• Journal of Animal Science and Technology
• /
• v.63 no.6
• /
• pp.1453-1463
• /
• 2021

Feeding is the most important behavior that represents the health and welfare of weanling pigs. The early detection of feed refusal is crucial for the control of disease in the initial stages and the detection of empty feeders for adding feed in a timely manner. This paper proposes a real-time technique for the detection and recognition of small pigs using a deep-leaning-based method. The proposed model focuses on detecting pigs on a feeder in a feeding position. Conventional methods detect pigs and then classify them into different behavior gestures. In contrast, in the proposed method, these two tasks are combined into a single process to detect only feeding behavior to increase the speed of detection. Considering the significant differences between pig behaviors at different sizes, adaptive adjustments are introduced into a you-only-look-once (YOLO) model, including an angle optimization strategy between the head and body for detecting a head in a feeder. According to experimental results, this method can detect the feeding behavior of pigs and screen non-feeding positions with 95.66%, 94.22%, and 96.56% average precision (AP) at an intersection over union (IoU) threshold of 0.5 for YOLOv3, YOLOv4, and an additional layer and with the proposed activation function, respectively. Drinking behavior was detected with 86.86%, 89.16%, and 86.41% AP at a 0.5 IoU threshold for YOLOv3, YOLOv4, and the proposed activation function, respectively. In terms of detection and classification, the results of our study demonstrate that the proposed method yields higher precision and recall compared to conventional methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3904-3922
• /
• 2022

As a research hotspot, pedestrian detection has a wide range of applications in the field of computer vision in recent years. However, current pedestrian detection methods have problems such as insufficient detection accuracy and large models that are not suitable for large-scale deployment. In view of these problems mentioned above, a lightweight pedestrian detection and early warning method using a new model called you only look once (Yolov5) is proposed in this paper, which utilizing advantages of Yolov5s model to achieve accurate and fast pedestrian recognition. In addition, this paper also optimizes the loss function of the batch normalization (BN) layer. After sparsification, pruning and fine-tuning, got a lot of optimization, the size of the model on the edge of the computing power is lower equipment can be deployed. Finally, from the experimental data presented in this paper, under the training of the road pedestrian dataset that we collected and processed independently, the Yolov5s model has certain advantages in terms of precision and other indicators compared with traditional single shot multiBox detector (SSD) model and fast region-convolutional neural network (Fast R-CNN) model. After pruning and lightweight, the size of training model is greatly reduced without a significant reduction in accuracy, and the final precision reaches 87%, while the model size is reduced to 7,723 KB.

• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.44-57
• /
• 2022

Fablab is a global network of digital fabrication facilities. Fablab is a digital workshop for individual manufacturing. In addition, Fablab is a next-generation digital infrastructure that connects education, training, R&D and production. The Fablab is a facility lab that makes the products you want, and it is a space where users-led products or services are discovered for the community. Furthermore, through various citizen-led projects, it is playing the role of innovation that changes the region and society. In this study, we examine the operating conditions of Fablabs in Korea and Japan (Fablab Seoul, Fablab Busan, Fablab Kamakura and Fablab Kitakagaya). It also explores the business model and sustainable development potential of each fablab. To this end, first, we compare and analyze the use of fablabs in both countries. Second, the purpose of the fablabs of both countries is analyzed. Third, we analyze the business models that the fablabs of both countries are taking for sustainable development through Lean Canvas. Based on the results obtained through case analysis of both countries, we make suggestions for the development of fablabs in Korea.

• BMB Reports
• /
• v.55 no.10
• /
• pp.512-517
• /
• 2022

Traumatic brain injury (TBI) is brain damage which is caused by the impact of external mechanical forces. TBI can lead to the temporary or permanent impairment of physical and cognitive abilities, resulting in abnormal behavior. We recently observed that a single session of early exercise in animals with TBI improved their behavioral performance in the absence of other cognitive abnormalities. In the present study, we investigated the therapeutic effects of continuous exercise during the early stages of TBI in rats. We found that continuous low-intensity exercise in early-stage improves the locomotion recovery in the TBI of animal models; however, it does not significantly enhance short-term memory capabilities. Moreover, continuous early exercise not only reduces the protein expression of cerebral damage-related markers, such as Glial Fibrillary Acid Protein (GFAP), Neuron-Specific Enolase (NSE), S100β, Protein Gene Products 9.5 (PGP9.5), and Heat Shock Protein 70 (HSP70), but it also decreases the expression of apoptosis-related protein BAX and cleaved caspase 3. Furthermore, exercise training in animals with TBI decreases the microglia activation and the expression of inflammatory cytokines in the serum, such as CCL20, IL-13, IL-1α, and IL-1β. These findings thus demonstrate that early exercise therapy for TBI may be an effective strategy in improving physiological function, and that serum protein levels are useful biomarkers for the predicition of the effectiveness of early exercise therapy.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.353-360
• /
• 2022

Due to the dense and complicated working environment, the construction industry is susceptible to many accidents. Worker's fall is a severe problem at the construction site, including falling into holes or openings because of the inadequate coverings as per the safety rules. During the construction or demolition of a building, openings and holes are formed in the floors and roofs. Many workers neglect to cover openings for ease of work while being aware of the risks of holes, openings, and gaps at heights. However, there are safety rules for worker safety; the holes and openings must be covered to prevent falls. The safety inspector typically examines it by visiting the construction site, which is time-consuming and requires safety manager efforts. Therefore, this study presented a worker-driven approach (the worker is involved in the reporting process) to facilitate safety managers by developing integrated computer vision and inertia sensors-based mobile applications to identify openings. The TensorFlow framework is used to design Convolutional Neural Network (CNN); the designed CNN is trained on a custom dataset for binary class openings and covered and deployed on an android smartphone. When an application captures an image, the device also extracts the accelerometer values to determine the inclination in parallel with the classification task of the device to predict the final output as floor (openings/ covered), wall (openings/covered), and roof (openings / covered). The proposed worker-driven approach will be extended with other case scenarios at the construction site.

• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.310-316
• /
• 2023

This study aims to predict uncertain future scenarios that may unfold in South Korea in the near future, utilizing the theory of extreme events(X-events). A group of 32 experts, consisting of government emergency planning officers, was selected as the focus group to achieve this objective. Using the Focus Group Interview (FGI) technique, opinions were gathered from this focus group regarding potential X-events that may occur within the advanced science and technology domains over the next 10 years. The analysis of these opinions revealed that government emergency planning officers regarded the "Obsolescence of current technology and systems," particularly in the context of cyber network paralysis as the most plausible X-event within science and technology. They also put forth challenging and intricate opinions, including the emergence of new weapon systems and ethical concerns associated with artificial intelligence (AI). Given that X-events are more likely to emerge in unanticipated areas rather than those that are widely predicted, the results obtained from this study carry significant importance. However, it's important to note that this study is grounded in a limited group of experts, highlighting the necessity for subsequent research involving a more extensive group of experts. This research seeks to stimulate studies on extreme events at a national level and contribute to the preparation for future X-event predictions and strategies for addressing them.

• Computers and Concrete
• /
• v.33 no.1
• /
• pp.55-75
• /
• 2024

The present study introduces an optimum performance soft computing model for predicting the compressive strength of high-performance concrete (HPC) by comparing models based on conventional (kernel-based, covariance function-based, and tree-based), advanced machine (least square support vector machine-LSSVM and minimax probability machine regressor-MPMR), and deep (artificial neural network-ANN) learning approaches using a common database for the first time. A compressive strength database, having results of 1030 concrete samples, has been compiled from the literature and preprocessed. For the purpose of training, testing, and validation of soft computing models, 803, 101, and 101 data points have been selected arbitrarily from preprocessed data points, i.e., 1005. Thirteen performance metrics, including three new metrics, i.e., a20-index, index of agreement, and index of scatter, have been implemented for each model. The performance comparison reveals that the SVM (kernel-based), ET (tree-based), MPMR (advanced), and ANN (deep) models have achieved higher performance in predicting the compressive strength of HPC. From the overall analysis of performance, accuracy, Taylor plot, accuracy metric, regression error characteristics curve, Anderson-Darling, Wilcoxon, Uncertainty, and reliability, it has been observed that model CS4 based on the ensemble tree has been recognized as an optimum performance model with higher performance, i.e., a correlation coefficient of 0.9352, root mean square error of 5.76 MPa, and mean absolute error of 4.1069 MPa. The present study also reveals that multicollinearity affects the prediction accuracy of Gaussian process regression, decision tree, multilinear regression, and adaptive boosting regressor models, novel research in compressive strength prediction of HPC. The cosine sensitivity analysis reveals that the prediction of compressive strength of HPC is highly affected by cement content, fine aggregate, coarse aggregate, and water content.

• IMMUNE NETWORK
• /
• v.24 no.1
• /
• pp.9.1-9.21
• /
• 2024

The cytokine IL-7 plays critical and nonredundant roles in T cell immunity so that the abundance and availability of IL-7 act as key regulatory mechanisms in T cell immunity. Importantly, IL-7 is not produced by T cells themselves but primarily by non-lymphoid lineage stromal cells and epithelial cells that are limited in their numbers. Thus, T cells depend on cell extrinsic IL-7, and the amount of in vivo IL-7 is considered a major factor in maximizing and maintaining the number of T cells in peripheral tissues. Moreover, IL-7 provides metabolic cues and promotes the survival of both naïve and memory T cells. Thus, IL-7 is also essential for the functional fitness of T cells. In this regard, there has been an extensive effort trying to increase the protein abundance of IL-7 in vivo, with the aim to augment T cell immunity and harness T cell functions in anti-tumor responses. Such approaches started under experimental animal models, but they recently culminated into clinical studies, with striking effects in re-establishing T cell immunity in immunocompromised patients, as well as boosting anti-tumor effects. Depending on the design, glycosylation, and the structure of recombinantly engineered IL-7 proteins and their mimetics, recombinant IL-7 molecules have shown dramatic differences in their stability, efficacy, cellular effects, and overall immune functions. The current review is aimed to summarize the past and present efforts in the field that led to clinical trials, and to highlight the therapeutical significance of IL-7 biology as a master regulator of T cell immunity.

• IMMUNE NETWORK
• /
• v.23 no.3
• /
• pp.29.1-29.23
• /
• 2023

Cholesterol (CL) is required for various biomolecular production processes, including those of cell membrane components. Therefore, to meet these needs, CL is converted into various derivatives. Among these derivatives is cholesterol sulfate (CS), a naturally produced CL derivative by the sulfotransferase family 2B1 (SULT2B1), which is widely present in human plasma. CS is involved in cell membrane stabilization, blood clotting, keratinocyte differentiation, and TCR nanocluster deformation. This study shows that treatment of T cells with CS resulted in the decreased surface expression of some surface T-cell proteins and reduced IL-2 release. Furthermore, T cells treated with CS significantly reduced lipid raft contents and membrane CLs. Surprisingly, using the electron microscope, we also observed that CS led to the disruption of T-cell microvilli, releasing small microvilli particles containing TCRs and other microvillar proteins. However, in vivo, T cells with CS showed aberrant migration to high endothelial venules and limited infiltrating splenic T-cell zones compared with the untreated T cells. Additionally, we observed significant alleviation of atopic dermatitis in mice injected with CS in the animal model. Based on these results, we conclude that CS is an immunosuppressive natural lipid that impairs TCR signaling by disrupting microvillar function in T cells, suggesting its usefulness as a therapeutic agent for alleviating T-cell-mediated hypersensitivity and a potential target for treating autoimmune diseases.

• Journal of the Korea Institute of Building Construction
• /
• v.24 no.1
• /
• pp.121-131
• /
• 2024

This research explores the potential of leveraging unstructured data from construction supervision documents, which contain detailed inspection insights from independent third-party monitors of building construction processes. With the evolution of analytical methodologies, such unstructured data has been recognized as a valuable source of information, offering diverse insights. The study introduces a framework designed to assess cost performance by applying advanced analytical methods to the unstructured data found in final construction supervision reports. Specifically, key phrases were identified using text mining and social network analysis techniques, and these phrases were then analyzed through binomial logistic regression to assess cost performance. The study found that predictions of cost performance based on unstructured data from supervision documents achieved an accuracy rate of approximately 73%. The findings of this research are anticipated to serve as a foundational resource for analyzing various forms of unstructured data generated within the construction sector in future projects.