• Smart Structures and Systems
• /
• v.29 no.6
• /
• pp.777-783
• /
• 2022

Even though several deep learning-based methods have been applied in the field of acoustic source localization, the previous works have only been conducted using the two-dimensional representation of the beamforming maps, particularly with the planar array system. While the acoustic sources are more required to be localized in a spherical microphone array system considering that we live and hear in the 3D world, the conventional 2D equirectangular map of the spherical beamforming map is highly vulnerable to the distortion that occurs when the 3D map is projected to the 2D space. In this study, a 3D deep learning approach is proposed to fulfill accurate source localization via distortion-free 3D representation. A target function is first proposed to obtain 3D source distribution maps that can represent multiple sources' positional and strength information. While the proposed target map expands the source localization task into a point-wise prediction task, a PointNet-based deep neural network is developed to precisely estimate the multiple sources' positions and strength information. While the proposed model's localization performance is evaluated, it is shown that the proposed method can achieve improved localization results from both quantitative and qualitative perspectives.

• International Journal of Contents
• /
• v.17 no.4
• /
• pp.1-15
• /
• 2021

Named entity recognition (NER) is a crucial task for NLP, which aims to extract information from texts. To build NER systems, deep learning (DL) models are learned with dictionary features by mapping each word in the dataset to dictionary features and generating a unique index. However, this technique might generate noisy labels, which pose significant challenges for the NER task. In this paper, we proposed DL-dictionary features, and evaluated them on two datasets, including the OntoNotes 5.0 dataset and our new infectious disease outbreak dataset named GFID. We used (1) a Bidirectional Long Short-Term Memory (BiLSTM) character and (2) pre-trained embedding to concatenate with (3) our proposed features, named the Convolutional Neural Network (CNN), BiLSTM, and self-attention dictionaries, respectively. The combined features (1-3) were fed through BiLSTM - Conditional Random Field (CRF) to predict named entity classes as outputs. We compared these outputs with other predictions of the BiLSTM character, pre-trained embedding, and dictionary features from previous research, which used the exact matching and partial matching dictionary technique. The findings showed that the model employing our dictionary features outperformed other models that used existing dictionary features. We also computed the F1 score with the GFID dataset to apply this technique to extract medical or healthcare information.

• Journal of Software Assessment and Valuation
• /
• v.16 no.2
• /
• pp.63-68
• /
• 2020

This paper proposes a face authentication system based on deep learning framework. The proposed system is consisted of face region detection and feature extraction using deep learning algorithm, and performed the face authentication using joint-bayesian matrix learning algorithm. The performance of proposed paper is evaluated by various face database , and the face image of one person consists of 2 images. The face authentication algorithm was performed by measuring similarity by applying 2048 dimension characteristic and combined Bayesian algorithm through Deep Neural network and calculating the same error rate that failed face certification. The result of proposed paper shows that the proposed system using deep learning and joint bayesian algorithms showed the equal error rate of 1.2%, and have a good performance compared to previous approach.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.141-151
• /
• 2022

In recent years, the industry and research communities have focused on developing autonomous crack inspection approaches, which mainly include image acquisition and crack detection. In these approaches, mobile devices such as cameras, drones or smartphones are utilized as sensing platforms to acquire structural images, and the deep learning (DL)-based methods are being developed as important crack detection approaches. However, the process of image acquisition and collection is time-consuming, which delays the inspection. Also, the present mobile devices such as smartphones can be not only a sensing platform but also a computing platform that can be embedded with deep neural networks (DNNs) to conduct on-site crack detection. Due to the limited computing resources of mobile devices, the size of the DNNs should be reduced to improve the computational efficiency. In this study, an architecture called pruned crack recognition network (PCR-Net) was developed for the detection of structural cracks. A dataset containing 11000 images was established based on the raw images from bridge inspections. A pruning method was introduced to reduce the size of the base architecture for the optimization of the model size. Comparative studies were conducted with image processing techniques (IPTs) and other DNNs for the evaluation of the performance of the proposed PCR-Net. Furthermore, a modularly designed framework that integrated the PCR-Net was developed to realize a DL-based crack detection application for smartphones. Finally, on-site crack detection experiments were carried out to validate the performance of the developed system of smartphone-based detection of structural cracks.

• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.257-268
• /
• 2022

When there is a missing value in the raw data, if ignore the missing values and proceed with the analysis, the accuracy decrease due to the decrease in the number of sample. The method of imputation and analyzing patterns and significant values can compensate for the problem of lower analysis quality and analysis accuracy as a result of bias rather than simply removing missing values. In this study, we proposed to study irregular data patterns and missing processing methods of data using machine learning techniques for the study of correction of missing values. we would like to propose a plan to replace the missing with data from a similar past point in time by finding the situation at the time when the missing data occurred. Unlike previous studies, data correction techniques present new algorithms using DNN and KNN-MLE techniques. As a result of the performance evaluation, the ANAE measurement value compared to the existing missing section correction algorithm confirmed a performance improvement of about 0.041 to 0.321.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2627-2647
• /
• 2022

The easy scalability and low cost of range-free localization algorithms have led to their wide attention and application in node localization of wireless sensor networks. However, the existing range-free localization algorithms still have problems, such as large cumulative errors and poor localization performance. To solve these problems, an incremental strategy-based residual regression network is proposed for node localization in wireless sensor networks. The algorithm predicts the coordinates of the nodes to be solved by building a deep learning model and fine-tunes the prediction results by regression based on the intersection of the communication range between the predicted and real coordinates and the loss function, which improves the localization performance of the algorithm. Moreover, a correction scheme is proposed to correct the augmented data in the incremental strategy, which reduces the cumulative error generated during the algorithm localization. The analysis through simulation experiments demonstrates that our proposed algorithm has strong robustness and has obvious advantages in localization performance compared with other algorithms.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.719-728
• /
• 2022

The prediction of short-term traffic flow is the theoretical basis of intelligent transportation as well as the key technology in traffic flow induction systems. The research on short-term traffic flow prediction has showed the considerable social value. At present, the support vector regression (SVR) intelligent prediction model that is suitable for small samples has been applied in this domain. Aiming at parameter selection difficulty and prediction accuracy improvement, the artificial bee colony (ABC) is adopted in optimizing SVR parameters, which is referred to as the ABC-SVR algorithm in the paper. The simulation experiments are carried out by comparing the ABC-SVR algorithm with SVR algorithm, and the feasibility of the proposed ABC-SVR algorithm is verified by result analysis. Continuously, the simulation experiments are carried out by comparing the ABC-SVR algorithm with particle swarm optimization SVR (PSO-SVR) algorithm and genetic optimization SVR (GA-SVR) algorithm, and a better optimization effect has been attained by simulation experiments and verified by statistical test. Simultaneously, the simulation experiments are carried out by comparing the ABC-SVR algorithm and wavelet neural network time series (WNN-TS) algorithm, and the prediction accuracy of the proposed ABC-SVR algorithm is improved and satisfactory prediction effects have been obtained.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.383-392
• /
• 2023

Post-earthquake building condition assessment is crucial for subsequent rescue and remediation and can be automated by emerging computer vision and deep learning technologies. This study is based on an endeavour for the 2nd International Competition of Structural Health Monitoring (IC-SHM 2021). The task package includes five image segmentation objectives - defects (crack/spall/rebar exposure), structural component, and damage state. The structural component and damage state tasks are identified as the priority that can form actionable decisions. A multi-task Convolutional Neural Network (CNN) is proposed to conduct the two major tasks simultaneously. The rest 3 sub-tasks (spall/crack/rebar exposure) were incorporated as auxiliary tasks. By synchronously learning defect information (spall/crack/rebar exposure), the multi-task CNN model outperforms the counterpart single-task models in recognizing structural components and estimating damage states. Particularly, the pixel-level damage state estimation witnesses a mIoU (mean intersection over union) improvement from 0.5855 to 0.6374. For the defect detection tasks, rebar exposure is omitted due to the extremely biased sample distribution. The segmentations of crack and spall are automated by single-task U-Net but with extra efforts to resample the provided data. The segmentation of small objects (spall and crack) benefits from the resampling method, with a substantial IoU increment of nearly 10%.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.133-139
• /
• 2023

This paper proposes a two-stage Water Shield Automation System (WSAS) to predict the possibility of river overflow and vehicle flooding due to sudden rainfall. The WSAS uses a two-stage Deep Neural Network (DNN) model. First, a river overflow prediction module is designed with LSTM to decide whether the river is flooded by predicting the river's water level rise. Second, a vehicle flooding prediction module predicts flooding of underground parking lots by detecting flooded tires with YOLOv5 from CCTV images. Finally, the WSAS automatically installs the water barrier whenever the river overflow and vehicle flooding events happen in the underground parking lots. The only constraint to implementing is that collecting training data for flooded vehicle tires is challenging. This paper exploits the Image C&S data augmentation technique to synthesize flooded tire images. Experimental results validate the superiority of WSAS by showing that the river overflow prediction module can reduce RMSE by three times compared with the previous method, and the vehicle flooding detection module can increase mAP by 20% compared with the naive detection method, respectively.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.513-513
• /
• 2023

최근 이상기후의 영향으로 국지성 및 집중호우로 인한 침수 피해가 증가하고 있다. 도시유역의 홍수는 사회적·경제적으로 큰 손실을 야기할 수 있어 실제 호우에 대한 침수 양상을 신속하게 예측하는것은 매우 중요하다. 이로 인해 침수 해석에 대한 결과를 빨리 제공할 수 있는 기계학습을 기반으로 한 도시 홍수 분석에 대한 연구가 증가하고 있다. 본 연구에서 적용한 LSTM(Long Short-Term Memory) 신경망은 기존 RNN(Recurrent neural network)이 가지고 있는 장기 의존성 문제를 해결하기 위해 고안된 모델으로 시계열 데이터에 대한 예측능력이 뛰어나다는 장점을 가지고있다. LSTM 신경망은 강우에 대한 격자별 침수심을 예측하기 위해 사용되었으며, 입력자료로 2000~2022년도에 걸친 도림천 유역의 침수피해를 야기한 지속시간 6시간 AWS(Automatic Weather System) 관측 강우 자료를 사용하였고 목표값으로 수집된 도림천 유역의 강우자료를 이용하여 SWMM(Storm Water Management Model)의 유출 결과를 바탕으로 수행된 2차원 침수해석 모의 결과를 사용하였다. 연구유역의 SWMM 배수 관망 입력자료의 정확성을 높이기 위해 서울시 하수관로 수위 현황 자료를 활용하여 매개변수 조정을 실시하였으며, 하수관로의 실측 수위와 모의 수위를 일치시켰다. LSTM 신경망을 이용하여 격자별로 예측된 침수심 데이터를 시각화하여 침수흔적도와 비교하였다.