• Journal of Information Science Theory and Practice
• /
• 제7권1호
• /
• pp.52-71
• /
• 2019

An insider threat is a threat that comes from people within the organization being attacked. It can be described as a function of the motivation, opportunity, and capability of the insider. Compared to managing the dimensions of opportunity and capability, assessing one's motivation in committing malicious acts poses more challenges to organizations because it usually involves a more obtrusive process of psychological examination. The existing body of research in psycholinguistics suggests that automated text analysis of electronic communications can be an alternative for predicting and detecting insider threat through unobtrusive behavior monitoring. However, a major challenge in employing this approach is that it is difficult to minimize the risk of missing any potential threat while maintaining an acceptable false alarm rate. To deal with the trade-off between the risk of missed catches and the false alarm rate, we propose a unified psycholinguistic framework that consolidates multiple text analyzers to carry out sentiment analysis, emotion analysis, and topic modeling on electronic communications for unobtrusive psychological assessment. The user scenarios presented in this paper demonstrated how the trade-off issue can be attenuated with different text analyzers working collaboratively to provide more comprehensive summaries of users' psychological states.

• The Journal of Asian Finance, Economics and Business
• /
• 제9권10호
• /
• pp.215-225
• /
• 2022

This study investigates employees' online reviews, conducts in-depth text topic mining, effectively summarizes the dimensions of employer brand value, and seeks effective ways to build employer brands from a multi-dimensional perspective. This study employs samples of employer reviews, filter keywords according to word frequency-inverse document frequency, builds a review network containing the same keywords, explore the community and summarize the theme dimensions. Simultaneously, it makes a dynamic comparison and analysis of the employer brand value dimension of different industries and enterprises. The study shows that the community exploration theme can be summarized into 11 dimensions of employer brand value, and the dimensions of employer brand value are significantly different across industries and among different enterprises within the industry. The attention to the employer brand value dimension has a significant time change. Various industries pay increasing attention to the dimension of work intensity and career development, while employers pay steady attention to the dimension of welfare benefits. The findings of this study suggest that seeking the heterogeneity of employer brand resources from the multi-dimensional differences and changes is an effective way to improve the competitiveness of enterprises in the human capital market.

• Asia pacific journal of information systems
• /
• 제32권4호
• /
• pp.945-963
• /
• 2022

With the widespread use of social media, online social platforms like Twitter have become a place of rapid dissemination of information-both accurate and inaccurate. After the COVID-19 outbreak, the overabundance of fake information and rumours on online social platforms about the COVID-19 pandemic has spread over society as quickly as the virus itself. As a result, fake news poses a significant threat to effective virus response by negatively affecting people's willingness to follow the proper public health guidelines and protocols, which makes it important to identify fake information from online platforms for the public interest. In this research, we introduce an approach to detect fake news using deep learning techniques, which outperform traditional machine learning techniques with a 93.1% accuracy. We then investigate the content differences between real and fake news by applying topic modeling and linguistic analysis. Our results show that topics on Politics and Government services are most common in fake news. In addition, we found that fake news has lower analytic and authenticity scores than real news. With the findings, we discuss important academic and practical implications of the study.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2013년도 추계학술대회 논문집
• /
• pp.63-64
• /
• 2013

Induction motors' faults detection is almost a popular topic among researchers. Monitoring the output of motors is a key factor in detecting these faults. (Short-time) Fourier, (continuous, discrete) wavelet, and extended Park vector transformations are among the methods for fault detection. One major deficiency of these methods is not being able to detect the severity of faults that carry low energy information, e.g. in ball bearing system failure, there is absolutely no way to detect the severity of fault using Fourier or wavelet transformations. In this paper, the authors have applied the Discrete Wavelet Transform (DWT) frequency-domain analysis to detect bearing faults in an induction motor. In other words, in discrete transform which the output signal is decomposed in several steps and frequency resolution increases considerably, the frequency-band analysis is performed and it will be verified that first of all, fault sidebands become more recognizable for detection in higher levels of decomposition, and secondly, the inner race bearing faults turn out easier in these levels; and all these matter because of eliminating the not-required high energy components in lower levels of decomposing.

• 한국산업융합학회 논문집
• /
• 제14권3호
• /
• pp.105-111
• /
• 2011

Landmark Spots in 2D gel electrophoresis are used in many methods of 2DEG spot matching. Landmark Spots are obtained manually and it is a bottle neck in the entire protein analysis process. Automated landmark spots detection is a very crucial topic in processing a massive amount of 2DGE data. In this paper, Automated landmark spot detection is proposed using point pattern matching and graph theory. Neighbor spots are defined by a graph theory to use and only a centered spot and its neighbor spots are considered for spot matching. Normalized Hausdorff distance is introduced as a criterion for measuring degree of similarity. In the conclusion, the method proposed in this paper can get about 50% of the total spot pairs and the accuracy rate is almost 100%, which the requirements of landmark spots are fully satisfied.

• 한국위성정보통신학회논문지
• /
• 제12권1호
• /
• pp.28-33
• /
• 2017

본 논문에서는 여러 곳에서 통용되고 있는 기존의 CW(continuous-wave) 레이더 송수신모델을 수정한 송수신모델을 제안한다. 최근에 심장박동과 호흡을 검출하기 위해 기존신호모델을 기반으로 CW(continuous-wave) 레이더에 대한연구가 진행 되고 있다. 그러나 이 통용되고 있는 수신모델은 인체 공학적으로 개념과 일치하지 않기 때문에 이모델을 근거로 실험을 할 경우 실제 개발되는 시스템 성능을 정확하게 예측할수 없다. 본 논문에서는 인체 공학상 개념과 일치하는 수정된 CW(continuous-wave) 레이더 송수신모델을 제안하고 가운시안 잡음rhk 다중경로 환경에서 심장박동 및 호흡검출에 대한 시뮬레이션을 수행하고 이를 기존수신모델과의 심장박동과 호흡검출에 대한 성능을 비교 분석한다.

• 한국공작기계학회논문집
• /
• 제10권1호
• /
• pp.1-9
• /
• 2001

The development of flexible automation in the manufacturing industry is concerned with production activities performed by unmanned machining system A major topic relevant to metal-cutting operations is monitoring toll wear, which affects process efficiency and product quality, and implementing automatic toll replacements. In this paper, the measurement of the cutting force components has been found to provide a method for an in-process detection of tool wear. The static com-ponents of cutting force have been used to detect flank wear. To eliminate the influence of variations in cutting conditions, tools, and workpiece materials, the force modeling is performed for various cutting conditions. The normalized force dis-parities are defined in this paper, and the relationships between normalized disparity and flank were are established. Final-ly, artificial neural network is used to learn these relationships and detect tool wear. According to proposed method, the static force components could provide the effective means to detect flank wear for varying cutting conditions in turning operation.

• Earthquakes and Structures
• /
• 제8권4호
• /
• pp.935-956
• /
• 2015

Structural Health Monitoring (SHM) of steel towers has become a hot research topic. From the literature, it is impractical and impossible to develop a "general" method that can detect all kinds of damages for all types of structures. A practical method should make use of the characteristics of the type of structures and the kind of damages. This paper reports a feasibility study on the use of measured modal parameters for the detection of damaged braces of tower structures following the Bayesian probabilistic approach. A substructure-based structural model-updating scheme, which groups different parts of the target structure systematically and is specially designed for tower structures, is developed to identify the stiffness distributions of the target structure under the undamaged and possibly damaged conditions. By comparing the identified stiffness distributions, the damage locations and the corresponding damage extents can be detected. By following the Bayesian theory, the probability model of the uncertain parameters is derived. The most probable model of the steel tower can be obtained by maximizing the probability density function (PDF) of the model parameters. Experimental case studies were employed to verify the proposed method. The contributions of this paper are not only on the proposal of the substructure-based Bayesian model updating method but also on the verification of the proposed methodology through measured data from a scale model of transmission tower under laboratory conditions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권8호
• /
• pp.4043-4060
• /
• 2017

Network Intrusion Detection (NID), an important topic in the field of information security, can be viewed as a pattern recognition problem. The existing pattern recognition methods can achieve a good performance when the number of training samples is large enough. However, modern network attacks are diverse and constantly updated, and the training samples have much smaller size. Furthermore, to improve the learning ability of SVM, the research of kernel functions mainly focus on the selection, construction and improvement of kernel functions. Nonetheless, in practice, there are no theories to solve the problem of the construction of kernel functions perfectly. In this paper, we effectively integrate the advantages of the radial basis function kernel and the polynomial kernel on the notion of the game theory and propose a novel kernel SVM algorithm with game theory for NID, called GTNID-SVM. The basic idea is to exploit the game theory in NID to get a SVM classifier with better learning ability and generalization performance. To the best of our knowledge, GTNID-SVM is the first algorithm that studies ensemble kernel function with game theory in NID. We conduct empirical studies on the DARPA dataset, and the results demonstrate that the proposed approach is feasible and more effective.

• Journal of Power Electronics
• /
• 제19권6호
• /
• pp.1566-1574
• /
• 2019

Maximum power point tracking (MPPT) under the partial shading condition is a challenging research topic for photovoltaic systems. Shaded photo-voltaic module result in complex peak patterns on the power versus voltage curve which can misguide classical MPPT algorithms. Thus, various kinds of global MPPT algorithms have been studied. These have typically consisted of partial shading detection, global peak search and MPPT. The conventional partial shading detection algorithm aims to detect all of the occurrences of partial shading. This results in excessive execution of global peak searches and discontinuous operation of the MPPT. This in turn, reduces the achievable power for the PV module. Based on a theoretical investigation of power verse voltage curve patterns under various partial shading conditions, it is realized that not all the occurrences of partial shadings require a global peak search. Thus, an intelligent partial shading detection algorithm that provides exact identification of global peak search necessity is essential for the efficient utilization of solar energy resources. This paper presents a new partial shading determinant algorithm utilizing adaptive threshold levels. Conventional methods tend to be too sensitive to sharp shading patterns but insensitive to smooth patterns. However, the proposed algorithm always shows superb performance, regardless of the partial shading patterns.