1,138 of 1,138 verified cases.
Identifying interactions between non-coding RNAs and RNA-binding proteins experimentally is expensive and time-consuming, and computational prediction remains challenging.
Predicting the final properties of 3D-printed polymer and polymer composite parts is difficult because material composition, processing conditions and microstructure vary.
Accurate prediction of reservoir temperature in geothermal energy systems is critical for optimization, but complex geothermal data challenges traditional modeling.
Predicting axial load capacity of composite concrete-encased steel columns is inaccurate, with traditional methods showing 10%-30% relative errors.
Efficiently assigning tasks to compatible clouds in dynamic multi-cloud environments is a crucial challenge, especially for ultra-reliable, low-latency applications.
Classifying skin lesions from dermoscopic images is difficult because existing methods struggle with complex information and long-range dependencies.
Designing multiscale structures under stress constraints is difficult because evaluating microstructure material properties and local stress states is computationally costly.
Detecting fabric defects automatically in real production settings where datasets are noisy and both plain and printed fabrics occur.
Traditional remote-sensing methods cannot precisely classify dynamic and complex urban land areas.
Thin-slice prostate MRI could improve cancer diagnostics but unacceptably prolongs acquisition time.
Machine learning-assisted materials design and discovery is limited by small datasets; virtual sample generation techniques are used to expand training data and guide discovery.
Oblique earth-space satellite links can detect rain in real time, but classifying rainy versus non-rainy periods from the indirect signal is difficult.
Identifying and subtyping amyloidosis (e.g., immunoglobulin light chain vs amyloid A) in kidney tissue normally requires special stains, immunolabeling, electron microscopy, or mass spectrometry.
Accurate and reliable predictions of biomass yield are needed for pasture management decisions such as fertilization, irrigation, grazing, and mowing.
Cracks in building facades worsen if not found quickly, and manual inspection of large buildings is impractical, motivating automated crack detection.
Conventional music playlist generators struggle to capture a target user's long-term listening preferences.
Prosumers in energy communities need to optimize how much energy to trade and at what price in peer-to-peer markets.
Deep-learning automated essay scoring systems are limited by the scarcity of large training datasets of manually rated essays.
Deep learning models for mitochondria segmentation in electron microscopy volumes need large annotated datasets and perform poorly on EM data from different tissues or species (domain shift).
Monitoring how colorectal cancer cells respond to therapy and linking gene expression to cell behaviour required new high-throughput phenotyping methods.
Weather conditions strongly affect inflow rates and substance concentrations in wastewater treatment plants, but this weather signal cannot be directly measured with traditional physical sensors, making plant control difficult.
Segmentation algorithms make topological errors, such as broken connections, on fine-scale structures in images.
Detecting malicious activity in Software Defined Network data planes requires efficient monitoring methods.
Lenders in peer-to-peer lending need to know which machine learning approach best predicts borrower default risk.