• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1330-1339
• /
• 2022

3D object detection generally aims to detect relatively large data such as automobiles, buses, persons, furniture, etc, so it is vulnerable to small object detection. In addition, in an environment with limited resources such as embedded devices, it is difficult to apply the model because of the huge amount of computation. In this paper, the accuracy of small object detection was improved by focusing on local features using only one layer, and the inference speed was improved through the proposed knowledge distillation method from large pre-trained network to small network and adaptive quantization method according to the parameter size. The proposed model was evaluated using SUN RGB-D Val and self-made apple tree data set. Finally, it achieved the accuracy performance of 62.04% at mAP@0.25 and 47.1% at mAP@0.5, and the inference speed was 120.5 scenes per sec, showing a fast real-time processing speed.

• Geomechanics and Engineering
• /
• v.30 no.5
• /
• pp.401-411
• /
• 2022

To obtain the dynamic mechanical properties, fracture modes, energy and brittleness characteristics of Furong Baijiao coal rock, the dynamic impact compression tests under 0, 4, 8 and 12 MPa confining pressure were carried out using the split Hopkinson pressure bar. The results show that failure mode of coal rock in uniaxial state is axial splitting failure, while it is mainly compression-shear failure with tensile failure in triaxial state. With strain rate and confining pressure increasing, compressive strength and peak strain increase, average fragmentation increases and fractal dimension decreases. Based on energy dissipation theory, the dissipated energy density of coal rock increases gradually with growing confining pressure, but it has little correlation with strain rate. Considering progressive destruction process of coal rock, damage variable was defined as the ratio of dissipated energy density to total absorbed energy density. The maximum damage rate was obtained by deriving damage variable to reflect its maximum failure severity, then a brittleness index BD was established based on the maximum damage rate. BD value declined gradually as confining pressure and strain rate increase, indicating the decrease of brittleness and destruction degree. When confining pressure rises to 12 MPa, brittleness index and average fragmentation gradually stabilize, which shows confining pressure growing cannot cause continuous damage. Finally, integrating dynamic deformation and destruction process of coal rock and according to its final failure characteristics under different confining pressures, BD value is used to classify the brittleness into four grades.

• Journal of the Korean Society for information Management
• /
• v.39 no.3
• /
• pp.293-310
• /
• 2022

In this study, we analyzed the performance of the BERT-based document classification model by automatically classifying documents in the field of library and information science based on the KoBERT. For this purpose, abstract data of 5,357 papers in 7 journals in the field of library and information science were analyzed and evaluated for any difference in the performance of automatic classification according to the size of the learned data. As performance evaluation scales, precision, recall, and F scale were used. As a result of the evaluation, subject areas with large amounts of data and high quality showed a high level of performance with an F scale of 90% or more. On the other hand, if the data quality was low, the similarity with other subject areas was high, and there were few features that were clearly distinguished thematically, a meaningful high-level performance evaluation could not be derived. This study is expected to be used as basic data to suggest the possibility of using a pre-trained learning model to automatically classify the academic documents.

• Journal of Broadcast Engineering
• /
• v.28 no.1
• /
• pp.124-131
• /
• 2023

Object detection techniques are increasingly used to obtain information on physical characteristics or situations of a specific area from remote images. The accuracy of object detection is decreased in remote sensing images with low resolution because the low resolution reduces the amount of detail that can be captured in an image. A single neural network is proposed to joint the super-resolution method and object detection method. The proposed method constructs a deep residual-based network to restore object features in low-resolution images. Moreover, the proposed method is used to improve the performance of object detection by jointing a single network with YOLOv5. The proposed method is experimentally tested using VEDAI data for low-resolution images. The results show that vehicle detection performance improved by 81.38% on mAP@0.5 for VISIBLE data.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.83-90
• /
• 2023

Blurred image is an important factor in lowering image recognition rates in Computer vision. This mainly occurs when the camera is unstablely out of focus or the object in the scene moves quickly during the exposure time. Blurred images greatly degrade visual quality, weakening visibility, and this phenomenon occurs frequently despite the continuous development digital camera technology. In this paper, it replace the modified building module based on the Deep multi-patch neural network designed with convolution neural networks to capture details of input images and Attention techniques to focus on objects in blurred images in many ways and strengthen the image. It measures and assigns each weight at different scales to differentiate the blurring of change and restores from rough to fine levels of the image to adjust both global and local region sequentially. Through this method, it show excellent results that recover degraded image quality, extract efficient object detection and features, and complement color constancy.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.77-90
• /
• 2023

Today, crops face many characteristics/diseases. Insect damage is one of the main characteristics/diseases. Insecticides are not always effective because they can be toxic to some birds. It will also disrupt the natural food chain for animals. A common practice of plant scientists is to visually assess plant damage (leaves, stems) due to disease based on the percentage of disease. Plants suffer from various diseases at any stage of their development. For farmers and agricultural professionals, disease management is a critical issue that requires immediate attention. It requires urgent diagnosis and preventive measures to maintain quality and minimize losses. Many researchers have provided plant disease detection techniques to support rapid disease diagnosis. In this review paper, we mainly focus on artificial intelligence (AI) technology, image processing technology (IP), deep learning technology (DL), vector machine (SVM) technology, the network Convergent neuronal (CNN) content Detailed description of the identification of different types of diseases in tomato and potato plants based on image retrieval technology (CBIR). It also includes the various types of diseases that typically exist in tomato and potato. Content-based Image Retrieval (CBIR) technologies should be used as a supplementary tool to enhance search accuracy by encouraging you to access collections of extra knowledge so that it can be useful. CBIR systems mainly use colour, form, and texture as core features, such that they work on the first level of the lowest level. This is the most sophisticated methods used to diagnose diseases of tomato plants.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1431-1445
• /
• 2022

We construct a deep neural network model named ECGResNet. This model can diagnosis diseases based on 12-lead ECG data of eight common cardiovascular diseases with a high accuracy. We chose the 16 Blocks of ResNet50 as the main body of the model and added the Squeeze-and-Excitation module to learn the data information between channels adaptively. We modified the first convolutional layer of ResNet50 which has a convolutional kernel of 7 to a superposition of convolutional kernels of 8 and 16 as our feature extraction method. This way allows the model to focus on the overall trend of the ECG signal while also noticing subtle changes. The model further improves the accuracy of cardiovascular and cerebrovascular disease classification by using a fully connected layer that integrates factors such as gender and age. The ECGResNet model adds Dropout layers to both the residual block and SE module of ResNet50, further avoiding the phenomenon of model overfitting. The model was eventually trained using a five-fold cross-validation and Flooding training method, with an accuracy of 95% on the test set and an F1-score of 0.841.We design a new deep neural network, innovate a multi-scale feature extraction method, and apply the SE module to extract features of ECG data.

• Ocean Systems Engineering
• /
• v.12 no.1
• /
• pp.87-142
• /
• 2022

An analysis for the computation of Fatigue Damage Index (FDI) under the effects of the various combination of the ocean loads like random waves, current, platform motion and VIV (Vortex Induced Vibration) for a certain design water depth is a critically important part of the analysis and design of the marine riser platform integrated system. Herein, a 'Computer Simulation Model (CSM)' is developed to combine the advantages of the frequency domain and time domain. A case study considering a steel catenary riser operating in 1000 m water depth has been conducted with semi-submersible. The riser is subjected to extreme environmental conditions and static and dynamic response analyses are performed and the Response Amplitude Operators (RAOs) of the offshore platform are computed with the frequency domain solution. Later the frequency domain results are integrated with time domain analysis system for the dynamic analysis in time domain. After that an extensive post processing is done to compute the FDI of the marine riser. In the present paper importance is given to the nature of the current profile and the VIV. At the end we have reported the detail results of the FDI comparison with VIV and without VIV under the linear current velocity and the FDI comparison with linear and power law current velocity with and without VIV. We have also reported the design recommendations for the marine riser in the regions where the higher fatigue damage is observed and the proposed CSM is implemented in industrially used standard soft solution systems (i.e., OrcaFlex^*TM and Ansys AQWA^**TM), Ms-Excel^***TM, and C++ programming language using its object oriented features.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.41.2-41.2
• /
• 2021

In this study, we generate He I 1083 nm images from Solar Dynamic Observatory (SDO)/Atmospheric Imaging Assembly (AIA) images using a novel deep learning method (pix2pixHD) based on conditional Generative Adversarial Networks (cGAN). He I 1083 nm images from National Solar Observatory (NSO)/Synoptic Optical Long-term Investigations of the Sun (SOLIS) are used as target data. We make three models: single input SDO/AIA 19.3 nm image for Model I, single input 30.4 nm image for Model II, and double input (19.3 and 30.4 nm) images for Model III. We use data from 2010 October to 2015 July except for June and December for training and the remaining one for test. Major results of our study are as follows. First, the models successfully generate He I 1083 nm images with high correlations. Second, the model with two input images shows better results than those with one input image in terms of metrics such as correlation coefficient (CC) and root mean squared error (RMSE). CC and RMSE between real and AI-generated ones for the model III with 4 by 4 binnings are 0.84 and 11.80, respectively. Third, AI-generated images show well observational features such as active regions, filaments, and coronal holes. This work is meaningful in that our model can produce He I 1083 nm images with higher cadence without data gaps, which would be useful for studying the time evolution of chromosphere and coronal holes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1794-1799
• /
• 2022

Recently, the increasing number of overloaded vehicles on the road poses a risk to traffic safety, such as falling objects, road damage, and chain collisions due to the abnormal weight distribution, and can cause great damage once an accident occurs. therefore we propose to build an object detection-based AI model to identify overloaded vehicles that cause such social problems. In addition, we present a simple yet effective method to construct an object detection model for the large-scale vehicle images. In particular, we utilize the large-scale of vehicle image sets provided by open AI-Hub, which include the overloaded vehicles. We inspected the specific features of sizes of vehicles and types of image sources, and pre-processed these images to train a deep learning-based object detection model. Also, we propose an integrated system for tracking the detected vehicles. Finally, we demonstrated that the detection performance of the overloaded vehicle was improved by about 23% compared to the one using raw data.