• Journal of Ocean Engineering and Technology
• /
• v.30 no.6
• /
• pp.526-534
• /
• 2016

This study had the goal of designing onboard structures for a pre-pilot mining test (PPMT), which is required for the commercialization of the deep-sea mining industry. This PPMT is planned to validate the performance of a hydraulic lifting system and verify the concept of operating through a moon-pool in the east sea, Korea. All of the onboard equipment and facility were designed by KRISO. Because the test was performed at the first development, it is difficult to determine what risk will occur in the facility. Therefore, risk-based design is required in the facility for the PPMT, which includes the facility layout, failure mode and effect analysis (FMEA), and risk reduction plan. All of the expected performances of the lifting system itself and the onboard facilities were qualitatively validated using the risk-based design.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.5
• /
• pp.195-204
• /
• 2018

In this paper, we propose both a new loss function and an online hard example mining scheme for improving the performance of single-stage object detectors which use deep convolutional neural networks. The proposed loss function and the online hard example mining scheme can not only overcome the problem of imbalance between the number of annotated objects and the number of background examples, but also improve the localization accuracy of each object. Therefore, the loss function and the mining scheme can provide intrinsically fast single-stage detectors with detection performance higher than or similar to that of two-stage detectors. In experiments conducted with the PASCAL VOC 2007 benchmark dataset, we show that the proposed loss function and the online hard example mining scheme can improve the performance of single-stage object detectors.

• Asia pacific journal of information systems
• /
• v.32 no.4
• /
• pp.770-802
• /
• 2022

With the development of deep learning techniques, text mining is producing breakthrough performance improvements, promising future applications, and practical use cases across many fields. Likewise, even though several attempts have been made in the field of financial information, few cases apply the current technological trends. Recently, companies and government agencies have attempted to conduct research and apply text mining in the field of financial information. First, in this study, we investigate various works using text mining to show what studies have been conducted in the financial sector. Second, to broaden the view of financial application, we provide a description of several text mining techniques that can be used in the field of financial information and summarize various paradigms in which these technologies can be applied. Third, we also provide practical cases for applying the latest text mining techniques in the field of financial information to provide more tangible guidance for those who will use text mining techniques in finance. Lastly, we propose potential future research topics in the field of financial information and present the research methods and utilization plans. This study can motivate researchers studying financial issues to use text mining techniques to gain new insights and improve their work from the rich information hidden in text data.

• Journal of Information Technology Services
• /
• v.17 no.1
• /
• pp.79-89
• /
• 2018

Sentiment analysis is a technique of text mining that extracts feelings of the person who wrote the sentence like movie review. The preliminary researches of sentiment analysis identify sentiments by using the dictionary which contains negative and positive words collected in advance. As researches on deep learning are actively carried out, sentiment analysis using deep learning model with morpheme or word unit has been done. However, this model has disadvantages in that the word dictionary varies according to the domain and the number of morphemes or words gets relatively larger than that of phonemes. Therefore, the size of the dictionary becomes large and the complexity of the model increases accordingly. We construct a sentiment analysis model using recurrent neural network by dividing input data into phoneme-level which is smaller than morpheme-level. To verify the performance, we use 30,000 movie reviews from the Korean biggest portal, Naver. Morpheme-level sentiment analysis model is also implemented and compared. As a result, the phoneme-level sentiment analysis model is superior to that of the morpheme-level, and in particular, the phoneme-level model using LSTM performs better than that of using GRU model. It is expected that Korean text processing based on a phoneme-level model can be applied to various text mining and language models.

• Structural Engineering and Mechanics
• /
• v.60 no.5
• /
• pp.809-828
• /
• 2016

In deep open pit mines, slope stability is very important. Particularly, increasing the depths increase the risks in mines having weak rock mass. Blasting operations in this type of open pits may have a negative impact on slope stability. Several or combination of methods can be used in order to enable better analysis in this type of deep open-pit mines. Numerical modeling is one of these options. Many complex problems can be integrated into numerical methods at the same time and analysis, solutions can be performed on a single model. Rock failure criterions and rock models are used in numerical modeling. Hoek-Brown and Mohr-Coulomb terms are the two most commonly used rock failure conditions. In this study, mine planning and discontinuity conditions of a lignite mine facing two big landslides previously, has been investigated. Moreover, the presence of some damage before starting the study was identified in surrounding structures. The primary research of this study is on slope study. In slope stability analysis, numerical modeling methods with Hoek-Brown and Mohr-Coulomb failure criterions were used separately. Preparing the input data to the numerical model, the outcomes of patented-blast vibration minimization method, developed by co-author was used. The analysis showed that, the model prepared by applying Hoek-Brown failure criterion, failed in the stage of 10. However, the model prepared by using Mohr-Coulomb failure criterion did not fail even in the stage 17. Examining the full research field, there has been ongoing production in this mine without any failure and damage to surface structures.

• Information Systems Review
• /
• v.20 no.4
• /
• pp.25-41
• /
• 2018

Applying predictive analytics to enterprise processes is an effective way to reduce operation costs and enhance productivity. Accordingly, the ability to predict business processes and performance indicators are regarded as a core capability. Recently, several works have predicted processes using deep learning in the form of recurrent neural networks (RNN). In particular, the approach of predicting the next step of activity using static or dynamic RNN has excellent results. However, few studies have given attention to applying deep learning in the form of dynamic RNN to predictions of process performance indicators. To fill this knowledge gap, the study developed an approach to using process mining and dynamic RNN. By utilizing actual data from a large domestic company, it has applied the suggested approach in estimating timely stocking in purchasing process, which is an important indicator of the process. The analytic methods and results of this study were presented and some implications and limitations are also discussed.

• Geomechanics and Engineering
• /
• v.37 no.3
• /
• pp.293-306
• /
• 2024

Influenced by the alternating effects of dynamic and static pressure during the mining process of close range coal seams, the surrounding rock support of cross mining roadway is difficult and the deformation mechanism is complex, which has become an important problem affecting the safe and efficient production of coal mines. The paper takes the inclined longwall mining of the 10304 working face of Zhongheng coal mine as the engineering background, analyzes the key strata fracture mechanism of the large inclined right-angle trapezoidal mining field, explores the stress distribution characteristics and transmission law of the surrounding rock of the roadway affected by the mining of the inclined coal seam, and proposes a segmented and hierarchical support method for the cross mining roadway affected by the mining of the close range coal seam group. The research results indicate that based on the derived expressions for shear and tensile fracture of key strata, the ultimate pushing distance and ultimate suspended area of a right angle trapezoidal mining area can be calculated and obtained. Within the cross mining section, along the horizontal direction of the coal wall of the working face, the peak shear stress is located near the middle of the boundary. The cracks on the floor of the cross mining roadway gradually develop in an elliptical funnel shape from the shallow to the deep. The dual coupling support system composed of active anchor rod support and passive U-shaped steel shed support proposed in this article achieves effective control of the stability of cross mining roadways, which achieves effective control of floor by coupling active support and preventive passive support to improve the strength of the surrounding rock itself. The research results are of great significance for guiding the layout, support control, and safe mining of cross mining roadways, and to some extent, can further enrich and improve the relevant theories of roof movement and control.

• Geomechanics and Engineering
• /
• v.15 no.6
• /
• pp.1153-1160
• /
• 2018

Rockbursts, catastrophic events involving the violent release of elastic energy stored in rock features, remain a worldwide challenge for geoengineering. Especially at deep-mining sites, rockbursts can occur in hard, high-stress, brittle rock zones, and the associated risk depends on such factors as mining activity and the stress on surrounding rocks. Rockbursts are often sudden and destructive, but there is still no unified standard for predicting them. Based on previous studies, a new Bayesian multi-index model was introduced to predict and evaluate rockbursts. In this method, the rock strength index, energy release index, and surrounding rock stress are the basic factors. Values from 18 rock samples were obtained, and the potential rockburst risks were evaluated. The rockburst tendencies of the samples were modelled using three existing methods. The results were compared with those obtained by the new Bayesian model, which was observed to predict rockbursts more effectively than the current methods.

• Journal of Ocean Engineering and Technology
• /
• v.29 no.2
• /
• pp.128-134
• /
• 2015

Axial vibration analysis is very important for a deep-seabed mining system. In this study, an axial vibration analysis was carried out to estimate the natural frequencies and tensions of the umbilical cable using experimental data obtained from the first pre-pilot mining test. The axial vibrations of the umbilical cable with a pilot mining robot at the bottom end were analytically determined. The range of the added mass coefficients of the pilot mining robot is estimated by comparing the experimental and analytical data. The natural frequencies and maximum tensions are calculated using four estimated added mass coefficients.

• Geomechanics and Engineering
• /
• v.28 no.5
• /
• pp.463-475
• /
• 2022

In the mine exploitation stage; one of the critical issues is the stability assessment of post-pillars. The instability of post-pillars leads to serious safety hazards in mining operations. The focus of this study is to assess the stability of post-pillars in the 130# stope in the central ore body at Trepça hard rock mine by employing both conventional (i.e., critical span curve) and numerical methods (i.e., FLAC3D). Moreover, a new numerical based index (i.e., Pillar Yield Ratio-PYR) was proposed. The aim of PYR index is to determine a border line between stable, potentially unstable, and failure state of post-pillars at a specific mine site. The critical value of pillar width to height ratio is 2.5 for deep production stopes (e.g., > 800 m). Results showed that pillar size, mining height and mining depth significantly have affected the post-pillar stability. The reliability of numerical based index (i.e., PYR) is verified based on empirical underground pillar stability graph developed by Lunder, 1994. The proposed pillar yield ratio index and pillar stability graph can be used as a design tool in new mining areas at Trepça hard rock mine and for other situations with similar geotechnical conditions.