• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.3
• /
• pp.399-407
• /
• 2019

In Korea, the construction industry has been known to have the highest risk of safety accidents compared to other industries. Therefore, in order to improve safety in the construction industry, several researches have been carried out from the past. This study aims at improving safety of labors in construction site by constructing an effective automatic safety helmet detection system using object detection algorithm based on image data of construction field. Deep learning was conducted using Region-based Fully Convolutional Network (R-FCN) which is one of the object detection algorithms based on Convolutional Neural Network (CNN) with Transfer Learning technique. Learning was conducted with 1089 images including human and safety helmet collected from ImageNet and the mean Average Precision (mAP) of the human and the safety helmet was measured as 0.86 and 0.83, respectively.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.2
• /
• pp.65-72
• /
• 2021

Recently, attacks on the network environment have been rapidly escalating and intelligent. Thus, the signature-based network intrusion detection system is becoming clear about its limitations. To solve these problems, research on machine learning-based intrusion detection systems is being conducted in many ways, but two problems are encountered to use machine learning for intrusion detection. The first is to find important features associated with learning for real-time detection, and the second is the imbalance of data used in learning. This problem is fatal because the performance of machine learning algorithms is data-dependent. In this paper, we propose the HSF-DNN, a network intrusion detection model based on a deep neural network to solve the problems presented above. The proposed HFS-DNN was learned through the NSL-KDD data set and performs performance comparisons with existing classification models. Experiments have confirmed that the proposed Hybrid Feature Selection algorithm does not degrade performance, and in an experiment between learning models that solved the imbalance problem, the model proposed in this paper showed the best performance.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.101-125
• /
• 2022

Recently, with the development of computing technology and the improvement of the cloud environment, deep learning technology has developed, and attempts to apply deep learning to various fields are increasing. A typical example is anomaly detection, which is a technique for identifying values or patterns that deviate from normal data. Among the representative types of anomaly detection, it is very difficult to detect a contextual anomaly that requires understanding of the overall situation. In general, detection of anomalies in image data is performed using a pre-trained model trained on large data. However, since this pre-trained model was created by focusing on object classification of images, there is a limit to be applied to anomaly detection that needs to understand complex situations created by various objects. Therefore, in this study, we newly propose a two-step pre-trained model for detecting abnormal situation. Our methodology performs additional learning from image captioning to understand not only mere objects but also the complicated situation created by them. Specifically, the proposed methodology transfers knowledge of the pre-trained model that has learned object classification with ImageNet data to the image captioning model, and uses the caption that describes the situation represented by the image. Afterwards, the weight obtained by learning the situational characteristics through images and captions is extracted and fine-tuning is performed to generate an anomaly detection model. To evaluate the performance of the proposed methodology, an anomaly detection experiment was performed on 400 situational images and the experimental results showed that the proposed methodology was superior in terms of anomaly detection accuracy and F1-score compared to the existing traditional pre-trained model.

• Journal of Korean Society for Quality Management
• /
• v.47 no.4
• /
• pp.783-793
• /
• 2019

Purpose: The purpose of this study is to apply the machine and deep learning methodology on error terms which are continuously auto-generated on the sensors with specific time period and prove the improvement effects of power generator prediction diagnosis system by comparing detection ability. Methods: The SVM(Support Vector Machine) and MLP(Multi Layer Perception) learning procedures were applied for predicting the target values and sequentially producing the error terms for confirming the detection improvement effects of suggested application. For checking the effectiveness of suggested procedures, several detection methodologies such as Cusum and EWMA were used for the comparison. Results: The statistical analysis result shows that without noticing the sequential trivial changes on current diagnosis system, suggested approach based on the error term diagnosis is sensing the changes in the very early stages. Conclusion: Using pattern of error terms as a diagnosis tool for the safety control process with SVM and MLP learning procedure, unusual symptoms could be detected earlier than current prediction system. By combining the suggested error term management methodology with current process seems to be meaningful for sustainable safety condition by early detecting the symptoms.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.11
• /
• pp.94-101
• /
• 2020

In the age of industry 4.0, artificial intelligence is being widely used to realize machinery condition monitoring. Due to their excellent performance and the ability to handle large volumes of data, machine learning techniques have been applied to realize the fault diagnosis of different equipment. In this study, we performed the failure mode effect analysis (FMEA) of an aluminum electrolytic capacitor by using deep learning and big data. Several tests were performed to identify the main failure mode of the aluminum electrolytic capacitor, and it was noted that the capacitance reduced significantly over time due to overheating. To reflect the capacitance degradation behavior over time, we employed the Vanilla long short-term memory (LSTM) neural network architecture. The LSTM neural network has been demonstrated to achieve excellent long-term predictions. The prediction results and metrics of the LSTM and Vanilla LSTM models were examined and compared. The Vanilla LSTM outperformed the conventional LSTM in terms of the computational resources and time required to predict the capacitance degradation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.792-812
• /
• 2022

Multi-agent systems often need to achieve the goal of learning more effectively for a task through coordination. Although the introduction of deep learning has addressed the state space problems, multi-agent learning remains infeasible because of the joint action spaces. Large-scale joint action spaces can be sparse according to implicit or explicit coordination structure, which can ensure reasonable coordination action through the coordination structure. In general, the multi-agent system is dynamic, which makes the relations among agents and the coordination structure are dynamic. Therefore, the explicit coordination structure can better represent the coordinative relationship among agents and achieve better coordination between agents. Inspired by the maximization of social group utility, we dynamically construct a factor graph as an explicit coordination structure to express the coordinative relationship according to the utility among agents and estimate the joint action values based on the local utility transfer among factor graphs. We present the application of such techniques in the scenario of multiple intelligent vehicle systems, where state space and action space are a problem and have too many interactions among agents. The results on the multiple intelligent vehicle systems demonstrate the efficiency and effectiveness of our proposed methods.

• KIPS Transactions on Computer and Communication Systems
• /
• v.7 no.1
• /
• pp.1-8
• /
• 2018

It is not easy to learn simple expressions of moving picture data since it contains noise and a lot of information in addition to time-based information. In this study, we propose a similarity representation method and a deep learning method between sequential data which can express such video data abstractly and simpler. This is to learn and obtain a function that allow them to have maximum information when interpreting the degree of similarity between image data vectors constituting a moving picture. Through the actual data, it is confirmed that the proposed method shows better classification performance than the existing moving image classification methods.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.301-307
• /
• 2022

Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.

• Nuclear Engineering and Technology
• /
• v.53 no.7
• /
• pp.2229-2236
• /
• 2021

In nuclear-related facilities, such as nuclear power plants, research reactors, accelerators, and nuclear waste storage sites, radiation detection, and mapping are required to prevent radiation overexposure. Sensor network systems consisting of radiation sensor interfaces and wxireless communication units have become promising tools that can be used for data collection of radiation detection that can in turn be used to draw a radiation map. During data collection, malfunctions in some of the sensors can occasionally occur due to radiation effects, physical damage, network defects, sensor loss, or other reasons. This paper proposes a reproduction strategy for radiation maps using a U-net model to compensate for the loss of radiation detection data. To perform machine learning and verification, 1,561 simulations and 417 measured data of a sensor network were performed. The reproduction results show an accuracy of over 90%. The proposed strategy can offer an effective method that can be used to resolve the data loss problem for conventional sensor network systems and will specifically contribute to making initial responses with preserved data and without the high cost of radiation leak accidents at nuclear facilities.

• Journal of information and communication convergence engineering
• /
• v.20 no.4
• /
• pp.288-294
• /
• 2022

The media content market has been growing, as various types of content are being mass-produced owing to the recent proliferation of the Internet and digital media. In addition, platforms that provide personalized services for content consumption are emerging and competing with each other to recommend personalized content. Existing platforms use a method in which a user directly inputs video metadata. Consequently, significant amounts of time and cost are consumed in processing large amounts of data. In this study, keyframes and audio spectra based on the YCbCr color model of a movie trailer were extracted for the automatic generation of metadata. The extracted audio spectra and image keyframes were used as learning data for genre recognition in deep learning. Deep learning was implemented to determine genres among the video metadata, and suggestions for utilization were proposed. A system that can automatically generate metadata established through the results of this study will be helpful for studying recommendation systems for media super-personalization.