Search

The rapid advancement of computer science technology and artificial intelligence has generated heightened investor interest in quantitative trading, primarily attributable to its exceptional efficiency and consistent performance. This paper presents the development of a volatility prediction system for the agricultural commodity exchange trading domain. The system utilizes raw financial data as input and produces trading decision-support as output using a volatility prediction based on Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) and Long Short-term Memory (LSTM) models. The main goal of the system is to enhance overall profitability through efficient management of trading losses. In addition, a denoising technique is utilized to reduce the influence of market noise and improve overall performance. The prototype has been trained and back-tested in the agricultural commodity market trading data from 2010-2023. The research findings suggest that the Multivariate Bidirected LSTM 2 layers model has the best accuracy of 91.38% in predicting the volatility of cotton commodities trading throughout the time frame spanning from October 21, 2022, to September 22, 2023. The GARCH model is widely utilized for volatility forecasting, but the Multivariate LSTM model has promise in offering investors a possible edge through enhanced forecasting accuracy.

Electrical fires frequently occur due to the ignition generated by electrical gadgets, wiring, cables, and multi-taps. These fires can cause numerous human casualties and property damage every year. The mechanisms that cause electrical fires are generally unique and require specialist research to understand their features fully. Due to the rising number of electrical fires, IT-based assessment models for electrical fire causes assessment have been proposed and experimented with to improve efficiency and accuracy. This survey aims to thoroughly examine and analyze the current advanced practices in detecting and evaluating electrical fire causes, focusing explicitly on IT-based assessment methods and simulations to provide a comprehensive review. The research objectives are achieved by conducting a survey on techniques and procedures utilized in prior works and research. Firstly, we introduce the survey of factors contributing to electrical fires. Next, electrical fire simulations to determine the causes and behavior of electrical fires are investigated. The assessment of electrical techniques to understand electrical fire causes has been emphasized. Lastly, the summaries and proposed enhancements to advance the progress in this domain are examined. To the best of our knowledge, this is the first time a survey on electrical fire causes assessment of IT-based approaches has been conducted. These findings are expected to become a valuable reference in this domain.

Accidents resulting from fires caused by electrical devices are frequent occurrences, inflicting substantial damage to both human lives and infrastructure in the Republic of Korea. To ascertain whether these fires stem from external or internal infrastructure factors, investigators such as the police, The National Institute of Scientific Investigation, and the National Fire Research Institute conduct fire-causing inspections. However, obtaining conclusive results in this regard is an intricate process, exacerbated by the dearth of adequate digital forensics tools and related programs. Among electrical devices, multi-socket outlets also contribute to fire incidents. This study explores the feasibility of employing CNN-based deep learning object detection models for fire-causing inspection systems targeting multi-socket outlets. Specifically, we introduce a novel image dataset comprising 6009 images of post-fire multi-socket outlets remaining, categorized into two classes: “burnt-in” and “burnt-out.” This dataset is utilized for training various models, including the YOLO-series (v5, v6, and v8), Faster-RCNN, RetinaNet, and SSD. Results from our experiments show the feasibility of six CNN models in detecting the cause of fire in post-fire sockets. Particularly, YOLOv5s surpasses other models with an accuracy of 89.1% mAP@0.5, a model size of 14.4MB, and an inference time of 44.5ms (equivalent to 22 fps) on RTX 3050. Subsequently, the trained models are implemented in an operational application for trial testing during an executive period.

The drone technology field has received attention and witnessed numerous impressive advancements that heralded substantial changes and opened new possibilities in different industries. Several advanced technologies, such as artificial intelligence, computer science, object avoidance technology, and others, have been collaboratively developed to empower drone operations. Drone technology software engineering overview can assist in identifying and prioritizing research gaps that require attention in future research. The main contribution is to investigate the recent development of drone technology by applying the literature review methodology. Our research involves a comprehensive literature review of drone technology software engineering, including worldwide journal papers and reviews published from 2010 to the present. To achieve this goal, we will first research the evolution of drone technology software engineering research trends. Second, we investigate approaches to ensuring the reliability, safety, and security of drone software systems. After that, software testing and validation methodologies have emerged to ensure the robustness and trustworthiness of drone systems are investigated. Finally, the potential of integration of AI/ML capabilities into drone software that has been progressing to enhance autonomous decision-making and adaptation in drone technology is described. As a result, summarized features of a drone system and its increasingly expanding variety of applications are discussed. After that, an analysis to identify the emerging trends, promising research directions, and ongoing challenges in the domain of drone software engineering is presented. These findings are expected to become a valuable reference in this research field.

Digital Twins technology is being increasingly adopted by various industries, heralding transformative changes and unlocking fresh possibilities. It offers high control over physical entities and efficiently manages intricate systems by integrating several technologies. While the aquaculture sector has witnessed several recent technological advances, it remains to be seen whether the industry is actively embracing the integration of digital twins into its operations. To address this research question, we investigate the applications based on Digital Twins technology in the aquaculture sector using a literature review methodology. Our research includes a comprehensive literature review on Digital Twins technology in aquaculture in many articles and reviews worldwide from 2017 to 2024. First, we research the extent to which Digital Twins technology has already been explicitly adopted in aquacultural systems and investigate their reported benefits. The researched systems are divided into three main types: simulation and digital model system, digital twins based system, and metaverse-based system. Second, we identify potential opportunities for aquacultural based on Digital Twins technology. In addition, we will discuss the overview architecture of the Digital Twins based aquaculture system and the properties of these trends in the future. The main contribution is to offer a comprehensive overview of the Aquaculture Digital Twins based system, examining its development implications through various case-study systems worldwide.

The coffee industry contributes to the economic restructuring of many countries, often associated with a closed process from production to consumption. The green coffee bean grading standard provided by the Specialty Coffee Association (SCA) is one of the best methods for grading coffee beans. Traditionally, the assessment of quality and classification of coffee beans relies on visual examination, which demands significant time and effort and is easily inaccurate. Deep learning technology, characterized by precision, velocity, and veracity, can be adopted to empower the reduction of human labor and improve the productivity, quality, and efficiency of these tasks. Therefore, this paper aims to address these issues by implementing deep learning to classify coffee bean quality in real time by integrating the system with a cloud-based solution. First, image processing and data augmentation techniques are employed to handle the coffee bean image data. Subsequently, the model is trained using YOLOv8, a framework for object recognition, and OpenCV, an open-source image processing technology, to classify coffee beans. Finally, an application is developed for real-time video and image-streaming coffee bean recognition using React Native, NodeJS, and Python. The experimental results provide empirical evidence that our system enhances accuracy and efficiency in the tasks of classifying coffee bean quality in nine distinct varieties of coffee beans, with the time required reduced to a mere 1 to 3 seconds. Our system can be a useful solution for coffee producers, processors, and traders without relying on stationary equipment, especially in large farms or warehouses.

Coffee, the second-largest global soft commodity, can take advantage of a comprehensive mining of daily and historical market data for more effective informed trading decisions. Advanced ICT and data mining technologies can change the trading market operation. The existing systems are confronted with certain constraints, including incomplete data, insufficient documentation for storage, and a requirement for a scalable infrastructure for big data analytics, such as a data warehouse or data lakehouse. To address this issue, the paper presents a design and implementation of a coffee commodity trading big data warehouse capable of analyzing various essential parameters for supporting informed decision-making. First, the designed system can automatically collect coffee trading data for New York Arabica coffee futures prices from selected worldwide reports and financial data portals. Next, the Extract, transform, and load (ETL) process is adopted to ingest coffee futures trading crawled data into the 3 layers data warehouse. Finally, the analytical system will extract and visualize selected key dimensions that influence coffee futures prices within different observation windows and perspectives. As a result, we implement a prototype of a coffee trading data warehouse on the crawled data from January 2000 to October 2022 and visualize trends in coffee futures prices based on the collected data for informed decision-making. The construction system is capable of stably operating and processing large volumes of transaction data. This paper will be valuable documentation for reference and decision support for coffee commodity trading enterprises and contribute to the development of future forecasting algorithms.

Massive jellyfish outbreaks have put human lives and marine ecosystems in great danger. As a result, the jellyfish detection methods have drawn a lot of attention, following two directions optical and sonar imaging. This work focuses on using optical imagery and CNN-based deep-learning object detection models to detect jellyfish. While labeled data of jellyfish play an important part in training deep learning models, there are a few open and available labeled datasets. Hence, we create our dataset to train these models using our model-assisted labeling method with over 11 thousand images of underwater jellyfish and corresponding annotation files in PASCAL VOC format. Our model-assisted labeling method saves the work of classical manual labeling by 70 percent, which is developed into application with YOLOv5. However, the YOLOv5 baseline suffers from the trade-off between real-time performance and low accuracy. Hence, an improved YOLOv5-nano is introduced based on adding GAM and replacing conventional Conv with CoordCov modules into the backbone of the conventional structure. The experiment results show that our improved model increases the accuracy of the conventional one by 1.3% and outperforms others including RetinaNet, SSD, Faster R-CNN, YOLOv6, and YOLOv8 at 89.1% mAP@0.5. On generalization performance, we verify the effectiveness of our work by conducting a test set of 15 different types of jellyfish with various shapes, colors, resolutions, and backgrounds. To conclude, our work establishes a comprehensive system from labeling the data, improving object detectors, and developing a feasible real-time jellyfish detector.

This paper minimizes fake news, which has been a hot topic recently, using blockchain and artificial intelligence technology, and verifies it with blockchain. Also, using Artificial Intelligence technology, we want to create an algorithm that predicts how fake news will spread in the future. You can see various attempts at a news media platform based on Blockchain technology. However, the Blockchain news media platform is still not getting the market response we expected. It is questionable whether the reason is simply because it is a new technology, so it takes a long time to gain trust from consumers, whether consumers are not yet expecting an innovative news media platform, or whether the explosive growth of the Blockchain news media platform is difficult for other reasons. Research to answer this or direct research between Blockchain and media platforms is still lacking. In addition, the method of verifying fake news using artificial intelligence was verified, ANN, CBR, and MDA were changed, and the experiment was verified for progress. In addition, the use of 5-fold cross-validation as a comparative method was added as described above to more closely examine the possibility of its usefulness even in general situations. Also, through various fields of artificial intelligence and blockchain, verification work was done with blockchain, and fake news prediction was made using artificial intelligence. Various experiments were conducted and performance tests were performed, while the performance of about 5,000 TTPS was recorded through the third experiment. In the future, we think it is necessary to combine Artificial Intelligence and blockchain technology.

How can scalable vector graphics (SVG) data of human faces be transformed to resemble specific animal faces? Since the early $20^{th}$ century, multimedia featuring animals has garnered significant attention, particularly as interest in anthropomorphic animals has grown. In this paper, we survey various anthropomorphic studies. Additionally, we develop a warping system for anthropomorphizing animal characters. Our system enables the automatic generation of anthropomorphized animal characters using SVG datasets. This dataset includes frontal and side views of 60 animal species commonly featured in animations, as well as male and female human characters. Users can create new anthropomorphized animal characters using our dataset and their vector data. Our warping system implements a continuous warping technique between animal and human facial shapes in ten stages, supported by a developed algorithm and an SVG warping program. The code of the warping system and SVG dataset are available at link: https://github.com/jenero05458/SVG_warping

With the development of artificial intelligence, there have been many attempts to incorporate artificial intelligence into algorithmic trading. In particular, reinforcement learning, which aims to solve dynamic decision-making problems, is attracting attention because of its high utilization in algorithmic trading. In this paper, we will implement a simple Deep Reinforcement Learning (DRL) trading robot to check the performance of DRL. In addition, we tried to find out how much performance improvement can be achieved by comparing a robot that learned a single stock data with a robot that learned stock data, market index, and interest rate data. This paper aims to develop a stock investment robot using a Proximal Policy Optimization (PPO) reinforcement learning algorithm and analyze the performance of the robot. The first robot used only the stock data of APPL INC, a single stock, as input, and the second robot used stock data of APPL INC and the S&P 500 index together with US interest rate data as input data. Afterward, the stock investment performance of the two robots for APPL INC was comparatively analyzed using the test data.

In the Smart Factory environment of the $4^{th}$ industrial revolution, much data is generated from equipment, IoT sensors, and a wide range of manufacturing systems. As manufacturing sites are scattered around the world, information exchange between geographically remote factories is ever more necessary. Also, higher quality and effective management can be achieved by integrating and analyzing the collected and refined data and deriving organic results in the ever-rapidly changing manufacturing environment. However, as the main factory consists of a separate network with much data generated, it is highly difficult to gather all data into one and refine it. The most widely used method of data gathering at present has an architecture where data is linked through integration of the centrally configured solutions for data gathering and linkage. In other words, legacy systems most commonly used in manufacturing sites such as ERP, MES, WMS, etc. use the central system called ESB or EAI, to collect data with the SOA method for inter-system data linkage and collection and pass it on to another legacy system. The centralized method is not suitable for gathering and converging data generated from dozens or hundreds of different factories that are regionally dispersed or made up of independent networks and are also extremely vulnerable in terms of security and safety. This article aims to investigate how to stably and effectively exchange and collect data in geographically remote, independent networks using Apache Kafka, one of the big data ecosystems, and how to enable easy analysis of such data so that users can effectively utilize it.

Vision Transformer (ViT) has been proposed as a new image recognition method in the field of computer vision. ViT applies a Transformer structure with excellent performance in the field of natural language processing to recognize images. Unlike existing Convolutional Neural Network (CNN) models, ViT can achieve State-Of-The-Art (SOTA) image recognition without inputting Inductive Biases into the model, demonstrating that the Transformer is a useful structure in the field of computer vision. However, ViT requires large datasets such as ImageNet-21K and Joint Foto Tree (JFT) for learning. In addition, it takes a lot of time to train. Moreover, there is a problem that location information is lost by inputting images in patch units. To improve such issues, many models are being proposed. In this paper, a new model is proposed by restructuring the Convolutional neural networks Meet vision Transformers (CMT) model by applying Coordinate Attention Block, a CNN model, to improve problems of the Vision Transformer family of models. The proposed model combines Transformer, which has shown excellent performance in Long Range, and CNN, which has shown excellent performance in Local Feature, to achieve higher performance than existing models. We also compared performance of the proposed model with those of existing models with relatively small datasets such as Canadian Institute For Advanced Research-10 (CIFAR-10), Self-Taught Learning-10 (STL-10), and Tiny-ImageNet to facilitate researchers’ access to the evaluation. Despite being restructured from the smallest CMT-Tiny model, the proposed model showed better accuracy than CMT-Tiny, CMT-XS, CMT-S, and CMT-B models with CIFAR-10, STL-10, and Tiny-ImageNet datasets. The proposed model showed an accuracy of 90.21% with the CIFAR-10 dataset, higher than existing CMT models except for the CMT-S model with an accuracy of 90.6%. It had the lowest loss value of 0.3967. The proposed model is expected to be utilized as a backbone in Object Detection and Segmentation fields in the future.

Autonomous underwater vehicles (AUVs) have been developed and used in research to perform various tasks such as marine surveys and the collection of bathymetric data in certain areas that are difficult for humans to access, such as deep seas. Because AUVs are limited in terms of their execution of tasks that require an extensive amount of energy, unmanned surface vehicles (USVs) and launch and recovery systems (LARS) are jointly used for the transport to task sites as well as the launch and recovery. To comply with international environmental regulations, there are ongoing attempts to reduce the generation of pollutants in USVs. This study focuses on developing an energy storage system (ESS) based power system and electric propulsion system for reducing the pollutants generated by USVs. A USV task scenario is set, and the required power amount is calculated; a power system that satisfies the required power is also configured. Furthermore, an energy management system (EMS) is designed and produced for monitoring and controlling the configured system. The performance is verified through a land experiment by designing and producing the components of the configured ESS-based electric propulsion system. The verified system is installed on a catamaran USV, and a field test was performed in the West Sea of Korea. The load required for propelling a catamaran USV having a length overall (LOA) of 11 m is analyzed through a marine field test, and the effects of a steering function of a vessel on the main thruster system are examined.

Abstract This paper deals with the current Blockchain adopted in the various types of trading markets supporting smart contracts that process text-based transaction information only when exchanging cryptocurrencies. Even though the Blockchain itself is decentralized, services can still be provided through a centralized system in order to provide adequate services to the users. It also allows the Autochain to apply Blockchain technology to existing businesses conducted under the Fourth Industrial Revolution to realize higher productivity or competitiveness and improve profitability to a remarkable extent. The Autochain is adaptable to all Blockchain technologies, companies, or research works around the world to overcome the limitations of the existing Blockchain technology. It creates the Blockchain-platform ecology chain and ecosystem, making our lives more convenient while revolutionizing every industry. In addition, it automates all Blockchain-based systems and offers a base for constructing a system wherein everyone can easily provide, operate, and maintain Blockchain services. This paper discusses a number of Blockchain-related technologies and presents a decentralized Application (dApp) exclusively designed for mobile use, taking house rental service as an example. It also presents the existing Blockchain and the Blockchain database storage method and proposes the dApp based on it.

Among the fire reports caused by seasonal devices registered with the Korea Fire Information Center in 2021, fires caused by heating cables accounted for the largest portion with 350 cases. As a result of analyzing the heating cable fires from 2015 to 2021, we have classified the heating cable fires into four types according to the method of winding the heating wire. First, we hypothesized that the temperature is high when the density is high due to the overlap of the hot wires or when there is a thermal insulating material. We predicted that the temperature would rise through a random game and established a reproducibility test plan. In order to check how heat generation changes depending on the winding method of antifreeze heating cables, we selected 10 manufacturers and checked the temperature characteristics according to the test conditions (Paragraph 11, Paragraph 19.101) of the Technical Regulations for Electrical and Telecommunication Products and Components of Korea (K 10013), tested the four methods mentioned in this thesis and compared and analyzed the results. The experiment results indicate that the temperature of the heater part in antifreeze heating cables was mostly higher than the conditions required by the existing standards in cases 1 to 4. In particular, in the case of No. 5 manufacturer’s sample, the temperature of the heating cable of Case 1 was measured to be the highest at 119.0 °C. In addition, as a result of applying the data engineering reproducibility test results in the framework of the random game λ proposed in this thesis, we have derived the same results as the predicted hypothesis. Case 1 refers to the case where a fire occurs due to the heating cable being wrapped around the water pipe and insulation or taped outside; It is one of the methods that users actually use a lot in the field. Based on experiment, we have concluded that the fire risk is high under the Case 1 condition. Thus, the test conditions in the existing K 10013 Standard need to be strengthened according to the Case 1 condition.

Photovoltaic (PV) technology converts solar energy into electrical energy, and the PV industry is an essential renewable energy industry. However, the amount of power generated through PV systems is closely related to unpredictable and uncontrollable environmental factors such as solar radiation, temperature, humidity, cloud cover, and wind speed. Particularly, changes in temperature and solar radiation can substantially affect power generation, causing a sudden surplus or reduction in the power output. Nevertheless, accurately predicting the energy produced by PV power generation systems is crucial. This paper proposes a hybrid model comprising a convolutional neural network (CNN) and long short-term memory (LSTM) for stable power generation forecasting. The CNN classifies weather conditions, while the LSTM learns power generation patterns based on the weather conditions. The proposed model was trained and tested using the PV power output data from a power plant in Busan, Korea. Quantitative and qualitative evaluations were performed to verify the performance of the model. The proposed model achieved a mean absolute percentage error of 4.58 on a sunny day and 7.06 on a cloudy day in the quantitative evaluation. The experimental results suggest that precise power generation forecasting is possible using the proposed model according to instantaneous changes in power generation patterns. Moreover, the proposed model can help optimize PV power plant operations.

With the smartization and autonomous navigation of vessels through ICT (Information and Communications Technologies)—combining IoT, artificial intelligence (AI), and Big Data—changes in the shipbuilding industry will progress quickly; we must acquire superior technology and vessel quality to partake in the revamped shipbuilding industry. This paper aims to research the means of collecting and managing big data in shipbuilding to suit a variety of data types and communication methods in the shipbuilding industry, as well as ways of utilizing the aforementioned big data in order to respond to rapidly progressing changes in the industry. Additionally, the model proposed in this paper is research based on the Asian shipbuilding industry.

One of the most important and challenging research subjects in computer vision is visual object tracking. The information obtained from the first frame consists of limited and insufficient information to represent an object. If prior information about robust representation that can represent an object well is not sufficient, object tracking fails when not robustly responding to changes in features of the target object according to various factors, namely shape, illumination variation, and scene distortion. In this paper, a real-time single object tracking algorithm is proposed based on a Siamese network to solve this problem. For the object feature extraction, we designed a fully convolutional neural network that removes a fully connected layer and configured a convolution block consisting of a bottleneck structure that preserves the information in a previous layer. This network was designed as a Siamese network, while a regional proposal network was combined at the end of the network for object tracking. The ImageNet Large-Scale Visual Recognition Challenge 2017 dataset was used to train the network in the pre-training phase. Then, in the experimental phase, the object tracking benchmark dataset was used to quantitatively evaluate the network. The experimental results revealed that the proposed tracking algorithm produced more competitive results compared to other tracking algorithms.

The key to the explosion of the Internet of Things and the ability to collect, analyze, and provide big data in the cloud is edge computing, which is a new computing paradigm in which data is processed from edges. Edge Computing has been attracting attention as one of the top 10 strategic technology trends in the past two years and has innovative potential. It provides shorter response times, lower bandwidth costs, and more robust data safety and privacy protection than cloud computing. In particular, artificial intelligence technologies are rapidly incorporating edge computing. In this paper, we introduce the concepts, backgrounds, and pros and cons of edge computing, explain how it operates and its structure hierarchically with artificial intelligence concepts, list examples of its applications in various fields, and finally suggest some improvements and discuss the challenges of its application in three representative technological fields. We intend to clarify various analyses and opinions regarding edge computing and artificial intelligence.

A smart grid is an intelligent power grid. In recent years, the smart grid environment and its applications are incorporated into a variety of areas. The smart grid environment, however, can expose much more information than the old environments. In the environment, smart devices can be media in the exposure of various and specific pieces of information as well as energy consumption. This poses a huge risk in that it, combined with other pieces of information, may expose much more information. The current smart grid environment raises a need to develop anonymous signature and authentication techniques to prevent privacy breaches. Trying to meet this need, the principal investigator conducted research for three years. This paper discusses both the research trends investigated by him and the limitations of the development research and future research in need. Smart grid security requires the development of encrypted anonymous authentication that is applicable to power plant security, including nuclear power plants as well as expandable test beds.

In March 2021, a case of speculation that abused private internal information came to light, which involved a group of public officials from the Korea Land and Housing Corporation (LH), and has since been labeled the ‘LH Scandal’. In this scandal, land was misappropriated as a means of creating fraudulent values, instead of returning it to marginalized people in real need of residential space. As a result of this, preventive measures for similar cases have become warranted. Consequently, related laws have been passed, but this is only expected to show its effect as a follow-up response, therefore requiring a preemptive response plan. In this paper, we will propose a conceptual framework that can detect speculation that abuses private internal information, enabling a preemptive response, utilizing outlier detection and Latent Dirichlet Allocation (LDA) methods. The system is designed to create a database (DB) with private inside real estate information, which is linked to another DB with a list of outlier-detected areas that can potentially indicate speculation, and then the system confirms any speculation by comparing the two DBs accordingly. Once a speculation case is confirmed, the system automatically reports the case to the investigative agency. By using this system, we expect to detect hidden speculation cases already committed, as well as speculation cases in real-time. Ultimately, we hope to protect the original purpose of redevelopment and the construction of new towns (housing/retail mixed-use zones), redistributing available land on behalf of marginalized people, who are lacking in residential space, by raising the utility of land.

PV (photovoltaic) capacity is steadily increasing every year, and the rate of increase is also increasing. A desert area with a large equipment installation area and abundant solar radiation is a good candidate. PV power plants installed in the desert have advantages in themselves, but when combined with desert aquacultures, additional benefits can be obtained while compensating for the shortcomings of the aquaculture industry. The importance of the aquaculture industry is increasing, with aquaculture products approaching half of the total supply of marine products due to sea environmental pollution and reduced resources. Moreover, in deserts, where marine products are difficult to obtain, aquaculture is a good way to save marine products. However, one of the many problems that complicate the introduction of aquaculture in the desert is that it is difficult to supply and demand electricity because the site is not near a viable electric grid. However, combination with PV can solve this problem. This paper investigates the solar power and aquaculture industry in the desert and explains the limitations and challenges of the solar power and aquaculture industry in the desert. Based on this, we hope to increase interest in the solar power and aquaculture industry in the desert and help with future research.

Research was conducted in this study to design data-based size recommendation and size coding systems specifically for online shopping malls, expecting to lighten the burden of holding excessive inventories often caused by the high return rate in these online malls. The recommendation system has been implemented focusing mainly on size extraction and recommendation functions along with a UI (user interface). For the former function, data are necessary to extract customers’ sizes and, for instance, the system to be used in China adopts their Chinese standard body size GB/T (Chinese national standard) considering that there are a variety of body types in their substantial population. The system shows the most similar size dataset among the body size GB/T dataset to the customer once he/she inputs his/her height and weight. Each GB/T data was entered after categorizing it according to the proportion between height and weight. For the latter function, size recommendation, size coding was performed first for all the clothes by the shop owner by entering individual size data. The clothes providing the most suitable fit for the customer are recommended by the selection of that which has the smallest deviation between coded clothes size and the customer body data after performing a series of comparative calculations. To validate the effectiveness of the extraction, a method that checks whether the difference between extracted size and the body size that has been measured remains within the error range of 4cm was used. The result showed there to be an approximate 88% matching rate for women and a slightly lower accuracy of 80% for men. Moreover, the error rate was relatively smaller for the upper half clothing such as shirts, jackets, and blouses or one-piece dresses. Such a result may have been generated since the GB/T data were actually the average data entered 10 years prior without categorizing nationalities, ages, and body types in detail. This research emphasized the necessity of a database containing a more segmented human body size data, which can be effective for extracting and recommending sizes more accurately as the latest ones continue to accumulate.

The rapid growth of aquaculture production has required a huge power demand, which is estimated to be about 40% of the total energy cost. However, it is possible to reduce this expense using alternatives such as renewable energy (i.e., solar energy) instead of non-renewable energy. Solar energy is one of the cleanest energy sources and is touted as a potential renewable energy source for the world with benefits such as reducing CO2 emissions, reversing global warming by being eco-friendly, and bringing innovation to sustainable aquaculture and potential cost-efficiency for manufacturing. In this review, we present an overview of using non-renewable and renewable energy sources for aquaculture by reviewing several articles and applications of solar energy at many companies in the world. Moreover, this review shows potential and future trends using solar energy for aquaculture.

This paper has tried to execute accurate demand forecasting by utilizing big data visualization and proposes a flexible and balanced electric power production big data virtualization based on a photovoltaic power plant. First of all, this paper has tried to align electricity demand and supply as much as possible using big data. Second, by using big data to predict the supply of new renewable energy, an attempt was made to incorporate new and renewable energy into the current power supply system and to recommend an efficient energy distribution method. The first presented problem that had to be solved was the improvement in the accuracy of the existing electricity demand for forecasting models. This was explained through the relationship between the power demand and the number of specific words in the paper that use crawling by utilizing big data. The next problem arose because the current electricity production and supply system stores the amount of new renewable energy by changing the form of energy that is produced through ESS or that is pumped through water power generation without taking the amount of new renewable energy that is generated from sources such as thermal power, nuclear power, and hydropower into consideration. This occurs due to the difficulty of predicting power production using new renewable energy and the absence of a prediction system, which is a problem due to the inefficiency of changing energy types. Therefore, using game theory, the theoretical foundation of a power demand forecasting model based on big data-based renewable energy production forecasting was prepared.

The need for non-face-to-face online health care has emerged through the era of “untact”. However, there is a lack of standardization work and research cases on the exercise effect of immersive content. In this study, the possibility of the exercise effect of VR e-sports among e-sports cases were presented through a visual algorithm analysis. In addition, the evaluation criteria were established. The research method compares and analyzes e-sports cases and VR e-sports cases by applying existing evaluation research cases. It also sets up a new evaluation standard. As for the analysis result, the device immersion method and interaction range were set through an algorithm analysis; FOV and frame immersion were set through typification; the user recognition method and interaction method were set through the visual diagram. Then, each derived result value was quantified and a new evaluation criterion was proposed.

Foreign Direct Investment (FDI) is an important resource that helps accelerate the development of the country’s economy, add substantial funding to growth and facilitate technology transfer. Republic of Korea (ROK) is one of the world’s developed countries with dynamic economy, advanced science and technology. In recent years, the Korean government has continuously formulated tax policies, policies to support the business economy and import policies to support foreign businesses in Korea. The Pangyo Valley Creative Economy Valley is being groomed as a global startup hub in Asia. Small and medium enterprises (SMEs) in foreign countries are increasingly interested and eager to seek investment opportunities in the Korean market. Nonetheless, for these companies, language barriers and cultural and institutional differences make it more difficult and time-consuming to learn about the Korean market (such as investment trends, laws, visa policies, taxes and business establishment issues in Korea, etc.). In this study, we explored the process of searching information and seeking investment opportunities and built a business consulting and support application in the first stages of starting a business in ROK to increase effectiveness and save time, which is also an innovative business practice in Use-case ROK. We designed our Virtual Assistant system that can crawl and analyze data on foreign investments in ROK from open data resource websites (data.co.kr) and used analytic and aggregation techniques to explore trends in investments of foreign enterprises. We also researched the process of searching information and seeking investment opportunities for SMEs when investing in ROK, government support policies, laws and taxes as well as a number of other related issues. We built datasets and used Natural Language Processing (NLP) together with Natural Language Understanding (NLU) algorithms to build chatbot applications. Friendly framework for new developers to add and build up the dataset of AI Assistant is built by providing input intent data function, input Entity data function, input utterance data function as well as training and test function. In addition, we built a web-app connected to the server to visualize all the results of research so that SMEs owners can easily use and look for information on investments. Based on the research results, we can make recommendations to SMEs in keeping with the changing investment trends in ROK.

The trash disposal system, using standard trash bags, has been adopted by the government of the Republic of Korea (ROK) for more than two decades. This has caused a sanitary problem, as well as some secondary pollution. It is possible to solve this problem by deploying more manpower, but considering the manpower and maintenance costs that impose a heavy burden on the local governments who are experiencing tight financial situations, it would not be feasible. Thus, an Internet of Things (IoT)-based Smart Trash Separation Bin model that can reduce the cost of trash separation work has been proposed in this paper. The three efficient designs that respectively use a sensor, image processing, or spectroscope technology are presented. These IoT-based designs can bring significant merit to reducing the manpower costs, as well as the administrative cost involved.

Recently, the interest in the plant factory-based crop production technologies is rising following the application of the smart farm technology to the agricultural arena. A lettuce production system platform is proposed in this study considering the effects of indoor environmental conditions and artificial light sources. The spectral characteristics of a visible ray according to growth performances were analyzed first to develop a control algorithm that can stimulate the plant’s growth for the proposal. Secondly, an imaging system was designed to analyze the plant’s growth characteristics based on the images and set up the system configuration. Lastly, a crop production system was proposed by using an experimental crop production group for environmental control and monitoring.

In real estate, there are various variables for the forecasting of future land prices, in addition to the macro and micro perspectives used in the current research. Examples of such variables are the economic growth rate, unemployment rate, regional development and important locations, and transportation. Therefore, in this paper, data on real estate and national price fluctuation rates were used to predict the ways in which future land prices will fluctuate, and macro and micro perspective variables were actively utilized in order to conduct land analysis based on Big Data analysis. We sought to understand what kinds of variables directly affect the fluctuation of the land, and to use this for future land price analysis. In addition to the two variables mentioned above, the factor of the landscape was also confirmed to be closely related to the real estate market. Therefore, in order to check the correlation between the landscape and the real estate market, we will examine the factors which change the land price in the landscape district, and then discuss how the landscape and real estate can interact. As a result, re-explaining the previous contents, the future land price is predicted by actively utilizing macro and micro variables in real estate land price prediction. Through this method, we want to increase the accuracy of the real estate market, which is difficult to predict, and we hope that it will be useful in the real estate market in the future.

Today, semi-structured and unstructured data are mainly collected and analyzed for data analysis applicable to various systems. Such data have a dense distribution of space and usually contain outliers and noise data. There have been ongoing research studies on clustering algorithms to classify such data (outliers and noise data). The K-means algorithm is one of the most investigated clustering algorithms. Researchers have pointed out a couple of problems such as processing clustering for the number of clusters, K, by an analyst through his or her random choices, producing biased results in data classification through the connection of nodes in dense data, and higher implementation costs and lower accuracy according to the selection models of the initial centroids. Most K-means researchers have pointed out the disadvantage of outliers belonging to external or other clusters instead of the concerned ones when K is big or small. Thus, the present study analyzed problems with the selection of initial centroids in the existing K-means algorithm and investigated a new K-means algorithm of selecting initial centroids. The present study proposed a method of cutting down clustering calculation costs by applying an initial center point approach based on space division and outliers so that no objects would be subordinate to the initial cluster center for dependence lower from the initial cluster center. Since data containing outliers could lead to inappropriate results when they are reflected in the choice of a center point of a cluster, the study proposed an algorithm to minimize the error rates of outliers based on an improved algorithm for space division and distance measurement. The performance experiment results of the proposed algorithm show that it lowered the execution costs by about 13–14% compared with those of previous studies when there was an increase in the volume of clustering data or the number of clusters. It also recorded a lower frequency of outliers, a lower effectiveness index, which assesses performance deterioration with outliers, and a reduction of outliers by about 60%.

The purpose of this study is to increase interest in health as human life is extended in modern society. Hence, many people in hospitals produce much medical data (EMR, PACS, OCS, EHR, MRI, X-ray) after treatment. Medical data are stored as structured and unstructured data. However, many medical data are causing errors, omissions and mistakes in the process of reading. This behavior is very important in dealing with human life and sometimes leads to medical accidents due to physician errors. Therefore, this research is conducted through the CNN intelligent agent cloud architecture to verify errors in reading existing medical image data. To reduce the error rule when reading medical image data, a faster R-CNN intelligent agent cloud architecture is proposed. It shows the result of increasing errors of existing error reading by more than 1.4 times (140%). In particular, it is an algorithm that analyses data stored by actual existing medical data through Conv feature map using deep ConvNet and ROI Projection. The data were verified using about 120,000 databases. It uses data to examine human lungs. In addition, the experimental environment established an environment that can handle GPU’s high performance and NVIDIA SLI multi-OS and multiple Quadro GPUs were used. In this experiment, the verification data composition was verified and randomly extracted from about 120,000 medical records and the similarity compared to the original data were measured by comparing about 40% of the extracted images. Finally, we want to reduce and verify the error rate of medical data reading.

The social interest in outdoor advertising signs, which have been recognized as an important element affecting impressions of a town, has been gradually increasing. However, when these signs are fully scattered around commercial areas, an oppressive feeling may be experienced by people, which cannot be neglected. Thus, this paper attempts to identify the characteristics of such visual oppression in urban landscapes through factor analysis, aiming to control them in such a way that does not oppress people. In addition, comparisons between Japanese and foreign nationals (i.e., foreign students from the Republic of Korea and the People’s Republic of China) were carried out, in order to check for any differences in perception of oppressive feelings depending on nationality. At the same time, to check for the possibility of different levels of perception depending on nationality, 20 Japanese and 20 foreign nationals (including Koreans and Chinese) were selected as test subjects. We expect this study to provide useful research material when reviewing the possibility of creating desirable urban landscapes or establishing guidelines for outdoor advertisements. For the research, landscape pictures focusing on outdoor advertising signs (15 wall, 6 roof-top, and 6 projection advertising signs) were taken as a sample for analysis. They were then presented in a 3D cyberdome for factor analysis, focusing on an impression evaluation test in relation to oppressive feelings. In addition, among the data obtained from the sample analysis, “Proportion,” which was considered to be the most influential factor on the oppressive feeling, was studied. The correlation coefficient between these two populations was 0.918, revealing a high level of correlation; thus, all subjects were treated as a single population. The factor analysis revealed 50.87% for the first factor (Evaluation), 25.39% for the second factor (capacity), and 9.47% for the third factor (Emotion), suggesting a relationship wherein the first factor decreased when the oppressive feeling increased; while the oppressive feeling increased along with the second factor.

A Micro Grid is an aggregate of many small-scale distributed energy resources (DERs); loads and can be operated independently or together with the existing power grid as a local power grid. The operator of such a grid takes charge of the energy supply and consumption of these resources and loads available in the grid. Meanwhile, the system operator of the grid considers the entire Micro Grid system to be a single load or a generator and assigns the responsibility of its internal management to the operator. The power production from a passive production resource is largely influenced by external environmental factors such as weather conditions, rather than operating conditions. Thus, this study conducted simulations for the cases where four kinds of conditional expressions had not been applied at all or one of them had been applied to compare and evaluate the effectiveness of each expression. As a result, the conditional equations were found to be effective when attempting to optimize the Micro Grids efficiently.

Although access control based on human face recognition has become popular in consumer applications, it still has several implementation issues before it can realize a stand-alone access control system. Owing to a lack of computational resources, lightweight and computationally efficient face recognition algorithms are required. The conventional access control systems require significant active cooperation from the users despite its non-aggressive nature. The lighting/illumination change is one of the most difficult and challenging problems for human-face-recognition-based access control applications. This paper presents the design and implementation of a user-friendly, stand-alone access control system based on human face recognition at a distance. The local binary pattern (LBP)-AdaBoost framework was employed for face and eyes detection, which is fast and invariant to illumination changes. It can detect faces and eyes of varied sizes at a distance. For fast face recognition with a high accuracy, the Gabor-LBP histogram framework was modified by substituting the Gabor wavelet with Gaussian derivative filters, which reduced the facial feature size by 40% of the Gabor-LBP-based facial features, and was robust to significant illumination changes and complicated backgrounds. The experiments on benchmark datasets produced face recognition accuracies of 97.27% on an E-face dataset and 99.06% on an XM2VTS dataset, respectively. The system achieved a 91.5% true acceptance rate with a 0.28% false acceptance rate and averaged a 5.26 frames/sec processing speed on a newly collected face image and video dataset in an indoor office environment.

With the current global food production capability, it is not difficult to anticipate that there will be a global food shortage when the world population grows beyond 10 billion by the end of the 21st century. Many projects are in motion to deal with this problem and some of them are considered to be quite feasible. Development and implementation of smart green houses and vertical farms are two major solutions for the expected crisis, but as other ICT-based systems, their security problems must be dealt with. Nevertheless, current network forensics is still unable to fully monitor and analyze computer network traffic to gather the evidences of malicious attacks or intrusions. Although major companies and government agencies have introduced various types of high-speed IDS into their networks, smaller firms or private organizations are unable to do so because of the cost involved. The lightweight IDS proposed in this study can be a suitable solution as this system can be operated with a common PC and peripherals. This system also underwent a test bed experiment and proved its efficiency. Jpcap library was used to capture transport packets which were then classified using typical communications protocols. The packet headers were subjected to analysis and the results were stored in database for later applications.

IoT devices are widely used in the smart home, automobile, and aerospace areas. Note, however, that recent information on thefts and hacking have given rise to many problems. The aim of this study is to overcome the security weaknesses of existing Internet of Things (IoT) devices using Blockchain technology, which is a recent issue. This technology is used in Machine-to-Machine (M2M) access payment—KYD (Know Your Device)—based on the reliability of existing IoT devices. Thus, this paper proposes a BoT (Blockchain of Things) ecosystem to overcome problems related to the hacking risk of IoT devices to be introduced, such as logistics management and history management. There are also many security vulnerabilities in the sensor multi-platform from the IoT point of view. In this paper, we propose a model that solves the security vulnerability in the sensor multi-platform by using blockchain technology on an empirical model. The color spectrum chain mentioned in this paper suggests a blockchain technique completed by using the multiple-agreement algorithm to enhance Thin-Plate Spline (TPS) performance and measure various security strengths. In conclusion, we propose a radix of the blockchain’s core algorithm to overcome the weaknesses of sensor devices such as automobile, airplane, and close-circuit television (CCTV) using blockchain technology. Because all IoT devices use wireless technology, they have a fundamental weakness over wired networks. Sensors are exposed to hacking and sensor multi-platforms are vulnerable to security by multiple channels. In addition, since IoT devices have a lot of security weaknesses we intend to show the authentication strength of security through the color spectrum chain and apply it to sensor and multi-platform using Blockchain in the future.

It is now known that more information can be leaked into the smart grid environment than into the existing environment. In particular, specific information such as energy consumption data can be exposed via smart devices. Such a phenomenon can incur considerable risks due to the fact that both the amount and the concreteness of information increase when more types of information are combined. As such, this study aimed to develop an anonymous signature technique along with a signature authentication technique to prevent infringements of privacy in the smart grid environment, and they were tested and verified at the testbed used in a previous study. To reinforce the security of the smart grid, a password and anonymous authentication algorithm which can be applied not only to extendable test sites but also to power plants, including nuclear power stations, was developed. The group signature scheme is an anonymous signature schemes where the authenticator verifies the group signature to determine whether the signer is a member of a certain group but he/she would not know which member actually signed in. However, in this scheme, the identity of the signer can be revealed through an “opener” in special circumstances involving accidents, incidents, or disputes. Since the opener can always identify the signer without his/her consent in such cases, the signer would be concerned about letting the opener find out his/her anonymous activities. Thus, an anonymous signature scheme where the signer issues a token when entering his/her signature to allow the opener to confirm his/her identity only from that token is proposed in this study.

In the Republic of Korea, one of the most widely discussed subjects related to future logistics technology is the drone-based delivery (transportation) system. Much (around 75%) of Korea’s territory consists of mountainous areas; however, the costs of installing internet facilities for drone landing sites are very high compared to other countries. Therefore, this paper proposes the power-line communication (PLC) system introduced in the author’s previous study as an alternative solution. For the system design, a number of lightning rods are used together with a monitoring system. The system algorithm performs substantial data analysis. Also, as the author found that instantaneous high-voltage currents were a major cause of fire incidents, a three-phase three-wire connection was used for the installation of the lightning rods (Bipolar Conventional Air Terminal). Thus, based on the PLC technology, an artificial intelligence (AI) which avoids lightning strikes at the drone landing site by interworking with a closed-circuit television (CCTV) monitoring system when a drone flies over the mountain regions is proposed in this paper. The algorithm was implemented with C++ and Unity/C#, whereas the application for the part concerning the integrated sensing was developed with Java Android.

Interest in green energy has increased worldwide. Therefore, smart grid projects to form a more efficient and eco-friendly intelligent grid by combining information technology (IT) technology with the existing grid are actively being conducted. In Korea, a national-level smart grid project road map has been confirmed, and an action plan has been prepared. Despite such actions, there may appear various threat scenarios in the application of the IT to the grid as a reverse function. Security technology is a measure to respond to such threats effectively. The security technology of a smart grid is an important factor that is directly related to the success or failure of the smart grid project. A smart grid is a new type of next-generation grid born of the fusion with IT. If the smart grid, the backbone of the power supply, is damaged by a cyberattack, it may cause huge damage, such as a nationwide power outage. In fact, there is an increasing cyberattack threat, and the cyber security threat to the smart grid is not insignificant. Furthermore, the legal system related to information protection is also important in order to support it systematically. In this paper, the necessity of the smart grid is examined, and the industry’s initiative toward the smart grid security threat and threat response is examined. In this paper, we also suggest a security plan of applying Rainbowchain, the Blockchain technology, to the smart grid and energy exchange. We propose achieving superior performance and security functions by using Rainbowchain, which contains seven authentication techniques among existing Blockchain technologies, and propose the ecosystem and architecture necessary for its application.

The obese population is increasing rapidly due to the change of lifestyle and diet habits. Obesity can cause various complications and is becoming a social disease. Nonetheless, many obese patients are unaware of the medical treatments that are right for them. Although a variety of online and offline obesity management services have been introduced, they are still not enough to attract the attention of users and are not much of help to solve the problem. Obesity healthcare and personalized health activities are the important factors. Since obesity is related to lifestyle habits, eating habits, and interests, I concluded that the big data analysis of these factors could deduce the problem. Therefore, I collected big data by applying the machine learning and crawling method to the unstructured citizen health data in Korea and the search data of Naver, which is a Korean portal company, and Google for keyword analysis for personalized health activities. It visualized the big data using text mining and word cloud. This study collected and analyzed the data concerning the interests related to obesity, change of interest on obesity, and treatment articles. The analysis showed a wide range of seasonal factors according to spring, summer, fall, and winter. It also visualized and completed the process of extracting the keywords appropriate for treatment of abdominal obesity and lower body obesity. The keyword big data analysis technique for personalized health activities proposed in this paper is based on individual’s interests, level of interest, and body type. Also, the user interface (UI) that visualizes the big data compatible with Android and Apple iOS. The users can see the data on the app screen. Many graphs and pictures can be seen via menu, and the significant data values are visualized through machine learning. Therefore, I expect that the big data analysis using various keywords specific to a person will result in measures for personalized treatment and health activities.

The indoor location-based control system estimates the indoor position of a user to provide the service he/she requires. The major elements involved in the system are the localization server, service-provision client, user application positioning technology. The localization server controls access of terminal devices (e.g., Smart Phones and other wireless devices) to determine their locations within a specified space first and then the service-provision client initiates required services such as indoor navigation and monitoring/surveillance. The user application provides necessary data to let the server to localize the devices or allow the user to receive various services from the client. The major technological elements involved in this system are indoor space partition method, Bluetooth 4.0, RSSI (Received Signal Strength Indication) and trilateration. The system also employs the BLE communication technology when determining the position of the user in an indoor space. The position information obtained is then used to control a specific device(s). These technologies are fundamental in achieving a “Smart Living”. An indoor location-based control system that provides services by estimating user’s indoor locations has been implemented in this study (First scenario). The algorithm introduced in this study (Second scenario) is effective in extracting valid samples from the RSSI dataset but has it has some drawbacks as well. Although we used a range-average algorithm that measures the shortest distance, there are some limitations because the measurement results depend on the sample size and the sample efficiency depends on sampling speeds and environmental changes. However, the Bluetooth system can be implemented at a relatively low cost so that once the problem of precision is solved, it can be applied to various fields.