Defensa y serguridad

Bioinspired Fully On‐Chip Learning Implemented on Memristive Neural Networks

01/07/2025 - This work proposes a memristive neural network based on van der Waals ferroelectric memristors and contrastive Hebbian learning, enabling fully on‐chip learning. The system achieves over 98%...

Anchoring Morphological Representations Unlocks Latent Proprioception in Soft Robots

01/07/2025 - The authors present ProSoRo, a proprioceptive soft robot that anchors morphological states to a single internal reference frame and employs a multimodal variational autoencoder for crossmodal...

Enhanced Embolic Signal Analysis through Ensemble Deep Learning Techniques Utilizing Transfer Learning and Layer Freezing Strategies

01/07/2025 - A 10‐convolutional neural network ensemble using transfer learning and layer freezing analyzes 400 Doppler‐ultrasound spectrograms to distinguish speckle, artifact, and ESs. Soft and hard voting...

CoRoFR: Community Detection of Feature Graph Improves Feature Selection Using Robust Fuzzy Rough Set

01/07/2025 - In machine learning, features often function as communities in many tasks, especially in medicine. However, existing feature selection methods struggle to mine feature collaborations, which can boost...

EndoARSS: Adapting Spatially Aware Foundation Model for Efficient Activity Recognition and Semantic Segmentation in Endoscopic Surgery

29/06/2025 - This article introduces EndoARSS, a novel multitask learning framework that combines surgical activity recognition and semantic segmentation for endoscopic surgery. Utilizing the foundation model...

Highly Efficient Classification of Time‐Series Based on Resistive Switching Cluster‐Assembled Materials

25/06/2025 - Cluster‐assembled nanocomposite devices are employed for the classification of neuronal traces, without any preprocessing of the input time‐series or prior training of the nonlinear devices. The...

NSIP: Neural Network SPICE Integration Platform for Ferroelectric Field‐Effect Transistor‐Based Crossbar Arrays

25/06/2025 - This study presents the neural network SPICE integration platform (NSIP), a novel simulation framework for FeFET‐based crossbar arrays in neuromorphic computing. NSIP accurately models synaptic...

RefineCatDiff: Toward High‐Quality Medical Image Segmentation via a Categorical Diffusion Refinement Framework

25/06/2025 - This study proposes RefineCatDiff, a refinement framework for high‐quality medical image segmentation. By developing a categorical distribution‐based discrete diffusion process for refinement,...

Adapting Image‐Based Models for 1D Data via Spider Plot Transformation and Transfer Learning

25/06/2025 - A novel method enables the use of pretrained image‐based neural networks for complex 1D data, including Raman and mid‐infrared spectra, electrocardiograms, and mass spectrometry. 2D spider plots...

A Field Programmable Gate Array‐Assisted Optoelectronic Emulator for Photonic Neuromorphic Computing

23/06/2025 - This work presents a hybrid optoelectronic architecture using field‐programmable‐gate‐array‐controlled optical components for multiplication operations. Data are encoded via electro‐optic...

Exploring the Influence of Applied Potential and Catalyst Morphology on the Selectivities of Copper Toward Carbon Dioxide Electroreduction Using Machine Learning

23/06/2025 - A machine learning‐assisted workflow integrates experimental data mining, model training, and SHapley Additive exPlanations‐based interpretation to map the coupled effects of catalyst morphology,...

Liveness‐Verified Dynamic Time Warping‐Based Authentication and Hybrid Adaptive Neuro‐Fuzzy Inference System Identification for Single‐Channel Diaphragmatic Breathing Surface Electromyography Biometrics

22/06/2025 - The first biometric framework to harness dynamic time warping (DTW) for single‐channel diaphragmatic surface electromyography authentication via post‐hoc alignment is presented. By optimally...

Advances in Invertebrate Biohybrid Robotics: Leveraging Nature for Locomotion and Sensing in Engineered Systems

22/06/2025 - This review explores invertebrate biohybrid robots that integrate living organisms—such as insects, jellyfish, spiders, and sea slugs—into robotic systems for locomotion, sensing, and actuation....

Quantifying Printing Quality for Printed Electrodes via Deep Learning and Spatial Association: Empowering Process Optimization

22/06/2025 - This study proposes a method to quantify the printing quality of roll‐to‐roll gravure‐printed electronics by combining deep learning and spatial association analysis. The proposed approach...

Phase Stability in Rare‐Earth‐Doped Apatites: A Machine Learning Approach

17/06/2025 - The thermal behavior and phase stability of rare‐earth‐doped apatites are investigated using high‐temperature X‐ray diffraction and thermogravimetric analysis. A machine learning decision...

Memimpedance‐Based Biomolecular Device for Adaptive Physical Reservoir Computing

16/06/2025 - By integrating fast‐switching ion‐channel‐based memristive and slow‐switching biomembrane‐based memcapacitive nodes within droplet interface bilayers, this hybrid memimpedance reservoir...

Reconfigurable Haptic Feedback: Comprehensive Design and Control Framework

16/06/2025 - Herein, a modular framework is presented for designing and controlling soft robotic haptic devices capable of shape and stiffness modulation. These reconfigurable modules enable adaptable tactile...

Building trust: Foundations of security, safety, and transparency in AI

20/05/2025 - This paper explores the rapidly evolving ecosystem of publicly available AI models and their potential implications on the security and safety landscape. Understanding their potential risks and...

Empowering Biomedical Research with Foundation Models in Computational Microscopy: A Systematic Review

19/05/2025 - The integration of foundation models into computational microscopy revolutionizes biomedical research by enhancing imaging resolution, accelerating data analysis, and enabling real‐time biological...

Configurable Kernel Map Implementation in Memristor Crossbar for Convolution Neural Network

15/05/2025 - A configurable kernel map implementation using a memristor crossbar array is presented. The crossbar array area can be configured based on the number of read cycles per inference, which directly...

A Novel Semi‐Automated Pipeline for Optimizing 3D‐Printed Drug Formulations

15/05/2025 - A novel, semi‐automated deep learning and differential evolution pipeline designed for generating medicines for 3D‐printed medicines is introduced. This pipeline successfully generates a diverse...