• Journal of Sensor Science and Technology
• /
• v.30 no.1
• /
• pp.15-19
• /
• 2021

Image processing is one of the major techniques that are used for computer vision. Nowadays, researchers are using machine learning and deep learning for the aforementioned task. In recent years, digit recognition tasks, i.e., automatic meter recognition approach using electric or water meters, have been studied several times. However, two major issues arise when we talk about previous studies: first, the use of the deep learning technique, which includes a large number of parameters that increase the computational cost and consume more power; and second, recent studies are limited to the detection of digits and not storing or providing detected digits to a database or mobile applications. This paper proposes a system that can detect the digital number of meter readings using a lightweight deep neural network (DNN) for low power consumption and send those digits to an Android mobile application in real-time to store them and make life easy. The proposed lightweight DNN is computationally inexpensive and exhibits accuracy similar to those of conventional DNNs.

• Journal of Positioning, Navigation, and Timing
• /
• v.10 no.1
• /
• pp.49-54
• /
• 2021

Indoor positioning system becomes of increasing interests due to the demands for accurate indoor location information where Global Navigation Satellite System signal does not approach. Wi-Fi access points (APs) built in many construction in advance helps developing a Wi-Fi Received Signal Strength Indicator (RSSI) based indoor localization. This localization method first collects pairs of position and RSSI measurement set, which is called fingerprint database, and then estimates a user's position when given a query measurement set by comparing the fingerprint database. The challenge arises from nonlinearity and noise on Wi-Fi RSSI measurements and complexity of handling a large amount of the fingerprint data. In this paper, machine learning techniques have been applied to implement Wi-Fi based localization. However, most of existing indoor localizations focus on single position estimation. The main contribution of this paper is to develop multi-target localization by using deep neural, which is beneficial when a massive crowd requests positioning service. This paper evaluates the proposed multilocalization based on deep learning from a multi-story building, and analyses its learning effect as increasing number of target positions.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.1
• /
• pp.108-113
• /
• 2022

The deep-learning-based measurement method with the through-focus scanning optical microscopy (TSOM) estimated the size of the object using the classification. However, the measurement performance of the method depends on the number of subdivided classes, and it is practically difficult to prepare data at regular intervals for training each class. We propose an approach to measure the size of an object in the TSOM image using the deep-learning regression model instead of using classification. We attempted our proposed method to estimate the top critical dimension (TCD) of through silicon via (TSV) holes with 2461 TSOM images and the results were compared with the existing method. As a result of our experiment, the average measurement error of our method was within 30 nm (1σ) which is 1/13.5 of the sampling distance of the applied microscope. Measurement errors decreased by 31% compared to the classification result. This result proves that the proposed method is more effective and practical than the classification method.

• The Journal of Information Systems
• /
• v.31 no.4
• /
• pp.01-23
• /
• 2022

Purpose This study aims to propose a deep learning-based fake review detection model by combining authors' linguistic features and semantic information of reviews. Design/methodology/approach This study used 358,071 review data of Yelp to develop fake review detection model. We employed linguistic inquiry and word count (LIWC) to extract 24 linguistic features of authors. Then we used deep learning architectures such as multilayer perceptron(MLP), long short-term memory(LSTM) and transformer to learn linguistic features and semantic features for fake review detection. Findings The results of our study show that detection models using both linguistic and semantic features outperformed other models using single type of features. In addition, this study confirmed that differences in linguistic features between fake reviewer and authentic reviewer are significant. That is, we found that linguistic features complement semantic information of reviews and further enhance predictive power of fake detection model.

• International Journal of Computer Science & Network Security
• /
• v.22 no.8
• /
• pp.343-351
• /
• 2022

A brain tumor forms when some tissue becomes old or damaged but does not die when it must, preventing new tissue from being born. Manually finding such masses in the brain by analyzing MRI images is challenging and time-consuming for experts. In this study, our main objective is to detect the brain's tumorous part, allowing rapid diagnosis to treat the primary disease instantly. With image processing techniques and deep learning prediction algorithms, our research makes a system capable of finding a tumor in MRI images of a brain automatically and accurately. Our tumor segmentation adopts the U-Net deep learning segmentation on the standard MICCAI BRATS 2018 dataset, which has MRI images with different modalities. The proposed approach was evaluated and achieved Dice Coefficients of 0.9795, 0.9855, 0.9793, and 0.9950 across several test datasets. These results show that the proposed system achieves excellent segmentation of tumors in MRIs using deep learning techniques such as the U-Net algorithm.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.587-598
• /
• 2022

To increase building change recognition accuracy, we present a deep learning-based building change detection using remote sensing images. In the proposed approach, by merging pixel-level and object-level information of multitemporal remote sensing images, we create the difference image (DI), and the frequency-domain significance technique is used to generate the DI saliency map. The fuzzy C-means clustering technique pre-classifies the coarse change detection map by defining the DI saliency map threshold. We then extract the neighborhood features of the unchanged pixels and the changed (buildings) from pixel-level and object-level feature images, which are then used as valid deep neural network (DNN) training samples. The trained DNNs are then utilized to identify changes in DI. The suggested strategy was evaluated and compared to current detection methods using two datasets. The results suggest that our proposed technique can detect more building change information and improve change detection accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.30-45
• /
• 2024

This study introduces an effective method for predicting individual local tax delinquencies using prevalent machine learning and deep learning algorithms. The evaluation of credit risk holds great significance in the financial realm, impacting both companies and individuals. While credit risk prediction has been explored using statistical and machine learning techniques, their application to tax arrears prediction remains underexplored. We forecast individual local tax defaults in Republic of Korea using machine and deep learning algorithms, including convolutional neural networks (CNN), long short-term memory (LSTM), and sequence-to-sequence (seq2seq). Our model incorporates diverse credit and public information like loan history, delinquency records, credit card usage, and public taxation data, offering richer insights than prior studies. The results highlight the superior predictive accuracy of the CNN model. Anticipating local tax arrears more effectively could lead to efficient allocation of administrative resources. By leveraging advanced machine learning, this research offers a promising avenue for refining tax collection strategies and resource management.

• Journal of Information Processing Systems
• /
• v.20 no.1
• /
• pp.13-23
• /
• 2024

Music brings pleasure and relaxation to people. Therefore, it is necessary to classify musical genres based on scenes. Identifying favorite musical genres from massive music data is a time-consuming and laborious task. Recent studies have suggested that machine learning algorithms are effective in distinguishing between various musical genres. However, meeting the actual requirements in terms of accuracy or timeliness is challenging. In this study, a hybrid machine learning model that combines a deep residual auto-encoder (DRAE) and support vector machine (SVM) for musical genre recognition was proposed. Eight manually extracted features from the Mel-frequency cepstral coefficients (MFCC) were employed in the preprocessing stage as the hybrid music data source. During the training stage, DRAE was employed to extract feature maps, which were then used as input for the SVM classifier. The experimental results indicated that this method achieved a 91.54% F1-score and 91.58% top-1 accuracy, outperforming existing approaches. This novel approach leverages deep architecture and conventional machine learning algorithms and provides a new horizon for musical genre classification tasks.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2004.04a
• /
• pp.473-476
• /
• 2004

In this study, hydrochemical studies of thermal waters in the Bugok and Magumsan areas showing geothermal anomalies were carried, and the applicability of ion seothermometers and multiple mineral equilibrium approach was examined to estimate their potential deep reservoir temperatures. Typical thermal waters of the two areas are clearly grouped into two major types, according to water chemistry: Na-Cl type (group A) and Na-SO4 type (group D). Compared to group A, group B and C waters show some modifications in chemistry. Group E waters show the modified chemistry from group D. Geothermal waters from the two areas showed some different chemical characteristics. The thermal waters of group A and B in Magumsan area are typically neutral to alkaline (pH=6.7 to 8.1) and Cl-rich (up to 446.1 mg/L), while the waters of group D and E in Bugok area are alkaline (pH=7.6 to 10.0) and SO$_4$-rich (up to 188.0 mg/L). The group A (Na-Cl type) and group D (Na-SO$_4$ type) waters correspond to mature or partially immature water, whereas the other types are immature water. The genesis of geothermal waters are considered as follows: group A and B waters were formed by seawater infiltration into reservoir rocks along faults and fracture zones and possibly affected by fossil connate waters in lithologic units through which deep hot waters circulate; on the other hand, group D and E waters were formed by the oxidation of sulfide minerals (mainly pyrite) in surrounding sedimentary rocks and/or hydrothermal veins occurring along restricted fracture channels and were possibly affected by the input and subsequent oxidation of S-bearing gases (e.g. H2S) from deep thermal reservoir (probably, cooling pluton). The application of quartz, Na-K, K-Mg geothermometers to the chemistry of representative group A and D waters yielded a reasonable temperature estimate (99-147$^{\circ}C$ and 90-142$^{\circ}C$) for deep geothermal reservoir. Aqueous liquid-rich fluid inclusions in fracture calcites obtained from drillcores in Bugok area have an average homogenization temperature of 128$^{\circ}C$, which corresponds to the results from ion geothermometers. The multiple mineral equilibrium approach yielded a similar temperature estimate (105-135$^{\circ}C$ and 100-14$0^{\circ}C$). We consider that deep reservoir temperatures of thermal waters in the Magumsan and Bugok areas can be estimated by the chemistry of typical Na-Cl and Na-SO$_4$ type waters and possibly approach 105-135$^{\circ}C$ and 100-14$0^{\circ}C$.

• Structural Engineering and Mechanics
• /
• v.57 no.4
• /
• pp.657-680
• /
• 2016

Reinforced concrete (RC) deep beams are structural members that predominantly fail in shear. Therefore, determining the shear strength of these types of beams is very important. The strut-and-tie method is commonly used to design deep beams, and this method has been adopted in many building codes (ACI318-14, Eurocode 2-2004, CSA A23.3-2004). In this study, the efficiency of artificial neural networks (ANNs) in predicting the shear strength of RC deep beams is investigated as a different approach to the strut-and-tie method. An ANN model was developed using experimental data for 214 normal and high-strength concrete deep beams from an existing literature database. Seven different input parameters affecting the shear strength of the RC deep beams were selected to create the ANN structure. Each parameter was arranged as an input vector and a corresponding output vector that includes the shear strength of the RC deep beam. The ANN model was trained and tested using a multi-layered back-propagation method. The most convenient ANN algorithm was determined as trainGDX. Additionally, the results in the existing literature and the accuracy of the strut-and-tie model in ACI318-14 in predicting the shear strength of the RC deep beams were investigated using the same test data. The study shows that the ANN model provides acceptable predictions of the ultimate shear strength of RC deep beams (maximum $R^2{\approx}0.97$). Additionally, the ANN model is shown to provide more accurate predictions of the shear capacity than all the other computed methods in this study. The ACI318-14-STM method was very conservative, as expected. Moreover, the study shows that the proposed ANN model predicts the shear strengths of RC deep beams better than does the strut-and-tie model approaches.