Electronics News and Research

RSS

New Memristor Mimics Brain Function to Prevent AI From Forgetting

Researchers from Jülich have developed a robust new memristor that mimics brain-like learning and memory. Its novel switching mechanism could overcome the “catastrophic forgetting” problem in neural networks.

21 Mar 2025

AI Tool DeepGuard Exposes Fake Images and Strengthens Digital Security

Researchers have developed DeepGuard, an AI-powered tool that accurately detects fake images and traces their origins, enhancing security and preventing misinformation.

3 Mar 2025

Smart Cyber Defense: AI Tech Helps Power Grids Fight Off Hackers

Researchers at the University of Missouri have developed CIBR-Fort, an AI-driven cybersecurity system that predicts and mitigates cyberattacks on power grids with 91.88% accuracy, ensuring real-time protection for critical infrastructure.

26 Feb 2025

Empathetic AI Drives Innovation and Job Satisfaction Among Retail Employees

Retail employees are more likely to innovate when AI systems demonstrate reliability and empathy, fostering a more engaging work environment. This study highlights how AI service quality influences job satisfaction, job fit, and innovation in the retail industry.

19 Feb 2025

From AI to Smart Agriculture: ETRI Startups Impress at CES 2025

Korean researchers showcased cutting-edge startup technologies at CES 2025, reinforcing South Korea’s global presence in innovation and entrepreneurship. Five ETRI-born companies won CES Innovation Awards, highlighting the success of ETRI’s technology incubator.

17 Feb 2025

AI System Integrates Data to Help Preserve the World’s Fragile Coral Reefs

Australian researchers are developing a global real-time monitoring system using machine learning and AI to track coral reef health and combat the rapid decline caused by climate change, aiming for quicker conservation intervention.

13 Feb 2025

AI Sensor Slashes False Fire Alarms by Analyzing Smoke Light Scattering

Researchers have developed an AI-powered fire detection sensor that significantly reduces false alarms by distinguishing between real fire smoke and non-fire aerosol particles using light scattering analysis. This innovation is expected to cut down on unnecessary fire engine dispatches and associated social costs.

4 Feb 2025

AI-Powered OPED Software Slashes EV Powertrain Development from Months to a Day

Researchers at TU Graz have developed OPED, an AI-powered software that shortens the development phase of battery electric vehicle powertrains from several months to just one day, optimizing components for efficiency, cost, and sustainability.

30 Jan 2025

AI Enhances Electrospray Deposition for Advanced Manufacturing

Researchers at Binghamton University and the University at Buffalo are using AI and computational modeling to refine electrospray deposition, a technique for producing ultra-thin polymer films with applications in electronics and healthcare.

30 Jan 2025

KAIST Develops Revolutionary Self-Learning Neuromorphic Chip for Edge AI

Researchers at KAIST have developed a highly reliable, selector-less memristor-based computing system that enables real-time, self-learning AI processing on edge devices, achieving accuracy comparable to ideal simulations in tasks like video foreground-background separation.

21 Jan 2025

LAISC Methodology Enhances AI Safety in Autonomous Systems

Researchers introduce the LAISC methodology to address AI safety concerns, offering systematic tools for mitigating risks in autonomous systems, validated with a driverless train case study.

7 Jan 2025

Next-Gen Microelectronics: DOE Unites AI and Cutting-Edge Materials

Researchers reimagine microelectronics with cutting-edge materials and AI to create energy-efficient systems that could transform computing, sensing, and scientific discovery worldwide.

7 Jan 2025

AI Extends EV Battery Life

Researchers developed a domain knowledge-guided machine learning framework that accurately estimates the state of health of lithium-ion batteries, achieving high precision even with limited data, to advance electric vehicle technologies.

18 Nov 2024

Deep Learning Boosts Security In Virtual Networks By Tackling Complex Intrusion Detection Challenges

Researchers developed a CNN-based deep learning model to enhance intrusion detection in virtual networks, addressing the unique challenges of encapsulation and dynamic environments.

15 Sep 2024

Hybrid Deep Learning Optimizes Renewable Power Flow

This study introduces HDRL-QIGA, a hybrid deep learning model combining reinforcement learning and quantum-inspired algorithms to optimize power flow in renewable energy systems. The model outperforms traditional methods, reducing fuel costs and power losses while ensuring voltage stability.

28 Aug 2024

ML Discovers 2D Materials with Unique Thermal Expansion

Researchers used machine learning and symbolic regression to identify 2D materials with diverse thermal expansion properties, including ZTE and extreme expansion cases. The study provided critical insights for designing materials with tailored thermal properties for advanced applications.

21 Aug 2024

ML Optimizes 5G Handover for Seamless Connectivity

A survey explored machine learning methods to optimize handover processes in 5G networks, addressing challenges like network densification and ensuring seamless communication. The study highlighted ML's potential to improve quality of service in next-generation networks.

21 Aug 2024

LLMs Detect UI Design Flaws Accurately

Researchers introduced UISGPT, a large language model system that identifies UI design smells by analyzing guidelines and input designs. The system significantly improves design flaw detection and generates clear, actionable reports, setting a new standard in UI design evaluation.

13 Aug 2024

AI-Powered E-Skin Boosts Rescue Robots' Capabilities

Researchers developed a multimodal electronic skin (e-skin) integrated with AI to boost rescue robots' efficiency in post-earthquake scenarios. Combining flexible ecoflex with PVA-CNF organohydrogel, the e-skin replicates human skin's sensory abilities and adds detection of object proximity and toxic gases like NO2.

12 Aug 2024

Deep Neural Network Improves Tea Leaf Pose Estimation

Researchers developed TeaPoseNet, a deep neural network for estimating tea leaf poses, focusing on the Yinghong No.9 variety. Trained on a custom dataset, TeaPoseNet improved pose recognition accuracy by 16.33% using a novel algorithm, enhancing tea leaf analysis.

8 Aug 2024