• 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 the Korea Society of Computer and Information
• /
• v.24 no.5
• /
• pp.49-58
• /
• 2019

In this paper, we propose an edge cloud platform architecture for implementing smart factory. The edge cloud platform is one of edge computing architecture which is mainly focusing on the efficient computing between IoT devices and central cloud. So far, edge computing has put emphasis on reducing latency, bandwidth and computing cost in areas like smart homes and self-driving cars. On the other hand, in this paper, we suggest not only common functional architecture of edge system but also light weight cloud based architecture to apply to the specialized requirements of smart factory. Cloud based edge architecture has many advantages in terms of scalability and reliability of resources and operation of various independent edge functions compare to typical edge system architecture. To make sure the availability of edge cloud platform in smart factory, we also analyze requirements of smart factory edge. We redefine requirements from a 4M1E(man, machine, material, method, element) perspective which are essentially needed to be digitalized and intelligent for physical operation of smart factory. Based on these requirements, we suggest layered(IoT Gateway, Edge Cloud, Central Cloud) application and data architecture. we also propose edge cloud platform architecture using lightweight container virtualization technology. Finally, we validate its implementation effects with case study. we apply proposed edge cloud architecture to the real manufacturing process and compare to existing equipment engineering system. As a result, we prove that the response performance of the proposed approach was improved by 84 to 92% better than existing method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.229-237
• /
• 2021

Cloud of things (CoTs) is a newer idea which combines cloud computing (CC) with the Internet of Things (IoT). IoT capable of comprehensively producing data, and cloud computing can be presented pathways that allow for the progression towards specific destinations. Integrating these technologies leads to the formation of a separate element referred to as the Cloud of Things (CoTs). It helps implement ideas that make businesses more efficient. This technology is useful for monitoring a device or a machine and managing or connecting them. Since there are a substantial amount of machines that can run the IoT, there is now more data available from the IoT that would have to be stored on a local basis for a provisional period, and this is impossible. CoTs is used to help manage and analyze data to additionally create usable information by permitting and applying the development of advanced technology. However, combining these elements has a few drawbacks in terms of how secure the process is. This investigation aims to recent study literature from the past 3 years that talk about how secure the technology is in terms of protecting by authentication, reliability, availability, confidentiality, and access control. Additionally, this investigation includes a discussion regarding some kinds of potential attacks when using Cloud of Things. It will also cover what the various authors recommend and conclude with as well as how the situation can be approached to prevent an attack.

• Journal of Internet Computing and Services
• /
• v.23 no.6
• /
• pp.15-26
• /
• 2022

Various subjects are carrying out cyberattacks using a variety of tactics and techniques. Additionally, cyberattacks for political and economic purposes are also being carried out by groups which is sponsored by its nation. To deal with cyberattacks, researchers used to classify the malware family and the subjects of the attack based on malware signature. Unfortunately, attackers can easily masquerade as other group. Also, as the attack varies with subject, techniques, and purpose, it is more effective for defenders to identify the attacker's purpose and goal to respond appropriately. The essential goal of cyberattacks is to threaten the information security of the target assets. Information security is achieved by preserving the confidentiality, integrity, and availability of the assets. In this paper, we relabel the attacker's goal based on MITRE ATT&CK® in the point of CIA triad as well as classifying cyber security reports to verify the labeling method. Experimental results show that the model classified the proposed CIA label with at most 80% probability.

• Journal of English Language & Literature
• /
• v.57 no.6
• /
• pp.939-958
• /
• 2011

Ezra Pound has an idea of poetry as a field of energy in which words interact with each other with kinetic energy. The energy field which Pound creates in his poem is analogous to the theory of electromagnetism developed by Michael Faraday and James Maxwell, who look upon the space around magnets, electric charges and currents not as empty but as filled with energy and activity. Pound argues that "words are charged with force like electricity," demonstrating that words charged with their own images or energies of positive or negative valence interact one another. This idea is similar to Faraday's concept of "line of force" which he used to represent the disposition of electric and magnetic forces in space. Pound's concept of "image" as an "intellectual and emotional complex in an instant" is remarkably consonant with the confluence of electric and magnetic fields that are coupled to each other as they travel through space in the form of electromagnetic waves. The instant profusion of conception and perception, much like that of electric and magnetic fields, enables Pound to move beyond the sequential and linear hierarchy in time and space. Particularly, Maxwell's stunning discovery that the electromagnetic waves propagate in space at 'the speed of light' has allowed Pound a relativistic sense of escape from the limitations of Newtonian absolute time and space. Pound's poetry transcends any geographical space and sequential time by rendering and juxtaposing images simultaneously. Pound was fully aware of light and electricity fundamental to what he called his world "the electric world." Pound's experiments in Imagism and Vorticism can be considered an attempt to rediscover a place for poetry in the modern world of science and technology. Almost all the appliances that we think of today as modern were laid down in the closing decades of the 19th century and the first decades of the 20th century, in response to the availability of electromagnetic energy. This paper explores how Pound responded to the age of modern technology and science, examining his conception of "image" through his many analogies and similes drawn from electromagnetism. Pound's imagist poetics and poetry come to embody, not only the characteristics of the electric age in the early twentieth century, but the principles of electromagnetism the electric age is based upon.

• Convergence Security Journal
• /
• v.23 no.4
• /
• pp.23-32
• /
• 2023

Container-based virtualization has attracted many attentions as an alternative to virtual machine technology because it can be used more lightly by sharing the host operating system instead of individual guest operating systems. However, this advantage may owe some vulnerabilities. In particular, excessive resource use of some containers can affect other containers, which is known as the noisy neighbor problem, so that the important property of isolation may not be guaranteed. The noisy neighbor problem can threat the availability of containers, so we need to consider the noisy neighbor problem as a security problem. In this paper, we investigate vulnerabilities on guarantee of isolation incurred by the noisy neighbor problem in container-based virtualization. For this we first analyze the structure of container-based virtualization environments. Then we present vulnerabilities in 3 functional layers and general directions for solutions with limitations.

• Ocean Systems Engineering
• /
• v.14 no.1
• /
• pp.85-99
• /
• 2024

Ocean surface currents have an essential role in the Earth's climate system and significantly impact the marine ecosystem, weather patterns, and human activities. However, predicting ocean surface currents remains challenging due to the complexity and variability of the oceanic processes involved. This review article provides an overview of the current research status, challenges, and opportunities in the prediction of ocean surface currents. We discuss the various observational and modelling approaches used to study ocean surface currents, including satellite remote sensing, in situ measurements, and numerical models. We also highlight the major challenges facing the prediction of ocean surface currents, such as data assimilation, model-observation integration, and the representation of sub-grid scale processes. In this article, we suggest that future research should focus on developing advanced modeling techniques, such as machine learning, and the integration of multiple observational platforms to improve the accuracy and skill of ocean surface current predictions. We also emphasize the need to address the limitations of observing instruments, such as delays in receiving data, versioning errors, missing data, and undocumented data processing techniques. Improving data availability and quality will be essential for enhancing the accuracy of predictions. The future research should focus on developing methods for effective bias correction, a series of data preprocessing procedures, and utilizing combined models and xAI models to incorporate data from various sources. Advancements in predicting ocean surface currents will benefit various applications such as maritime operations, climate studies, and ecosystem management.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2002.06a
• /
• pp.148-155
• /
• 2002

Multithreaded models improve the efficiency of parallel systems by combining inner parallelism, asynchronous data availability and the locality of von Neumann model. This model executes thread code which is generated by compiler and of which quality is given by the method of generation. But multithreaded models have the demerit that execution model is restricted to a specific platform. On the contrary, Java has the platform independency, so if we can translate from threads code to Java bytecode, we can use the advantages of multithreaded models in many platforms. Java executes Java bytecode which is intermediate language format for Java virtual machine. Java bytecode plays a role of an intermediate language in translator and Java virtual machine work as back-end in translator. But, Java bytecode which is translated from multithreaded models have the demerit that it is not secure. This paper, multhithread code whose feature of platform independent can execute in java virtual machine. We design and implement translator which translate from thread code of multithreaded code to Java bytecode and which check secure problems from Java bytecode.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.1009-1029
• /
• 2023

Urban trees play a vital role in urban ecosystems,significantly reducing impervious surfaces and impacting carbon cycling within the city. Although previous research has demonstrated the efficacy of employing artificial intelligence in conjunction with airborne light detection and ranging (LiDAR) data to generate urban tree information, the availability and cost constraints associated with LiDAR data pose limitations. Consequently, this study employed freely accessible, high-resolution multispectral satellite imagery (i.e., Sentinel-2 data) to estimate fractional tree canopy cover (FTC) within the urban confines of Suwon, South Korea, employing machine learning techniques. This study leveraged a median composite image derived from a time series of Sentinel-2 images. In order to account for the diverse land cover found in urban areas, the model incorporated three types of input variables: average (mean) and standard deviation (std) values within a 30-meter grid from 10 m resolution of optical indices from Sentinel-2, and fractional coverage for distinct land cover classes within 30 m grids from the existing level 3 land cover map. Four schemes with different combinations of input variables were compared. Notably, when all three factors (i.e., mean, std, and fractional cover) were used to consider the variation of landcover in urban areas(Scheme 4, S4), the machine learning model exhibited improved performance compared to using only the mean of optical indices (Scheme 1). Of the various models proposed, the random forest (RF) model with S4 demonstrated the most remarkable performance, achieving R² of 0.8196, and mean absolute error (MAE) of 0.0749, and a root mean squared error (RMSE) of 0.1022. The std variable exhibited the highest impact on model outputs within the heterogeneous land covers based on the variable importance analysis. This trained RF model with S4 was then applied to the entire Suwon region, consistently delivering robust results with an R² of 0.8702, MAE of 0.0873, and RMSE of 0.1335. The FTC estimation method developed in this study is expected to offer advantages for application in various regions, providing fundamental data for a better understanding of carbon dynamics in urban ecosystems in the future.