• Korean Journal of Optics and Photonics
• /
• v.30 no.3
• /
• pp.114-119
• /
• 2019

This paper discusses the development of a Raman lidar system for remote detection and measurement of hydrogen gas by using a photon counter. The Raman signal of the hydrogen gas is very weak and has a very low signal-to-noise ratio. The photon counter has the advantage of improving the signal-to-noise ratio, because it has a discriminator to eliminate the background noise from the Raman signal of the hydrogen gas. Therefore, a small and portable Raman lidar system was developed using a low-power pulsed laser and a photon-counter system to measure the hydrogen gas concentration remotely. To verify the capability of measuring hydrogen gas using the developed photon-counting Raman lidar system, experiments were carried out using a gas chamber in which it is possible to adjust the hydrogen gas concentration. As a result, our photon-counting Raman lidar system is seen to measure a minimum concentration of 0.65 vol.% hydrogen gas at a distance of 10 m.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3708-3728
• /
• 2021

Indian herbal plants are used in agriculture and in the food, cosmetics, and pharmaceutical industries. Laboratory-based tests are routinely used to identify and classify similar herb species by analyzing their internal cell structures. In this paper, we have applied computer vision techniques to do the same. The original leaf image was preprocessed using the Chan-Vese active contour segmentation algorithm to efface the background from the image by setting the contraction bias as (v) -1 and smoothing factor (µ) as 0.5, and bringing the initial contour close to the image boundary. Thereafter the segmented grayscale image was fed to a leaky capacitance fired neuron model (LCFN), which differentiates between similar herbs by combining different groups of pixels in the leaf image. The LFCN's decay constant (f), decay constant (g) and threshold (h) parameters were empirically assigned as 0.7, 0.6 and h=18 to generate the 1D feature vector. The LCFN time sequence identified the internal leaf structure at different iterations. Our proposed framework was tested against newly collected herbal species of natural images, geometrically variant images in terms of size, orientation and position. The 1D sequence and shape features of aloe, betel, Indian borage, bittergourd, grape, insulin herb, guava, mango, nilavembu, nithiyakalyani, sweet basil and pomegranate were fed into the 5-fold Bayesian regularization neural network (BRNN), K-nearest neighbors (KNN), support vector machine (SVM), and ensemble classifier to obtain the highest classification accuracy of 91.19%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.12 no.5
• /
• pp.15-25
• /
• 2002

In this paper a design of high performance cryptographic processor which implements AES Rijndael algorithm is described. To eliminate performance degradation due to round-key computation delay of conventional processor, the on-the-fly precomputation of round key based on modified round structure is adopted. And on-the-fly round key generator which supports 128, 192, and 256-bit key has modular structure. The designed processor has iterative structure which uses 1 clock cycle per round and supports three operation modes, such as ECB, CBC, and CTR mode which is a candidate for new AES modes of operation. The cryptographic processor designed in Verilog-HDL and synthesized using 0.251$\mu\textrm{m}$ CMOS cell library consists of about 51,000 gates. Simulation results show that the critical path delay is about 7.5ns and it can operate up to 125Mhz clock frequency at 2.5V supply. Its peak performance is about 1.45Gbps encryption or decryption rate under 128-bit key ECB mode.

• Journal of The Korean Society of Integrative Medicine
• /
• v.8 no.4
• /
• pp.125-131
• /
• 2020

Purpose : Lower extremity orthoses have been used as conservative methods to recover gait of the stroke patients. The purpose of this study is to examine how newly designed pelvic belt orthosis can improve gait ability and dynamic balance of adults with Hemiparesis after stroke. Methods : 22 patients who had hemiparesis after stroke participated in this study. Two groups were randomly created by assigning 10 subjects to the experimental group and the rest of the 12 subjects to the control group. The control group was treated by conventional physical therapy and occupational therapy. Identical therapy protocols were used to treat the experimental group who were assigned to wear the pelvic belt orthosis during post measurement. This study has a group of independent variables including group, gender, age, height, MAS, lesion side, cause and a group of dependent variables including gait speed, cadence, step length, stride length, and dynamic balance. The GAITRite system was used to measure spatial-temporal gain parameters and the balance system SD to measure dynamic balance. The data was analyzed using R version 3.3.1. Random forest, boosting algorithm, and MANOVA test were conducted to determine the effects of independent variables on dependent variables. Results : This study has a group of independent variables including group, gender, age, height, MAS, lesion side, cause and a group of dependent variables including gait speed, cadence, step length, stride length, and dynamic balance. The independent variable "group" has the most important value, which is approximately 25.42 (%IncMSE) representing a value three times greater than the second important predictor "height." Conclusion : As a result of this research, the hypothesis is validated with conclusion that Pelvic Belt orthosis could be effectively used for improving gait ability and balance of the patients with post-stroke hemiparesis.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1567-1577
• /
• 2020

Urban land cover classification is role in urban planning and management. So, it's important to improve classification accuracy on urban location. In this paper, machine learning model, Support Vector Machine (SVM) and Artificial Neural Network (ANN) are proposed for urban land cover classification based on high resolution satellite imagery (KOMPSAT-3A). Satellite image was trained based on 25 m rectangle grid to create training data, and training models used for classifying test area. During the validation process, we presented confusion matrix for each result with 250 Ground Truth Points (GTP). Of the four SVM kernels and the two activation functions ANN, the SVM Polynomial kernel model had the highest accuracy of 86%. In the process of comparing the SVM and ANN using GTP, the SVM model was more effective than the ANN model for KOMPSAT-3A classification. Among the four classes (building, road, vegetation, and bare-soil), building class showed the lowest classification accuracy due to the shadow caused by the high rise building.

• Structural Engineering and Mechanics
• /
• v.81 no.3
• /
• pp.293-303
• /
• 2022

As infrastructure ages and traffic load increases, serious public concerns have arisen for the well-being of bridges. The current health monitoring practice focuses on large-scale bridges rather than short span bridges. However, it is critical that more attention should be given to these behind-the-scene bridges. The relevant information about the construction methods and as-built properties are most likely missing. Additionally, since the condition of a bridge has unavoidably changed during service, due to weathering and deterioration, the material properties and boundary conditions would also have changed since its construction. Therefore, it is not appropriate to continue using the design values of the bridge parameters when undertaking any analysis to evaluate bridge performance. It is imperative to update the model, using finite element (FE) analysis to reflect the current structural condition. In this study, a FE model is established to simulate a concrete culvert bridge in New South Wales, Australia. That model, however, contains a number of parameter uncertainties that would compromise the accuracy of analytical results. The model is therefore updated with a neural network (NN) optimisation algorithm incorporating Monte Carlo (MC) simulation to minimise the uncertainties in parameters. The modal frequency and strain responses produced by the updated FE model are compared with the frequency and strain values on-site measured by sensors. The outcome indicates that the NN model updating incorporating MC simulation is a feasible and robust optimisation method for updating numerical models so as to minimise the difference between numerical models and their real-world counterparts.

• Composite Materials and Engineering
• /
• v.3 no.3
• /
• pp.201-220
• /
• 2021

In this study, potential of three machine learning techniques i.e., M5P, Support vector machines and Gaussian processes were evaluated to find the best algorithm for the prediction of flexural strength of concrete mix with steel fibre. The study comprises the comparison of results obtained from above-said techniques for given dataset. The dataset consists of 124 observations from past research studies and this dataset is randomly divided into two subsets namely training and testing datasets with (70-30)% proportion by weight. Cement, fine aggregates, coarse aggregates, water, super plasticizer/ high-range water reducer, steel fibre, fibre length and curing days were taken as input parameters whereas flexural strength of the concrete mix was taken as the output parameter. Performance of the techniques was checked by statistic evaluation parameters. Results show that the Gaussian process technique works better than other techniques with its minimum error bandwidth. Statistical analysis shows that the Gaussian process predicts better results with higher coefficient of correlation value (0.9138) and minimum mean absolute error (1.2954) and Root mean square error value (1.9672). Sensitivity analysis proves that steel fibre is the significant parameter among other parameters to predict the flexural strength of concrete mix. According to the shape of the fibre, the mixed type performs better for this data than the hooked shape of the steel fibre, which has a higher CC of 0.9649, which shows that the shape of fibers do effect the flexural strength of the concrete. However, the intricacy of the mixed fibres needs further investigations. For future mixes, the most favorable range for the increase in flexural strength of concrete mix found to be (1-3)%.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.21-32
• /
• 2022

Image labeling must be preceded in order to perform object detection, and this task is considered a significant burden in building a deep learning model. Tens of thousands of images need to be trained for building a deep learning model, and human labelers have many limitations in labeling these images manually. In order to overcome these difficulties, this study proposes a method to perform object detection without significant performance degradation, even though labeling some images rather than the entire image. Specifically, in this study, low-resolution oriental painting images are converted into high-quality images using a super-resolution algorithm, and the effect of SSIM and PSNR derived in this process on the mAP of object detection is analyzed. We expect that the results of this study can contribute significantly to constructing deep learning models such as image classification, object detection, and image segmentation that require efficient image labeling.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.77-84
• /
• 2022

In this paper, we propose a Label Reassignment Strategy to improve the performance of an object detection algorithm. Our approach involves two stages: an inference stage and an assignment stage. In the inference stage, we perform multi-scale inference with predefined scale sizes on a trained model and re-infer masked images to obtain robust classification results. In the assignment stage, we calculate the IoU between bounding boxes to remove duplicates. We also check box and class occurrence between the detection result and annotation label to re-assign the dominant class type. We trained the YOLOX-L model with the re-annotated dataset to validate our strategy. The model achieved a 3.9% improvement in mAP and 3x better performance on AP_S compared to the model trained with the original dataset. Our results demonstrate that the proposed Label Reassignment Strategy can effectively improve the performance of an object detection model.