• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.4
• /
• pp.43-54
• /
• 2007

This paper presents design and verification of a face detection hardware for real time application. Face detection algorithm detects rough face position based on already acquired feature parameter data. The hardware is composed of five main modules: Integral Image Calculator, Feature Coordinate Calculator, Feature Difference Calculator, Cascade Calculator, and Window Detection. It also includes on-chip Integral Image memory and Feature Parameter memory. The face detection hardware was verified by using S3C2440A CPU of Samsung Electronics, Virtex4LX100 FPGA of Xilinx, and a CCD Camera module. Our design uses 3,251 LUTs of Xilinx FPGA and takes about 1.96${\sim}$0.13 sec for face detection depending on sliding-window step size, when synthesized for Virtex4LX100 FPGA. When synthesized on Magnachip 0.25um ASIC library, it uses about 410,000 gates (Combinational area about 345,000 gates, Noncombinational area about 65,000 gates) and takes less than 0.5 sec for face realtime detection. This size and performance shows that it is adequate to use for embedded system applications. It has been fabricated as a real chip as a part of XF1201 chip and proven to work.

• The Journal of Engineering Geology
• /
• v.23 no.3
• /
• pp.283-292
• /
• 2013

A calcareous rock slope failed during excavation of the slope for construction of a tunnel entrance. The slope is located at the construction site for widening highway in Yeongwol, Korea. Field surveys, laboratory tests, and numerical analyses were performed to determine the reason for the slope failure. The numerical analysis revealed that the safety factor of the slope before construction of the entrance was less than 1, and that this decreased after construction. After construction of the entrance, the sliding zone of the slope increased and slope stability decreased because the shear strain and plastic zone in the slope over the tunnel entrance showed an increase relative to the lower part of the slope. To enhance the stability of the slope for construction of the tunnel entrance, countermeasures such as rock bolts, rock anchors, and FRP (Fiber glass Reinforced Plastic) grouting were adopted in light of the field conditions. Serial field monitoring performed to confirm the reinforcing effects of the adopted countermeasures revealed a small amount of horizontal deformation of the slope soils, most of the elastic deformation that can regain its former value. In addition, the axial forces of the rock bolt and anchor were more strongly affected by slope excavation during construction of the tunnel entrance than by tunnel excavation or the rainy season, and the axial forces tended to converge after excavation of the tunnel. Therefore, we can confirm that the slope is currently safe.

• Journal of the Korea Concrete Institute
• /
• v.17 no.4 s.88
• /
• pp.595-602
• /
• 2005

The purpose of this study is to utilize recycled concrete aggregates as permeable pavement materials. This study evaluates mechanical properties and durability of porous concrete depending on mixing rates of recycled aggregates and polyme. As a result, void ratio and permeability coefficient of porous concrete for pavement increased a little as mixing rate of recycled aggregates increased. Void ratio and permeability coefficient increased a lot as mixing rate of polymer increased. As polymer was mixed $20\%$, national regulation of permeable concrete for pavement($8\%$ and 0.01cm/sec) was met. Compressive strength and flexural strength decreased as mixing rate of recycled aggregates increased but they increased a lot as mixing rate of polymer increased. Even when recycled aggregates were mixed $75\%\;with\;10\%$ polymer mixed, national regulation of pavement concrete(18MPa and 4.5MPa) was met. In addition, regarding sliding resistance, BPN increased as mixing rate of recycled aggregates increased. But BPN decreased as polymer was mixed. Compared to crushed stone aggregates, abrasion resistance and freeze-thaw resistance decreased as mixing rate of recycled aggregates Increased. When polymer was mixed, abrasion resistance and freeze-thaw resistance improved remarkably. Compared to non-mixture, $10\%$ mixture of polymer improved abrasion resistance and freeze-thaw resistance about $8.6\%$ and 3.8times respectively.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.32 no.2
• /
• pp.95-105
• /
• 2020

In this study, using the CADMAS-SURF model, the characteristics of the wave pressures and the wave forces were analyzed according to the installation position of the parapet on top of the caisson, and the stability evaluation was carried out using estimated wave forces for the design wave condition. Numerical results show that adopting the rear-parapet reduces the front maximum wave pressures and wave forces, and the maximum wave pressure acting on the rear-parapet increases slightly compared to the front parapet, but the wave force acting on the rear-parapet has little effect on the stability of the breakwater due to the phase difference with the wave force acting on the front of the breakwater. In addition, impulsive wave pressures did not occur, as Yamamoto et al. (2013) pointed out the problem of the rear-parapet breakwater. As a result of the stability against sliding and overturning, it was estimated that the target safety factor of 1.2 could be secured by the self-weight of 13% less than the case of the front parapet. At this time, the maximum ground pressure was also reduced by 30%, and the applicability of the rear-parapet structure to the actual site was evaluated as high.

• Journal of Biosystems Engineering
• /
• v.41 no.4
• /
• pp.288-293
• /
• 2016

Purpose: The purpose of this study was to investigate the key factors in designing a three-wheeled two-row soybean reaper (riding type) that is suitable for soybean production, and ensure worker safety by proposing optimal work conditions for the prototype of the designed machine in relation to the slope of the road. Methods: A three-wheeled two-row soybean reaper (riding type) was designed and its prototype was fabricated based on the local soybean-production approach. This approach was considered to be closely related to the prototype-designing of the cutter and the wheel driving system of the reaper. Load distribution on the wheels of the prototype, its minimum turning radius, static lateral overturning angle, tilt angle during driving, and The working and rear overturning (back flip) angle were measured. Based on the gathered information, investigations were conducted regarding optimal work conditions for the prototype. The investigations took into account driving stability and worker safety. Results: The minimum ground clearance of the prototype was 0.5 m. The blade height of the prototype was adjusted such that the cutter was operated in line with the height of the ridges. The load distribution on the prototype's wheels was found to be 1 (front wheel: F): 1.35 (rear-left wheel: RL): 1.43 (rear-right wheel: RR). With the ratio of load distribution between the RL and RR wheels being 1: 1.05, the left-to-right lateral loads were found to be well-balanced. The minimum turning radius of the prototype was 2.0 m. Such a small turning radius was considered to be beneficial for cutting work on small-scale fields. The sliding of the prototype started at $25^{\circ}$, and its lateral overturning started at $39.3^{\circ}$. Further, the critical slope angle for the worker to drive the prototype in the direction of the contour line on an incline was found to be $12.8^{\circ}$, and the safe angle of slope for the cutting was measured to be less than $6^{\circ}$. The critical angle of slope that allowed for work was found to be $10^{\circ}$, at which point the prototype would overturn backward when given impact forces of 1,060 N on its front wheel. Conclusions: It was determined that farmers using the prototype would be able to work safely in most soybean production areas, provided that they complied with safe working conditions during driving and cutting.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.310-318
• /
• 2018

Recently, the importance of big data analysis is increasing as a large amount of data is generated by various devices connected to the Internet with the advent of Internet of Things (IoT). Especially, it is necessary to analyze various large-scale IoT streaming sensor data generated in real time and provide various services through new meaningful prediction. This paper proposes a real-time indoor PM10 concentration prediction LSTM model based on streaming data generated from IoT sensor using AWS. We also construct a real-time indoor PM10 concentration prediction service based on the proposed model. Data used in the paper is streaming data collected from the PM10 IoT sensor for 24 hours. This time series data is converted into sequence data consisting of 30 consecutive values from time series data for use as input data of LSTM. The LSTM model is learned through a sliding window process of moving to the immediately adjacent dataset. In order to improve the performance of the model, incremental learning method is applied to the streaming data collected every 24 hours. The linear regression and recurrent neural networks (RNN) models are compared to evaluate the performance of LSTM model. Experimental results show that the proposed LSTM prediction model has 700% improvement over linear regression and 140% improvement over RNN model for its performance level.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.7
• /
• pp.299-306
• /
• 2022

In recent, sensors embedded in robots, equipment, and circuits have become common, and research for diagnosing device failures by learning measured sensor data is being actively conducted. This failure diagnosis study is divided into a classification model for predicting failure situations or types and a regression model for numerically predicting failure conditions. In the case of a classification model, it simply checks the presence or absence of a failure or defect (Class), whereas a regression model has a higher learning difficulty because it has to predict one value among countless numbers. So, the reason that regression modeling is more difficult is that there are many irregular situations in which it is difficult to determine one output from a similar input when predicting by matching input and output. Therefore, in this paper, we focus on input and output data with periodicity, analyze the input/output relationship, and secure regularity between input and output data by performing sliding window-based input data patterning. In order to apply the proposed method, in this study, current and temperature data with periodicity were collected from MMC(Modular Multilevel Converter) circuit system and learning was carried out using ANN. As a result of the experiment, it was confirmed that when a window of 2% or more of one cycle was applied, performance of 97% or more of fit could be secured.

• Journal of Navigation and Port Research
• /
• v.46 no.4
• /
• pp.367-374
• /
• 2022

The purpose of this study was to propose a deep learning algorithm that applies to the fault diagnosis of fuel pumps and purifiers of autonomous ships. A deep learning algorithm reflecting the time dependence of the measured signal was configured, and the failure pattern was trained using the vibration signal, measured in the equipment's regular operation and failure state. Considering the sequential time-dependence of deterioration implied in the vibration signal, this study adopts Conv1D with sliding window computation for fault detection. The time dependence was also reflected, by transferring the measured signal from two-dimensional to three-dimensional. Additionally, the optimal values of the hyper-parameters of the Conv1D model were determined, using the grid search technique. Finally, the results show that the proposed data preprocessing method as well as the Conv1D model, can reflect the sequential dependency between the fault and its effect on the measured signal, and appropriately perform anomaly as well as failure detection, of the equipment chosen for application.

• Journal of the Korean Geotechnical Society
• /
• v.15 no.4
• /
• pp.113-132
• /
• 1999

Recently in Korea, application of the soil nailing is gradually extended to the sites of excavations and slopes having various ground conditions and field characteristics. Design of the soil nailing is generally carried out in two steps, The First step is to examine the minimum safety factor against a sliding of the reinforced nailed-soil mass based on the limit equilibrium approach, and the second step is to check the maximum displacement expected to occur at facing using the numerical analysis technique. However, design parameters related to the soil nailing system are so various that a reliable design method considering interrelationships between these design parameters is continuously necessary. Additionally, taking into account the anisotropic characteristics of in-situ grounds, disturbances in collecting the soil samples and errors in measurements, a systematic analysis of the field measurement data as well as a rational technique of the optimum design is required to improve with respect to economical efficiency. As a part of these purposes, in the present study, a procedure for the optimum design of a soil nailing excavation wall system is proposed. Focusing on a minimization of the expenses in construction, the optimum design procedure is formulated based on the genetic algorithm. Neural network theory is further adopted in predicting the maximum horizontal displacement at a shotcrete facing. Using the proposed procedure, various effects of relevant design parameters are also analyzed. Finally, an optimized design section is compared with the existing design section at the excavation site being constructed, in order to verify a validity of the proposed procedure.

• Journal of KIISE:Databases
• /
• v.31 no.5
• /
• pp.468-478
• /
• 2004

It is essential in various application areas of data mining and bioinformatics to effectively retrieve the occurrences of interesting patterns from sequence databases. For example, let's consider a network event management system that records the types and timestamp values of events occurred in a specific network component(ex. router). The typical query to find out the temporal casual relationships among the network events is as fellows: 'Find all occurrences of CiscoDCDLinkUp that are fellowed by MLMStatusUP that are subsequently followed by TCPConnectionClose, under the constraint that the interval between the first two events is not larger than 20 seconds, and the interval between the first and third events is not larger than 40 secondsTCPConnectionClose. This paper proposes an indexing method that enables to efficiently answer such a query. Unlike the previous methods that rely on inefficient sequential scan methods or data structures not easily supported by DBMSs, the proposed method uses a multi-dimensional spatial index, which is proven to be efficient both in storage and search, to find the answers quickly without false dismissals. Given a sliding window W, the input to a multi-dimensional spatial index is a n-dimensional vector whose i-th element is the interval between the first event of W and the first occurrence of the event type Ei in W. Here, n is the number of event types that can be occurred in the system of interest. The problem of‘dimensionality curse’may happen when n is large. Therefore, we use the dimension selection or event type grouping to avoid this problem. The experimental results reveal that our proposed technique can be a few orders of magnitude faster than the sequential scan and ISO-Depth index methods.hods.