• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권6호
• /
• pp.2186-2196
• /
• 2014

Spam mail is one of the most general mail dysfunctions, which may cause psychological damage to internet users. As internet usage increases, the amount of spam mail has also gradually increased. Indiscriminate sending, in particular, occurs when spam mail is sent using smart phones or tablets connected to wireless networks. Spam mail consists of approximately 68% of mail traffic; however, it is believed that the true percentage of spam mail is at a much more severe level. In order to analyze and detect spam mail, we introduce a technique based on spam mail characteristics and text mining; in particular, spam mail is detected by extracting the linguistic analysis and language processing. Existing spam mail is analyzed, and hidden spam signatures are extracted using text clustering. Our proposed method utilizes a text mining system to improve the detection and error detection rates for existing spam mail and to respond to new spam mail types.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제6권4호
• /
• pp.1160-1181
• /
• 2014

Springing and whipping are becoming increasingly important considerations in ship design as container ships increase in size. In this study, the springing and whipping characteristics of a large container ship were investigated through a series of systematic model tests in waves. A multi-segmented hull model with a backbone was adopted for measurement of springing and whipping signals. A conversion method for extracting torsion springing and whipping is described in this paper for the case of an open-section backbone. Higher-order springing, higher-mode torsion responses, and the effects of linear and nonlinear springing in irregular waves are highlighted in the discussion.

• Journal of Electrical Engineering and Technology
• /
• 제13권2호
• /
• pp.961-968
• /
• 2018

Recently, researches on automatic recognition of human activities have been actively carried out with the emergence of various intelligent systems. Since a large amount of visual data can be secured through Closed Circuit Television, it is required to recognize human behavior in a dynamic situation rather than a static situation. In this paper, we propose new intelligent human activity recognition model using the trajectory information extracted from the video sequence. The proposed model consists of three steps: segmentation and partitioning of trajectory step, feature extraction step, and behavioral learning step. First, the entire trajectory is fuzzy partitioned according to the motion characteristics, and then temporal features and spatial features are extracted. Using the extracted features, four pedestrian behaviors were modeled by decision tree learning algorithm and performance evaluation was performed. The experiments in this paper were conducted using Caviar data sets. Experimental results show that trajectory provides good activity recognition accuracy by extracting instantaneous property and distinctive regional property.

• 한국CDE학회논문집
• /
• 제6권4호
• /
• pp.263-270
• /
• 2001

In stamping-die manufacturing, the first step is to build die patterns for lost wax casting process. A recent industry trend is to manufacture the die pattern using 3-axis NC machining. This study identifies technical considerations of the pattern machining caused by the characteristics of Styrofoam material, and proposes technical methods related to establishing a process plan and generating tool paths for optimizing the pattern machining. In this paper, the process plan includes the fellowing three items: 1) deter-mining a global machining sequence-a sequence of profile, top, bottom machining and two set-ups, 2) extracting machining features from a pattern model and merging them, and 3) determining a machining sequence of machining features. To each machining feature, this study determines the machining start point, generates the approach tool path, and proposes a tool path linking method fur reducing the distance of the cutter rapid motion. Finally, a smooth tool path generation and an automatic feedrate adjustment (AFA) method are introduced far raising the machining efficiency.

• 천문학회보
• /
• 제39권1호
• /
• pp.56.1-56.1
• /
• 2014

With the advent of high-resolution high-sensitivity observations, spiral patterns have been revealed around several asymptotic giant branch (AGB) stars. Such patterns can provide possible evidence for the existence of central binary stars embedded in outflowing circumstellar envelopes. It is, however, not generally recognized that the binary induced pattern, vertically extended from the orbital plane, exhibits a ring-like pattern with an inclined viewing angle. I will first review the binary-induced spiral-shell patterns on the AGB circumstellar envelopes with the effect of inclination angle with respect to the orbital plane, of which large inclination cases reveal incomplete ring-like patterns. I will describe a method of extracting such spiral-shell from the gas kinematics of an incomplete ring-like pattern to place constraints on the characteristics of the (unknown) central binary stars. This first success may open the possibility of connecting the ring-like patterns commonly found in the AGB circumstellar envelopes and in the outer parts of (pre-)planetary nebulae and pointing to the conceivable presence of central binary systems, which may give a clue for the onset of asymmetrical planetary nebulae.

• 음성과학
• /
• 제10권4호
• /
• pp.167-177
• /
• 2003

This paper presents a method of building an exceptional pronunciation dictionary for Korean automatic pronunciation generator. An automatic pronunciation generator is an essential element of speech recognition system and a TTS (Text-To-Speech) system. It is composed of a part of regular rules and an exceptional pronunciation dictionary. The exceptional pronunciation dictionary is created by extracting the words which have exceptional pronunciations from text corpus based on the characteristics of the words of exceptional pronunciation through phonological research and text analysis. Thus, the method contributes to improve performance of Korean automatic pronunciation generator as well as the performance of speech recognition system and TTS system.

• Structural Monitoring and Maintenance
• /
• 제2권4호
• /
• pp.357-382
• /
• 2015

This paper provides an overview of the use of different Distributed Optical Fiber Sensor systems (DOFSs) to perform Structural Health Monitoring (SHM) in the specific case of civil engineering structures. Nowadays, there are several methods available for extracting distributed measurements from optical fiber, and their use have to be according with the aims of the SHM performance. The continuous-in-space data is the common advantage of the different DOFSs over other conventional health monitoring systems and, depending on the particular characteristics of each DOFS, a global and/or local health structural evaluation is possible with different accuracy. Firstly, the fundamentals of different DOFSs and their principal advantages and disadvantages are presented. Then, laboratory and field tests using different DOFSs systems to measure strain in structural elements and civil structures are presented and discussed. Finally, based on the current applications, conclusions and future trends of DOFSs in SHM in civil structures are proposed.

• Steel and Composite Structures
• /
• 제28권1호
• /
• pp.25-37
• /
• 2018

For the first time, the parametric instability characteristics of tow-steered variable stiffness composite laminated (VSCL) cylindrical panels is investigated using B-spline finite strip method (FSM). The panel is considered containing geometrical defects including cutout and delamination. The material properties are assumed to vary along the panel axial length of any lamina according to a linear fiber-orientation variation. A uniformly distributed inplane longitudinal loading varies harmoni-cally with time is considered. The instability load frequency regions corresponding to the assumed in-plane parametric load-ing is derived using the Bolotin's first order approximation through an energy approach. In order to demonstrate the capabili-ties of the developed formulation in predicting stability behavior of the thin-walled VSCL structures, some representative results are obtained and compared with those in the literature wherever available. It is shown that the B-spline FSM is a proper tool for extracting the stability boundaries of perforated delaminated VSCL panels.

• 한국기계가공학회지
• /
• 제9권1호
• /
• pp.74-80
• /
• 2010

The purpose of reverse engineering design using 3D measurement data is an accurate reconstruction of real body. In oder to accomplish this object, it is important that creating exact extracting edges should be studying out first of all. This study used edge-based method to find out edge point from the measuring point data. The characteristics are analysed using the mean curvature block method on the fitting NURBS curve and defined edges through block removal condition. The results showed that only using the NURBS curve of maximum curvature analysis to define correct edge of real geometry is limited, but this segmentation approach provides simplified necessary condition for edge classification, and an effectiveness to classify a straight line, curves and fillets etc.

• ETRI Journal
• /
• 제33권5호
• /
• pp.720-730
• /
• 2011

Opinion mining involves the analysis of customer opinions using product reviews and provides meaningful information including the polarity of the opinions. In opinion mining, feature extraction is important since the customers do not normally express their product opinions holistically but separately according to its individual features. However, previous research on feature-based opinion mining has not had good results due to drawbacks, such as selecting a feature considering only syntactical grammar information or treating features with similar meanings as different. To solve these problems, this paper proposes an enhanced feature extraction and refinement method called FEROM that effectively extracts correct features from review data by exploiting both grammatical properties and semantic characteristics of feature words and refines the features by recognizing and merging similar ones. A series of experiments performed on actual online review data demonstrated that FEROM is highly effective at extracting and refining features for analyzing customer review data and eventually contributes to accurate and functional opinion mining.