• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.233-248
• /
• 2023

In the process of building the future of smart cities, innovation in mobility and road infrastructure is one of the most important topics. In particular, with the proliferation of autonomous vehicles and various types of mobility on the road, such as electric bicycles, electric kickboards, and electric wheels, roads have a variety of actors to accommodate, including traditional cars and pedestrians, and conflicts between them need to be resolved. Complete streets, a term coined in the United States in 2003, refers to the design and operation of roads that consider the equitable safety and convenience of all road users, including pedestrians, bicyclists, public transportation users, personal mobility (PM) users, and automobile drivers. Currently, many cities overseas are implementing complete streets, and research is being actively conducted to institutionalize them. However, there is a lack of research and discussion on complete streets in Korea. Therefore, this study aims to formalize the main factors to be considered in the design of complete streets by collecting and analyzing the opinions of academic and practitioner experts through the Delphi method. A total of three Delphi surveys were conducted, collecting free responses from experts through the first open-ended survey and organizing them into keywords to create the second and third closed-ended surveys. The second and third rounds of the survey consisted of a total of 52 questions, and 34 items out of 52 were selected as the final factors.

• Journal of Wetlands Research
• /
• v.26 no.3
• /
• pp.245-253
• /
• 2024

Blue-green algal bloom, or harmful algal bloom has a negative impact on the aquatic ecosystem and purified water supply system due to oxygen depletion in the water body, odor, and secretion of toxic substances in the freshwater ecosystem. This Blue-green algal bloom is expected to increase in intensity and frequency due to the increase in algae's residence time in the water body after the construction of the Nakdong River weir, as well as the increase in surface temperature due to climate change. In this study, in order to respond to the expected increase in green algae phenomenon, an algal bloom forecast system based on hydro-meteorological factors was presented for preemptive response before issuing a algal bloom warning. Through polyserial correlation analysis, the preceding influence periods of temperature and discharge according to the algal bloom forecast level were derived. Using the decision tree classification, a machine learning technique, Classification models for the algal bloom forecast levels based on temperature and discharge of the preceding period were derived. And a algal bloom forecast system based on hydro-meteorological factors was derived based on the results of the decision tree classification models. The proposed algae forecast system based on hydro-meteorological factors can be used as basic research for preemptive response before blue-green algal blooms.

• Informatization Policy
• /
• v.26 no.3
• /
• pp.69-89
• /
• 2019

In order to implement smart cities that will become living spaces in the fourth industrial revolution era, detailed privacy information such as residents' living information, buildings and facilities information must be collected and processed in real time. While city functions and convenience for individuals are being facilitated, threats to personal information exposure and leakage are also likely to increase at the same time. Therefore, the design concept for personal information protection should be considered and accordingly reflected from the stages of smart city design, technology development and operation planning of intelligent information (AI) facilities. The results of the analysis show that for activation of smart cities and operation of data-driven cities, the concept of Privacy by Design (PbD) has already been introduced in the institutional, industrial and technological aspects, particularly in the cases of European countries and the US. In order to strengthen the local and global competitiveness of smart cities and the country, Korea also needs to actively deploy PbD as a strategy to secure a data-driven economy, which is the core strategy for smart cities. Therefore, the study suggests policy implications focused on approaches to legislative improvement and technology development support, which reflect the basic properties of PbD as defined in the study.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.41 no.5
• /
• pp.493-504
• /
• 2021

The target site, Goejeongcheon flows through downtown of Saha-gu, Busan and it connects to the Nakdong-gang estuary. But non-point pollutants and sewage sludge are partially flowing into the stream and deposited. As a result, dissolved oxygen concentrations of the stream were observed close to the anaerobic condition. Multistage Vortex Aerator was applied for restoring this urban stream. It dissolves oxygen by repeatedly causing collisions between water and oxygen by vortex flow. The changes in water quality and odor were monitored for 2 months while circulating 1 m³/min of water with 22 ppm dissolved oxygen. As a result of the operation, the dissolved oxygen was improved from slightly Bad (4)~Bad (5) to Good (1b)~Normal (3) grade, and the total phosphorus concentration was decreased by 76 % on average. In the case of complex odor, a maximum reduction of 84.5 % was observed on the day the entire river was anaerobic. Through this study, we evaluated the feasibility of applying pure oxygen and Vortex Aerator for the the stream restoration. It is expected that the results of this study can be used for full-scale design.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.6
• /
• pp.7-14
• /
• 2019

The automatic monitoring and detection of crowd behavior in the surveillance videos has obtained significant attention in the field of computer vision due to its vast applications such as security, safety and protection of assets etc. Also, the field of crowd analysis is growing upwards in the research community. For this purpose, it is very necessary to detect and analyze the crowd behavior. In this paper, we proposed a deep learning-based method which detects abnormal activities in surveillance cameras installed in a smart city. A fine-tuned VGG-16 model is trained on publicly available benchmark crowd dataset and is tested on real-time streaming. The CCTV camera captures the video stream, when abnormal activity is detected, an alert is generated and is sent to the nearest police station to take immediate action before further loss. We experimentally have proven that the proposed method outperforms over the existing state-of-the-art techniques.

• Journal of Cadastre & Land InformatiX
• /
• v.51 no.1
• /
• pp.67-77
• /
• 2021

Spatial data is becoming very important as a medium that connects various data produced in smart cities, digital twins, autonomous driving, smart construction, and other applications. In addition, the rapid construction and update of spatial information is becoming a hot topic to satisfy the diverse needs of consumers in this field. This study developed a software prototype that can match the position of an image-based 3D building model produced without Ground Control Points using existing spatial data. As a result of applying this software to the test area, the 3D building model produced based on the image and the existing spatial data show a high positional matching rate, so that it can be widely used in applications requiring the latest 3D spatial data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1762-1769
• /
• 2021

The final goal of this study is to develop a system that can analyze whether a wanted vehicle is a criminal vehicle from images collected from black boxes, smartphones, CCTVs, and so on. Data collection was collected using a self-developed black box. The used data in this study has used a total of 83,753 cases such as the eight vehicle types(truck, RV, passenger car, van, SUV, bus, sports car, electric vehicle) and 434 vehicle models. As a result of vehicle recognition using YOLO v5, mAP was found to be 80%. As a result of identifying the vehicle model with ReXNet using the self-developed black box, the accuracy was found to be 99%. The result was verified by surveying field police officers. These results suggest that improving the accuracy of data labeling helps to improve vehicle recognition performance.

• Journal of the Korean Geotechnical Society
• /
• v.39 no.12
• /
• pp.103-114
• /
• 2023

Monitoring the site of an underground construction wall is crucial to confirm the stability of the supports and ground due to excavation. In particular, it is essential to maintain the accuracy of a load cell gauge, which identifies the load of the support transmitted from the excavated ground. However, research on verification methods and regulations that can identify the accuracy of load cell gauges at construction sites is inadequate, which is a problem as load cell gauges are installed without proper performance inspections. In this study, performance tests were conducted by a complete investigation of load cell gauges sold in Korea and comparing them with foreign products to determine defect causes. In addition, the criteria for selecting a load cell gauge were presented, and the results of this study were considered to help select a highly reliable load cell gauge.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.93-104
• /
• 2024

Demand response is a strategy that encourages customers to adjust their consumption patterns at times of peak demand with the aim to improve the reliability of the power grid and minimize expenses. The integration of renewable energy sources into smart grids poses significant challenges due to their intermittent and unpredictable nature. Demand response strategies, coupled with reinforcement learning techniques, have emerged as promising approaches to address these challenges and optimize grid operations where traditional methods fail to meet such kind of complex requirements. This research focuses on investigating the application of reinforcement learning algorithms in demand response for renewable energy integration. The objectives include optimizing demand-side flexibility, improving renewable energy utilization, and enhancing grid stability. The results emphasize the effectiveness of demand response strategies based on reinforcement learning in enhancing grid flexibility and facilitating the integration of renewable energy.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.4
• /
• pp.113-126
• /
• 2024

Shotcrete lining is an important material for the stability of tunnels in NATM tunnels. However, stressmeters for stress measurements of shotcrete lining are installed in the field without performance verification because of a lack of research on methods, procedures, regulations, and reliability of measurement equipment. To solve this problem, all shotcrete stressmeters currently used in Korea were investigated. For each stressmeter, external inspection and structural and functional inspection were performed to identify defects and problems in devices. For this purpose, a shotcrete stressmeter performance test device capable of load loading in stages was developed and obtained KOLAS certification. Using the device, stressmeter performance tests were conducted. Structural problems of integrated- and cell-type shotcrete stressmeters were identified through concrete mold tests, and improvement plans and performance verification procedures were suggested. The results of this study are expected to contribute to the preparation of regulations for the performance verification of shotcrete stressmeters and the selection of measuring instruments in the field in the future.