• 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 Processing Systems
• /
• 제19권2호
• /
• pp.211-218
• /
• 2023

In order to improve the low accuracy of traditional wireless network health information retrieval methods, a wireless network health information retrieval method is designed based on data mining algorithm. The invalid health information stored in wireless network is filtered by data mapping, and the health information is clustered by data mining algorithm. On this basis, the high-frequency words of health information are classified to realize wireless network health information retrieval. The experimental results show that exactitude of design way is significantly higher than that of the traditional method, which can solve the problem of low accuracy of the traditional wireless network health information retrieval method.

• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.381-389
• /
• 2022

With the collection of huge volumes of text, image, audio, video or combinations of these, in a word multimedia data, the need to explore them in order to discover possible new, unexpected and possibly valuable information for decision making was born. Starting from the already existing data mining, but not as its extension, multimedia mining appeared as a distinct field with increased complexity and many characteristic aspects. Later, the concept of big data was extended to multimedia, resulting in multimedia big data, which in turn attracted the multimedia big data mining process. This paper aims to survey multimedia data mining, starting from the general concept and following the transition from multimedia data mining to multimedia big data mining, through an up-to-date synthesis of works in the field, which is a novelty, from our best of knowledge.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권10호
• /
• pp.3230-3255
• /
• 2022

Causality mining in NLP is a significant area of interest, which benefits in many daily life applications, including decision making, business risk management, question answering, future event prediction, scenario generation, and information retrieval. Mining those causalities was a challenging and open problem for the prior non-statistical and statistical techniques using web sources that required hand-crafted linguistics patterns for feature engineering, which were subject to domain knowledge and required much human effort. Those studies overlooked implicit, ambiguous, and heterogeneous causality and focused on explicit causality mining. In contrast to statistical and non-statistical approaches, we present Bidirectional Encoder Representations from Transformers (BERT) integrated with Multi-level Feature Networks (MFN) for causality recognition, called BERT+MFN for causality recognition in noisy and informal web datasets without human-designed features. In our model, MFN consists of a three-column knowledge-oriented network (TC-KN), bi-LSTM, and Relation Network (RN) that mine causality information at the segment level. BERT captures semantic features at the word level. We perform experiments on Alternative Lexicalization (AltLexes) datasets. The experimental outcomes show that our model outperforms baseline causality and text mining techniques.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권10호
• /
• pp.5023-5038
• /
• 2017

Big data is an emerging technology which deals with wide range of data sets with sizes beyond the ability to work with software tools which is commonly used for processing of data. When we consider a huge network, we have to process a large amount of network information generated, which consists of both normal and abnormal activity logs in large volume of multi-dimensional data. Intrusion Detection System (IDS) is required to monitor the network and to detect the malicious nodes and activities in the network. Massive amount of data makes it difficult to detect threats and attacks. Sequential Pattern mining may be used to identify the patterns of malicious activities which have been an emerging popular trend due to the consideration of quantities, profits and time orders of item. Here we propose a sequential pattern mining algorithm with fuzzy logic feature selection and fuzzy weighted support for huge volumes of network logs to be implemented in Apache Hadoop YARN, which solves the problem of speed and time constraints. Fuzzy logic feature selection selects important features from the feature set. Fuzzy weighted supports provide weights to the inputs and avoid multiple scans. In our simulation we use the attack log from NS-2 MANET environment and compare the proposed algorithm with the state-of-the-art sequential Pattern Mining algorithm, SPADE and Support Vector Machine with Hadoop environment.

• 한국컴퓨터정보학회논문지
• /
• 제24권7호
• /
• pp.125-133
• /
• 2019

Because military weapons systems for special purposes are small and complex, they are not easy to maintain. Therefore, it is very important to maintain combat strength through quick maintenance in the event of a breakdown. In particular, naval ships are complex weapon systems equipped with various equipment, so other equipment must be considered for maintenance in the event of equipment failure, so that skilled maintenance personnel have a great influence on rapid maintenance. Therefore, in this paper, we analyzed maintenance data of defense equipment maintenance information system through text mining and social network analysis(SNA), and tried to identify the naval ship maintenance expertise. The defense equipment maintenance information system is a system that manages military equipment efficiently. In this study, the data(2,538cases) of some naval ship maintenance teams were analyzed. In detail, we examined the contents of main maintenance and maintenance personnel through text mining(word cloud, word network). Next, social network analysis(collaboration analysis, centrality analysis) was used to confirm the collaboration relationship between maintenance personnel and maintenance expertise. Finally, we compare the results of text mining and social network analysis(SNA) to find out appropriate methods for finding and finding naval ship maintenance expertise.

• 한국산업정보학회논문지
• /
• 제14권3호
• /
• pp.22-29
• /
• 2009

컴퓨터를 통해서 들어오는 다양한 형태의 침입을 효과적으로 탐지하기 위해서 이전에는 오용탐지 기법이 주로 이용되어 왔다. 오용탐지 기법은 이전에 알려지지 않은 침입 방법들을 효과적으로 탐지할 수 있기 때문이다. 하지만, 해당 기법에서는 정상적인 네트워크 접속 형태가 몇 가지 패턴으로 고정되어 있다고 가정한다. 이러한 이유 때문에 새로운 정상적인 네트워크 연결이 비정상행위로 탐지되기도 한다. 본 논문에서는 연관 마이닝 기법을 활용한 침입 탐지 방법을 제안한다. 논문에서 제안되는 방법은 패킷내 마이닝 단계와 패킷간 마이닝 두가지 단계로 구성된다. 제안된 방법의 성능은 대표적인 네트워크 침입 탐지 방법인 JAM과의 비교 실험을 통하여 평가하였다.

• KNOM Review
• /
• 제23권1호
• /
• pp.26-33
• /
• 2020

비트코인은 일반적으로 사용하고 있는 달러, 원화, 유로, 엔화 등 세계적인 종이 화폐와 달리 은행과 금융기관 등과 같은 중앙 집중 기관에 의존하지 않는 암호화폐이다. 비트코인 네트워크에서는 채굴(mining) 작업으로 거래 내역이 담긴 블록을 생성하고, 블록이 생성되었다는 메시지를 모든 참여 노드에게 브로드캐스팅(broadcasting) 방식으로 전파하여 검증을 통해 신뢰성을 확보한다. 이와 같이 비트코인 네트워크에서 채굴과 블록 전파는 P2P 네트워크의 성능에 크게 영향을 받는다. 채굴의 경우 네트워크 내에서 먼저 채굴을 진행하고, 더 빠르게 채굴에 대한 증명을 전파하는지에 따라 보상을 받는 노드가 달라진다. 본 논문에서는 비트코인 네트워크에서 수행되는 기존의 이웃 연결 방식과 블록 전파 방식에 대한 문제점을 지역적인 특성과 RTT(Round-To-Trip) 값 측정을 적용하여 블록 전파 속도향상을 위한 개선 알고리즘을 제시한다. 실험을 통해 개선 알고리즘과 기존 알고리즘의 성능 비교하여 전반적인 블록 전파 시간이 감소한 것을 검증한다.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2003년도 추계학술대회
• /
• pp.57-72
• /
• 2003

This article provides integrated neural network models for the interest rate forecasting using change-point detection. The model is composed of three phases. The first phase is to detect successive structural changes in interest rate dataset. The second phase is to forecast change-point group with data mining classifiers. The final phase is to forecast the interest rate with BPN. Based on this structure, we propose three integrated neural network models in terms of data mining classifier: (1) multivariate discriminant analysis (MDA)-supported neural network model, (2) case based reasoning (CBR)-supported neural network model and (3) backpropagation neural networks (BPN)-supported neural network model. Subsequently, we compare these models with a neural network model alone and, in addition, determine which of three classifiers (MDA, CBR and BPN) can perform better. For interest rate forecasting, this study then examines the predictability of integrated neural network models to represent the structural change.

• International Journal of Computer Science & Network Security
• /
• 제23권5호
• /
• pp.207-211
• /
• 2023

Traditional methods for datamining typically assume that the data is small, centralized, memory resident and static. But this assumption is no longer acceptable, because datasets are growing very fast hence becoming huge from time to time. There is fast growing need to manage data with efficient mining algorithms. In such a scenario it is inevitable to carry out data mining in a distributed environment and Frequent Itemset Mining (FIM) is no exception. Thus, the need of an efficient incremental mining algorithm arises. We propose the Distributed Incremental Approximate Frequent Itemset Mining (DIAFIM) which is an incremental FIM algorithm and works on the distributed parallel MapReduce environment. The key contribution of this research is devising an incremental mining algorithm that works on the distributed parallel MapReduce environment.