• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.685-692
• /
• 2024

In this paper, we propose a new CNN model to improve the recognition performance of command voice signals. This method obtains a spectrogram image after performing a short-time Fourier transform (STFT) of the input signal and improves command recognition performance through supervised learning using a CNN model. After Fourier transforming the input signal for each short-time section, a spectrogram image is obtained and multi-classification learning is performed using a CNN deep learning model. This effectively classifies commands by converting the time domain voice signal to the frequency domain to express the characteristics well and performing deep learning training using the spectrogram image for the conversion parameters. To verify the performance of the speech recognition system proposed in this study, a simulation program using Tensorflow and Keras libraries was created and a simulation experiment was performed. As a result of the experiment, it was confirmed that an accuracy of 92.5% could be obtained using the proposed deep learning algorithm.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.6
• /
• pp.137-145
• /
• 2010

Digital vessel have to accurate and efficient mange the digital data from various sensors in the digital vessel. But, In sensor network, it is difficult to transmit and analyze the entire stream data depending on limited networks, power and processor. Therefore it is suitable to use alternative stream data processing after classifying the continuous stream data. In this paper, We propose efficient processing method that arrange some sensors (temperature, humidity, lighting, voice) and process query based on sliding window for efficient input stream and pre-clustering using multiple Support Vector Machine(SVM) algorithm and manage hash table to summarized information. Processing performance improve as store and search and memory using hash table and usage reduced so maintain hash table in memory. We obtained to efficient result that accuracy rate and processing performance of proposal method using 35,912 data sets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.96-116
• /
• 2016

Sensing coverage is a fundamental issue for Wireless Sensor Networks (WSNs). Several coverage configuration protocols have been developed; most of them presume the availability of precise knowledge about each node location via GPS receivers. However, equipping each sensor node with a GPS is very expensive in terms of both energy and cost. On the other hand, several GPS-less localization algorithms that aim at obtaining nodes locations with a low cost have been proposed. Although their deep correlation, sensing coverage and localization have long been treated separately. In this paper, we analyze, design and evaluate a novel integrated framework providing both localization and coverage guarantees for WSNs. We integrate the well-known Coverage Configuration Protocol CCP with an improved version of the localization algorithm AT-Dist. We enhanced the original specification of AT-Dist in order to guarantee the necessary localization accuracy required by CCP. In our proposed framework, a few number of nodes are assumed to know their exact positions and dynamically vary their transmission ranges. The remaining sensors positions are derived, as accurately as possible, using this little initial location information. All nodes positions (exact and derived) are then used as an input for the coverage module. Extensive simulation results show that, even with a very low anchor density, our proposal reaches the same performance and efficiency as the ideal CCP based on complete and precise knowledge of sensors coordinates.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.12A
• /
• pp.1340-1348
• /
• 2004

In this paper, we propose a PAPR-minimized sequence mapping scheme that achieves the minimum Peak-to-Average Power Ratio (PAPR) and the minimum amount of computations for the OFDM system. To reduce the PAPR, the mapping table is created with information about block index and symbol patterns of the lower signal power. When the input data sequence comes, it performed division by the block length to find the quotient and remainder. The symbol pattern of the lower signal power can be found in terms of the block index as the quotient in the mapping table and transmitted with remainder as the side information to distinguish and recover the original data sequence in the receiver. The two methods with the proposed mapping scheme are proposed in this paper. One is with mapping table to recover the O%M signal in both transmitter and receiver. The other is with mapping table only in transmitter to reduce the load and the complexity in the mobile system. We show that this algorithm provides the PAPR reduction, the simple processing and less computational complexity to be implemented for the multi-carrier system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.11
• /
• pp.2113-2118
• /
• 2016

Smart Jewelry is applied to the components of the Internet of Things. The process of obtaining the status information to the input of the sensor. And it controls the light color of the LED. Because to express the beauty of twinkling lights that can be felt in the jewelery and aesthetic functions were applied in order to feel the mystery. Smart Jewelry is capable of communication, interaction, wearable. Smart jewelery was equipped with a color, temperature, ambient light sensor. It was designed to allow interaction with a Bluetooth module. Applying an algorithm so that the light jewelry colors can vary depending on the circumstances of the smart jewelry wearer had been implemented by the mobile application. It can be realized in digital technology and the convergence of life. It presents the orientation development of the smart jewelery device on IoT environment.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.514-517
• /
• 2017

In solar photovoltaic systems, power generation is greatly affected by the weather conditions, so it is essential to predict solar energy for stable load operation. Therefore, data on weather conditions are needed as inputs to machine learning algorithms for solar energy prediction. In this paper, we use 15 kinds of weather data such as the precipitation accumulated during the 3 hours of the surface, upward and downward longwave radiation average, upward and downward shortwave radiation average, the temperature during the past 3 hours at 2 m above from the ground and temperature from the ground surface as input data to the algorithm. We analyzed the statistical characteristics and correlations of weather data and extracted the downward and upward shortwave radiation averages as a major elements of a feature vector with high correlation of 70% or more with solar energy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.3
• /
• pp.360-366
• /
• 2008

The initial fuzzy partitions in fuzzy rule-based classification systems are determined by considering the domain region of each attribute with the given data, and the optimal classification boundaries within the fuzzy partitions can be discovered by tuning their parameters using various learning processes such as neural network, genetic algorithm, and so on. In this paper, we propose a selection method for fuzzy partition based on statistical information to maximize the performance of pattern classification without learning processes where statistical information is used to extract the uncertainty regions (i.e., the regions which the classification boundaries in pattern classification problems are determined) in each input attribute from the numerical data. Moreover the methods for extracting the candidate rules which are associated with the partition intervals generated by statistical information and for minimizing the coupling problem between the candidate rules are additionally discussed. In order to show the effectiveness of the proposed method, we compared the classification accuracy of the proposed with those of conventional methods on the IRIS and New Thyroid Cancer data. From experimental results, we can confirm the fact that the proposed method only considering statistical information of the numerical patterns provides equal to or better classification accuracy than that of the conventional methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.3
• /
• pp.232-247
• /
• 1991

This paper proposes a new classification algorithm using characteristic and structural information of printed Hanja as preliminary stages of Hanja-character recognition. Hanja is difficult for not only recognition but classification as many character and complicated structure. In this paper, to solve thie problem, extracted common subpattern in classified pattern after processing type classification fot Hanja pattern. First, we extracted subpattern, after we process preprecessing about input of character pattern, extracting directional segment, labeling on 4-directional pattern and 12 type classified using structural information based on the subpattern existing region of character pattern. Though the experiment, this study obtained that classified rate of Hanja is 93.07% on 1800 character of educational Hanja and 90.12% on 4888 character of KS C5601 standard TRIGEM LBP Hanja font and saw that as extracting subpattern at classified data was this paper possibly applied to the recognition.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.4 s.42
• /
• pp.137-145
• /
• 2006

A user remembers a melody as not the combination of pitch and duration which is written in score but the contour which is composed of the relative pitch and duration. Because of the way of remembering a melody the previous Music Information Retrieval Systems which uses keyboard Playing or score as the main input melody are not easily acceptable in Query By Humming Systems. In this paper, we mention about the considerable checkpoints for Query By Humming System and previous researches. And we propose the feature extraction which is similar with the way of remembering a melody and similarity computation algorithms between melody in humming and melody in music. The proposed similarity computation algorithms solves the problem which can be happened when only uses the relative pitches by using relative durations.

• Journal of Korea Society of Industrial Information Systems
• /
• v.23 no.6
• /
• pp.21-27
• /
• 2018

Wearing degree and uneven wearing detection algorithm using horizontal edge information is proposed in this paper. The noise in the input image is removed by bilateral filter, and then edges are extracted from the filtered image by using the proposed mask. As the tire is worn, grooves of tire shoulder or sipes are changed more than the vertical grooves. Therefore the edges from grooves of tire shoulder or sipes have more information about the tire wearing than the edges from vertical grooves. Proposed mask that is reflected this feature is used to extract the horizontal edges. After edge extraction, the edge image is represented in two-level system. The edge pixels of the binarization image are used to decide the wearing degree and uneven wearing. This proposed method can be used easily without any other equipments. The proposed method is conducted with a real vehicle, and the experimental results show the good performance of the proposed method in detecting wearing degree and uneven wearing.