Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Blake Davidson
Billion-Spectrum AI Corpus Pushes Proteomics Into the Deep Learning Era
Proteomics has long labored under a paradox: the field generates staggering volumes of data, yet its machine learning models have been starved of the kind of curated, standardized corpora that fueled the revolutions in language and vision. Now, a team led by researchers at Westlake University, Fudan University and the Shanghai Artificial Intelligence Laboratory has taken a decisive step toward closing that gap.
AI Learns to Read Dangerous URLs Character by Character While Showing Its Work
Every click on a link is a small act of trust, and cybercriminals have learned to exploit it with remarkable sophistication. Phishing pages, malware distribution servers, and defaced websites all announce themselves through their web addresses, yet the signals are subtle, constantly shifting, and often deliberately disguised.
Lightweight AI Tool Outsmarts Deep Learning at Spotting Disordered Proteins
Not every protein in the cell folds into a tidy, well-defined three-dimensional shape. A large and biologically crucial class of proteins, known as intrinsically disordered proteins and regions, remains flexible and structureless under normal physiological conditions, and that very flexibility is what allows them to switch gene activity on and off, mediate cellular stress responses, and enable molecular recognition between proteins.
New Two-Stage Regression Framework Tames Multicollinearity and Boosts Prediction Accuracy
Regression analysis sits at the heart of modern data science, yet it remains haunted by an old adversary: multicollinearity, the phenomenon in which predictor variables are so tightly correlated with one another that standard estimation procedures become unstable and unreliable.
Machine Learning Puts Handwriting-Based Personality Analysis to a Rigorous Test
For decades, graphologists have claimed that the slant of a letter, the pressure of a pen stroke, or the spacing between words can reveal the hidden contours of a person’s character. The idea has proved remarkably durable, resurfacing in the modern era dressed in the language of artificial intelligence.
AI Steps Into the Emergency Room and the Disaster Zone, But Nurses Are Still Waiting
When a disaster strikes, the entire health system compresses into a single, terrifying equation: too many patients, too little time, and resources that were never designed to stretch that far. Emergency departments live in that compressed state every day, and disaster response simply amplifies it.
AI Watchdog That Learns Normal Water and Spots Contamination in Real Time
Freshwater is under pressure from every direction: industrial discharge, expanding cities, intensifying agriculture, and a climate that keeps shifting the baseline of what rivers and reservoirs consider normal. Yet the way most of the world monitors its water has barely changed in decades. Samples are collected, driven to laboratories, analyzed, and reported days or even weeks later. By the time contamination is confirmed, the pollutant may have traveled far downstream.
Wolf-Inspired AI Tuning Pushes Speech Emotion Recognition Across Languages and Labs
Computers that can hear how we feel, not just what we say, have long been a tantalizing goal for artificial intelligence researchers. A machine that recognizes anger in a caller’s voice could de-escalate a customer service crisis before it begins; one that detects anxiety in a patient’s speech could flag mental health deterioration days before a clinical appointment.
AI and Machine Learning Take Center Stage in Measuring the Economic Fallout of Digital Transformation
Digital transformation has quietly become one of the most powerful economic forces of the twenty-first century, reshaping how businesses operate, how governments deliver services, and how societies adapt to relentless technological change. Yet for all its visibility, the true economic impact of this transformation has been remarkably difficult to measure. A new open-access survey published in the Journal of Big Data by Munir Majdalawieh, S.
Faces and Words Align: How Policy Announcers’ Expressions Match Their Message
When a government official steps up to the podium to announce a new housing policy, the audience receives two streams of information at once: the words being spoken and the expression on the speaker’s face. A new study published in Humanities and Social Sciences Communications suggests that these two channels are not independent.
Pep2Net Unifies Fragmented Peptide Databases With a Cross-Attention AI Model
Peptides, the short chains of amino acids that act as hormones, antibiotics, toxins, signaling molecules and drug candidates, have long been a blind spot in computational biology. While whole proteins now benefit from mature databases and powerful machine-learning models, peptide research remains scattered across dozens of specialist resources, each with its own format, labeling conventions and idiosyncrasies.
AI Reads Fingernails Like a Graph to Diagnose Disease With Explainable Attention
Fingernails are often described as windows into the body’s health, and for good reason. Fungal infections, psoriasis, and even some cardiovascular and liver conditions all leave telltale marks on the nail plate, from discoloration and thickening to ridges, cracks, and surface irregularities. Yet reading these signs is notoriously subjective, even for trained clinicians, because different nail disorders can look strikingly similar.
CMS Replaces Hand-Coded Physics Rules with a Transformer That Reads Whole Collisions
Every proton-proton collision at the Large Hadron Collider detonates into a spray of billions of potential signals in a fraction of a nanosecond, and before physicists can say anything about a collision, software must turn raw detector electronics into a list of particles.
Deep Learning AI Detects and Repairs Hacker Attacks on Brain Signals in Real Time
Electroencephalogram signals, the faint electrical whispers of the human brain recorded from the scalp, have become one of the most valuable data streams in modern medicine. They guide the diagnosis of epilepsy, sleep disorders, and encephalopathies, and they increasingly drive brain-computer interfaces that let paralyzed patients type, speak, and control prosthetic devices with thought alone.
Pixels Become Cuboids: Turning RGB Values Into 3D Blocks Helps AI See and Draw
Every digital image that has ever been photographed, scanned, or generated is, at heart, a grid of numbers. Each pixel stores three values for red, green, and blue, and conventional image processing treats these numbers as little more than coordinates in an abstract color space. A new study published in Multimedia Tools and Applications argues that this flat, purely numerical view leaves something important on the table: geometry.
Two-Stage AI Cracks the Hidden Pore Problem in Concrete Scans
Concrete looks deceptively simple from the outside, but inside a single block of the world’s most-used building material lies a hidden landscape of air-filled voids, cement paste and coarse aggregate grains that determines whether a bridge deck lasts fifty years or fails in twenty. X-ray computed tomography can reveal that landscape in exquisite detail, yet turning raw CT slices into reliable maps of pores, paste and stone has long been a stubborn computational problem.
Mask-Aware AI Transformer Outperforms Benchmarks in Forecasting GDP From Incomplete Data
Forecasting gross domestic product has always been one of the hardest problems in economics, and a new study argues that the missing piece may literally be the missing data. A research team led by Asiye Omidian and Maral Mirzamohammadi has built a deep-learning architecture called a mask-aware Multivariate Correlation Transformer, or MCT, that is explicitly designed to forecast GDP from short, heterogeneous, and incomplete annual macroeconomic histories.
AI-Powered Wavelet System Spots Hidden Cable Faults Before They Trigger Blackouts
Buried beneath city streets and inside some of the most safety-critical industrial sites on Earth, underground transmission cables carry enormous amounts of electrical power with almost no physical visibility. When one of these cables fails, the fault is invisible to the eye, hidden under meters of soil or concrete, and the consequences can range from prolonged blackouts to dangerous conditions in facilities such as nuclear power plants.
Zigzag Walls and Triple Nanoparticles Boost Heat Transfer in Magnetized Porous Cavities
Engineers have long sought ways to squeeze more cooling power out of passive thermal systems, those that move heat without pumps, fans, or any moving parts at all. A new computational study published in Results in Engineering takes this pursuit to an unusual level of complexity, combining a zigzag-corrugated wall, a water-saturated porous metal-like matrix, a strong magnetic field, and a cutting-edge coolant loaded with three different kinds of nanoparticles.
New Framework Weighs Cost, Coverage and Speed to Pick the Right Industrial IoT Intrusion Detector
Industrial networks have quietly become one of the most contested battlegrounds in modern cybersecurity. As factories, power grids and hospitals wire thousands of sensors and actuators into edge-based Industrial Internet of Things architectures, the attack surface has expanded faster than the tools designed to defend it. Denial-of-service floods, reconnaissance probes, injection attacks and malware now converge on heterogeneous devices that were never built with security in mind.
AI Meets the Blueprint: Six Years of Research Reveal How Smart BIM Is Reshaping Real Estate
Buildings have long been designed on paper, then on screens, and increasingly inside living digital models that carry every wall, pipe, duct, and dollar through the entire life of a property. Building Information Modeling, or BIM, is that digital backbone, and a new study published in Applied Intelligence has now mapped, with unusual rigor, how artificial intelligence is being fused with BIM across the real estate development industry.
PLOS ONE Retracts Underwater Image Enhancement Paper Over Similarities to Prior Work
A 2024 study that promised a new way to sharpen the murky images captured beneath the ocean’s surface has been struck from the scientific record.
AI Learns to Play Piano Like a Human by Combining Rules With Reinforcement Learning
Choosing which finger presses which piano key sounds like a small detail, but it is one of the hardest problems in automated music performance. A single phrase can be fingered in dozens of plausible ways, and the difference between an awkward, jerky passage and a flowing, comfortable one often comes down to decisions made dozens of notes in advance.
Old-School Convolutional Networks Strike Back in Long-Range Time Series Forecasting
For the better part of a decade, the story of long-term time series forecasting has been written by Transformers. These attention-driven architectures, borrowed from natural language processing, swept through the forecasting literature on the promise that their global receptive fields could capture long-range dependencies that older models supposedly could not.
AI Turns Ordinary Smartphones Into Mosquito Egg Counters for Dengue Surveillance
Aedes aegypti is one of the most consequential insects on the planet. The mosquito, which has spread far beyond its African origins to colonize tropical and subtropical cities across the globe, is the primary vector for dengue, Zika, chikungunya, and yellow fever viruses. As urbanization and climate shifts expand its range, public health agencies face a persistent problem: knowing where the mosquito is breeding, and in what numbers, before outbreaks erupt.
AI Learns to Compose: Hybrid Model Blends Deep Learning and Reinforcement Learning to Write Better Melodies
Artificial intelligence has been writing music for years, but anyone who has listened closely to machine-generated melodies knows the problem: the notes often wander, the harmony drifts, and the rhythm loses its footing.
New AI Framework Tackles the Trickiest Problem in Reading News: Spotting Events
Every day, newsrooms, intelligence analysts, and financial institutions rely on software to answer a deceptively simple question: what happened in this text? The task, known as event detection, asks a machine to scan a sentence and identify the words that signal an event—say, an attack, a merger, or an election—along with the type of event those words represent.
AI Model Reads Lead-Lag Signals to Sharpen Carbon Price Forecasts
Carbon markets are notoriously difficult to predict. Prices in emissions trading systems do not simply react to the latest headline; they drift, overshoot, and respond to energy markets, financial conditions, and international carbon trading signals at different speeds, sometimes hours or days apart.
Dual-Stream AI Learns Where and When to Look in Wearable Sensor Data
Wearable devices have quietly become some of the most ubiquitous computers on the planet, wrapped around wrists, clipped to waistbands and tucked into clothing, continuously streaming accelerometer, gyroscope and physiological data about the human body in motion. Turning those raw signals into a reliable understanding of what a person is actually doing—walking upstairs, folding laundry, descending a staircase—remains one of the deceptively hard problems in machine learning.
Memory Wall Threatens AI for Science: New Survey Maps the Fixes
Deep learning has quietly become the engine room of modern science. From predicting how a protein folds into its three-dimensional shape to forecasting the path of a hurricane or screening millions of candidate drug molecules, Transformer-based models now sit at the heart of research workflows in biology, medicine, chemistry, and meteorology.
AI Reads Dental X-Rays and Patient Data Together to Gauge Gum Disease Severity
Periodontal disease is one of the most common chronic conditions on the planet, and one of its most telling signs hides in plain sight on a routine dental X-ray: the slow, silent erosion of the bone that anchors teeth in the jaw. Reading that erosion, however, is as much an art as a science.
AI Model Predicts Molecular Curvature Directly, Skipping Costly Derivatives
Every molecule sits on a landscape. Stretch a bond, bend an angle, twist a dihedral, and the electronic energy rises or falls across a high-dimensional surface that chemists call the potential energy surface. The gradient of that surface tells a simulation which way is downhill, but the curvature tells it something far richer: how sharply the energy bends, whether a structure is a true minimum, a saddle point on the path between reactants and products, or something stranger.
AI Reads Whole Coronary Angiograms and Predicts Heart Risk a Year Ahead
An artificial intelligence system trained on more than 200,000 coronary angiography videos can now interpret an entire heart catheterization in one pass, detecting dangerously narrowed arteries, spotting chronic total occlusions, blood clots and calcification, and even forecasting a patient’s risk of a major cardiac event over the following year.
One AI model to fix them all: foundation network restores seven types of medical images
Medical imaging is the bedrock of modern diagnosis, yet the pictures clinicians actually work with are rarely pristine. Computed tomography scans are degraded by metal artefacts from implants, magnetic resonance images suffer from patient motion and undersampling, positron emission tomography is inherently noisy at low radiation doses, and endoscopic, ultrasound, fundus and X-ray images each carry their own characteristic flaws.
New Scale Reveals How Gifted Students Learn With Artificial Intelligence
Generative artificial intelligence has swept into classrooms faster than almost any educational technology before it, and psychologists are still scrambling to answer a deceptively simple question: how do students actually change the way they learn when a large language model is sitting beside them? A new study published in Current Psychology by Majed Saeed Aldalham of King Khalid University in Saudi Arabia offers one of the most rigorous answers to date.
New AI Framework Sharpens the Hunt for Actions Hidden in Untrimmed Video
Every minute of unedited video footage contains a hidden architecture of events: a gymnast mounts a beam, holds a pose, dismounts; a surveillance camera watches a person walk, pause, and suddenly run. Teaching machines to find not just what happens in such footage but exactly when it begins and ends is the task of temporal action localization, one of the most demanding problems in computer vision.
AI Learns to Scrub Bias From Fake Data Before It Poisons Real Decisions
Synthetic data has quietly become one of the most consequential technologies in modern machine learning. In domains like finance, healthcare, and education, real records are locked behind privacy walls, governed by regulation, or simply too scarce to train reliable models. Generators that fabricate realistic fake records promise a way out: models can learn from statistically faithful stand-ins without exposing a single real patient or customer.
Correlated Noise Sabotages Long-Range AI Forecasts, and a Simple Fix Emerges
For years, a seductive intuition has governed the design of deep learning models that forecast the future: the more history you feed them, the better they should predict what comes next. Feed a weather model a week of sensor readings instead of a day, and it should uncover richer cycles, deeper context, sharper predictions.
AI Model Reads Gray and White Matter Signals to Spot Autism with 87% Accuracy
Autism spectrum disorder has long been one of the most challenging conditions to diagnose objectively. Clinicians still rely largely on behavioral observation, which can vary widely between specialists and often delays identification of a condition where early intervention matters enormously.
Ice-Inspired Algorithm Gets Smarter, Boosting Monkeypox Prediction Accuracy
Optimization algorithms are the quiet workhorses of modern data science, quietly searching vast mathematical landscapes for the best possible solutions to problems that would overwhelm human intuition. When those landscapes grow to thousands of dimensions, as they routinely do in genomics, medical imaging, and large-scale sensor networks, even the most cleverly designed search strategies can stall.
AI Virtual Patients Let Medical Students Practice Doctor-Patient Talks
Medical students have long learned the art of the clinical interview by practicing on actors hired to play patients. That gold-standard method is expensive, hard to schedule, and impossible to scale to every student who wants extra practice.
Deep Learning Meets Blockchain: VoteChain Slashes Energy Use in Financial Consensus
Blockchain networks have long been trapped in an uncomfortable trade-off: the mechanisms that keep distributed ledgers secure tend to be the same mechanisms that devour electricity. Proof-of-work systems famously consume power on the scale of small nations, while even more modest voting-based protocols carry computational overheads that add up quickly at financial scale.
Layered Stacking Ensemble Promises Sharper Fixes for Missing Data
Missing values are the quiet saboteurs of modern data analysis. Whether the data come from clinical trials, national surveys, sensor networks or economic registers, some entries are almost always absent, and how analysts cope with those gaps can determine whether a study’s conclusions hold up or quietly fall apart.
AI Meets Blockchain: New Shield for Connected Car Networks
Every connected car on the road today is a rolling computer, constantly exchanging messages with other vehicles, roadside units, traffic management systems, and even pedestrians’ devices. This constant chatter, known as vehicle-to-everything or V2X communication, is the nervous system of the emerging intelligent transportation landscape, and it becomes even more critical as sixth-generation (6G) networks promise the ultra-low latency and massive connectivity that autonomous driving demands.
A Classic Statistics Test Gets a Streaming Makeover to Catch Anomalies in Real Time
Every second, an unfathomable torrent of data flows through the world’s servers: stock ticks, sensor readings, network logs, production metrics. Buried inside those streams are the signals that matter most, the sudden spikes, the quiet drifts, the anomalies that announce a failing machine, a fraudulent transaction, or a cyberattack in progress.
Smarter Downsampling and Attention Help AI Read Faces More Accurately
Facial expression recognition has quietly become one of the most consequential technologies in modern computing, powering everything from driver-monitoring systems and mental-health screening tools to human-computer interfaces that adapt to a user’s emotional state.
AI Model Hits Near-Perfect Accuracy in Predicting Perovskite Bandgaps
A new hybrid artificial intelligence framework claims to predict the bandgap energy of organic perovskite materials with almost flawless precision, a development that could accelerate the search for next-generation solar cells and optoelectronic devices.
AI Transformer Hits 98% Accuracy Spotting Jute Pests Before They Devastate Crops
Jute, the golden fiber that supports millions of farmers across South Asia, has a silent enemy: an array of seventeen pest species that can quietly strip fields of their yield and slash the economic value of the harvest. Identifying which insect is attacking a crop has traditionally depended on the trained eye of farmers and extension workers, a process that is slow, inconsistent, and often too late to prevent serious damage.
New AI Defense MAPLE Cleans Adversarial Images and Reshapes Decision Boundaries
Deep neural networks now power everything from face recognition to medical image analysis, yet a tiny, carefully crafted nudge to an input image can make them fail spectacularly. These manipulated inputs, known as adversarial examples, are nearly invisible to the human eye but can flip a classifier’s output with alarming reliability.
Merging Memory: New KVCB Method Slims AI Caches Without Losing the Long Tail
Large language models have transformed how the world writes, codes, and reasons, but behind every fluent sentence lies an enormous bookkeeping problem. As these models generate text token by token, they store a growing record of past computations known as the key-value cache, which allows each new word to attend to everything that came before without repeating work.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Blake
Contact Blake, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack