• KIPS Transactions on Computer and Communication Systems
• /
• v.7 no.5
• /
• pp.127-136
• /
• 2018

In this paper, we propose a PIN entry method that combines with machine learning technique on smartphone. We use not only a PIN but also touch time intervals and locations as factors to identify whether the user is correct or not. In the user registration phase, a remote server was used to train/create a machine learning model using data that collected from end-user device (i.e. smartphone). In the user authentication phase, the pre-trained model and the saved PIN was used to decide the authentication success or failure. We examined that there is no big inconvenience to use this technique (FRR: 0%) and more secure than the previous PIN entry techniques (FAR : 0%), through usability and security experiments, as a result we could confirm that this technique can be used sufficiently. In addition, we examined that a security incident is unlikely to occur (FAR: 5%) even if the PIN is leaked through the shoulder surfing attack experiments.

• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.12
• /
• pp.497-506
• /
• 2017

There have been previous researches about user authentication by analyzing the user's gait or behavior or action using the accelerometer sensor of smartphone, but there was a lack of user convenience to apply PIN entry. In this paper, we propose the technique for PIN entry without a touch on smartphone, the technique uses an accelerometer sensor and a vibration sensor built in the smartphone to enter the PIN. We conducted a usability experiment using the proposed technique and confirmed that the usability can be increased according to users become accustomed to this technique and that the users can enter PIN with 12.9 seconds and a probability of 100% on average. Also we conducted a security experiment and confirmed that an attack success rate is 0% when an attacker attacked the user using the recording attack and that it is more secure than the previous PIN entry technique. As a result, we was able to confirm that this technique can be used sufficiently.

• Journal of the Institute of Convergence Signal Processing
• /
• v.19 no.2
• /
• pp.77-88
• /
• 2018

This paper proposes a RBFNN(Radial Basis Function Neural Network) based decentralized adaptive tracking control scheme using PSO(Particle Swarm Optimization) for an uncertain electrically driven robot system with input saturation. Practically, the magnitudes of input voltage and current signals are limited due to the saturation of actuators in robot systems. The proposed controller overcomes this input saturation and does not require any robot link and actuator model parameters. The fitness function used in the presented PSO scheme is expressed as a multi-objective function including the magnitudes of voltages and currents as well as the tracking errors. Using a PSO scheme, the control gains and the number of the RBFs are tuned automatically and thus the performance of the control system is improved. The stability of the total control system is guaranteed by the Lyapunov stability analysis. The validity and robustness of the proposed control scheme are verified through simulation results.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.10
• /
• pp.3226-3235
• /
• 2000

The more complex and larger semiconductor integraed circuits become, the core important delay test becomes which guarantees that semiconductor integrated circuits operate in time. In this paper, we propose a new partial enhanced scan method that can generate test patterns for path delay faults offectively. We implemented a new partial enhanced scan method based on an automatic test pattern generator(ATPG) which uses implication and justification . First. we generate test patterns in the standard scan environment. And if test patterns are not generated regularly in the scan chain, we determine flip-flops which applied enhanced scan flip-flops using the information derived for running an automatic test pattern generator inthe circuti. Determming enhanced scan flip-flops are based on a fault coverage or a hardware overhead. through the expenment for JSCAS 89 benchmark sequential circuits, we compared the fault coverage in the standard scan enviroment and enhance scan environment, partial enhanced scan environment. And we proved the effectiveness of the new partial enhanced scan method by identifying a high fault coverage.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.1
• /
• pp.51-56
• /
• 2023

This study investigates the effect of sEMG sampling frequency on CNN learning performance at Korean finger number recognition application. Since the bigger sampling frequency of sEMG signals generates bigger size of input data and takes longer CNN's learning time. It makes making real-time system implementation more difficult and more costly. Thus, there might be appropriate sampling frequency when collecting sEMG signals. To this end, this work choose five different sampling frequencies which are 1,024Hz, 512Hz, 256Hz, 128Hz and 64Hz and investigates CNN learning performance with sEMG data taken at each sampling frequency. The comparative study shows that all CNN recognized Korean finger number one to five at the accuracy of 100% and CNN with sEMG signals collected at 256Hz sampling frequency takes the shortest learning time to reach the epoch at which korean finger number gestures are recognized at the accuracy of 100%.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.257-260
• /
• 2020

사전 학습을 기반으로 하는 BERT계열의 모델들이 다양한 언어 및 자연어 처리 태스크들에서 뛰어난 성능을 보이고 있지만, masked language model의 경우 입력 문장의 15%만 마스킹을 함으로써 학습 효율이 떨어지고 미세 조정 시 마스킹 토큰이 등장하지 않는 불일치 문제도 존재한다. 이러한 문제를 효과적으로 해결한 ELECTRA는 영어 벤치마크에서 기존의 언어모델들 보다 뛰어난 성능을 보여주었지만 한국어에 대한 관련 연구는 부족한 실정이다. 본 연구에서는 ELECTRA를 한국어 코퍼스에 대해 학습시키고, 다양한 한국어 자연어 이해 태스크들에 대해 실험을 진행한다. 실험을 통해 ELECTRA의 모델 크기별 성능 평가를 진행하였고, 여러 한국어 태스크들에 대해서 평가함으로써 ELECTRA 모델이 기존의 언어 모델들보다 좋은 성능을 보인다는 것을 입증하였다.

• Journal of Korea Game Society
• /
• v.16 no.2
• /
• pp.119-128
• /
• 2016

In computer games, most of GUI methods are keyboards, mouses and touch screens. The total time of processing the sound commands for games is the sum of input time and recognition time. In this paper, we propose a method for taking only the prefixes of the input signals for sound commands, resulting in the reduced the total processing time, instead of taking the whole input signals. In our method, command sounds are recognized using HMM(Hidden Markov Model), where separate HMM's are built for the whole input signals and their prefix signals. We experiment our proposed method with representative commands of platform games. The experiment shows that the total processing time of input command signals reduces without decreasing recognition rate significantly. The study will contribute to enhance the versatility of GUI for computer games.

• Journal of Korea Game Society
• /
• v.15 no.1
• /
• pp.135-144
• /
• 2015

Smart TV has been the most popular communication device since 2010. It is the multi-functional device conjugated a variety of features such as Apps, Web surfing, viewing VOD and so on. However, the contents and development tools for smart TV are still relatively small and research for game contents development tools is also insufficient. In this study, we are to design and develop a framework for developers to make Smart TV game contents easily. The STGF (Smart TV Game Framework) we developed is made up of 3 managers such as input manager, screen data process manager, and game status process manager. We verified the usefulness of STGF through developing "Pentomiro" App launched commercially in 2013. With STGF development time would be expected to be reduced, because we spend little time in basic development steps such as input, output, and data processing and error correction processing.

• Journal of Korea Multimedia Society
• /
• v.12 no.9
• /
• pp.1242-1251
• /
• 2009

A DSMS(Data Stream Management System) in ubiquitous environment processes huge data that input from a number of sensor. The existed system is used with a load shedding method that is eliminated with a part of huge data stream when it doesn't process the huge data stream. The Load shedding method has to filter a part of input data. This is because, data completeness or reliability is decreased. In this paper, we proposed the overload prediction load balancing to maintain data completeness when the system has an overload. The proposed method predicts the overload time. and than it is decreased with data loss when achieves the prediction overload time. The performance evaluation shows that the proposed method performs better than the existed method.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.10
• /
• pp.2591-2599
• /
• 1998

In this paper, we proose a method of recognizing unknown words and correcting spelling errors(including spacing erors) to increase the performance of Korean information processing systems. Unknown words are recognized through comparative analysis of two or more morphologically similar eojeols(spacing units in Korean) including the same unknown word candidates. And spacing errors and spelling errors are corrected by using lexicatlized rules shich are automatically extracted from very large raw corpus. The extractionof the lexicalized rules is based on morphological and contextual similarities between error eojeols and their corection eojeols which are confirmed to be used in the corpus. The experimental result shows that our system can recognize unknown words in an accuracy of 98.9%, and can correct spacing errors and spelling errors in accuracies of 98.1% and 97.1%, respectively.