• 한국멀티미디어학회논문지
• /
• 제23권2호
• /
• pp.343-350
• /
• 2020

In the era of the Fourth Industrial Revolution in the digital revolution is taking place, various attempts have been made to provide various contents in a digital environment. In this paper, agent-recruitment service system based on collaborative deep learning is proposed for the intelligent head hunting service. The service system is improved from previous research [7] using collaborative deep learning for more reliable recommendation results. The Collaborative deep learning is a hybrid recommendation algorithm using "Recurrent Neural Network(RNN)" specialized for exponential calculation, "collaborative filtering" which is traditional recommendation filtering methods, and "KNN-Clustering" for similar user analysis. The proposed service system can expect more reliable recommendation results than previous research and showed high satisfaction in user survey for verification.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권10호
• /
• pp.1799-1813
• /
• 2011

Many researches indicate that programming learning could help improve problem solving skills through algorithmic thinking. But in general, programming learning has been focused on programming language features and it also gave a heavy cognitive load to learners. Therefore, this paper proposes a programming activity process to improve novice programming learners' algorithmic thinking efficiently. An experiment was performed to measure the effectiveness of the proposed programming activity process. After the experiment, the learners' perception on programming was shown to be changed, to effective activity in improving problem solving.

• 센서학회지
• /
• 제33권3호
• /
• pp.119-124
• /
• 2024

Effective fire sensing is important to protect lives and property from the disaster. In this paper, we present an intelligent visual sensing method for detecting fires based on machine learning techniques. The proposed method involves a two-step process. In the first step, fire and non-fire images are used to train a convolutional neural network (CNN), and in the next step, feature vectors consisting of 256 values obtained from the CNN are used for the learning of a support vector machine (SVM). Linear and nonlinear SVMs with different parameters are intensively tested. We found that the proposed hybrid method using an SVM with a linear kernel effectively increased the recall rate of fire image detection without compromising detection accuracy when an imbalanced dataset was used for learning. This is a major contribution of this study because recall is important, particularly in the sensing of disaster situations such as fires. In our experiments, the proposed system exhibited an accuracy of 96.9% and a recall rate of 92.9% for test image data.

• Smart Structures and Systems
• /
• 제31권5호
• /
• pp.485-500
• /
• 2023

Machine learning-based structural health monitoring (ML-based SHM) methods are researched extensively in the recent decade due to the availability of advanced information and sensing technology. ML methods are well-known for their pattern recognition capability for complex problems. However, the main obstacle of ML-based SHM is that it often requires pre-collected historical data for model training. In most actual scenarios, damage presence can be detected using the unsupervised learning method through anomaly detection, but to further identify the damage types would require prior knowledge or historical events as references. This creates the cold-start problem, especially for new and unobserved structures. Modal-based methods identify damages based on the changes in the structural global properties but often require dense measurements for accurate results. Therefore, a two-stage hybrid modal-machine learning damage detection scheme is proposed. The first stage detects damage presence using Principal Component Analysis-Frequency Response Function (PCA-FRF) in an unsupervised manner, whereas the second stage further identifies the damage. To solve the cold-start problem, mode shape assessment using the first mode is initiated when no trained model is available yet in the second stage. The damage identified by the modal-based method would be stored for future training. This work highlights the performance of the scheme in alleviating the cold-start issue as it transitions through different phases, starting from zero damage sample available. Results showed that single and multiple damages can be identified at an acceptable accuracy level even when training samples are limited.

• Computers and Concrete
• /
• 제34권3호
• /
• pp.279-296
• /
• 2024

In this study, ensemble machine learning (ML) models are employed to estimate the hardened properties of Self-Compacting Geopolymer Concrete (SCGC). The input variables affecting model development include the content of the SCGC such as the binder material, the age of the specimen, and the ratio of alkaline solution. On the other hand, the output parameters examined includes compressive strength, flexural strength, and split tensile strength. The ensemble machine learning models are trained and validated using a database comprising 396 records compiled from 132 unique mix trials performed in the laboratory. Diverse machine learning techniques, notably K-nearest neighbours (KNN), Random Forest, and Extreme Gradient Boosting (XGBoost), have been employed to construct the models coupled with Bayesian optimisation (BO) for the purpose of hyperparameter tuning. Furthermore, the application of nested cross-validation has been employed in order to mitigate the risk of overfitting. The findings of this study reveal that the BO-XGBoost hybrid model confirms better predictive accuracy in comparison to other models. The R² values for compressive strength, flexural strength, and split tensile strength are 0.9974, 0.9978, and 0.9937, respectively. Additionally, the BO-XGBoost hybrid model exhibits the lowest RMSE values of 0.8712, 0.0773, and 0.0799 for compressive strength, flexural strength, and split tensile strength, respectively. Furthermore, a SHAP dependency analysis was conducted to ascertain the significance of each parameter. It is observed from this study that GGBS, Flyash, and the age of specimens exhibit a substantial level of influence when predicting the strengths of geopolymers.

• 경영정보학연구
• /
• 제25권1호
• /
• pp.129-143
• /
• 2023

빅데이터 시대를 맞이하여 인공지능 분야는 괄목할만한 성장을 보이고 있으며 특히 딥러닝에 의한 이미지 분류 학습방법이 중요한 영역으로 자리하고 있다. 이미지 분류에서 많이 사용되어 온 CNN의 성능을 더욱 개선하기 위해 다양한 연구가 활발하게 진행되었는데, 이 중에서 대표적인 방법이 CRNN(Convolutional Recurrent Neural Network) 알고리즘이다. CRNN 알고리즘은 이미지 분류를 위한 CNN과 시계열적 요소를 인식하기 위한 RNN의 조합으로 구성되는데, CRNN의 RNN영역에서 사용하는 입력값은 학습 대상의 이미지를 합성곱과 풀링 기법을 적용하여 추출된 결과물을 flatten한 값이고, 이 입력값들은 이미지 내 동일 위상에 있는 픽셀값들이 서로 다른 순서로 나타나기 때문에, RNN에서 의도한 이미지 내 배열 순서를 제대로 학습하기 어렵다는 한계점을 지닌다. 따라서 본 연구는 인코더와 디코더의 개념을 응용한 CNN과 RNN의 새로운 하이브리드 방법을 제안하여, 이미지 분류 성능을 향상시키는 것을 목적으로 하였다. 본 연구에서는 다양한 알고리즘 비교 실험을 통해, 새로운 하이브리드 방법의 효과성을 검증하였다. 본 연구는 인코더와 디코더 개념의 적용 가능성을 넓히고, 제안한 방법이 기존 하이브리드 방법에 비해, 복잡도가 크게 증가하지 않아 모델 학습 시간과 인프라 구축 비용 측면에서 이점을 있다는 점에서 학문적 시사점을 가진다. 또한, 정확한 이미지 분류가 필요한 다양한 분야에서 제공되는 서비스의 품질을 높일 수 있는 가능성을 제시하였다는 점에서 실무적 시사점을 가진다.

• Smart Structures and Systems
• /
• 제24권6호
• /
• pp.733-744
• /
• 2019

Wind speed forecasting is critical for a variety of engineering tasks, such as wind energy harvesting, scheduling of a wind power system, and dynamic control of structures (e.g., wind turbine, bridge, and building). Wind speed, which has characteristics of random, nonlinear and uncertainty, is difficult to forecast. Nowadays, machine learning approaches (generalized regression neural network (GRNN), back propagation neural network (BPNN), and extreme learning machine (ELM)) are widely used for wind speed forecasting. In this study, two schemes are proposed to improve the forecasting performance of machine learning approaches. One is that optimization algorithms, i.e., cross validation (CV), genetic algorithm (GA), and particle swarm optimization (PSO), are used to automatically find the optimal model parameters. The other is that the combination of different machine learning methods is proposed by finite mixture (FM) method. Specifically, CV-GRNN, GA-BPNN, PSO-ELM belong to optimization algorithm-assisted machine learning approaches, and FM is a hybrid machine learning approach consisting of GRNN, BPNN, and ELM. The effectiveness of these machine learning methods in wind speed forecasting are fully investigated by one-year field monitoring data, and their performance is comprehensively compared.

• 의학교육논단
• /
• 제23권3호
• /
• pp.147-153
• /
• 2021

The coronavirus disease 2019 (COVID-19) pandemic made it necessary for medical schools to restructure their curriculum by switching from face-to-face instruction to various forms of flexible learning. Flexible learning is a student-centered approach to learning that has received interest in many educational sectors. It is a critical strategy for expanding access to higher education during the pandemic. As flexible learning includes online, blended, hybrid, and hyflex learning options, learners have the opportunity to select an instruction modality based on their needs and interests. The shift to flexible learning in medical education took place rapidly in response to the COVID-19 pandemic, and learners, instructors, and schools were not prepared for this instructional change. Through the lens of the technology acceptance model, human agency, and a social constructivist perspective, I examine students, instructors, and educational institutions' roles in successfully navigating the digital transformation era. The pandemic has also accelerated the use of advanced information and communication technologies, such as artificial intelligence and virtual reality, in learning. Through a review of the literature, this paper aimed to reflect on current flexible learning practices from the instructional design and educational technology perspective and explore emerging technologies that may be implemented in future medical education.

• 지능정보연구
• /
• 제12권3호
• /
• pp.67-82
• /
• 2006

가상 로봇의 행동 진화를 위해서 규칙 구성자와 연결 구성자를 구성하여 분류 규칙과 진화 신경망을 형성하는 혼합형 행동 진화 모델(Hybrid Behavior Evolution Model)을 제안한다. 본 모델에서는 행동 지식을 두 수준에서 표현하였다. 상위 수준에서는 규칙 구성자와 연결 구성자를 구성하여 표현력을 향상시켰다. 하위 수준에서는 행동 지식을 비트 스트링 형태의 염색체로 표현하여, 이들 염색체를 대상으로 유전자 연산을 적용하여 학습을 수행시켰다. 적합도가 최적인 염색체를 추출하여 가상 로봇을 구성하였다. 구성된 가상 로봇은 주변 상황을 인식하여 입력 정보와 규칙 정보를 이용하여 패턴을 분류하였고, 그 결과를 신경망에서 처리하여 행동하였다. 제안된 모델을 평가하기 위해서 HBES(Hybrid Behavior Evolution System)를 개발하여 가상 로봇의 먹이 수집 문제에 적용하였다. 제안한 시스템을 실험한 결과, 동일한 조건의 진화 신경망보다 학습 시간이 적게 소요되었다. 그리고, 규칙이 적합도 향상에 주는 영향을 평가하기 위해서, 학습이 완료된 염색체들에 대해서 규칙을 적용한 것과, 그렇지 않은 것을 각각 수행하여 적합도를 측정하였다. 그 결과, 규칙을 적용하지 않으면 적합도가 저하되는 것을 확인하였다. 제안된 모델은 가상 로봇의 행동 진화에 있어서 기존의 진화 신경망 방식 보다 학습 성능이 우수하고 규칙적인 행동을 수행하는 것을 확인하였다.

• 디지털콘텐츠학회 논문지
• /
• 제18권1호
• /
• pp.93-99
• /
• 2017

Long Short Term Memory (LSTM) Recurrent Neural Network (RNN)를 이용한 hybrid 방법은 음성 인식률을 크게 향상시켰다. Hybrid 방법에 기반한 음향모델을 학습하기 위해서는 Gaussian Mixture Model (GMM)-Hidden Markov Model (HMM)로부터 forced align된 HMM state sequence가 필요하다. 그러나, GMM-HMM을 학습하기 위해서 많은 연산 시간이 요구되고 있다. 본 논문에서는 학습 속도를 향상하기 위해, LSTM RNN 기반 한국어 음성인식을 위한 end-to-end 방법을 제안한다. 이를 구현하기 위해, Connectionist Temporal Classification (CTC) 알고리즘을 제안한다. 제안하는 방법은 기존의 방법과 비슷한 인식률을 보였지만, 학습 속도는 1.27 배 더 빨라진 성능을 보였다.