Science – Page 6

Pig ‘Tattoos’: How Back Marks Unlock Automated Animal ID

27.03.2026 by qfx

This study utilizes a defined set of back marks - including dot-dot, horizontal dot lines, ‘i’, ‘o’, reversed ‘t’, ‘s’, ‘v’, vertical lines, and ‘x’ - as fundamental elements within its methodology.

A new study highlights the importance of strategically designed back markings for reliably identifying individual pigs using computer vision and machine learning.

Unlocking Microbial Power: How Anode Materials Boost Bioelectricity Generation

27.03.2026 by qfx

The study demonstrates that selecting appropriate latent dimensions improves imputation accuracy-measured by root mean squared error (RMSE) during five-fold cross-validation-even when missing data follows a missing not at random (MNAR) pattern, and specifically, when validation sets exhibit missing completely at random (MCAR) data-suggesting robustness to common missingness mechanisms.

New research demonstrates how carefully selected anode materials can dramatically improve the efficiency of microbial fuel cells used for wastewater treatment and sustainable energy production.

Mapping Anomalies: A New Vision for Long-Term Trajectory Analysis

27.03.2026 by qfx

TITAnD encodes the chaotic whispers of movement - whether dense GPS streams or sparse stay-points - into a unified hyperspectral trajectory image, where each pixel doesn’t simply mark location, but embodies a confluence of space, semantics, time, and the subtle poetry of motion [latex] day × time [/latex].

Researchers have developed a novel method for detecting unusual patterns in months-long GPS data by transforming movement into visual representations.

Predicting the Future: A New Approach to Irregular Time Series Forecasting

27.03.2026 by qfx

Researchers have developed a deep learning model that accurately forecasts complex systems even when data is missing or unevenly spaced in time.

Learning to Route: AI Surpasses Heuristics for the Traveling Salesman Problem

27.03.2026 by qfx

$The system calculates node embeddings from graph coordinates, then utilizes a causal transformer decoder-informed by both node transitions and predicted relational trajectory graphs [latex]\hat{R}_{t}[/latex]-to forecast subsequent relational trajectory graphs [latex]\tilde{R}_{t}[/latex], demonstrating a method for relational reasoning within dynamic graph structures.$

A new approach using offline reinforcement learning trains an AI to find better routes than traditional methods, even without live experimentation.

Hidden Signals: Backdooring Deep Learning for Wireless Communication

27.03.2026 by qfx

Explainable artificial intelligence (XAI) techniques guide adversarial attacks against deep neural networks, recurrent neural networks, and convolutional neural networks, demonstrating vulnerabilities across diverse architectures.

Researchers have demonstrated a novel attack that subtly manipulates radio signals to compromise deep learning-based automatic modulation classifiers.

The Writing is on the Wall: Reimagining Education in the AI Era

27.03.2026 by qfx

As AI writing tools become increasingly sophisticated, educators must move beyond simply detecting plagiarism and focus on cultivating essential cognitive skills.

Truth Decay: How Well Do AI Models Spot Fake News?

27.03.2026 by qfx

Dataset-specific experiments reveal a varied performance landscape, as evidenced by the distribution of F1-scores across different datasets, highlighting the sensitivity of the system to input data characteristics.

A new study rigorously compares popular artificial intelligence techniques for detecting misinformation, revealing persistent challenges in generalizing across different news sources.

Spotting the Machine: A New Approach to AI Text Detection

27.03.2026 by qfx

Exons-Detect proposes a system built not on construction, but on discerning patterns - a method for identifying exon boundaries within genomic sequences by leveraging the inherent statistical properties of splicing signals, thereby acknowledging that the search for genetic code is less about building a map and more about cultivating an understanding of existing, complex arrangements.

Researchers have developed a novel, training-free method to reliably identify text generated by artificial intelligence by focusing on key linguistic signals within the text itself.

Simulating the Real World of High-Frequency Trading

27.03.2026 by qfx

$The quantile regression (QR) model failed to detect any discernible impact on the average price path surrounding a simulated metaorder, as evidenced by a distribution of inter-event times [latex]\Delta t[/latex] that aligns between empirical data (blue) and the QR prediction (green).$

New research tackles the challenges of accurately modeling limit order books to better evaluate trading strategies in dynamic markets.