• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.12
• /
• pp.291-306
• /
• 2020

Nowadays, Data-Network-AI (DNA)-based intelligent services and applications have become a reality to provide a new dimension of services that improve the quality of life and productivity of businesses. Artificial intelligence (AI) can enhance the value of IoT data (data collected by IoT devices). The internet of things (IoT) promotes the learning and intelligence capability of AI. To extract insights from massive volume IoT data in real-time using deep learning, processing capability needs to happen in the IoT end devices where data is generated. However, deep learning requires a significant number of computational resources that may not be available at the IoT end devices. Such problems have been addressed by transporting bulks of data from the IoT end devices to the cloud datacenters for processing. But transferring IoT big data to the cloud incurs prohibitively high transmission delay and privacy issues which are a major concern. Edge computing, where distributed computing nodes are placed close to the IoT end devices, is a viable solution to meet the high computation and low-latency requirements and to preserve the privacy of users. This paper provides a comprehensive review of the current state of leveraging deep learning within edge computing to unleash the potential of IoT big data generated from IoT end devices. We believe that the revision will have a contribution to the development of DNA-based intelligent services and applications. It describes the different distributed training and inference architectures of deep learning models across multiple nodes of the edge computing platform. It also provides the different privacy-preserving approaches of deep learning on the edge computing environment and the various application domains where deep learning on the network edge can be useful. Finally, it discusses open issues and challenges leveraging deep learning within edge computing.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.4
• /
• pp.47-58
• /
• 2022

Many 1g shaking table tests with an SDOF structure supported by a single pile were performed to evaluate the soil-structure interaction (SSI) effect. Since most structures supported by group piles are MDOF structures with columns, the SSI effect is simulated using a large 1g shaking table test and numerical analysis. According to the results, the movement in the piles tends to increase with input acceleration and when the input frequency is similar to the natural frequency. Furthermore, the slope of the dynamic p-y curve remains constant regardless of the variation of acceleration and input frequency. According to the results of the dynamic p-y backbone curve and the moment of group piles, a center pile with a leading pile has more soil resistance than side piles with a trailing pile, and the effect of group piles is observed above the 7D center to center pile distance.

• Journal of Digital Convergence
• /
• v.19 no.8
• /
• pp.11-20
• /
• 2021

Due to the Covid-19 Pandemic, the world is facing the most serious crisis since the Great Depression, and is facing a new paradigm of the Untact era. Korea has also announced various policies and legal systems, including the 'Korean version of the New Deal', but it is conflicting between the use of information and the protection of information. In this paper, we derive thresholds by analyzing policies, statutes and technologies in the public cloud. Based on this, we propose to introduce the "Building a Nationwide Public Virtual Machine" as a key task to secure the next-generation national growth engine so that all citizens can use digital services in a secure and reliable environment with equal access to information. Through this, all citizens can use various digital new technology services only with low-priced and low-specification terminals, and by establishing a dedicated center for information protection, we want to respond to rapidly increasing security threats. It also points out that the domestic cloud-related legal system only emphasizes the use of information while overlooking the importance of security, and suggests the right direction for the legal system to move forward.

• Journal of Internet Computing and Services
• /
• v.22 no.6
• /
• pp.129-140
• /
• 2021

The next generation mBcN should be built to cooperate with the wireless network to support hyper-speed and hyper-connectivity. In this paper, we propose a network architecture for the cooperation mBcN and 5G commercial network and architecture of the cooperative security gateway required for the cooperation. The proposed cooperative security gateway is between gNB and UPF to support LBO, SFC, and security. Our analysis shows that the proposed architecture has several advantages. First of all, user equipment connected with the mBcN can be easily connected through the 5G commercial radio network to the mBcN. Second, the military application traffic can be transmitted to mBcN without going through the 5G core network, reducing the end-to-end transmission delay without causing the traffic load on the 5G core network. In addition, the security level of the military application can effectively be maintained because the user equipment can be connected to the cooperative security gateway, and the traffic generated by the user equipment is transmitted to the mBcN without going through the 5G core network. Finally, we demonstrate that LBO, SFC, and security modules are essential functions of the proposed gateway in the 5G test-bed environment.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.2
• /
• pp.67-72
• /
• 2022

Recently, various intelligent application services using artificial intelligence are being actively developed. In particular, research on artificial intelligence-based real-time prediction services is being actively conducted in the manufacturing industry, and the demand for artificial intelligence services that can detect and predict fire and odors is very high. However, most of the existing detection and prediction systems do not predict the occurrence of fires and odors, but rather provide detection services after occurrence. This is because AI-based prediction service technology is not applied in existing systems. In addition, fire prediction, odor detection and odor level prediction services are services with ultra-low delay characteristics. Therefore, in order to provide ultra-low-latency prediction service, edge computing technology is combined with artificial intelligence models, so that faster inference results can be applied to the field faster than the cloud is being developed. Therefore, in this paper, we propose an LSTM algorithm-based learning model that can be used for fire prediction and odor detection/prediction, which are most required in the manufacturing industry. In addition, the proposed learning model is designed to be implemented in edge devices, and it is proposed to receive real-time sensor data from the IoT terminal and apply this data to the inference model to predict fire and odor conditions in real time. The proposed model evaluated the prediction accuracy of the learning model through three performance indicators, and the evaluation result showed an average performance of over 90%.

• Journal of the Korea Institute of Building Construction
• /
• v.22 no.4
• /
• pp.347-358
• /
• 2022

In order to satisfy the extraction and use of information such as estimates and processes required in the design and construction stages of BIM, which is an expectation of overall construction operation for the design and construction stage of domestic buildings, it is insufficient to supply and apply mobile technologies or terminals. In this paper, standardization of BIM-based processes from the design stage to the construction stage is proposed as an efficient construction system method through mobile-based simulation and test-bed case analysis review. The current status and potential of BIM application were identified through theoretical review of BIM and case studies at home and abroad. In addition, the overall flow of the project and the direction of effective process construction were investigated through each process by 3D, 4D, and 5D execution stage and the role of each collaborator. 4D building process BIM simulation system using mobile was implemented by applying a visualization engine that simulates process information, object information connection module, and related object information. Therefore, it was possible to minimize the possibility of re-construction of the BIM design and construction process model through the visualization of 2D drawings based on the 3D model of the building and the review of errors and interferences in the drawings. In addition, in the implementation of simulation for each process of the construction process through mobile devices, it was possible to support construction progress and process management according to the optimal option selected by the user.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.6
• /
• pp.17-28
• /
• 2022

The effect of the soil-structure interaction (SSI) on has been recently evaluated in shaking table tests. However, most of these tests were conducted on single-degree-of-freedom (SDOF) superstructures and a single-pile. This study investigates the inertial interaction effect of a multi-degree-of-freedom (MDOF) superstructure system with a group piles on a large-scale shaking table test. Whereas the SDOF superstructure system shows a single-frequency amplification tendency, the MDOF superstructure system exhibited amplification tendencies of the acceleration phase and frequency responses for multiple frequencies. In addition, the amplification phenomenon between the footing and the column-type superstructure exceeded that between the footing and the wall-type superstructure, indicating a greater inertial interaction effect of the column-type superstructure. The relationship between shear force and inertial force, the relative vertical and horizontal displacements on the footing was figured out. Also, the ananlysis of dynamic p-y curve at each depth was conducted. In summary, the MDOF and SDOP superstructure systems exhibited different behaviors and the column-type superstructure exerted a higher interaction effect than the wall-type superstructure.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.619-625
• /
• 2023

In this paper, the remote care of medical beds with multiple body pressure sensors is described. Falling is one of the factors that seriously threaten the safety of patients and harm their health. In this study, a new bed was developed to overcome this. The bed system consists of a keyboard that can operate, a keyboard controller that manages the movement of the keyboard, a sensor that measures body pressure, a sensor controller that transmits and receives sensor values, a main controller that checks it and operates automatically or manually according to the algorithm, and a server that oversees all these information. The bed system checks the patient's location through a sensor and wirelessly alerts the server through the main controller when the patient determines that there is a risk of falling, so that the nurse or nurse can recognize the patient's dangerous condition. The server may receive state data transmitted from the wired/wireless terminal to monitor whether the bed system is operating normally. The controller of the keyboard operates a keyboard-type mechanism and automatically controls the prevention of bedsores connected by body pressure sensors to physically separate the area to which the patient's pressure is applied to prevent bedsores. The main controller checks the presence of the patient's bed and transmits it to the server. In conclusion, the proposed system can smart monitor the user's state and perform remote care.

• Journal of the Korean Geotechnical Society
• /
• v.26 no.8
• /
• pp.77-88
• /
• 2010

In this study, 1 g shaking table group pile tests were performed for various conditions of subgrade and pile spacing. The pile spacing was changed from three to seven times of pile diameters. It could be confirmed that the dynamic p-y curves for the group pile observed as the results of a series of shaking table tests show difference according to the pile spacing, the pile location within the pile group, the relative density of subgrade and the excess pore pressure during earthquake. The dynamic p-multipliers were calculated by comparing the dynamic p-y backbone curves of a single pile suggested by Yang (2009) and dynamic p-y curves for the group pile. Dynamic p-multiplier values overall increase as the relative density of subgrade and amplitude of input acceleration increase. The dynamic group pile effect was neglected, if the pile spacing was seven times as large as pile diameters. It was found that the exisiting p-multiplier values suggested by various researchers for the static and dynamic loading, and the values recommended by globally used specifications show difference with the test results by up to 0.7 (approximately 70%). Therefore, the dynamic p-multipliers were newly suggested according to the pile spacing and the relative density of subgrade using the test results.

• Journal of the Korean Geotechnical Society
• /
• v.26 no.8
• /
• pp.27-37
• /
• 2010

Downdrag force develops when a pile is driven through a soil layer which will settle more than a pile. There is no obvious criterion for application of the current pile design method considering the negative skin friction. Therefore, in this study, numerical analyses were performed to investigate the behavior of a single pile subjected to negative skin friction and their results were used to determine the applicability of the current design method. Including three different sites in Song-do area and two different cases with friction pile and end bearing pile conditions, total six cases were considered. The load-settlement relationships and the neutral points were estimated for different end bearing conditions and the allowable bearing capacity of piles with negative skin friction was investigated through parametric studies. Based on the results showed that the negative skin friction made a major influence on the settlement of a pile and its stress. However the allowable bearing capacity may not be influenced by the negative skin friction. Compared with the allowable bearing capacity obtained from the ultimate bearing capacity with the safety factor of 3, the current design method with the safety factor of 3 underestimated the allowable bearing capacities regardless of the end bearing conditions. On the other hand, the current design method with the safety factor of 2 yielded reasonable results depending on the end bearing conditions.