• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.242-252
• /
• 2021

Following the intuition that the local information in time instances is hardly incorporated into the posterior sequence in long short-term memory (LSTM), this paper proposes an attention augmented mechanism for fault diagnosis of the complex chemical process data. Unlike conventional fault diagnosis and classification methods, an attention mechanism layer architecture is introduced to detect and focus on local temporal information. The augmented deep network results preserve each local instance's importance and contribution and allow the interpretable feature representation and classification simultaneously. The comprehensive comparative analyses demonstrate that the developed model has a high-quality fault classification rate of 95.49%, on average. The results are comparable to those obtained using various other techniques for the Tennessee Eastman benchmark process.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.11a
• /
• pp.57-58
• /
• 2010

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2005.11a
• /
• pp.81-85
• /
• 2005

Recently, fire resistance of high performance concrete for explosive spalling was issued as high performance concrete was vulnerable to the explosive spalling in initial fire. Therefore, in this study, an experiment about reduction effect to explosive spalling of high performance concrete is performed by adding several polymer fiber with various volume fraction, an then final fiber and volume fraction of that which reduce the explosive spalling of high performance concrete is presented. As the result of this study, the most fitted fiber volume fraction of reducing effect for explosive spalling at high performance concrete is under the 0.1%, as consider the flowability and efficiency.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.25-28
• /
• 2020

Automatic segmentation of brain tissues such as WM, GM, and CSF from brain MRI scans is helpful for the diagnosis of many neurological disorders. Accurate segmentation of these brain structures is a very challenging task due to low tissue contrast, bias filed, and partial volume effects. With the aim to improve brain MRI segmentation accuracy, we propose an end-to-end convolutional based U-SegNet architecture designed with multi-scale kernels, which includes cascaded dilated convolutions for the task of brain MRI segmentation. The multi-scale convolution kernels are designed to extract abundant semantic features and capture context information at different scales. Further, the cascaded dilated convolution scheme helps to alleviate the vanishing gradient problem in the proposed model. Experimental outcomes indicate that the proposed architecture is superior to the traditional deep-learning methods such as Segnet, U-net, and U-Segnet and achieves high performance with an average DSC of 93% and 86% of JI value for brain MRI segmentation.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.12 no.2
• /
• pp.69-77
• /
• 2006

Angiography means that a check up to know an abnormal condition in all the blood vessels include from the heart, aortae, cerobrovascular and abdonominal artery to hands and feet. Main examples of this are cerebral angiography, abdominal, liver for urinary anomaly, renovascular angiography, and artery and vein in arms and legs. Angiography uses radial rays or angiography equipment for an image output during interventional procedure and compositive diagnosis. The acts which performed in a projection room have changed drastically. In general, it is performed by using equipment which is attached one or two C-arms and the method of inserting catheter in vein after anesthesia. For this reason, some rooms that consist of angiography room units should be planned not only for expensiveness equipment and facilities also to be germ-free. Nowadays, in the angiography unit case, it is placed independently as the central part of many hospitals. It does not belong to the imaging medical department any more as considering raising filming times and the relation between C.C.U.(coronary care unit) and operation unit. This means the acts performed are diversified and well-organized rooms in support of diagnosis are required. However, it is difficult to plan the angiography room unit due to domestic researches and data on this unit are not enough. Therefore, this study aims at bringing up basic issue for architectural planning of the angiography unit in general hospital.

• KNOM Review
• /
• v.23 no.1
• /
• pp.18-25
• /
• 2020

Recently, a research on a smart factory was developed from a concept of factory automation(FA) to the formation of collecting and analyzing data. This trend is accelerated as the development of communication technology(5G) and IoT devices are developed in various ways according to the field situation. In addition, digital transformation has been actively conducted in the strengthening corporate competitiveness, and various optimization studies are being conducted through process re-adjustment by combining data received from various IoT equipment and automated facilities. Therefore, in this paper, we propose a system architecture and its related components in diagnosing and repairing facility failure using a prediction system which is one of the related researches.

• Journal of the Korea Institute of Building Construction
• /
• v.21 no.6
• /
• pp.665-676
• /
• 2021

As the number of deteriorated buildings increases, the importance of safety diagnosis and maintenance of buildings has been rising. Existing visual investigations and building safety diagnosis objectivity and reliability are poor due to their reliance on the subjective judgment of the examiner. Therefore, this study presented the limitations of the previously conducted appearance investigation and proposed 3D Point Cloud data to increase the accuracy of existing detailed inspection data. In addition, this study conducted a calculation of an objective building safety grade using a Deep-Neural Network(DNN) structure. The DNN structure is generated using the existing detailed inspection data and precise safety diagnosis data, and the safety grade is calculated after applying the state evaluation data obtained using a 3D Point Cloud model. This proposed process was applied to 10 deteriorated buildings through the case study, and achieved a time reduction of about 50% compared to a conventional manual safety diagnosis based on the same building area. Subsequently, in this study, the accuracy of the safety grade calculation process was verified by comparing the safety grade result value with the existing value, and a DNN with a high accuracy of about 90% was constructed. This is expected to improve economic feasibility in the future by increasing the reliability of calculated safety ratings of old buildings, saving money and time compared to existing technologies.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.8 no.3
• /
• pp.243-251
• /
• 2016

Autonomous Underwater Vehicles (AUVs) generally work in complex marine environments. Any fault in AUVs may cause significant losses. Thus, system reliability and automatic fault diagnosis are important. To address the actuator failure of AUVs, a fault diagnosis method based on the Gaussian particle filter is proposed in this study. Six free-space motion equation mathematical models are established in accordance with the actuator configuration of AUVs. The value of the control (moment) loss parameter is adopted on the basis of these models to represent underwater vehicle malfunction, and an actuator failure model is established. An improved Gaussian particle filtering algorithm is proposed and is used to estimate the AUV failure model and motion state. Bayes algorithm is employed to perform robot fault detection. The sliding window method is adopted for fault magnitude estimation. The feasibility and validity of the proposed method are verified through simulation experiments and experimental data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.224-227
• /
• 2015

Data transmission via the car driver's tethered smart phone may have a volume-dependent billing in case car driver' phone transmits data in real-time to the remote data center. The on-board diagnosis data generated are temporary stored locally to mobile remote diagnosis application on the car driver's phone, and then transmit to the data center later when car driver connects to the Internet. To increase the easiest of using the remote vehicle application without blocking other tasks to be executing on the cloud, node.js stands as a suitable candidate for handling tasks of data storage on the cloud via mobile network. We demonstrate the effectiveness of the proposed architecture by simulating a preliminary case study of an android application responsible of real time analysis by using a vehicle-to- smart phones applications interface approach that considers the smart phones to act as a remote user which passes driver inputs and delivers output from external applications. In this paper, we propose a study on development of Remote Vehicle fault diagnostic system features web server architecture based event loop approach using node.js platform, and wireless communication to handle vehicle diagnostics data to a data center.

• BioChip Journal
• /
• v.12 no.4
• /
• pp.332-339
• /
• 2018

The future neuro-prosthetic devices would be required spikes data monitoring through sub-nanoscale transistors that enables to neuroscientists and clinicals for scalable, wireless and implantable applications. This research investigates the spikes monitoring through integrated CNT front-end amplifier for neuro-prosthetic diagnosis. The proposed carbon nanotube-based architecture consists of front-end amplifier (FEA), integrate fire neuron and pseudo resistor technique that observed high electrical performance through neural activity. A pseudo resistor technique ensures large input impedance for integrated FEA by compensating the input leakage current. While carbon nanotube based FEA provides low-voltage operation with directly impacts on the power consumption and also give detector size that demonstrates fidelity of the neural signals. The observed neural activity shows amplitude of spiking in terms of action potential up to $80{\mu}V$ while local field potentials up to 40 mV by using proposed architecture. This fully integrated architecture is implemented in Analog cadence virtuoso using design kit of CNT process. The fabricated chip consumes less power consumption of $2{\mu}W$ under the supply voltage of 0.7 V. The experimental and simulated results of the integrated FEA achieves $60G{\Omega}$ of input impedance and input referred noise of $8.5nv/{\sqrt{Hz}}$ over the wide bandwidth. Moreover, measured gain of the amplifier achieves 75 dB midband from range of 1 KHz to 35 KHz. The proposed research provides refreshing neural recording data through nanotube integrated circuit and which could be beneficial for the next generation neuroscientists.