Performance for rotor system of hybrid electromagnetic bearing and elastic foil gas bearing with dynamic characteristics analysis under deep learning. by Xiangxi Du, Yanhua Sun

“…Analysis of the classification accuracy and loss function based on the CNN model shows that the convolution kernel size of 7*1 and the batch size of 128 can realize the best performance of CNN in fault classification. …”
Get full text

Synthesis of propellant grade HHTPB by hydrogenation of HTPB using Pd-activated charcoal as catalyst by Ch. Devi Vara Prasad, P. Kanakaraju, R Vinu, Abhijit P Deshpande

“…However, the propellant formulation should be optimized with the help of plasticizers, solid loading, etc., to achieve the required properties.…”
Get full text

Neuro-VGNB: Transfer Learning-Based Approach for Detecting Brain Stroke by Muhammad Usama Tanveer, Kashif Munir, Bharati Rathore, Abdulatif Alabdulatif, Rutvij H. Jhaveri, Maham Fatima

“…A brain stroke occurs when blood flow to the brain is interrupted leading to potential brain damage and loss of functions controlled by the affected area. …”
Get full text

A hybrid adversarial autoencoder-graph network model with dynamic fusion for robust scRNA-seq clustering by Binhua Tang, Yingying Feng, Xinyu Gao

“…In addition, scCAGN combines three different loss functions to optimize clustering performance through a joint clustering approach. …”
Get full text

DualPlaqueNet with dual-branch structure and attention mechanism for carotid plaque semantic segmentation and size prediction by Lili Deng, Xingyu Duan, Yongxiang Sun, Yunling Wang, Dongmei Song, Xiaokai Duan

“…However, ultrasound images suffer from high noise, low contrast, and blurred edges, making it difficult for traditional image processing methods to accurately extract plaque information.ObjectiveTo establish a deep learning-based DualPlaqueNet model for semantic segmentation and size prediction of plaques in carotid ultrasound images, thereby providing comprehensive and accurate auxiliary information for clinical risk assessment and personalized diagnosis and treatment.MethodsDualPlaqueNet uses a dual-branch architecture combined with attention mechanisms and joint loss functions to optimize segmentation and regression. …”
Get full text

A review on plant metabolite-mediated nanoparticle synthesis: sustainable applications in horticultural crops by Komal G. Lakhani, Rasmieh Hamid, Elaheh Motamedi, G. V. Marviya

“…Applications of these nanoparticles include nanofertilizers for efficient nutrient delivery, nanopesticides for targeted pest control, and nano-packaging to reduce post-harvest losses. In addition, they function as nano(bio)sensors for the early detection of pathogens to ensure crop health and minimize losses. …”
Get full text

Workbench for a Parabolic Trough Solar Collector with a Tracking System by Luciano A. Fiamonzini, Gustavo A. R. Rivas, Oswaldo H. Ando Junior

“…Yet, the efficiency in function of the flow became optimal when the flow regime became turbulent. …”
Get full text

The RESOLVE and ECO Gas in Galaxy Groups Initiative: The Group Finder and the Group H i–Halo Mass Relation by Zackary L. Hutchens, Sheila J. Kannappan, Andreas A. Berlind, Mehnaaz Asad, Kathleen D. Eckert, David V. Stark, Derrick S. Carr, Ella R. Castelloe, Andrew J. Baker, Kelley M. Hess, Amanda J. Moffett, Mark A. Norris, Darren Croton

“…We use mock catalogs to optimize the group finder’s performance. Compared to friends-of-friends (with false-pair splitting), the G3 algorithm offers improved completeness and halo-mass recovery with minimal loss of purity. …”
Get full text

Comprehensive techno-environmental evaluation of an isolated PV/wind/biomass hybrid microgrid employing various battery technologies: A comparative analysis. by Mohammed Alqahtani, Saeed Alhajri, Ahmed S Menesy, Ali Maher Mohammed, Hamdy M Sultan, Muhammad Khalid

“…Using data from Tabuk, Saudi Arabia (28.38° N, 36.56° E), the study seeks to achieve optimal sizing for solar PV, wind, biomass, and battery storage components to minimize the net present cost (NPC) and ensure reliable power supply, adhering to specified loss of power supply probability (LPSP) and excess energy thresholds. …”
Get full text

An Encoding Technique for Multiobjective Evolutionary Algorithms Applied to Power Distribution System Reconfiguration by J. L. Guardado, F. Rivas-Davalos, J. Torres, S. Maximov, E. Melgoza

“…Network reconfiguration is an alternative to reduce power losses and optimize the operation of power distribution systems. …”
Get full text

Two-Step Probabilistic Method to Enable Demand Response Programs in Renewable-Based Integrated Energy Systems by Farshad Jafari, Haidar Samet, Ali Reza Seifi, Mohammad Rastegar

“…In the first step, an optimization problem is solved to determine the optimal energy cost for each customer. …”
Get full text

Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground by Peng Wang, Xiaoqiang Li, Chunxiao Song, Shipeng Zhai

“…The results show that compared with DDQN algorithm, TDDQN has the advantages of fast convergence and low loss function.…”
Get full text

A Deep Learning Inversion Method for 3D Temperature Structures in the South China Sea with Physical Constraints by Dongcan Xu, Yahao Liu, Yuan Kong

“…To address the multiparameter complexity of temperature retrieval, physical constraints—particularly the heat budget balance of water bodies—are incorporated into the loss function. Experiments demonstrate that the physics-informed ConvLSTM model significantly improves the temperature estimation accuracy by simultaneously optimizing the physical consistency and predictive performance. …”
Get full text

Intelligent Obstacle Avoidance Algorithm for Mobile Robots in Uncertain Environment by Liwei Guan, Yu Lu, Zhijie He, Xi Chen

“…First, through network training, the accuracy rate of the test set is stable at 98%, and the loss of the function value has also been reduced from the original 0.79 to 0.08, which is 10 times smaller. …”
Get full text

Development of Adaptive Testing Method Based on Neurotechnologies by E. V. Chumakova, D. G. Korneev, M. S. Gasparian

“…SGD, Adam, NAdam and RMSprop implemented in Keras were compared as optimizers to achieve faster convergence. Adam showed the best results in terms of accuracy, while the MSE loss function (mean square error) was used together with the optimizer. …”
Get full text

Cardiac MRI study of adverse events in patients treated with immune checkpoint inhibitors: a prospective cohort study of cardiac adverse events by Antonio Di Muzio, Alessandro Marchese, Lorenzo Monti, Cristina Panico, Marinos Kallikourdis, Gianluigi Condorelli, Armando Santoro, Matteo Simonelli, Angelo Dipasquale, Pasquale Persico, Laura Giordano, Giovanna Finocchiaro, Agnese Losurdo, Matteo Perrino, Marco Francone, Chiara Catalano, Simone Serio, Federica Catapano, Stefano Figliozzi, Carla D’Andrea, Marco Cremonesi, Maria Chiara Tronconi, Enrico Lugli

“…ICI treatment was associated with a significant left ventricular ejection function (LVEF) reduction pre-ICI versus post-ICI treatment (60.1±8% to 58.1±8%, p=0.002, paired t-test) and more than 3% LVEF loss in a substantial proportion of patients (18; 32%). …”
Get full text

DAMI-YOLOv8l: A multi-scale detection framework for light-trapping insect pest monitoring by Xiao Chen, Xinting Yang, Huan Hu, Tianjun Li, Zijie Zhou, Wenyong Li

“…Additionally, the MPDinner-IoU loss function optimizes feature measurement for small insect pest datasets by introducing geometric correction capabilities. …”
Get full text

Effect of Axial Clearance on Volumetric Efficiency of Non-circular Planetary Gear Hydraulic Motors by Li Xiang, Peng Xianlong

“…Firstly, according to the principle of the gap leakage in the rotating plane and the friction force in the fluid, the leakage and power loss formula between the wheels were derived, so as to calculate the optimal solution of the axial clearance of the motor under 30 MPa pressure difference. …”
Get full text

An edge server placement based on graph clustering in mobile edge computing by Shanshan Zhang, Jiong Yu, Mingjian Hu

“…The model mainly consists of a two-layer graph convolutional network (GCN) component and a differentiable version of K-means clustering component, which transforms the server placement problem into an end-to-end learning optimization problem on a graph. It trains the GCN network to achieve the best clustering results with the expectation of average delay and load balancing as the loss function to obtain the edge server placement and user assignment scheme. …”
Get full text

Metabolic musculoskeletal disorders in patients with inflammatory bowel disease by Young Joo Yang, Seong Ran Jeon

“…Moreover, a multidisciplinary approach that addresses both metabolic and inflammatory aspects is essential for optimizing physical function and improving treatment outcomes in patients who have IBD with musculoskeletal involvement.…”
Get full text