• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.265-272
• /
• 2022

As the risk of lung cancer has increased, early-stage detection and treatment of cancers have received a lot of attention. Among various medical imaging approaches, computer tomography (CT) has been widely utilized to examine the size and growth rate of lung nodules. However, the process of manual examination is a time-consuming task, and it causes physical and mental fatigue for medical professionals. Recently, many computer-aided diagnostic methods have been proposed to reduce the workload of medical professionals. In recent studies, encoder-decoder architectures have shown reliable performances in medical image segmentation, and it is adopted to predict lesion candidates. However, localizing nodules in lung CT images is a challenging problem due to the extremely small sizes and unstructured shapes of nodules. To solve these problems, we utilize atrous spatial pyramid pooling (ASPP) to minimize the loss of information for a general U-Net baseline model to extract rich representations from various receptive fields. Moreover, we propose mixed-up attention mechanism of reverse, boundary and convolutional block attention module (CBAM) to improve the accuracy of segmentation small scale of various shapes. The performance of the proposed model is compared with several previous attention mechanisms on the LIDC-IDRI dataset, and experimental results demonstrate that reverse, boundary, and CBAM (RB-CBAM) are effective in the segmentation of small nodules.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.24 no.66
• /
• pp.69-77
• /
• 2001

The management of return flows induced by the various forms of reuse of products and materials in industrial production processes has received growing attention throughout this decade. As one of the developing countries in the world trade market, we have to apply the reverse logistics system considering an environment seriously, and to implement reverse logistics activities abreast with the forward logistics system of a companies. Therefore, the objective of this study was to discuss what the reverse logistics system of Environmentally Conscious Logistics Systems(ECLS) is by introducing a case study.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1998.04a
• /
• pp.390-397
• /
• 1998

An approach to identifying input forces is proposed using measured structural dynamic responses and its analytical model. The identification of input forces is a reverse process and ill-conditioned problem. Its solution is unstable and generally case dependent. In this paper, the ill-condition is described considering characteristic matrix which is defined by reduced dynamic stiffness matrix. Special attention is focused on the condition number of a characteristic matrix used in the solution algorithm of this reverse process. Simple example is presented in support of the ill-condition of a reverse process.

• Journal of Information Processing Systems
• /
• v.20 no.4
• /
• pp.535-549
• /
• 2024

Facial expressions (FEs) serve as fundamental components for human emotion assessment and human-computer interaction. Traditional convolutional neural networks tend to overlook valuable information during the FE feature extraction, resulting in suboptimal recognition rates. To address this problem, we propose a deep learning framework that incorporates hierarchical feature fusion, contextual data, and an attention mechanism for precise FE recognition. In our approach, we leveraged an enhanced VGGNet16 as the backbone network and introduced an improved group convolutional channel attention (GCCA) module in each block to emphasize the crucial expression features. A partial decoder was added at the end of the backbone network to facilitate the fusion of multilevel features for a comprehensive feature map. A reverse attention mechanism guides the model to refine details layer-by-layer while introducing contextual information and extracting richer expression features. To enhance feature distinguishability, we employed islanding loss in combination with softmax loss, creating a joint loss function. Using two open datasets, our experimental results demonstrated the effectiveness of our framework. Our framework achieved an average accuracy rate of 74.08% on the FER2013 dataset and 98.66% on the CK+ dataset, outperforming advanced methods in both recognition accuracy and stability.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2004.10a
• /
• pp.565-565
• /
• 2004

Due to limitation of resources and increasing concerns about environment, reverse logistics has received growing attention in recent years. In this paper, we propose three types of reverse logistics networks based on reuse of returnable containers, materials recycling process and remanufacturing for parts reuse. First, the sender in the re-usable item network supplies containers for the recipient and orders either new containers from external supplier or returnable containers cleaned from the container depot. Second, the recycling center in the proposed recycling network collects either end of life products from customer or faulty goods from manufacturer, collected products are dismantled into materials and materials go into recycling process. Finally, the manufacturer in the proposed remanufacturing network has two alternatives for supplying parts: either ordering the required parts to external supplier or overhauling disassembled parts and bringing them back 'as new' conditions. In this product recovery environment, we build optimal order quantity models to minimize the total logistics costs related to reverse logistics network. The validity of the proposed model is investigated through comprehensive computational experiments.

• Applied Chemistry for Engineering
• /
• v.33 no.6
• /
• pp.551-556
• /
• 2022

The desalinated water obtained by the water treatment process based on the membrane is attracting a lot of attention as a promising technology that can solve the global water shortage problem. Reverse osmosis membrane-based desalination, one of the most widely used desalination processes, is a technology that desalinates abundant seawater on Earth, thus having great potential in the desalination industry. To improve the performance of the desalination process, it is necessary to understand the reverse osmosis mechanism of the membrane at the atomic/molecular level. In this review, we introduce molecular simulation, which plays an important role in material research today, and the roles of computational simulation at the atomic/molecular level in the development of reverse osmosis membranes.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.03b
• /
• pp.472-473
• /
• 2008

Flow boiling in parallel microchannels has received attention as an effective heat sink mechanism for power-densities encountered in microelectronic equipment. the bubble dynamics coupled with boiling heat transfer in microchannels is still not well understood due to the technological difficulties in obtaining detailed measurements of microscale two-phase flows. In this study, complete numerical simulation is performed to further clarify the dynamics of flow boiling in microchannels. The level set method for tracking the liquid-vapor interface is modified to include the effects of phase change and contact angle. The method is further extended to treat the no-slip and contact angle conditions on the immersed solid. Also, the reverse flow observed during flow boiling in parallel microchannels has been investigated. Based on the numerical results, the effects of channel shape and inlet area restriction on the bubble growth, reverse flow and heat transfer are quantified.

• Korean Institute of Interior Design Journal
• /
• v.25 no.5
• /
• pp.71-81
• /
• 2016

This research has been carried out with the objects of sporting goods shops to find out what structure of those shops raises more interest from customers. The tracking eyes on the objects which are the same but seen to have different structures has revealed the followings. Customers' visual appreciation of Reverse left/right Images (11.1) was found to be higher than that of Original Images (10.6). Furthermore, the reverse left/right image of the space also was found to attract more interest from customers, which led them to have longer observation. The below is about the interpretation of the spatial exploration by observation time and the appreciation of its visual content in line with the experiment objects of selling spaces. The longer the space was observed, (1)the higher the expansive searching of space was, (2)the more spots were observed as if they did not know what to see after they first observed at early hours, (3)later (in the time range of 64~73 seconds) they came to look at the spots in which they got interested, (4)and then again they suddenly got lost what to see. When the change of observation characteristics by time range is reviewed, it can be seen that the searching of original images is changed from Divergent Feature to Convergent Feature when the observation time increases from the early stage of observation to the later. On the contrary, the reverse left/right images were found to have the opposite searching features, that is, from convergent exploration to divergent exploration. These findings show that the reverse left/right images of the sporting goods shops, which were the experiment objects, have more factors attracting customers' attention and interest and that it is the very shop-structure which makes customers have better visual appreciation of those shops.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.18 no.11
• /
• pp.1243-1253
• /
• 2007

Recently UHF RFID system has drawn a great deal of attention because of its potential to revolutionize supply chain management. An important characterization of the performance of a RFID system is 'interrogation range', which is defined as the maximum distance between a reader and a tag. Forward-link interrogation range is defined as the maximum distance from which the tag receives just enough power to turn on and back-scatter, and reverse-tink interrogation range is the maximum distance from which the reader can detect this back-scattered signal. A link balance has to be found between the two interrogation ranges. In this paper, the interrogation range equations are formulated in both forward-link and reverse-link and a trade-off between the two values is investigated in order to maximize the interrogation range. As a result, it is observed that the gain of the reader antenna, the isolation of the circulator, and the phase noise of the local oscillator with range correlation effect mainly determine the reverse-link interrogation range.

• Clinics in Shoulder and Elbow
• /
• v.23 no.2
• /
• pp.100-104
• /
• 2020

Function and strength of the deltoid muscle are important in reverse shoulder arthroplasty (RSA). Moreover, location and shape of the acromion, clavicle, and scapular spine, which are origins of the deltoid muscle, are also important. The frequency of os acromiale is 5% to 15%; however, it is rare in the Asian population, affecting approximately 0.7% of Koreans. RSA has rarely been reported in patients with os acromiale. We present a case series of two patients with cuff tear and arthropathy combined with os acromiale who underwent RSA. From 2016 to 2018, two patients with os acromiale who presented with pain and limited range of motion (ROM) underwent RSA with cuff tear arthropathy using the subscapularis-sparing deltopectoral approach. Their ROM, visual analog scale (VAS), and satisfaction were evaluated before and after surgery. In both patients, VAS decreased, ROM increased, and postoperative satisfaction increased. There were no specific complications due to os acromiale. The VAS, ROM, and satisfaction of patients improved after surgery compared with values before surgery. However, careful attention must be given during surgery to ensure optimal repair and recovery.