• 인터넷정보학회논문지
• /
• 제16권6호
• /
• pp.89-95
• /
• 2015

전통적인 빈발 패턴 마이닝은 데이터베이스로부터 사용자 정의 최소 임계치 이상의 빈도수를 가지는 유효 패턴들을 식별한다. 적절한 임계치 설정은 해당 도메인에 대한 사전 지식을 요구하므로 쉬운 작업이 아니다. 따라서 임계치 설정을 통한 마이닝 결과의 정밀한 제어 불가능으로 인해 도메인 지식을 기반으로 하지 않는 패턴 마이닝 방법이 필요하게 되었다. 상위 K 빈발 패턴 마이닝은 이러한 문제를 해결하기 위해 제안되었으며, 임계치 설정 없이 상위 K개의 중요 패턴들을 마이닝 한다. 사용자는 이를 적용함으로써 데이터베이스에 상관없이 가장 높은 빈도수의 패턴부터 K번째로 높은 빈도수의 패턴까지 찾아낼 수 있다. 비록 상위 K 빈발 패턴 마이닝이 임계치 설정 없이 상위 K개의 중요 패턴들을 마이닝 하지만, 트랜잭션 내 아이템 수량과 데이터베이스 내 서로 다른 아이템 중요도를 고려하지 못하여 많은 실세계 응용의 요구에 부합하지 못한다. 하이 유틸리티 패턴 마이닝은 아이템 중요도가 포함된 비 바이너리 데이터베이스의 특성을 고려하기 위해 제안되었으나 최소 임계치를 필요로 한다. 최근 임계치 설정 없는 하이 유틸리티 패턴 마이닝을 위한 상위 K 하이 유틸리티 패턴 마이닝이 개발되었으며, 이를 통해 사용자는 사전 지식 없이 원하는 수의 패턴을 마이닝 할 수 있다. 본 논문은 상위 K 하이 유틸리티 패턴 마이닝을 위한 알고리즘을 분석한다. 최신 알고리즘에 대한 성능분석을 통해 개선사항 및 발전 방향에 대해 고찰한다.

• Geomechanics and Engineering
• /
• 제22권2호
• /
• pp.133-142
• /
• 2020

The evolution of the mining-induced fracture network formed during longwall top coal caving (LTCC) has a great influence on the gas drainage, roof control, top coal recovery ratio and engineering safety of aquifers. To reveal the evolution of the mining-induced stress and fracture network formed during LTCC, the fracture network in front of the working face was observed by borehole video experiments. A discrete element model was established by the universal discrete element code (UDEC) to explore the local stress distribution. The regression relationship between the fractal dimension of the fracture network and mining stress was established. The results revealed the following: (1) The mining disturbance had the most severe impact on the borehole depth range between approximately 10 m and 25 m. (2) The distribution of fractures was related to the lithology and its integrity. The coal seam was mainly microfractures, which formed a complex fracture network. The hard rock stratum was mainly included longitudinal cracks and separated fissures. (3) Through a numerical simulation, the stress distribution in front of the mining face and the development of the fracturing of the overlying rock were obtained. There was a quadratic relationship between the fractal dimension of the fractures and the mining stress. The results obtained herein will provide a reference for engineering projects under similar geological conditions.

• Journal of information and communication convergence engineering
• /
• 제22권1호
• /
• pp.44-55
• /
• 2024

High-utility itemset mining (HUIM) is a dominant technology that enables enterprises to make real-time decisions, including supply chain management, customer segmentation, and business analytics. However, classical support value-driven Apriori solutions are confined and unable to meet real-time enterprise demands, especially for large amounts of input data. This study introduces a groundbreaking model for top-N high utility itemset mining in real-time enterprise applications. Unlike traditional Apriori-based solutions, the proposed convolutional sequential embedding metrics-driven cosine-similarity-based multilayer perception learning model leverages global and contextual features, including semantic attributes, for enhanced top-N recommendations over sequential transactions. The MATLAB-based simulations of the model on diverse datasets, demonstrated an impressive precision (0.5632), mean absolute error (MAE) (0.7610), hit rate (HR)@K (0.5720), and normalized discounted cumulative gain (NDCG)@K (0.4268). The average MAE across different datasets and latent dimensions was 0.608. Additionally, the model achieved remarkable cumulative accuracy and precision of 97.94% and 97.04% in performance, respectively, surpassing existing state-of-the-art models. This affirms the robustness and effectiveness of the proposed model in real-time enterprise scenarios.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.549-552
• /
• 2004

Since open-cut mining excavates gradually from the top of the mountain, vegetation planting is needed to reduce negative environmental impact on the surrounding environment. Accordingly, this study aimed at performing the environmental monitoring of the open-cut mining ground using the satellite remote sensing technique. As the research technique, in order to grasp the environmental change around the open-cut mining ground, NDVI (normalized difference vegetation index) was calculated, and every year change of the vegetation activity was analyzed. The results of the study showed lower vegetation activity in the open-cut mining ground compared to the surrounding areas and suggested the need for closed monitoring by remote sensing techniques.

• Ocean and Polar Research
• /
• 제36권4호
• /
• pp.475-485
• /
• 2014

Seawater flow characteristics around a manganese nodule mining device in deep sea were analyzed through numerical investigation. The mining device influences the seawater flow field with complicated velocity distributions, and they are largely dependent on the seawater flow speed, device moving speed, and injection velocity from the collecting part. The flow velocity and turbulent kinetic energy distributions are compared at several positions from the device rear, side, and top, and it is possible to predict the distance from which the mining device affects the seawater flow field through the variation of turbulent kinetic energy. With the operation of the collecting device the turbulent kinetic energy remarkably increases, and it gradually decreases along the seawater flow direction. Turbulent kinetic energy behind the mining system increases with the seawater flow velocity. The transient behavior of nodule particles, which are not collected, is also predicted. This study will be helpful in creating an optimal design for a manganese nodule collecting device that can operate efficiently and which is eco-friendly.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 추계학술대회
• /
• pp.201-202
• /
• 2018

본 논문에서는 기존 ImageNet과 Oxford-IIIT Pet Image의 Dataset에서 제공하는 개 품종 이미지와 인터넷 상에서 개 품종 이미지를 데이터 마이닝을 통해 획득된 개 품종 이미지를 결합하고 Random-Label을 추가 하여 개 품종 122개의 클래스와 개 품종이 아닌 1개의 클래스를 인식하는 방법에 대해 소개 한다. 기존 DB만을 사용하였을 때 개 품종 인식률 대비 기존 DB와 수집 DB를 모두 사용한 개 품종 인식률이 Top-1에 대해서 1.5% 개선되었다. 개가 아닌 이미지 인식은 랜덤 DB를 10000장의 경우 93% 인식률을 확인했다.

• 자원리싸이클링
• /
• 제25권5호
• /
• pp.3-13
• /
• 2016

도시광산산업 통계는 도시광산산업을 체계적으로 육성하기 위해서 가장 기본적으로 필요한 자료이며 산업현황을 이해하는데 중요한 수단이다. 본 연구에서는 국가통계를 활용하는 Top-down 방식과 개별 기업현황 조사를 하는 Bottom-up 방식을 병행한 통계조사 방법을 통하여 도시광산 재자원화 규모 및 업체 현황을 조사하였다. 그 결과 도시광산 재자원화 규모는 19.6조 원으로 국내 금속수요의 약 22%를 도시광산에서 공급하고 있었다. 또한 도시광산 업체는 917개로 수도권과 경상권에 대다수 분포하고 있었으며, 약 58%의 업체가 10인 이하의 소기업으로 조사되었다. 2009년 도시광산 업체 현황 조사결과와 비교하였을 때, 도시광산 업체수는 전반적으로 증가하였고, 특히 희소금속 관련 기업 수의 증가 폭이 컸다. 본 연구는 기존의 간접적인 도시광산 통계 결과와 달리 실제 도시광산 업체에서 생산되는 금속자원 규모 및 관련 업체에 대한 통계자료를 산정하여 제시했다는 점에서 연구의 차별성 및 의의를 지닌다.

• Geomechanics and Engineering
• /
• 제11권3호
• /
• pp.401-420
• /
• 2016

The stability of deep coal roadways with large sections and thick top coal is a typical challenge in many coal mines in China. The innovative Universal Discrete Element Code (UDEC) trigon block is adopted to create a numerical model based on a case study at the Dongtan coal mine in China to better understand the failure mechanism and stability control mechanism of this kind of roadway. The failure process of an unsupported roadway is simulated, and the results suggest that the deformation of the roof is more serious than that of the sides and floor, especially in the center of the roof. The radial stress that is released is more intense than the tangential stress, while a large zone of relaxation appears around the roadway. The failure process begins from partial failure at roadway corners, and then propagates deeper into the roof and sides, finally resulting in large deformation in the roadway. A combined support system is proposed to support roadways based on an analysis of the simulation results. The numerical simulation and field monitoring suggest that the availability of this support method is feasible both in theory and practice, which can provide helpful references for research on the failure mechanisms and scientific support designing of engineering in deep coal mines.

• 스마트미디어저널
• /
• 제2권2호
• /
• pp.20-27
• /
• 2013

The concept of social media is top of the agenda for many business executives and decision makers, as well as consultants try to identify ways where companies can make profitable use of applications such as Netflix, Flixster. The social media is playing an increasingly important role as the information sources for customers making product choices etc. With the flourish of Web 2.0 technology, customer reviews are becoming more and more useful and important information resources for people to save their time and energy on purchasing products that they want. This paper proposes the Bayesian Probabilistic Classification algorithm to mine the social media review, and evaluates it by different splits and cross validation mechanism from the real data set. The explored study experimental results show the robustness and effectiveness of proposed approach for mining the social media review.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2006년 창립20주년기념 정기학술대회 및 국제워크샵
• /
• pp.315-318
• /
• 2006

This paper concerns about coupled dynamic analysis of the deep-seabed mining system in launching operation. The dynamic behavior of mining system consisting of lifting pipe, buffer station, flexible conduit and self-propelled miner is simulated in time domain. The launching operation is divided into four critical phases: (1) deployment of miner and flexible conduit, (2) deployment of lifting pipe, flexible conduit and miner, (3) touch-down of miner, (4) final launching. The dynamic responses of sub-systems - miner, flexible conduit, buffer and lifting pipe - are analyzed in each launching phase. According to the changing periods of forced excitation at the top, the dynamic responses of sub-systems are diverse in their characteristics. It has been shown that the total integrated responses of sub-systems are strongly affected by the design parameters. Especially, the principal dimensions of flexible conduit seem to be significant in determining of the global response. Based on the simulation results, safe operation conditions are investigated.