Telecomunicaciones, información y comunicación

Synthetic Electrocardiogram Spectrogram Generation Using Generative Adversarial Network‐Based Models: A Comparative Study
03/11/2025 - Cardiovascular diseases are leading death causes; electrocardiogram (ECG) analysis is slow, motivating machine learning and deep learning. This study compares deep convolutional generative...
Disentangling Coincident Cell Events Using Deep Transfer Learning and Compressive Sensing
03/11/2025 - Overlapping cells during detection distort single‐cell measurements and reduce diagnostic accuracy. A hybrid framework combining a fully convolutional neural network with compressive sensing to...
Step‐Efficient Parallel Implementation of n‐bit Full Adders Using Stateful Logic in Memristor Crossbar Arrays
30/10/2025 - A step‐efficient stateful logic architecture is demonstrated using a fabricated 32 × 32 memristor crossbar array, enabling parallel n‐bit full adder operations directly in memory. By...
RanBALL: An Ensemble Machine Learning Framework for Accurate Subtype Identification of Pediatric B‐Cell Acute Lymphoblastic Leukemia
30/10/2025 - Here, we present RanBALL, an ensemble random projection‐based model for accurate and cost‐effective identification of B‐cell acute lymphoblastic leukemia subtypes is presented. By preserving...
Bridging High‐Fidelity Simulations and Physics‐Based Learning using a Surrogate Model for Soft Robot Control
30/10/2025 - A surrogate‐model‐based framework is proposed for combining high‐fidelity finite element method and efficient physics simulations to enable fast, accurate soft robot simulation for...
Predicting Postresection Colorectal Liver Metastases Recurrence Using Advanced Graph Neural Networks with Explainability and Causal Inference
30/10/2025 - This study introduces a framework that combines graph neural networks with causal inference to forecast recurrence and uncover the clinical and pathological factors driving it. It further provides...
A Soft Wearable Robot for Vertical Jump Enhancement via a Pneumatic Energy‐Storing Propulsion Actuator and Triarticular Kinetic‐Chained Structure
28/10/2025 - The Jump‐Enhancing Textile Suit integrates the Pneumatic Energy‐Storing Propulsion Actuator (PESPA) and the Triarticular Kinetic‐Chained Structure (TKiCS). PESPA stores elastic energy under...
Machine Learning Elucidates Population Density‐Dependent Morphological Phenotypic Changes of Macrophages
26/10/2025 - Herein, label‐free phase‐contrast microscopy imaging with machine learning to interrogate the relationship between the population density and morphological features of macrophages is coupled....
Cryogenic Neuromorphic Synaptic Behavior in 180 nm Silicon Transistors for Emerging Computing Systems
26/10/2025 - This study investigates the neuromorphic plasticity behavior of 180 nm bulk complementary metal oxide semiconductor (CMOS) transistors at cryogenic temperatures. The observed hysteresis data reveal...
A Compact, Self‐Recovering Wire Electrode Electrohydrodynamic Pump for High‐Speed McKibben Artificial Muscle Actuation
26/10/2025 - A compact and self‐recovering wire electrode electrohydrodynamic pump achieves high pressure, fast flowrate, and automatic recovery after dielectric discharge breakdowns. The pump delivers twice...
Compact Modeling of Volatile‐Switching Electrochemical Metallization Memory Cells by Means of the Electromotive Force
26/10/2025 - A volatile‐switching compact model of electrochemical metallization memory cells for neuromorphic architecture is developed and validated by reliable reproduction of device characterization...
Robust Dysarthric Speech Recognition with GAN Enhancement and LLM Correction
26/10/2025 - This study tackles dysarthric speech recognition by combining generative adversarial network (GAN)‐generated synthetic data with large language model (LLM)‐based error correction. The approach...
Machine Learning‐Based Standard Compact Model Binning Parameter Extraction Methodology for Integrated Circuit Design of Next‐Generation Semiconductor Devices
26/10/2025 - This study presents a neural network‐based methodology for Berkeley Short‐Channel IGFET Model–Common Multi‐Gate parameter extraction of gate‐all‐around field effect transistors,...
Wirelessly Powered Soft Magnetic Robot with Microneedle for Electrical Stimulation and Drug Delivery
26/10/2025 - A wirelessly powered soft magnetic robot integrates microneedles to enable dual functions: electrical stimulation (86.7% efficiency at 6 cm, tunable 0–20 V voltage, 0.4–50 ms pulses) and...
A community‐driven vision for a new knowledge resource for AI
26/10/2025 - The long‐standing goal of creating a comprehensive, multi‐purpose knowledge resource, reminiscent of the 1984 Cyc project, still persists in AI. Despite the success of knowledge resources like...
Multiobjective Environmental Cleanup with Autonomous Surface Vehicle Fleets Using Multitask Multiagent Deep Reinforcement Learning
20/10/2025 - This study presents a multitask strategy for plastic cleanup with autonomous surface vehicles, combining exploration and cleaning phases. A two‐headed Deep Q‐Network shared by all agents is...
CAGE challenge 4: A scalable multi‐agent reinforcement learning gym for autonomous cyber defence
21/10/2025 - As cyber threats become increasingly automated and sophisticated, novel solutions must be introduced to improve defense of enterprise networks. Deep reinforcement learning (DRL) has demonstrated...
Marco de planificación y control para un robot cuadrúpedo de configuración variable
17/10/2025 - Multiconfiguration quadruped robots enhance adaptability by switching between mammal‐like and reptile‐like morphologies. This study presents a nonlinear constraint‐based motion planner...
A Robotic Urinary Bladder Enabling Volume Monitoring and Assisted Micturition
17/10/2025 - An implantable robotic bladder is presented that can store urine in an origami‐designed enclosure. An inductance sensing principle can monitor and transfer the urine volume in real‐time. It can...
Natural Entanglement Inspired Cilia‐Like Soft Gripper for Rapid Adaptive Grasping
13/10/2025 - Inspired by natural entanglement, a lightweight, low‐cost soft gripper is developed using wire‐actuated silicone tubes. Rapid self‐entanglement enables adaptive grasping of diverse objects...
IAR‐Net: Tabular Deep Learning Model for Interventionalist's Action Recognition
13/10/2025 - This study presents IAR‐Net, a deep‐learning framework for catheterization action recognition. To ensure optimality, this study quantifies interoperator similarities and differences using...