• Journal of Broadcast Engineering
• /
• v.22 no.2
• /
• pp.234-239
• /
• 2017

A real-time violence detection algorithm based on a new descriptor using the magnitude and direction changes of movement in images is proposed. The descriptor was developed from the observation that the changes of violent actions are much larger than those of normal movements. Descriptor feature vectors consisting of descriptor values during several frames are obtained and these are inputs to SVM(Support Vector Machine) classifier for discriminating violence actions from and non-violence actions. Comparison experiments between the ViF(Violent Flow) and the proposed algorithm were conducted with three different types of datasets. The experimental results show that the proposed algorithm outperforms the ViF in every case.

• Journal of Welding and Joining
• /
• v.16 no.4
• /
• pp.125-135
• /
• 1998

The shielded metal arc welding (SMAW) by AC power source was performed to evaluate the arc stability by arc monitoring and analysing. In this study, the arc stability index was evaluated quantitatively by using he coefficient of resistance variation for welding time. This coefficient was obtained for the long time (20sec.) by analysing the waveforms of welding current, voltage and resistance. The coefficient was applied to indicate numerically the variation level of arc length and the degree of arc extinction. Using the coefficient of resistance variation in practical welding, the arc stability of the high titanium oxide electrode (KS E4313) turned out to be better than that of the low hydrogen electrode (KS E4316). In evaluating the skill level of welders by the coefficient, the horizontal fillet weaving welding became clear to be very discriminating because the higher level welder could weave in keeping constant arc length, but the lower level welder showed the characteristics of weaving with the unstable arc length. And it was confirmed that the welding defects as blow holes was formed when the arc stability index were high.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.39 no.11
• /
• pp.995-1004
• /
• 2011

Object X-ray method commonly used for hole search in overset grids requires huge amount of time due to complicated vector calculations to search the cross-points as well as time-consuming hole search algorithm with respect to background grids. Especially, when the grid system is in motion relative to the background, hole points should be searched at every time step, leading to hung computational burden. To cope with this difficulties, this study presents an efficient hole search algorithm mainly designed to reduce hole searching time. To this end, virtual surface with reduced grid points is suggested and logical operators are employed as a classification algorithm instead of complicated vector calculations. In addition, the searching process is further accelerated by designating hole points in a row rather than discriminating hole points with respect to each background grid points. If there exists a relative motion, the present algorithm requires much less time because only the virtual surface needs to be moved at every time step. The hole searching time has been systematically compared for a few selected geometries.

• Science of Emotion and Sensibility
• /
• v.11 no.4
• /
• pp.637-644
• /
• 2008

Human emotion has been tried to be recognized by physiological measurements in developing emotion machine enabling to understand and react to user's emotion. This study is to find the time-dependent physiological measurements and their variation characteristics for discriminating emotions according to dimensional emotion model. Ten university students were asked to watch sixteen prepared images to evoke different emotions. Their subjective emotions and autonomic nervous responses such as ECG (electrocardiogram), PPG (photoplethysmogram), GSR (Galvanic skin response), RSP (respiration), and SKT(skin temperature) were measured during experiment. And these responses were analyzed into HR(Heart Rate), Respiration Rate, GSR amplitude average, SKT amplitude average, PPG amplitude, and PTT(Pulse Transition Time). TDPs(Time dependent parameters) defined as the delay, the activation, the half recovery and the full recovery of respective physiological signal in this study have been determined and statistically compared between variations from different emotions. The significant tendencies in TDP were shown between emotions. Therefore, TDP may provide useful measurements with emotion recognition.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.684-691
• /
• 2006

As many functionalities such as cameras and MP3 players are converged to mobile phones, more intuitive and interesting interaction methods are essential. In this paper, we present applications and their enabling technologies for gesture interactive cell phones. They employ gesture recognition and real-time shake detection algorithm for supporting motion-based user interface and entertainment applications respectively. The gesture recognition algorithm classifies users' movement into one of predefined gestures by modeling basic components of acceleration signals and their relationships. The recognition performance is further enhanced by discriminating frequently confusing classes with support vector machines. The shake detection algorithm detects in real time the exact motion moment when the phone is shaken significantly by utilizing variance and mean of acceleration signals. The gesture interaction algorithms show reliable performance for commercialization; with 100 novice users, the average recognition rate was 96.9% on 11 gestures (digits 1-9, O, X) and users' movements were detected in real time. We have applied the motion understanding technologies to Samsung cell phones in Korean, American, Chinese and European markets since May 2005.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.3 no.4
• /
• pp.35-42
• /
• 2010

This paper reviews the current studies about the current secure OS, security module and SELinux, and suggests Linux access control module that uses the user discriminating authentication, security authority inheritance of subjects and objects, reference monitor and MAC class process and real-time audit trailing using DB. First, during the user authentication process, it distinguishes the access permission IP and separates the superuser(root)'s authority from that of the security manager by making the users input the security level and the protection category. Second, when the subjects have access to the objects through security authority inheritance of subjects and objects, the suggested system carries out the access control by comparing the security information of the subjects with that of the objects. Third, this system implements a Reference Monitor audit on every current events happening in the kernel. As it decides the access permission after checking the current MAC security attributes, it can block any malicious intrusion in advance. Fourth, through the real-time audit trailing system, it detects all activities in the operating system, records them in the database and offers the security manager with the related security audit data in real-time.

• Journal of Electrical Engineering and Technology
• /
• v.1 no.2
• /
• pp.137-144
• /
• 2006

This paper proposes novel protection schemes for grid-connected distributed generation (DG) units using the fault location algorithm. The grid-connected DG would be influenced by abnormal distribution line conditions. Identification of the fault location for the distribution lines at the relaying point of DG helps solve the problems of the protection relays for DG. The proposed scheme first identifies fault locations using currents and voltages measured at DG and source impedance of distribution networks. Then the actual faulted feeder is identified, applying time-current characteristic curves (TCC) of overcurrent relay (OCR). The method considering the fault location and TCC of OCR might improve the performance of the conventional relays for DG. Test results show that the method prevents the superfluous operations of protection devices by discriminating the faulted feeder, whether it is a distribution line where DG is integrated or out of the line emanated from the substation to which the DGs are connected.

• Korean Journal of Agricultural Science
• /
• v.39 no.1
• /
• pp.111-116
• /
• 2012

Nondestructive evaluation of seed viability is one of the highly demanding technologies for seed production industry. Conventional seed sorting technologies, such as tetrazolium and standard germination test are destructive, time consuming, and labor intensive methods. Near infrared spectroscopy technique has shown good potential for nondestructive quality measurements for food and agricultural products. In this study, FT-NIR spectroscopy was used to classify normal and artificially aged lettuce seeds. The spectra with the range of 1100~2500 nm were scanned for lettuce seeds and analyzed using the principal component analysis(PCA) method. To classify viable seeds from nonviable seeds, a calibration modeling set was developed with a partial least square(PLS) method. The calibration model developed from PLS resulted in 98% classification accuracy with the Savitzky-Golay $1^{st}$ derivative preprocessing method. The prediction accuracy for the test data set was 93% with the MSC(Multiplicative Scatter Correction) preprocessing method. The results show that FT-NIR has good potential for discriminating non-viable lettuce seeds from viable ones.

• Journal of Sensor Science and Technology
• /
• v.23 no.6
• /
• pp.377-382
• /
• 2014

Detecting and segmenting diffuse targets in laser ranging data is a critical problem for tactical reconnaissance. In this study, we propose a new method that facilitates the characterization of diffuse irregularly shaped objects using "spin images," i.e., local 2D histograms of laser returns oriented in 3D space, and a clustering process. The proposed "cluster-based spin imaging" method resolves the problem of using standard spin images for diffuse targets and it eliminates much of the computational complexity that characterizes the production of conventional spin images. The direct processing of pre-segmented laser points, including internal points that penetrate through a diffuse object's topmost surfaces, avoids some of the requirements of the approach used at present for spin image generation, while it also greatly reduces the high computational time overheads incurred by searches to find correlated images. We employed 3D airborne range data over forested terrain to demonstrate the effectiveness of this method in discriminating the different geometric structures of individual tree clusters. Our experiments showed that cluster-based spin images have the potential to separate classes in terms of different ages and portions of tree crowns.

• Bulletin of the Korean Chemical Society
• /
• v.25 no.2
• /
• pp.177-181
• /
• 2004

A PVC membrane electrode for silver ion based on a new cone shaped calix[4]arene (CASCA) as membrane carrier was prepared. The electrode exhibits a Nernstian response for $Ag^+$ over a wide concentration range ($1.0{\times}10^{-1}-8.0{\times}10^{-6}$M) with a slope of 58.2 {\pm}$ 0.5 mV per decade. The limit of detection of the sensor is $5.0{\times}10^{-6}$M. The sensor has a very fast response time (~5 s) in the concentration range of ${\leq}=1.0{\times}10^{-3}$ M, and a useful working pH range of 4.0-9.5. The proposed sensor displays excellent discriminating ability toward $Ag^+$ ion with respect to common alkali, alkaline earth, transition and heavy metal ions. It was used as an indicator electrode in potentiometric titration of $Ag^+$ with EDTA and in direct determination of silver ion in wastewater of silver electroplating.