• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권5호
• /
• pp.161-168
• /
• 2021

균열은 건물, 교량, 도로, 수송관 등의 기반시설의 안전성에 영향을 주는 요소이다. 본 연구에서는 검사 비용과 시간을 줄일 수 있는 자동화된 균열 탐지 시스템을 다룬다. 환경과 표면에 강건한 시스템을 구성하기 위해서, 본 연구에서는 여러 사전 연구에서 사용된 다양한 표면의 균열 데이터 셋을 수집하여 통합 데이터 셋을 구축하였다. 이후, 컴퓨터 비전 분야에 높은 성능을 발휘하는 VGG, ResNet, WideResNet, ResNeXt, DenseNet, EfficientNet 딥러닝 모델을 적용하였다. 통합 데이터 셋은 훈련 집합(80%)과 테스트 집합(20%)으로 나누어 모델 성능을 검증하기 위해서 사용했다. 실험 결과, DenseNet121 모델이 높은 마라미터 효율성을 가지면서도 테스트 집합에 대해 96.20%의 정확도를 달성하여 가장 높은 성능을 보여주었다. 딥러닝 모델의 균열 검출 성능 검증을 통해, DenseNet121를 활용하여 컴퓨팅 자원이 적은 소형 디바이스에서도 높은 균열 검출 성능을 보이는 탐지 시스템을 구축이 가능함을 확인했다.

• 시스템엔지니어링학술지
• /
• 제18권2호
• /
• pp.75-93
• /
• 2022

Machine learning (ML) data-driven meta-model is proposed as a surrogate model to reduce the excessive computational cost of the physics-based model and facilitate the real-time prediction of a nuclear power plant's transient response. To forecast the transient response three machine learning (ML) meta-models based on recurrent neural networks (RNNs); specifically, Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and a sequence combination of Convolutional Neural Network (CNN) and LSTM are developed. The chosen accident scenario is a control element assembly withdrawal at power concurrent with the Loss Of Offsite Power (LOOP). The transient response was obtained using the best estimate thermal hydraulics code, MARS-KS, and cross-validated against the Design and control document (DCD). DAKOTA software is loosely coupled with MARS-KS code via a python interface to perform the Best Estimate Plus Uncertainty Quantification (BEPU) analysis and generate a time series database of the system response to train, test and validate the ML meta-models. Key uncertain parameters identified as required by the CASU methodology were propagated using the non-parametric Monte-Carlo (MC) random propagation and Latin Hypercube Sampling technique until a statistically significant database (181 samples) as required by Wilk's fifth order is achieved with 95% probability and 95% confidence level. The three ML RNN models were built and optimized with the help of the Talos tool and demonstrated excellent performance in forecasting the most probable NPP transient response. This research was guided by the Systems Engineering (SE) approach for the systematic and efficient planning and execution of the research.

• 지적과 국토정보
• /
• 제51권2호
• /
• pp.141-150
• /
• 2021

미세먼지는 사람의 건강에 많은 영향을 미치는 물질로서 이와 관련하여 다양한 연구가 이루어지고 있다. 미세먼지의 인체 영향으로 인해 서울시 모니터링 네트워크에서 측정된 과거 데이터를 활용하여 미세먼지를 예측하려는 다양한 연구가 진행되고 있다. 본 연구는 2019년 5월 서울시의 미세먼지를 중점으로 진행하였으며, 학습에 사용한 변수는 SO₂, CO, NO₂, O₃와 같은 대기오염물질 데이터를 활용하였다. 예측모델은 Adaboost에 기반하여 구축하였고, 훈련모델은 PM₁₀과 PM_2.5로 구분하였다. 에러 메트릭스를 통한 예측모델의 정확도 평가 결과로 Adaboost가 시도되었다. 대기오염물질은 초미세먼지와 더 높은 상관성을 보이는 것으로 나타났지만, 보다 효과적인 분포등급을 제시하기 위해서는 많은 양의 데이터를 학습하고, PM₁₀과 PM_2.5의 공간분포 등급을 효과적으로 예측하기 위해서 교통량 등의 추가적인 변수를 활용할 필요성이 있다고 판단된다.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.251-266
• /
• 2022

Structural Health Monitoring (SHM) of critical infrastructure comprises a major pillar of maintenance management, shielding public safety and economic sustainability. Although SHM is usually associated with data-driven metrics and thresholds, expert judgement is essential, especially in cases where erroneous predictions can bear casualties or substantial economic loss. Considering that visual inspections are time consuming and potentially subjective, artificial-intelligence tools may be leveraged in order to minimize the inspection effort and provide objective outcomes. In this context, timely detection of sensor malfunctioning is crucial in preventing inaccurate assessment and false alarms. The present work introduces a sensor-fault detection and interpretation framework, based on the well-established support-vector machine scheme for anomaly detection, combined with a coalitional game-theory approach. The proposed framework is implemented in two datasets, provided along the 1st International Project Competition for Structural Health Monitoring (IPC-SHM 2020), comprising acceleration and cable-load measurements from two real cable-stayed bridges. The results demonstrate good predictive performance and highlight the potential for seamless adaption of the algorithm to intrinsically different data domains. For the first time, the term "decision trajectories", originating from the field of cognitive sciences, is introduced and applied in the context of SHM. This provides an intuitive and comprehensive illustration of the impact of individual features, along with an elaboration on feature dependencies that drive individual model predictions. Overall, the proposed framework provides an easy-to-train, application-agnostic and interpretable anomaly detector, which can be integrated into the preprocessing part of various SHM and condition-monitoring applications, offering a first screening of the sensor health prior to further analysis.

• 한국재난정보학회 논문집
• /
• 제18권3호
• /
• pp.487-494
• /
• 2022

연구목적: 본 연구는 시대적 환경의 변화에 따른 경찰의 다양한 활동에 대한 성과를 효율적으로 증진시킬 수 있는 메타버스 기반 경찰교육훈련모델을 제안하고자 한다. 연구방법: HMD과 햅틱기술을 이용하여 표현되는 Avatar Controller를 생성하고, Network Interface에 접속하여 Cloud Education Server에서의 지휘통제모듈과 교육훈련콘텐츠모듈, 분석모듈 등을 통하여 개인 또는 팀 단위로 교육훈련 할 수 있다. 연구결과: 본 연구의 제안모델에서는 개인이나 팀 단위의 메타버스 기반 교육훈련 시 지휘통제모듈을 접목시킴으로써 테러나 범죄 상황 전반에 대하여 지휘감독요원들이 실시간으로 상황을 모니터링하여 지휘통제 하에 대응훈련을 하게 함으로써 팀원들 간의 유기적인 협업훈련도 가능하게 하였다. 결론: 메타버스를 기반으로 한 개인 또는 팀 단위의 경찰교육훈련은 몰입감, 상호작용 그리고 다양한 상황에서의 신속한 판단 등을 바탕으로 현실과 거의 흡사한 환경을 조성함으로써 보다 더 효율적이고 안전적인 교육훈련환경을 제공할 수 있기 때문에 향후 각국에서 메타버스를 기반으로 한 교육훈련 대응모델들은 지속적으로 성장하며 교육훈련에 있어서 새로운 대안으로 제시될 것으로 기대된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권2호
• /
• pp.369-390
• /
• 2023

Technologies for disaster management are highly sought areas for research and commercial deployment. Landslides, Flood, cyclones, earthquakes, forest fires and road/train accidents are some causes of disasters. Capturing video and accessing data in real time from the disaster site can help first responders make split second decisions which may save human lives and valuable resource destructions. In this context the communication technologies performing the task should have high bandwidth and low latency which only 5G can deliver. But unfortunately in India, deployment of the 5G mobile communication systems is yet to give a shape and again in remote areas unavailability of 4G signals is still severe. In this situation the authors have proposed, simulated and experimented a 4G-5G communication scheme where from the disaster site the signals will be transmitted by a 5G terminal to a nearby 4G-5G gateway installed in a mobile vehicle. The received 5G signal will be further relayed by the 4G-5G gateway to the fixed 4G base station for onward transmission towards the disaster management station for decision making, deployment and relief monitoring. The 4G-5G gateway acts as a relay and converter of 5G signal to 4G signal and vice versa. This relayed system can be further mounted on a vehicle mounted relay (VMR) as proposed by 3GPP in Release 18. The scheme is also in the same line of context with Verizon's, "Tactical Humanitarian Operations Response" (THOR) vehicle concept. The performance of the link is studied in different channel conditions, the throughput achieved is superb. The authors have implemented the above mentioned system towards smart campus networking and monitoring landslides activities which are common in their regions.

• Geomechanics and Engineering
• /
• 제31권6호
• /
• pp.545-556
• /
• 2022

Evaluation and optimization of tunnel wall convergence (TWC) plays a vital role in preventing potential problems during tunnel construction and utilization stage. When convergence occurs at a high rate, it can lead to significant problems such as reducing the advance rate and safety, which in turn increases operating costs. In order to design an effective solution, it is important to accurately predict the degree of TWC; this can reduce the level of concern and have a positive effect on the design. With the development of soft computing methods, the use of deep learning algorithms and neural networks in tunnel construction has expanded in recent years. The current study aims to employ the long-short-term memory (LSTM) deep neural network predictor model to predict the TWC, based on 550 data points of observed parameters developed by collecting required data from different tunnelling projects. Among the data collected during the pre-construction and construction phases of the project, 80% is randomly used to train the model and the rest is used to test the model. Several loss functions including root mean square error (RMSE) and coefficient of determination (R²) were used to assess the performance and precision of the applied method. The results of the proposed models indicate an acceptable and reliable accuracy. In fact, the results show that the predicted values are in good agreement with the observed actual data. The proposed model can be considered for use in similar ground and tunneling conditions. It is important to note that this work has the potential to reduce the tunneling uncertainties significantly and make deep learning a valuable tool for planning tunnels.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.34-34
• /
• 2023

The Chah-Nimeh reservoirs, which are a sort of natural lakes located in the border of Iran and Afghanistan, are the main drinking and agricultural water resources of Sistan arid region. Considering the occurrence of intense seasonal wind, locally known as levar wind, this study aims to explore the possibility to provide a TSM (Total Suspended Matter) monitoring model of Chah-Nimeh reservoirs using multi-temporal satellite images and in-situ wind speed data. The results show that a strong correlation between TSM concentration and wind speed are present. The developed empirical model indicated high performance in retrieving spatiotemporal distribution of the TSM concentration with R²=0.98 and RMSE=0.92g/m³. Following this observation, we also consider a machine learning-based model to predicts the average TSM using only wind speed. We connect our in-situ wind speed data to the TSM data generated from the inversion of multi-temporal satellite imagery to train a neural network based mode l(Wind2TSM-Net). Examining Wind2TSM-Net model indicates this model can retrieve the TSM accurately utilizing only wind speed (R²=0.88 and RMSE=1.97g/m³). Moreover, this results of this study show tha the TSM concentration can be estimated using only in situ wind speed data independent of the satellite images. Specifically, such model can supply a temporally persistent means of monitoring TSM that is not limited by the temporal resolution of imagery or the cloud cover problem in the optical remote sensing.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.95-100
• /
• 2023

Due to Traffic accidents people faces health and economical casualties around the world. As the population increases vehicles on road increase which leads to congestion in cities. Congestion can lead to increasing accident risks due to the expansion in transportation systems. Modern cities are adopting various technologies to minimize traffic accidents by predicting mathematically. Traffic accidents cause economical casualties and potential death. Therefore, to ensure people's safety, the concept of the smart city makes sense. In a smart city, traffic accident factors like road condition, light condition, weather condition etcetera are important to consider to predict traffic accident severity. Several machine learning models can significantly be employed to determine and predict traffic accident severity. This research paper illustrated the performance of a hybridized neural network and compared it with other machine learning models in order to measure the accuracy of predicting traffic accident severity. Dataset of city Leeds, UK is being used to train and test the model. Then the results are being compared with each other. Particle Swarm optimization with artificial neural network (PSO-ANN) gave promising results compared to other machine learning models like Random Forest, Naïve Bayes, Nearest Centroid, K Nearest Neighbor Classification. PSO- ANN model can be adopted in the transportation system to counter traffic accident issues. The nearest centroid model gave the lowest accuracy score whereas PSO-ANN gave the highest accuracy score. All the test results and findings obtained in our study can provide valuable information on reducing traffic accidents.

• 대한의용생체공학회:의공학회지
• /
• 제44권3호
• /
• pp.211-217
• /
• 2023

Recently, many studies have introduced artificial intelligence systems in the surgical process to reduce the incidence and mortality of complications in patients. Bleeding is a major cause of operative mortality and complications. However, there have been few studies conducted on detecting bleeding in surgical videos. To advance the development of deep learning models for detecting intraoperative hemorrhage, three models have been trained and compared; such as, YOLOv5, RetinaNet50, and RetinaNet101. We collected 1,016 bleeding images extracted from five surgical videos. The ground truths were labeled based on agreement from two specialists. To train and evaluate models, we divided the datasets into training data, validation data, and test data. For training, 812 images (80%) were selected from the dataset. Another 102 images (10%) were used for evaluation and the remaining 102 images (10%) were used as the evaluation data. The three main metrics used to evaluate performance are precision, recall, and false positive per image (FPPI). Based on the evaluation metrics, RetinaNet101 achieved the best detection results out of the three models (Precision rate of 0.99±0.01, Recall rate of 0.93±0.02, and FPPI of 0.01±0.01). The information on the bleeding detected in surgical videos can be quickly transmitted to the operating room, improving patient outcomes.