• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.5
• /
• pp.667-674
• /
• 2023

In the event of a disaster occurring within a building, the prompt and efficient evacuation and rescue of occupants within the building becomes the foremost priority to minimize casualties. For the purpose of such rescue operations, it is essential to ascertain the distribution of individuals within the building. Nevertheless, there is a primary dependence on accounts provided by pertinent individuals like building proprietors or security staff, alongside fundamental data encompassing floor dimensions and maximum capacity. Consequently, accurate determination of the number of occupants within the building holds paramount significance in reducing uncertainties at the site and facilitating effective rescue activities during the golden hour. This research introduces a methodology employing computer vision algorithms to count the number of occupants within distinct building locations based on images captured by installed multiple CCTV cameras. The counting methodology consists of three stages: (1) establishing virtual Lines of Interest (LOI) for each camera to construct a multi-camera network environment, (2) detecting and tracking people within the monitoring area using deep learning, and (3) aggregating counts across the multi-camera network. The proposed methodology was validated through experiments conducted in a five-story building with the average accurary of 89.9% and the average MAE of 0.178 and RMSE of 0.339, and the advantages of using multiple cameras for occupant counting were explained. This paper showed the potential of the proposed methodology for more effective and timely disaster management through common surveillance systems by providing prompt occupancy information.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.5
• /
• pp.505-511
• /
• 2023

In the present study, a deep learning model was established to predict the motion response of small fishing vessels. Hydrodynamic performances were evaluated for two small fishing vessels for the dataset of deep learning model. The deep learning model of the Long Short-Term Memory (LSTM) which is one of the recurrent neural network was utilized. The input data of LSTM model consisted of time series of six(6) degrees of freedom motions and wave height and the output label was selected as the time series data of six(6) degrees of freedom motions. The hyperparameter and input window length studies were performed to optimize LSTM model. The time series motion response according to different wave direction was predicted by establised LSTM. The predicted time series motion response showed good overall agreement with the analysis results. As the length of the time series increased, differences between the predicted values and analysis results were increased, which is due to the reduced influence of long-term data in the training process. The overall error of the predicted data indicated that more than 85% of the data showed an error within 10%. The established LSTM model is expected to be utilized in monitoring and alarm systems for small fishing vessels.

• Journal of Korea Water Resources Association
• /
• v.56 no.6
• /
• pp.393-402
• /
• 2023

Drought, which has been increasing in frequency and magnitude due to recent abnormal weather events, poses severe challenges in various sectors. To address this issue, it is important to develop technologies for drought monitoring, forecasting, and response in order to implement effective measures and safeguard the ecological health of aquatic systems during water scarcity caused by drought. This study aimed to predict water quality fluctuations during drought periods by integrating the watershed model HSPF and the water quality model QUAL-MEV. The researchers examined the SPI and RCP 4.5 scenarios, and analyzed water quality changes based on flow rates by simulating them using the HSPF and QUAL-MEV models. The study found a strong correlation between water flow and water quality during the low flow. However, the relationship between precipitation and water quality was deemed insignificant. Moreover, the flow rate and SPI6 exhibited different trends. It was observed that the relationship with the mid- to long-term drought index was not significant when predicting changes in water quality influenced by drought. Therefore, to accurately assess the impact of drought on water quality, it is necessary to employ a short-term drought index and develop an evaluation method that considers fluctuations in flow.

• Journal of the Korean Geotechnical Society
• /
• v.23 no.3
• /
• pp.5-13
• /
• 2007

The performance of innovative prestressed support (IPS) earth retention system applied in soft clay was investigated and presented. The IPS wale system provides a high flexural stiffness to resist the bending by lateral earth pressure, and transfers lateral earth pressure to strut supports. The IPS wale system provides a larger spacing of support than conventional braced and anchored systems. The IPS earth retention system was selected for temporary earth support in a building construction in North Busan area. The excavation was made 28.8 m wide, 52.0 m long, and 16.1 m deep through loose fill to soft clay. The IPS system consists of 650 mm thick slurry walls, and five levels of IPS wales and struts. Field monitoring data were collected including wall deflections at six locations, ground water levels at four locations, IPS wale deflections at thirty locations, and axial loads on struts at twenty locations, during construction. The IPS earth retention system applied in soft clay performed successfully within a designed criterion. Field measurements were compared with design assumptions of the IPS earth retention system. The applicability and stability of the IPS earth retention system in soft clay were investigated and evaluated.

• Journal of the Korean Geotechnical Society
• /
• v.24 no.5
• /
• pp.65-78
• /
• 2008

In case of cut-slopes or shallow-depth tunnels, sliding along with discontinuities or rotation could play a critical role in judging stability. Although numerical analysis is widely used to check the stability of these cut-slopes and shallow-depth tunnels in early design process, common analysis programs are based on continuum model. Performing continuum model analysis regarding discontinuities is possible by reducing overall strength of jointed rock mass. It is also possible by applying ubiquitous joint model to Mohr-Coulomb failure criteria. In numerical analysis of cut-slope, main geotechnical properties such as cohesion, friction angle and elastic modulus can be evaluated by empirical equations. This study tried to compare two main systems, RMR and GSI system by applying them to in-situ hazardous cut-slopes. In addition, this study applied ubiquitous joint model to simulation model with inputs derived by RMR and GSI system to compare with displacements obtained by in-situ monitoring. To sum up, numerical analysis mixed with GSI inputs and ubiquitous joint model proved to provide most reliable results which were similar to actual displacements and their patterns.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.3
• /
• pp.73-82
• /
• 2022

Auto-scaling is one of the most important functions for cloud computing technology. Even if the number of users or service requests is explosively increased or decreased, system resources and service instances can be appropriately expanded or reduced to provide services suitable for the situation and it can improves stability and cost-effectiveness. However, since the policy is performed based on a single metric data at the time of monitoring a specific system resource, there is a problem that the service is already affected or the service instance that is actually needed cannot be managed in detail. To solve this problem, in this paper, we propose a method to predict system resource and service response time using a multivariate time series analysis model and establish an auto-scaling policy based on this. To verify this, implement it as a custom scheduler in the Kubernetes environment and compare it with the Kubernetes default auto-scaling method through experiments. The proposed method utilizes predictive data based on the impact between system resources and response time to preemptively execute auto-scaling for expected situations, thereby securing system stability and providing as much as necessary within the scope of not degrading service quality. It shows results that allow you to manage instances in detail.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.8
• /
• pp.327-342
• /
• 2017

In this paper, we introduce an integrated processing system of smart sensor data for IoT service which collects sensor data and efficiently processes it. Based on the technology of collecting sensor data to the development of the IoT field and sending it to the network · Based on the receiving technology, as various projects such as smart homes, autonomous running vehicles progress, the sensor data is processed and effectively An autonomous control system to utilize has been a problem. However, since the data type of the sensor for monitoring the autonomous control system varies according to the domain, a sensor data integration processing system applying the autonomous control system to various different domains is necessary. Therefore, in this paper, we introduce the Smart Sensor Data Integrated Processing System, apply it and use the window as a reference to process internal and external sensor data 1) receiveData, 2) parseData, 3) addToDatabase 3 With the process of the stage, we provide and implement the automatic window opening / closing system "Smart Window" which ventilates to create a comfortable indoor environment by autonomous control system. As a result, standby information is collected and monitored, and machine learning for performing statistical analysis and better autonomous control based on the stored data is made possible.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.241-265
• /
• 2023

A corporate insolvency prediction model serves as a vital tool for objectively monitoring the financial condition of companies. It enables timely warnings, facilitates responsive actions, and supports the formulation of effective management strategies to mitigate bankruptcy risks and enhance performance. Investors and financial institutions utilize default prediction models to minimize financial losses. As the interest in utilizing artificial intelligence (AI) technology for corporate insolvency prediction grows, extensive research has been conducted in this domain. However, there is an increasing demand for explainable AI models in corporate insolvency prediction, emphasizing interpretability and reliability. The SHAP (SHapley Additive exPlanations) technique has gained significant popularity and has demonstrated strong performance in various applications. Nonetheless, it has limitations such as computational cost, processing time, and scalability concerns based on the number of variables. This study introduces a novel approach to variable selection that reduces the number of variables by averaging SHAP values from bootstrapped data subsets instead of using the entire dataset. This technique aims to improve computational efficiency while maintaining excellent predictive performance. To obtain classification results, we aim to train random forest, XGBoost, and C5.0 models using carefully selected variables with high interpretability. The classification accuracy of the ensemble model, generated through soft voting as the goal of high-performance model design, is compared with the individual models. The study leverages data from 1,698 Korean light industrial companies and employs bootstrapping to create distinct data groups. Logistic Regression is employed to calculate SHAP values for each data group, and their averages are computed to derive the final SHAP values. The proposed model enhances interpretability and aims to achieve superior predictive performance.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.23-34
• /
• 2023

Wearable technology for military applications has received considerable attention as a means of personal status check and monitoring. Among many, an implementation to recognize specific motion states of a human is promising in that allows active management of troops by immediately collecting the operational status and movement status of individual soldiers. In this study, as an extension of military wearable application research, a new ankle wearable device is proposed that can glean the information of a soldier on the battlefield on which action he/she takes in which environment. Presuming a virtual situation, the soldier's upper limbs are easily exposed to uncertainties about circumstances. Therefore, a sensing module is attached to the ankle of the soldier that may always interact with the ground. The obtained data comprises 3-axis accelerations and 3-axis rotational velocities, which cannot be interpreted by hand-made algorithms. In this study, to discern the behavioral characteristics of a human using these dynamic data, a data-driven model is introduced; four features extracted from sliced data (minimum, maximum, mean, and standard deviation) are utilized as an input of the model to learn and classify eight primary military movements (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). As a result, the proposed device could recognize a movement status of a solider with 95.16% accuracy in an arbitrary test situation. This research is meaningful since an effective way of motion recognition has been introduced that can be furtherly extended to various military applications by incorporating wearable technology and artificial intelligence.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.33 no.2
• /
• pp.230-246
• /
• 2023

Objectives: The climate crisis has arrived and heat-related illnesses are increasing. It is necessary to discover new high-heat risk industries and understand the environment . It is also necessary to prioritize risks of industries that have not been included in the management target to date. The study was intended to monitor and evaluate the thermal risk of high-priority workplaces. Methods: A prioritization method was developed based on five factors: occurrence of and death due to heat-related illnesses, work environment monitoring, indoor work rate, small heat source, and limited heat dissipation. it, was applied to industrial accidents caused by heat-related illnesses. Wet bulb temperature index and apparent temperature were measured in July and August at 24 workplaces in seven industries and assessed for thermal risk. Results: The wet bulb temperature index was in the range of 23.8~31.9℃, and exposure limits were exceeded in the growing of crops, food services activities and accommodation, and building construction. The apparent temperature was in the range of 26.8~36.7℃, and exceeded the temperature standard for issuing heatwave warnings in growing of crops, food services activities and accommodation, warehousing, welding, and building construction. Both temperature index in growing of crops and building construction were higher than the outside air temperature. Conclusions: In the workplace, risks in industries that have not be controlled and recognized through existing systems was identified. it is necessary to provide break times according to the work-rest time ratio required during dangerous time period.