• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.5
• /
• pp.2141-2155
• /
• 2020

In order to meet the requirements of background change, illumination variation, moving shadow interference and high accuracy in object detection of moving camera, and strive for real-time and high efficiency, this paper presents an object detection algorithm based on sparse approximation recursion and sparse coding migration in subspace. First, low-rank sparse decomposition is used to reduce the dimension of the data. Combining with dictionary sparse representation, the computational model is established by the recursive formula of sparse approximation with the video sequences taken as subspace sets. And the moving object is calculated by the background difference method, which effectively reduces the computational complexity and running time. According to the idea of sparse coding migration, the above operations are carried out in the down-sampling space to further reduce the requirements of computational complexity and memory storage, and this will be adapt to multi-scale target objects and overcome the impact of large anomaly areas. Finally, experiments are carried out on VDAO datasets containing 59 sets of videos. The experimental results show that the algorithm can detect moving object effectively in the moving camera with uniform speed, not only in terms of low computational complexity but also in terms of low storage requirements, so that our proposed algorithm is suitable for detection systems with high real-time requirements.

• Journal of the Korean Society for Railway
• /
• v.9 no.6 s.37
• /
• pp.746-752
• /
• 2006

The major objective of this study is to investigate the dynamic behavior evaluation of split PC sleepers for railway turnout by the field test. In railway engineering, a turnout is necessary to allow a vehicle to move from one track to another. So, turnout is required very complex railway technologies such as lolling stock, track. In reference to conventional line speed-up and improvement railway, accurate assembly of turnout affects travel ins qualify of turnout area and running safety. Because of heavy weight and a large volume of the long sleeper used to turnout and car limit, transport and the prerequisite for trouble-free transport of the factory pre-assembled major turnout components is achieved through division of long sleepers. The one of the advantages for using a split sleeper is to reduce the dynamic vibration according to the information of developed nations. Therefore, we investigate the characteristic of dynamic behaviors of split sleepers which are adopted for the first time to improve performance of turnout From the field test results of the split sleeper, it is evaluated that the modification of weight, material and stiffness compared with wood sleeper is very effective for the ballast safety. However, the decrease in vibration of split sleeper was not found out.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.65 no.2
• /
• pp.77-83
• /
• 2016

The electric quality of train is represented by voltage and current harmonics at PT(Ratio 25,000/15/[V]) which is located between pantograph and primary winding of train transformer. In this paper, voltage and current harmonics were measured on the test EMU(electric multiple unit)train with maximum speed of 180km/h in existing railway lines(chungbuk, Taeback, Honam). As a results of test, it is found that the electric quality of train depends on the mostly operation conditions which is accelerating mode and braking mode on each sections. Voltage THD is above all 3[%] and current harmonics is monitored from lowest Harmonic to highest Harmonic in case of accelerating mode. But, highest current harmonics is not monitored in case of breaking mode. The results in this paper can help to stabilize the power device and power converter of the test EMU train.

• Journal of Advanced Marine Engineering and Technology
• /
• v.9 no.2
• /
• pp.159-169
• /
• 1985

The calculation of torsional vibration for marine diesel engine propulsion shafting is normally carried out by equalizing exciting energy to damping energy, or using the dynamic magnifier. But, with these methods, the vibration amplitudes are calculated only for resonance points and vibration amplitudes of other running speeds of engine are determined by the estimation. Recently, many energy-saving ships have been built and on these ships, two-stroke, supercharged, super-long stroke diesel engines which have a small number of cylinders are usually installed. In these cases, the first order critical-torsional vibrations of these engine shaftings appear ordinarily near the MCR speed and the stress amplitudes of their vibration skirts exceed the limit stress defined by the rules of classification society. To predict the above condition in the design stage, the synthesized vibration amplitudes of all orders which are summed up according to their phase angles must be calculated from the drawings of propulsion shaft systems. In this study, a theoretical method to fulfill the above calculation is derived and a computer program is developed according to the derived method. And a shafting system of two-stroke, super-long stroke diesel engine which was installed in a bulk carrier is analyzed with this method. The measured values of this engine shafting are compared with those of calculated results and they show a fairly good agreement.

• Smart Structures and Systems
• /
• v.21 no.5
• /
• pp.549-559
• /
• 2018

The dynamic behaviors of the bridge structures have great effects on the comfortability and safety of running high-speed trains, which can also reflect the structural degradation. This paper aims to reveal the characteristics of the dynamic behaviors induced by train loadings for a combined highway and railway bridge. Monitoring-based analysis of the acceleration and dynamic displacement of the bridge girder is carried out. The effects of train loadings on the vertical acceleration of the bridge girder are analyzed; the spatial variability of the train-induced lateral girder displacement is studied; and statistical analysis has been performed for the daily extreme values of the train-induced girder deflections. It is revealed that there are great time and spatial variabilities for the acceleration induced by train loadings for the combined highway and railway cable-stayed bridge. The daily extreme values of the train-induced girder deflections can be well fitted by the general extreme value distribution.

• International Journal of Contents
• /
• v.16 no.3
• /
• pp.1-17
• /
• 2020

Human motion recognition is essential for user-centric services such as surveillance-based security, elderly condition monitoring, exercise tracking, daily calories expend analysis, etc. It is typically based on the movement data analysis such as the acceleration and angular velocity of a target user. The existing motion recognition studies are only intended to measure the basic information (e.g., user's stride, number of steps, speed) or to recognize single motion (e.g., sitting, running, walking). Thus, a new mechanism is required to identify the transition of single motions for assessing a user's consecutive motion more accurately as well as recognizing the user's body and surrounding situations arising from the motion. Thus, in this paper, we collect the human movement data through Android smartphones in real time for five targeting single motions and propose a mechanism to recognize a consecutive motion including transitions among various motions and an occurred situation, with the state transition model to check if a vulnerable (life-threatening) condition, especially for the elderly, has occurred or not. Through implementation and experiments, we demonstrate that the proposed mechanism recognizes a consecutive motion and a user's situation accurately and quickly. As a result of the recognition experiment about mix sequence likened to daily motion, the proposed adoptive weighting method showed 4% (Holding time=15 sec), 88% (30 sec), 6.5% (60 sec) improvements compared to static method.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.13 no.1
• /
• pp.40-47
• /
• 1989

Alternator noises are composed of magnetic noise, mechanical noise, and ventilation noise. These noises depend on the design of magnetic parts and fans, the machining accuracy of each element, and assembled conditions. In running alternator there are various exciting forces which can generate noises and vibrations. In order to identify the noise sources of the alternator, the characteristics of noises and vibrations are analyzed as rotating speed is increased. And the experiment for structural vibration is carried out. From results of experimental study, the noise sources are identified and their contributions to the overall noise level are investigated. Their results can lead the instruction to the noise reduction on the alternator.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.4 s.193
• /
• pp.84-92
• /
• 2007

Dynamic process planning requires not only more flexible capabilities of a CAPP system but also higher utility of the generated process plans. In order to meet the requirements, this paper develops an algorithm that can select machines for the machining operations by calculating the machine loads. The developed algorithm is based on the multi-objective genetic algorithm that gives rise to a set of optimal solutions (in general, known as the Pareto-optimal solutions). The objective is to satisfy both the minimization number of part movements and the maximization of machine utilization. The algorithm is characterized by a new and efficient method for nondominated sorting through K-means algorithm, which can speed up the running time, as well as a method of two stages for genetic operations, which can maintain a diverse set of solutions. The performance of the algorithm is evaluated by comparing with another multiple objective genetic algorithm, called NSGA-II and branch and bound algorithm.

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.5
• /
• pp.572-577
• /
• 2011

Curve squealing of inter-city railway vehicle is a noise with high acoustic pressure and rather narrow frequency spectra. This noise turns out to be very annoying for the people living in the neighborhood of locations and the passenger in railway vehicle where this phenomenon occurs. Squealing is caused by a self-exited stick-slip oscillation in the wheel-rail contact. Curve squeal noise of railway vehicles that passed by a factor of the speed limit, so to overcome in order to improve running performance is one of the largest technology. In the present paper, characteristic of squeal noise behavior at the Hanvit-200 tilting train test-site. Curve squealing of railway wheels/rail contact occurs in R400~ R800 curves with a frequency range of about 4~11 kHz. If the curve is less than the radius of wheel frail contact due to |left-right| noise level difference (dBA) shows a significant effect of squeal noise were more likely.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2003.11a
• /
• pp.85-90
• /
• 2003

Although wear resistance of material improves with increasing its hardness, it is known that the wear resistance of steel is varied with hardness of counter material. In this context, wear properties of steel must be depended on the difference of hardness between the testpiece and the counter material. In this study, using the pin-on-disc type wear machine, annealed carbon steels were tested against ahoy tool steels with various levels of hardness. Then the changes of wear properties of carbon steel according to the hardness of counter material were investigated and the morphology of worn surface after test were evaluated. The results indicate that if there are no remarkable difference of hardness between them, wear resistance of carbon steel in running-in wear decreases with increasing the hardness of counter material. However, its wear properties at the range of high sliding speed have no relation with hardness of counter material. It is clear that wear properties is influenced by the formation of oxide of steel on their worn surface during wear.