• The Journal of the Korea Contents Association
• /
• v.19 no.1
• /
• pp.1-15
• /
• 2019

One of the biggest difficulties in the vocational training field is the dropout problem. A large number of students drop out during the training process, which hampers the waste of the state budget and the improvement of the youth employment rate. Previous studies have mainly analyzed the cause of dropouts. The purpose of this study is to propose a machine learning based model that predicts dropout in advance by using various information of learners. In particular, this study aimed to improve the accuracy of the prediction model by taking into consideration not only structured data but also unstructured data. Analysis of unstructured data was performed using Word2vec and Convolutional Neural Network(CNN), which are the most popular text analysis technologies. We could find that application of the proposed model to the actual data of a domestic vocational training institute improved the prediction accuracy by up to 20%. In addition, the support vector machine-based prediction model using both structured and unstructured data showed high prediction accuracy of the latter half of 90%.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.1
• /
• pp.37-44
• /
• 2019

With the advance of digital IT technology, the performance of the printing and scanning devices is improved and their price becomes cheaper. As a result, the public can easily access these devices for crimes such as forgery of official and private documents. Therefore, if we can identify which printing device is used to print the documents, it would help to narrow the investigation and identify suspects. In this paper, we propose a deep learning model for printer identification. A convolutional neural network model based on local features which is widely used for identification in recent is presented. Then, another model including a step to calculate global features and hence improving the convergence speed and accuracy is presented. Using 8 printer models, the performance of the presented models was compared with previous feature-based identification methods. Experimental results show that the presented model using local feature and global feature achieved 97.23% and 99.98% accuracy respectively, which is much better than other previous methods in accuracy.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.264-272
• /
• 2019

In this paper, we propose a 3D human body reconstruction and refinement method from the frames extracted from a video to obtain natural and smooth motion in temporal domain. Individual frames extracted from the video are fed into convolutional neural network to estimate the location of the joint and the silhouette of the human body. This is done by projecting the parameter-based 3D deformable model to 2D image and by estimating the value of the optimal parameters. If the reconstruction process for each frame is performed independently, temporal consistency of human pose and shape cannot be guaranteed, yielding an inaccurate result. To alleviate this problem, the proposed method analyzes and interpolates the principal component parameters of the 3D morphable model reconstructed from each individual frame. Experimental result shows that the erroneous frames are corrected and refined by utilizing the relation between the previous and the next frames to obtain the improved 3D human reconstruction result.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.635-644
• /
• 2020

Object recognition, detection and instance segmentation based on DL (Deep Learning) have being used in various practices, and mainly optical images are used as training data for DL models. The major objective of this paper is object segmentation and building detection by utilizing multimodal datasets as well as optical images for training Detectron2 model that is one of the improved R-CNN (Region-based Convolutional Neural Network). For the implementation, infrared aerial images, LiDAR data, and edges from the images, and Haralick features, that are representing statistical texture information, from LiDAR (Light Detection And Ranging) data were generated. The performance of the DL models depends on not only on the amount and characteristics of the training data, but also on the fusion method especially for the multimodal data. The results of segmenting objects and detecting buildings by applying hybrid fusion - which is a mixed method of early fusion and late fusion - results in a 32.65% improvement in building detection rate compared to training by optical image only. The experiments demonstrated complementary effect of the training multimodal data having unique characteristics and fusion strategy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.3
• /
• pp.341-348
• /
• 2020

The ability to extract useful information from an image, such as the human eye, is an interface technology essential for AI computer implementation. The building recognition technology has a lower recognition rate than other image recognition technologies due to the various building shapes, the ambient noise images according to the season, and the distortion by angle and distance. The computer vision based building recognition algorithms presented so far has limitations in discernment and expandability due to manual definition of building characteristics. This paper introduces the deep learning CNN (Convolutional Neural Network) model, and proposes new method to improve the recognition rate even by changes of building images caused by season, illumination, angle and perspective. This paper introduces the partial images that characterize the building, such as windows or wall images, and executes the training with whole building images. Experimental results show that the building recognition rate is improved by about 14% compared to the general CNN model.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.1
• /
• pp.43-50
• /
• 2022

Correlation Power Analysis(CPA) is a sub-channel attack method that measures the detailed power consumption of attack target equipment equipped with cryptographic algorithms and guesses the secret key used in cryptographic algorithms with more than 90% probability. Since CPA performs analysis based on statistics, a large amount of data is necessarily required. Therefore, the CPA must measure power consumption for at least about 15 minutes for each attack. In this paper proposes a method of using a Convolutional Neural Network(CNN) capable of accumulating input data and predicting results to solve the data collection problem of CPA. By collecting and learning the power consumption of the target equipment in advance, entering any power consumption can immediately estimate the secret key, improving the computational speed and 96.7% of the secret key estimation accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.87-93
• /
• 2023

In this paper, we propose a system that accurately and efficiently determines forward head posture based on network learning by analyzing the user's skeletal posture. Forward head posture syndrome is a condition in which the forward head posture is changed by keeping the neck in a bent forward position for a long time, causing pain in the back, shoulders, and lower back, and it is known that daily posture habits are more effective than surgery or drug treatment. Existing methods use convolutional neural networks using webcams, and these approaches are affected by the brightness, lighting, skin color, etc. of the image, so there is a problem that they are only performed for a specific person. To alleviate this problem, this paper extracts the skeleton from the image and learns the data corresponding to the side rather than the frontal view to find the forward head posture more efficiently and accurately than the previous method. The results show that the accuracy is improved in various experimental scenes compared to the previous method.

• Phonetics and Speech Sciences
• /
• v.14 no.4
• /
• pp.35-43
• /
• 2022

This paper studies how to improve the identification rate of laryngeal disability speech data by convolutional neural network (CNN) and machine learning ensemble learning methods. In general, the number of laryngeal dysfunction speech data is small, so even if identifiers are constructed by statistical methods, the phenomenon caused by overfitting depending on the training method can lead to a decrease the identification rate when exposed to external data. In this work, we try to combine results derived from CNN models and machine learning models with various accuracy in a multi-voting manner to ensure improved classification efficiency compared to the original trained models. The Pusan National University Hospital (PNUH) dataset was used to train and validate algorithms. The dataset contains normal voice and voice data of benign and malignant tumors. In the experiment, an attempt was made to distinguish between normal and benign tumors and malignant tumors. As a result of the experiment, the random forest method was found to be the best ensemble method and showed an identification rate of 85%.

• Journal of Digital Policy
• /
• v.3 no.1
• /
• pp.27-32
• /
• 2024

In this paper, proposes a super resolution method that enhances the quality of results by refining texture features, contrasting each, and utilizing the results as weights. For the improvement of quality, a precise and clear restoration result in details such as boundary areas is crucial in super resolution, along with minimizing unnecessary artifacts like noise. The proposed method constructs a residual block structure with multiple paths and skip-connections for feature estimation in conventional Convolutional Neural Network (CNN)-based super resolution methods to enhance quality. Additional learning is performed for sharpened and blurred image results for further texture analysis. By contrasting each super resolution result and allocating weights through this process, the proposed method achieves improved quality in detailed and smoothed areas of the image. The experimental results of the proposed method, evaluated using the PSNR and SSIM values as quality metrics, show higher results compared to existing algorithms, confirming the enhancement in quality.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.5
• /
• pp.2099-2106
• /
• 2018

This study presents a novel approach of discriminative feature vectors based on manifold learning using nonlinear dimension reduction (DR) technique to improve loss function, and combine with the Adversarial examples to regularize the object function for image classification. The traditional convolutional neural networks (CNN) with many new regularization approach has been successfully used for image classification tasks, and it achieved good results, hence it costs a lot of Calculated spacing and timing. Significantly, distrinct from traditional CNN, we discriminate the feature vectors for objects without empirically-tuned parameter, these Discriminative features intend to remain the lower-dimensional relationship corresponding high-dimension manifold after projecting the image feature vectors from high-dimension to lower-dimension, and we optimize the constrains of the preserving local features based on manifold, which narrow the mapped feature information from the same class and push different class away. Using Adversarial examples, improved loss function with additional regularization term intends to boost the Robustness and generalization of neural network. experimental results indicate that the approach based on discriminative feature of manifold learning is not only valid, but also more efficient in image classification tasks. Furthermore, the proposed approach achieves competitive classification performances for three benchmark datasets : MNIST, CIFAR-10, SVHN.