• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.2
• /
• pp.676-692
• /
• 2018

Saliency detection in neurobiology is a vehement research during the last few years, several cognitive and interactive systems are designed to simulate saliency model (an attentional mechanism, which focuses on the worthiest part in the image). In this paper, a bottom up saliency detection model is proposed by taking into account the color and luminance frequency features of RGB, CIE $L^*a^*b^*$ color space of the image. We employ low-level features of image and apply band pass filter to estimate and highlight salient region. We compute the likelihood probability by applying Bayesian framework at pixels. Experiments on two publically available datasets (MSRA and SED2) show that our saliency model performs better as compared to the ten state of the art algorithms by achieving higher precision, better recall and F-Measure.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.209-216
• /
• 2019

Over the past decade, researchers were able to solve complex medical problems as well as acquire deeper understanding of entire issue due to the availability of machine learning techniques, particularly predictive algorithms and automatic recognition of patterns in medical imaging. In this study, a technique called transfer learning has been utilized to classify Magnetic Resonance (MR) images by a pre-trained Convolutional Neural Network (CNN). Rather than training an entire model from scratch, transfer learning approach uses the CNN model by fine-tuning them, to classify MR images into Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal control (NC). The performance of this method has been evaluated over Alzheimer's Disease Neuroimaging (ADNI) dataset by changing the learning rate of the model. Moreover, in this study, in order to demonstrate the transfer learning approach we utilize different pre-trained deep learning models such as GoogLeNet, VGG-16, AlexNet and ResNet-18, and compare their efficiency to classify AD. The overall classification accuracy resulted by GoogLeNet for training and testing was 99.84% and 98.25% respectively, which was exceptionally more than other models training and testing accuracies.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.233-238
• /
• 1993

In this paper, two diagnosis algorithms using the simple fuzzy, cognitive map (FCM) that is an useful qualitative model are proposed. The first basic algorithm is considered as a simple transition of Shiozaki's signed directed graph approach to FCM framework. And the second one is an extended version of the basic algorithm. In the extension, three important concepts, modified temporal associative memory (TAM) recall, temporal pattern matching algorithm and hierarchical decomposition are adopted. As the resultant diagnosis scheme takes short computation time, it can be used for on-line fault diagnosis of large scale and complex processes that conventional diagnosis methods cannot be applied. The diagnosis system can be trained by the basic algorithm and generates FCM model for every experienced process fault. In on-line application, the self-generated fault model FCM generates predicted pattern sequences, which are compared with observed pattern sequences to declare the origin of fault. In practical case, observed pattern sequences depend on transport time. So if predicted pattern sequences are different from observed ones, the time weighted FCM with transport delay can be used to generate predicted ones. The fault diagnosis procedure can be completed during the actual propagation since pattern sequences of tvo different faults do not coincide in general.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.19 no.12
• /
• pp.1339-1349
• /
• 2008

In this paper, a nonlinear relationship between an input complex envelope and an output complex envelope of m-th harmonic zone is theoretically analyzed, and AM/$AM_m$ and AM/$PM_m$ are defined. A scheme to extract these characteristics from measured in-phase and quadrature-phase data is suggested. The proposed analysis is verified with a fundamental-fundamental and fundamental-third harmonic measurements for a InGaP power amplifier(PA). Based on the harmonic-band nonlinear analysis and extraction scheme, a new technique to send a signal in m-th harmonic band with a harmonic signal Linearization Digital Predistortion(DPD) scheme is presented. A numerical analysis and a Look-Up Table(LUT) based DPD algorithms to linearize output signal on m-th harmonic zone are developed. For a 16- and a 64-QAM input signals, a DPD for third harmonic signal linearization is implemented, and output spectrum and signal constellation are measured. The wholly distorted signals are linearized, and thus the measured Error Vector Magnitudes (EVM) are 6.4 % and 6.5 % respectively. The results show that a proposed scheme linearizes a nonlinearly distorted harmonic band signals. The proposed nonlinear analysis and predistortion scheme can be applied to multiband transmitter in next generation software defined radio(SDR)/cognitive radio(CR) wireless system.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.55-68
• /
• 2023

In recent years, the Television White Space (TVWS) has attracted the interest of many researchers due to its propagation characteristics obtainable between 470MHz and 790MHz spectrum bands. The plenty of unused channels in the TV spectrum allows the secondary users (SUs) to use the channels for broadband services especially in rural areas. However, when the number of SUs increases in the TVWS wireless network the aggregate interference also increases. Aggregate interferences are the combined harmful interferences that can include both co-channel and adjacent interferences. The aggregate interference on the side of Primary Users (PUs) has been extensively scrutinized. Therefore, resource allocation (power and spectrum) is crucial when designing the TVWS network to avoid interferences from Secondary Users (SUs) to PUs and among SUs themselves. This paper proposes a model to improve the resource allocation for reducing the aggregate interface among SUs for broadband services in rural areas. The proposed model uses joint power and spectrum hybrid Firefly algorithm (FA), Genetic algorithm (GA), and Particle Swarm Optimization algorithm (PSO) which is considered the Co-channel interference (CCI) and Adjacent Channel Interference (ACI). The algorithm is integrated with the admission control algorithm so that; there is a possibility to remove some of the SUs in the TVWS network whenever the SINR threshold for SUs and PU are not met. We considered the infeasible system whereby all SUs and PU may not be supported simultaneously. Therefore, we proposed a joint spectrum and power allocation with an admission control algorithm whose better complexity and performance than the ones which have been proposed in the existing algorithms in the literature. The performance of the proposed algorithm is compared using the metrics such as sum throughput, PU SINR, algorithm running time and SU SINR less than threshold and the results show that the PSOFAGA with ELGR admission control algorithm has best performance compared to GA, PSO, FA, and FAGAPSO algorithms.

• The Journal of the Korea Contents Association
• /
• v.22 no.5
• /
• pp.56-66
• /
• 2022

Due to the recent increase in information encountered on social media, algorithm-based recommendation formats selectively provide information based on user information, which often causes a filter bubble effect by an Echo Chamber. Eco-chamber refers to a phenomenon in which beliefs are amplified or strengthened by communication only in an enclosed system, and filter bubbles refer to a phenomenon in which information providers provide customized information according to users' interests, and users encounter only filtered information. The purpose of this study is to propose a method of efficiently selecting information as a way to improve the filter bubble phenomenon by such an echo chamber. The research progress method analyzed recommended algorithms used on YouTube, Facebook and Amazon. In this study, humanities solutions such as training critical thinking skills of social media users and strengthening objective ethical standards according to self-preservation laws, and technical solutions of model-based cooperative filtering or cross-recommendation methods were presented. As a result, recommended algorithms should continue to supplement technology and develop new techniques, and humanities should make efforts to overcome cognitive dissonance and prevent users from falling into confirmation bias through critical thinking training and political communication education.

• 한국정보교육학회:학술대회논문집
• /
• 2010.08a
• /
• pp.271-280
• /
• 2010

Education focus on cultivating creative talent in the rapidly changing knowledge and Information society. Algorithms of computer science students to logical thinking and problem solving to find the best solution is an effective learning content. But the algorithm often educate at the University of reality when considering the level of elementary school students' cognitive structure and it is very important for teaching. In this study, based on the principle of the algorithm with an educational content for students to understand the principles of their own problems as the best way to resolve the situation with the ability to want to kidney. Content that contains elements of the game interesting for students to participate actively interested in effective teaching methods to the understanding of the principles of the algorithm will be a big help.

• Journal of Advanced Navigation Technology
• /
• v.13 no.3
• /
• pp.378-384
• /
• 2009

In this paper, we consider a cyclostationary-feature-detection based spectrum sensing algorithm for ATSC signal detection. One of the proposed algorithms for IEEE 802.22 standardization organization which meet the requirements of IEEE 802.22 is Thomson's algorithm based on cyclostationary feature detection. We propose an interpolation-based spectrum sensing algorithm for ATSC signal detection, which has less computation complexity than that of Thomson's algorithm and provides no performance loss compared to Thomson's algorithm. By using zero-padding in time domain and effective sensing scanning method, the proposed algorithm requires less computational complexity and shows no performance degradation compared to Thomson's algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.8C
• /
• pp.529-535
• /
• 2011

After permission for utilization of TV white space by FCC, a lot of attentions are focused on spectrum sensing, and various spectrum sensing methods have been proposed. However, they do not consider real environment, thus they are hard to achieve the required performance. In this paper, we propose resolutions for the problem which could be occurred in implementation of spectrum sensing module and verify performance of the proposed methods with computer simulation. The first proposed method utilizes channel status information to separate received signal and spurious for reducing false alarm probability caused by system internal spurious. The another proposed scheme is subband normalization method to prevent miss detection caused by multiple narrow band signals with different received signal strength. The simulation results verify that we can prevent false alarm cause by spurious components with the proposed system internal spurious cognition. Moreover, the proposed subband normalization method shows that it could overcome performance degradation caused by received signal strength difference.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.8A
• /
• pp.633-639
• /
• 2009

For operation of IEEE 802.22 WRAN system, spectrum sensing is a essential function. However, due to strict sensing requirement of WRAN system, spectrum sensing process of CR nodes require long quiet period. In addition, CR nodes sometimes fail to detect licensed users due to shadowing effect of wireless communication environment. To overcome this problem, CR nodes collaborate with each other for increasing the sensing reliability or mitigating the sensitivity requirement. A general approach for decision fusion, the "k out of N" rule is often taken as the decision fusion rule for its simplicity. However, since k out of N rules can not achieve better performance than the highest SNR node when SNR is largely different among CR nodes, the local SNR of each node should be considered to achieve better performance. In this paper, we propose two novel data fusion methods by utilizing confidence vector which represents the confidence level of individual sensing result. The simulation results show that the proposed schemes improve the signal detection performance than the conventional data fusion algorithms.