• The Journal of the Acoustical Society of Korea
• /
• v.22 no.3
• /
• pp.188-193
• /
• 2003

Regardless of the distribution of the adaptation data in the testing environment, model-based adaptation methods that have so far been reported in various literature incorporates the adaptation data undiscriminatingly in reducing the mismatch between the training and testing environments. When the amount of data is small and the parameter tying is extensive, adaptation based on outlier data can be detrimental to the performance of the recognizer. The distribution of the adaptation data plays a critical role on the adaptation performance. In order to maximally improve the recognition rate in the testing environment using only a small number of adaptation data, supervised weighted training is applied to the structural maximum a posterior (SMAP) algorithm. We evaluate the performance of the proposed weighted SMAP (WSMAP) and SMAP on TIDIGITS corpus. The proposed WSMAP has been found to perform better for a small amount of data. The general idea of incorporating the distribution of the adaptation data is applicable to other adaptation algorithms.

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.511-518
• /
• 2022

Supervised learning based on deep learning has made a leap forward in various application fields. However, many supervised learning methods work under the common assumption that training and test data are extracted from the same distribution. If it deviates from this constraint, the deep learning network trained in the training domain is highly likely to deteriorate rapidly in the test domain due to the distribution difference between domains. Domain adaptation is a methodology of transfer learning that trains a deep learning network to make successful inferences in a label-poor test domain (i.e., target domain) based on learned knowledge of a labeled-rich training domain (i.e., source domain). In particular, the unsupervised domain adaptation technique deals with the domain adaptation problem by assuming that only image data without labels in the target domain can be accessed. In this paper, we explore the unsupervised domain adaptation techniques.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.18 no.2
• /
• pp.89-104
• /
• 2015

In order to effectively manage forested areas in South Korea on a national scale, using remotely sensed data is considered most suitable. In this study, utilizing Land coverage maps and Forest type maps of national geographic information instead of collecting field data was tested for conducting supervised classification on SPOT-5 and KOMPSAT-2 imagery focusing on forested areas. Supervised classification were conducted in two ways: analysing a whole area around the study site and/or only forested areas around the study site, using Support Vector Machine. The overall accuracy for the classification on the whole area ranged from 54.9% to 68.9% with kappa coefficients of over 0.4, which meant the supervised classification was in general considered moderate because of sub-classifying forested areas into three categories (i.e. hardwood, conifer, mixed forests). Compared to this, the overall accuracy for forested areas were better for sub-classification of forested areas probably due to less distraction in the classification. To further improve the overall accuracy, it is needed to gain individual imagery rather than mosaic imagery to use more spetral bands and select more suitable conditions such as seasonal timing. It is also necessary to obtain precise and accurate training data for sub-classifying forested areas. This new approach can be considered as a basis of developing an excellent analysis manner for understanding and managing forest landscape.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.197-206
• /
• 2021

GPR data is used for underground exploration. The data gathered are interpreted by experts based on experience as the underground facilities often reflect GPR. In addition, GPR data are different in the noise and characteristics of the data depending on the equipment, environment, etc. This often results in insufficient data with accurate labels. Generally, a large amount of training data have to be obtained to apply CNN models that exhibit high performance in image classification problems. However, due to the characteristics of GPR data, it makes difficult to obtain sufficient data. Finally, this makes neural networks unable to learn based on general supervised learning methods. This paper proposes an image classification method considering data characteristics to ensure that the accuracy of each label is similar. The proposed method is based on semi-supervised learning, and the image is classified using clustering techniques after extracting the feature values of the image from the neural network. This method can be utilized not only when the amount of the labeled data is insufficient, but also when labels that depend on the data are not highly reliable.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1910-1914
• /
• 2015

Human posture recognition is an attractive and challenging topic in computer vision due to its promising applications in the areas of personal health care, environmental awareness, human-computer-interaction and surveillance systems. Human posture recognition in video sequences consists of two stages: the first stage is training and evaluation and the second is deployment. In the first stage, the system is trained and evaluated using datasets of human postures to ‘teach’ the system to classify human postures for any future inputs. When the training and evaluation process is deemed satisfactory as measured by recognition rates, the trained system is then deployed to recognize human postures in any input video sequence. Different classifiers were used in the training such as Multilayer Perceptron Feedforward Neural networks, Self-Organizing Maps, Fuzzy C Means and K Means. Results show that supervised learning classifiers tend to perform better than unsupervised classifiers for the case of human posture recognition.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.407-408
• /
• 2007

In this paper, we present a new method for classifying object using LVQ (Learning Vector Quantization) with flexible output layer. The proposed LVQ is a supervised learning method that dynamically generates output neurons and initializes automatically the weight vectors from training patterns. If the classes of the nearest output neuron is different from the class of the training pattern, a new output neuron is created and the given training pattern is used to initialize the weight vector of the created neuron. The proposed method is significantly different from the previous competitive learning algorithms in the point that the output neurons are dynamically generated during the learning process.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.6
• /
• pp.594-601
• /
• 1997

A new algorithm is proposed for training the multilayer perceptrion(MLP) in pattern classification problems to accelerate the learning speed. It is shown that the sigmoid activation function of the output node can have deterimental effect on the performance of learning. To overcome this detrimental effect and to use the information fully in supervised learning, an objective function for binary modes is proposed. This objective function is composed with two new output activation functions which are selectively used depending on desired values of training patterns. The effect of the objective function is analyzed and a training algorithm is proposed based on this. Its performance is tested in several examples. Simulation results show that the performance of the proposed method is better than that of the conventional error back propagation (EBP) method.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06a
• /
• pp.1015-1020
• /
• 1994

This paper presents the Korean digit recognition method under noise environment using the spectral mapping training based on static supervised adaptation algorithm. In the presented recognition method, as a result of spectral mapping from one space of noisy speech spectrum to another space of speech spectrum without noise, spectral distortion of noisy speech is improved, and the recognition rate is higher than that of the conventional method using VQ and DTW without noise processing, and even when SNR level is 0 dB, the recognition rate is 10 times of that using the conventional method. It has been confirmed that the spectral mapping training has an ability to improve the recognition performance for speech in noise environment.

• The Journal of Korea Robotics Society
• /
• v.14 no.2
• /
• pp.114-121
• /
• 2019

This paper presents a new benchmark system for visual odometry (VO) and monocular depth estimation (MDE). As deep learning has become a key technology in computer vision, many researchers are trying to apply deep learning to VO and MDE. Just a couple of years ago, they were independently studied in a supervised way, but now they are coupled and trained together in an unsupervised way. However, before designing fancy models and losses, we have to customize datasets to use them for training and testing. After training, the model has to be compared with the existing models, which is also a huge burden. The benchmark provides input dataset ready-to-use for VO and MDE research in 'tfrecords' format and output dataset that includes model checkpoints and inference results of the existing models. It also provides various tools for data formatting, training, and evaluation. In the experiments, the exsiting models were evaluated to verify their performances presented in the corresponding papers and we found that the evaluation result is inferior to the presented performances.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.375-386
• /
• 2022

The city of Khartoum, the capital of Sudan, was heavily damaged by the flood of the Nile in 2020. Classification using satellite images can define the damaged area and help emergency response. As Synthetic Aperture Radar (SAR) uses microwave that can penetrate cloud, it is suitable to use in the flood study. In this study, Random Forest classifier, one of the supervised classification algorithms, was applied to the flood event in Khartoum with various sizes of the training dataset and number of images using Sentinel-1 SAR. To create a training dataset, we used unsupervised classification and visual inspection. Firstly, Random Forest was performed by reducing the size of each class of the training dataset, but no notable difference was found. Next, we performed Random Forest with various number of images. Accuracy became better as the number of images in creased, but converged to a maximum value when the dataset covers the duration from flood to the completion of drainage.