• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2014.10a
• /
• pp.353-354
• /
• 2014

An active vibration control technique of a time-varying cantilever beam is proposed in this study. A simple in-house coil sensor instead of expensive commercial sensors was used to measure the vibrational displacement of the beam. Active band pass filters and artificial neutral net works detect the frequencies, amplitudes, and phases of the main vibration mode. The time constants of the low pass filter representing the positive position feedback controller are updated in real-time, which generates the control voltage input to actuate the piezoelectric actuator and suppress the vibration. An experiment was successfully performed to verify the algorithm for a cantilever beam, which fundamental natural frequency arbitrarily varies between 9 Hz ~ 18 Hz. The present active vibration suppression technique can be applied to variety of structures which undergoes large variation of dynamic characteristics while operating.

• Nuclear Engineering and Technology
• /
• v.54 no.12
• /
• pp.4684-4692
• /
• 2022

Radionuclide identification is an important part of the nuclear material identification system. The development of artificial intelligence and machine learning has made nuclide identification rapid and automatic. However, many methods directly use existing deep learning models to analyze the gamma-ray spectrum, which lacks interpretability for researchers. This study proposes an explainable radionuclide identification algorithm based on the convolutional neural network and class activation mapping. This method shows the area of interest of the neural network on the gamma-ray spectrum by generating a class activation map. We analyzed the class activation map of the gamma-ray spectrum of different types, different gross counts, and different signal-to-noise ratios. The results show that the convolutional neural network attempted to learn the relationship between the input gamma-ray spectrum and the nuclide type, and could identify the nuclide based on the photoelectric peak and Compton edge. Furthermore, the results explain why the neural network could identify gamma-ray spectra with low counts and low signal-to-noise ratios. Thus, the findings improve researchers' confidence in the ability of neural networks to identify nuclides and promote the application of artificial intelligence methods in the field of nuclide identification.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.247-250
• /
• 2008

The paper presents the advanced radiometric calibration method, called the lRCM (Iterative Radiometric Calibration Method), in order to avoid an operational constraint (solar source) for calibration. The IRCM assumes that an optical instrument is equipped with a filter assembly which consists of same band filters with different transmission ratios. Given all the noise sources (including the artificial one caused by the filters) of an image sensor, the noncentral ${\chi}^2$ distribution of the output result is induced by the approach of a noise PDF (Power Density Function). Finally, the radiometric calibration problem is transformed into equating two independent relations for the image sensor gains through the specified distribution.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.2
• /
• pp.133-139
• /
• 2013

This paper proposes a vision-based indoor localization method for autonomous vehicles. A single upward-facing digital camera was mounted on an autonomous vehicle and used as a vision sensor to identify artificial landmarks and any natural corner features. An interest point detector was used to find the natural features. Using an optical flow detection algorithm, information related to the direction and vehicle translation was defined. This information was used to track the vehicle movements. Random noise related to uneven light disrupted the calculation of the vehicle translation. Thus, to estimate the vehicle translation, a Kalman filter was used to calculate the vehicle position. These algorithms were tested on a vehicle in a real environment. The image processing method could recognize the landmarks precisely, while the Kalman filter algorithm could estimate the vehicle's position accurately. The experimental results confirmed that the proposed approaches can be implemented in practical situations.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.143-151
• /
• 2012

A new data-driven method for the design of a blind modulation frequency filter that suppresses the slow-varying noise components is proposed. The proposed method is based on the temporal local decorrelation of the feature vector sequence, and is done on an utterance-by-utterance basis. Although the conventional modulation frequency filtering approaches the same form regardless of the task and environment conditions, the proposed method can provide an adaptive modulation frequency filter that outperforms conventional methods for each utterance. In addition, the method ultimately performs channel normalization in a feature domain with applications to log-spectral parameters. The performance was evaluated by speaker-independent isolated-word recognition experiments under additive noise environments. The proposed method achieved outstanding improvement for speech recognition in environments with significant noise and was also effective in a range of feature representations.

• Current Optics and Photonics
• /
• v.7 no.6
• /
• pp.708-713
• /
• 2023

A robust all-fiber nonlinear amplifying loop-mirror-based mode-locked femtosecond laser is demonstrated. Power-dependent nonlinear phase shift in a Sagnac loop enables stable and power-efficient mode-locking working as an artificial saturable absorber. The pump power is adjusted to achieve the lowest intensity noise for stable long-term operation. The minimum pump power for mode-locking is 180 mW, and the optimal pump power is 300 mW. The lowest integrated root-mean-square relative intensity noise of a free-running mode-locked laser is 0.009% [integration bandwidth: 1 Hz-10 MHz]. The long-term repetition-rate instability of a free-running mode-locked laser is 10^-7 over 1,000 s averaging time. The repetition-rate phase noise scaled at 10-GHz carrier is -122 dBc/Hz at 10 kHz Fourier frequency. The demonstrated method can be applied as a seed source in high-precision real-time mid-infrared molecular spectroscopy.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2005.05a
• /
• pp.945-948
• /
• 2005

Mobile computing devices are becoming increasingly prevalent in a huge range of physical area, offering a considerable market opportunity. The focus of this paper is on the development of a platform of fault diagnosis system integrating with personal digital assistant (PDA). An improvement of induction machine rotor fault diagnosis based on AI algorithms approach is presented. This network system consists of two parts; condition monitoring and fault diagnosis by using Artificial Intelligence algorithm. LabVIEW allows easy interaction between acquisition instrumentation and operators. Also it can easily integrate AI algorithm. This paper presents a development environment fur intelligent application for PDA. The introduced configuration is a LabVIEW application in PDA module toolkit which is LabVIEW software.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.14 no.2
• /
• pp.57-62
• /
• 1978

When fisherman use the boat seine net to catch anchovy, a large noise (drum can, small drum and small gong) is used to scare the anchovy school along the wing nets, and into the bag net were they are caught. We want to know how much of an effect these s:mnds have on forceing the anchovy school towards the bag net. The underwater sounds of ancho\'y, drum can, small drum and small gong were analyzed in the labroatory. The behavioral responeses to the playback sounds of anchovy feeding and sounds of artificial instruments were also investigated. The feeding and artificial sounds of the samples were recorded by a tape recorder through a hydrophone in an anechoic aquarium. The sound intensity level was measured by means of a sound level meter in an anechoic chamber. The frequency and intensity of various sounds were analyzed with an analyzing system consisting of a ~-octave filter set, a high speed level recorder, an amplifier and an oscilloscope. The most successful recording was edited into a 9 to 10 second sound track and was repeated in a sequence of 9 to 10 second intervals. The sequence was then reproduced into an anechoic aquarium through the underwater speaker. The results of investigation are as follows; 1. The frequency of the feeding sound was 63~80Hz, and the pressure level produced was less than 32db. 2. The frequencies of the artificial sounds were 315~ 1,OOOHz, and the pressure levels were 88~95 db in the air. 3. When a hydrophone was placed 70cm below the surface with artificial sounds (drum can, small drum and small gong) produced 1 meter above the surface, the pressure level decreased about 30db. 4. The feeding sound was ineffective in attracting the anchovy, because of interference from ambient noise. 5. The artificial sounds had such a small effect on the anchovy's that they could not be used in ocean fisheries.

• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.201-207
• /
• 2024

Voice is a critical element of human communication, and the development of speech recognition models is one of the significant achievements in artificial intelligence, which has recently been applied in various aspects of human life. The application of speech recognition models in the military field is also inevitable. However, before artificial intelligence models can be applied in the military, it is necessary to research their vulnerabilities. In this study, we evaluates the military applicability of the multilingual speech recognition model "Whisper" by examining its vulnerabilities to battlefield noise, white noise, and adversarial attacks. In experiments involving battlefield noise, Whisper showed significant performance degradation with an average Character Error Rate (CER) of 72.4%, indicating difficulties in military applications. In experiments with white noise, Whisper was robust to low-intensity noise but showed performance degradation under high-intensity noise. Adversarial attack experiments revealed vulnerabilities at specific epsilon values. Therefore, the Whisper model requires improvements through fine-tuning, adversarial training, and other methods.

• Journal of KSNVE
• /
• v.6 no.5
• /
• pp.555-565
• /
• 1996

This paper is concerned with the theoretical and experimental study on the force control of a miniature robotic finger that grasps an object at three other positions with the fingertip. The artificial finger is a uniform flexible cantilever beam equipped with a distributed set of compact grasping force sensors. Control action is applied by a piezoceramic bimorph strip placed at the base of the finger. The mathematical model of the assembled electro- mechanical system is developed. The distributed sensors are described by a set of concentrated mass-spring system. The formulated equations of motion are then applied to a control problem in which the finger is commanded to grasp an object. The H$_{\infty}$-controller is introduced to drive the finger. The usefulness of the proposed control technique is verified by simulation and experiment..