• Steel and Composite Structures
• /
• v.45 no.6
• /
• pp.865-876
• /
• 2022

The slit members have lower strength and lower stiffness, which might lead to lower energy dissipation. In order to improve the seismic performance of the slit members, the paper proposes the shear lead damper, which has stable performance and small deformation energy dissipation capacity. Therefore, the shear lead damper can set in the vertical silts of the slit member to transmit the shear force and improve energy dissipation, which is suitable for the slit member. Initially, the symmetrical teeth-shaped lead damper was tested and analyzed. Then the staggered teeth-shaped lead dampers were developed and analyzed, based on the defect analysis and build improvements of the symmetrical specimen. Based on the parameter analysis, the main influence factors of hysteretic performance are the internal teeth, the steel baffles, and the width and length of damper. Finally, the theoretical analysis was presented on the hysteretic curve. And the skeleton curve and hysteresis path were identified. Based on the above theoretical analysis, the design method was proposed, including the damping force, the hysteresis model and the design recommendations.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.613-623
• /
• 2022

Autism spectrum disorder (ASD) is a developmental disorder associated with cognitive and neurobehavioral disorders. It affects the person's behavior and performance. Autism affects verbal and non-verbal communication in social interactions. Early screening and diagnosis of ASD are essential and helpful for early educational planning and treatment, the provision of family support, and for providing appropriate medical support for the child on time. Thus, developing automated methods for diagnosing ASD is becoming an essential need. Herein, we investigate using various machine learning methods to build predictive models for diagnosing ASD in children using facial images. To achieve this, we used an autistic children dataset containing 2936 facial images of children with autism and typical children. In application, we used classical machine learning methods, such as support vector machine and random forest. In addition to using deep-learning methods, we used a state-of-the-art method, that is, automated machine learning (AutoML). We compared the results obtained from the existing techniques. Consequently, we obtained that AutoML achieved the highest performance of approximately 96% accuracy via the Hyperpot and tree-based pipeline optimization tool optimization. Furthermore, AutoML methods enabled us to easily find the best parameter settings without any human efforts for feature engineering.

• Steel and Composite Structures
• /
• v.48 no.4
• /
• pp.475-483
• /
• 2023

In this paper, a new energy-efficient semi-active hybrid bulk damper is developed that is cost-effective for use in structural applications. In this work, the possibility of active and semi-active component configurations combined with suitable control algorithms, especially vibration control methods, is explored. The equations of motion for a container bridge equipped with an MDOF Mass Tuned Damper (M-TMD) system are established, and the combination of excitation, adhesion, and control effects are performed by a proprietary package and commercial custom submodel software. Systematic methods for the synthesis of structural components and active systems have been used in many applications because of the main interest in designing efficient devices and high-performance structural systems. A rational strategy can be established by properly controlling the master injection frequency parameter. Simulation results show that the multiscale model approach is achieved and meets accuracy with high computational efficiency. The M-TMD system can significantly improve the overall response of constrained structures by modestly reducing the critical stress amplitude of the frame. This design can be believed to build affordable, safe, environmentally friendly, resilient, sustainable infrastructure and transportation.

• Journal of Wellbeing Management and Applied Psychology
• /
• v.6 no.2
• /
• pp.27-31
• /
• 2023

Purpose: Establishment of a real-time monitoring system for odor control in traditional markets in Gangwon-do and a system for linking prevention facilities. Research design, data and methodology: Build server and system logic based on data through real-time monitoring device (sensor-based). A temporary data generation program for deep learning is developed to develop a model for odor data. Results: A REST API was developed for using the model prediction service, and a test was performed to find an algorithm with high prediction probability and parameter values optimized for learning. In the deep learning algorithm for AI modeling development, Pandas was used for data analysis and processing, and TensorFlow V2 (keras) was used as the deep learning library. The activation function was swish, the performance of the model was optimized for Adam, the performance was measured with MSE, the model method was Functional API, and the model storage format was Sequential API (LSTM)/HDF5. Conclusions: The developed system has the potential to effectively monitor and manage odors in traditional markets. By utilizing real-time data, the system can provide timely alerts and facilitate preventive measures to control and mitigate odors. The AI modeling component enhances the system's predictive capabilities, allowing for proactive odor management.

• Journal of Animal Environmental Science
• /
• v.18 no.sup
• /
• pp.81-90
• /
• 2012

This study was evaluated high end research grade Near infrared spectrophotometer (NIRS) to low end popular field grade multiple Near infrared spectrophotometer (NIRS) for rapid analysis at forage quality at sight with 241 samples of Italian ryegrass silage during 3 years collected whole country for evaluate accuracy and precision between instruments. Firstly collected and build database high end research grade NIRS using with Unity Scientific Model 2500X (650 nm~2,500 nm) then trim and fit to low end popular field grade NIRS with Unity Scientific Model 1400 (1,400 nm~2,400 nm) then build and create calibration, transfer calibration with special transfer algorithm. The result between instruments was 0.000%~0.343% differences, rapidly analysis for chemical constituents, NDF, ADF, and crude protein, crude ash and fermentation parameter such as moisture, pH and lactic acid, finally forage quality parameter, TDN, DMI, RFV within 5 minutes at sight and the result equivalent with laboratory data. Nevertheless during 3 years collected samples for build calibration was organic samples that make differentiate by local or yearly bases etc. This strongly suggest population evaluation technique needed and constantly update calibration and maintenance calibration to proper handling database accumulation and spread out by knowledgable control laboratory analysis and reflect calibration update such as powerful control center needed for long lasting usage of forage analysis with NIRS at sight. Especially the agriculture products such as forage will continuously changes that made easily find out the changes and update routinely, if not near future NIRS was worthless due to those changes. Many research related NIRS was shortly study not long term study that made not well using NIRS, so the system needed check simple and instantly using with local language supported signal methods Global Distance (GD) and Neighbour Distance (ND) algorithm. Finally the multiple popular field grades instruments should be the same results not only between research grade instruments but also between multiple popular field grade instruments that needed easily transfer calibration and maintenance between instruments via internet networking techniques.

• Journal of the Korean Geotechnical Society
• /
• v.35 no.11
• /
• pp.51-62
• /
• 2019

In this study, a simple method to estimate the soil water content variation in a wide area was proposed using hyperspectral near-infrared images. The reflectance data of a sand, granite soils, and a kaolinite were measured by reflecting the soil samples with different wavelengths in the visible and near-infrared (VNIR) regions using hyperspectral cameras. The measured reflectances and parameters were used to build a water content prediction model using the Partial Least Square Regression (PLSR) analysis. In the water content prediction model, the Area of Reflectance (Near-infrared, NIR) parameter was the most suitable parameter to determine the water content. The parameter was applicable regardless of the soil type, as the coefficient of determination (R²) exceeded 0.9 for each soil sample. Additionally, the mean absolute percentage error (MAPE) was less than 15% when compared with the actual water content of the soil. Therefore, the predictability of water content variation for soils with water content lower than 50% was confirmed. Accordingly through this study, the predictability of water content variation in several soil types using the hyperspectral near-infrared images was confirmed. For further development, a model that incorporates soil classification would be required to improve the accuracy of the model and to predict higher range of water contents.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.3
• /
• pp.77-90
• /
• 2018

Software Defect Prediction (SDP) is a field of study that identifies defective modules. With insufficient local data, a company can exploit Cross-Project Defect Prediction (CPDP), a way to build a classifier using dataset collected from other companies. Most machine learning algorithms for SDP have used more than one parameter that significantly affects prediction performance depending on different values. The objective of this study is to propose a parameter selection technique to enhance the performance of CPDP. Using a Harmony Search algorithm (HS), our approach tunes parameters of cost-sensitive boosting, a method to tackle class imbalance causing the difficulty of prediction. According to distributional characteristics, parameter ranges and constraint rules between parameters are defined and applied to HS. The proposed approach is compared with three CPDP methods and a Within-Project Defect Prediction (WPDP) method over fifteen target projects. The experimental results indicate that the proposed model outperforms the other CPDP methods in the context of class imbalance. Unlike the previous researches showing high probability of false alarm or low probability of detection, our approach provides acceptable high PD and low PF while providing high overall performance. It also provides similar performance compared with WPDP.

• Journal of The Geomorphological Association of Korea
• /
• v.15 no.2
• /
• pp.37-53
• /
• 2008

This study has developed a water balance model for the catchment of Byungchun river using a BROOK90 4.4e physical deterministic water balance model with the long-term meterological data and stream run off data obtained from the basin of Byungchun river in Korea. It is intended that the validation model with calibrated model fitting parameter can build a long-term water balance plan for a period when meterological data are available but stream runoff data are not. Results of this study have satisfied the first expectation as an experiment for water balance modeling since measured stream runoff data have turned out to be very similar to simulated stream runoff data. Through the confirmation of model fitting parameters and validated simulation, water balance for the period of 1998 to 2006 has been restored. Unless the conditions of geomophology, vegetation, soil and land use change, meterological data alone can produce various hydrometeorological data related to stream runoff amount, soil water amount, and evapotranspiration. This study opens up a new horizon in restoring water balance in the past as well planning water balance in the present. The obtained results from this study are expected to be used in predicting future water balance in the wake of the changes in climate and vegetation in Korea.

• Journal of Environmental Impact Assessment
• /
• v.29 no.6
• /
• pp.403-413
• /
• 2020

A mathematical model comprised with eight simultaneous quasi-linear partial differential equations was suggested to provide optimal chlorination strategy. Upstream weighted finite element method was employed to construct multidimensional numerical code. The code was verified against measured concentrations in three type of reactors. Boundary conditions and reaction rate were calibrated for the sixteen cases of experimental results to regenerate the measured values. Eight reaction rate coefficients were estimated from the modeling result. The reaction rate coefficients were expressed in terms of pH and temperature. Automatic optimal algorithm was invented to estimate the reaction rate coefficients by minimizing the sum of squares of the numerical errors and combined with the model. In order to minimize the concentration of chlorine and pollutants at the final usage sites, a real-time predictive control system is imperative which can predict the water quality variables from the chlorine disinfection process at the water purification plant to the customer by means of a model and operate the disinfection process according to the influent water quality. This model can be used to build such a system in water treatment plants.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.13 no.2 s.54
• /
• pp.172-180
• /
• 2009

Normally in order to build a semi-active control system equipped with MR damper, the dynamic modeling of the damper is required to numerically predict its dynamic damping force and also its behavioral characteristics. For the dynamic modeling of the MR damper, this paper attempts to predict and evaluate its dynamic behavior by applying specifically both a power model and a Bingham model. Dynamic loading tests were performed on the squeeze type of damper specially designed for this research, and force-displacement hysteresis loops confirmed the effectiveness of the damper as a semi-active control device. In the meantime, in order to evaluate the effectiveness of each model applied, the model parameter for each model was identified. On the basis of the parameter, we derived the error ratio of the force-velocity relationship curve and the dynamic damping force, which was contrasted and compared with the experimental results of the squeeze type of damper. Finally, the squeeze type of MR damper developed in this research was proved to be valid as a semi-active control device, and also the evaluation of the two dynamic models showed they were working fine so that they were likely to be easily utilized to numerically predict the dynamic characteristics of any dampers with MR fluid as well as the squeeze type of MR damper.