• Clean Technology
• /
• v.28 no.4
• /
• pp.323-330
• /
• 2022

Microfluidic paper-based analytical devices (μPADs) have recently been in the spotlight for their applicability in point-of-care diagnostics and environmental material detection. This study presents a double-sided printing method for fabricating 3D-μPADs, providing simple and cost effective metal ion detection. The design of the 3D-μPAD was made into an acryl stamp by laser cutting and then coating it with a thin layer of PDMS using the spin-coating method. This fabricated stamp was used to form the 3D structure of the hydrophobic barrier through a double-sided contact printing method. The fabrication of the 3D hydrophobic barrier within a single sheet was optimized by controlling the spin-coating rate, reagent ratio and contacting time. The optimal conditions were found by analyzing the area change of the PDMS hydrophobic barrier and hydrophilic channel using ink with chromatography paper. Using the fabricated 3D-μPAD under optimized conditions, Ni²⁺, Cu²⁺, Hg²⁺, and pH were detected at different concentrations and displayed with color intensity in grayscale for quantitative analysis using ImageJ. This study demonstrated that a 3D-μPAD biosensor can be applied to detect metal ions without special analysis equipment. This 3D-μPAD provides a highly portable and rapid on-site monitoring platform for detecting multiple heavy metal ions with extremely high repeatability, which is useful for resource-limited areas and developing countries.

• KIPS Transactions on Software and Data Engineering
• /
• v.13 no.1
• /
• pp.35-49
• /
• 2024

Video captioning technology, as a significant outcome of the integration between computer vision and natural language processing, has emerged as a key research direction in the field of artificial intelligence. This technology aims to achieve automatic understanding and language expression of video content, enabling computers to transform visual information in videos into textual form. This paper provides an initial analysis of the research trends in deep learning-based video captioning and categorizes them into four main groups: CNN-RNN-based Model, RNN-RNN-based Model, Multimodal-based Model, and Transformer-based Model, and explain the concept of each video captioning model. The features, pros and cons were discussed. This paper lists commonly used datasets and performance evaluation methods in the video captioning field. The dataset encompasses diverse domains and scenarios, offering extensive resources for the training and validation of video captioning models. The model performance evaluation method mentions major evaluation indicators and provides practical references for researchers to evaluate model performance from various angles. Finally, as future research tasks for video captioning, there are major challenges that need to be continuously improved, such as maintaining temporal consistency and accurate description of dynamic scenes, which increase the complexity in real-world applications, and new tasks that need to be studied are presented such as temporal relationship modeling and multimodal data integration.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.1-17
• /
• 2017

The deep learning framework is software designed to help develop deep learning models. Some of its important functions include "automatic differentiation" and "utilization of GPU". The list of popular deep learning framework includes Caffe (BVLC) and Theano (University of Montreal). And recently, Microsoft's deep learning framework, Microsoft Cognitive Toolkit, was released as open-source license, following Google's Tensorflow a year earlier. The early deep learning frameworks have been developed mainly for research at universities. Beginning with the inception of Tensorflow, however, it seems that companies such as Microsoft and Facebook have started to join the competition of framework development. Given the trend, Google and other companies are expected to continue investing in the deep learning framework to bring forward the initiative in the artificial intelligence business. From this point of view, we think it is a good time to compare some of deep learning frameworks. So we compare three deep learning frameworks which can be used as a Python library. Those are Google's Tensorflow, Microsoft's CNTK, and Theano which is sort of a predecessor of the preceding two. The most common and important function of deep learning frameworks is the ability to perform automatic differentiation. Basically all the mathematical expressions of deep learning models can be represented as computational graphs, which consist of nodes and edges. Partial derivatives on each edge of a computational graph can then be obtained. With the partial derivatives, we can let software compute differentiation of any node with respect to any variable by utilizing chain rule of Calculus. First of all, the convenience of coding is in the order of CNTK, Tensorflow, and Theano. The criterion is simply based on the lengths of the codes and the learning curve and the ease of coding are not the main concern. According to the criteria, Theano was the most difficult to implement with, and CNTK and Tensorflow were somewhat easier. With Tensorflow, we need to define weight variables and biases explicitly. The reason that CNTK and Tensorflow are easier to implement with is that those frameworks provide us with more abstraction than Theano. We, however, need to mention that low-level coding is not always bad. It gives us flexibility of coding. With the low-level coding such as in Theano, we can implement and test any new deep learning models or any new search methods that we can think of. The assessment of the execution speed of each framework is that there is not meaningful difference. According to the experiment, execution speeds of Theano and Tensorflow are very similar, although the experiment was limited to a CNN model. In the case of CNTK, the experimental environment was not maintained as the same. The code written in CNTK has to be run in PC environment without GPU where codes execute as much as 50 times slower than with GPU. But we concluded that the difference of execution speed was within the range of variation caused by the different hardware setup. In this study, we compared three types of deep learning framework: Theano, Tensorflow, and CNTK. According to Wikipedia, there are 12 available deep learning frameworks. And 15 different attributes differentiate each framework. Some of the important attributes would include interface language (Python, C ++, Java, etc.) and the availability of libraries on various deep learning models such as CNN, RNN, DBN, and etc. And if a user implements a large scale deep learning model, it will also be important to support multiple GPU or multiple servers. Also, if you are learning the deep learning model, it would also be important if there are enough examples and references.

• Journal of the Korean Applied Science and Technology
• /
• v.36 no.4
• /
• pp.1472-1484
• /
• 2019

This study aimed to verify the effects of nutritional status, K-ADL, K-IADL, and social network on the life satisfaction of the elderly in home. Total 213 research subjects participated in this study, and their average age was 71.38±5.59. As the methods of analysis, using the SPSS 21.0, this study examined the differences between variables in accordance with the general characteristics, and then verified the correlations between independent variables of nutritional status, K-ADL, K-IADL, social network(family networks, friends networks), and life satisfaction. In order to verify the factors having effects on the life satisfaction of the elderly in home, the stepwise multiple regression analysis was conducted. In the results of this study, in the general characteristics, the life satisfaction showed statistically significant differences in accordance with education(F=5.280, p=.002), economic condition(F=22.407, p<.001), monthly income(F=3.181, p=.015), and subjective health status(F=14.933, p<.001). In the results of verifying the correlation between independent variables, the life satisfaction showed positive correlations with family networks(r=268, p<.001) and friends networks(r=.286, p<.001) while the nutritional status(r=-.222, p=.001), K-IADL(r=-.235, p=.001), and interdependent social support(r=-.283, p<.001) showed negative correlations. The predictive factors on the life satisfaction of the elderly in home included the economic condition(β=.358, p<.001), subjective health status(β=.245, p<.001), interdependent social support(β=-.158, p=.009), and K-IADL(β=-.153, p=.012), and the explanatory power was 30.1%. The regression model was statistically significant(F=23.778, p<.001). Based on such results of this study, it would be necessary to develop programs that could maintain and improve the health of the elderly, and also provide financial support to the elderly suffering from economic hardship, in order to improve the life satisfaction of the elderly in home. Moreover, there should be the concrete measures for vitalizing the community-connected activities for interdependent social support.

• Information Systems Review
• /
• v.18 no.4
• /
• pp.17-42
• /
• 2016

Information security incidents caused by authorized insiders are increasing in financial firms, and this increase is particularly increased by outsourced contractors. With the increase in outsourcing in financial firms, outsourced contractors having authorized right has become a threat and could violate an organization's information security policy. This study aims to analyze the differences between own employees and outsourced contractors and to determine the factors affecting the violation of information security policy to mitigate information security incidents. This study examines the factors driving employees to violate information security policy in financial firms based on the theory of planned behavior, general deterrence theory, and information security awareness, and the moderating effects of employee type between own employees and outsourced contractors. We used 363 samples that were collected through both online and offline surveys and conducted partial least square-structural equation modeling and multiple group analysis to determine the differences between own employees (246 samples, 68%) and outsourced contractors (117 samples, 32%). We found that the perceived sanction and information security awareness support the information security policy violation attitude and subjective norm, and the perceived sanction does not support the information security policy behavior control. The moderating effects of employee type in the research model were also supported. According to the t-test result between own employees and outsourced contractors, outsourced contractors' behavior control supported information security violation intention but not subject norms. The academic implications of this study is expected to be the basis for future research on outsourced contractors' violation of information security policy and a guide to develop information security awareness programs for outsourced contractors to control these incidents. Financial firms need to develop an information security awareness program for outsourced contractors to increase the knowledge and understanding of information security policy. Moreover, this program is effective for outsourced contractors.