• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5276-5298
• /
• 2019

Internet of Things (IoT) based sensor networks have gained unprecedented popularity in recent years. With the exponential explosion of the objects (sensors and mobiles), the bandwidth and the speed of data transmission are dwarfed by the anticipated emergence of IoT. In this paper, we propose a novel heterogeneous IoT model integrated the power line communication (PLC) and WiFi network to increase the network capacity and cope with the rapid growth of the objects. We firstly propose the mean transmission delay calculation algorithm based the 3D Markov chain according to the multi-priority of the objects. Then, the attractor selection algorithm, which is based on the adaptive behavior of the biological system, is exploited. The combined the 3D Markov chain and the attractor selection model, named MASM, can select the optimal path adaptively in the heterogeneous IoT according to the environment. Furthermore, we verify that the MASM improves the transmission efficiency and reduce the transmission delay effectively. The simulation results show that the MASM is stable to changes in the environment and more applicable for the heterogeneous IoT, compared with the other algorithms.

• Journal of Digital Contents Society
• /
• v.18 no.1
• /
• pp.141-147
• /
• 2017

Scalable extension of High Efficiency Video Coding (SHVC) standard uses the up-sampled residual data from the base layer to make a residual data in the enhancement layer. This paper describes an efficient algorithm for improving coding gain by using the filtered residual signal of base layer in the Scalable extension of High Efficiency Video Coding (SHVC). The proposed adaptive filter selection mechanism uses the smoothing and sharpening filters to enhance the quality of inter-layer prediction. Based on two filters and the existing up-sampling filter, a rate-distortion (RD)-cost fuction-based competitive scheme is proposed to get better quality of video. Experimental results showed that average BD-rate gains of 1.5%, 2.1%, and 1.7% for Y, U and V components, respectively, were achieved, compared with SHVC reference software 5.0, which is based on HEVC reference model (HM) 13.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.79-87
• /
• 2024

Recently, the importance of pre-trained language models (PLM) has been emphasized for natural language processing (NLP) such as text classification, sentiment analysis, and question answering. Korean PLM shows high performance in NLP in general-purpose domains, but is weak in domains such as finance, medicine, and law. The main goal of this study is to propose a language model learning process and method to build a financial-specific language model that shows good performance not only in the financial domain but also in general-purpose domains. The five steps of the financial-specific language model are (1) financial data collection and preprocessing, (2) selection of model architecture such as PLM or foundation model, (3) domain data learning and instruction tuning, (4) model verification and evaluation, and (5) model deployment and utilization. Through this, a method for constructing pre-learning data that takes advantage of the characteristics of the financial domain and an efficient LLM training method, adaptive learning and instruction tuning techniques, were presented.

• ETRI Journal
• /
• v.33 no.2
• /
• pp.295-298
• /
• 2011

We propose a motion-compensated frame interpolation method in which an accurate backward/forward motion vector pair (MVP) is estimated based on a parabolic motion model. A reliability measure for an MVP is also proposed to select the most reliable MVP for each interpolated block. The possibility of deformation of bidirectional corresponding blocks is estimated from the selected MVP. Then, each interpolated block is produced by combining corresponding blocks with the weights based on the possibility of deformation. Experimental results show that the proposed method improves PSNR performance by up to 2.8 dB as compared to conventional methods and achieves higher visual quality without annoying blockiness artifacts.

• Journal of Communications and Networks
• /
• v.10 no.1
• /
• pp.28-37
• /
• 2008

In this paper, we investigate the problem of minimizing the average transmission power of users while guaranteeing the average delay constraints in time-varying uplink channels. We design a scheduler that selects a user for transmission and determines the transmission rate of the selected user based on the channel and backlog information of users. Since it requires prohibitively high computation complexity to determine an optimal scheduler for multi-user systems, we propose a low-complexity scheduling scheme that can achieve near-optimal performance. In this scheme, we reduce the complexity by decomposing the multiuser problem into multiple individual user problems. We arrange the probability of selecting each user such that it can be determined only by the information of the corresponding user and then optimize the transmission rate of each user independently. We solve the user problem by using a dynamic programming approach and analyze the upper and lower bounds of average transmission power and average delay, respectively. In addition, we investigate the effects of the user selection algorithm on the performance for different channel models. We show that a channel-adaptive user selection algorithm can improve the energy efficiency under uncorrelated channels but the gain is obtainable only for loose delay requirements in the case of correlated channels. Based on this, we propose a user selection algorithm that adapts itself to both the channel condition and the backlog level, which turns out to be energy-efficient over wide range of delay requirement regardless of the channel model.

• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.232-240
• /
• 2022

To fulfill user expectations, the rapid evolution of software techniques and approaches has necessitated reliable and flawless software operations. Aging prediction in the software under operation is becoming a basic and unavoidable requirement for ensuring the systems' availability, reliability, and operations. In this paper, an improved evolutionary computing-driven extreme learning scheme (ECD-ELM) has been suggested for object-oriented software aging prediction. To perform aging prediction, we employed a variety of metrics, including program size, McCube complexity metrics, Halstead metrics, runtime failure event metrics, and some unique aging-related metrics (ARM). In our suggested paradigm, extracting OOP software metrics is done after pre-processing, which includes outlier detection and normalization. This technique improved our proposed system's ability to deal with instances with unbalanced biases and metrics. Further, different dimensional reduction and feature selection algorithms such as principal component analysis (PCA), linear discriminant analysis (LDA), and T-Test analysis have been applied. We have suggested a single hidden layer multi-feed forward neural network (SL-MFNN) based ELM, where an adaptive genetic algorithm (AGA) has been applied to estimate the weight and bias parameters for ELM learning. Unlike the traditional neural networks model, the implementation of GA-based ELM with LDA feature selection has outperformed other aging prediction approaches in terms of prediction accuracy, precision, recall, and F-measure. The results affirm that the implementation of outlier detection, normalization of imbalanced metrics, LDA-based feature selection, and GA-based ELM can be the reliable solution for object-oriented software aging prediction.

• Nuclear Engineering and Technology
• /
• v.56 no.9
• /
• pp.3740-3749
• /
• 2024

To reduce the losses caused by aging failure of insulation gate bipolar transistor (IGBT), which is the core components of nuclear power plant rod position indicating and rod control (RPC) system. It is necessary to conduct studies on its life prediction. The selection of IGBT failure characteristic parameters in existing research relies heavily on failure principles and expert experience. Moreover, the analysis and learning of time-domain degradation data have not been fully conducted, resulting in low prediction efficiency as the monotonicity, time correlation, and poor anti-interference ability of extracted degradation features. This paper utilizes the advantages of the stacked denoising autoencoder(SDAE) network in adaptive feature extraction and denoising capabilities to perform adaptive feature extraction on IGBT time-domain degradation data; establishes a long-short-term memory (LSTM) prediction model, and optimizes the learning rate, number of nodes in the hidden layer, and number of hidden layers using the Gray Wolf Optimization (GWO) algorithm; conducts verification experiments on the IGBT accelerated aging dataset provided by NASA PCoE Research Center, and selects performance evaluation indicators to compare and analyze the prediction results of the SDAE-LSTM model, PSOLSTM model, and BP model. The results show that the SDAE-LSTM model can achieve more accurate and stable IGBT life prediction.

• Communications for Statistical Applications and Methods
• /
• v.12 no.3
• /
• pp.713-727
• /
• 2005

Among different regression approaches, nonparametric procedures perform well under different conditions. In practice it is very hard to identify which is the best procedure for the data at hand, thus model combination is of practical importance. In this paper, we focus on one dimensional regression with fixed design. Polynomial regression, local regression, and smoothing spline are considered. The data are split into two parts, one part is used for estimation and the other part is used for prediction. Prediction performances are used to assign weights to different regression procedures. Simulation results show that the combined estimator performs better or similarly compared with the estimator chosen by cross validation. The combined estimator generates a similar risk to the best candidate procedure for the data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.5
• /
• pp.2277-2298
• /
• 2019

Adaptive learning in e-learning has garnered researchers' interest. In it, learning resources could be recommended automatically to achieve a personalized learning experience. There are various ways to realize it. One of the realistic ways is adaptive learning path recommendation, in which learning resources are provided according to learners' requirements. This paper summarizes existing works and proposes an innovative approach. Firstly, a learner-centred concept map is created using graph theory based on the features of the learners and concepts. Then, the approach generates a linear concept sequence from the concept map using the proposed traversal algorithm. Finally, Learning Objects (LOs), which are the smallest concrete units that make up a learning path, are organized based on the concept sequences. In order to realize this step, we model it as a multi-objective combinatorial optimization problem, and an improved immune algorithm (IIA) is proposed to solve it. In the experimental stage, a series of simulated experiments are conducted on nine datasets with different levels of complexity. The results show that the proposed algorithm increases the computational efficiency and effectiveness. Moreover, an empirical study is carried out to validate the proposed approach from a pedagogical view. Compared with a self-selection based approach and the other evolutionary algorithm based approaches, the proposed approach produces better outcomes in terms of learners' homework, final exam grades and satisfaction.

• The Korean Journal of Applied Statistics
• /
• v.37 no.1
• /
• pp.1-12
• /
• 2024

In many real-world data, multiple response variables are often dependent on the same set of explanatory variables. In particular, if several response variables are correlated with each other, simultaneous estimation considering the correlation between response variables might be more effective way than individual analysis by each response variable. In this multivariate regression analysis, least distance estimator (LDE) can estimate the regression coefficients simultaneously to minimize the distance between each training data and the estimates in a multidimensional Euclidean space. It provides a robustness for the outliers as well. In this paper, we examine the least distance estimation method in multivariate linear regression analysis, and furthermore, we present the penalized least distance estimator (PLDE) for efficient variable selection. The LDE technique applied with the adaptive group LASSO penalty term (AGLDE) is proposed in this study which can reflect the correlation between response variables in the model and can efficiently select variables according to the importance of explanatory variables. The validity of the proposed method was confirmed through simulations and real data analysis.