• KIISE Transactions on Computing Practices
• /
• v.21 no.4
• /
• pp.338-342
• /
• 2015

Recurrent Neural Network (RNN), a machine learning model which can handle time-series data, can possess more varied structures than a feed-forward neural network, since a RNN allows hidden-to-hidden connections. This research focuses on the network structure among hidden neurons, and discusses the information processing capability of RNN. Time-series learning potential and dynamics of RNNs are investigated upon several well-established network structure models. Hidden neuron network structure is found to have significant impact on the performance of a model, and the performance variations are generally correlated with the criticality of the network dynamics. Especially Preferential Attachment Network model showed an interesting behavior. These findings provide clues for performance improvement of the RNN.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.599-602
• /
• 2003

A new technique is presented to construct predictive models of plasma etch processes. This was accomplished by combining a backpropagation neural network (BPNN) and a random generator (RC). The RG played a critical role to control neuron gradients in the hidden layer, The predictive model constructed in this way is referred to as a randomized BPNN (RG-BPNN). The proposed scheme was evaluated with a set of experimental plasma etch process data. The etch process was characterized by a 2$^3$ full factorial experiment. The etch responses modeled are 4, including aluminum (Al) etch rate, profile angle, Al selectivity, and do bias. Additional test data were prepared to evaluate model appropriateness. The performance of RC-BPNN was evaluated as a function of the number of hidden neurons and the range of gradient. for given range and hidden neurons, 100 sets of random neuron gradients were generated and among them one best set was selected for evaluation. Compared to the conventional BPNN, the proposed RC-BPNN demonstrated about 50％ improvements in all comparisons. This illustrates that the RG-BPNN of multi-valued gradients is an effective way to considerably improve the predictive ability of current BPNN of single-valued gradient.

• Journal of Korean Academy of Nursing
• /
• v.40 no.5
• /
• pp.662-675
• /
• 2010

Purpose: This ethnography was done to explore the meaning of illness in Korean Americans with chronic hepatitis B. Methods: The participants were 6 patients with chronic hepatitis B and 6 general informants who could provide relevant data. Data were collected from iterative fieldwork with ethnographic interviews within Korean communities in two cities in the United States. Data were analyzed using causal chain analysis developed by Wolcott. Results: The analyses revealed three meanings for the illness: hidden disease, intentionally hidden disease, and inevitably hidden disease. The contexts of meaning of illness included characteristics of the illness, social stigma, structure of health care system and communication patterns and discourse between health care providers and clients. Conclusion: The meaning of illness was based on folk illness concepts and constructed in the sociocultural context. Folk etiology, pathology and interpretation of one's symptoms were factors influencing illness behavior. These findings could be a cornerstone for culture specific care for Korean Americans with chronic hepatitis B.

• Journal of Korean Association for Spatial Structures
• /
• v.18 no.4
• /
• pp.69-80
• /
• 2018

In this study, an algorithm applying deep learning to the truss structures was proposed. Deep learning is a method of raising the accuracy of machine learning by creating a neural networks in a computer. Neural networks consist of input layers, hidden layers and output layers. Numerous studies have focused on the introduction of neural networks and performed under limited examples and conditions, but this study focused on two- and three-dimensional truss structures to prove the effectiveness of algorithms. and the training phase was divided into training model based on the dataset size and epochs. At these case, a specific data value was selected and the error rate was shown by comparing the actual data value with the predicted value, and the error rate decreases as the data set and the number of hidden layers increases. In consequence, it showed that it is possible to predict the result quickly and accurately without using a numerical analysis program when applying the deep learning technique to the field of structural analysis.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.91-102
• /
• 2022

With the evolution of wireless sensor network (WSN) technology, the routing policy has foremost importance in the Internet of Things (IoT). A systematic routing policy is one of the primary mechanics to make certain the precise and robust transmission of wireless sensor networks in an energy-efficient manner. In an IoT environment, WSN is utilized for controlling services concerning data like, data gathering, sensing and transmission. With the advantages of IoT potentialities, the traditional routing in a WSN are augmented with decision-making in an energy efficient manner to concur finer optimization. In this paper, we study how to combine IoT-based deep learning classifier with routing called, Kriging Regressive Deep Belief Neural Learning (KR-DBNL) to propose an efficient data packet routing to cope with scalability issues and therefore ensure robust data packet transmission. The KR-DBNL method includes four layers, namely input layer, two hidden layers and one output layer for performing data transmission between source and destination sensor node. Initially, the KR-DBNL method acquires the patient data from different location. Followed by which, the input layer transmits sensor nodes to first hidden layer where analysis of energy consumption, bandwidth consumption and light intensity are made using kriging regression function to perform classification. According to classified results, sensor nodes are classified into higher performance and lower performance sensor nodes. The higher performance sensor nodes are then transmitted to second hidden layer. Here high performance sensor nodes neighbouring sensor with higher signal strength and frequency are selected and sent to the output layer where the actual data packet transmission is performed. Experimental evaluation is carried out on factors such as energy consumption, packet delivery ratio, packet loss rate and end-to-end delay with respect to number of patient data packets and sensor nodes.

• Journal of Korea Multimedia Society
• /
• v.19 no.1
• /
• pp.22-29
• /
• 2016

Hidden Markov Model is one of the most successful and popular tools for modeling real world sequential data. Real world signals come in a variety of shapes and variabilities, among which temporal and spectral ones are the prime targets that the HMM aims at. A new problem that is gaining increasing attention is characterizing missing observations in incomplete data sequences. They are incomplete in that there are holes or omitted measurements. The standard HMM algorithms have been developed for complete data with a measurements at each regular point in time. This paper presents a modified algorithm for a discrete HMM that allows substantial amount of omissions in the input sequence. Basically it is a variant of Baum-Welch which explicitly considers the case of isolated or a number of omissions in succession. The algorithm has been tested on online handwriting samples expressed in direction codes. An extensive set of experiments show that the HMM so modeled are highly flexible showing a consistent and robust performance regardless of the amount of omissions.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.143-148
• /
• 2022

In this paper, we employ deep neural network (DNN) to discern Android user interaction data distribution from artificial data distribution. We utilize real Android user interaction trace dataset collected from [1] to evaluate our DNN design. In particular, we use sequential model with 4 dense hidden layers and 1 dense output layer in TensorFlow and Keras. We also deploy sigmoid activation function for a dense output layer with 1 neuron and ReLU activation function for each dense hidden layer with 32 neurons. Our evaluation shows that our DNN design fulfills high test accuracy of at least 0.9955 and low test loss of at most 0.0116 in all cases of artificial data distributions.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.1C
• /
• pp.24-31
• /
• 2003

In this paper, a new opto-digital multiple information hiding and real-time extracting system is implemented. That is, multiple information is hidden in a cover image by using the stego keys which are generated by combined use of random sequence(RS) and Hadamard matrix(HM) and these hidden information is extracted in real-time by using a new optical correlator-based extraction system. In the experiment, 3 kinds of information, English alphabet of "N", "R", "L" having 512$\times$512 pixels, are formulated 8$\times$8 blocks and each of these information is multiplied with the corresponding stego keys having 64$\times$64 pixels one by one. And then, by adding these modulated data to a cover image of "Lena"having 512$\times$512 pixels, a stego image is finally generated. In this paper, as an extraction system, a new optical nonlinear joint transform correlator(NJTC) is introduced to extract the hidden data from a stego image in real-time, in which optical correlation between the stego image and each of the stego keys is performed and from these correlation outputs the hidden data can be asily exacted in real-time. Especially, it is found that the SNRs of the correlation outputs in the proposed optical NJTC-based extraction system has been improved to 7㏈ on average by comparison with those of the conventional JTC system under the condition of having a nonlinear parameter less than k=0.4. This good experimental results might suggest a possibility of implementation of an opto-digital multiple information hiding and real-time extracting system.

• Journal of Digital Convergence
• /
• v.15 no.10
• /
• pp.525-535
• /
• 2017

The purpose of this study aims to examine consumer perception and current status of water park. The Naver and Daum were used for data collection channels and the keyword 'water park' was used for data retrieval. The data analysis period was limited to the study period from January 1, 2015 to December 31, 2016 for a total of two years. First, as a result of the frequency analysis, hidden cameras, Lotte water park, arrests, suspects, gimhae were in top 5 in 2015, Lotte water park, swimming, summer, opening, admission ticket were in top 5 in 2016. Second, as a result of the connection degree central analysis, hidden camera, arrest, suspect, female, shower room were in top 5 in 2015, swimming, Lotte water park, summer and One Mount, admission ticket were in top 5 in 2016. Third, as a result of the N-GRAM network graph, the water park/hidden camera, the hidden camera/hidden camera, the suspect/arrest, the Gimhae/Lotte water park, water park/suspect were in top 5 in 2015, and One Mount/water park, Gimhae/Lotte water park, water park/admission ticket, water park/water park, water park/opening were in top 5 in 2016. Fourth, as a result of the CONCOR analysis, three groups in 2015 and two groups in 2016 were formed.

• Journal of Korea Society of Industrial Information Systems
• /
• v.13 no.3
• /
• pp.23-30
• /
• 2008

A data hiding method based on least significant bit (LSB) substitution and multi-pixel differencing (MPD) is presented on the proposed method to improve the capacity of the hidden secret data and to provide an imperceptible visual quality. First, a sum of different values for four-pixel sub-block is calculated. The low value of the sum can be located on a smooth block and the high value is located on an edged block. The secret data are hidden into the cover image by LSB method in the smooth block, while MPD method in the edged block. The experimental results show that the proposed method has a higher capacity and maintains a good visual quality.