• Genomics & Informatics
• /
• 제19권3호
• /
• pp.22.1-22.5
• /
• 2021

Automatic document classification for highly interrelated classes is a demanding task that becomes more challenging when there is little labeled data for training. Such is the case of the coronavirus disease 2019 (COVID-19) clinical repository-a repository of classified and translated academic articles related to COVID-19 and relevant to the clinical practice-where a 3-way classification scheme is being applied to COVID-19 literature. During the 7th Biomedical Linked Annotation Hackathon (BLAH7) hackathon, we performed experiments to explore the use of named-entity-recognition (NER) to improve the classification. We processed the literature with OntoGene's Biomedical Entity Recogniser (OGER) and used the resulting identified Named Entities (NE) and their links to major biological databases as extra input features for the classifier. We compared the results with a baseline model without the OGER extracted features. In these proof-of-concept experiments, we observed a clear gain on COVID-19 literature classification. In particular, NE's origin was useful to classify document types and NE's type for clinical specialties. Due to the limitations of the small dataset, we can only conclude that our results suggests that NER would benefit this classification task. In order to accurately estimate this benefit, further experiments with a larger dataset would be needed.

• 한국멀티미디어학회논문지
• /
• 제25권1호
• /
• pp.39-51
• /
• 2022

Image-based gender classification and age estimation of human are classic problems in computer vision. Most of researches in this field focus just only one task of either gender classification or age estimation and most of the reported methods for each task focus on accuracy performance and are not computationally light. Thus, running both tasks together simultaneously on low cost mobile or embedded systems with limited cpu processing speed and memory capacity are practically prohibited. In this paper, we propose a novel light-weight gender classification and age estimation method based on ensemble multitasking deep learning with light-weight processing neural network architecture, which processes both gender classification and age estimation simultaneously and in real-time even for embedded systems. Through experiments over various well-known datasets, it is shown that the proposed method performs comparably to the state-of-the-art gender classification and/or age estimation methods with respect to accuracy and runs fast enough (average 14fps) on a Jestson Nano embedded board.

• 아동학회지
• /
• 제20권3호
• /
• pp.259-273
• /
• 1999

This studied investigated children's music identification, classification, and seriation cognitive task performance abilities by age and sex. The subjects were l20 six-, eight-, and ten-year-old school children. There were significant positive correlations among music cognition tasks and significant age and sex differences within each of the music tasks. Ten-year-old children were more likely to complete their music identification tasks than the younger children and girls were more likely than boys to complete their music identification tasks. Eight- and 10-year-old children were more likely to complete their music classification tasks than the younger group. Piagetian stage theory was demonstrated in children's music classification task performance. There was an age-related increase in the performance of the music seriation tasks. Developmental sequential theory was demonstrated in music seriation performance.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.481-488
• /
• 2007

In this paper, we propose a method to classify movie review documents into positive or negative opinions. There are several approaches to classify documents. The previous studies, however, used only a single classifier for the classification task. We describe a multiple classifier for the review document classification task. The method consists of three classifiers based on SVMs, ME and score calculation. We apply two voting methods and SVMs to the integration process of single classifiers. The integrated methods improved the accuracy as compared with the three single classifiers. The experimental results show the effectiveness of our method.

• 대한인간공학회:학술대회논문집
• /
• 대한인간공학회 1997년도 추계학술대회논문집
• /
• pp.437-440
• /
• 1997

The association of poor body postures with pains or symptoms of musculoskeletal discorders has been reported by many researchers. An ergonomic evaluation of postural stresses as well as biomechanical stresses is also important especially when a job involves highly repetitive or prolonged poor body postures. The human body is divided into five parts: shoulder/upper arm, lower arm/wrist, back, neck, lower extremities. A work-sampling based macropostural classification system was developed to characterize various postures in this study. Application of the posture classification schema developed in this study to 7 automobile assembly tasks showed that the schema can be used as a tool to didntify the operation and tasks involving highly stressful body postures. This posture classification schema can also be applied as a basis for quantitive evaluating the workload of manual task.

• 대한물리의학회지
• /
• 제12권1호
• /
• pp.121-129
• /
• 2017

PURPOSE: This study was conducted to determine the effect of dual-task training (based on the International Classification of Functioning, Disability, and Health; ICF) on walking ability and self-efficacy in individuals with chronic stroke. METHODS: 22 chronic stroke patients participated in this study. Participants were randomly allocated into either the single-task group (n=11) or the dual-task group (n=11). Both groups had physical training three a week for 4 weeks, and at a three-week follow-up. Outcome measures included the 10m walking test (10MWT), figure of 8 walk test (F8WT), dynamic gait index (DGI), and Self-efficacy scale. All data were analyzed using SPSS 18.0 for Windows. Between-group and within-group comparison were analyzed by using the Mann-Whitney U test and Wilcoxon singed-rank test respectively. RESULTS: In the dual-task group, the 10MWT, time and steps of F8WT, DGI, and self-efficacy showed significant differences between pre- and post-test (p<.05). The Changes between the pre- and post-test values of 10MWT (p<.05), DGI (p<.05), and self-efficacy scale (p<.05) showed significant differences between the dual-task group and single-task group. CONCLUSION: Participants reported improved walking ability and self-efficacy, suggesting that dual-task training holds promise in the rehabilitation of walking in chronic stroke patients. This study showed that ICF-based on a dual-task protocol contiributes to motor learning after chronic stroke.

• 한국안전학회지
• /
• 제16권4호
• /
• pp.168-174
• /
• 2001

For human error analysis, the structure and situation of a task should be analyzed in advance. The paper introduces Structured Information Analysis (SIA) as a task analysis method for error analysis, and delineates the result of application on the emergency procedure of Korean Standard Nuclear Plants (KSNPs). From the task analysis about emergency procedure of KSNP, total 72 specific task goals were identified in the level of system function, and 86 generic tasks were classified from the viewpoint of physical sameness of the task description. Human errors are dependent on task types so that the result of task analysis would be used as a basis for the error analysis on the emergency tasks in nuclear power plants.

• 로봇학회논문지
• /
• 제1권1호
• /
• pp.1-8
• /
• 2006

In this paper, we propose a methodology for classifying types of lower limb disability and their mechanical structure, based on extensive survey of previous developments. We also propose a task-oriented design with human-friendly and energy-efficient assistive system. The result can be used for optimal design of wearable walking-assistive robot considering the type of disability and the content of task.

• International Journal of Computer Science & Network Security
• /
• 제22권3호
• /
• pp.163-172
• /
• 2022

The interconnection of an enormous number of devices into the Internet at a massive scale is a consequence of the Internet of Things (IoT). As a result, tasks offloading from these IoT devices to remote cloud data centers become expensive and inefficient as their number and amount of its emitted data increase exponentially. It is also a challenge to optimize IoT device energy consumption while meeting its application time deadline and data delivery constraints. Consequently, Fog Computing was proposed to support efficient IoT tasks processing as it has a feature of lower service delay, being adjacent to IoT nodes. However, cloud task offloading is still performed frequently as Fog computing has less resources compared to remote cloud. Thus, optimized schemes are required to correctly characterize and distribute IoT devices tasks offloading in a hybrid IoT, Fog, and cloud paradigm. In this paper, we present a detailed survey and classification of of recently published research articles that address the energy efficiency of task offloading schemes in IoT-Fog-Cloud paradigm. Moreover, we also developed a taxonomy for the classification of these schemes and provided a comparative study of different schemes: by identifying achieved advantage and disadvantage of each scheme, as well its related drawbacks and limitations. Moreover, we also state open research issues in the development of energy efficient, scalable, optimized task offloading schemes for Fog computing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권4호
• /
• pp.1275-1292
• /
• 2021

As a fine-grained classification problem, aspect-level sentiment classification predicts the sentiment polarity for different aspects in context. To address this issue, researchers have widely used attention mechanisms to abstract the relationship between context and aspects. Still, it is difficult to effectively obtain a more profound semantic representation, and the strong correlation between local context features and the aspect-based sentiment is rarely considered. In this paper, a hybrid attention capsule network for aspect-level sentiment classification (ABASCap) was proposed. In this model, the multi-head self-attention was improved, and a context mask mechanism based on adjustable context window was proposed, so as to effectively obtain the internal association between aspects and context. Moreover, the dynamic routing algorithm and activation function in capsule network were optimized to meet the task requirements. Finally, sufficient experiments were conducted on three benchmark datasets in different domains. Compared with other baseline models, ABASCap achieved better classification results, and outperformed the state-of-the-art methods in this task after incorporating pre-training BERT.