• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.1
• /
• pp.13-18
• /
• 2019

In this study, we investigate important keywords and their relationships among the keywords for social issues, and analyze topics to find subjects of the social issues. In particular, we collected twitter data with the keyword 'metoo' which has attracted much attention in these days, and perform keyword analysis and topic modeling. First, we preprocess the twitter data, identified important keywords, and analyzed the relatedness of the keywords. After then, topic modeling is performed to find subjects related to 'metoo'. Our experimental results showed that relatedness of keywords and subjects on social issues in twitter are well identified based on keyword analysis and topic modeling.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.9
• /
• pp.3221-3242
• /
• 2021

The purpose of the study is to examine the current study trend of 'QR code' and suggest a direction for the future study of big data analysis: (1) Background: study trend of 'QR code' and analysis of the text by subject field and year; (2) Methodology: data scraping and collection, EXCEL summary, and preprocess and big data analysis by R x 64 4.0.2 program package; (3) the findings: first, the trend showed a continuous increase in 'QR code' studies in general and the findings were applied in various fields. Second, the analysis of frequent keywords showed somewhat different results by subject field and year, but the overall results were similar. Third, the visualization of the frequent keywords also showed similar results as that of frequent keyword analysis; and (4) the conclusions: in general, 'QR code' studies are used in various fields, and the trend is likely to increase in the future as well. And the findings of this study are a reflection that 'QR code' is an aspect of our social and cultural phenomena, so that it is necessary to think that 'QR code' is a tool and an application of information. An expansion of the scope of the analysis is expected to show us more meaningful indications on 'QR code' study trends and development potential.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2356-2376
• /
• 2021

In this paper, we proposed a novel modulation recognition method based on quantum elephant herding algorithm (QEHA) evolving neural network under impulse noise environment. We use the adaptive weight myriad filter to preprocess the received digital modulation signals which passing through the impulsive noise channel, and then the instantaneous characteristics and high order cumulant features of digital modulation signals are extracted as classification feature set, finally, the BP neural network (BPNN) model as a classifier for automatic digital modulation recognition. Besides, based on the elephant herding optimization (EHO) algorithm and quantum computing mechanism, we design a quantum elephant herding algorithm (QEHA) to optimize the initial thresholds and weights of the BPNN, which solves the problem that traditional BPNN is easy into local minimum values and poor robustness. The experimental results prove that the adaptive weight myriad filter we used can remove the impulsive noise effectively, and the proposed QEHA-BPNN classifier has better recognition performance than other conventional pattern recognition classifiers. Compared with other global optimization algorithms, the QEHA designed in this paper has a faster convergence speed and higher convergence accuracy. Furthermore, the effect of symbol shape has been considered, which can satisfy the need for engineering.

• Journal of information and communication convergence engineering
• /
• v.19 no.2
• /
• pp.79-83
• /
• 2021

This paper proposes a novel image classification method based on few-shot learning, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small datasets and improve the accuracy of classification. This method uses model structure optimization to extend the basic convolutional neural network (CNN) model and extracts more image features by adding convolutional layers, thereby improving the classification accuracy. We incorporated certain measures to improve the performance of the model. First, we used general methods such as setting a lower learning rate and shuffling to promote the rapid convergence of the model. Second, we used the data expansion technology to preprocess small datasets to increase the number of training data sets and suppress over-fitting. We applied the model to 10 monkey species and achieved outstanding performances. Experiments indicated that our proposed method achieved an accuracy of 87.92%, which is 26.1% higher than that of the traditional CNN method and 1.1% higher than that of the deep convolutional neural network ResNet50.

• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.237-246
• /
• 2022

Among the technologies of the 4th industrial revolution, drones that have grown rapidly and are being used in various industries can be operated by the pilot directly or can be operated automatically through programming. In order to be controlled by a pilot or to operate automatically, it is essential to predict and analyze the optimal path for the drone to move without obstacles. In this paper, after securing and analyzing the pilot training dataset through the unmanned aerial vehicle piloting training platform designed through prior research, the profile of the dataset that should be preceded to search and derive the optimal route of the unmanned aerial vehicle was designed. The drone pilot training data includes the speed, movement distance, and angle of the drone, and the data set is visualized to unify the properties showing the same pattern into one and preprocess the properties showing the outliers. It is expected that the proposed big data-based profile can be used to predict and analyze the optimal movement path of an unmanned aerial vehicle.

• Journal of Information Processing Systems
• /
• v.19 no.2
• /
• pp.258-266
• /
• 2023

Aiming at the problems of poor customer satisfaction and poor accuracy of customer classification, this paper proposes a customer classification model based on speech recognition. First, this paper analyzes the temporal data characteristics of customer demand data, identifies the influencing factors of customer demand behavior, and determines the process of feature extraction of customer voice signals. Then, the emotional association rules of customer demands are designed, and the classification model of customer demands is constructed through cluster analysis. Next, the Euclidean distance method is used to preprocess customer behavior data. The fuzzy clustering characteristics of customer demands are obtained by the fuzzy clustering method. Finally, on the basis of naive Bayesian algorithm, a customer demand classification model based on speech recognition is completed. Experimental results show that the proposed method improves the accuracy of the customer demand classification to more than 80%, and improves customer satisfaction to more than 90%. It solves the problems of poor customer satisfaction and low customer classification accuracy of the existing classification methods, which have practical application value.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.23 no.2
• /
• pp.243-248
• /
• 1986

The impurities in As and Ga sources and the contamination of the GaAs substrate prior to growing of MBE GaAs epitaxial layer have been investigated using RHEED, AES and RGA methods. The as source was contaminated by H2O, CO, CO2 and AsO, and the Ga source was contaminated by H2, H2O, CO and CO2. These contaminants could easily be removed by prebaking the source. On the other hand, GaAs substrate was contaminated principally carbon and oxygen. The oxygen could easily be removed by heating the substrate above 480\ulcorner, and the carbon could also be reduced by sputtering the substrate with 1ke V Ar+. The chemically etched substrate surface prior to growing the layer was rough, but it was made to be smooth and clean by heating it above 530 \ulcorner.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.737-745
• /
• 2023

This paper discusses a study on developing an artificial intelligence model to detect incidents of fires in distribution switchboard using thermal images. The objective of the research is to preprocess collected thermal images into suitable data for object detection models and design a model capable of determining the occurrence of fires within distribution panels. The study utilizes thermal image data from AI-HUB's industrial complex for training. Two CNN-based deep learning object detection algorithms, namely Faster R-CNN and RetinaNet, are employed to construct models. The paper compares and analyzes these two models, ultimately proposing the optimal model for the task.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.8
• /
• pp.456-462
• /
• 2002

We are developing searching algorithms for weighted strings such as protein sequences. Let${\sum}$ be an alphabet and for each $a{\in}{\sum}$ its weight ${\mu}(a)$ is given. Given a string $A=a_1a_2…a_n\; with each ai{\in}{\sum}$, a substring<$A(i.j)=a_ia_{i+1}…a_j$ has weight ${\in}(A(i.j))={\in}(a_i)+{\in}(a_i+1)+…+{\in}(a_j)$.The problem we are dealing with is to preprocess A to build a searching structure, and later, given a query weight M, the structure is used to answer the question of whether there is a substring A(i,j) such that$M={\in}(A(i,j))$.In this paper an algorithm that improves over the previous result will be presented. The previously best known algorithm answers a query in $0(\frac{nlog\;logn}{log\; n})$time using a searching structure that requires O(n) amount of memory. Our algorithm reduces the memory requirement to $0(\frac{n}{log\; n})$ while achieving the same query answer time.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.141-146
• /
• 2008

As the interest about ubiquitous environment is increasing, there are many researches about the services in this environment. These services have important issues in interpreting the users' context, using many kinds of sensors, like PDA, GPS and accelerometers. Low level raw data, which sensors like accelerometers calibrates, are hard to use, and to provide real-time services preprocessing and interpreting the data into context, in real-time, is important. This paper describes a context integrate system which can integrate these sensors and also sensors which has raw data, like accelerometers and physiological sensors, and define the context interpret rule with XML. The proposing system reduces programming operations when adding a sensor to the sensor network or modifying the context interpreting rule by using XML. By using this system, we implemented a real-time data monitoring system which can describe the numeric data into graphs, and assist the user to validate the data and results of the preprocess phase, and also support the external services and applications to use the context of the user.