• Journal of Multimedia Information System
• /
• v.5 no.2
• /
• pp.79-82
• /
• 2018

Due to the handheld holding of smartphones and the presence of light leakage and non-balanced contrast, the detection of the retina area in smartphone-captured fundus images is more challenging than retinography-captured fundus images. This paper presents a computationally efficient image processing pipeline in order to detect and enhance the retina area in smartphone-captured fundus images. The developed pipeline consists of five image processing components, namely point spread function parameter estimation, deconvolution, contrast balancing, circular Hough transform, and retina area extraction. The results obtained indicate a typical fundus image captured by a smartphone through a D-EYE lens is processed in 1 second.

• Asian Journal for Public Opinion Research
• /
• v.11 no.4
• /
• pp.304-326
• /
• 2023

News shows often deliver crosscutting information to their audiences by inviting commentators from rival political parties. If these news shows foster the formation of informed and balanced views of the audience, mass media could provide countermeasures against political polarization. To test the effect of such news shows, this study conducted an experiment with two variants of a simulated radio talk show. In the partisan scenario, the two guest commentators' affiliations suggested their ideological orientation. In the non-partisan scenario, the commentators had neutral affiliations. We divided participants into two ideology groups, liberals and conservative, and compared each group's evaluation of the commentators in the two scenarios. Two multivariate analysis of variance (MANOVA) tests were conducted to analyze the effect of the perceived ideology of the commentators on respondents' attitudes toward the commentators' arguments depending on their own ideological inclinations. The analyses results did not support the hypothesis that anticipated partisan attitudes towards the commentators' arguments. It was only the liberal respondents who showed statistically significant different attitudes toward commentators' arguments in each of the two scenarios. The findings suggest that such broadcast shows do not automatically trigger partisan message processing and may help the audience to develop informed and balanced opinions. While the current study failed to find conclusive evidence to support the hypotheses, it also found that the perceived ideology of the information source may trigger partisan attitudes for certain types of issues. Future studies with different experiment designs are needed to investigate the issue further.

• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.870-881
• /
• 2020

Because SCADA monitoring data of wind turbines are large and fast changing, the unbalanced proportion of data in various working conditions makes it difficult to process fault feature data. The existing methods mainly introduce new and non-repeating instances by interpolating adjacent minority samples. In order to overcome the shortcomings of these methods which does not consider boundary conditions in balancing data, an improved over-sampling balancing algorithm SC-SMOTE (safe circle synthetic minority oversampling technology) is proposed to optimize data sets. Then, for the balanced data sets, a fault diagnosis method based on improved k-nearest neighbors (kNN) classification for wind turbine blade icing is adopted. Compared with the SMOTE algorithm, the experimental results show that the method is effective in the diagnosis of fan blade icing fault and improves the accuracy of diagnosis.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.1
• /
• pp.80-87
• /
• 2001

This article shows how general software-ergonomic principles are successfully applied in the design of user friendly graphical interfaces. A theoretical model(WOB-Model) is derived from empirical studies and validated in the development of several systems. It provides basic principles within a well-balanced framework and leads to concrete design guidelines. The user tests with the software shows that many of the common usability problems can be eliminated.

• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.159-172
• /
• 2024

The number of healthcare products available for pets has increased in recent times, which has prompted active research into wearable devices for pets. However, the data collected through such devices are limited by outliers and missing values owing to the anomalous and irregular characteristics of pets. Hence, we propose pet behavior recognition based on a hybrid one-dimensional convolutional neural network (CNN) and long short- term memory (LSTM) model using pet wearable devices. An Arduino-based pet wearable device was first fabricated to collect data for behavior recognition, where gyroscope and accelerometer values were collected using the device. Then, data augmentation was performed after replacing any missing values and outliers via preprocessing. At this time, the behaviors were classified into five types. To prevent bias from specific actions in the data augmentation, the number of datasets was compared and balanced, and CNN-LSTM-based deep learning was performed. The five subdivided behaviors and overall performance were then evaluated, and the overall accuracy of behavior recognition was found to be about 88.76%.

• Journal of Information Processing Systems
• /
• v.6 no.3
• /
• pp.295-306
• /
• 2010

Network lifetime is a critical issue in Wireless Sensor Networks (WSNs). In which, a large number of sensor nodes communicate together to perform a predetermined sensing task. In such networks, the network life time depends mainly on the lifetime of the sensor nodes constituting the network. Therefore, it is essential to balance the energy consumption among all sensor nodes to ensure the network connectivity. In this paper, we propose an energy-efficient data routing protocol for wireless sensor networks. Contrary to the protocol proposed in [6], that always selects the path with minimum hop count to the base station, our proposed routing protocol may choose a longer path that will provide better distribution of the energy consumption among the sensor nodes. Simulation results indicate clearly that compared to the routing protocol proposed in [6], our proposed protocol evenly distributes the energy consumption among the network nodes thus maximizing the network life time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11c
• /
• pp.1759-1762
• /
• 2003

최근 키 분배 프로토콜과는 다르게 하드웨어에 암호키를 저장하여 사용하는 것과 달리, 사용자가 기억할 수 있는 길이의 패스워드(password)를 사용해 서버와의 인증과 키 교환을 동시에 수행하는 패스워드 기반 키 분배 프로토콜이 제안되고 있다. 본 논문에서는 이러한 패스워드 기반의 키 분배 프로토콜 중 BPKA(Balanced Password-authenticated Key Agreement)에 속하는 DH-EKE(Diffie-Hellman Encrypted Key Exchange), PAK(Password-Authenticated Key exchange), SPEKE(Simple Password Exponential Key Exchange) 프로토콜을 비교 분석하고, 이를 바탕으로 기존의 BPKA 프로토콜에 비해 적은 연산량을 가지면서 사용자와 서버가 각기 다른 정보를 갖는 패스워드-검증자 기반 프로토콜을 제안한다. 본 논문에서 제안하는 패스워드 기반 키 분배 프로토콜의 안전성 분석을 위해 Active Impersonation 과 Forward Secrecy, Off-line dictionary attack, Man-in-the -middle Attack 등의 공격모델을 적용하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.1167-1169
• /
• 2009

Multipath routing in wireless sensor networks has been proven to provide with increased data delivery ratio, security, robustness to node and link failures, network throughput, etc. However, the energy cost for multiple routes construction and their maintenance is very high. This paper proposes a sink-initiated, node-disjoint multipath routing protocol for static wireless sensor networks that significantly minimizes the route construction messages and thereby saves the critical batter energy of sensor nodes. It also distributes the traffic load spatially over many nodes in the forwarding paths, which ensures balanced energy consumption in the network and thereby increases the network lifetime. The simulation results show that it decreases the routing overhead as well as the standard deviation of nodes' residual energies.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.308-311
• /
• 2008

본 연구는 대기업을 중심으로 확산 되고 있는 BPM(Business Process Management) 분석하기 위해 BSC (Balanced Score Card)의 이론적 방법을 고찰하였으며, BPM에 대한 개요를 시작으로 BPM의 기대효과와 향후 시장동향에 대해서 발췌를 하였으며, P사의 구축방안과 추진과정에 필요한 System의 환경을 분석하였다. 대기업을 중심으로 BPM이 도입이되고 있지만 우수한 중소업체도 사장의 환경변화에 대응을 위해 도입하는 업체를 발굴하여 BPM 도입성과에 대해서 분석을 하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.12C
• /
• pp.1642-1651
• /
• 2004

Advance of internet access technology requires more internet bandwidth and high-speed packet processing. IP address lookups in routers are essential elements which should be performed in real time for packets arriving tens-of-million packets per second. In this paper, we proposed a new architecture for efficient IP address lookup. The proposed scheme produces multiple balanced trees stored into a single SRAM. The proposed scheme performs sequential binary searches on multiple trees. Performance evaluation results show that p개posed architecture requires 301.7KByte SRAM to store about 40,000 prefix samples, and an address lookup is achieved by 11.3 memory accesses in average.