• Korean Journal of Remote Sensing
• /
• v.37 no.6_3
• /
• pp.1923-1929
• /
• 2021

Earth observation satellites are being used in various field and are being developed in many countries due to their high utility and marketability. Korea is developing various Earth observation satellites according to National Space Development Plan. Among them, the Korea Multi-Purpose Satellite(KOMPSAT) series is the most representative low-orbit satellite. So far, a total of five KOMPSAT have been launched to meet the national image demand and have been used in various fields, including national institutions. This special issue introduces research related to data processing, analysis, and utilization using various image data from the KOMPSAT series. Meanwhile, for the uninterrupted utilization of the subsequent KOMPSAT image data, data processing and utilization research suitable for high-resolution images must be continued, and related research contents will be continuously shared through a special issue.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.4
• /
• pp.785-794
• /
• 2019

Recently Deep Learning technology, one of the fourth industrial revolution technologies, is used to identify the hidden meaning of network data that is difficult to detect in the security arena and to predict attacks. Property and quality analysis of data sources are required before selecting the deep learning algorithm to be used for intrusion detection. This is because it affects the detection method depending on the contamination of the data used for learning. Therefore, the characteristics of the data should be identified and the characteristics selected. In this paper, the characteristics of malware were analyzed using network data set and the effect of each feature on performance was analyzed when the deep learning model was applied. The traffic classification experiment was conducted on the comparison of characteristics according to network characteristics and 96.52% accuracy was classified based on the selected characteristics.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.15-22
• /
• 2019

Recent technological advances in three-dimensional (3D) sensing devices and machine learning such as deep leaning has enabled data-driven 3D applications. Research on artificial intelligence has developed for the past few years and 3D deep learning has been introduced. This is the result of the availability of high-quality big data, increases in computing power, and development of new algorithms; before the introduction of 3D deep leaning, the main targets for deep learning were one-dimensional (1D) audio files and two-dimensional (2D) images. The research field of deep leaning has extended from discriminative models such as classification/segmentation/reconstruction models to generative models such as those including style transfer and generation of non-existing data. Unlike 2D learning, it is not easy to acquire 3D learning data. Although low-cost 3D data acquisition sensors have become increasingly popular owing to advances in 3D vision technology, the generation/acquisition of 3D data is still very difficult. Even if 3D data can be acquired, post-processing remains a significant problem. Moreover, it is not easy to directly apply existing network models such as convolution networks owing to the various ways in which 3D data is represented. In this paper, we summarize technological trends in AI-based 3D content generation.

• Journal of information and communication convergence engineering
• /
• v.17 no.1
• /
• pp.74-83
• /
• 2019

This study designs a squat posture recognition system that can provide correct squat posture guidelines. This system comprises two modules: a Kinect camera for monitoring users' body movements and a Wii Balance Board(WBB) for measuring balanced postures with legs. Squat posture recognition involves two states: "Stand" and "Squat." Further, each state is divided into two postures: correct and incorrect. The incorrect postures of the Stand and Squat states were classified into three and two different types of postures, respectively. The factors that determine whether a posture is incorrect or correct include the difference between shoulder width and ankle width, knee angle, and coordinate of center of pressure(CoP). An expert and 10 participants participated in experiments, and the three factors used to determine the posture were measured using both Kinect and WBB. The acquired data from each device show that the expert's posture is more stable than that of the subjects. This data was classified using a support vector machine (SVM) and $na{\ddot{i}}ve$ Bayes classifier. The classification results showed that the accuracy achieved using the SVM and $na{\ddot{i}}ve$ Bayes classifier was 95.61% and 81.82%, respectively. Therefore, the developed system that used Kinect and WBB could classify correct and incorrect postures with high accuracy. Unlike in other studies, we obtained the spatial coordinates using Kinect and measured the length of the body. The balance of the body was measured using CoP coordinates obtained from the WBB, and meaningful results were obtained from the measured values. Finally, the developed system can help people analyze the squat posture easily and conveniently anywhere and can help present correct squat posture guidelines. By using this system, users can easily analyze the squat posture in daily life and suggest safe and accurate postures.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3708-3728
• /
• 2021

Indian herbal plants are used in agriculture and in the food, cosmetics, and pharmaceutical industries. Laboratory-based tests are routinely used to identify and classify similar herb species by analyzing their internal cell structures. In this paper, we have applied computer vision techniques to do the same. The original leaf image was preprocessed using the Chan-Vese active contour segmentation algorithm to efface the background from the image by setting the contraction bias as (v) -1 and smoothing factor (µ) as 0.5, and bringing the initial contour close to the image boundary. Thereafter the segmented grayscale image was fed to a leaky capacitance fired neuron model (LCFN), which differentiates between similar herbs by combining different groups of pixels in the leaf image. The LFCN's decay constant (f), decay constant (g) and threshold (h) parameters were empirically assigned as 0.7, 0.6 and h=18 to generate the 1D feature vector. The LCFN time sequence identified the internal leaf structure at different iterations. Our proposed framework was tested against newly collected herbal species of natural images, geometrically variant images in terms of size, orientation and position. The 1D sequence and shape features of aloe, betel, Indian borage, bittergourd, grape, insulin herb, guava, mango, nilavembu, nithiyakalyani, sweet basil and pomegranate were fed into the 5-fold Bayesian regularization neural network (BRNN), K-nearest neighbors (KNN), support vector machine (SVM), and ensemble classifier to obtain the highest classification accuracy of 91.19%.

• Journal of Korean Society of Archives and Records Management
• /
• v.19 no.4
• /
• pp.221-230
• /
• 2019

This paper aims to introduce the case of operating electronic document system and record management system as one system called i-Works at Korea Midland Power Company. i-Works combines intelligent services, such as artificial intelligence and a chatbot, as a supplementary tool for record management. As such, the preparation process and progress direction for the development of the record management system is introduced, an in-depth review of real-time transfer and utilization of the functional classification system to enhance the utilization of the current records is presented, and new technologies, such as artificial intelligence for an efficient management of the increasing number of electronic records, are established.

• Journal of Cadastre & Land InformatiX
• /
• v.50 no.2
• /
• pp.37-51
• /
• 2020

With the development of machine learning and deep learning technologies, there has been increasing interest and attempt to apply these technologies to the detection of urban changes. However, the traditional methods of detecting changes and constructing spatial information are still often performed manually by humans, which is costly and time-consuming. Besides, a large number of people are needed to efficiently detect changes in buildings in urban areas. Therefore, in this study, a methodology that can detect changes by classifying road, building, and vegetation objects that are highly utilized in the geospatial information field was proposed by applying deep learning technology to point clouds. As a result of the experiment, roads, buildings, and vegetation were classified with an accuracy of 92% or more, and attributes information of the objects could be automatically constructed through this. In addition, if time-series data is constructed, it is thought that changes can be detected and attributes of existing digital maps can be inspected through the proposed methodology.

• 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.

• Resources Recycling
• /
• v.30 no.4
• /
• pp.3-10
• /
• 2021

The field of recycling for waste electronic components, which is the typical example of an urban mine, requires the development of useful sorting techniques. In this study, a sorter based on image identification by deep learning was developed to select electronic components into four groups. They were recovered from waste printed circuit boards and should be separated to depend on the difference after treatment. The sorter consists of a workstation with GPU, camera, belt conveyor, air compressor. A small piece (less than 3.5 cm) of electronic components on the belt conveyor (belt speed: 6 cm/s) was taken and learned as teaching data. The accuracy of the image identification was 96% as kinds and 99% as groups. The optimum condition of sorting was determined by evaluating accuracies of image identification and recovery rates by blowdown when changing the operating condition such as belt speed and blowdown time of compressed air. Under the optimum condition, the accuracy of image classification in groups was 98.7%. The sorting rate was more than 70%.

• 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.