• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.49-55
• /
• 2021

Recently, with the development of database, it is possible to store a lot of data generated in finance, security, and networks. These data are being analyzed through classifiers based on machine learning. The main problem at this time is data imbalance. When we train imbalanced data, it may happen that classification accuracy is degraded due to over-fitting with majority class data. To overcome the problem of data imbalance, oversampling strategy that increases the quantity of data of minority class data is widely used. It requires to tuning process about suitable method and parameters for data distribution. To improve the process, In this study, we propose a strategy to explore and optimize oversampling combinations and ratio based on various methods such as synthetic minority oversampling technique and generative adversarial networks through genetic algorithms. After sampling credit card fraud detection which is a representative case of data imbalance, with the proposed strategy and single oversampling strategies, we compare the performance of trained classifiers with each data. As a result, a strategy that is optimized by exploring for ratio of each method with genetic algorithms was superior to previous strategies.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.8
• /
• pp.993-998
• /
• 2020

The technology of interiors is currently developing around the world. According to various studies, the use of plants to create an environment in the home interior is increasing. However, households using furniture are designed as environment-friendly environment interiors, and in Korea and abroad, plants are used for home interiors. Unexpected accidents are occurring. As a result, there were books and broadcasts about the dangers of specific plants, but until now, accidents continue to occur because they do not properly recognize the dangers of specific plants. Therefore, in this paper, we propose a toxic plant identification system based on a multiplicative neural network model that identifies common toxic plants commonly found in Korea. We propose a high efficiency model. Through this, toxic plants can be identified with higher accuracy and safety accidents caused by toxic plants.

• Korean Journal of Agricultural Science
• /
• v.47 no.4
• /
• pp.933-940
• /
• 2020

Land-use change matrix data is important for calculating the LULUCF (land use, land use change and forestry) sector of the national greenhouse gas inventory. In this study, land cover changes in 2004 and 2019 were compared using the Wall-to-Wall technique with a land cover map of Sejong City from the Ministry of Environment. Sejong City was classified into six land use classes according to the Intergovernmental Panel on Climate Change (IPCC) guidelines: Forest land, crop land, grassland, wetland, settlement and other land. The coordinate system of the land cover maps of 2004 and 2019 were harmonized and the land use was reclassified. The results indicate that during the 15 years from 2004 to 2019 forestlands and croplands decreased from 50.4% (234.2 ㎢) and 34.6% (161.0 ㎢) to 43.4% (201.7 ㎢) and 20.7% (96.2 ㎢), respectively, while Settlement and Other land area increased significantly from 8.9% (41.1 ㎢) and 1.4% (6.9 ㎢) to 35.6% (119.0 ㎢) and 6.5% (30.3 ㎢). 79.㎢ of cropland area (96.2 ㎢) in 2019 was maintained as cropland, and 8.8 ㎢, 1.7 ㎢, 0.5 ㎢, 5.4 ㎢, and 0.4 ㎢ were converted from forestland, grassland, wetland, and settlement, respectively. This research, however, is subject to several limitations. The uncertainty of the land use change matrix when using the wall-to-wall technique depends on the accuracy of the utilized land cover map. Also, the land cover maps have different resolutions and different classification criteria for each production period. Despite these limitations, creating a land use change matrix using the Wall-to-Wall technique with a Land cover map has great advantages of saving time and money.

• Tunnel and Underground Space
• /
• v.31 no.1
• /
• pp.25-40
• /
• 2021

As the era of Industry 4.0 arrives, the researches using artificial intelligence in the field of rock engineering as well have increased. For a better understanding and availability of AI, this paper analyzed the types of algorithms and how to apply them to the research papers where AI is applied among domestic and international studies related to tunnels, blasting and mines that are major objects in which rock engineering techniques are applied. The analysis results show that the main specific fields in which AI is applied are rock mass classification and prediction of TBM advance rate as well as geological condition ahead of TBM in a tunnel field, prediction of fragmentation and flyrock in a blasting field, and the evaluation of subsidence risk in abandoned mines. Of various AI algorithms, an artificial neural network is overwhelmingly applied among investigated fields. To enhance the credibility and accuracy of a study result, an accurate and thorough understanding on AI algorithms that a researcher wants to use is essential, and it is expected that to solve various problems in the rock engineering fields which have difficulty in approaching or analyzing at present, research ideas using not only machine learning but also deep learning such as CNN or RNN will increase.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1123-1130
• /
• 2020

This study aims to classify the severity in car crashes using five classification learning models. The dataset used in this study contains 21,013 vehicle crashes, obtained from Korea Expressway Corporation, between the year of 2015-2017 and the LightGBM(Light Gradient Boosting Model) performed well with the highest accuracy. LightGBM, the number of involved vehicles, type of accident, incident location, incident lane type, types of accidents, types of vehicles involved in accidents were shown as priority factors. Based on the results of this model, the establishment of a management strategy for response of highway traffic accident should be presented through a consistent prediction process of accident severity level. This study identifies applicability of Machine Learning Models for Predicting of the Severity of Car Traffic Accidents on a Highway and suggests that various machine learning techniques based on big data that can be used in the future.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.319-328
• /
• 2021

Parallel administration of numerous drugs increases Drug-Drug Interaction (DDI) because one drug might affect the activity of other drugs. DDI causes negative or positive impacts on therapeutic output. So there is a need to discover DDI to enhance the safety of consuming drugs. Though there are several DDI system exist to predict an interaction but nowadays it becomes impossible to maintain with a large number of biomedical texts which is getting increased rapidly. Mostly the existing DDI system address classification issues, and especially rely on handcrafted features, and some features which are based on particular domain tools. The objective of this paper to predict DDI in a way to avoid adverse effects caused by the consumed drugs, to predict similarities among the drug, Drug pair similarity calculation is performed. The best optimal weight is obtained with the support of KHA. LSTM function with weight obtained from KHA and makes bets prediction of DDI. Our methodology depends on (LSTM-KHA) for the detection of DDI. Similarities among the drugs are measured with the help of drug pair similarity calculation. KHA is used to find the best optimal weight which is used by LSTM to predict DDI. The experimental result was conducted on three kinds of dataset DS1 (CYP), DS2 (NCYP), and DS3 taken from the DrugBank database. To evaluate the performance of proposed work in terms of performance metrics like accuracy, recall, precision, F-measures, AUPR, AUC, and AUROC. Experimental results express that the proposed method outperforms other existing methods for predicting DDI. LSTMKHA produces reasonable performance metrics when compared to the existing DDI prediction model.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1464-1475
• /
• 2020

Due to the spread of COVID-19, the online lecture has become more prevalent. However, it was found that a lot of students and professors are experiencing lack of communication. This study is therefore designed to improve interactive communication between professors and students in real-time online lectures. To do so, we explore deep learning approaches for automatic recognition of students' facial expressions and classification of their understanding into 3 classes (Understand / Neutral / Not Understand). We use 'BlazeFace' model for face detection and 'ResNet-GRU' model for facial expression recognition (FER). We name this entire process 'Degree of Understanding (DoU)' algorithm. DoU algorithm can analyze a multitude of students collectively and present the result in visualized statistics. To our knowledge, this study has great significance in that this is the first study offers the statistics of understanding in lectures using FER. As a result, the algorithm achieved rapid speed of 0.098sec/frame with high accuracy of 94.3% in CPU environment, demonstrating the potential to be applied to real-time online lectures. DoU Algorithm can be extended to various fields where facial expressions play important roles in communications such as interactions with hearing impaired people.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1224-1230
• /
• 2020

Since the spread of smart phones, interest in wearable devices has increased and diversified, and is closely related to the lives of users, and has been used as a method for providing personalized services. In this paper, we propose a method to detect the user's behavior by applying information from a 3-axis acceleration sensor and a 3-axis gyro sensor embedded in a smartphone to a convolutional neural network. Human behavior differs according to the size and range of motion, starting and ending time, including the duration of the signal data constituting the motion. Therefore, there is a performance problem for accuracy when applied to a convolutional neural network as it is. Therefore, we proposed a Time-Division Feature Fusion Convolutional Neural Network (TDFFCNN) that learns the characteristics of the sensor data segmented over time. The proposed method outperformed other classifiers such as SVM, IBk, convolutional neural network, and long-term memory circulatory neural network.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.2
• /
• pp.165-170
• /
• 2021

Machine learning has recently been applied to research in most areas. This is because the results of machine learning are not determined, but the learning of input data creates the objective function, which enables the determination of new data. In addition, the increase in accumulated data affects the accuracy of machine learning results. The data collected here is an important factor in machine learning. The proposed system is a convergence system of cloud systems and local fog systems for service delivery. Thus, the cloud system provides machine learning and infrastructure for services, while the fog system is located in the middle of the cloud and the user to collect and refine data. The data for this application shall be based on the Sensitive data generated by smart devices. The machine learning technique applied to this system uses SVM algorithm for classification and RNN algorithm for status recognition.

• Journal of Korea Game Society
• /
• v.21 no.4
• /
• pp.3-12
• /
• 2021

In this study, models for predicting the final result of League of Legends game were constructed for each rank using data from the first 10 minutes of the game. Variable importance was extracted from the prediction models to derive strategic direction in early phase of the game. As a result, it was possible to predict final results with over 70% accuracy in all ranks. It was found that early game advantage tends to lead to the final win and this tendency appeared stronger as it goes to challenger ranks. Kill(death) was found to be the most influential factor for win, however, there were also variables whose importance rank changed according to rank. This indicates there is a difference in the strategic direction in the early stage of the game depending on the rank.