• Membrane Journal
• /
• v.32 no.2
• /
• pp.91-99
• /
• 2022

It is a global challenge to fulfill the demand for clean water at an affordable cost to all the strata of the population. Desalination of seawater as well as brackish water by the membrane separation process is a well-established and cost-efficient method. However, there is still inherent problem of membrane fouling, disposal of the reject as well as a capital-intensive process. While electrodialysis (ED) is a membrane-based separation process in which a driving force is the potential difference. The advantages of ED process are excellent efficiency and low operation cost. Ion exchange membrane (IEM) used in the ED process needs to have higher chemical and thermal stability along with excellent mechanical strength for long-term use without losing its efficiency. The ion exchange capacity of the ED membrane is largely dependent on the conductivity of IEMs. In this review, the modification strategy of the pristine membrane to enhance the stability and ion conductivity of cation exchange membrane (CEM) and anion exchange membrane (AEM) is discussed.

• Journal of Software Assessment and Valuation
• /
• v.16 no.2
• /
• pp.109-115
• /
• 2020

In this paper, the problem that occurs when negative voltage is generated using an inexpensive buck device in an IT device that is supplied with a single power by an adapter or battery is analyzed. For the cause analysis, the principle of operation of the buck device and the principle of the inverter circuit were examined, and the circuit characteristics of the inverter circuit were analyzed using the buck device. As a result of the analysis, it was confirmed that the inverter circuit using the buck device initially needs a large starting current, and in particular, in the case of a current capacity that is less than the starting current in the circuit that supplies power, it was confirmed that it could fall into a state similar to the latch-up phenomenon. In order to confirm the analysis result, an experimental circuit was constructed and the input current was checked. If the supply current is sufficient, it is confirmed that over-current flows and starts. If the supply current is insufficient, the circuit cannot start and a latch-up phenomenon occurs.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.29-39
• /
• 2022

Crack detection plays an important role in the maintenance and protection of steel box girder of bridges. However, since the cracks only occupy an extremely small region of the high-resolution images captured from actual conditions, the existing methods cannot deal with this kind of image effectively. To solve this problem, this paper proposed a novel three-stage method based on deep learning technology and morphology operations. The training set and test set used in this paper are composed of 360 images (4928 × 3264 pixels) in steel girder box. The first stage of the proposed model converted high-resolution images into sub-images by using patch-based method and located the region of cracks by CBAM ResNet-50 model. The Recall reaches 0.95 on the test set. The second stage of our method uses the Attention U-Net model to get the accurate geometric edges of cracks based on results in the first stage. The IoU of the segmentation model implemented in this stage attains 0.48. In the third stage of the model, we remove the wrong-predicted isolated points in the predicted results through dilate operation and outlier elimination algorithm. The IoU of test set ascends to 0.70 after this stage. Ablation experiments are conducted to optimize the parameters and further promote the accuracy of the proposed method. The result shows that: (1) the best patch size of sub-images is 1024 × 1024. (2) the CBAM ResNet-50 and the Attention U-Net achieved the best results in the first and the second stage, respectively. (3) Pre-training the model of the first two stages can improve the IoU by 2.9%. In general, our method is of great significance for crack detection.

• Korean Journal of Construction Engineering and Management
• /
• v.23 no.5
• /
• pp.56-64
• /
• 2022

Although pilot projects have been actively carried out from 2017 to present to institutionalize CM at Risk, one of the major tasks for innovation in the construction industry, standards and processes related to Design VE, a key tool for determining GMP in the pre-construction phase, have not yet been established. Therefore, through research and operation status related to CM at Risk and Design VE, and survey on project participants' perception, the problem of the existing design VE process was derived, and the design VE process suitable for the CM at Risk project was proposed. The application plan was proposed in three aspects: Schedule, Cycle, and Process, and the appropriateness and applicability were verified through FGI. The results of this study are expected to be used as basic data on the establishment and legislation of order standards to be made in the future.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.455-462
• /
• 2022

This study attempted to examine the problems of the expression and format of native advertisements appearing on various platforms and to prepare a plan to regulate them. To this end, in-depth interviews were conducted to those in charge of advertising practice and examined. First, as a problem with the expression and format of native advertisements, it was considered that the congestion and deception of indiscriminate native advertisements appearing on various platforms could bring negative perceptions to consumers. For the second user's interaction, it was considered that customized advertising expressions through targeting by platform should be produced. Third, regarding the regulation of native advertisements, it was suggested that regulatory measures for consumer protection should be prepared and that market autonomy should be left to it. A strategic operation plan for native advertising according to various platforms should be prepared.

• Journal of Industrial Convergence
• /
• v.20 no.2
• /
• pp.45-50
• /
• 2022

In this study, an e-portfolio system was constructed and utilized to communicate with students, while processing the overall procedure of teaching-learning activities as data for qualitative improvement in the non-face-to-face educational environment. The e-portfolio system was designed to support the entire process of reflection from the instructor's lesson planning, regular checking of the learner's understanding during the course operation process, online communication, and support for learner-centered educational activities. Analyzing the effectiveness of the communication-based learning effect between instructors and learners using the e-portfolio in liberal arts programming classes, which may be difficult for non-major students, a significant correlation was found in problem-solving skills, and midterm and final exams. Additionally, the result of analyzing the expanded applicability of e-portfolio satisfaction demonstrated a significant correlation with the students' computational thinking ability, test results, assignments, and academic performance. It was found to have a significant effect on the improvement of computational thinking ability. If non-face-to-face education is conducted using the proposed e-portfolio system type, it will be possible to improve the quality of online education, while communicating effectively with students.

• Journal of dental hygiene science
• /
• v.22 no.4
• /
• pp.233-240
• /
• 2022

Background: In modern society, rapid changes in the medical environment have required medical staff to access various information and be competent in active and effective problem-solving through collegial interactions. In line with these changes, universities are aiming to connect education. This study aimed to provide basic data of connected-convergence education by survey the awareness and needs of college students in health-related fields. Methods: This study included 122 college students from the health field. A survey regarding "the awareness and need of connected-convergence education" was conducted and general characteristics of the participants were collected from June to July 2022. Results: The awareness of connected-convergence education was low at 19.7%, but the intention to participate was high at 74.6%. Subject requirements were 18.0% for medical psychology, 13.5% for communication and counseling, 13.5% for medical artificial intelligence technology convergence, and 10.4% for sports health management. In the group showing high satisfaction with the major curriculum, the demand for connected education was also high. For efficient operation, it was investigated that it was necessary to secure specialized training courses, recognition of liberal arts credits, the right to register for courses equal to those of major students, and secure dedicated classrooms. Conclusion: Although the awareness and experience of connected-convergence education among the participants were low, the intention to participate was high. As such a plan to revitalize the university curriculum was required. It is timely to discuss the nurturing of convergence-type talents and multidisciplinary thinking skills. It is meaningful to provide basic data necessary for connected-convergence education in health-related fields at university. Universities should strive to enhance job competency in the health field by providing connected-convergence education based on student demands.

• Journal of Broadcast Engineering
• /
• v.28 no.1
• /
• pp.132-140
• /
• 2023

In this paper, we propose a method for performance enhancement of speech declipping using clipping detector. Clipping occurs when the input speech level exceeds the dynamic range of microphone, and it significantly degrades the speech quality. Recently, many methods for high-performance speech declipping based on machine learning have been developed. However, they often deteriorate the speech signal because of degradation in signal reconstruction process when the degree of clipping is not high. To solve this problem, we propose a new approach that combines the declipping network and clipping detector, which enables a selective declipping operation depending on the clipping level and provides high-quality speech in all clipping levels. We measured the declipping performance using various metrics and confirmed that the proposed method improves the average performance over all clipping levels, compared with the conventional methods, and greatly improves the performance when the clipping distortion is small.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.89-100
• /
• 2023

Recently, on-device artificial intelligence (AI) solutions using mobile devices and embedded edge devices have emerged in various fields, such as computer vision, to address network traffic burdens, low-energy operations, and security problems. Although vision transformer deep learning models have outperformed conventional convolutional neural network (CNN) models in computer vision, they require more computations and parameters than CNN models. Thus, they are not directly applicable to embedded edge devices with limited hardware resources. Many researchers have proposed various model compression methods or lightweight architectures for vision transformers; however, there are only a few studies evaluating the effects of model compression techniques of vision transformers on performance. Regarding this problem, this paper presents a performance evaluation of vision transformers on embedded platforms. We investigated the behaviors of three vision transformers: DeiT, LeViT, and MobileViT. Each model performance was evaluated by accuracy and inference time on edge devices using the ImageNet dataset. We assessed the effects of the quantization method applied to the models on latency enhancement and accuracy degradation by profiling the proportion of response time occupied by major operations. In addition, we evaluated the performance of each model on GPU and EdgeTPU-based edge devices. In our experimental results, LeViT showed the best performance in CPU-based edge devices, and DeiT-small showed the highest performance improvement in GPU-based edge devices. In addition, only MobileViT models showed performance improvement on EdgeTPU. Summarizing the analysis results through profiling, the degree of performance improvement of each vision transformer model was highly dependent on the proportion of parts that could be optimized in the target edge device. In summary, to apply vision transformers to on-device AI solutions, either proper operation composition and optimizations specific to target edge devices must be considered.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.4
• /
• pp.1-7
• /
• 2009

This paper presents a process routing (PR) algorithm with multiple objectives. PR determines the optimum sequence of operations for transforming a raw material into a completed part within the available machining resources. In any computer aided process planning (CAPP) system, selection of the machining operation sequence is one of the most critical activities for manufacturing a part and for the technical specification in the part drawing. Here, the goal could be to generate the sequence that optimizes production time, production cost, machine utilization or with multiple these criteria. The Pareto Stratum Niche Cubicle (PS NC) GA has been adopted to find the optimum sequence of operations that optimize two conflicting criteria; production cost and production quality. The numerical analysis shows that the proposed PS NC GA is both effective and efficient to the PR problem.