Tag: Computational efficiency

A new conjugate gradient method derived from a second-order Taylor series expansion improves neural network training efficiency and heart disease ...

A parallel hybrid algorithm combining sine cosine and tabu search improves mobile robot path planning performance by up to 265% ...

Researchers have developed a dual-constrained pulse-coupled neural network algorithm that accelerates robotic path planning by suppressing redundant neuron activations without ...

The new open-source tool assigns sequencing reads and linked-read molecules to genomic regions up to 60 times faster than full ...

Researchers have validated an optoelectronic deep learning framework using single-map dynamics and state-skipping training that reduces computational resource requirements by ...

A new algorithm refines classical loop tracing in transportation simplex methods, matching optimal solutions while cutting redundant loop enumeration and ...

A new hybrid CNN-Transformer model called AGDE-Net accurately segments tumor cores and peritumoral edema in adult glioma MRI while keeping ...

A new 3D Mamba-based model segments brain tumors with consistent accuracy gains and a 15x efficiency improvement over existing state-of-the-art ...

Researchers have developed an adaptive large-eddy simulation framework whose mesh refines and coarsens dynamically based on local velocity fluctuation intensity, ...

A new study reports that combining correlation-based feature pruning with resource-aware adaptive learning improved accuracy and reduced memory use on ...

A hybrid of probabilistic roadmaps and bidirectional A* search produced shorter paths and faster planning times than Dijkstra-based and conventional ...

A new two-stage reduced order model combines hyper-reduction and Gaussian process regression to cut both training and prediction costs for ...

A hybrid framework combines a local neural-network surrogate with exact quasi-polynomial spectral validation to speed up stability optimization for delayed ...

A new study shows that a frozen CLIP vision-language model with lightweight adapters can improve human activity recognition in low-light ...

A new framework uses ant colony optimization to configure a modified DeepLabV3+ network with a residual feature fusion module, reporting ...

A preprint under review in Wind Energy Science shows that a compact set of wind speed and turbulence descriptors is ...

A six-parameter steady-state fuel-cell model fitted with Enhanced Artificial Rabbits Optimization produced very low voltage errors on both a 5-watt ...

A new hybrid reliability method called AK-FOCM combines active learning Kriging with first order control variates to estimate rare failure ...

A new classifier called CABLE-kNN caches local neighborhood evidence during training and neutralizes class priors, beating ordinary kNN on imbalanced ...

Researchers have developed an evidential deep learning framework that detects stroke with near-perfect accuracy while quantifying its own uncertainty in ...