• The Journal of the Korea Contents Association
• /
• v.16 no.8
• /
• pp.427-434
• /
• 2016

This paper focuses on a real-time hardware processing by implementing the ARM Cortex-M4 based embedded system, using a conversion algorithm from a muscular sense to both visual and auditory elements, which recognizes rotations of a human body, directional changes and motion amounts out of human senses. As an input method of muscular sense, AHRS(Attitude Heading Reference System) was used to acquire roll, pitch and yaw values in real time. These three input values were converted into three elements of HSI color model such as intensity, hue and saturation, respectively. Final color signals were acquired by converting HSI into RGB color model. In addition, Three input values of muscular sense were converted into three elements of sound such as octave, scale and velocity, which were synthesized to give an output sound using MIDI(Musical Instrument Digital Interface). The analysis results of both output color and sound signals revealed that input signals of muscular sense were correctly converted into both color and sound in real time by the proposed conversion method.

• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.1
• /
• pp.77-85
• /
• 2014

Medicine-bottle classification algorithm to avoid medicine accidents must be robust to a geometric change such as rotation, size variation, location movement of the medicine bottles. In this paper, we propose an algorithm to classify the medicine bottles exactly in real-time by using SIFT(Scale Invariant Feature Transform) which is robust to the geometric change. In first, we classify medicine bottles by size using minimum boundary rectangle(MBR) of medicine bottles as a striking feature in order to classify the medicine bottles. We extract label region in the MBR and the region of interest(ROI) considering rotation. Then, we classify medicine bottles using SIFT for the extracted ROI. We also simplify the number of octave of SIFT in order to improve a process speed of SIFT. We confirm to classify all the medicine bottles exactly as a result of performance evaluation of the proposed algorithm about images of 250 medicine bottles. We also confirm to improve the process time more than twice the processing time by simplifying the number of octave of SIFT.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.207-215
• /
• 2014

In this paper, we propose a Micro Real-Time Control System (MRTCS) for decreasing the delay during interrupts processing and data transfer on sensor nodes. The MRTCS consists of a control, sensor nodes based on Controller Area Network (CAN) device. The control node was designed with Real Time Operating System (RTOS) on top of the small Micro Control Unit (sMCU). Sensor nodes have the CAN device without sMCU, which have multiple Digital Inputs, Outputs (DI/DO) and the CAN controller. We have evaluated with OCTAVE v3.6.4 from open source for system performance. Simulation results show that the system performance was increased through the delay reducing for interrupt processing and internal data transfer. We verify that a proposed MRTCS approach will be adapted to various real-time control system.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.5
• /
• pp.31-36
• /
• 2011

In this paper, Mel-Frequency Cepstral Coefficient (MFCC), Decorrelated Filter Bank (DFB), Octave-based Spectral Contrast (OSC), Zero-Crossing Rate (ZCR), and Spectral Contract/Roll-Off are combined as a set of multiple feature-vectors for the music genre classification system based on the Support Vector Machine (SVM) classifier. In the conventional system, feature vectors for the entire genre classes are normalized for the SVM model training and classification. However, in this paper, selected feature vectors that are compared based on the One-Against-One (OAO) SVM classifier are only used for normalization. Using OSC as a single feature-vector and the multiple feature-vectors, we obtain the genre classification rates of 60.8% and 77.4%, respectively, with the conventional normalization method. Using the proposed normalization method, we obtain the increased classification rates by 8.2% and 3.3% for OSC and the multiple feature-vectors, respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.3
• /
• pp.98-103
• /
• 2001

The binaural auditory system of human has the capability of differentiating the direction and distance of sound sources. This feature is well characterised in terms of the inter-aural intensity difference (IID), the inter-aural time difference (ITD) and/or the spectral shape difference (SSD) arising from the acoustic transfer of a sound source to the outer ears. This paper proposes an effective way of extracting the three sound perception factors (IID, ITD, SSD) from the head-related transfer functions (HRTF's) that depends on the direction and distance of the acoustic source from the listener. It includes the estimation method of the equivalent ITD and 1/3-octave band-based IID factors and their usage to locate a sound source in space. Subjective and objective tests were carried out to examine the effectiveness of the proposed methodology and its applicability to real sound systems. Those experimental results are illustrated in this paper.

• The Journal of the Korea Contents Association
• /
• v.15 no.12
• /
• pp.8-17
• /
• 2015

This paper presents a sound into color signal conversion using a colored-hearing synesthesia. The aim of the present paper is to implement a real-time conversion system which focuses on both hearing and sight which account for a great part of bodily senses. The proposed method of the real-time conversion of color into sound, in this paper, was simple and intuitive where scale, octave and velocity were extracted from MIDI input signals, which were converted into hue, intensity and saturation, respectively, as basic elements of HSI color model. In experiments, we implemented both the hardware system for delivering MIDI signals to PC and the VC++ based software system for monitoring both input and output signals, so we made certain that the conversion was correctly performed by the proposed method.

• International Journal of Highway Engineering
• /
• v.15 no.4
• /
• pp.95-105
• /
• 2013

PURPOSES: The purpose of this study is to research the influence of road traffic noise by road slope through the analysis of the field road traffic noise and determine consideration of road slope in the case of appling active noise cancellation. METHODS: This study measures vehicle's noise by the NCPX method at the three field sections such as uphill, downhill, and flatland. Total sound pressure and sound pressure level by the 1/3 octave band frequency are calculated through the raw field data. Total sound pressure level is compared by ANOVA test and T test statistically. The results obtained are compared in accordance with the road slope and the progress of the uphill section. RESULTS : The noise characteristic of early, medium, and last parts of uphill was found to be consistent when the vehicle was travelling uphill section. The result of statistical test, it was shown that total sound pressures are not different each other. According to the comparison by the geometry, sound pressure of the uphill section was higher than those of the flatland and downhill section in high frequency band. By the result of statistical test, total sound pressure are different according to geometry in the case of high vehicle speed. In the comparison result by road slope, each sound pressure level was found to be consistent in total frequency. However, total sound pressure proportionally increased according to road slope. CONCLUSIONS: It is found that the effect of road slope on noise generation was little in this experimental sites.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.234-242
• /
• 2019

In this paper, we propose a deep neural network which extracts SIFT feature points by determining whether the center pixel of a cropped image is a SIFT feature point. The data set of this network consists of a DIV2K dataset cut into $33{\times}33$ size and uses RGB image unlike SIFT which uses black and white image. The ground truth consists of the RobHess SIFT features extracted by setting the octave (scale) to 0, the sigma to 1.6, and the intervals to 3. Based on the VGG-16, we construct an increasingly deep network of 13 to 23 and 33 convolution layers, and experiment with changing the method of increasing the image scale. The result of using the sigmoid function as the activation function of the output layer is compared with the result using the softmax function. Experimental results show that the proposed network not only has more than 99% extraction accuracy but also has high extraction repeatability for distorted images.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.3
• /
• pp.229-236
• /
• 2020

In this paper, the tone of Daegeum, one of the most representative wind instruments of our country, was analyzed. Daegeum is widely used as Jeongak Daegeum and Sanjo Daegeum, which are played in royal and wind music, and Sanjo Daegeum is mainly played in Sanjo, Sinawi and folk music. The reason why the two pieces of music are being played in different music genres is due to the improvement of the length of the pipe and the location of the finger holes, allowing the Sanjo Daegeum to perform faster than Jeongak Daegeum, apply various techniques, and make the choice of musical instruments harmonized with music by making the difference in tone. For timber analysis of Jeongak Daegeum and Sanjo Daegeum, the composition of the overtones was visually verified through Spectrogram and Spectrum Analizer, in which the results of recordings were recorded by playing octave low, flat, and octave high positions with the same power. From this, Jeongak Daegeum, which is rich in low-pitched sound, harmonizes with solemn music such as royal music, and Sanjo Daegeum, which has a relatively clear high-pitched sound, is well suited to bright music such as solo music.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.4
• /
• pp.223-231
• /
• 2018

Recently, due to various environmental problems, blast tracks in tunnel are replaced with concrete tracks, but they have more adverse effects on noise than blast tracks so that additional noise measures are needed. Among these measures, sound-absorbing blocks start to be used due to its easy and quick installation. However, the performance of sound absorption blocks need to be verified under real environmental and operational conditions. In this paper, interior noise levels in KTX train cruising in Dalseong tunnel are measured before and after the installation of sound-absorbing blocks and the measured data are analyzed and compared. Additionally, noise reduction are estimated by modeling the high speed train, the tunnel and absorption blocks. Measurement devices and methods are used according to ISO 3381 and the equivalent sound pressure levels during the cruising time inside the tunnel are computed. In addition to overall SPLs(Sound Pressure Levels), 1/3-octave-band levels are also analyzed to account for the frequency characteristics of sound absorption and equipment noise in a cabin. In addition, to consider the effects of train cruising speeds and environmental conditions on the measurements, the measured data are corrected by using those measured during the train-passing through the tunnels located before and behind the Dalseong tunnel. Analysis of measured results showed that the maximum noise reduction of 6.8 dB (A) can be achieved for the local region where the sound-absorbing blocks are installed. Finally, through the comparison of predicted 1/3-octave band SPLs for the KTX interior noise with the measurements, the understanding of noise reduction mechanism due to sound-absorbing blocks is enhanced.