• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.2
• /
• pp.81-86
• /
• 2014

In this paper, we present an effective sound classification system for recognizing the real-time context of a smartphone user. Our system avoids unnecessary consumption of limited computational resource by filtering both silence and white noise out of input sound data in the pre-processing step. It also improves the classification performance on low energy-level sounds by amplifying them as pre-processing. Moreover, for efficient learning and application of HMM classification models, our system executes the dimension reduction and discretization on the feature vectors through k-means clustering. We collected a large amount of 8 different type sound data from daily life in a university research building and then conducted experiments using them. Through these experiments, our system showed high classification performance.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.2 no.1
• /
• pp.35-46
• /
• 1998

Structural damage is used to be modeled through reductions in the stiffness of structural elements for the purpose of damage estimation of structural system. In this study, the concept of joint damage is employed for more realistic damage assessment of a steel structure. The joint damage is estimated damage based on the mode shape informations using neural networks, The beam-to-column connection in a steel frame structure is represented by a rotational spring at the fixed end of a beam element. The severity of joint damage is defined as the reduction ratio of the connection stiffness with respect to the value of the intact joint. The concept of the substructural identification is used for the localized damage assessment in a large structure. The feasibility of the proposed method is examined using an example with simulated data. It has been found that the joint damages can be reasonably estimated for the case with the measurements of the mode vectors subjected to noise.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.9
• /
• pp.72-80
• /
• 2019

In this task, the tool dynamometer design and manufacture, and the Ansys S/W structural analysis program for tool attachment that satisfies the cutting force measurement requirements of the tool dynamometer system are used to determine the cutting force generated by metal cutting using 3-axis static structural analysis and the LabVIEW system. The cutting power in a cutting process using a milling tool for processing metals provides useful information for understanding the processing, optimization, tool status monitoring, and tool design. Thus, various methods of measuring cutting power have been proposed. The device consists of a strain-gauge-based sensor fitted to a new design force sensing element, which is then placed in a force reduction. The force-sensing element is designed as a symmetrical cross beam with four arms of a rectangular parallel line. Furthermore, data duplication is eliminated by the appropriate setting the strain gauge attachment position and the construction of a suitable Wheatstone full-bridge circuit. This device is intended for use with rotating spindles such as milling tools. Verification and machining tests were performed to determine the static and dynamic characteristics of the tool dynamometer. The verification tests were performed by analyzing the difference between strain data measured by weight and that derived by theoretical calculations. Processing test was performed by attaching a tool dynamometer to the MCT to analyze data generated by the measuring equipment during machining. To maintain high productivity and precision, the system monitors and suppresses process disturbances such as chatter vibration, imbalances, overload, collision, forced vibration due to tool failure, and excessive tool wear; additionally, a tool dynamometer with a high signal-to-noise ratio is provided.

• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2019.10a
• /
• pp.87-87
• /
• 2019

The consumption of herbal medicine and related products (herbal products) have increased in South Korea. At the same time the quality, safety, and efficacy of herbal products is being raised. Currently, the herbal products are standardized and controlled according to the requirements of the Korean Pharmacopoeia, the National Institute of Health and the Ministry of Public Health and Social Affairs. The validation of herbal products and their medicinal component is important, since many of these herbal products are composed of two or more medicinal plants. However, there are no tools to support the validation process. Interest in deep learning has exploded over the past decade, for herbal medicine using algorithms to achieve herb recognition, symptom related target prediction, and drug repositioning have been reported. In this study, individual images of four herbs (Panax ginseng C.A. Meyer, Atractylodes macrocephala Koidz, Poria cocos Wolf, Glycyrrhiza uralensis Fischer), actually sold in the market, were achieved. Certain image preprocessing steps such as noise reduction and resize were formatted. After the features are optimized, we applied GoogLeNet_Inception v4 model for herb image recognition. Experimental results show that our method achieved test accuracy of 95%. However, there are two limitations in the current study. Firstly, due to the relatively small data collection (100 images), the training loss is much lower than validation loss which possess overfitting problem. Secondly, herbal products are mostly in a mixture, the applied method cannot be reliable to detect a single herb from a mixture. Thus, further large data collection and improved object detection is needed for better classification.

• Journal of the Korea Safety Management & Science
• /
• v.17 no.3
• /
• pp.115-123
• /
• 2015

The study conducted statistical analysis of survey on the 239 workers participating in national Tower Crane installation/dismantlement in order to identify work environment and health hazard exposure of Tower Crane workers. Consequently for work related safety status of Tower Crane workers, the number of installation/dismantlement work was the highest at 15-20 times per month, and safety equipments were not arranged at work and they felt highly anxious when boarding on the Tower Crane. Furthermore, it is found that they feel anxious working in the influence of the weather, noise, vibration, wind, the sun ray, and structure characteristic. They have very low satisfaction in the insecureness of workplace and the work environment, and recognizes that their work affect highly on the health. 81.6% of workers have experienced accident at work, the cause of accidents were mainly due to poor work environment, and the health abnormality they have experienced were mostly fatigue and concentration reduction. For job stress, job demand and conflict in relationship were the highest sections. Total 66.5% of workers complained of musculoskeletal disorder related subjective symptom, and back pain patients were the highest of all groups.

• Journal of the Korean Society for Railway
• /
• v.19 no.4
• /
• pp.409-416
• /
• 2016

The contact force characteristic between the pantograph and the catenary wire represents the current collection quality of trains; it should be precisely controlled under international standard. Recently, a noise reduction cover has been installed around the pantograph of high speed trains. However, little study on the contact force by the pantograph cover has been conducted. In this study, the impact on the current collection performance of the pantograph cover was analyzed by dynamic contact force measurement using a next generation high speed train (HEMU-430X). As a result, it was confirmed that the attachment of a pantograph cover could lower the mean contact force by approximately 50N at 300km/h. In addition, the pure difference of the average contact force by the presence of pantograph cover, except for the static pressure, was measured and found to be up to 110N at 300km/h. It was also found that the standard deviation of the contact force of 3~5N could be changed by use of a pantograph cover.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.31-37
• /
• 2021

In this paper, we propose an outlier detection algorithm called C-SCGP to prevent the degradation of localization performance based on RSS (Received Signal Strength) and AOA (Angle of Arrival) in the presence of outliers in wireless sensor networks. Since the accuracy of target estimation can significantly deteriorate due to various cause of outliers such as malfunction of sensor, jamming, and severe noise, it is important to detect and filter out all outliers. The single cluster graph partitioning (SCGP) algorithm has been widely used to remove such outliers. The proposed continuous-SCGP (C-SCGP) algorithm overcomes the weakness of the SCGP that requires the threshold and computing probability of outliers, which are impratical in many applications. The results of numerical simulations show that the performance of C-SCGP without setting threshold and probability computation is the same performance of SCGP.

• Journal of the Korean Solar Energy Society
• /
• v.38 no.6
• /
• pp.51-63
• /
• 2018

Nowadays the bifacial PV system market and its applications are increasing rapidly. The performance of the bifacial PV system take advantage of its rear surface irradiance. Also, the ground albedo, PV module tilt and azimuth, PV module installation height, shading effect and module temperature are factors of bifacial PV system performance. This paper investigates how the performance of bifacial PV system is influenced by above factors. First, we analyzed the energy yield depending on PV module installation by simulation. Secondly, we compare energy performance evaluation of monofacial and bifacial module on different weather condition by experiment. Thirdly, we tested the albedo effect and checked operating characteristics using Dupont Tyvek material for the bifacial PV module. Fourthly, we check the shading effect of bifacial PV module on bypass diode operating. Finally, we applied the bifacial PV module in the nearby subway station for the noise reduction barrier using a qualified simulation program. In summary, we confirm that the energy performance superiority of the bifacial PV module has a lot of application use including road. Also, we have confirmed the bifacial module and inverter design should be considered by rear surface irradiance.

• Convergence Security Journal
• /
• v.18 no.4
• /
• pp.62-71
• /
• 2018

The rapid growth of virtual reality technology in the era of the 4th Industrial Revolution has accelerated scientification of combat training systems in addition to ICT(information and communications technology) in military field. Recently, research and development of simulators based on virtual reality have been actively conducted in order to solve sensitive issues such as increase of civil complaints due to the noise of a shooting range, prevention of shooting accident, and reduction of training cost. In this paper, we propose two key solutions: spatial synchronization method and modified point mass trajectory model with small angle approximation to overcome technical limitations of a current training simulator. A trainee who wears a haptic vest in a mixed reality environment built in MARS(medium-range assault rifle shooting simulator) is able to conduct not only precision shooting but also two-way engagement with virtual opponents. It is possible for trainee to receive more reliable evaluations in the MARS than an existing rifle simulator based on laser.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.2
• /
• pp.113-119
• /
• 2019

We have developed the multi-functioned friction measuring instrument for the previous research. In here, we improved the performance of friction measuring instrument by applying the adaptive smoothing method and analyzed the friction of plate and monitoring function of friction surface through scratch tests. We substituted lubricant steel plate to lubricant oil used for reducing the friction when fabricating steel plate because lubricant oil was regarded as one of the major causes for the environmental pollution. In particular, the functions of various plate such as galvannealed steel sheets were analyzed because friction coefficient could be changed depending on the type of organic/inorganic plate or state of coating layer. Therefore, we demonstrated that adaptive smoothing method could enhance the accuracy of measuring instrument which eliminate the noise. As a result of using the method, it showed the reduction rate 0.0417% for the friction coefficient 0.16.