• Journal of Korean Society of Water and Wastewater
• /
• v.38 no.1
• /
• pp.1-15
• /
• 2024

Occurrence of process environment changes, such as influent load variances and process condition changes, can reduce treatment efficiency, increasing effluent water quality. In order to prevent exceeding effluent standards, it is necessary to manage effluent water quality based on process operation data including influent and process condition before exceeding occur. Accordingly, the development of the effluent water quality prediction system and the application of technology to wastewater treatment processes are getting attention. Therefore, in this study, through the multi-channel measuring instruments in the bio-reactor and smart multi-item water quality sensors (location in bio-reactor influent/effluent) were installed in The Seonam water recycling center #2 treatment plant series 3, it was collected water quality data centering around COD, T-N. Using the collected data, the artificial intelligence-based effluent quality prediction model was developed, and relative errors were compared with effluent TMS measurement data. Through relative error comparison, the applicability of the artificial intelligence-based effluent water quality prediction model in wastewater treatment process was reviewed.

• Analytical Science and Technology
• /
• v.24 no.6
• /
• pp.533-543
• /
• 2011

The hERG (human ether-a-go-go related gene) ion channel is a main factor for cardiac repolarization, and the blockade of this channel could induce arrhythmia and sudden death. Therefore, potential hERG ion channel inhibitors are now a primary concern in the drug discovery process, and lots of efforts are focused on the minimizing the cardiotoxic side effect. In this study, $IC_{50}$ data of 202 organic compounds in HEK (human embryonic kidney) cell from literatures were used to develop predictive 2D-QSAR model. Multiple linear regression (MLR), Support Vector Machine (SVM), and artificial neural network (ANN) were utilized to predict inhibition concentration of hERG ion channel as machine learning methods. Population based-forward selection method with cross-validation procedure was combined with each learning method and used to select best subset descriptors for each learning algorithm. The best model was ANN model based on 14 descriptors ($R^2_{CV}$=0.617, RMSECV=0.762, MAECV=0.583) and the MLR model could describe the structural characteristics of inhibitors and interaction with hERG receptors. The validation of QSAR models was evaluated through the 5-fold cross-validation and Y-scrambling test.

• Journal of Wetlands Research
• /
• v.23 no.2
• /
• pp.107-115
• /
• 2021

In order to analyze wave propagation, tidal current, and sediment transport in the vicinity of the Gaeya open channel, it was classified into before(CASE1W) and after(CASE2W) installation of various artificial structures, and the calculation results for CASE1W and CASE2W were compared. For wave propagation, the results of incident and reflected waves were derived using the SWAN numerical model, and the tidal current velocity results were derived using the FLOW2DH numerical model for tidal current. The results of the SWAN numerical model and the FLOW2DH numerical model became the input conditions for the SEDTRAN numerical model that predicts sediment transport, and the maximum bed shear stress and suspended sediment concentration distribution near the Gaeya open channel were calculated through the SEDTRAN numerical model. As a result of the calculation of the SWAN numerical model, the wave height of CASE2W was increased by 40~50 % compared to CASE1W because the incident wave was diffracted and superimposed and the reflected wave was generated by about 7 km long northen jetty. As a result of the calculation of the FLOW2DH numerical model, According to the northen breakwater, the northen jetty and Geumrando, CASE2W was calculated 10~30 % faster than CASE1W in the tidal current of the Gaeya open channel. As a result of the calculation of the SEDTRAN numerical model, the section where the maximum bed shear stress is 1.0 N/m² or more and the suspended concentration is 80mg/L or more was widely distributed in the Gaeya open channel from the marine environment by the complex wave field(incident wave, reflected wave and tidal wave) and the installation of various artificial structures. it is believed that a sedimentation phenomenon occurred in the Gaeya open channel.

• Journal of Internet of Things and Convergence
• /
• v.9 no.3
• /
• pp.93-98
• /
• 2023

In this paper, an artificial neural network based on simulated annealing was constructed. The mapping relationship between the parameters of micro-scaled flow channels electrochemical machining and the channel shape was established by training the samples. The depth and width of micro-scaled flow channels electrochemical machining on stainless steel surface were predicted, and the flow channels experiment was carried out with pulse power supply in NaNO3 solution to verify the established network model. The results show that the depth and width of the channel predicted by the simulated annealing artificial neural network with "4-7-2" structure are very close to the experimental values, and the error is less than 5.3%. The predicted and experimental data show that the etching degree in the process of channels electrochemical machining is closely related to voltage and current density. When the voltage is less than 5V, a "small island" is formed in the channel; When the voltage is greater than 40V, the lateral etching of the channel is relatively large, and the "dam" between the channels disappears. When the voltage is 25V, the machining morphology of the channel is the best.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.14 no.5
• /
• pp.658-665
• /
• 2014

The neural stimulators have been employed to the visual prostheses system based on the functional electrical stimulation (FES). Due to the size limitation of the implantable device, the smaller area of the unit current driver pixel is highly desired for higher resolution current stimulation system. This paper presents a 16-channel compact current-mode neural stimulator IC with digital to analog converter (DAC) sharing scheme for artificial retinal prostheses. The individual pixel circuits in the stimulator IC share a single 6 bit DAC using the sample-and-hold scheme. The DAC sharing scheme enables the simultaneous stimulation on multiple active pixels with a single DAC while maintaining small size and low power. The layout size of the stimulator circuit with the DAC sharing scheme is reduced to be 51.98 %, compared to the conventional scheme. The stimulator IC is designed using standard $0.18{\mu}m$ 1P6M process. The chip size except the I/O cells is $437{\mu}m{\times}501{\mu}m$.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.18 no.4 s.119
• /
• pp.379-388
• /
• 2007

This paper presents a real-time respiration and heartbeat detector comprised of a 1.6 GHz single-channel Doppler sensor and analog/digital signal processing block for remote vital sign detection. The RF front end of the Doppler sensor consists of an oscillator, mixer, low noise amplifier, branch-line hybrid and patch antenna. We apply artificial transmission lines(ATLs) to the branch-line hybrid, which leads to a size reduction of 40 % in the hybrid, while its performance is very comparable to that of a conventional hybrid. The analog signal conditioning block is implemented using second order Sallen-Key active filters and the digital signal processing block is realized with a LabVIEW program on a computer. The respiration and heartbeat detection is demonstrated at a distance of 50 cm using the developed system.

• Journal of Distribution Science
• /
• v.15 no.4
• /
• pp.69-78
• /
• 2017

Purpose - The study was AI as exploratory study on artificial intelligence (AI) shopping information services, to explore the possibility of a new business of the distribution industry. For research, we compare to IBM of consumer awareness surveys an AI shopping information service for retailing channel and target goods group. Finally, we present to service scenario for distribution service using AI. Research design, data, and methodology - First, to identify possible the success of the information service shopping using AI, AI technology for the consumer is very important for the acceptance of judgement. Therefore, we explored the possibility of AI information service for business as a shopping. The experimental data were used to interpret the meaning of the relevant literature and the IBM Institute of Business Value (IBV) Report 2015. This research is based on the use of a technical acceptance model (TAM) to determine whether the consumer would adopt the 'AI shopping information service' technology. Step 1 of the process assumes that the consumer adopts AI technology. In step 2, consumers find their preference channels and goods targeted at them as per their preferences. Finally Step 3, we present scenario for 'AI shopping information service' based on the results of Step 1 and 2. Results - Consumers have expressed their high interests in the new shopping information services, especially the on/off line distribution channels can use shopping information to increase the efficiency in provision of goods. Digital channel (such as SNS, online shopping etc.) is especially high value goods such as cars, furniture, and home appliances by displaying it to an appropriate product group. Conclusions - The study reveals the potential for the use of new business models such as 'AI shopping information service' by the distribution industry. We present seven scenario related AI application refer from IBM suggestion, and the findings would enable the distribution industry to approach target consumers with their products, especially high value goods. 'Shopping advisor' is considered to the most effective. In order to apply to the other field of the distribution industry business, which utilizes AI technology, it should be accompanied by additional empirical data analysis should be undertaken.

• Journal of Korea Water Resources Association
• /
• v.44 no.6
• /
• pp.429-438
• /
• 2011

In order to simulate a free surface flow in a trench channel, a three-dimensional incompressible unsteady Reynolds-averaged Navier-Stokes (RANS) equations are closed with the ${\kappa}-{\epsilon}$ model. The artificial compressibility (AC) method is used. Because the pressure fields can be coupled directly with the velocity fields, the incompressible Navier-Stokes (INS) equations can be solved for the unknown variables such as velocity components and pressure. The governing equations are discretized in a conservation form using a second order accurate finite volume method on non-staggered grids. In order to prevent the oscillatory behavior of computed solutions known as odd-even decoupling, an artificial dissipation using the flux-difference splitting upwind scheme is applied. To enhance the efficiency and robustness of the numerical algorithm, the implicit method of the Beam and Warming method is employed. The treatment of the free surface, so-called interface-tracking method, is proposed using the free surface evolution equation and the kinematic free surface boundary conditions at the free surface instead of the dynamic free surface boundary condition. AC method in this paper can be applied only to the hydrodynamic pressure using the decomposition into hydrostatic pressure and hydrodynamic pressure components. In this study, the boundary-fitted grids are used and advanced each time the free surface moved. The accuracy of our RANS solver is compared with the laboratory experimental and numerical data for a fully turbulent shallow-water trench flow. The algorithm yields practically identical velocity profiles that are in good overall agreement with the laboratory experimental measurement for the turbulent flow.

• The Korean Journal of Quaternary Research
• /
• v.16 no.1
• /
• pp.17-27
• /
• 2002

Analysis of No. 199∼145 cross-sections set up by the Ministry of Construction (1978) in the middle reaches of the Sumjin River around Sunchang, Daegang, and Goksung areas have been done for delineating the changes In fluvial geomorphic features. The entire river-bed in the study area has been considerably degraded since 1978. In some cross-sections, the thalweg shillings are observed. Two aspects are responsible for the erosion-dominant environment. First, flow velocity has been increased. Human activities including wetland destruction, ex-channel destruction and artificial levee construction reduced the channel width, and fixed the channel geometry. This has resulted in increase of the water velocity. Pebble and granule∼coarse sand are prevailing on the river-bed, indicate the high speed of the currents. Second, aggregate has been intensively mined during 1980s∼1990s around the areas. Especially, in the right side of the cross-sections No. 188∼187 and the left side of the cross-section No. 155, erosion toward under the artificial levee is remarkable. This can be led to bank failure in case of heavy rainfall.

• Nuclear Engineering and Technology
• /
• v.30 no.3
• /
• pp.245-261
• /
• 1998

In order to validate the variable aperture channel model that can deal with the non-uniform How rate in flow domain, migration experiments of conservative tracer were performed in two artificial fractures, a parallel and a wedge-shaped fracture. These different fracture shapes were designed to give different flow pattern. The fractures were made from a transparent acrylic plastic plate and a granite slab with dimensions of 10 $\times$ 61 $\times$ 61 cm. Uranine (Fluorescein sodium salt) was used as a conservative tracer. The volumetric flow rates of uranine feed solution were 30 mL/ hr, giving a mean residence time in the fracture of approximately 24 hours for the parallel fracture and 34 hours for the wedge-shaped fracture. The migration plumes of uranine were photographed to obtain profiles in space and time for movement of a tracer in fractures. The photographed migration plume was greatly affected by the geometric shape of fractures. The variable aperture channel model could have predicted the experimental results for the parallel fracture with a large accuracy. It is expected that the variable aperture channel model would be effective to predict the transport of the contaminant, especially, with the flow rate variation in a fracture.