed method is validated in a virtual reality scenario using an immersive head mounted display. Results show that the proposed method can effectively estimate the VFOA of test subjects in different test scenarios. The findings in this study broaden the knowledge of detecting the visual focus and distraction of construction workers, and envision the future work in improving work's ability of hazard recognition.

• ETRI Journal
• /
• v.46 no.4
• /
• pp.633-647
• /
• 2024

In e-commerce platforms, sentiment analysis on an enormous number of user reviews efficiently enhances user satisfaction. In this article, an automated product recommendation system is developed based on machine and deep-learning models. In the initial step, the text data are acquired from the Amazon Product Reviews dataset, which includes 60 000 customer reviews with 14 806 neutral reviews, 19 567 negative reviews, and 25 627 positive reviews. Further, the text data denoising is carried out using techniques such as stop word removal, stemming, segregation, lemmatization, and tokenization. Removing stop-words (duplicate and inconsistent text) and other denoising techniques improves the classification performance and decreases the training time of the model. Next, vectorization is accomplished utilizing the term frequency-inverse document frequency technique, which converts denoised text to numerical vectors for faster code execution. The obtained feature vectors are given to the modified convolutional neural network model for sentiment analysis on e-commerce platforms. The empirical result shows that the proposed model obtained a mean accuracy of 97.40% on the APR dataset.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.1 no.1
• /
• pp.19-24
• /
• 2009

It is necessary that the industry has to develop various automated control technology for efficient creation of manufacture automation system according to rapid market situation. One of the technologies is the fused complex control based on PLC-based controlled system. According to rapid growth and distribution of various automated control technologies using PLC, the engineers in automation, Production and manufacturing technologies fields have difficulties in systematic studying on the technologies by choosing an optimal route due to various industry-applied examples and ranges, in spite that the technology is essential. Therefore, the researchers indicate applied outputs and effects extracted by systematically developing systematic company-specified training program by analyzing education procedure drawbacks for S-company engineers.

• The Korean Journal of Physiology and Pharmacology
• /
• v.24 no.1
• /
• pp.89-99
• /
• 2020

Although microscopic analysis of tissue slides has been the basis for disease diagnosis for decades, intra- and inter-observer variabilities remain issues to be resolved. The recent introduction of digital scanners has allowed for using deep learning in the analysis of tissue images because many whole slide images (WSIs) are accessible to researchers. In the present study, we investigated the possibility of a deep learning-based, fully automated, computer-aided diagnosis system with WSIs from a stomach adenocarcinoma dataset. Three different convolutional neural network architectures were tested to determine the better architecture for tissue classifier. Each network was trained to classify small tissue patches into normal or tumor. Based on the patch-level classification, tumor probability heatmaps can be overlaid on tissue images. We observed three different tissue patterns, including clear normal, clear tumor and ambiguous cases. We suggest that longer inspection time can be assigned to ambiguous cases compared to clear normal cases, increasing the accuracy and efficiency of histopathologic diagnosis by pre-evaluating the status of the WSIs. When the classifier was tested with completely different WSI dataset, the performance was not optimal because of the different tissue preparation quality. By including a small amount of data from the new dataset for training, the performance for the new dataset was much enhanced. These results indicated that WSI dataset should include tissues prepared from many different preparation conditions to construct a generalized tissue classifier. Thus, multi-national/multi-center dataset should be built for the application of deep learning in the real world medical practice.

• Journal of Biomedical Engineering Research
• /
• v.26 no.5
• /
• pp.343-349
• /
• 2005

Continuously motivating people to exercise regularly is more important than finding a way out of barriers such as lack of time, cost of equipment, lack of nearby facilities, and poor weather. Our proposed system presents practicable methods of motivation through a diverse exercise aid system. The Health Improvement and Management System (all-in-one system which saves space and maintenance costs) measures and evaluates a diverse body shape analysis and physical fitness test and directs users to automated personalized exercise prescription which is prescribed by the expert system of three types of exercise templates: aerobics, anaerobics, and leisure sports. Automated personalized exercise prescriptions are built into XML based documents because the data needs to be in the form of flexible, expansible, and convertible structures in order to process various exercise templates, BIOFIT, a digital exercise trainer, monitors and provides feedback on the physiological parameters while users are working out in the gymnasium. If these parameters do not range within the prescribed target zone, the device will alarm users to control the exercise and make the exercise trainer adjust systemically the proper exercise level. Numeric health information such as the report of the physical fitness test and the exercise prescription makes people stay interested in exercising. In addition, this service can be delivered through the Internet.