Automatic improvement of deep learning-based cell segmentation in time-lapse microscopy by neural architecture search
Deep learning networks for segmenting live cells in time-lapse microscopy are hard and slow to design, requiring expert knowledge.
Papers
1,138 of 1,138 verified cases.
Potato Surface Defect Detection Based on Deep Transfer Learning
Business & Industry
Industrial Vision Systems and Defect Detection
solved
importance 4/10
scale stated
Potato surface defect detection is challenging due to irregular potato shapes and various defect types, and is crucial for automating food production and processing.
A novel deep learning model based on convolutional neural networks for employee churn prediction
Companies suffer performance losses when valuable employees quit, so they need systems that predict employee churn in advance.
Automated Essay Scoring Using Transformer Models
Education & Everyday
Natural Language Processing Techniques
partially solved
importance 4/10
scale stated
Manual scoring of learner text is burdensome; the study tests whether transformer models beat bag-of-words methods for automated scoring.
AptaNet as a deep learning approach for aptamer–protein interaction prediction
Identifying which short DNA/RNA aptamers bind to which target proteins is slow and costly to do experimentally. AptaNet was built to predict aptamer-protein interaction pairs computationally.
Survival Prediction in Gallbladder Cancer Using CT Based Machine Learning
Medicine & Health
Radiomics and Machine Learning in Medical Imaging
ai assisted
importance 4/10
scale stated
Doctors lacked a tool to predict overall survival for gallbladder cancer patients from pre-treatment CT scans. The study built a machine learning model combining CT features with clinical information to predict survival.
Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station
Farmers need detailed short-to-medium-range, high-resolution local forecasts, but major numerical weather prediction models only provide 6-hourly forecasts at 10-20 km grid length.
Practical fluorescence reconstruction microscopy for large samples and low-magnification imaging
Fluorescence reconstruction microscopy reduces phototoxicity and simplifies sample prep, but is complex to implement and existing benchmarks do not reflect practical value.
Machine learning for faster and smarter fluorescence lifetime imaging microscopy
Biology & Life Sciences
Advanced Fluorescence Microscopy Techniques
ai assisted
importance 4/10
scale stated
Fluorescence lifetime imaging microscopy (FLIM) is useful for biomedical research, but its calculation, analysis and interpretation are complex, slow and computationally expensive.
A Hybrid Flux Balance Analysis and Machine Learning Pipeline Elucidates Metabolic Adaptation in Cyanobacteria
Biology & Life Sciences
Microbial Metabolic Engineering and Bioproduction
ai assisted
importance 4/10
scale stated
How the cyanobacterium Synechococcus sp. PCC 7002 metabolically adapts to fluctuations in light intensity and salinity was not well understood.
Obstacle Avoidance Drone by Deep Reinforcement Learning and Its Racing with Human Pilot
Training drones to avoid obstacles without the laborious labeled datasets that supervised learning requires.
Viable and necrotic tumor assessment from whole slide images of osteosarcoma using machine-learning and deep-learning models
Pathological estimation of viable versus necrotic tumor after chemotherapy in osteosarcoma requires laborious analysis of whole slide images.
Machine learning methods for short‐term bid forecasting in the renewable energy market: A case study in Italy
Energy providers need to predict next-day total wind energy bid volumes in Italy's day-ahead market to size bids and manage network imbalance.
Multi-Feature Classification of Multi-Sensor Satellite Imagery Based on Dual-Polarimetric Sentinel-1A, Landsat-8 OLI, and Hyperion Images for Urban Land-Cover Classification
Climate & Environment
Synthetic Aperture Radar (SAR) Applications and Techniques
ai assisted
importance 4/10
scale stated
Improving urban land-cover classification accuracy using multi-sensor satellite imagery and determining which features contribute most.
Machine learning for combinatorial optimization of brace placement of steel frames
Optimally placing braces in steel frames during seismic retrofit is a combinatorial optimization problem whose many structural analyses make it computationally very costly.
A Machine Learning Approach for Using the Postmortem Skin Microbiome to Estimate the Postmortem Interval
Biology & Life Sciences
Forensic Entomology and Diptera Studies
ai assisted
importance 4/10
scale stated
Forensic investigators need to estimate the postmortem interval (time since death) for cadavers found after unknown time periods, and current methods have substantial limitations.
Credit Card Default Prediction: An Empirical Analysis on Predictive Performance Using Statistical and Machine Learning Methods
Business & Industry
Financial Distress and Bankruptcy Prediction
ai assisted
importance 4/10
scale stated
Predicting which credit card holders will default, and whether machine learning beats traditional statistical methods, using Taiwan UCI data.
A Review of Large Language Models for Automated Test Case Generation
Software & Coding
Software Testing and Debugging Techniques
ai assisted
importance 4/10
scale stated
Manually creating test cases for software is effortful; the paper reviews whether large language models can automate test case generation.
Forest Disturbance Monitoring Using Cloud-Based Sentinel-2 Satellite Imagery and Machine Learning
Forest damage has become more frequent in Hungary, and rapid, cost-effective monitoring of disturbances was needed.
A Survey of Incremental Deep Learning for Defect Detection in Manufacturing
Engineering & Materials
Industrial Vision Systems and Defect Detection
ai assisted
importance 4/10
scale stated
Deep learning defect detection models in manufacturing need to be rigorously updated in real time with new tasks, classes or decision pathways without degrading, e.g. via catastrophic forgetting.
Advanced UAV Design Optimization Through Deep Learning-Based Surrogate Models
Engineering & Materials
Advanced Multi-Objective Optimization Algorithms
ai assisted
importance 4/10
scale stated
Conceptual UAV design requires simultaneous optimization of aerodynamics, structure, stealth and propulsion, which is computationally expensive with traditional methods.
Machine learning-driven discovery of novel therapeutic targets in diabetic foot ulcers
Medicine & Health
Diabetic Foot Ulcer Assessment and Management
ai assisted
importance 4/10
scale stated
Key genes driving diabetic foot ulcer pathogenesis and treatment response were not well identified.
Machine learning-based soft-sensor development for road quality classification
Engineering & Materials
Structural Health Monitoring Techniques
ai assisted
importance 4/10
scale stated
Road defects cause health, safety, and vehicle-damage costs, so a low-cost onboard system was built to detect and classify road quality.
Bridging Locomotion and Manipulation Using Reconfigurable Robotic Limbs via Reinforcement Learning
Robots usually learn locomotion and manipulation separately; unifying both skills on reconfigurable limbs lacked data-driven evidence.