• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.75-81
• /
• 2021

Since plant growth is greatly influenced by moisture, it is important to control the soil to have optimal moisture for the plant being grown. Recently, researches on automatically analyzing plant growth information including soil moisture using spectral images are being conducted. However, hyperspectral images are difficult to use due to huge amount of data appearing in spectral bands. In this paper, we propose a method to solve the complexity of hyperspectral images using a CNN. Since the proposed method automatically analyzes the entire band of the target hyperspectral using deep learning, there is no need to make an effort to find a specific band for analysis of each image. In order to show the effectiveness of the proposed system, we conduct an experiment to analyze moistures using hyperspectral images obtained from soil.

• KNOM Review
• /
• v.24 no.1
• /
• pp.1-12
• /
• 2021

VM (Virtual Machine) live migration is a server virtualization technique for deploying a running VM to another server node while minimizing downtime of a service the VM provides. Currently, in cloud data centers, VM live migration is widely used to apply load balancing on CPU workload and network traffic, to reduce electricity consumption by consolidating active VMs into specific location groups of servers, and to provide uninterrupted service during the maintenance of hardware and software update on servers. It is critical to use VMlive migration as a prevention or mitigation measure for possible failure when its indications are detected or predicted. In this paper, we propose two VNF live migration methods; one for predictive load balancing and the other for a proactive measure in failure. Both need machine learning models that learn periodic monitoring data of resource usage and logs from servers and VMs/VNFs. We apply the second method to a vEPC (Virtual Evolved Pakcet Core) failure scenario to provide a detailed case study.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1784-1789
• /
• 2021

Korean sentiment classification task is used in real-world services such as chatbots and analysis of user's purchase reviews. And due to the development of deep learning technology, neural network models with high performance are being applied. However, the neural network model is not easy to interpret what the input sentences are predicting due to which words, and recently, model interpretation methods for interpreting these neural network models have been popularly proposed. In this paper, we used the LIME algorithm among the model interpretation methods to interpret which of the words in the input sentences of the models learned with the korean sentiment classification dataset. As a result, the interpretation of the Bi-LSTM model with 85.24% performance included 25,283 words, but 84.20% of the transformer model with relatively low performance showed that the transformer model was more reliable than the Bi-LSTM model because it contains 26,447 words.

• Journal of Digital Convergence
• /
• v.19 no.11
• /
• pp.85-93
• /
• 2021

The government is pursuing plans to create new e-government services. In terms of improving business procedures, dBrain (finance), e-people (personnel), and Onnara (electronic payment and business management) have achieved considerable results, and are currently making efforts to improve existing administrative services using newly emerged ICT. Among them, this paper attempted to study whether self-learning-based intelligent administrative services are efficient in the work process of public officials promoting actual work and affect their continued use. Based on individual perceptions and attitudes toward advanced ICTs such as AI, big data, and blockchain, public officials' influences on administrative services were identified and verified using UTAUT variables. They believe that the establishment and introduction of innovative administrative services can be used more efficiently, and they have high expectations for the use and provision of services as ICT develops. In the future, a model will be also applied to citizens

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.131-138
• /
• 2022

Git's commit message is closely related to the project life cycle, and by this characteristic, it can greatly contribute to cost reduction and improvement of work efficiency by identifying risk factors and project status of project operation activities. Among these related fields, there are many studies that classify commit messages as types of software maintenance, and the maximum accuracy among the studies is 87%. In this paper, the purpose of using a solution using the commit classification model is to design and implement a complex classification model that combines several models to increase the accuracy of the previously published models and increase the reliability of the model. In this paper, a dataset was constructed by extracting automated labeling and source changes and trained using the DistillBERT model. As a result of verification, reliability was secured by obtaining an F1 score of 95%, which is 8% higher than the maximum of 87% reported in previous studies. Using the results of this study, it is expected that the reliability of the model will be increased and it will be possible to apply it to solutions such as software and project management.

• Journal of Practical Engineering Education
• /
• v.14 no.1
• /
• pp.49-59
• /
• 2022

This study was conducted to develop a teaching competency scales customized for teaching programs conducted by Center for Teaching & Learning at A University. To achieve this purpose, a preliminary study was set up, which consists of three competency groups (basic competency, practice competency, innovation competency) and 26 learning competency factors through a review of previous studies. In order to verify the reliability and validity of the provisional teaching competency scales, an online survey was conducted on A university teachers in September 2020, The collected questionnaire data were organized and exploratory factor analysis and confirmatory factor analysis were conducted. As a result of exploratory factor analysis, 26 teaching competency was reduced to 17. As a result of the confirmatory factor analysis, the model was found to be good, Also, as a result of analyzing the construct reliability and AVE of the confirmed teaching competency factors, all 17 factors showed a good level of .7 or more. The teaching competency scales developed through this study can be used as basic data for performance evaluation and development of new programs of CTL teaching program.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.312-318
• /
• 2022

This paper proposes a model which classifies the type of guns and information about sound source location using deep neural network. The proposed classification model is composed of convolutional neural networks (CNN) and long short-term memory (LSTM). For training and test the model, we use the Gunshot Audio Forensic Dataset generated by the project supported by the National Institute of Justice (NIJ). The acoustic signals are transformed to Mel-Spectrogram and they are provided as learning and test data for the proposed model. The model is compared with the control model consisting of convolutional neural networks only. The proposed model shows high accuracy more than 90 %.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.11-19
• /
• 2022

Recently, various researches on medical image generation have been suggested, and it becomes crucial to accurately evaluate the quality and diversity of the generated medical images. For this purpose, the expert's visual turing test, feature distribution visualization, and quantitative evaluation through IS and FID are evaluated. However, there are few methods for quantitatively evaluating medical images in terms of fidelity and diversity. In this paper, images are generated by learning a chest CT dataset of non-small cell lung cancer patients through DCGAN and PGGAN generative models, and the performance of the two generative models are evaluated in terms of fidelity and diversity. The performance is quantitatively evaluated through IS and FID, which are one-dimensional score-based evaluation methods, and Precision and Recall, Improved Precision and Recall, which are two-dimensional score-based evaluation methods, and the characteristics and limitations of each evaluation method are also analyzed in medical imaging.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.3
• /
• pp.83-95
• /
• 2022

This paper proposes a system that performs object detection and distance estimation for application to autonomous vehicles. Object detection is performed by a network that adjusts the split grid to the input image ratio using the characteristics of the recently actively used deep learning model YOLOv4, and is trained to a custom dataset. The distance to the detected object is estimated using a bounding box and homography. As a result of the experiment, the proposed method improved in overall detection performance and processing speed close to real-time. Compared to the existing YOLOv4, the total mAP of the proposed method increased by 4.03%. The accuracy of object recognition such as pedestrians, vehicles, construction sites, and PE drums, which frequently occur when driving to the city center, has been improved. The processing speed is approximately 55 FPS. The average of the distance estimation error was 5.25m in the X coordinate and 0.97m in the Y coordinate.

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.527-537
• /
• 2022

As multimedia contents demand and supply increase, internet traffic around the world increases. Several standardization groups are striving to establish more efficient compression standards to mitigate the problem. In particular, research to introduce deep learning technology into compression standards is actively underway. Despite the fact that deep learning-based technologies show high performance, they suffer from the domain gap problem when test video sequences have different characteristics of training video sequences. To this end, several methods have been made to introduce content-adaptive deep video compression. In this paper, we will look into these methods by three aspects: codec information-aware methods, model selection methods, and information signaling methods.