• Journal of Convergence for Information Technology
• /
• v.11 no.5
• /
• pp.30-37
• /
• 2021

Various devices are connected to the Internet, and attacks using the Internet are occurring. Among such attacks, there are attacks that use malicious URLs to make users access to wrong phishing sites or distribute malicious viruses. Therefore, how to detect such malicious URL attacks is one of the important security issues. Among recent deep learning technologies, neural networks are showing good performance in image recognition, speech recognition, and pattern recognition. This neural network can be applied to research that analyzes and detects patterns of malicious URL characteristics. In this paper, performance analysis according to various parameters was performed on a method of detecting malicious URLs using neural networks. In this paper, malicious URL detection performance was analyzed while changing the activation function, learning rate, and neural network structure. The experimental data was crawled by Alexa top 1 million and Whois to build the data, and the machine learning library used TensorFlow. As a result of the experiment, when the number of layers is 4, the learning rate is 0.005, and the number of nodes in each layer is 100, the accuracy of 97.8% and the f1 score of 92.94% are obtained.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1137-1144
• /
• 2022

In this study, an artificial intelligence(AI) was developed to help with facial expression practice in order to express emotions. The developed AI used multimodal inputs consisting of sentences and facial images for deep neural networks (DNNs). The DNNs calculated similarities between the emotions predicted by the sentences and the emotions predicted by facial images. The user practiced facial expressions based on the situation given by sentences, and the AI provided the user with numerical feedback based on the similarity between the emotion predicted by sentence and the emotion predicted by facial expression. ResNet34 structure was trained on FER2013 public data to predict emotions from facial images. To predict emotions in sentences, KoBERT model was trained in transfer learning manner using the conversational speech dataset for emotion classification opened to the public by AIHub. The DNN that predicts emotions from the facial images demonstrated 65% accuracy, which is comparable to human emotional classification ability. The DNN that predicts emotions from the sentences achieved 90% accuracy. The performance of the developed AI was evaluated through experiments with changing facial expressions in which an ordinary person was participated.

• Journal of Industrial Convergence
• /
• v.22 no.4
• /
• pp.11-19
• /
• 2024

The purpose of this study was to analyze user reviews of running applications using text mining. This study used user reviews of Nike Run Club and Runkeeper in the Google Play Store using the selenium package of python3 as the analysis data, and separated the morphemes by leaving only Korean nouns through the OKT analyzer. After morpheme separation, we created a rankNL dictionary to remove stopwords. To analyze the data, we used TF, TF-IDF and LDA topic modeling in text mining. The results of this study are as follows. First, the keywords 'record', 'app', and 'workout' were identified as the top keywords in the user reviews of Nike Run Club and Runkeeper applications, and there were differences in the rankings of TF and TF-IDF. Second, the LDA topic modeling of Nike Run Club identified the topics of 'basic items', 'additional features', 'errors', and 'location-based data', and the topics of Runkeeper identified the topics of 'errors', 'voice function', 'running data', 'benefits', and 'motivation'. Based on the results, it is recommended that errors and improvements should be made to contribute to the competitiveness of the application.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.1
• /
• pp.1-9
• /
• 2024

This paper analyzes the trends in generative AI technology based on patent application documents. To achieve this, we selected 5,433 generative AI-related patents filed in South Korea, the United States, and Europe from 2003 to 2023, and analyzed the data by country, technology category, year, and applicant, presenting it visually to find insights and understand the flow of technology. The analysis shows that patents in the image category account for 36.9%, the largest share, with a continuous increase in filings, while filings in the text/document and music/speech categories have either decreased or remained stable since 2019. Although the company with the highest number of filings is a South Korean company, four out of the top five filers are U.S. companies, and all companies have filed the majority of their patents in the U.S., indicating that generative AI is growing and competing centered around the U.S. market. The findings of this paper are expected to be useful for future research and development in generative AI, as well as for formulating strategies for acquiring intellectual property.

• Information Systems Review
• /
• v.22 no.2
• /
• pp.77-99
• /
• 2020

Smart speaker is a device that provides an interactive voice-based service that can search and use various information and contents such as music, calendar, weather, and merchandise using artificial intelligence. Since AI technology provides more sophisticated and optimized services to users by accumulating data, early smart speaker manufacturers tried to build a platform through aggressive marketing. However, the frequency of using smart speakers is less than once a month, accounting for more than one third of the total, and user satisfaction is only 49%. Accordingly, the necessity of strengthening the user experience of smart speakers has emerged in order to acquire a large number of users and to enable continuous use. Therefore, this study analyzes the user experience of the smart speaker and proposes a method for enhancing the user experience of the smart speaker. Based on the analysis results in two stages, we propose ways to enhance the user experience of smart speakers by model. The existing research on the user experience of the smart speaker was mainly conducted by survey and interview-based research, whereas this study collected the actual review data written by the user. Also, this study interpreted the analysis result based on the smart speaker user experience dimension. There is an academic significance in interpreting the text mining results by developing the smart speaker user experience dimension. Based on the results of this study, we can suggest strategies for enhancing the user experience to smart speaker manufacturers.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.189-198
• /
• 2024

Lipreading is one of the important parts of speech recognition, and several studies have been conducted to improve the performance of lipreading in lipreading systems for speech recognition. Recent studies have used method to modify the model architecture of lipreading system to improve recognition performance. Unlike previous research that improve recognition performance by modifying model architecture, we aim to improve recognition performance without any change in model architecture. In order to improve the recognition performance without modifying the model architecture, we refer to the cues used in human lipreading and set other regions such as chin and cheeks as regions of interest along with the lip region, which is the existing region of interest of lipreading systems, and compare the recognition rate of each region of interest to propose the highest performing region of interest In addition, assuming that the difference in normalization results caused by the difference in interpolation method during the process of normalizing the size of the region of interest affects the recognition performance, we interpolate the same region of interest using nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation, and compare the recognition rate of each interpolation method to propose the best performing interpolation method. Each region of interest was detected by training an object detection neural network, and dynamic time warping templates were generated by normalizing each region of interest, extracting and combining features, and mapping the dimensionality reduction of the combined features into a low-dimensional space. The recognition rate was evaluated by comparing the distance between the generated dynamic time warping templates and the data mapped to the low-dimensional space. In the comparison of regions of interest, the result of the region of interest containing only the lip region showed an average recognition rate of 97.36%, which is 3.44% higher than the average recognition rate of 93.92% in the previous study, and in the comparison of interpolation methods, the bilinear interpolation method performed 97.36%, which is 14.65% higher than the nearest neighbor interpolation method and 5.55% higher than the bicubic interpolation method. The code used in this study can be found a https://github.com/haraisi2/Lipreading-Systems.

• Korean Chemical Engineering Research
• /
• v.47 no.5
• /
• pp.558-564
• /
• 2009

POF(Polymer optical fiber) offers advantages of lighter, inexpensive, and easier to use over GOF(glass optical fiber). Its higher transmission loss and low bandwidth, however, make it suitable only for short distance networking such as LAN. The polymer materials and its synthesis technology of low transmission loss and the broader application for flexible POF are the two of many critical areas to be investigated more. In the current study, low-noise POF modules are developed and optimized with a low noise amplifier and low cost LED of 650 nm. In order to demonstrate the dynamic characteristics of the POF module for optical communication and sensing, we have built an image transfer module, optical transmission speed measurement module, optical transceiver for RS-232, and sound-transfer module, and the signal characteristics of them are evaluated. It is found that the module can be readily used for a quick and simple measurement of optical transfer speed. With help of analog amplifier, LED, and PD, sound and image transfers through a maximum 60 m optical waveguide have been confirmed. Real-time data transfer was also demonstrated in PID control, which is thought to be valuable to industrial plant design and control.

• Information Systems Review
• /
• v.12 no.1
• /
• pp.145-164
• /
• 2010

Since the third generation (3G) mobile communication service has been launched by most mobile communication operators in Korea, the portion of data service in mobile communication service becomes one of the most important factors in mobile communication service market. In past mobile communication market, most mobile communication operators made their profit mostly from voice communication service. However, the portion of profit from data service has gradually increased based on both video phone call and mobile Internet service. In this situation, LG telecom launched the full browsing mobile Internet service. This service provides a new type of mobile Internet service platform which enables to access the World Wide Web using mobile browsers, so we generally access the Web using web browsers in the desktop computer. Under the open network structure of mobile Internet like situation, it is very important to analyze the factors which can affect the competition between mobile communication service companies. So, in this paper, we first present the current state of full browsing service, followed by the expectation of its growth potentials and barriers. Then, we analyze the advantages and disadvantage of LG telecom as a first-mover and SK telecom/KTF as followers. Finally, based on this analysis, we predict the future competition among these companies and the market.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37C no.9
• /
• pp.829-840
• /
• 2012

Recently, in network communication environments, it is changing very fast from wired to wireless. The open shortest path firtst (OSPF), one of link state routing protocols, mainly used in wired networks, is the routing method to select optimal traffic path as identifying the link state of neighbor routers. The traditional OSPF cost functions performs with first fixed cost permanently, unless the router link is changed. However, in wireless networks, the performance of links show big difference by other environment factors. The bit error rate (BER), a parameter which can quite affect link state in wireless networks, is not considered in the traditional OSPF cost functions. Only a link bandwidth is considered in the traditional OSPF cost functions. In this paper, we verify the various parameters which can affect link performance, whether it is permissible to use as the parameter of proposed cost functions. To propose new cost functions, we use the effective bandwidth. This bandwidth is calculated by proposed formula using the BER of the network link and link bandwidth. As applied by the proposed triggering condition, the calculated effective bandwidth decrease the unstable of network by generating less link state update messages in wireless networks that frequently changes the link state. Simulation results show that the proposed cost functions significantly outperforms the traditional cost functions in wireless networks in terms of the services of VoIP and data transmission.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.2 no.4
• /
• pp.545-551
• /
• 1998

The Radio communication by existing SSB, VHF, etc. in a coast station and a base station for military affairs is still used to a very important the device of information delivery or transmitting and receiving by the remote controller to using to the exclusive cable for a equipment established at a long distance. When a number of consumer to connected and operated by a number of transceiver is essential for a circuit controller of ICS, in KOREA, is devoted by import to considerable quantity because of to be delayed development of this field. This Paper has been realized to optimal algorithm and designing of a circuit connection controller by multi-processor to pre-stage for the development of ICS. The H/W is composed able to remote control to circuit connector with the several slave processor and a processor for master, and this has taken possible through without any obstacle to communication circuits of a control signal by FSK system. The S/W make possible monitoring for communication condition of other circuits by means of a serial communication system by the multi-processing. This paper has been studied for connecting to a circuits wished to rapidly and precisely by the full application to a interrupt technique. A technique to control by remote to a number of transceiver is a way increasing to application for a frequency resource of the limited MF/SF, VHF and the existing radio communication technique. According to, this paper will achieve to be the reduction of energy & equipment and multiplicity of information delivery in the general communication and disposal to rapid and exact for the important communication as distress, urgency and safety on the sea.