Results 111 to 120 of about 133,461 (264)

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

Resource‐Aware Contrastive Scattering Meta‐Learning for Efficient Few‐Shot Acoustic Anomaly Detection

Advanced Intelligent Systems, EarlyView.
This paper introduces a resource‐aware Contrastive Scattering Meta‐Learning (CSML) framework for acoustic anomaly detection. By leveraging training‐free wavelet scattering and metric‐based meta‐learning, the model achieves competitive performance with only 50 K learnable parameters—a 98% reduction compared to state‐of‐the‐art frameworks—enabling ...
Rami Zewail, Bassem Mokhtar
wiley   +1 more source

Soft Active Electromyography Interface for Machine Learning‐Enabled Silent Speech Recognition

Advanced Intelligent Systems, EarlyView.
A soft, hand‐worn electromyography interface enables intent‐driven silent speech recognition without continuous facial attachment. The device integrates liquid‐metal interconnects, a transparent flexible circuit, and elastomer encapsulation with a fingertip electrode that contacts perioral muscles only on demand.
Yuta Kurotaki, Shusuke Yamakoshi, Reitaro Yoshida, Yutaka Isoda, Tamami Takano, Yuji Isano, Yusuke Miyake, Kentaro Kuribayashi, Hiroki Ota   +8 more
wiley   +1 more source

Toward Complex In‐Car Environment Human–Vehicle Interactions Through Smart Glasses and sEMG‐Based Gesture Recognition

Advanced Intelligent Systems, EarlyView.
This study proposes a novel weighted random forest multimodal fusion method that combines smart glasses and sEMG data for in‐vehicle gesture interaction. It realizes stable performance in dim, occluded, and other constrained scenarios, providing feasible solutions and laying a foundation for universal human–machine interaction.
Wenbo Zhang, Wenting Wei, Kuang Li, Chuyuan Bian, Junkai Xu, Jianing Qiu, Yuxi Lu, Bin He, Shuo Jiang   +8 more
wiley   +1 more source

AI‐Assisted IoT‐Enabled ECG Monitoring: Integrating Foundational and Generative AI Tools for Sustainable Smart Healthcare—Recent Trends

AI &Innovation, EarlyView.
ABSTRACT The rapid evolution of the Internet of Things (IoT) has significantly advanced the field of electrocardiogram (ECG) monitoring, enabling real‐time, remote, and patient‐centric cardiac care. This paper presents a comprehensive survey of AI assisted IoT‐based ECG monitoring systems, focusing on the integration of emerging technologies such as ...
Amrita Choudhury, Kandarpa Kumar Sarma, Lachit Dutta   +2 more
wiley   +1 more source

Histidine Supplementation Stabilizes Hearing and Vision and Improves Growth in HARS1‐Related Autosomal Recessive Disorder Associated With Usher‐Like Symptoms

American Journal of Medical Genetics Part A, EarlyView.
ABSTRACT Autosomal recessive HARS1‐related disorder (originally described as Usher syndrome type 3B) caused by a homozygous Y454S variant in the histidyl‐tRNA synthetase gene (HARS1) is characterized by progressive sensorineural hearing and vision loss and respiratory deterioration with risk for sudden death following febrile illnesses.
Victoria Mok Siu, Rosan Kenana, Rana Chakrabarti, Sarah D. P. Wilhelm, Joseph Andrews, Susan J. Leat, Christina Parker, Michael Miller, Leslie A. Nangle, Wendy McCaul, Ashfia Chowdhury, Natalie Hutchings, Ryan A. Adams, Lauren Guy, Mandy Rhody, Verena Juncal, Marisa I. Mendes, Desiree E. C. Smith, Gajja S. Salomons, Angelica A. Moresco, Daphne L. McCulloch, D. Holmes Morton, Ilka U. Heinemann, C. Anthony Rupar   +23 more
wiley   +1 more source

TECHNOLOGIES GÉO-SPATIALES POUR RENFORCER LES DISPOSITIFS DE GESTION DES TERRES AGRICOLES : APPUI À LA GESTION DES SURFACES AGRUMICOLES PAR TÉLÉDÉTECTION DANS LA PLAINE DE TRIFFA-BERKANE (MAROC)

African Journal on Land Policy and Geospatial Sciences, 2018
L’objectif de ce papier est de proposer et implémenter une procédure de classification d’images satellitaires optique et radar pour la cartographie des cultures, notamment la production d’une carte d’agrumes.
Loubna El Mansouri, Rachid Hadria, Imane Lahmer, Omar Moutaib, Abdessadek Oujemaa, Amine ElGorch   +5 more
doaj  

Refining Domain‐Based Prognostication in DNM1 Encephalopathy: A Mild Phenotype Associated With a GTPase Domain Variant

American Journal of Medical Genetics Part A, EarlyView.
ABSTRACT DNM1 encephalopathy is a rare autosomal dominant genetic condition characterized by a range of neurological and developmental manifestations. The typical phenotype is severe, including profound intellectual disability, treatment‐resistant epilepsy, ataxia, and structural brain abnormalities. However, milder presentations have increasingly been
Caroline Crain, Hope Northrup, Laura S. Farach, Sureni V. Mullegama, Kathleen Shields, Gretchen Von Allmen, Kate Richardson   +6 more
wiley   +1 more source

Psychosocial Stress in the Chinese Community: Speech Analytics Through Linguistic and Acoustic Fusion Using Machine Learning. [PDF]

JMIR Biomed Eng
Chu AMY, Lam BSY, Tsang JTY, Tiwari A, Chan JNL, So MKP.   +5 more
europepmc   +1 more source

Systematic pathway‐level analysis defines conserved transcriptional divergence between primary lung tumors and cell line models

Animal Models and Experimental Medicine, EarlyView.
Lung cancer cell lines diverge substantially from primary tumors at the transcriptional level. Using single‐sample gene set enrichment analysis and L1‐penalized feature selection across TCGA‐LUAD and CCLE‐LUAD, we identified five Hallmark pathways (E2F targets, G2M checkpoint, IFNγ response, coagulation, and EMT) that discriminated primary tumors from ...
Pritam Bera, Rajesh Raju, Debodipta Das
wiley   +1 more source