Results 101 to 110 of about 119 (119)

Machine Learning‐Based Wind Classification by Wing Deformation in Biomimetic Flapping Robots: Biomimetic Flexible Structures Improve Wind Sensing

Advanced Intelligent Systems, EarlyView.
Strain gauges are attached to biomimetic flapping wings to investigate how wing strain sensors detect wind directions. A convolutional neural network model for wind direction classification is developed through experiments. The results reveal that wind classification is possible with strain data of only 0.2 flapping cycles, and the use of biomimetic ...
Kenta Kubota, Hiroto Tanaka
wiley   +1 more source

A Hybrid Transfer Learning Framework for Brain Tumor Diagnosis

Advanced 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, Md. Alif Sheakh, Mst. Sazia Tahosin, Md. Zahid Hasan, Taslima Ferdaus Shuva, Touhid Bhuiyan, Muhammad Ali Abdullah Almoyad, Nabil Anan Orka, Md. Tanvir Rahman, Risala Tasin Khan, M. Shamim Kaiser, Mohammad Ali Moni   +11 more
wiley   +1 more source

Graph‐Based Representation Approach for Deep Learning of Organic Light‐Emitting Diode Devices

Advanced Intelligent Systems, EarlyView.
In this study, a novel graph‐based representation methodology is proposed to effectively address current challenges in description. An ideal approach to representing the device parameters in the static equilibrium state is suggested. In the trained predictive model, superior accuracy is demonstrated, making it a reliable tool for representing organic ...
Taeyang Lee, Jeongwhan Choi, Inyeob Na, Insun Yoo, Sungil Woo, Kwang Jong Kim, Mikyung Park, Joonghwan Yang, Jeongguk Min, Seokwoo Lee, Noseong Park, Joonyoung Yang   +11 more
wiley   +1 more source

Ultrasensitive Ultrasoft Buckled Crack‐Based Sensor for Respiration Measurement and Enhanced Human–Machine Interface

Advanced Intelligent Systems, EarlyView.
The Buckled, Ultrasoft, Crack‐based, Large strain, EpiDermal (BUCKLED) sensor is a flexible, ultrasensitive wearable strain sensor designed to precisely measure subtle skin deformations. By utilizing a buckled structure to enhance compliance integrating crack‐based sensing mechanisms, it improves accuracy in applications like respiratory monitoring ...
Jingoo Lee, Taewi Kim, Hyeongseok Kim, Sunghoon Im, Jieun Park, Inyong Park, Dae Hoon Park, Bangwoo Han, Daeshik Kang, Gunhee Lee   +9 more
wiley   +1 more source

Machine Learning‐Assisted Simulations and Predictions for Battery Interfaces

Advanced Intelligent Systems, EarlyView.
This review summarizes machine learning (ML)‐assisted simulations and predictions at battery interfaces. It highlights how employing ML algorithms with machine vision, enables the lithium dendrite growth simulation, the solid–electrolyte interphase formation, and other interfacial dynamics.
Zhaojun Sun, Xin Li, Yiming Wu, Qilin Gu, Shiyou Zheng   +4 more
wiley   +1 more source

π‐PhenoDrug: A Comprehensive Deep Learning‐Based Pipeline for Phenotypic Drug Screening in High‐Content Analysis

Advanced Intelligent Systems, EarlyView.
This study develops a deep learning‐based pipeline named π‐PhenoDrug for cell phenotype‐driven drug activity screening. π‐PhenoDrug integrates cell segmentation, morphological profile construction, and phenotype analysis modules, and it can assess drug effects on living cells in both supervised and unsupervised modes.
Xiao Li, Qinxue Ouyang, Mingfei Han, Xiaoqing Liu, Fuchu He, Yunping Zhu, Ling Leng, Jie Ma   +7 more
wiley   +1 more source

A Motion‐Sensing Integrated Soft Robot with Triboelectric Nanogenerator for Pipeline Inspection

Advanced Intelligent Systems, EarlyView.
A soft robot integrated with triboelectric nanogenerator‐based tactile sensors is proposed to achieve locomotion within pipelines and exteroception of different materials and structures of pipeline inner surfaces. By introducing a 1D‐convolutional neural network algorithm, the soft robot's accuracy in recognizing eight different pipe inner surface ...
Rui Chen, Huigang Wang, Haoji Wang, Huijiang Wang, Li Bai, Xinpei Ai, Lifu Liu, Zhihao Hu, Zean Yuan   +8 more
wiley   +1 more source

Implementation of a Biologically Inspired Responsive Joint Attention System for a Social Robot

Advanced Intelligent Systems, EarlyView.
This work introduces a responsive joint attention system in the social robot Mini, enabling dynamic, human‐like responses based on the user's head, body, and gaze. The system enhances user engagement and robot responsiveness. An experiment reveals significant improvements in social presence when the system is active, validating its effectiveness in ...
Jesús García‐Martínez, Juan José Gamboa‐Montero, José Carlos Castillo, Álvaro Castro‐González, Miguel Angel Salichs   +4 more
wiley   +1 more source

Medical Image Hybrid Watermark Algorithm Based on Frequency Domain Processing and Inception v3

Advanced Intelligent Systems, EarlyView.
Frequency domain processing and Inceptionv3 method is used in this article for digital image watermarking of medical images. The algorithm extracts feature vectors from medical images using discrete wavelet transform and discrete cosine transform, enhancing the robustness of the image watermark With the widespread use of digital medical images in ...
Yu Fan, Jingbing Li, Uzair Aslam Bhatti, Saqib Ali Nawaz, Yenwei Chen   +4 more
wiley   +1 more source

Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks

IEEE Communications Surveys and Tutorials, 2020
Chunxiao Jiang, Haijun Zhang, Jingjing Wang   +2 more
exaly