• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.3
• /
• pp.201-207
• /
• 2021

Deep learning, a type of machine learning, performs learning while changing the weights as it progresses through each learning process. Tensor Flow and Keras provide the results of the end of the learning in graph form. Thus, If an error occurs, the result must be discarded. Consequently, existing technologies provide a function to roll back learning results, but the rollback function is limited to results up to five times. Moreover, they applied the concept of MLOps to track the deep learning process, but no rollback capability is provided. In this paper, we construct a system that manages the intermediate value of the learning process by blockchain to record the intermediate learning process and can rollback in the event of an error. To perform the functions of blockchain, the deep learning process and the rollback of learning results are designed to work by writing Smart Contracts. Performance evaluation shows that, when evaluating the rollback function of the existing deep learning method, the proposed method has a 100% recovery rate, compared to the existing technique, which reduces the recovery rate after 6 times, down to 10% when 50 times. In addition, when using Smart Contract in Ethereum blockchain, it is confirmed that 1.57 million won is continuously consumed per block creation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1704-1720
• /
• 2020

Recognizing food from photographs presents many applications for machine learning, computer vision and dietetics, etc. Recent progress of deep learning techniques accelerates the recognition of food in a great scale. We build a hierarchical structure composed of deep CNN to recognize and classify food from photographs. We build a dataset for Korean food of 18 classes, which are further categorized in 4 major classes. Our hierarchical recognizer classifies foods into four major classes in the first step. Each food in the major classes is further classified into the exact class in the second step. We employ DenseNet structure for the baseline of our recognizer. The hierarchical structure provides higher accuracy and F1 score than those from the single-structured recognizer.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.3
• /
• pp.197-206
• /
• 2019

Telemarketing has been used in finance due to the reduction of offline channels. In order to select telemarketing target customers, various machine learning techniques have emerged to maximize the effect of minimum cost. However, there are problems that the class imbalance, which the number of marketing success customers is smaller than the number of failed customers, and the recall rate is lower than accuracy. In this paper, we propose a method that solve the imbalanced class problem and increase the recall rate to improve the efficiency. The hybrid sampling method is applied to balance the data in the class, and the stacked deep network is applied to improve the recall and precision as well as the accuracy. The proposed method is applied to actual bank telemarketing data. As a result of the comparison experiment, the accuracy, the recall, and the precision is improved higher than that of the conventional methods.

• Journal of Multimedia Information System
• /
• v.7 no.1
• /
• pp.11-16
• /
• 2020

Deep Learning has become the most important technology in the field of artificial intelligence machine learning, with its high performance overwhelming existing methods in various applications. In this paper, an interactive window service based on object recognition technology is proposed. The main goal is to implement an object recognition technology using this deep learning technology to remove the existing eye tracking technology, which requires users to wear eye tracking devices themselves, and to implement an eye tracking technology that uses only usual cameras to track users' eye. We design an interactive system based on efficient eye detection and pupil tracking method that can verify the user's eye movement. To estimate the view-direction of user's eye, we initialize to make the reference (origin) coordinate. Then the view direction is estimated from the extracted eye pupils from the origin coordinate. Also, we propose a blink detection technique based on the eye apply ratio (EAR). With the extracted view direction and eye action, we provide some augmented information of interest without the existing complex and expensive eye-tracking systems with various service topics and situations. For verification, the user guiding service is implemented as a proto-type model with the school map to inform the location information of the desired location or building.

• Nuclear Engineering and Technology
• /
• v.53 no.2
• /
• pp.522-531
• /
• 2021

We describe a new deep learning model - Convolutional eXtreme Gradient Boosting (ConvXGB) for classification problems based on convolutional neural nets and Chen et al.'s XGBoost. As well as image data, ConvXGB also supports the general classification problems, with a data preprocessing module. ConvXGB consists of several stacked convolutional layers to learn the features of the input and is able to learn features automatically, followed by XGBoost in the last layer for predicting the class labels. The ConvXGB model is simplified by reducing the number of parameters under appropriate conditions, since it is not necessary re-adjust the weight values in a back propagation cycle. Experiments on several data sets from UCL Repository, including images and general data sets, showed that our model handled the classification problems, for all the tested data sets, slightly better than CNN and XGBoost alone and was sometimes significantly better.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1075-1080
• /
• 2022

Recently, the effort is continuously applied in machine learning and deep learning algorithm which is represented as artificial intelligence algorithm in the varies field such as prediction, classification and clustering. In this paper, we propose detection algorithm for un-peeling status of PCB protection film by using Dectron2. We use 42 images of data as training and 19 images of data as testing based on 61 images which was taken under the condition of a critical reflection angel of 42.8°. As a result, we get 16 images that was detected and 3 images that was not detected among 19 images of testing data.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.3
• /
• pp.487-499
• /
• 2022

Machine learning such as deep learning have been widely used in recent years. Recently deep learning is performed in a trusted execution environment such as ARM TrustZone to improve security in edge devices and embedded devices with low computing resource. To mitigate this problem, we propose TPMP that efficiently uses the limited memory of TEE through DNN model partitioning. TPMP achieves high confidentiality of DNN by performing DNN models that could not be run with existing memory scheduling methods in TEE through optimized memory scheduling. TPMP required a similar amount of computational resources to previous methodologies.

• International Journal of Computer Science & Network Security
• /
• v.22 no.12
• /
• pp.98-106
• /
• 2022

A condition of the retina known as hypertensive retinopathy (HR) is connected to high blood pressure. The severity and persistence of hypertension are directly correlated with the incidence of HR. To avoid blindness, it is essential to recognize and assess HR as soon as possible. Few computer-aided systems are currently available that can diagnose HR issues. On the other hand, those systems focused on gathering characteristics from a variety of retinopathy-related HR lesions and categorizing them using conventional machine-learning algorithms. Consequently, for limited applications, significant and complicated image processing methods are necessary. As seen in recent similar systems, the preciseness of classification is likewise lacking. To address these issues, a new CAD HR-diagnosis system employing the advanced Deep Dense CNN Learning (DD-CNN) technology is being developed to early identify HR. The HR-diagnosis system utilized a convolutional neural network that was previously trained as a feature extractor. The statistical investigation of more than 1400 retinography images is undertaken to assess the accuracy of the implemented system using several performance metrics such as specificity (SP), sensitivity (SE), area under the receiver operating curve (AUC), and accuracy (ACC). On average, we achieved a SE of 97%, ACC of 98%, SP of 99%, and AUC of 0.98. These results indicate that the proposed DD-CNN classifier is used to diagnose hypertensive retinopathy.

• Korean Journal of Remote Sensing
• /
• v.40 no.2
• /
• pp.167-177
• /
• 2024

With advancements in satellite technology, interest in target detection and identification is increasing quantitatively and qualitatively. Synthetic Aperture Radar(SAR) images, which can be acquired regardless of weather conditions, have been applied to various areas combined with machine learning based detection algorithms. However, conventional studies primarily focused on the detection of stationary targets. In this study, we proposed a method to identify moving targets using an algorithm that integrates sub-aperture SAR images and cosine similarity calculations. Utilizing a transformer-based deep learning target detection model, we extracted the bounding box of each target, designated the area as a region of interest (ROI), estimated the similarity between sub-aperture SAR images, and determined movement based on a predefined similarity threshold. Through the proposed algorithm, the quantitative evaluation of target identification capability enhanced its accuracy compared to when training with the targets with two different classes. It signified the effectiveness of our approach in maintaining accuracy while reliably discerning whether a target is in motion.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.2
• /
• pp.189-196
• /
• 2024

Classification of drones and birds is challenging due to diverse flight patterns and limited data availability. Previous research has focused on identifying the flight patterns of unmanned aerial vehicles by emphasizing dynamic features such as speed and heading. However, this approach tends to neglect crucial spatial information, making accurate discrimination of unmanned aerial vehicle characteristics challenging. Furthermore, training methods for situations with imbalanced data among classes have not been proposed by traditional machine learning techniques. In this paper, we propose a data processing method that preserves angle information while maintaining positional details, enabling the deep learning model to better comprehend positional information of drones. Additionally, we introduce a training technique to address the issue of data imbalance.