Results 171 to 180 of about 154,181 (262)

YOLOv8-TF: Transformer-Enhanced YOLOv8 for Underwater Fish Species Recognition with Class Imbalance Handling. [PDF]

Sensors (Basel)
Shah C, Nabi MM, Alaba SY, Ebu IA, Prior J, Campbell MD, Caillouet R, Grossi MD, Rowell T, Wallace F, Ball JE, Moorhead R.   +11 more
europepmc   +1 more source

Solid‐State Diffusion and Intermetallic Phase Formation in Roll‐Bonded Mg–Zn Composites With Kirigami‐Patterned Inlay

Advanced Engineering Materials, EarlyView.
Mg–Zn composites with a thickness of 0.21 mm were fabricated using roll bonding of a kirigami‐patterned Mg alloy inlay within a Zn matrix. Thermal activation following this process led to the formation of tailored intermetallic structures, which provided the composite with enhanced flexural strength.
Yaroslav Frolov, Oleksandr Bobukh, Christian Klose, Florian Nürnberger, Hans Jürgen Maier   +4 more
wiley   +1 more source

Time‐Dependent Oxidation and Scale Evolution of a Wrought Co/Ni‐Based Superalloy

Advanced Engineering Materials, EarlyView.
This study shows how a new wrought Co/Ni‐based superalloy resists oxidation at 800 ∘$^\circ$C. The oxide scale changes from rough, fast‐growing spinel to a dense, protective chromia–alumina layer. Atom probe analysis reveals tiny refractory‐rich bubbles at the interface that mark the transition to long‐term, diffusion‐controlled protection ...
Cameron Crabb, Zachary T. Kloenne, Samuel R. Rogers, Chi Hang Dominik Kwok, Mark C. Hardy, Michele S. Conroy, David Dye   +6 more
wiley   +1 more source

Comparative investigation of bagging enhanced machine learning for early detection of HCV infections using class imbalance technique with feature selection. [PDF]

PLoS One
Tusher EH, Ismail MA, Akib A, Gabralla LA, Ibrahim AO, Som HM, Remli MA.   +6 more
europepmc   +1 more source

Is an Apple an Orange? A Large Language Model Benchmark for Candidate Term Extraction and Subclass Decisions Against Upper Ontologies in Engineering and Materials Science

Advanced Engineering Materials, EarlyView.
Building machine‐readable vocabularies for materials science is slow, expert‐driven work. This study benchmarks 13 large language models on two of its first steps: finding candidate terms in engineering articles and deciding where they belong in a class hierarchy.
Thomas Bjarsch, Maximilian Holland, Klaus Drechsler, Johannes Schilp   +3 more
wiley   +1 more source

DECNet: Left Atrial Pulmonary Vein Class Imbalance Classification Network. [PDF]

J Imaging Inform Med
Zhang G, Gu W, Liang T, Li Y, Guo W, Gong Z, Ju R.   +6 more
europepmc   +1 more source

Microstructure‐Controlled Crack Propagation and Fracture Resistance in MoSiBTiC Alloy Revealed by Multiscale Extended Finite Element Method Modeling

Advanced Engineering Materials, EarlyView.
A two‐dimensional multiscale finite element analysis framework was established for the first‐generation MoSiBTiC alloy, and the mechanical and fracture‐related parameters of the constituent phases were calibrated through experiments and simulations. The framework provides a basis for analyzing crack propagation behavior in its complex microstructure ...
Junfeng Du, Takahiro Kaneko, Xinyu Yan, Takahito Ohmura, Kyosuke Yoshimi   +4 more
wiley   +1 more source

Machine Learning Approach on Predictive Model Establishment for In-Hospital Mortality in Acute Myocardial Infarction Patients Post-Percutaneous Coronary Intervention: Solutions for Databases With Dimensionality Reduction and Class Imbalance. [PDF]

Rev Cardiovasc Med
Li W, Lei P, Dong R, He S, Zhang Z, Han B.   +5 more
europepmc   +1 more source

Impact of lightGBM hyperparameters on class imbalance

Class imbalance is a common problem in Machine Learning (ML) that introduces bias during the training phase of ML models, compromising their accuracy and reliability. This problem is particularly critical in fields such as disease diagnosis and credit risk assessment, where it is crucial to accurately predict the minority class.
openaire   +2 more sources

High‐Temperature Nanoindentation of Metals: Assessing Thermal Drift, Frame Compliance, and Chemical Composition Effects on the Reported Mechanical Properties

Advanced Engineering Materials, EarlyView.
Do not let thermal drift and instrument artifacts deceive high‐temperature nanoindentation results. We compare classical Oliver–Pharr and automatic image recognition analyses across steels and a Ni alloy to quantify these effects. Accounting for artifacts reveals systematic softening with temperature, while Cr and Ni additions boost resistance ...
Velislava Yonkova, Steffen Brinckmann, Ruth Schwaiger   +2 more
wiley   +1 more source