• 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 Information Technology Services
• /
• v.20 no.6
• /
• pp.141-150
• /
• 2021

With the recent spread of the concept of Smart Cities which is to solve urban problems with ICT technology, Living Lab, which identifies the demands of citizens who dwell in the city and verifies the acceptability of the services being introduced, has become an important topic. Living Lab is an open innovation platform introduced in consideration of the user's perspective in real life and is a new approach in that service developers use collective intelligence in the process of Co-creation with users. Living Lab is operated on topics which is close to citizens' daily lives such as energy, housing, transportation, and education. In particular, as energy and environmental-focused Living Lab emerges in accordance with the 'Korean New Deal Policy', interest and importance in the field are increasing. The paper derives the characteristics of water resource Living Lab through case analysis of several Living Lab practices. Water resource Living Lab in Daejeon and Chuncheon, which are located in Korea, and water resource Living Lab in Romania and Indonesia are covered in this paper as the reference. The paper finally analyzes the case of Sambang Water Living Lab in Gimhae, which is the city located in southern part of Korea. As a result of case analysis, the urban water resource Living Lab focuses on the raw water of urban water resource and should respond sensitively to the safety of citizens. And for the success of this urban water resource Living Lab, it is essential to ensure that citizens participating in the Living Lab clearly understand the concept of water resources, and citizens' opinions to be implemented as services.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1287-1294
• /
• 2021

This paper is a study on the implementation of a sensor-based smart compression system for improving home and street environments. Since modernization, the amount of garbage has been increasing every year, and this has seriously adversely affected not only people but also ecosystems such as marine pollution and soil pollution. In particular, in large cities with large floating populations, garbage is dumped on the streets without proper measures to deal with the amount of waste generated. In order to improve this problem, this paper intends to implement a system with automatic compression and opening/closing functions using sensors. This system is designed to activate automatic opening/closing function through an infrared sensor, and automatically opening and closing when the inclination is changed using an impact sensor. In addition, by installing a distance sensor, the amount of internal waste can be easily monitored from the outside, and a manual compression switch and a manual opening/closing switch is separately designed to enable opening and closing and compression as needed to increase the effectiveness.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.335-349
• /
• 2023

Bridges constantly undergo deterioration and damage, the most common ones being concrete damage and exposed rebar. Periodic inspection of bridges to identify damages can aid in their quick remediation. Likewise, identifying components can provide context for damage assessment and help gauge a bridge's state of interaction with its surroundings. Current inspection techniques rely on manual site visits, which can be time-consuming and costly. More recently, robotic inspection assisted by autonomous data analytics based on Computer Vision (CV) and Artificial Intelligence (AI) has been viewed as a suitable alternative to manual inspection because of its efficiency and accuracy. To aid research in this avenue, this study performs a comparative assessment of different architectures, loss functions, and ensembling strategies for the autonomous segmentation of bridge components and damages. The experiments lead to several interesting discoveries. Nested Reg-UNet architecture is found to outperform five other state-of-the-art architectures in both damage and component segmentation tasks. The architecture is built by combining a Nested UNet style dense configuration with a pretrained RegNet encoder. In terms of the mean Intersection over Union (mIoU) metric, the Nested Reg-UNet architecture provides an improvement of 2.86% on the damage segmentation task and 1.66% on the component segmentation task compared to the state-of-the-art UNet architecture. Furthermore, it is demonstrated that incorporating the Lovasz-Softmax loss function to counter class imbalance can boost performance by 3.44% in the component segmentation task over the most employed alternative, weighted Cross Entropy (wCE). Finally, weighted softmax ensembling is found to be quite effective when used synchronously with the Nested Reg-UNet architecture by providing mIoU improvement of 0.74% in the component segmentation task and 1.14% in the damage segmentation task over a single-architecture baseline. Overall, the best mIoU of 92.50% for the component segmentation task and 84.19% for the damage segmentation task validate the feasibility of these techniques for autonomous bridge component and damage segmentation using RGB images.

• Smart Media Journal
• /
• v.13 no.2
• /
• pp.108-121
• /
• 2024

In the IT industry, the complexity and volatility of corporate networks are gradually evolving, and concurrently, the significance of corporate networks is increasing. Previous research has employed network analysis to scrutinize inter-corporate trade relationships for strategic and policy making. However, previous studies focused on the overall network structure from a macroscopic perspective, presenting limitations in applicability at the individual IT corporation level. This study develops a novel research model incorporating sector and region-level network analysis based on connection strength, along with the derivation of a composite node centrality indicator. Using this methodology, we analyzed corporate networks across nine metropolitan areas using IT corporate transaction data. The results means that cities with a manufacturing base, such as Incheon, Busan, and Daegu, have recently established cooperative networks with IT companies. We also found that in the IT industry in Gwangju and Daejeon, certain companies dominate the transaction network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1527-1552
• /
• 2018

The rapidly-evolving demand of applications using wireless sensor networks in several areas such as building and industrial automation or smart cities, among other, makes it necessary to determine and provide QoS support mechanisms which can satisfy the requirements of applications. In this paper we propose a mechanism that establishes different QoS levels, based on Publish/Subscribe model for wireless networks to meet application requirements, to provide reliable delivery of packet and timeliness. The first level delivers packets in a best effort way. The second one intends to provide reliable packet delivery with a novel approach for Retransmission Timeout (RTO) calculation, which adjusts the RTO depending on the subscriber Packet Delivery Ratio (PDR). The third one provides the same reliable packet delivery as the second one, but in addition, it provides data aggregation trying to be efficient in terms of energy consumption and the use of network bandwidth. The last one provides timeliness in the packet delivery. We evaluate each QoS Level with several performance metrics such as PDR, Message Delivery Ratio, Duplicated and Retransmitted Packet Ratio and Packet Timeliness Ratio to demonstrate that our proposal provides significant improvements based on the increase of the PDR obtained.

• Journal of Distribution Science
• /
• v.18 no.9
• /
• pp.19-30
• /
• 2020

Purpose: As an environmental concern increases, customers pay more attention to purchase organic food. While customers' purchase intention of organic food has been widely studied, there are lacks of researches regarding the moderation effect of environmental concern and the interactive effect of level of education based on the Theory of Planned Behavior (TPB). This study examines the influence of level of education and environmental concern on purchase intention based on the Theory of Planned Behavior and organic food in Vietnam. Research design, data and methodology: The methodology of mixed methods of qualitative and quantitative is applied with a survey of 420 customers being conducted to collect data from three biggest cities in Vietnam: Ho Chi Minh, DaNang and Hanoi. SPSS 23 and SMART-PLS 3.2 are used for data analysis. Results: The result shows that the customers have more environmental concern which increases their attitude to the intention of purchasing organic food. Moreover, there has not the three-way interactive effect of level of education, environmental concern and attitude on purchase intention toward organic food. Conclusions: This enriches the existing literature with the moderation of environmental concern to the relationship between attitude and purchase intention toward organic food in Vietnam based on the Theory of Planned Behavior.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.33-39
• /
• 2008

Most New Zealanders reside in coastal regions and four of the larger cities are situated on active floodplains. There have been many recent storm events with rainfall AEPs of 1/150 or rarer and there have been recent flood-related disasters. Insurance claim statistics indicate that the frequency of floods is increasing. Such statistics are alarming local government authorities, insurance companies and populations in low-lying areas. The underlying physical and hydrologic causes of the flood disasters are investigated. It is found that the present numbers of rare rainfall events are not unexpected and there does not appear to be any significant trend evident in the occurrence of river floods. What is revealed is that the river floods appear clustered in certain decades. The clusters do not occur at the same times in different parts of the county. Recently there have been more floods in the north of New Zealand which is where more of the population lives. Also, the increase in population has seen more houses built in locations prone to flooding. Thus the increase in flood-related insurance claims is attributed to more people getting in the way of floods, rather than an increase in the number of floods that have occurred.

• Smart Structures and Systems
• /
• v.26 no.1
• /
• pp.1-10
• /
• 2020

Turkey is a transcontinental country located partly in Asia and partly in Europe, and hosted by diverse civilizations including Hittite, Urartu, Lydia, Phrygia, Pontius, Byzantine, Seljuk's and Ottomans. At various times, these built many historic monuments representing the most significant characteristics of their civilizations. Today, these monuments contribute enormously to the esthetic beauty of environment and important to many cities of Turkey in attracting tourism. The survival of these monuments depends on the investigation of structural behavior and implementation of needed repairing and/or strengthening applications. Hence, many countries have made deeper investigations and regulations to assess their monuments' structural behavior. This paper presents the dynamic behavior investigation of a monumental masonry mosque, the "İskenderpaşa Mosque" in Trabzon (Turkey), by performing an experimental examination with non-destructive testing. The dynamic behavior investigation was carried out by determining the dynamic characteristic called as natural frequencies, mode shapes and damping ratios. The experimental dynamic characteristics were extracted by Operational Modal Analysis (OMA). In addition, Finite Element (FE) model of masonry mosque was constructed in ANSYS software and the numerical dynamic characteristics such as natural frequencies and mode shapes were also obtained and compared to experimental ones. The paper aims at presenting the non-destructive testing procedure of a masonry mosque as well as the comparison of experimental and numerical dynamic characteristics obtained from the mosque.