• International Journal of Computer Science & Network Security
• /
• v.23 no.6
• /
• pp.27-34
• /
• 2023

This paper proposed an Inter-Carrier-Interference (ICI) Canceling Orthogonal Frequency Division Multiplexing (OFDM) receiver for 5G mobile system to support 500 km/h linear motor high speed terrestrial transportation service. A receiver in such high-speed train sees the transmission channel which is composed of multiple Doppler-shifted propagation paths. Then, a loss of sub-carrier orthogonality due to Doppler-spread channels causes ICI. The ICI Canceler is realized by the following three steps. First, using the Demodulation Reference Symbol (DMRS) pilot signals, it analyzes three parameters such as attenuation, relative delay, and Doppler-shift of each multi-path component. Secondly, based on the sets of three parameters, Channel Transfer Function (CTF) of sender sub-carrier number 𝒏 to receiver sub-carrier number 𝒍 is generated. In case of 𝒏≠𝒍, the CTF corresponds to ICI factor. Thirdly, since ICI factor is obtained, by applying ICI reverse operation by Multi-Tap Equalizer, ICI canceling can be realized. ICI canceling performance has been simulated assuming severe channel condition such as 500 km/h, 2 path reverse Doppler Shift for QPSK, 16QAM, 64QAM and 256QAM modulations. In particular, for modulation schemes below 16QAM, we confirmed that the difference between BER in a 2 path reverse Doppler shift environment and stationary environment at a moving speed of 500 km/h was very small when the number of taps in the multi-tap equalizer was set to 31 taps or more. We also confirmed that the BER performance in high-speed mobile communications for multi-level modulation schemes above 64QAM is dramatically improved by the use of a multi-tap equalizer.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.93-99
• /
• 2019

In this paper, we propose a smart meter that uses GRU model, which is one of artificial neural networks, for the efficient energy management. We collected power consumption data that train GRU model through the proposed smart meter. The implemented smart meter has automatic power measurement and real-time observation function and load control function through power consumption prediction. We determined a reference value to control the load by using Root Mean Squared Error (RMS), which is one of performance evaluation indexes, with 20% margin. We confirmed that the smart meter with automatic load control increases the efficiency of energy management.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.3
• /
• pp.401-406
• /
• 2021

Recently, mean-teacher models based on convolutional recurrent neural networks are popularly used in audio event detection. The mean-teacher model is an architecture that consists of two parallel CRNNs and it is possible to train them effectively on the weakly-labelled and unlabeled audio data by using the consistency learning metric at the output of the two neural networks. In this study, we tried to improve the performance of the mean-teacher model by using additional derivative features of the log-mel spectrum. In the audio event detection experiments using the training and test data from the Task 4 of the DCASE 2018/2019 Challenges, we could obtain maximally a 8.1% relative decrease in the ER(Error Rate) in the mean-teacher model using proposed derivative features.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.293-302
• /
• 2016

Since the electricity is produced and consumed simultaneously, predicting the electric load and securing affordable electric power are necessary for reliable electric power supply. In particular, a university campus is one of the highest power consuming institutions and tends to have a wide variation of electric load depending on time and environment. For these reasons, an accurate electric load forecasting method that can predict power consumption in real-time is required for efficient power supply and management. Even though various influencing factors of power consumption have been discovered for the educational institutions by analyzing power consumption patterns and usage cases, further studies are required for the quantitative prediction of electric load. In this paper, we build an electric load forecasting model by implementing and evaluating various machine learning algorithms. To do that, we consider three building clusters in a campus and collect their power consumption every 15 minutes for more than one year. In the preprocessing, features are represented by considering periodic characteristic of the data and principal component analysis is performed for the features. In order to train the electric load forecasting model, we employ both artificial neural network and support vector machine. We evaluate the prediction performance of each forecasting model by 5-fold cross-validation and compare the prediction result to real electric load.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.141-148
• /
• 2021

In some intersections or busy traffic roads, there are more pedestrians in a specific period of time, and there are many traffic accidents caused by road congestion. Especially at the intersection where there are schools nearby, it is particularly important to protect the traffic safety of students in busy hours. In the past, when designing traffic lights, the safety of pedestrians was seldom taken into account, and the identification of motor vehicles and traffic optimization were mostly studied. How to keep the road smooth as far as possible under the premise of ensuring the safety of pedestrians, especially students, will be the key research direction of this paper. This paper will focus on person, motorcycle, bicycle, car and bus recognition research. Through investigation and comparison, this paper proposes to use YOLO v4 network to identify the location and quantity of objects. YOLO v4 has the characteristics of strong ability of small target recognition, high precision and fast processing speed, and sets the data acquisition object to train and test the image set. Using the statistics of the accuracy rate, error rate and omission rate of the target in the video, the network trained in this paper can accurately and effectively identify persons, motorcycles, bicycles, cars and buses in the moving images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.4
• /
• pp.698-706
• /
• 2016

In order to move mobile robots to desired locations in a minimum time, optimal control problems have to be solved; however, their analytic solutions are almost impossible to obtain due to robot nonlinear equations. This paper presents a method to get optimal control gains of mobile robots using genetic algorithms. Since the optimal control gains of mobile robots depend on the initial conditions, the initial condition range is discretized to form some grid points, and genetic algorithms are applied to provide the optimal control gains for the corresponding grid points. The optimal control gains for general initial conditions may be obtained by use of neural networks. So the optimal control gains and the corresponding grid points are used to train neural networks. The trained neural networks can supply pseudo-optimal control gains. Finally simulation studies have been conducted to verify the effectiveness of the method presented in this paper.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.4
• /
• pp.688-697
• /
• 2017

It is very difficult to solve mathematically the optimal control problem for non - linear mobile robots to move to target points with minimum energy related to velocity, acceleration and angular velocity in minimum time. This paper proposes a method to obtain optimal control gains with which mobile robots move with minimum energy related to velocity, acceleration and angular velocity in minimum time using genetic algorithms. Mobile robots are non - linear systems so that their optimal control gains depend on initial positions. Hence initial positions are divided into some partition points and optimal control gains are obtained at each partition point with genetical algorithms. These optimal control gains are used to train neural networks that generate proper control gains at arbitrary initial position. Finally computer simulation studies have been conducted to verify the effectiveness of the method proposed in this paper.

• Journal of the Korean Society for Railway
• /
• v.15 no.5
• /
• pp.454-458
• /
• 2012

The CBTC(Communication based Train Control) and WPAN(Wireless Personal Area Network) systems employed on 2.4GHz ISM band wireless networks provide complementary service within the same environment. Coexistence between the networks will be impaired if the mutual packets are uncertainty associated the timing or gaussian distance. This paper analyzes the impact of the mutual interference and proposed method to minimize the effect of the WPAN system signals on CBTC system. The performance analysis is illustrated by examining the symbol error rate versus signal to noise interference ratio in terms of carrier frequency offset. The method contributes to reduce the symbol error rate drastically. However it can't be a fundamental solution for the impact on the interference problem. It may be needed for railway only frequency after checking the problems of the current railway frequency.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.10
• /
• pp.1300-1306
• /
• 2018

The purpose of this study is to see possibility of Char2Vec as alternative of Word2Vec that most famous word embedding model in Sentence Similarity Measure Problem by Deep-Learning. In experiment, we used the Siamese Ma-LSTM recurrent neural network architecture for measure similarity two random sentences. Siamese Ma-LSTM model was implemented with tensorflow. We train each model with 200 epoch on gpu environment and it took about 20 hours. Then we compared Word2Vec based model training result with Char2Vec based model training result. as a result, model of based with Char2Vec that initialized random weight record 75.1% validation dataset accuracy and model of based with Word2Vec that pretrained with 3 million words and phrase record 71.6% validation dataset accuracy. so Char2Vec is suitable alternate of Word2Vec to optimize high system memory requirements problem.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.4
• /
• pp.79-86
• /
• 2019

This paper describes a time-series data prediction based on artificial neural networks (ANN). In this study, a batch based ANN model and a stochastic ANN model have been implemented using TensorFlow libraries. Each model are evaluated by comparing training and testing errors that are measured through experiment. To train and test each model, tax dataset was used that are collected from the government website of indiana state budget agency in USA from 2001 to 2018. The dataset includes tax incomes of individual, product sales, company, and total tax incomes. The experimental results show that batch model reveals better performance than stochastic model. Using the batch scheme, we have conducted a prediction experiment. In the experiment, total taxes are predicted during next seven months, and compared with actual collected total taxes. The results shows that predicted data are almost same with the actual data.