• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3804-3819
• /
• 2018

The increasing popularity of HTTP adaptive video streaming services has dramatically increased bandwidth requirements on operator networks, which attempt to shape their traffic through Deep Packet inspection (DPI). However, Google and certain content providers have started to encrypt their video services. As a result, operators often encounter difficulties in shaping their encrypted video traffic via DPI. This highlights the need for new traffic classification methods for encrypted HTTP adaptive video streaming to enable smart traffic shaping. These new methods will have to effectively estimate the quality representation layer and playout buffer. We present a new machine learning method and show for the first time that video quality representation classification for (YouTube) encrypted HTTP adaptive streaming is possible. The crawler codes and the datasets are provided in [43,44,51]. An extensive empirical evaluation shows that our method is able to independently classify every video segment into one of the quality representation layers with 97% accuracy if the browser is Safari with a Flash Player and 77% accuracy if the browser is Chrome, Explorer, Firefox or Safari with an HTML5 player.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.5
• /
• pp.3000-3005
• /
• 2015

Reliable monitoring and diagnosis of industrial processes is quite important for in terms of quality and safety. The goal of fault diagnosis is to find process variables responsible for causing specific abnormalities of the process. This work presents a classification-based diagnostic scheme based on nonlinear representation of process data. The use of a nonlinear kernel technique is able to reduce the size of the data considered and provides efficient and reliable representation of the measurement data. As a filtering stage a preprocessing is performed to eliminate unwanted parts of the data with enhanced performance. The case study of an industrial batch process has shown that the performance of the scheme outperformed other methods. In addition, the use of a nonlinear representation technique and filtering improved the diagnosis performance in the case study.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.242-252
• /
• 2021

Following the intuition that the local information in time instances is hardly incorporated into the posterior sequence in long short-term memory (LSTM), this paper proposes an attention augmented mechanism for fault diagnosis of the complex chemical process data. Unlike conventional fault diagnosis and classification methods, an attention mechanism layer architecture is introduced to detect and focus on local temporal information. The augmented deep network results preserve each local instance's importance and contribution and allow the interpretable feature representation and classification simultaneously. The comprehensive comparative analyses demonstrate that the developed model has a high-quality fault classification rate of 95.49%, on average. The results are comparable to those obtained using various other techniques for the Tennessee Eastman benchmark process.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.411-414
• /
• 2021

One of the elements of technology that has become extremely critical within the field of education today is Deep learning. It has been especially used in the area of natural language processing, with some word-representation vectors playing a critical role. However, some of the low-resource languages, such as Swahili, which is spoken in East and Central Africa, do not fall into this category. Natural Language Processing is a field of artificial intelligence where systems and computational algorithms are built that can automatically understand, analyze, manipulate, and potentially generate human language. After coming to discover that some African languages fail to have a proper representation within language processing, even going so far as to describe them as lower resource languages because of inadequate data for NLP, we decided to study the Swahili language. As it stands currently, language modeling using neural networks requires adequate data to guarantee quality word representation, which is important for natural language processing (NLP) tasks. Most African languages have no data for such processing. The main aim of this project is to recognize and focus on the classification of words in English, Swahili, and Korean with a particular emphasis on the low-resource Swahili language. Finally, we are going to create our own dataset and reprocess the data using Python Script, formulate the syllabic alphabet, and finally develop an English, Swahili, and Korean word analogy dataset.

• ETRI Journal
• /
• v.43 no.2
• /
• pp.299-312
• /
• 2021

It is necessary to achieve high performance in the task of zero anaphora resolution (ZAR) for completely understanding the texts in Korean, Japanese, Chinese, and various other languages. Deep-learning-based models are being employed for building ZAR systems, owing to the success of deep learning in the recent years. However, the objective of building a high-quality ZAR system is far from being achieved even using these models. To enhance the current ZAR techniques, we fine-tuned a pretrained bidirectional encoder representations from transformers (BERT). Notably, BERT is a general language representation model that enables systems to utilize deep bidirectional contextual information in a natural language text. It extensively exploits the attention mechanism based upon the sequence-transduction model Transformer. In our model, classification is simultaneously performed for all the words in the input word sequence to decide whether each word can be an antecedent. We seek end-to-end learning by disallowing any use of hand-crafted or dependency-parsing features. Experimental results show that compared with other models, our approach can significantly improve the performance of ZAR.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.239-245
• /
• 2020

Blockchain, machine learning, and big data are among the key components of the future IT track. These technologies are used in various fields; hence their increasing application. This paper discusses the technologies developed in various research fields, such as data representation, Blockchain application, 3D shape recognition and classification, query method, classification method, and search algorithm, to provide insights into the future paradigm. In this paper, we present a summary of 18 high-quality accepted articles following a rigorous review process in the fields of Blockchain, machine learning, and big data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.8
• /
• pp.216-223
• /
• 2019

Fault detection during production processes is one of the required operational tasks to run production processes both safely and consistently. Unexpected operational events or undetected process faults can have a serious impact on the production systems and subsequently on the final products' quality. In addition, such situations may lead to malfunctions or breakdowns of production processes. To reliably detect such abnormalities, a new one-class classification-based detection scheme has recently been developed The proposed method consists of four steps:1) noise filtering, 2) feature selection, 3) nonlinear representation and 4) outlier detection. The performance of the proposed scheme was demonstrated using the multivariate data obtained from a simulation process. The results have shown that the proposed method produced reliable monitoring results and outperforms any existing methods with an average improvement of 25.4%. The use of proper feature selection in the proposed framework yielded better detection performance.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.45-46
• /
• 2018

This paper focuses on human activities monitoring problem using onboard smartphone sensors as data generator. Monitoring such activities can be very important to detect anomalies and prevent disease from patients. Machine learning (ML) algorithms appear to be ideal approaches to use for processing data from smartphone to get sense of how to classify human activities. ML algorithms depend on quality, the quantity and even more important, the properties or features, that can be learnt from data. This paper proposes a mobile virtual reality visualization system that helps to view data representation in a very immersive way so that its quality and discriminative characteristics may be evaluated and improved. The proposed system comes as well with a handy data collecting application that can be accessed directly by the VR visualization part.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.

• KIISE Transactions on Computing Practices
• /
• v.23 no.4
• /
• pp.268-273
• /
• 2017

Recently, deep learning encoder-based approach has been actively applied in the field of sentiment classification. However, Long Short-Term Memory network deep learning encoder, the commonly used architecture, lacks the quality of vector representation when the length of the documents is prolonged. In this study, for effective classification of the sentiment documents, we suggest the use of attention method-based deep learning encoder that generates document vector representation by weighted sum of the outputs of Long Short-Term Memory network based on importance. In addition, we propose methods to modify the attention method-based deep learning encoder to suit the sentiment classification field, which consist of a part that is to applied to window attention method and an attention weight adjustment part. In the window attention method part, the weights are obtained in the window units to effectively recognize feeling features that consist of more than one word. In the attention weight adjustment part, the learned weights are smoothened. Experimental results revealed that the performance of the proposed method outperformed Long Short-Term Memory network encoder, showing 89.67% in accuracy criteria.