• 한국컴퓨터정보학회논문지
• /
• 제21권5호
• /
• pp.91-98
• /
• 2016

We propose a method to train a model that can predict the probability of a crime being committed. CCTV data by matching criminal events are required to train the crime prediction model. However, collecting CCTV data appropriate for training is difficult. Thus, we collected actual criminal records and converted them to an appropriate format using variables by considering a crime prediction environment and the availability of real-time data collection from CCTV. In addition, we identified new specific crime types according to the characteristics of criminal events and trained and tested the prediction model by applying neural network partial least squares for each crime type. Results show a level of predictive accuracy sufficiently significant to demonstrate the applicability of CCTV to real-time crime prediction.

• The Journal of Asian Finance, Economics and Business
• /
• 제8권2호
• /
• pp.195-200
• /
• 2021

In recent years, Vietnam's economic growth rate has been attributed to the growth of many well-managed industries within Southeast Asia. Among them is the civil construction industry. Construction projects typically take a long time to complete and require a huge budget. Many socio-economic variables and factors affect total construction project costs due to market fluctuations. In recent years, crucial socioeconomic development indicators of construction reached a fairly high growth rate. Also, most infrastructure and construction projects have a high degree of complexity and uncertainty. This makes it challenging to predict the accurate project price. These challenges raise the need to recognize significant factors that influence the construction price index of civil buildings in Vietnam, both micro and macro. Therefore, this paper presents critical factors that affect the construction price index using the fuzzy extent analysis process in an uncertain environment. This proposed quantitative model is expected to reflect the uncertainty in the process of evaluating and ranking the influencing factors of the construction price index in Vietnam. The research results would also allow project stakeholders to be more informed of the factors affecting the construction price index in the context of Vietnam's civil construction industry. They also enable construction contractors to estimate project costs and bid rates better, enhancing their project and risk management performance.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권9호
• /
• pp.399-406
• /
• 2023

클라우드 컴퓨팅은 에지 서버가 동작하는 포그(fog) 레이어가 결합된 에지(edge) 컴퓨팅 아키텍처로 진화하고 있다. 에지 컴퓨팅 아키텍처가 관심을 받는 이유는 짧은 통신 지연으로 실시간 IoT 응용을 지원할 수 있기 때문이다. 이와 동시에 인공지능 기술을 도입한 많은 클라우드 작업 스케줄링 기법들이 제안되었다. 인공지능 기반의 클라우드 작업 스케줄링 기법은 기존 기법보다 더 좋은 성능을 보이지만 스케줄링 시간이 다소 소요된다는 단점이 있다. 이 논문에서는 에지 컴퓨팅 환경에서 분산 딥러닝 학습 기반의 동적 스케줄링 기법을 제안한다. 제안하는 기법은 기존 기법보다 스케줄링 시간이 짧은 장점이 있다. 또한 멀티 에이전트를 통한 분산 딥러닝 학습의 효과성을 보이기 위해 확장적인 실험 환경에서 제안 기법과 기존 인공지능 기법의 성능일 비교 평가하였다. 성능 실험 결과 기존 인공지능 기반 클라우드 작업 스케줄링 기법보다 짧은 스케줄링 시간을 보여 IoT 실시간 응용에 적합함을 보였으며, 확장적인 실험에서도 제안 기법이 완료된 작업의 수에 대하여 우수한 성능을 보임을 증명하였다.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1996년도 춘계공동학술대회논문집; 공군사관학교, 청주; 26-27 Apr. 1996
• /
• pp.131-134
• /
• 1996

Application of machine learning to scheduling problems has focused on improving system performance based on opportunistic selection among multitudes of simple rules. This study proposes a new method of learning scheduling rules, which first establishes qualitatively meaningful criteria and quantitatively optimizes the use of them, a similar way as human scheduler accumulate their expertise. The weighting of these criteria is trained in response to the system states through simulation. To mimic human quantitative feelings, distributed fuzzy sets are used for assessing the system state. The proposed method was applied to job dispatching in a simulated FMS environment. The job-dispatching criteria used were the length of the processing time of a job and the situation of the next workstation. The results show that the proposed method can develop efficient and robust scheduling strategies, which can also provide understandable and usable know-hows to the human scheduler.

• Asia pacific journal of information systems
• /
• 제32권2호
• /
• pp.226-248
• /
• 2022

The existing model for sentiment analysis of product reviews learned from past data and new data was labeled based on training. But new data was never used by the existing system for making a decision. The proposed Aspect-based multi-agent Deep Reinforcement learning Sentiment Analysis (ADRSA) model learned from its very first data without the help of any training dataset and labeled a sentence with aspect category and sentiment polarity. It keeps on learning from the new data and updates its knowledge for improving its intelligence. The decision of the proposed system changed over time based on the new data. So, the accuracy of the sentiment analysis using deep reinforcement learning was improved over supervised learning and unsupervised learning methods. Hence, the sentiments of premium customers on a particular site can be explored to other customers effectively. A dynamic environment with a strong knowledge base can help the system to remember the sentences and usage State Action Reward State Action (SARSA) algorithm with Bidirectional Encoder Representations from Transformers (BERT) model improved the performance of the proposed system in terms of accuracy when compared to the state of art methods.

• 한국물환경학회지
• /
• 제37권4호
• /
• pp.275-285
• /
• 2021

Algal bloom is an important issue in maintaining the safety of the drinking water supply system. Fast detection and classification of algae images are essential for the management of algal blooms. Conventional visual identification using a microscope is a labor-intensive and time-consuming method that often requires several hours to several days in order to obtain analysis results from field water samples. In recent decades, various deep learning algorithms have been developed and widely used in object detection studies. YOLO is a state-of-the-art deep learning algorithm. In this study the third version of the YOLO algorithm, namely, YOLOv3, was used to develop an algae image detection model. YOLOv3 is one of the most representative one-stage object detection algorithms with faster inference time, which is an important benefit of YOLO. A total of 1,114 algae images for 30 genera collected by microscope were used to develop the YOLOv3 algae image detection model. The algae images were divided into four groups with five, 10, 20, and 30 genera for training and testing the model. The mean average precision (mAP) was 81, 70, 52, and 41 for data sets with five, 10, 20, and 30 genera, respectively. The precision was higher than 0.8 for all four image groups. These results show the practical applicability of the deep learning algorithm, YOLOv3, for algae image detection.

• 한국멀티미디어학회논문지
• /
• 제24권6호
• /
• pp.838-848
• /
• 2021

Parents' influence on children's development is generally considered essential. This paper attempts to explore the role of AR in preschool education from the perspective of parents, aiming to help parents better understand the impact of children's use of augmented reality in preschool education. The subjects were parents of children in the preschool age range (3-6 years old), and the experimental equipment was AR cognitive cards. In order to extract parents' views on AR, five parents were invited to conduct an experiment with their children using AR cognition cards, and then an open interview survey was conducted. In the second experiment, the answers obtained from the first experiment were sorted out and formed a questionnaire to conduct a closed-book survey. It shows that parents are satisfied with the characteristics of AR to assist their children's learning. At the same time, parents also value technology, usage management and playing environment. AR can stimulate children's learning initiative. Children like to use AR, AR is suitable for learning, make parents satisfied. But even if AR is suitable for learning, parents will control the time their children use it.

• 한국융합학회논문지
• /
• 제11권8호
• /
• pp.139-145
• /
• 2020

컴퓨터 기술의 급속한 발전으로 인해 ICT 기술을 이용한 온라인 학습은 이미 우리 생활에 빠르게 정착하고 있다. 음악 교육은 오프라인 기반의 환경을 중심으로 진행되었으나, 온라인 교육에 시공간 제약이 없다는 점, 학습자 주도의 쌍방향 교육이 가능하다는 점에서 그 교육 방식을 온라인으로 전환하는 연구가 활발히 진행되고 있다. 본 연구는 온라인에서 적응형 학습이 가능하도록 '화성학' 학습 시스템을 제안, 설계, 구현하는 일련의 과정을 담는다. 이 시스템은 다음과 같은 긍정적 효과를 기대할 수 있다. 첫째, LMS 기반의 플랫폼을 제공하여, 경제적·지리적 요인에 해당하는 사회적 교육 문제를 해결할 수 있다. 둘째, 온라인 적응형 화성학 학습 시스템이 자동으로 제공하는 객관적인 학습 피드백과 교수자의 학습 피드백을 모두 제공한다. 셋째, 학습자가 자신이 학습한 화성학 문제에 대한 추천 답안을 받을 수 있다. 이러한 이점을 활용한 온라인 적응형 화성학 학습 시스템은 교수자와 학습자 간의 효과적인 교수 학습을 증진시킬 수 있을 것으로 기대한다.

• 품질경영학회지
• /
• 제48권4호
• /
• pp.553-566
• /
• 2020

Purpose: The purpose of this study was to design a framework for generating one-class classification algorithm based on Hyper-Rectangle(H-RTGL) in a distributed environment connected by network. Methods: At first, we devised one-class classifier based on H-RTGL which can be performed by distributed computing nodes considering model and data parallelism. Then, we also designed facilitating components for execution of distributed processing. In the end, we validate both effectiveness and efficiency of the classifier obtained from the proposed framework by a numerical experiment using data set obtained from UCI machine learning repository. Results: We designed distributed processing framework capable of one-class classification based on H-RTGL in distributed environment consisting of physically separated computing nodes. It includes components for implementation of model and data parallelism, which enables distributed generation of classifier. From a numerical experiment, we could observe that there was no significant change of classification performance assessed by statistical test and elapsed time was reduced due to application of distributed processing in dataset with considerable size. Conclusion: Based on such result, we can conclude that application of distributed processing for generating classifier can preserve classification performance and it can improve the efficiency of classification algorithms. In addition, we suggested an idea for future research directions of this paper as well as limitation of our work.

• 상하수도학회지
• /
• 제38권2호
• /
• pp.83-93
• /
• 2024

In this study, we present a sewer pipe inspection technique through a combination of active sonar technology and deep learning algorithms. It is difficult to inspect pipes containing water using conventional CCTV inspection methods, and there are various limitations, so a new approach is needed. In this paper, we introduce a inspection method using active sonar, and apply an auto encoder deep learning model to process sonar data to distinguish between normal and abnormal pipelines. This model underwent training on sonar data from a controlled environment under the assumption of normal pipeline conditions and utilized anomaly detection techniques to identify deviations from established standards. This approach presents a new perspective in pipeline inspection, promising to reduce the time and resources required for sewer system management and to enhance the reliability of pipeline inspections.