• Environmental and Resource Economics Review
• /
• v.22 no.4
• /
• pp.671-689
• /
• 2013

Transmission mechanisms of volatility between two crude oil markets (WTI and Brent markets) have drawn the attention of numerous academics and practitioners because they both play crucial roles in portfolio and risk management in crude oil markets. In this context, we examined the volatility linkages between two representative crude oil markets using a VECM and an asymmetric bivariate GARCH model. First, looking at the return transmission through the VECM test, we found a long-run equilibrium and bidirectional relationship between two crude oil markets. However, the estimation results of the GARCH-BEKK model suggest that there is unidirectional volatility spillover from the WTI market to the Brent market, implying that the WTI market tends to exert influence over the Brent market and not vice versa. Regarding asymmetric volatility transmission, we also found that bad news volatility in the WTI market increases the volatility of the Brent market. Thus, WTI information is transmitted into the Brent market, indicating that the prices of the WTI market seem to lead the prices of the Brent market.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.90-100
• /
• 2020

Named entity recognition (NER) continues to be an important task in natural language processing because it is featured as a subtask and/or subproblem in information extraction and machine translation. In Urdu language processing, it is a very difficult task. This paper proposes various deep recurrent neural network (DRNN) learning models with word embedding. Experimental results demonstrate that they improve upon current state-of-the-art NER approaches for Urdu. The DRRN models evaluated include forward and bidirectional extensions of the long short-term memory and back propagation through time approaches. The proposed models consider both language-dependent features, such as part-of-speech tags, and language-independent features, such as the "context windows" of words. The effectiveness of the DRNN models with word embedding for NER in Urdu is demonstrated using three datasets. The results reveal that the proposed approach significantly outperforms previous conditional random field and artificial neural network approaches. The best f-measure values achieved on the three benchmark datasets using the proposed deep learning approaches are 81.1%, 79.94%, and 63.21%, respectively.

• Nuclear Engineering and Technology
• /
• v.52 no.6
• /
• pp.1327-1333
• /
• 2020

The global warming phenomenon emerges from the issue of climate change, which attracts the attention of intellectuals towards clean energy sources from dirty energy sources. Among clean sources, nuclear energy is getting immense attention among policymakers. However, the role of nuclear energy in pollution emissions reduction has remained inconclusive and demand for further investigation. Therefore, the current study contributes to extend knowledge by investigating the nexus between nuclear energy, economic growth, and CO₂ emissions in a developing country context such as Pakistan for the period between 1973 and 2017. The auto-regressive distributive lag model summarizes the nuclear energy has negative effect on environmental pollution as it releases carbon emission in the environment. Moreover, vector error correction Granger causality provides evidence for bidirectional causality between nuclear energy and carbon emissions. These interesting findings provide new insight, and policy guidelines provided based on these results.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.238-246
• /
• 2021

The rapid rise of the Internet and social media has resulted in a large number of text-based reviews being placed on sites such as social media. In the age of social media, utilizing machine learning technologies to analyze the emotional context of comments aids in the understanding of QoS for any product or service. The classification and analysis of user reviews aids in the improvement of QoS. (Quality of Services). Machine Learning algorithms have evolved into a powerful tool for analyzing user sentiment. Unlike traditional categorization models, which are based on a set of rules. In sentiment categorization, Bidirectional Long Short-Term Memory (BiLSTM) has shown significant results, and Convolution Neural Network (CNN) has shown promising results. Using convolutions and pooling layers, CNN can successfully extract local information. BiLSTM uses dual LSTM orientations to increase the amount of background knowledge available to deep learning models. The suggested hybrid model combines the benefits of these two deep learning-based algorithms. The data source for analysis and classification was user reviews of Indian Railway Services on Twitter. The suggested hybrid model uses the Keras Embedding technique as an input source. The suggested model takes in data and generates lower-dimensional characteristics that result in a categorization result. The suggested hybrid model's performance was compared using Keras and Word2Vec, and the proposed model showed a significant improvement in response with an accuracy of 95.19 percent.

• Journal of Oral Medicine and Pain
• /
• v.40 no.3
• /
• pp.89-95
• /
• 2015

All living organisms have a biological clock that orchestrates every biological process and function, and this internal clock operates following a circadian rhythm. This biological clock is known to influence various clinical indicators such as blood pressure and body temperature. Also, the fluctuation of signs and symptoms of diseases including pain disorders are affected by circadian rhythm. It has been reported that the pain intensity of various somatic and neuropathic pain disorders show unique pain patterns that depend on the passage of time. The generation of pain patterns could be explained by extrinsic (e.g., physical activity, tactile stimulation, ambient temperature) and also intrinsic factors (neural and neuroendocrine modulation) that are related to the circadian rhythm. It is important to recognize and identify the individual pain pattern in pain therapy to approve treatment outcome. Moreover, chronotherapeutics which considers pain patterns and pharmacokinetics in context of the circadian rhythm could produce greater analgesia in response to medication. However, only a limited number of studies handle the issue of pain patterns according to circadian rhythm and chronotherapeutics in the orofacial region. The present review intends to reflect on the most recent and relevant data concerning the bidirectional relation between pain disorders of the orofacial region and circadian patterns.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.16 no.3
• /
• pp.33-48
• /
• 2014

Based on the advent and dissemination of new developments concerning information & telecommunications technology, web services have brought new paradigms into society, thus facilitating the birth and evolution of various service industries to society as a whole. This study is aimed at investigating the expansion of the first Birthday party culture and design examples of the first Birthday partywear appearing in social media, through an inquiry into the communication functions inherent in social media. Also, the development of the first Birthday partywear designs for women aged 20 to 30 years was accomplished by categorically analyzing design characteristics in preferred fashion styles uploaded and shared within online childcare communities. First, it can be concluded that due to the bidirectional flow of information between corporations and consumers occurring from the expansion of social media, the entire structure of the market is undergoing great changes. Next, the need for the supply of professionalized the first Birthday partywear can be proved by the influx of party planners and caterers into this new industry. Third, Through a categorical analysis of these 523 photos, elegance style was the most preferred while classic and romantic styles followed. Last of all, 5 pieces of partywear reflecting contemporary consumer lifestyles which focus on 'enjoying one's own life' were created under the concept of 'Romantic chic'. The created designs aim to present a style which follows the predominant trend of elegance, classic and romantic, whilst keeping sensitivity in moderation. In this context, this study has aimed to present fundamental research data in the field of online the first Birthday partywear, through the development of the first Birthday partywear design based on the first Birthday party consumer characteristics gleaned from various forms of social media.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.8
• /
• pp.243-250
• /
• 2020

Knowledge graph-based question answering not only requires deep understanding of the given natural language questions, but it also needs effective reasoning to find the correct answers on a large knowledge graph. In this paper, we propose a deep neural network model for effective reasoning on a knowledge graph, which can find correct answers to complex questions requiring multi-hop inference. The proposed model makes use of highly expressive bilinear graph neural network (BGNN), which can utilize context information between a pair of neighboring nodes, as well as allows bidirectional feature propagation between each entity node and one of its neighboring nodes on a knowledge graph. Performing experiments with an open-domain knowledge base (Freebase) and two natural-language question answering benchmark datasets(WebQuestionsSP and MetaQA), we demonstrate the effectiveness and performance of the proposed model.

• Phonetics and Speech Sciences
• /
• v.11 no.2
• /
• pp.57-64
• /
• 2019

In this paper, we construct a Korean text-to-speech system using the Merlin toolkit which is an open source system for speech synthesis. In the text-to-speech system, the HMM-based statistical parametric speech synthesis method is widely used, but it is known that the quality of synthesized speech is degraded due to limitations of the acoustic modeling scheme that includes context factors. In this paper, we propose an acoustic modeling architecture that uses deep neural network technique, which shows excellent performance in various fields. Fully connected deep feedforward neural network (DNN), recurrent neural network (RNN), gated recurrent unit (GRU), long short-term memory (LSTM), bidirectional LSTM (BLSTM) are included in the architecture. Experimental results have shown that the performance is improved by including sequence modeling in the architecture, and the architecture with LSTM or BLSTM shows the best performance. It has been also found that inclusion of delta and delta-delta components in the acoustic feature parameters is advantageous for performance improvement.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.131-131
• /
• 2021

Deep learning models, especially those based on long short-term memory (LSTM), have presented their superiority in addressing time series data issues recently. This study aims to comprehensively evaluate the performance of deep learning models that belong to the supervised learning category in streamflow prediction. Therefore, six deep learning models-standard LSTM, standard gated recurrent unit (GRU), stacked LSTM, bidirectional LSTM (BiLSTM), feed-forward neural network (FFNN), and convolutional neural network (CNN) models-were of interest in this study. The Red River system, one of the largest river basins in Vietnam, was adopted as a case study. In addition, deep learning models were designed to forecast flowrate for one- and two-day ahead at Son Tay hydrological station on the Red River using a series of observed flowrate data at seven hydrological stations on three major river branches of the Red River system-Thao River, Da River, and Lo River-as the input data for training, validation, and testing. The comparison results have indicated that the four LSTM-based models exhibit significantly better performance and maintain stability than the FFNN and CNN models. Moreover, LSTM-based models may reach impressive predictions even in the presence of upstream reservoirs and dams. In the case of the stacked LSTM and BiLSTM models, the complexity of these models is not accompanied by performance improvement because their respective performance is not higher than the two standard models (LSTM and GRU). As a result, we realized that in the context of hydrological forecasting problems, simple architectural models such as LSTM and GRU (with one hidden layer) are sufficient to produce highly reliable forecasts while minimizing computation time because of the sequential data nature.

• Information Systems Review
• /
• v.15 no.3
• /
• pp.71-87
• /
• 2013

Companies as well as the Korean government show growing attention to the Smart Work which is enabled by the ongoing development of information and communication technologies (ICTs). Smart Work can be regarded as an extended version of telecommuting or distance work and defined as "working efficiently and conveniently regardless of time and place utilizing ICTs." Smart Work currently puts its emphasis on the work and life balance by changing the ways of working. Despite its emphasis on work and life balance, it is expected the boundaries between work and nonwork would blur, work and nonwork boundaries may become more permeable, and role conflicts would occur more times than before. To find ways to enhance work and life balance while escaping from expected conflicts in the context of Smart Work, we investigate the work and nonwork boundary strengths and the factors affecting them. In the course, we consider asymmetries between the work and nonwork boundary strengths and bidirectional nature of work and nonwork permeability. We develop two research models having work and nonwork boundary strengths as respective dependent variables. We empirically found that work role identification and nonwork-to-work permeability had influences on the boundary strength at work and that work-to-nonwork permeability affected the boundary strength at nonwork. However, nonwork role identification did not show any significant influence on the boundary strength at nonwork.