• Journal of Drive and Control
• /
• v.21 no.2
• /
• pp.1-7
• /
• 2024

This paper proposes a novel cooling system for hydrogen fuel cell cooling systems by integrating heat pump technology to enhance operational efficiency. The study analyzed the cooling efficiency of the fuel cell cooling system. With the increasing focus on eco-friendly vehicle technologies to address environmental concerns and global warming, the transportation sector, a major contributor to greenhouse gas emissions, needs technological enhancements for better efficiency. The proposed cooling system was modeled through 1-D simulations. The analysis results of parameters such as thermal balance, temperature, and pressure of each component confirmed the stable operation of the system. By examining variations in the cooling system's flow rate, compressor RPM, and the Coefficient of Performance (COP) based on different refrigerants, initial research was conducted to derive optimal operating conditions and parameter values.

• Journal of Information Processing Systems
• /
• v.20 no.4
• /
• pp.558-573
• /
• 2024

Considering factors such as illumination, camera quality variations, and background-specific variations, identifying a face using a smartphone-based facial image capture application is challenging. Face Image Quality Assessment refers to the process of taking a face image as input and producing some form of "quality" estimate as an output. Typically, quality assessment techniques use deep learning methods to categorize images. The models used in deep learning are shown as black boxes. This raises the question of the trustworthiness of the models. Several explainability techniques have gained importance in building this trust. Explainability techniques provide visual evidence of the active regions within an image on which the deep learning model makes a prediction. Here, we developed a technique for reliable prediction of facial images before medical analysis and security operations. A combination of gradient-weighted class activation mapping and local interpretable model-agnostic explanations were used to explain the model. This approach has been implemented in the preselection of facial images for skin feature extraction, which is important in critical medical science applications. We demonstrate that the use of combined explanations provides better visual explanations for the model, where both the saliency map and perturbation-based explainability techniques verify predictions.

• The Korean Journal of Medicine
• /
• v.99 no.1
• /
• pp.11-16
• /
• 2024

Myelodysplastic syndrome (MDS) is a heterogeneous disorder with diverse prognoses influenced by cytopenias, genetic variants, and myeloblast proportions in the bone marrow. Accurate prognosis prediction and tailored treatment plans are essential. The International Prognostic Scoring System-Molecular (IPSS-M), which additionally reflects the impact of MDS-related genetic mutations to the clinical and laboratory information, is anticipated to offer superior prognostic accuracy compared to existing systems like the Revised International Prognostic Scoring System (IPSS-R). Despite its statistical complexity, its web-based calculation and ease of discussing results with patients using intuitive data sets provide notable advantages. Progress in MDS treatment, exemplified by effective anemia correction with an erythropoiesis-maturation agent in SF3B1-mutated cases and efforts to refine poor prognoses in TP53-mutated cases, reflects the evolving landscape of genetic-based interventions in MDS. Advancements in genetic diagnostic technology, combined with enhanced knowledge of the bone marrow niche, are anticipated to lead to significant improvement in MDS treatment outcomes in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1888-1906
• /
• 2024

Aiming at the problems that the edge of melanoma image is fuzzy, the contrast with the background is low, and the hair occlusion makes it difficult to segment accurately, this paper proposes a model MSCNet for melanoma segmentation based on U-net frame. Firstly, a multi-scale pyramid fusion module is designed to reconstruct the skip connection and transmit global information to the decoder. Secondly, the contextural information conduction module is innovatively added to the top of the encoder. The module provides different receptive fields for the segmented target by using the hole convolution with different expansion rates, so as to better fuse multi-scale contextural information. In addition, in order to suppress redundant information in the input image and pay more attention to melanoma feature information, global channel attention mechanism is introduced into the decoder. Finally, In order to solve the problem of lesion class imbalance, this paper uses a combined loss function. The algorithm of this paper is verified on ISIC 2017 and ISIC 2018 public datasets. The experimental results indicate that the proposed algorithm has better accuracy for melanoma segmentation compared with other CNN-based image segmentation algorithms.

• Hip & pelvis
• /
• v.36 no.3
• /
• pp.161-167
• /
• 2024

Periprosthetic joint infection (PJI) is regarded as a critical factor contributing to the failure of primary and revision total joint arthroplasty (TJA). With the increasing prevalence of TJA, a significant increase in the incidence of PJI is expected. The escalating number of cases, along with the significant economic strain imposed on healthcare systems, place emphasis on the pressing need for development of effective strategies for prevention. PJI not only affects patient outcomes but also increases mortality rates, thus its prevention is a matter of vital importance. The longer-term survival rates for PJI after total hip and knee arthroplasty correspond with or are lower than those for prevalent cancers in older adults while exceeding those for other types of cancers. Because of the multifaceted nature of infection risk, a collaborative effort among healthcare professionals is essential to implementing diverse strategies for prevention. Rigorous validation of the efficacy of emerging novel preventive techniques will be required. The combined application of these strategies can minimize the risk of infection, thus their comprehensive adoption is important. Collectively, the risk of PJI could be substantially minimized by application of a multifaceted approach implementing these strategies, leading to improvement of patient outcomes and a reduced economic burden.

• Structural Engineering and Mechanics
• /
• v.91 no.6
• /
• pp.627-642
• /
• 2024

In the present work, the deformation and stresses induced in a functionally graded disk have been reported for different loading conditions. The governing differential equation is solved using the classical method namely Navier's method by considering thermal and mechanical boundary conditions at the surface of the disk. To simplify solving the second-order differential equation, a plane stress condition was assumed. Following validation using a one-dimensional steady-state heat condition problem, temperature variations were computed for constant heat generation and varying conductivity. The research aims to investigate both the individual and combined effects of rotation, gravity, and temperature with constant heat generation on a hollow disk operating under complex loading conditions. The results demonstrated a high degree of accuracy when compared with those in existing literature. Material properties, such as Young's modulus, density, conductivity, and thermal expansion coefficient, were modeled using a power law variation along the disk's radius by considering aluminum as a base material. The proposed analytical method is straightforward, providing valuable insights into the behavior of disks under various loading conditions. This method is particularly useful for researchers and industries in selecting appropriate loading conditions and grading parameters for engineering applications, including aerospace components, energy systems, and rotary machinery parts.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2281-2297
• /
• 2024

Employing multiple drones as a swarm to complete missions can sharply improve the working efficiency and expand the scope of investigation. Remote UAV swarms utilize satellites as relays to forward investigation information. The increasing amount of data demands higher transmission rate and complex field network coding (CFNC) is deemed as an effective solution for data return. CFNC applied to UAV swarms enhances transmission efficiency by occupying only two time slots, which is less than other network coding schemes. However, conventional CFNC applied to UAVs is combined with constant coding and modulation scheme and results in a waste of spectrum resource when the channel conditions are better. In order to avoid the waste of power resources of the relay satellite and further improve spectral efficiency, a CFNC transmission scheme with MPSK modulation is proposed in this paper. For the proposed scheme, the satellite relay no longer directly forwards information, but transmits information after processing according to the current channel state. The proposed transmission scheme not only maintains throughput advantage of CFNC, but also enhances spectral efficiency, which obtains higher throughput performance. The symbol error probability (SEP) and throughput results corroborated by Monte Carlo simulation show that the proposed transmission scheme improves spectral efficiency in multiples compared to the conventional CFNC schemes. In addition, the proposed transmission scheme enhances the throughput performance for different topology structures while keeping SEP below a certain value.

• Smart Structures and Systems
• /
• v.33 no.6
• /
• pp.415-430
• /
• 2024

To control vertical and lateral compound vibration simultaneously using an integrated smart controller, passive tuned mass damper (TMD) and tuned liquid damper (TLD) are updated and combined to an adaptive-passive TMD-TLD (AP-TMD-TLD) system. As for the vertical AP-TMD part on top of the vertical spring, it can retune itself through varying the level of liquid in the tank to adjust its mass, while the lateral AP-TLD part at the bottom of the vertical spring can retune itself by changing the level of liquid. Further, for multimodal response control, the multiple AP-TMD-TLD (MAP-TMD-TLD) system is proposed as well. Each AP-TMD-TLD in the system can identify the structural vertical and lateral modal frequencies through the wavelet-transform (WT) based algorithm and retune its vertical and lateral natural frequencies both through adjusting the level of liquid in the AP-TMD and AP-TLD parts respectively. A cantilever cable-stayed landscape bridge which is sensitive to both human-induced and wind-induced vibrations is presented as a case study. For comparison, initial parameters of MAP-TMD-TLD are mistuned. Results show that the presented system can retune its vertical and lateral frequencies precisely, while the retuned system has a better bi-directional compound control effect than the mistuned system before the retuning operation and can improve the serviceability significantly.

• Journal of Fashion Business
• /
• v.28 no.4
• /
• pp.129-148
• /
• 2024

With the advent of the 4th industrial era and the development of digital technologies such as artificial intelligence (AI), metaverse, 3D printing, and 3D virtual wearing systems, the fashion industry continues to attempt to use digital technology and introduce it into various areas. The purpose of this study was to determine whether fashion and digital technology could be combined to create works and to suggest ways to apply digital technology in the fashion industry. As a research method, image generative AI, Midjourney was applied to the initial design ideation stage to derive inspiration images. 3D printing technique was then introduced as a production method to print fashion jewelry. As a result of the research, a total of six jewelry designs printed with a 3D printer were developed. One necklace, one bracelet, three earrings, and one ring were developed. This study identified the possibility of applying digital technology to real fashion jewelry design products by designing jewelry based on inspirational images derived from image generation AI and producing pieces of fashion jewelry with 3D modeling tasks and 3D printing outputs. This study is significant in that it expands the expression area of fashion jewelry design that combines digital technology.

• Ocean Systems Engineering
• /
• v.14 no.3
• /
• pp.301-314
• /
• 2024

In this study, the lift coefficient and wave deformations for a two-dimensional flat-plate in non-cavitating condition were computed using a closed-form (analytic) solution. This plate moves at a constant speed beneath a free surface in water of finite depth. The model represents the flat-plate using a lumped vortex element within the constraints of potential flow theory. The kinematic and dynamic free surface conditions were combined and linearized. This linearized free surface condition was then applied to get the total velocity potential. The method of images was utilized to account for the effects of finite depth in the calculations. The lift coefficient of the flat-plate and wave elevations on the free surface were calculated using the closed-form solution. The lift coefficients derived from the present analytic solution were validated by comparing them with Plotkin's method in the case of deep water. Wave elevations were also compared with those obtained from a numerical method. A comprehensive discussion on the impact of Froude number, submergence depth of flat-plate from the calm free surface, the angle of attack and the depths of finite bottom on the results - namely, lift coefficients and free surface deformations - is provided.