Results 271 to 280 of about 1,182,353 (322)

A Hybrid Transfer Learning Framework for Brain Tumor Diagnosis

open access: yesAdvanced Intelligent Systems, Volume 7, Issue 3, March 2025.
A novel hybrid transfer learning approach for brain tumor classification achieves 99.47% accuracy using magnetic resonance imaging (MRI) images. By combining image preprocessing, ensemble deep learning, and explainable artificial intelligence (XAI) techniques like gradient‐weighted class activation mapping and SHapley Additive exPlanations (SHAP), the ...
Sadia Islam Tonni   +11 more
wiley   +1 more source

Compliant Robotics in Space: A Prospective Review of Soft and Deformable Systems for Space Missions

open access: yesAdvanced Intelligent Systems, EarlyView.
Compliant robots are increasingly becoming integral to space exploration due to their adaptability, flexibility, and lightweight design. This article reviews categories such as soft, reconfigurable, and hyper‐redundant robots and their evolving role in enhancing space missions.
Hamed Rahimi Nohooji, Holger Voos
wiley   +1 more source

Analysis of a Memcapacitor‐Based Online Learning Neural Network Accelerator Framework

open access: yesAdvanced Intelligent Systems, EarlyView.
This study introduces a novel CMOS‐based memcapacitor framework for efficient neuromorphic computing, achieving 98.4% accuracy on (MNIST) modified national institute of standards and technology and 85.9% on canadian institute for advanced research( CIFAR)‐10.
Ankur Singh, Dowon Kim, Byung‐Geun Lee
wiley   +1 more source

Untethered Autonomous Holonomic Mobile Micromanipulator for Operations in Isolated Confined Spaces

open access: yesAdvanced Intelligent Systems, EarlyView.
Herein, a lightweight (515 g), compact (10 cm3), untethered holonomic mobile micromanipulator powered by piezoelectric actuators is presented. It autonomously manipulates mm to sub‐mm objects and droplets in narrow, hazardous spaces, achieving 0.18 ± 0.51 mm positioning accuracy and −0.4° ± 1.2° angular deviation.
Ryosuke Kinoshita   +7 more
wiley   +1 more source

A Study on Optimal Data Bandwidth of Recurrent Neural Network–Based Dynamics Model for Robot Manipulators

open access: yesAdvanced Intelligent Systems, EarlyView.
In this article, RNN–based learning method is proposed to achieve overall dynamic model of robot manipulators, which is established by optimal data‐bandwidth. The optimal data‐bandwidth is developed as a key behavior of the proposed method, which is designed on the loss function and its derivative.
Seungcheon Shin   +2 more
wiley   +1 more source

Decreasing the Cost of Morphing in Adaptive Morphogenetic Robots

open access: yesAdvanced Intelligent Systems, EarlyView.
Shape‐morphing propulsive limbs enhance locomotion across land‐to‐water transitions, but prior designs rely on thermally responsive components, coupling performance to environmental temperature. This study introduces a pressure‐responsive mechanism that reduces morphing energy costs, enables rapid transitions, and minimizes failure modes.
Luis A. Ramirez   +3 more
wiley   +1 more source

Self‐Organized Multitarget Pursuit in Multi‐Unmanned Aerial Vehicle Systems via Hierarchical Probabilistic Graphical Models

open access: yesAdvanced Intelligent Systems, EarlyView.
Multi‐UAV systems face challenges in adversarial environments due to limited adaptability and interpretability. This study proposes a self‐organized approach using hierarchical probabilistic graphical models with density‐driven parameter estimation.
Yixin Huang   +5 more
wiley   +1 more source

Energy‐Efficient Knapsack Optimization Using Probabilistic Memristor Crossbars

open access: yesAdvanced Intelligent Systems, EarlyView.
The knapsack problem, a nondeterministic polynomial‐time (NP)‐hard combinatorial optimization problem, is solved energy‐efficiently. This work presents an algorithm‐hardware co‐design and implementation for practical (non‐ideal) NP‐hard problems with destabilizing self‐feedback (non‐zero diagonal) and non‐binary Hamiltonian representations under analog
Jinzhan Li, Suhas Kumar, Su‐in Yi
wiley   +1 more source

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

open access: yesAdvanced Intelligent Systems, EarlyView.
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 warping deep–normal–deep breath cycles, DTW achieves perfect genuine–impostor separation (equal error rates = 0%), while a parallel adaptive neuro‐fuzzy inference ...
Beyza Eraslan   +2 more
wiley   +1 more source

Home - About - Disclaimer - Privacy