Results 151 to 160 of about 3,187 (246)

Boosted unsupervised feature selection for tumor gene expression profiles

CAAI Transactions on Intelligence Technology, EarlyView.
Abstract In an unsupervised scenario, it is challenging but essential to eliminate noise and redundant features for tumour gene expression profiles. However, the current unsupervised feature selection methods treat all samples equally, which tend to learn discriminative features from simple samples.
Yifan Shi, Kaixiang Yang, Mengzhi Wang, Zhiwen Yu, Huanqiang Zeng, Yang Hu   +5 more
wiley   +1 more source

Bayesian adaptive sampling: A smart approach for affordable germination phenotyping. [PDF]

Plant Phenomics
Mercier F, Bouhlel N, El Ghaziri A, Vu JL, Buitink J, Rousseau D.   +5 more
europepmc   +1 more source

AI‐Powered Anomaly Detection for Secure Internet of Things (IoT): Optimising XGBoost and Deep Learning With Bayesian Optimisation

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Intelligent and adaptive defence systems that can quickly thwart changing cyberthreats are becoming more and more necessary in the dynamic and data‐intensive Internet of things (IoT) environment. Using the NSL‐KDD benchmark dataset, this paper presents an improved anomaly detection system that combines an optimised sequential neural network ...
Seong‐O Shim, Lal Hussain, Mohammed A. Alqarni, Faisal S. Alsubaei, Rasha Jamal Atwah   +4 more
wiley   +1 more source

Assembly theory and its relationship with computational complexity. [PDF]

Npj Complex
Kempes CP, Lachmann M, Iannaccone A, Matthew Fricke G, Redwan Chowdhury M, Walker SI, Cronin L.   +6 more
europepmc   +1 more source

Spectral Components of Honey Bee Sound Signals Recorded Inside and Outside the Beehive: An Explainable Machine Learning Approach to Diurnal Pattern Recognition. [PDF]

Sensors (Basel)
Książek P, Libal U, Król-Nowak A.
europepmc   +1 more source

Optimizing SMILES token sequences via trie-based refinement and transition graph filtering. [PDF]

J Cheminform
Radhakrishnan S, Mody K, Venkatesh A, Venkatesh A.   +3 more
europepmc   +1 more source

Multi‐Step Ahead Short‐Term Load Forecasting Based on MCNN‐MMoL

IET Smart Energy Systems, EarlyView.
This paper proposes the MCNN‐MMOL model to eliminate cumulative errors in multi‐step load forecasting. The innovation lies in the MCNN's parallel convolutional branches that achieve multi‐scale feature fusion by balancing global load trends and local sub‐load dynamics.
Suxun Zhu, Bowen Ren, Lili Zheng, Abdullah M. Alharbi, Changhua Yang, Shidong Wu, Aotian Yuan, Hengrui Ma   +7 more
wiley   +1 more source

Acyclic and star coloring parameters of fractal cubic networks. [PDF]

Sci Rep
Renuga C, Meiyappan D, Prabhu S, Arulperumjothi M.   +3 more
europepmc   +1 more source

The Consequences of Soil Organic Carbon for Crop Yield, Farm Productivity and Profit

Australian Journal of Agricultural and Resource Economics, EarlyView.
ABSTRACT Crop choices affect soil organic carbon (SOC) stocks, allowing farmers to manipulate the amount of carbon sequestered in the soil over time. This paper examines the private and public benefits of crop rotations that sequester additional carbon across the province of Saskatchewan, Canada using a novel field‐level dataset from the Saskatchewan ...
Devin Allen Serfas
wiley   +1 more source

Decoding lactylation in neuropathic pain: Immune cell infiltration patterns and machine learning-identified candidate biomarkers. [PDF]

Medicine (Baltimore)
Wu W, Yang D.
europepmc   +1 more source