• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.40-48
• /
• 2023

Speech Emotions recognition has become the active research theme in speech processing and in applications based on human-machine interaction. In this work, our system is a two-stage approach, namely feature extraction and classification engine. Firstly, two sets of feature are investigated which are: the first one is extracting only 13 Mel-frequency Cepstral Coefficient (MFCC) from emotional speech samples and the second one is applying features fusions between the three features: Zero Crossing Rate (ZCR), Teager Energy Operator (TEO), and Harmonic to Noise Rate (HNR) and MFCC features. Secondly, we use two types of classification techniques which are: the Support Vector Machines (SVM) and the k-Nearest Neighbor (k-NN) to show the performance between them. Besides that, we investigate the importance of the recent advances in machine learning including the deep kernel learning. A large set of experiments are conducted on Surrey Audio-Visual Expressed Emotion (SAVEE) dataset for seven emotions. The results of our experiments showed given good accuracy compared with the previous studies.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.250-262
• /
• 2024

Air-writing recognition is relevant in areas such as natural human-computer interaction, augmented reality, and virtual reality. A trajectory is the most natural way to represent air writing. We analyze the recognition accuracy of words written in air considering five features, namely, writing direction, curvature, trajectory, orthocenter, and ellipsoid, as well as different parameters of a hidden Markov model classifier. Experiments were performed on two representative datasets, whose sample trajectories were collected using a Leap Motion Controller from a fingertip performing air writing. Dataset D₁ contains 840 English words from 21 classes, and dataset D₂ contains 1600 English words from 40 classes. A genetic algorithm was combined with a hidden Markov model classifier to obtain the best subset of features. Combination ftrajectory, orthocenter, writing direction, curvatureg provided the best feature set, achieving recognition accuracies on datasets D₁ and D₂ of 98.81% and 83.58%, respectively.

• BMB Reports
• /
• v.50 no.4
• /
• pp.226-231
• /
• 2017

At the post-transcriptional and translational levels, microRNA (miRNA) represses protein-coding genes via seed pairing to the 3' untranslated regions (UTRs) of mRNA. Although working models of miRNA-mediated gene silencing are successfully established using miRNA transfections and knockouts, the regulatory interaction between miRNA and long non-coding RNA (lncRNA) remain unknown. In particular, how the mRNA-resembling lncRNAs with 5' cap, 3' poly(A)-tail, or coding features, are regulated by miRNA is yet to be examined. We therefore investigated the functional interaction between miRNAs and lncRNAs with/without those features, in miRNA-transfected early zebrafish embryos. We observed that the greatest determinants of the miRNA-mediated silencing of lncRNAs were the 5' cap and 3' poly(A)-tails in lncRNAs, at both the post-transcriptional and translational levels. The lncRNAs confirmed to contain 5' cap, 3' poly(A)-tail, and the canonical miRNA target sites, were observed to be repressed in the level of both RNA and ribosome-protected fragment, while those with the miRNA target sites and without 5' cap and 3' poly(A)-tail, were not robustly repressed by miRNA introduction, thus suggesting a role as a miRNA-decoy.

• Journal of Korean Elementary Science Education
• /
• v.39 no.1
• /
• pp.40-53
• /
• 2020

This study analyzed the features of norms formed in mobile-based science problem-solving and interpreted them from the perspective of digital citizenship. For this, we implemented two mobile-based science problem-solving activities for nine elementary school preparatory teachers composed of two groups, and analyzed the norms observed in their activities. As a result, four norms were found as follows. First, the information presented as a basis should be scientifically reliable. Second, the information need to be searched widely, but the information should be selected and reconstructed in relation to the problem. Third, in a mobile environment, the ideas should be clearly expressed and understood. Fourth, courtesies in mobile interaction should be represented more politely than in face-to-face interaction. Based on the four norms found in this study, we discussed the characteristics and factors of digital citizenship for judging scientifically reliable and relevant information and expressing ideas clearer in mobile environment. Finally, we suggested the educational implications for fostering digital citizens who can judge and practice 'science issues' in a 'mobile environment'.

• ETRI Journal
• /
• v.44 no.6
• /
• pp.1004-1019
• /
• 2022

For autonomous driving without high-definition maps, we present a model capable of generating multiple plausible paths from egocentric images for autonomous vehicles. Our generative model comprises two neural networks: feature extraction network (FEN) and path generation network (PGN). The FEN extracts meaningful features from an egocentric image, whereas the PGN generates multiple paths from the features, given a driving intention and speed. To ensure that the paths generated are plausible and consistent with the intention, we introduce an attentive discriminator and train it with the PGN under a generative adversarial network framework. Furthermore, we devise an interaction model between the positions in the paths and the intentions hidden in the positions and design a novel PGN architecture that reflects the interaction model for improving the accuracy and diversity of the generated paths. Finally, we introduce ETRIDriving, a dataset for autonomous driving, in which the recorded sensor data are labeled with discrete high-level driving actions, and demonstrate the state-of-the-art performance of the proposed model on ETRIDriving in terms of accuracy and diversity.

• BMB Reports
• /
• v.57 no.6
• /
• pp.273-280
• /
• 2024

Cancer cells metastasize to distant organs by altering their characteristics within the tumor microenvironment (TME) to effectively overcome challenges during the multistep tumorigenesis. Plasticity endows cancer cell with the capacity to shift between different morphological states to invade, disseminate, and seed metastasis. The epithelial-to-mesenchymal transition (EMT) is a theory derived from tissue biopsy, which explains the acquisition of EMT transcription factors (TFs) that convey mesenchymal features during cancer migration and invasion. On the other hand, adherent-to-suspension transition (AST) is an emerging theory derived from liquid biopsy, which describes the acquisition of hematopoietic features by AST-TFs that reprograms anchorage dependency during the dissemination of circulating tumor cells (CTCs). The induction and plasticity of EMT and AST dynamically reprogram cell-cell interaction and cell-matrix interaction during cancer dissemination and colonization. Here, we review the mechanisms governing cellular plasticity of AST and EMT during the metastatic cascade and discuss therapeutic challenges posed by these two morphological adaptations to provide insights for establishing new therapeutic interventions.

• Journal of Information Technology Applications and Management
• /
• v.31 no.2
• /
• pp.35-49
• /
• 2024

With the development of e-commerce, live streaming e-commerce, as an emerging marketing method, is on the rise. It integrates various ways of information delivery, providing consumers with unprecedented shopping experiences, particularly through its interactive nature, which can increase audience engagement and immersion. This study delves into how interactive elements in live streaming e-commerce influence consumer emotions and purchase intentions. By employing literature review and empirical analysis methods, we analyzed various interactive factors in the live streaming e-commerce environment and revealed the process through which these factors stimulate audience emotions and lead to specific purchasing behaviors. The results confirm that the interactive appeal of live streaming e-commerce significantly influences consumers' positive emotional responses, consequently enhancing purchase intentions. This study aims to explore the relationship between the interactive features of live streaming e-commerce and consumer emotional responses and purchase intentions, thereby filling theoretical gaps in the field of live streaming e-commerce and proposing new marketing theories. Additionally, by analyzing how interactive features stimulate consumers, optimal live content strategies can be proposed for live streaming e-commerce platforms and hosts, thus aiding in the improvement of marketing strategies and sales effectiveness.

• IMMUNE NETWORK
• /
• v.21 no.3
• /
• pp.19.1-19.18
• /
• 2021

Clinical and molecular phenotypes of asthma are complex. The main phenotypes of adult asthma are characterized by eosinophil and/or neutrophil cell dominant airway inflammation that represent distinct clinical features. Upper and lower airways constitute a unique system and their interaction shows functional complementarity. Although human upper airway contains various indigenous commensals and opportunistic pathogenic microbiome, imbalance of this interactions lead to pathogen overgrowth and increased inflammation and airway remodeling. Competition for epithelial cell attachment, different susceptibilities to host defense molecules and antimicrobial peptides, and the production of proinflammatory cytokine and pattern recognition receptors possibly determine the pattern of this inflammation. Exposure to environmental factors, including infection, air pollution, smoking is commonly associated with asthma comorbidity, severity, exacerbation and resistance to anti-microbial and steroid treatment, and these effects may also be modulated by host and microbial genetics. Administration of probiotic, antibiotic and corticosteroid treatment for asthma may modify the composition of resident microbiota and clinical features. This review summarizes the effect of some environmental factors on the upper respiratory microbiome, the interaction between host-microbiome, and potential impact of asthma treatment on the composition of the upper airway microbiome.

• Journal of Science Education
• /
• v.37 no.1
• /
• pp.117-130
• /
• 2013

The purpose of this study was to analyze the patterns and features of interaction in teacher interviewing with high school students' small group for biology learning. The interactions in variety between the students and between the students and the teacher were made as the interviews with each small group were repeated to feedback for biology learning. The patterns of interaction were categorized into four types by interactive level of interaction among group members and a teacher: leader representation without interaction among students and the teacher(LR, leader representation), interaction among a part of students and the teacher(PSI, partial students interaction), active interaction among students inside the group, but only interaction between the teacher and the leader student(SAI, students active interaction), and interaction between all of the students and the teacher(teacher-students active interaction). Even though complex patterns of interactions were made among the students at the initial stage of insufficient understanding on the study concept, the simple interaction processes were shown as students had gradually completed the understanding on the concept. It was displayed that the interaction in the small group for biology study provides the opportunity to confirm and understand the concept to the students who were poor at the understanding on the concept, and it can influence positively on the mutual creation of study concept.

• Journal of the Ergonomics Society of Korea
• /
• v.31 no.3
• /
• pp.427-435
• /
• 2012

The aim of this study is to investigate facial temperature changes induced by facial expression and emotional state in order to recognize a persons emotion using facial thermal images. Background: Facial thermal images have two advantages compared to visual images. Firstly, facial temperature measured by thermal camera does not depend on skin color, darkness, and lighting condition. Secondly, facial thermal images are changed not only by facial expression but also emotional state. To our knowledge, there is no study to concurrently investigate these two sources of facial temperature changes. Method: 231 students participated in the experiment. Four kinds of stimuli inducing anger, fear, boredom, and neutral were presented to participants and the facial temperatures were measured by an infrared camera. Each stimulus consisted of baseline and emotion period. Baseline period lasted during 1min and emotion period 1~3min. In the data analysis, the temperature differences between the baseline and emotion state were analyzed. Eyes, mouth, and glabella were selected for facial expression features, and forehead, nose, cheeks were selected for emotional state features. Results: The temperatures of eyes, mouth, glanella, forehead, and nose area were significantly decreased during the emotional experience and the changes were significantly different by the kind of emotion. The result of linear discriminant analysis for emotion recognition showed that the correct classification percentage in four emotions was 62.7% when using both facial expression features and emotional state features. The accuracy was slightly but significantly decreased at 56.7% when using only facial expression features, and the accuracy was 40.2% when using only emotional state features. Conclusion: Facial expression features are essential in emotion recognition, but emotion state features are also important to classify the emotion. Application: The results of this study can be applied to human-computer interaction system in the work places or the automobiles.