• Smart Structures and Systems
• /
• v.32 no.3
• /
• pp.179-193
• /
• 2023

This study explores an alternative to the existing centralized process for data anomaly detection in modern Internet of Things (IoT)-based structural health monitoring (SHM) systems. An edge intelligence framework is proposed for the early detection and classification of various data anomalies facilitating quality enhancement of acquired data before transmitting to a central system. State-of-the-art deep neural network pruning techniques are investigated and compared aiming to significantly reduce the network size so that it can run efficiently on resource-constrained edge devices such as wireless smart sensors. Further, depthwise separable convolution (DSC) is invoked, the integration of which with advanced structural pruning methods exhibited superior compression capability. Last but not least, quantization-aware training (QAT) is adopted for faster processing and lower memory and power consumption. The proposed edge intelligence framework will eventually lead to reduced network overload and latency. This will enable intelligent self-adaptation strategies to be employed to timely deal with a faulty sensor, minimizing the wasteful use of power, memory, and other resources in wireless smart sensors, increasing efficiency, and reducing maintenance costs for modern smart SHM systems. This study presents a theoretical foundation for the proposed framework, the validation of which through actual field trials is a scope for future work.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.279-286
• /
• 2005

The objective of this study is to suggest a credit scoring model of a capital company's customers by integration of multiple classifiers using genetic algorithm. For this purpose , an integrated model is derived in two phases. In first phase, three types of classifiers MLP (Multi-Layered Perceptron), RBF (Radial Basis Function) and linear models - are trained, in which each type has three ones respectively so htat we have nine classifiers totally. In second phase, genetic algorithm is applied twice for integration of classifiers. That is, after htree models are derived from each group, a final one is from these three, In result, our suggested model shows a superior accuracy to any single ones.

• Journal of Korean Society of Water and Wastewater
• /
• v.27 no.1
• /
• pp.11-20
• /
• 2013

This Study includes the information of integrated discussion and economies of scale on local governments' sewerage treatment plant through translog function based on the reality reports of sewerage treatment plant operation published by Ministry of Environment and sewerage statistics data from 2005 to 2010. Based on analysis results from the data of 35 local governments in Jeollanamdo and Jeollabukdo, which are selected as pilot project areas of sewerage facility integration by Ministry of Environment and have low percent of sewered population, it shows the existence of economies of scale. The economies of scale on sewerage treatment show the loss of approximately 22,211 thousand ton/day in sewage treatment, it is 1.7 times compared to the average treatment amount of 35 local governments as of 2010. It means the economies of scale can be achieved by lowering operation cost along with large scale integration in installation, operation and maintenance due to the features of sewerage industry as one of network industry.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2008.06a
• /
• pp.346-346
• /
• 2008

최근 디지털 컨버젼스에 의해서 정보 단말기 network가 디지털 기술을 기반으로 유기적으로 융 복합화 되고 있으며 BT, NT, ET, IT의 융합 기술의 필요성이 점차적으로 증대되고 있다. 이러한 환경 하에서 다양한 정보 및 서비스의 송신 및 수신이 가능한 휴대 단말기의 필요성에 부응하여 기존의 전화 기능, 카메라, DMB 이외에도 홈 네트워크, mobile internet 등 더욱 다양한 기능들이 요구되고 있다. 종래에는 수동 부품과 능동 부품의 실장을 별개로 추진했으나 최근에는 수동 및 능동 부품을 하나의 패키지 내에 실장 가능하도록 하는 3-D Integration을 추진하고 있다. 지금까지 여러 부품들을 실장 시키기 위한 공정들의 대부분은 높은 온도에서 공정이 이루어졌으나 여러 부품들을 손상 없이 집적화하고 실장하기 위해서는 저온화 공정이 필요하다. 최근 많은 저온 공정 중에서 Aerosol Deposition Method는 상온에서 세라믹 후막을 성막할 수 있어 가장 주목받고 있는 공정중의 하나이다. 본 연구에서는 3-D Integration을 실현하기 위해 이종 접합에 유리하고 상온에서 성막 공정이 이루어지는 Aerosol Deposition Method를 이용하여 금속 기판 위에 금속, 폴리머, 세라믹 후막을 성막시켰다. 기판 재료로는 Cu 기판을 사용하였으며 출발 파우더로는 Polyimide 파우더와 $Al_2O_3$ 파우더, Ag 파우더를 사용하였으며 이종 접합간의 메커니즘의 양상을 보기 위해 같은 조건에서 이종 접합간의 성막률을 비교하였으며 FE-SEM으로 미세 구조를 관찰하였다. 또한 기판의 표면 거칠기에 따른 메커니즘의 양상을 연구하였다.

• Korean Journal of Construction Engineering and Management
• /
• v.8 no.4
• /
• pp.119-127
• /
• 2007

Cost and Schedule is the most important information, and how efficiently manage this information is the key issue for Construction Project Management. Domestically, systematic scheduling method such as CPM network is not only used widely but integration of time and cost information also is. In order to effectively integrate and use the time and cost information, it is suggested that WBS(Work Breakdown Structure) based QDB(Quantity Database) should be generated from the design phase and, WBS and QDB related system tool should be supported. It could be helpful to relate and integrate other construction project information.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.894-907
• /
• 2022

The features extracted by convolutional neural networks are more descriptive of images than traditional features, and their convolutional layers are more suitable for retrieving images than are fully connected layers. The convolutional layer features will consume considerable time and memory if used directly to match an image. Therefore, this paper proposes a feature weighting and region integration method for convolutional layer features to form global feature vectors and subsequently use them for image matching. First, the 3D feature of the last convolutional layer is extracted, and the convolutional feature is subsequently weighted again to highlight the edge information and position information of the image. Next, we integrate several regional eigenvectors that are processed by sliding windows into a global eigenvector. Finally, the initial ranking of the retrieval is obtained by measuring the similarity of the query image and the test image using the cosine distance, and the final mean Average Precision (mAP) is obtained by using the extended query method for rearrangement. We conduct experiments using the Oxford5k and Paris6k datasets and their extended datasets, Paris106k and Oxford105k. These experimental results indicate that the global feature extracted by the new method can better describe an image.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.4
• /
• pp.591-600
• /
• 2005

In this paper, we discuss real-time control of networked control systems (NCSs) and practical issues in the choice of the communication networks for this purpose. An appropriate integration of control systems, real-time environments, and network communication systems allows the optimization of the quality-of-control (QoC) in NCSs. We compare several prevailing network types that may be used in control applications to offer a guideline of choosing a proper network. A real-time operating environment is also presented as an important ingredient of NCS design. To evaluate its feasibility and effectiveness, a real-time NCS containing a ball magnetic levitation (Maglev) setup is implemented via an Ethernet. Based on the experimental results, it is concluded in this paper that real-time control via Ethernet is a practical and feasible solution to NCS design.

• Smart Media Journal
• /
• v.1 no.1
• /
• pp.58-63
• /
• 2012

It is a superordinate concept to a network control system which optimally distributes the battery power to overall length parts through the linkage control drive and absorbs/integrates network diagnostics and overlapped functions with overall length control systems. This study is to develop a system that maximize the battery power and motor effectiveness by controlling motor battery controlling module with common MCU Integration linkage controlling system, and to develop S/W and H/W that can be controlled by linked with each controlling module in CAN method through using Autosar's standardized software.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.439-441
• /
• 2012

The use of a mobile agent in hospital environment offers an opportunity to deliver better services for patients and staffs. Furthermore, medical errors will be reduced because M-health system helps to verify the medical process. Optimized security protocols and mechanisms are employed for the high performance and security. Finally, a challenge in the near future will be converge the integration of Ubiquitous Sensor Network (USN) with security protocols for applying the hospital environment. We proposed secure authentication and protocol with Mobile Agent for ubiquitous sensor network under healthcare system surroundings.

• Proceedings of the IEEK Conference
• /
• 2003.07c
• /
• pp.2537-2540
• /
• 2003

In this paper, an integrated monitoring system is implemented for industrial equipments which use different types of network protocols to communicate with other equipments. Dedicated gateway systems mate it difficult to modify or to add contents of network systems for communication with other systems. We suggest an integration method of effectively utilizing the general purpose gateway system (ETOS-l00A) which converts various types of protocols into TCP/IP protocol. To demonstrate the validity of the proposed integrated monitoring system, PLC-based automated inspection system is considered and the monitoring system is implemented using Visual Basic and HMI software.