Digital Library[ Search Result ]
A Similarity-Based Multi-Knowledge Transfer Algorithm for Enhancing Learning Efficiency of Reinforcement Learning-Based Autonomous Agent
Yeryeong Cho, Soohyun Park, Joongheon Kim
http://doi.org/10.5626/JOK.2025.52.4.310
This paper proposed a similarity-based multi-knowledge transfer algorithm (SMTRL) to enhance the learning efficiency of autonomous agents in reinforcement learning. SMTRL can calculates the similarity between pre-trained models and the current model and dynamically adjust the knowledge transfer ratio based on this similarity to maximize learning efficiency. In complex environments, autonomous agents face significant challenges when learning independently, as this process can be time-consuming and inefficient, making knowledge transfer essential. However, differences between pre-trained models and actual environments can result in negative transfer, leading to diminished learning performance. To tackle this issue, SMTRL dynamically can adjusts the ratio of knowledge transfer from highly similar pre-trained models, thereby accelerating learning stability. Furthermore, experimental results demonstrated that the proposed algorithm outperformed traditional reinforcement learning and traditional knowledge transfer learning in terms of convergence speed. Therefore, this paper introduces a novel approach to efficient knowledge transfer for autonomous agents and discusses its applicability to complex mobility environments and directions for future research.
Proposal of An Intent Classification Method Using Text Augmentation Techniques and Transfer Learning
Huiwon Lee, Sungho Park, Chaewon Lee, Seunghyun Lee, Kangbae Lee
http://doi.org/10.5626/JOK.2024.51.2.141
Intent classification is the first step of task-directed chatbots and is an important phase in performance improvement. However, task-oriented chatbots are limited by a lack of data for specific domains. The purpose of this study is to solve the problem of data limitation by utilizing text augmentation techniques and transfer learning. Previously, studies using transfer learning and text augmentation techniques existed, but it was difficult to find studies applicable to various domains. This study proposes a text augmentation technique and transfer learning method applicable to various domains. For the experiment, less than 10,000, 20,000, and 30,000 data were constructed according to the ratio of actual utterance intentions in 8 domains. As a result of the experiment, although differences existed depending on the domain, it was confirmed that the method proposed in this study was excellent for all 8 domains. It was confirmed that the accuracy for the 8 domains improved by 10%, 3.4%, and 1.9%, respectively on average with the decreasing size of the training data, and the F1-Score improved by 30%, 12%, and 7.5%, respectively on average.
Corroboration of Skin Diseases: Measuring the Severity of Vitiligo Using Transfer Learning
http://doi.org/10.5626/JOK.2023.50.1.72
Vitiligo is a commonly acquired skin disorder that results from the loss of melanin pigment from the epidermis and is clinically indicated by pale or white patches on the body. Preliminary treatment is essential for vitiligo, but vitiligo does not cause pain or health problems. Therefore, vitiligo patents are treated when skin lesions are visible on the outside. The subjective judgment treats vitiligo of dermatologist’s, and there is no quantitative and objective analysis method through imaging, because it is difficult to obtain a medical image. Several diagnostic methods have been developed through a few medical studies. In this paper, we propose a method for area of vitiligo through image segmentation using metastasis learning to overcome the limitations of vitiligo medical data collection. The transfer learning model was selected by experimenting with the possibility of application to deep learning models such as U-net, FCN, and Deeplab. In addition, the severity of Vitiligo was measured using the VASI score used in the medical field, converting the skin image into an RGB skin image representing skin areas. In the experimental results, when trained with an imbalanced vitiligo image dataset, the performance of Deeplab, measured by F1-score and IoU, was superior to that of U-net and the image processing method. Additionally, the method for calculating the VASI score in vitiligo image proposed in this paper showed the possibility of being used for vitiligo diagnosis.
A Cross Domain Adaptation Method based on Adversarial Cycle Consistence Learning for Rotary Machine Fault Diagnosis
http://doi.org/10.5626/JOK.2022.49.7.530
Research on data-based fault diagnosis models is being actively conducted in various industries. However, in the case of industrial equipment, various operating conditions occur, and it is difficult to secure sufficient training data. To solve this problem, a cross-domain adaptation technique can be utilized. In this study, we propose an adversarial consistency-maintaining transformation learning method that can maintain failure classification consistency even for the new untrained environmental data using the rotating body vibration data. The data generated through consistent learning creates a continuous invariant latent space between the new operating condition data distribution and the known data distribution and learns to maintain the failure classification performance through an adversarial learning network that shares the failure classification characteristic information. Therefore, the proposed method can provide a more stable and general classification performance by expanding the potential space to minimize the discrepancy between domain data. The experimental results of the proposed model showed about 88% accuracy for a real-machine dataset, and compared to the existing cross-domain adaptive learning methods, it showed a performance improvement of about 5-10%. According to the results of this study, it is expected to be an effective solution for the problem of equipment failure diagnosis at actual industrial sites.
Effective Transfer Learning in Text Classification with the Label-Based Discriminative Feature Learning
http://doi.org/10.5626/JOK.2022.49.3.214
The performance of the natural language processing with transfer learning methodology has improved by pre-training language models with a large amount of general data and applying them on downstream tasks. However, the problem is that it learns general features rather than those specific to the downstream tasks as the data used in pre-training is irrelevant to the downstream tasks. This paper proposes a novel learning method for embeddings of pre-trained models to learn specific features of the downstream tasks. The proposed method is to learn the label feature of the downstream tasks through contrast learning with label embedding and sampled data pairs. To demonstrate the performance of the proposed method, we conducted experiments on sentence classification datasets and evaluated whether features of downstream tasks have been learned through PCA(Principal component analysis) and clustering on embeddings.
Using Vertical and Horizonal Hidden Vector of BERT, Attention-based Separated Transfer Learning Model for Dialog Response Selection
http://doi.org/10.5626/JOK.2021.48.1.119
The purpose of this paper is to create a dialog response selection system that accurately identifies the next utterance (one correct answer out of 100 candidates) of a given dialog based on data provided by DSTC. To this end, BERT was used; BERT can be used for multiple purposes and achieves high performance, but it is not easy to customize the model, and it is also difficult to transform the input data format for performance optimization. To address these issues, we propose an effective data augmentation method, and we also propose an independent transfer learning model that involves extracting contextual attention information (self-attention vector) from the BERT model. This made it possible to achieve a performance improvement of 22.85% over the previous value.
CNN-based Speech Emotion Recognition Model Applying Transfer Learning and Attention Mechanism
Jung Hyun Lee, Ui Nyoung Yoon, Geun-Sik Jo
http://doi.org/10.5626/JOK.2020.47.7.665
Existing speech-based emotion recognition studies can be classified into the case of using a voice feature value and a variety of voice feature values. In the case of using a voice feature value, there is a problem that it is difficult to reflect the complex factors of the voice such as loudness, overtone structure, and range of voices. In the case of using various voice feature values, studies based on machine learning comprise a large number, and there is a disadvantage in that emotion recognition accuracy is relatively lower than that of deep learning-based studies. To resolve this problem, we propose a speech emotion recognition model based on a CNN(Convolutional Neural Network) using Mel-Spectrogram and Mel Frequency Cepstral Coefficient (MFCC) as voice feature values. The proposed model applied transfer learning and attention to improve learning speed and accuracy, and achieved 77.65% emotion recognition accuracy, showing higher performance than the comparison works.
A Transfer Learning Method for Solving Imbalance Data of Abusive Sentence Classification
http://doi.org/10.5626/JOK.2017.44.12.1275
The supervised learning approach is suitable for classification of insulting sentences, but pre-decided training sentences are necessary. Since a Character-level Convolution Neural Network is robust for each character, so is appropriate for classifying abusive sentences, however, has a drawback that demanding a lot of training sentences. In this paper, we propose transfer learning method that reusing the trained filters in the real classification process after the filters get the characteristics of offensive words by generated abusive/normal pair of sentences. We got higher performances of the classifier by decreasing the effects of data shortage and class imbalance. We executed experiments and evaluations for three datasets and got higher F1-score of character-level CNN classifier when applying transfer learning in all datasets.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr