• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• 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)
• /
• v.10 no.1
• /
• pp.136-151
• /
• 2016

Flexible large-scale WLANs are now widely deployed in crowded and highly mobile places such as campus, airport, shopping mall and company etc. But network management is hard for large-scale WLANs due to highly uneven interference and throughput among links. So the traffic is difficult to predict accurately. In the paper, through analysis of traffic in two real large-scale WLANs, Granger Causality is found in both scenarios. In combination with information entropy, it shows that the traffic prediction of target AP considering Granger Causality can be more predictable than that utilizing target AP alone, or that of considering irrelevant APs. So We develops new method -Granger Causality and Vector Auto-Regression (GCVAR), which takes APs series sharing Granger Causality based on Vector Auto-regression (VAR) into account, to predict the traffic flow in two real scenarios, thus redundant and noise introduced by multivariate time series could be removed. Experiments show that GCVAR is much more effective compared to that of traditional univariate time series (e.g. ARIMA, WARIMA). In particular, GCVAR consumes two orders of magnitude less than that caused by ARIMA/WARIMA.

• Journal of Korean Society of Transportation
• /
• v.20 no.1
• /
• pp.101-110
• /
• 2002

This study first explains general features of traffic assignment models and network loading methods, and investigates the relationship between them. Then it introduces a dynamic network loading method, which accounts far time variable additionally. First of all, this study suggests that it is important to consider some requirements for the dynamic network loading, such as causality, FIFO(First-In-First-Out) discipline, the flow propagation, and the flow conservation. The details of dynamic network loafing methods are explained in the form of algorithm, and numerical examples are shown in the test network by adopting deterministic queuing model for a link Performance function.

• Proceedings of the KSME Conference
• /
• 2008.11a
• /
• pp.695-700
• /
• 2008

Artificial neural network (ANN) has been extensively used in areas of nonlinear system modeling, analysis and design applications. Basically, ANN has its distinct capabilities of implementing system identification and/or function approximation using a number of input/output patterns that can be obtained via numerical and/or experimental manners. The paper describes a role of ANN, especially a back-propagation neural network (BPN) in the context of engineering analysis, design and optimization. Fundamental mechanism of BPN is briefly summarized in terms of training procedure and function approximation. The BPN based causality analysis (CA) is further discussed to realize the problem decomposition in the context of multidisciplinary design optimization. Such CA is also applied to quantitatively evaluate the uncoupled or decoupled design matrix in the context of axiomatic design with the independence axiom.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.40 no.4
• /
• pp.65-81
• /
• 2015

As research management is growing in importance for research organizations, their disciplinary structures need to be interpreted. However, it is not only difficult but ambiguous to detect causal relations between subjects because diverse disciplines interacting with each other lead the development of organizational research. Therefore, this article summarizes the major concepts and results recently achieved in the related fields such as research management, bibliographic analysis, information theory, and networks to characterize organizational knowledge structures. Relevant analytical methods obtained from the literature can be applied to empirical situations. Predictive causal relations can be measured using an information theoretic indicator on a series of organizational research portfolios identified from bibliographic information. A network approach would be suitable to manage organizational research effort from a holistic view. Knowledge structures of the Government-funded Research Institutes in Korea are explored experimentally.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.51-62
• /
• 2022

AI-based speed prediction studies have been conducted quite actively. However, while the importance of explainable AI is emerging, the study of interpreting and reasoning the AI-based speed predictions has not been carried out much. Therefore, in this paper, 'Explainable Deep Graph Neural Network (GNN)' is devised to analyze the speed prediction and assess the nearby road influence for reasoning the critical contributions to a given road situation. The model's output was explained by comparing the differences in output before and after masking the input values of the GNN model. Using TOPIS traffic speed data, we applied our GNN models for the major congested roads in Seoul. We verified our approach through a traffic flow simulation by adjusting the most influential nearby roads' speed and observing the congestion's relief on the road of interest accordingly. This is meaningful in that our approach can be applied to the transportation network and traffic flow can be improved by controlling specific nearby roads based on the inference results.

• Journal of the Korean Geographical Society
• /
• v.48 no.1
• /
• pp.72-86
• /
• 2013

Industrial agglomeration is an old theme in economic geography and many studies have been devoted to this topic. But only few have empirically looked at the time trend of industrial agglomeration. This study measured agglomeration of U.S. industries over last 29 years and measurement results indicated that industrial clustering has occurred during the study period in all study industries without a common time trend shared amongst the study industries. The agglomeration levels then were plugged in to investigate causalities, i.e. causal relations, around industrial agglomeration. Three variables were selected to see causal relations with agglomeration levels based on literatures, and our focus was given to the causality between transport network and agglomeration. Causal relation from transport to agglomeration was found in various industries and this supports the argument that the development of transportation influences industrial agglomeration. At the same time inverse and bi-directional causalities were also revealed implying more complex relationship between these two.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.8A
• /
• pp.1407-1416
• /
• 2001

인터넷 서비스를 구내망에 제공하기 위한 인트라넷에서도 인터넷과 동일하게 고속 멀티미디어 및 QoS 보장형 서비스의 요구가 증가하고 있다. 이러한 요구를 충족시키기 위해서 인트라넷에서도 서비스별 트래픽 관리와 망자원의 효율적인 관리가 필요하게 되었다. 본 논문에서는 TINA 체계의 장애관리 기능에 따른 관리를 위해 인트라넷을 각각의 Layer Network 관점에서 재구성하였다. 효율적인 장애관리를 위한 기능 구조를 제안하고, 제안된 구조와 TINA 표준에 따라 장애관리 연사객체를 설계 및 구현한다. 또한, 경보 상관 관계 분석 및 장애 위치 식별 및 국지화(localization)를 위해 인트라넷에서의 장애원인 및 결과 관계를 나타내는 Fault Causality Graph를 제안한다.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2005.09a
• /
• pp.373-378
• /
• 2005

The diagrammatic language for pathways is widely used for representing systems knowledge as a network of causal relations. Biologists infer and hypothesize with pathways to design experiments and verify models, and to identify potential drug targets. Although there have been many approaches to formalize pathways to simulate a system, reasoning with incomplete and high level knowledge has not been possible. We present a qualitative formalization of a pathway language with incomplete causal descriptions and its translation into propositional temporal logic to automate the reasoning process. Such automation accelerates the identification of drug targets in pathways.

• Journal of Biomedical Engineering Research
• /
• v.29 no.3
• /
• pp.179-186
• /
• 2008

This paper presents a portable tele-assessment system designed for remote evaluation of the hypertonic elbow joint of neurologically impaired patients. A patient's upper limb was securely strapped to a portable limb-stretching device which is connected through Internet to a portable haptic device by which a clinician remotely moved the patient's elbow joint and felt the resistance from the patient. Elbow flexion angle and joint torques were measured from both master and slave devices and bilaterally fed back to their counterparts. In order to overcome problems associated with the network latency, two different tele-operation schemes were proposed depending on relative speed of tasks compared to the amount of time delay. For slow movement tasks, the bilateral tele-operation was achieved in real-time by designing control architectures after causality analysis. For fast movement tasks, we used a semi-real-time tele-operation scheme which provided the clinicians with stable and transparent feeling. The tele-assessment system was verified experimentally on patients with stroke. The devices were made portable and low cost, which makes it potentially more accessible to patients in remote areas.