Results 91 to 100 of about 683,409 (316)

Improving the Robustness of Visual Teach‐and‐Repeat Navigation Using Drift Error Correction and Event‐Based Vision for Low‐Light Environments

Advanced Robotics Research, EarlyView.
Visual teach‐and‐repeat (VTR) navigation allows robots to learn and follow routes without building a full metric map. We show that navigation accuracy for VTR can be improved by integrating a topological map with error‐drift correction based on stereo vision.
Fuhai Ling, Ze Huang, Tony J. Prescott
wiley   +1 more source

Implementation of MobileNet Architecture for Skin Cancer Disease Classification

Journal of Applied Informatics and Computing
As the number of occurrences of skin cancer increases year, it becomes more and more crucial to identify the disease accurately and effectively. This study aims to implement and evaluate the MobileNet architecture for classifying nine types of skin ...
Haniifa Aliila Faudyta, Jesica Trivena Sinaga, Egia Rosi Subhiyakto   +2 more
doaj   +1 more source

Data‐Driven Bulldozer Blade Control for Autonomous Terrain Leveling

Advanced Robotics Research, EarlyView.
A simulation‐driven framework for autonomous bulldozer leveling is presented, combining high‐fidelity terramechanics simulation with a neural‐network‐based reduced‐order model. Gradient‐based optimization enables efficient, low‐level blade control that balances leveling quality and operation time.
Harry Zhang, Ganesh Arivoli, Huzaifa Unjhawala, Luning Bakke, Radu Serban, Dan Negrut   +5 more
wiley   +1 more source

Comparative Study: Flower Classification using Deep Learning, SMOTE and Fine-Tuning

Journal of Applied Informatics and Computing
Deep learning is a technology that can be used to classify flowers. In this research, flower type classification using the CNN method with several existing CNN architectures will be discussed.
Vincentius Praskatama, Guruh Fajar Shidik, Amanda Prawita Ningrum   +2 more
doaj   +1 more source

Deep Learning Approach for Predicting Efficiency in Organic Photovoltaics from 2D Molecular Images of D/A Pairs

Advanced Theory and Simulations, EarlyView.
This study highlights the potential of deep learning, particularly Convolutional Neural Networks (CNNs), for predicting the photovoltaic performance of organic solar cells. By leveraging 2D images representing donor/acceptor molecular pairs, the model accurately estimates key performance indicators proving that this image‐based approach offers a fast ...
Khoukha Khoussa, Patrick Lévêque, Larbi Boubchir   +2 more
wiley   +1 more source

Analysis of digital intelligent financial audit system based on improved BiLSTM neural network

Nonlinear Engineering
Traditional auditing methods have difficulties in detecting various financial issues hidden in massive amounts of data. With the continuous advancement of deep learning and digital technology, new audit methods have been provided for computer auditing ...
Zhu Xincai
doaj   +1 more source

EEG Depression Recognition Based on Multi-domain Features Combined with CBAM Model

Journal of Harbin University of Science and Technology
At present, the electroencephalogram (EEG) identification method for depression mainly uses a single feature extraction method, which cannot cover multi-domain feature information, resulting in poor classification performance of the existing model ...
CHEN Yu, HU Xiuxiu, WANG Sheng
doaj   +1 more source

A Review on Biodegradable Materials of Sustainable Soft Robotics and Electronics

Advanced Science, EarlyView.
Biodegradable materials are gaining increasing attention in soft robotics and electronics due to their environmental friendliness, showing great potential for sustainability. In this review, the classification of biodegradable materials, their applications in the field of soft robotics and electronics, as well as the challenges and future prospects ...
Yizhu Xie, Jiaxin Han, Xingyi Dai, Xuyang Zhang, Kangwen Xiao, Junhui Huang, Yajun Cao, Aihua Zhong, Long‐Biao Huang   +8 more
wiley   +1 more source

Real-Time Anomaly Detection in Solar Panel Arrays: Integrating Single Shot Multibox Detector (Ssd) With Iot and Edge Computing [PDF]

ITM Web of Conferences
Convolutional Neural Networks (CNNs) have revolutionized feature extraction for fault detection in solar panels by using hierarchical spatial extraction using convolutional layers These networks reveal important features such as cracks, hotspots, and ...
Babu Y. Rajendra, Priyadarsini N. Indira, Sirisha P.G.K., Reddy C. Ravishankar   +3 more
doaj   +1 more source

An Ultrathin, Cyano‐Functionalized Copolymeric Memristor by iCVD Process for Driving Convolutional Neural Networks of High‐Resolution Images

Advanced Science, EarlyView.
Two‐terminal polymer memristors based on cyano‐functionalized copolymer films are developed via a solvent‐free, initiated chemical vapor deposition (iCVD) process for high‐resolution image classification. Molecularly engineered p(CEA‐co‐DEGDVE) films enable stable, linear, and symmetric conductance modulation, supporting multi‐level weight mapping in ...
Ji In Kim, Minsu So, Woo Jin Wang, Taehoon Kim, Eun Su Jeong, Kyumin Sim, Hamin Park, Sung Kyu Kim, Yong Goo Shin, Junhwan Choi, Min Ju Kim   +10 more
wiley   +1 more source