• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.1
• /
• pp.113-120
• /
• 2015

In this paper, we propose a feature extraction method using the stacked autoencoders which consist of restricted Boltzmann machines. The stacked autoencoders is a sort of deep networks. Restricted Boltzmann machines (RBMs) are probabilistic graphical models that can be interpreted as stochastic neural networks. In terms of pattern classification problem, the feature extraction is a key issue. We use the stacked autoencoders networks to extract new features which have a good influence on the improvement of the classification performance. After feature extraction, fuzzy k-nearest neighbors algorithm is used for a classifier which classifies the new extracted data set. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1020-1025
• /
• 2021

Facial alignment is very important task for human life. And facial landmark detection is one of the instrumental methods in face alignment. We introduce the stacked hourglass networks with transposed convolutional layers for facial landmark detection. our method substitutes nearest neighbor upsampling for transposed convolutional layer. Our method returns better accuracy in facial landmark detection compared to stacked hourglass networks with nearest neighbor upsampling.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.952-959
• /
• 2018

Clustering is one of the most fundamental algorithms in machine learning. The performance of clustering is affected by the distribution of data, and when there are more data or more dimensions, the performance is degraded. For this reason, we use a stacked auto encoder, one of the deep learning algorithms, to reduce the dimension of data which generate a feature vector that best represents the input data. We use k-means, which is a famous algorithm, as a clustering. Sine the feature vector which reduced dimensions are also multi dimensional, we use the Euclidean distance as well as the cosine similarity to increase the performance which calculating the similarity between the center of the cluster and the data as a vector. A deep clustering networks combining a stacked auto encoder and k-means re-trains the networks when the k-means result changes. When re-training the networks, the loss function of the stacked auto encoder and the loss function of the k-means are combined to improve the performance and the stability of the network. Experiments of benchmark image ad document dataset empirically validated the power of the proposed algorithm.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.1
• /
• pp.151-160
• /
• 2024

Artificial Neural Networks that enabled Artificial Intelligence are being used in many fields. However, the application to mechanical structures has several problems and research is incomplete. One of the problems is that it is difficult to secure a large amount of data necessary for learning Artificial Neural Networks. In particular, it is important to detect and recognize external forces and forces for safety working and accident prevention of mechanical structures. This study examined the possibility by applying the Current Neural Network of Artificial Neural Networks to detect and recognize the load on the machine. Tens of thousands of data are required for general learning of Recurrent Neural Networks, and to secure large amounts of data, this paper derives load data from ANSYS structural analysis results and applies a stacked auto-encoder technique to secure the amount of data that can be learned. The usefulness of Stacked Auto-Encoder data was examined by comparing Stacked Auto-Encoder data and ANSYS data. In addition, in order to improve the accuracy of detection and recognition of load data with a Recurrent Neural Network, the optimal conditions are proposed by investigating the effects of related functions.

• KIISE Transactions on Computing Practices
• /
• v.24 no.3
• /
• pp.113-121
• /
• 2018

Position encoding is a method of applying weights according to position of words that appear in a sentence. Pointer networks is a deep learning model that outputs corresponding index with an input sequence. This model can be applied to coreference resolution using attribute. However, the pointer networks has a problem in that its performance is degraded when the length of input sequence is long. To solve this problem, we proposed two contributions to resolve the coreference. First, we applied position encoding and dynamic position encoding to pointer networks. Second, we stack deeply layers of encoder to make high-level abstraction. As results, the position encoding based stacked pointer networks model proposed in this paper had a CoNLL F1 performance of 71.78%, which was improved by 6.01% compared to vanilla pointer networks.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.3
• /
• pp.197-206
• /
• 2019

Telemarketing has been used in finance due to the reduction of offline channels. In order to select telemarketing target customers, various machine learning techniques have emerged to maximize the effect of minimum cost. However, there are problems that the class imbalance, which the number of marketing success customers is smaller than the number of failed customers, and the recall rate is lower than accuracy. In this paper, we propose a method that solve the imbalanced class problem and increase the recall rate to improve the efficiency. The hybrid sampling method is applied to balance the data in the class, and the stacked deep network is applied to improve the recall and precision as well as the accuracy. The proposed method is applied to actual bank telemarketing data. As a result of the comparison experiment, the accuracy, the recall, and the precision is improved higher than that of the conventional methods.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.12 no.2
• /
• pp.139-149
• /
• 2012

A 3D stacked IC is made by multiple dies (possibly) with heterogeneous process technologies. Therefore, die-to-die variation in 2D chips renders on-package variation (OPV) in a 3D chip. In spite of the different variation effect in 3D chips, generally, 3D die stacking can produce high yield due to the smaller individual die area and the averaging effect of variation on data path. However, 3D clock network can experience unintended huge clock skew due to the different clock propagation routes on multiple stacked dies. In this paper, we analyze the on-package variation effect on 3D clock networks and show the necessity of a post silicon management method such as body biasing technique for the OPV induced 3D clock skew control in 3D stacked IC designs. Then, we present a parametric yield improvement method to mitigate the OPV induced 3D clock skew.

• Journal of Korea Multimedia Society
• /
• v.23 no.2
• /
• pp.216-226
• /
• 2020

In this paper, a stacked convolutional autoencoder model is proposed in order to classify Alzheimer's disease with high accuracy in PET/CT images. The proposed model makes use of the latent space representation - which is also called the bottleneck, of the encoder-decoder architecture: The input image is sent through the pipeline and the encoder part, using stacked convolutional filters, extracts the most useful information. This information is in the bottleneck, which then uses Softmax classification operation to classify between Alzheimer's disease, Mild Cognitive Impairment, and Normal Control. Using the data from Dong-A University, the model performs classification in detecting Alzheimer's disease up to 98.54% accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.536-564
• /
• 2019

Soft faults are inherent in wireless sensor networks (WSNs) due to external and internal errors. The failure of processes in a protocol stack are caused by errors on various layers. In this work, impact of errors and channel misbehavior on process execution is investigated to provide an error classification mechanism. Considering implementation of WSN protocol stack, inter-process correlations of stacked and peer layer processes are modeled. The proposed model is realized through local and global decision trees for fault diagnosis. A hybrid framework is proposed to implement local decision tree on sensor nodes and global decision tree on diagnostic cluster head. Local decision tree is employed to diagnose critical failures due to errors in stacked processes at node level. Global decision tree, diagnoses critical failures due to errors in peer layer processes at network level. The proposed model has been analyzed using fault tree analysis. The framework implementation has been done in Castalia. Simulation results validate the inter-process correlation model-based fault diagnosis. The hybrid framework distributes processing load on sensor nodes and diagnostic cluster head in a decentralized way, reducing communication overhead.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.4
• /
• pp.293-301
• /
• 2001

This paper reviews three methods to compute a pointwise confidence interval of neuro-fuzzy models and compares their estimation perfonnanee through simulations. The eOITl.putation methods under consideration include stacked generalization using cross-validation, predictive error bar in regressive models, and local reliability measure for the networks employing a local representation scheme. These methods implemented on the neuro-fuzzy models are applied to the problems of simple function approximation and chaotic time series prediction. The results of reliability estimation are compared both quantitatively and qualitatively.