• Journal of Bio-Environment Control
• /
• v.31 no.3
• /
• pp.255-260
• /
• 2022

This study aimed to develop a service model that uses a deep learning algorithm for detecting diseases and pests in strawberries through image data. In addition, the pest detection performance of deep learning models was further improved by proposing segmented image data sets specialized in disease and pest symptoms. The CNN-based YOLO deep learning model was selected to enhance the existing R-CNN-based model's slow learning speed and inference speed. A general image data set and a proposed segmented image dataset was prepared to train the pest and disease detection model. When the deep learning model was trained with the general training data set, the pest detection rate was 81.35%, and the pest detection reliability was 73.35%. On the other hand, when the deep learning model was trained with the segmented image dataset, the pest detection rate increased to 91.93%, and detection reliability was increased to 83.41%. This study concludes with the possibility of improving the performance of the deep learning model by using a segmented image dataset instead of a general image dataset.

• The Mathematical Education
• /
• v.62 no.2
• /
• pp.289-302
• /
• 2023

In today's digital information society, student knowledge and skills to analyze big data and make informed decisions have become an important goal of school mathematics. Integrating big data statistical projects with digital technologies in high school <Artificial Intelligence> mathematics courses has the potential to provide students with a learning experience of high impact that can develop these essential skills. This paper proposes a set of guidelines for designing effective big data statistical project-based tasks and evaluates the tasks in the artificial intelligence mathematics textbook against these criteria. The proposed guidelines recommend that projects should: (1) align knowledge and skills with the national school mathematics curriculum; (2) use preprocessed massive datasets; (3) employ data scientists' problem-solving methods; (4) encourage decision-making; (5) leverage technological tools; and (6) promote collaborative learning. The findings indicate that few textbooks fully align with these guidelines, with most failing to incorporate elements corresponding to Guideline 2 in their project tasks. In addition, most tasks in the textbooks overlook or omit data preprocessing, either by using smaller datasets or by using big data without any form of preprocessing. This can potentially result in misconceptions among students regarding the nature of big data. Furthermore, this paper discusses the relevant mathematical knowledge and skills necessary for artificial intelligence, as well as the potential benefits and pedagogical considerations associated with integrating technology into big data tasks. This research sheds light on teaching mathematical concepts with machine learning algorithms and the effective use of technology tools in big data education.

• Journal of the Korea Society for Simulation
• /
• v.19 no.1
• /
• pp.23-31
• /
• 2010

Due to the fact that fisheye lens can provide super wide angles with the minimum number of cameras, field-of-view over 180 degrees, many vehicles are attempting to mount the camera system. Not only use the camera as a viewing system, but also as a camera sensor, camera calibration should be preceded, and geometrical correction on the radial distortion is needed to provide the images for the driver's assistance. In this thesis, we introduce a geometric correction technique to minimize the loss of the image data from a vehicle fish-eye lens having a field of view over $180^{\circ}$, and a asymmetric distortion. Geometric correction is a process in which a camera model with a distortion model is established, and then a corrected view is generated after camera parameters are calculated through a calibration process. First, the FOV model to imitate a asymmetric distortion configuration is used as the distortion model. Then, we need to unify the axis ratio because a horizontal view of the vehicle fish-eye lens is asymmetrically wide for the driver, and estimate the parameters by applying a non-linear optimization algorithm. Finally, we create a corrected view by a backward mapping, and provide a function to optimize the ratio for the horizontal and vertical axes. This minimizes image data loss and improves the visual perception when the input image is undistorted through a perspective projection.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.649-654
• /
• 2023

This paper proposes the design of a neural network structure search model using graph convolutional neural networks. Deep learning has a problem of not being able to verify whether the designed model has a structure with optimized performance due to the nature of learning as a black box. The neural network structure search model is composed of a recurrent neural network that creates a model and a convolutional neural network that is the generated network. Conventional neural network structure search models use recurrent neural networks, but in this paper, we propose GC-NAS, which uses graph convolutional neural networks instead of recurrent neural networks to create convolutional neural network models. The proposed GC-NAS uses the Layer Extraction Block to explore depth, and the Hyper Parameter Prediction Block to explore spatial and temporal information (hyper parameters) based on depth information in parallel. Therefore, since the depth information is reflected, the search area is wider, and the purpose of the search area of the model is clear by conducting a parallel search with depth information, so it is judged to be superior in theoretical structure compared to GC-NAS. GC-NAS is expected to solve the problem of the high-dimensional time axis and the range of spatial search of recurrent neural networks in the existing neural network structure search model through the graph convolutional neural network block and graph generation algorithm. In addition, we hope that the GC-NAS proposed in this paper will serve as an opportunity for active research on the application of graph convolutional neural networks to neural network structure search.

• Journal of Life Science
• /
• v.33 no.6
• /
• pp.490-497
• /
• 2023

Pregnant women may need to take medications to treat preexisting diseases or diseases that develop during pregnancy. However, some drugs may be fetotoxic and lead to, for example, teratogenicity and growth retardation. Predicting the fetotoxicity of drugs is thus important for the health of the mother and fetus. The fetotoxicity of many drugs has not been established because various challenges hinder the ability of researchers to determine their fetotoxicity. The need exists for in silico-based fetotoxicity assessment models, as they can modernize the testing paradigm, improve predictability, and reduce the use of animals and the costs of fetotoxicity testing. In this study, we collected data on the fetotoxicity of drugs and constructed fetotoxicity prediction models based on various machine learning algorithms. We optimized the models for more precise predictions by tuning the hyperparameters. We then performed quantitative performance evaluations. The results indicated that the constructed machine learning-based models had high performance (AUROC >0.85, AUPR >0.9) in fetotoxicity prediction. We also analyzed the feature importance of our model's predictions, which could be leveraged to identify the specific features of drugs that are strongly associated with fetotoxicity. The proposed model can be used to prescreen drugs and drug candidates at a lower cost and in less time. It provides a predictive score for fetotoxicity risk, which may be beneficial in the design of studies on fetotoxicity in human pregnancy.

• 한국체육학회지인문사회과학편
• /
• v.57 no.6
• /
• pp.293-308
• /
• 2018

This study was carried out to investigate the current trends in skiing-related research from existing literature in the field of kinematics, measurement sensor and computer simulation. In the field of kinematics, research is being conducted on the mechanism of ski turn, posture analysis according to the grade and skill level of skiers, friction force of ski and snow, and air resistance. In the field of measurement sensor and computer simulation, researches are being conducted for researching and developing equipment using IMU sensor and GPS. The results of this study are as follows. First, beyond the limits of the existing kinematic analysis, it is necessary to develop measurement equipment that can analyze the entire skiing area and can be deployed with ease at the sports scene. Second, research on the accuracy of information obtained using measurement sensors and various analysis techniques based on these measures should be carried out continuously to provide data that can help the sports scene. Third, it is necessary to use computer simulation methods to clarify the injury mechanism and discover ways to prevent injuries related to skiing. Fourth, it is necessary to provide optimized ski trajectory algorithm by developing 3D ski model using computer simulation and comparing with actual skiing data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.171-173
• /
• 2022

The 4th industrial revolution technology is developing people's lives more efficiently. GIS provided on the Internet services such as traffic information and time information makes people getting more quickly to destination. National geographic information service(NGIS) and each local government are making basic data to investigate SOC accessibility for analyzing optimal point. To construct the shortest distance, the accessibility from the starting point to the arrival point is analyzed. Applying road network map, the starting point and the ending point, the shortest distance, the optimal accessibility is calculated by using Dijkstra algorithm. The analysis information from multiple starting points to multiple destinations was required more than 3 steps of manual analysis to decide the position for the optimal point, within about 0.1% error. It took more time to process the many-to-many (M×N) calculation, requiring at least 32G memory specification of the computer. If an optimal proximity analysis service is provided at a desired location more versatile, it is possible to efficiently analyze locations that are vulnerable to business start-up and living facilities access, and facility selection for the public.

• Journal of the Korean Society for information Management
• /
• v.40 no.4
• /
• pp.307-327
• /
• 2023

To analyze the impact of word embedding on book titles, this study utilized word embedding models (Word2vec, GloVe, fastText) to generate embedding vectors from book titles. These vectors were then used as classification features for automatic classification. The classifier utilized the k-nearest neighbors (kNN) algorithm, with the categories for automatic classification based on the DDC (Dewey Decimal Classification) main class 300 assigned by libraries to books. In the automatic classification experiment applying word embeddings to book titles, the Skip-gram architectures of Word2vec and fastText showed better results in the automatic classification performance of the kNN classifier compared to the TF-IDF features. In the optimization of various hyperparameters across the three models, the Skip-gram architecture of the fastText model demonstrated overall good performance. Specifically, better performance was observed when using hierarchical softmax and larger embedding dimensions as hyperparameters in this model. From a performance perspective, fastText can generate embeddings for substrings or subwords using the n-gram method, which has been shown to increase recall. The Skip-gram architecture of the Word2vec model generally showed good performance at low dimensions(size 300) and with small sizes of negative sampling (3 or 5).

• Clean Technology
• /
• v.29 no.4
• /
• pp.305-312
• /
• 2023

Due to the strengthening of environmental requirements, aging denitrification facilities need to improve their performance. The present study aims to suggest the possibility of improving performance using computational analysis techniques. This involved modifying both the geometric design and the operating conditions, including the flow path shape of the equipment such as the inlet guide vane and the curved diffusing part, and the flow control of the ammonia injection nozzle. The conditions presented in this study were compared with existing operating conditions in terms of the flow uniformity, the NH₃/NO molar ratio of the mixed gas flowing into the catalyst layer, and the total pressure drop of the facility. The flow field applied in the computational analysis ranged from the outlet of the economizer in the combustion furnace to the inlet of the air preheater, the full domain of the denitrification facility. The performances were derived by solving the flow fields using ANSYS-Fluent and the injection amount of ammonia was adjusted for each nozzle using Design Xplorer. Compared to the denitrification performances of the equipment currently in operation, the conditions proposed in this study showed an improvement in the flow uniformity and NH₃/NO composition ratio by 45.1% and 8.7%, respectively, but the total pressure drop increased by 1.24%.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.236-244
• /
• 2024

A representative problem in domestic chestnut industry is the high loss of flesh due to excessive knife peeling in order to increase the peeling rate, resulting in a decrease in production efficiency. In this study, a prediction model for weight loss rate of chestnut by stage of knife peeling process was developed as undergarment study to optimize conditions of the machine. 51 control conditions of the two-stage blade peeler used in the experiment were derived and repeated three times to obtain a total of 153 data. Machine learning(ML) models including artificial neural network (ANN) and random forest (RF) were implemented to predict the weight loss rate by chestnut peel stage (after 1st peeling, 2nd peeling, and after final discharge). The performance of the models were evaluated by calculating the values of coefficient of determination (R), normalized root mean square error (nRMSE), and mean absolute error (MAE). After all peeling stages, RF model have better prediction accuracy with higher R values and low prediction error with lower nRMSE and MAE values, compared to ANN model. The final selected RF prediction model showed excellent performance with insignificant error between the experimental and predicted values. As a result, the proposed model can be useful to set optimum condition of knife peeling for the purpose of minimizing the weight loss of domestic chestnut flesh with maximizing peeling rate.