• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.208-216
• /
• 2023

The purpose of our study is to design datasets for Artificial Intelligence learning for cold sea fish farming. Salmon is considered one of the most popular fish species among men and women of all ages, but most supplies depend on imports. Recently, salmon farming, which is rapidly emerging as a specialized industry in Gangwon-do, has attracted attention. Therefore, in order to successfully develop salmon farming, the need to systematically build data related to salmon and salmon farming and use it to develop aquaculture techniques is raised. Meanwhile, the catch of pollack continues to decrease. Efforts should be made to improve the major factors affecting pollack survival based on data, as well as increasing the discharge volume for resource recovery. To this end, it is necessary to systematically collect and analyze data related to pollack catch and ecology to prepare a sustainable resource management strategy. Image data was obtained using CCTV and underwater cameras to establish an intelligent aquaculture strategy for salmon and pollock, which are considered representative fish species in Gangwon-do. Using these data, we built learning data suitable for AI analysis and prediction. Such data construction can be used to develop models for predicting the growth of salmon and pollack, and to develop algorithms for AI services that can predict water temperature, one of the key variables that determine the survival rate of pollack. This in turn will enable intelligent aquaculture and resource management taking into account the ecological characteristics of fish species. These studies look forward to achievements on an important level for sustainable fisheries and fisheries resource management.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.6
• /
• pp.315-324
• /
• 2022

The experimental data obtained in a wave flume were analyzed using machine learning techniques to establish a model that predicts the input wave height of the wavemaker based on the waves that have experienced wave shoaling and to verify the performance of the established model. For this purpose, artificial neural network (NN), the most representative machine learning technique, and Gaussian process regression (GPR), one of the non-parametric regression analysis methods, were applied respectively. Then, the predictive performance of the two models was compared. The analysis was performed independently for the case of using all the data at once and for the case by classifying the data with a criterion related to the occurrence of wave breaking. When the data were not classified, the error between the input wave height at the wavemaker and the measured value was relatively large for both the NN and GPR models. On the other hand, if the data were divided into non-breaking and breaking conditions, the accuracy of predicting the input wave height was greatly improved. Among the two models, the overall performance of the GPR model was better than that of the NN model.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.165-184
• /
• 2023

Recently, Deep learning analysis of unstructured text data using language models, such as Google's BERT and OpenAI's GPT has shown remarkable results in various applications. Most language models are used to learn generalized linguistic information from pre-training data and then update their weights for downstream tasks through a fine-tuning process. However, some concerns have been raised that privacy may be violated in the process of using these language models, i.e., data privacy may be violated when data owner provides large amounts of data to the model owner to perform fine-tuning of the language model. Conversely, when the model owner discloses the entire model to the data owner, the structure and weights of the model are disclosed, which may violate the privacy of the model. The concept of offsite tuning has been recently proposed to perform fine-tuning of language models while protecting privacy in such situations. But the study has a limitation that it does not provide a concrete way to apply the proposed methodology to text classification models. In this study, we propose a concrete method to apply offsite tuning with an additional classifier to protect the privacy of the model and data when performing multi-classification fine-tuning on Korean documents. To evaluate the performance of the proposed methodology, we conducted experiments on about 200,000 Korean documents from five major fields, ICT, electrical, electronic, mechanical, and medical, provided by AIHub, and found that the proposed plug-in model outperforms the zero-shot model and the offsite model in terms of classification accuracy.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1421-1429
• /
• 2017

Human activity recognition has been studied using various sensors and algorithms. Human activity recognition can be divided into sensor based and vision based on the method. In this paper, we proposed an activity recognition system using acceleration sensor and gyroscope sensor in smartphone among sensor based methods. We used Deep Belief Network (DBN), which is one of the most popular deep learning methods, to improve an accuracy of human activity recognition. DBN uses the entire input set as a common input. However, because of the characteristics of different time window depending on the type of human activity, the RBMs, which is a component of DBN, are configured hierarchically by combining them from different time windows. As a result of applying to real data, The proposed human activity recognition system showed stable precision.

• Journal of the Korean Society of Visualization
• /
• v.19 no.1
• /
• pp.68-73
• /
• 2021

In this study, the detection of rubber o-ring defects was carried out using k-fold cross validation and Support Vector Machine (SVM) algorithm. The data process was carried out in 3 steps. First, we proceeded with a frame alignment to eliminate unnecessary regions in the learning and secondly, we applied gray-scale changes for computational reduction. Finally, data processing was carried out using image augmentation to prevent data overfitting. After processing data, SVM algorithm was used to obtain normal and defect detection accuracy. In addition, we applied the SVM algorithm through the k-fold cross validation method to compare the classification accuracy. As a result, we obtain results that show better performance by applying the k-fold cross validation method.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.4
• /
• pp.228-239
• /
• 2022

Many countries around the world using ICT technologies have various technologies to keep pace with the 4th industrial revolution, and various algorithms and systems have been developed accordingly. Among them, many industries and researchers are investing in unmanned automation systems based on AI. At the time when new technology development and algorithms are developed, decision-making by big data analysis applied to AI systems must be equipped with more sophistication. We apply, Pearson's correlation analysis is applied to six independent variables to find out the job satisfaction that office workers feel according to their job characteristics. First, a correlation coefficient is obtained to find out the degree of correlation for each variable. Second, the presence or absence of correlation for each data is verified through hypothesis testing. Third, after visualization processing using the size of the correlation coefficient, the degree of correlation between data is investigated. Fourth, the degree of correlation between variables will be verified based on the correlation coefficient obtained through the experiment and the results of the hypothesis test

• Journal of Platform Technology
• /
• v.9 no.3
• /
• pp.63-69
• /
• 2021

Limited materials to make coins for countries and designs suitable for hand-carry make the shape, size, and color of coins similar. This similarity makes that it is difficult for visitors to identify each country's coins. To solve this problem, we propose the coin classification method using CNN effective to image processing. In our coin identification method, we collect the training data by using web crawling and use OpenCV for preprocessing. After preprocessing, we extract features from an image by using three CNN layers and classify coins by using two fully connected network layers. To show that our model designed in this paper is effective for coin classification, we evaluate our model using eight different coin types. From our experimental results, the accuracy for coin classification is about 99.5%.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.11-29
• /
• 2022

Pre-trained language models are the most important and widely used tools in natural language processing tasks. Since those have been pre-trained for a large amount of corpus, high performance can be expected even with fine-tuning learning using a small number of data. Since the elements necessary for implementation, such as a pre-trained tokenizer and a deep learning model including pre-trained weights, are distributed together, the cost and period of natural language processing has been greatly reduced. Transformer variants are the most representative pre-trained language models that provide these advantages. Those are being actively used in other fields such as computer vision and audio applications. In order to make it easier for researchers to understand the pre-trained language model and apply it to natural language processing tasks, this paper describes the definition of the language model and the pre-learning language model, and discusses the development process of the pre-trained language model and especially representative Transformer variants.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.47-53
• /
• 2023

Recently, research on a smart farm that creates new values by combining information and communication technology(ICT) with agriculture has been actively done. In order for domestic smart farm technology to have productivity at the same level of advanced agricultural countries, automated decision-making using machine learning is necessary. However, current smart greenhouse data collection technologies in our country are not enough to perform big data analysis or machine learning. In this paper, we design and implement a smart greenhouse data preprocessing system for autonomous machine learning. The proposed system applies target data to various preprocessing techniques. And the proposed system evaluate the performance of each preprocessing technique and store optimal preprocessing technique for each data. Stored optimal preprocessing techniques are used to perform preprocessing on newly collected data

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.355-363
• /
• 2022

Korea is pursuing a plan to switch and expand energy sources with a focus on renewable energy with the goal of becoming carbon neutral by 2050. As the instability of energy supply increases due to the intermittent nature of renewable energy, accurate prediction of the amount of renewable energy generation is becoming more important. Therefore, the government has opened a small-scale power brokerage market and is implementing a system that pays settlements according to the accuracy of renewable energy prediction. In this paper, a prediction model was implemented using a statistical model and an artificial intelligence model for the prediction of solar power generation. In addition, the results of prediction accuracy were compared and analyzed, and the revenue from the settlement amount of the renewable energy generation forecasting system was estimated.