• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.2
• /
• pp.81-86
• /
• 2014

In this paper, we present an effective sound classification system for recognizing the real-time context of a smartphone user. Our system avoids unnecessary consumption of limited computational resource by filtering both silence and white noise out of input sound data in the pre-processing step. It also improves the classification performance on low energy-level sounds by amplifying them as pre-processing. Moreover, for efficient learning and application of HMM classification models, our system executes the dimension reduction and discretization on the feature vectors through k-means clustering. We collected a large amount of 8 different type sound data from daily life in a university research building and then conducted experiments using them. Through these experiments, our system showed high classification performance.

• The Korean Journal of Applied Statistics
• /
• v.35 no.5
• /
• pp.667-684
• /
• 2022

Gene expression data present the level of mRNA abundance of each gene, and analyses of gene expressions have provided key ideas for understanding the mechanism of diseases and developing new drugs and therapies. Nowadays high-throughput technologies such as DNA microarray and RNA-sequencing enabled the simultaneous measurement of thousands of gene expressions, giving rise to a characteristic of gene expression data known as high dimensionality. Due to the high-dimensionality, learning models to analyze gene expression data are prone to overfitting problems, and to solve this issue, dimension reduction or feature selection techniques are commonly used as a preprocessing step. In particular, we can remove irrelevant and redundant genes and identify important genes using gene selection methods in the preprocessing step. Various gene selection methods have been developed in the context of machine learning so far. In this paper, we intensively review recent works on gene selection methods using machine learning approaches. In addition, the underlying difficulties with current gene selection methods as well as future research directions are discussed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2991-3007
• /
• 2022

Two dimensional locality preserving projections (2D-LPP) is an improved algorithm of 2D image to solve the small sample size (SSS) problems which locality preserving projections (LPP) meets. It's able to find the low dimension manifold mapping that not only preserves local information but also detects manifold embedded in original data spaces. However, 2D-LPP is simple and elegant. So, inspired by the comparison experiments between two dimensional linear discriminant analysis (2D-LDA) and linear discriminant analysis (LDA) which indicated that matrix based methods don't always perform better even when training samples are limited, we surmise 2D-LPP may meet the same limitation as 2D-LDA and propose a novel matrix exponential method to enhance the performance of 2D-LPP. 2D-MELPP is equivalent to employing distance diffusion mapping to transform original images into a new space, and margins between labels are broadened, which is beneficial for solving classification problems. Nonetheless, the computational time complexity of 2D-MELPP is extremely high. In this paper, we replace some of matrix multiplications with multiple multiplications to save the memory cost and provide an efficient way for solving 2D-MELPP. We test it on public databases: random 3D data set, ORL, AR face database and Polyu Palmprint database and compare it with other 2D methods like 2D-LDA, 2D-LPP and 1D methods like LPP and exponential locality preserving projections (ELPP), finding it outperforms than others in recognition accuracy. We also compare different dimensions of projection vector and record the cost time on the ORL, AR face database and Polyu Palmprint database. The experiment results above proves that our advanced algorithm has a better performance on 3 independent public databases.

• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.463-476
• /
• 2022

In this paper, we propose a table tennis posture classification system using a cooperative robot to develop a table tennis robot that can be trained like a real game. The most ideal table tennis robot would be a robot with a high joint driving speed and a high degree of freedom. Therefore, in this paper, we intend to use a cooperative robot with sufficient degrees of freedom to develop a robot that can be trained like a real game. However, cooperative robots have the disadvantage of slow joint driving speed. These shortcomings are expected to be overcome through quick recognition. Therefore, in this paper, we try to quickly classify the opponent's posture to overcome the slow joint driving speed. To this end, learning about dynamic postures was conducted using image data as input, and finally, three classification models were created and comparative experiments and evaluations were performed on the designated dynamic postures. In conclusion, comparative experimental data demonstrate the highest classification accuracy and fastest classification speed in classification models using MLP (Multi-Layer Perceptron), and thus demonstrate the validity of the proposed algorithm.

• Journal of the Korean Institute of Gas
• /
• v.2 no.4
• /
• pp.60-66
• /
• 1998

The hot stove system is a process that is continuously and constantly generating the hot combustion air required for the blast furnace. The hot stove process is considered as a main energy consumption process because it consumes about $20\%$ of the total energy in steel making works. So, many researchers have interested in the improvement of the heat efficiency of the hot stove to reduce the energy consumption. But they have difficulties in improving the heat efficiency of the hot stove because there is no precise information on heat transformation occurring during the heating period. In order to model the relationship between the operating conditions and heat efficiencies, we propose a neural network using feature extraction as one of experimental modeling methods. In order to show the performance of the model, we compare it with Partial Least Square (PLS) method. Both methods have similarities in using the dimension reduction technique. And then we present the simulation results on the prediction of the heat efficiency of the hot stove.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.