• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.647-654
• /
• 2023

Deep Learning is a useful method for classifying and recognizing complex data such as images and text, and the accuracy of the deep learning method is the basis for making artificial intelligence-based services on the Internet useful. However, the vast amount of user da vita used for training in deep learning has led to privacy violation problems, and it is worried that companies that have collected personal and sensitive data of users, such as photographs and voices, own the data indefinitely. Users cannot delete their data and cannot limit the purpose of use. For example, data owners such as medical institutions that want to apply deep learning technology to patients' medical records cannot share patient data because of privacy and confidentiality issues, making it difficult to benefit from deep learning technology. In this paper, we have designed a privacy preservation technique-applied deep learning technique that allows multiple workers to use a neural network model jointly, without sharing input datasets, in multi-party system. We proposed a method that can selectively share small subsets using an optimization algorithm based on modified stochastic gradient descent, confirming that it could facilitate training with increased learning accuracy while protecting private information.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.361-361
• /
• 2022

최근 기후변화의 영향으로 국지성 집중호우에 의한 홍수 피해가 빈번히 발생하고 있으며, 이로 인한 인명 및 재산 피해가 증가하고 있다. 2020년의 경우, 최장 기간 장마로 인해 금강유역을 비롯한 전국에서 산사태, 제방 붕괴, 침수 등 많은 피해가 발생하였다. 이러한 홍수피해 저감을 위해서는 신뢰도 높은 홍수량 예측이 요구된다. 특히, 토양수분과 같이 시간에 따른 유역 수문 정보를 모의 과정에서 고려하는 것이 매우 중요하다. 아울러, 유역 전반에 대한 토양수분 정보는 실시간으로 획득하는 것이 어려워 이를 고려할 수 있는 강우-유출모형을 활용하는 것이 바람직하다. 이러한 수문모형으로 SURR(Sejong University Rainfall Runoff) 모형이 있으며 다양한 적용 및 평가를 통해 모형 활용성에 대한 증진이 요구되는 실정이다. 본 연구에서는 저류함수 기반의 시단위 연속형 강우-유출모형(SURR 모형)을 활용한 강우-유출 모의를 수행하여 홍수 피해가 컸던 금강유역을 대상으로 모형의 적용성을 평가하고자 한다. 평가기간은 2006~2020년으로써 유량관측 지점별 매개변수 검·보정을 수행하였다. 관측 및 모의 유량에 대한 도시적 및 통계적(CC, RMSE, NSE) 평가를 수행하여 유출 모의에 대한 정확도를 평가하였다. 평가결과, 관측 및 모의 유량 간의 거동이 유사한 것으로 나타났으며 첨두유량 및 시간이 비교적 잘 일치하는 것으로 나타나 대상유역의 신뢰도 높은 유출량을 모의하는데 적합한 것으로 확인되었다. 본 연구 결과는 향후 AI 기법과 연계한 돌발홍수 예측 연구에 활용하여 정확도 높은 유역 홍수량 예측 및 선행시간 확보에 도움이 될 것으로 기대된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.37-37
• /
• 2022

유효우량 산정을 위하여 국내에서 주로 사용되는 모형은 NRCS-CN(Natural Resources Conservation Service - curve number) 모형으로, 유역의 유출 능력을 나타내는 유출곡선지수(runoff curve number, CN)와 같은 NRCS-CN 모형의 매개변수들은 관측 강우-유출자료 또는 토양도, 토지피복지도 등을 이용하여 유역마다 결정된 값이 사용되고 있다. 그러나 유역의 CN값은 유역의 토양 상태와 같은 환경적 조건에 따라 달라질 수 있으며, 이를 반영하기 위하여 선행토양함수조건(antecedent moisture condition, AMC)을 이용하여 CN값을 조정하는 방법이 사용되고 있으나, AMC 조건에 따른 CN 값의 갑작스런 변화는 유출량의 극단적인 변화를 가져올 수 있다. NRCS-CN 모형과 더불어 강우 손실량 산정에 많이 사용되는 모형으로 Green-Ampt 모형이 있다. Green-Ampt 모형은 유역에서 발생하는 침투현상의 물리적 과정을 고려하는 모형이라는 장점이 있으나, 모형에 활용되는 다양한 물리적인 매개변수들을 산정하기 위해서는 유역에 대한 많은 조사가 선행되어야 한다. 또한 이렇게 산정된 매개변수들은 유역 내 토양이나 식생 조건 등에 따른 여러 불확실성을 내포하고 있어 실무적용에 어려움이 있다. 따라서 본 연구에서는, 현재 사용되고 있는 강우손실 모형들의 매개변수를 추정하기 위한 방법을 제시하고자 하였다. 본 연구에서 제시하는 방법은 인공지능(AI) 기술 중 하나인 딥러닝(deep-learning) 기법을 기반으로 하고 있으며, 딥러닝 모형으로는 장단기 메모리(Long Short-Term Memory, LSTM) 모형이 활용되었다. 딥러닝 모형의 입력 데이터는 유역에서의 강우특성이나 토양수분, 증발산, 식생 특성들을 나타내는 인자이며, 모의 결과는 유역에서 발생한 총 유출량으로 강우손실 모형들의 매개변수 값들은 이들을 활용하여 도출될 수 있다. 산정된 매개변수 값들을 강우손실 모형에 적용하여 실제 유역들에서의 유효우량 산정에 활용해보았으며, 동역학파 기반의 강우-유출 모형을 사용하여 유출을 예측해보았다. 예측된 유출수문곡선을 관측 자료와 비교 시 NSE=0.5 이상으로 산정되어 유출이 적절히 예측되었음을 확인했다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.132-133
• /
• 2023

The safe evacuation of people during disasters is of utmost importance. Various life safety evacuation simulation tools have been developed and implemented, with most relying on algorithms that analyze maps to extract the shortest path and guide agents along predetermined routes. While effective in predicting evacuation routes in stable disaster conditions and short timeframes, this approach falls short in dynamic situations where disaster scenarios constantly change. Existing algorithms struggle to respond to such scenarios, prompting the need for a more adaptive evacuation route algorithm that can respond to changing disasters. Artificial intelligence technology based on reinforcement learning holds the potential to develop such an algorithm. As a fundamental step in algorithm development, this study aims to evaluate whether an evacuation algorithm developed by reinforcement learning satisfies the performance conditions of the evacuation simulation tool required by IMO MSC.1/Circ1533.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.67-77
• /
• 2023

This study represents an innovative research conducted in the smart farm environment, developing a deep learning-based disease and pest detection model and applying it to the Intelligent Internet of Things (IoT) platform to explore new possibilities in the implementation of digital agricultural environments. The core of the research was the integration of the latest ImageNet models such as Pseudo-Labeling, RegNet, EfficientNet, and preprocessing methods to detect various diseases and pests in complex agricultural environments with high accuracy. To this end, ensemble learning techniques were applied to maximize the accuracy and stability of the model, and the model was evaluated using various performance indicators such as mean Average Precision (mAP), precision, recall, accuracy, and box loss. Additionally, the SHAP framework was utilized to gain a deeper understanding of the model's prediction criteria, making the decision-making process more transparent. This analysis provided significant insights into how the model considers various variables to detect diseases and pests.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.259-266
• /
• 2023

In this paper, we propose an algorithm that can improve the accuracy performance of collaborative filtering using attribute-based opinion mining (ABOM). For the experiment, a total of 1,227 online consumer review data about smartphone apps from domestic smartphone users were used for analysis. After morpheme analysis using the KKMA (Kkokkoma) analyzer and emotional word analysis using KOSAC, attribute extraction is performed using LDA topic modeling, and the topic modeling results for each weighted review are used to add up the ratings of collaborative filtering and the sentiment score. MAE, MAPE, and RMSE, which are statistical model performance evaluations that calculate the average accuracy error, were used. Through experiments, we predicted the accuracy of online customers' app ratings (APP_Score) by combining traditional collaborative filtering among the recommendation algorithms and the attribute-based opinion mining (ABOM) technique, which combines LDA attribute extraction and sentiment analysis. As a result of the analysis, it was found that the prediction accuracy of ratings using attribute-based opinion mining CF was better than that of ratings implementing traditional collaborative filtering.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.12
• /
• pp.357-362
• /
• 2023

Bridges are important transportation infrastructure, but they are subject to damage and cracking due to various environmental factors and constant traffic loads, which accelerate their aging. With many bridges now older than their original construction, there is a need for systems to ensure safety and diagnose deterioration. Bridges are already utilizing structural health monitoring (SHM) technology to monitor the condition of bridges in real time or periodically. Along with this technology, the development of intelligent bridge monitoring technology utilizing artificial intelligence and Internet of Things technology is underway. In this paper, we study an edge system technique for predicting bridge safety using fast Fourier transform and dimensionality reduction algorithm for maintenance of aging bridges. In particular, unlike previous studies, we investigate whether it is possible to form a dataset using sensor data collected from actual bridges and check the safety of bridges.

• Information Systems Review
• /
• v.18 no.4
• /
• pp.173-187
• /
• 2016

This study on the social effects of Internet of Things (IoTs) provides an overview of future job prospects through the scenario planning approach, highlighting the challenges and opportunities that IoTs will bring in the future. IoTs and the related field of technological innovations have become increasingly important in both academic and business communities in the past few years because of computing power breakthrough and its price drop. IoTs enables people to deal with routine works efficiently and challenges them even in non-routine and/or cognitive tasks, which are considered a unique area for individuals. The scenario planning analysis helps us to define the uncertain boundary and to estimate the potential opportunities and inherent threats to provide decision makers with a mind map on how the development of IoTs can influence employment. To assess the potential effects on jobs described in our scenarios, we briefly examine the local structure of employment and discuss which careers are expected to decline or grow in particular among the 52 standard occupational classifications in Korea.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.6
• /
• pp.175-182
• /
• 2024

In wireless sensor networks, batteries limit lifespan, and heavy data transmission around the sink causes the hotspot problem. To address this, data collection amounts are allocated to child nodes to limit transmission. However, this approach has issues with nodes far from the sink having excessive energy and failing to transmit the allocated amount due to data transmission errors. This paper proposes a method to prevent sensor data loss through error recovery via retransmission. The method ensures that each node's retransmission volume stays within its allocated data amount and energy limits, using excess energy for error recovery. Simulations show that this technique effectively recovers data transmission errors, collects data, minimizes energy depletion around the sink, and increases data collection rates.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.163-169
• /
• 2020

Recently, research on automation and unmanned operation of machines in the industrial field has been conducted with the advent of AI, Big data, and the IoT, which are the core technologies of the Fourth Industrial Revolution. The machines for these automation processes are controlled based on the data collected from the sensors attached to them, and further, the processes are managed. Conventionally, the abnormalities of sensors are periodically checked and managed. However, due to various environmental factors and situations in the industrial field, there are cases where the inspection due to the failure is not missed or failures are not detected to prevent damage due to sensor failure. In addition, even if a failure occurs, it is not immediately detected, which worsens the process loss. Therefore, in order to prevent damage caused by such a sudden sensor failure, it is necessary to identify the failure of the sensor in an embedded system in real-time and to diagnose the failure and determine the type for a quick response. In this paper, a deep neural network-based fault diagnosis system is designed and implemented using Raspberry Pi to classify typical sensor fault types such as erratic fault, hard-over fault, spike fault, and stuck fault. In order to diagnose sensor failure, the network is constructed using Google's proposed Inverted residual block structure of MobilieNetV2. The proposed scheme reduces memory usage and improves the performance of the conventional CNN technique to classify sensor faults.