• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2310-2332
• /
• 2020

In recent years, deep learning techniques have achieved tremendous successes in natural language processing, speech recognition and image processing. Collaborative filtering(CF) recommendation is one of widely used methods and has significant effects in implementing the new recommendation function, but it also has limitations in dealing with the problem of poor scalability, cold start and data sparsity, etc. Combining the traditional recommendation algorithm with the deep learning model has brought great opportunity for the construction of a new recommender system. In this paper, we propose a novel collaborative recommendation model based on auxiliary stacked denoising autoencoder(ASDAE), the model learns effective the preferences of users from auxiliary information. Firstly, we integrate auxiliary information with rating information. Then, we design a stacked denoising autoencoder based collaborative recommendation model to learn the preferences of users from auxiliary information and rating information. Finally, we conduct comprehensive experiments on three real datasets to compare our proposed model with state-of-the-art methods. Experimental results demonstrate that our proposed model is superior to other recommendation methods.

• Journal of information and communication convergence engineering
• /
• v.18 no.1
• /
• pp.28-32
• /
• 2020

Railway transportation is the main land-based transportation in most countries. Accordingly, railway-transportation safety has always been a key issue for many researchers. Railway pedestrian accidents are the main reasons of railway-transportation casualties. In this study, we conduct experiments to determine which of the latest convolutional neural network models and algorithms are appropriate to build pedestrian railroad accident prevention systems. When a drone cruises over a pre-specified path and altitude, the real-time status around the rail is recorded, following which the image information is transmitted back to the server in time. Subsequently, the images are analyzed to determine whether pedestrians are present around the railroads, and a speed-deceleration order is immediately sent to the train driver, resulting in a reduction of the instances of pedestrian railroad accidents. This is the first part of an envisioned drone-based intelligent security system. This system can effectively address the problem of insufficient manual police force.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.07a
• /
• pp.19-22
• /
• 2015

주차는 자동차를 이용하는 사람들의 편리한 이동을 위한 기반 행위에 포함되는 요소이다. 따라서 이러한 주차 문제를 해결하는 다양한 서비스가 존재하나, 이러한 서비스를 제공하는 시스템을 개발하기 위해서는 주차공간의 특성을 고려해야 하는 어려움이 있다. 본 연구에서는 카메라 모듈과 딥러닝 알고리즘을 기반으로 하는 이미지 센싱을 활용하여 기존 시스템의 주차 감지 센서부 구축의 문제점을 개선하며, 주차장 수요가 많은 '러쉬 타임'을 반영하여 주차공간을 안내하고 운전자를 유도하는 주차정보시스템을 개발한다.

• Journal of Korea Multimedia Society
• /
• v.24 no.7
• /
• pp.860-867
• /
• 2021

Lane detection is important technology for implementing ADAS or autonomous driving. Although edge detection has been typically used for the lane detection however, false detections occur frequently. To improve this problem, a deep learning based lane detection algorithm is proposed in this paper. This algorithm is mounted on an ARM-based embedded system to implement a LDW(lane departure warning). Since the embedded environment lacks computing power, the VGG-11, a lightweight model based on VGG-13, has been proposed. In order to evaluate the performance of the LDW, the test was conducted according to the test scenario of NHTSA.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.406-409
• /
• 2023

With the explosion of information, recommendation algorithms are becoming increasingly important in providing people with appropriate content, enhancing their online experience. In this paper, we propose a recommender system using advanced deep reinforcement learning(DRL) techniques. This method is more adaptive and integrative than traditional methods. We selected the MovieLens dataset and employed the precision metric to assess the effectiveness of our algorithm. The result of our implementation outperforms other baseline techniques, delivering better results for Top-N item recommendations.

• Journal of Sensor Science and Technology
• /
• v.33 no.5
• /
• pp.248-254
• /
• 2024

Artificial intelligence techniques have improved fire-detection methods; however, false alarms still occur. Conventional methods detect fires using current sensors, which can lead to detection errors due to temporary environmental changes or noise. Thus, fire-detection methods must include a trend analysis of past information. We propose a deep-learning-based fire detection method using multi-sensor data and Kendall's tau. The proposed system used a BiLSTM model to predict fires using pre-processed multi-sensor data and extracted trend information. Kendall's tau indicates the trend of a time-series data as a score; therefore, it is easy to obtain a target pattern. The experimental results showed that the proposed system with trend values recorded an accuracy of 99.93% for BiLSTM and GRU models in a 20-tap moving average filter and 40% fire threshold. Thus, the proposed trend approach is more accurate than that of conventional approaches.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.373-380
• /
• 2022

This paper presents a deep learning based group synchronization that supports networked immersive interactions between remote users. The goal of group synchronization is to enable all participants to synchronously interact with others for increasing user presence Most previous methods focus on NTP-based clock synchronization to enhance time accuracy. Moving average filters are used to control media playout time on the synchronization server. As an example, the exponentially weighted moving average(EWMA) would be able to track and estimate accurate playout time if the changes in input data are not significant. However it needs more time to be stable for any given change over time due to codec and system loads or fluctuations in network status. To tackle this problem, this work proposes the Deep Group Synchronization(DeepGroupSync), a group synchronization based on deep learning that models important features from the data. This model consists of two Gated Recurrent Unit(GRU) layers and one fully-connected layer, which predicts an optimal playout time by utilizing the sequential playout delays. The experiments are conducted with an existing method that uses the EWMA and the proposed method that uses the DeepGroupSync. The results show that the proposed method are more robust against unpredictable or rapid network condition changes than the existing method.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1421-1429
• /
• 2017

Human activity recognition has been studied using various sensors and algorithms. Human activity recognition can be divided into sensor based and vision based on the method. In this paper, we proposed an activity recognition system using acceleration sensor and gyroscope sensor in smartphone among sensor based methods. We used Deep Belief Network (DBN), which is one of the most popular deep learning methods, to improve an accuracy of human activity recognition. DBN uses the entire input set as a common input. However, because of the characteristics of different time window depending on the type of human activity, the RBMs, which is a component of DBN, are configured hierarchically by combining them from different time windows. As a result of applying to real data, The proposed human activity recognition system showed stable precision.

• Korean Journal of Construction Engineering and Management
• /
• v.20 no.2
• /
• pp.3-12
• /
• 2019

Despite the importance and function of productivity information, in the Korean construction industry, the method of collecting and analyzing productivity data has not been organized. Also, in most cases, productivity management is reliant on the experience and intuitions of field managers, and productivity data are rarely being utilized in planning and management. Accordingly, this study intends to develop a prediction model for interior finishes of apartment using deep learning techniques, so as to provide a foundation for analyzing the productivity impacting factors and predicting productivity. The result of the study, productivity prediction model for interior finishes of apartment using deep learning techniques, can be a basic module of apartment project management system by applying deep learning to reliable productivity data and developing as data is accumulated in the future. It can also be used in project engineering processes such as estimating work, calculating work days for process planning, and calculating input labor based on productivity data from similar projects in the past. Further, when productivity diverging from predicted productivity is discovered during construction, it is expected that it will be possible to analyze the cause(s) thereof and implement prompt response and preventive measures.

• Journal of Korea Water Resources Association
• /
• v.54 no.5
• /
• pp.301-309
• /
• 2021

In this study, we tried to improve the performance of the existing U-net-based deep learning rainfall prediction model, which can weaken the meaning of time series order. For this, ConvLSTM2D U-Net structure model considering temporal consistency of data was applied, and we evaluated accuracy of the ConvLSTM2D U-Net model using a RainNet model and an extrapolation-based advection model. In addition, we tried to improve the uncertainty in the model training process by performing learning not only with a single model but also with 10 ensemble models. The trained neural network rainfall prediction model was optimized to generate 10-minute advance prediction data using four consecutive data of the past 30 minutes from the present. The results of deep learning rainfall prediction models are difficult to identify schematically distinct differences, but with ConvLSTM2D U-Net, the magnitude of the prediction error is the smallest and the location of rainfall is relatively accurate. In particular, the ensemble ConvLSTM2D U-Net showed high CSI, low MAE, and a narrow error range, and predicted rainfall more accurately and stable prediction performance than other models. However, the prediction performance for a specific point was very low compared to the prediction performance for the entire area, and the deep learning rainfall prediction model also had limitations. Through this study, it was confirmed that the ConvLSTM2D U-Net neural network structure to account for the change of time could increase the prediction accuracy, but there is still a limitation of the convolution deep neural network model due to spatial smoothing in the strong rainfall region or detailed rainfall prediction.