• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.568-576
• /
• 2022

Automatic modulation classification(AMC) is a core technique in Software Defined Radio(SDR) platform that enables smart and flexible spectrum sensing and access in a wide frequency band. In this study, we propose a simple yet accurate deep learning-based method that allows AMC for variable-size radio signals. To this end, we design a classification architecture consisting of two Convolutional Neural Network(CNN)-based models, namely main and small models, which were trained on radio signal datasets with two different signal sizes, respectively. Then, for a received signal input with an arbitrary length, modulation classification is performed by augmenting the input samples using a self-replicating padding technique to fit the input layer size of our model. Experiments using the RadioML 2018.01A dataset demonstrated that the proposed method provides higher accuracy than the existing methods in all signal-to-noise ratio(SNR) domains with less computation overhead.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.312-318
• /
• 2022

This paper proposes a model which classifies the type of guns and information about sound source location using deep neural network. The proposed classification model is composed of convolutional neural networks (CNN) and long short-term memory (LSTM). For training and test the model, we use the Gunshot Audio Forensic Dataset generated by the project supported by the National Institute of Justice (NIJ). The acoustic signals are transformed to Mel-Spectrogram and they are provided as learning and test data for the proposed model. The model is compared with the control model consisting of convolutional neural networks only. The proposed model shows high accuracy more than 90 %.

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.273-279
• /
• 2023

The use of line memory is essential for image filtering in image processing hardware. After input data is stored in line memory, filtering is performed after synchronization to use the stored data. A sync generator is used for synchronization, and in the case of a conventional sync generator, the input sync signal is delayed by one row of the input image. If a signal delayed by two rows is required, it is necessary to connect two modules. This approach increases the size of the hardware and cannot be designed efficiently. In this paper, we propose a sync generator that generates multiple types of delayed signals by adding a finite state machine. The hardware design was coded in Verilog HDL, and performance is verified by applying it to image processing hardware using field programmable gate array board.

• Journal of IKEEE
• /
• v.26 no.1
• /
• pp.1-9
• /
• 2022

In order to secure the reliability of the power system and to increase the penetration level of distributed energy resources (DERs), requirements such as IEEE 1547 have been revised to strengthen the grid connection standards for DER. This paper proposes a control scheme for smart inverter functions based on IEEE 1547-2018 that satisfy these standards, and introduces a power HILS-based test platform built for verification of smart inverter. Among the smart inverter functions, Volt-var and Frequency-watt allow the curve to be set from the upper level to comply with the interoperability and operation time of enable signals for each function are controlled by references from the upper level. According to the requirement, Volt-var and Frequency-watt are performed via power HILS platform and verified through the measurement results that all of the specified type tests were satisfied.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.2
• /
• pp.219-228
• /
• 2022

One of the most pressing and demanding issues today in the conditions of widespread transformation and digitalization of spheres of human activity is information security and ensuring the integrity of data. The main research and development in the field of information security is aimed at improving efficiency and rationalization. One of the main means of data transmission and operation of information complexes are fiber-optic systems. To date, there have been incidents of illegal intrusion and theft of information, passing through this type of communication. Thus, today there is a problem associated with insufficient information security in fiber-optic data transmission systems. One of the most effective tools to counter acts of illegal interference in systems are artificial intelligence and cryptographic algorithms of information protection. It is the symbiosis of these two tools that can qualitatively improve the level of information security in fiber-optic data transmission systems. Thus, the authors of this article pursue the goal associated with the description of an innovative system for protecting information from violations in fiber-optic data transmission systems based on the integration of intelligent cryptographic algorithms.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.845-850
• /
• 2023

In this paper, we propose a method for diagnosing ball bearing vibration using transfer learning. STFT, which can analyze vibration signals in time-frequency, was used as input to CNN to diagnose failures. In order to rapidly learn CNN-based deep artificial neural networks and improve diagnostic performance, we proposed a transfer learning-based deep learning learning technique. For transfer learning, the feature extractor and classifier were selectively learned using a VGG-based image classification model, the data set for learning was publicly available ball bearing vibration data provided by Case Western Reserve University, and performance was evaluated by comparing the proposed method with the existing CNN model. Experimental results not only prove that transfer learning is useful for condition diagnosis in ball bearing vibration data, but also allow other industries to use transfer learning to improve condition diagnosis.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.677-682
• /
• 2023

A large number of motors and sensors are used to drive a humanoid robot. In order to solve the wiring problem that occurs when connecting multiple actuators, a controller based on a communication network has been used, and CAN, which is advantageous in terms of cost and a highly reliable communication protocol, was mainly used. In terms of the structure of the controller, a torque control type structure that is easy to implement an advanced algorithm into the upper controller is preferred. In this case, the low communication bandwidth of CAN becomes a problem, and in order to obtain sufficient communication bandwidth, a communication network is configured by separating into a plurality of CAN networks. In this study, a stability analysis on transmission time delay is performed for a multi-motor control system in which high-speed FlexRay and low-speed CAN communication networks are hierarchically connected in order to obtain a high communication bandwidth, and sensor information and driving signals are delivered within the allowed transmission time. The proposed hierarchical network-based control system is expected to improve control performance because it can implement multiple motor control systems with a single network.

• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.17-22
• /
• 2023

Brain-Machine Interfaces(BMI) are interfaces that control machines by decoding brainwaves, which are electrical signals generated from neural activities. Although BMIs can be applied in various fields, their widespread usage is hindered by the low portability of the hardware required for brainwave measurement and decoding. To address this issue, previous research proposed a brain-machine interface system based on the Internet of Things (IoT) using cloud computing. In this study, we developed and tested an application that uses brainwaves to control the Pong game, demonstrating the real-time usability of the system. The results showed that users of the proposed BMI achieved scores comparable to optimal control artificial intelligence in real-time Pong game matches. Thus, this research suggests that IoT-based brain-machine interfaces can be utilized in a variety of real-time applications in everyday life.

• Journal of the Korean Society of Safety
• /
• v.38 no.5
• /
• pp.1-7
• /
• 2023

This study analyzes the operational characteristics of 311 aged and non-aged residual current circuit breakers (RCCBs) in low-voltage consumer contexts. It investigates the influence of external temperature and harmonics based on the rated current multiples. To simulate temperature variations, a convectional oven was used around the circuit breakers. Additionally, the generation of harmonic reference signals and data measurement for overcurrent experiments were conducted using NI SCXI, myDAQ, and LabVIEW. An observation revealed that as the ambient temperature increased, the operating time of RCCBs decreased in the time delay region. This was attributed to the faster response or bending of the bimetal, which is the tripping element. However, aged RCCBs encountered challenges with tripping outside the protective curve. The operating time of the circuit breakers exhibited an acceleration influenced by the order and content of harmonic currents, potentially leading to malfunctions. Aged RCCBs demonstrated faster operating times than their non-aged counterparts. However, the difference in operating time varied based on the manufacturer's and operating environment of the RCCBs. Frequent malfunctions of RCCBs can result in power outages. In cases where these circuit breakers fail to operate, they can lead to secondary damages, including electrical fires and shocks. Consequently, it is imperative to consider the operating environment of RCCBs and provide appropriate replacement cycles to mitigate these risks.

• Nuclear Engineering and Technology
• /
• v.55 no.12
• /
• pp.4570-4575
• /
• 2023

Noise and Radio-frequency interference or RFI causes a significant restriction on the Free induction Decay or FID signal detection of the Nuclear Quadrupole Resonance procedure. Therefore, using this method in non-isolated environments such as industry and ports requires extraordinary measures. For this purpose, noise reduction algorithms and increasing signal-to-noise-and-interference ratio or SNIR have been used. In this research, sodium nitrite has been used as a sample and algorithms have been tested in a non-isolated environment. The resonant frequencies for the 150 g of test sample were measured at 303 K at about 1 MHz and 3.4 MHz. The main novelty in this study was, (1) using two types of antennas in the receiver to improve adaptive noise and interference cancellation, (2) using a separate helical antenna in the transmitter to eliminate the duplexer, (3) estimating the noise before sending the pulse to calculate the weighting factors and reduce the noise by adaptive noise cancellation, (3) reject the interference by blanking algorithm, (4) pulse integration in the frequency domain to increase the SNR, and (5) increasing the detection speed by new pulse integration technique. By interference rejection and noise cancellation, the SNIR is improved to 9.24 dB at 1 MHz and to 7.28 dB at 3.4 MHz, and by pulse integration 44.8 dB FID signal amplification is achieved, and the FID signals are detected at 1.057 MHz and 3.402 MHz at room temperature.