Design and validation of ultra-compact metamaterial-based biosensor for non-invasive cervical cancer diagnosis in terahertz regime. by Musa N Hamza, Mohammad Tariqul Islam, Sunil Lavadiya, Iftikhar Ud Din, Bruno Sanches, Slawomir Koziel, Md Shabiul Islam

“…This includes identification of the spatial extent of the malignant tissue. Excellent electrical properties of the sensor are accompanied by its compact size, which is highly desirable for non-invasive and portable applications.…”
Get full text

Spatial-Channel Multiscale Transformer Network for Hyperspectral Unmixing by Haixin Sun, Qiuguang Cao, Fanlei Meng, Jingwen Xu, Mengdi Cheng

“…Specifically, a compact feature projection (CFP) module is first used to extract shallow discriminative features. …”
Get full text

Enhanced Spatial Clustering for Crime Analysis: Novel Advances in Ward-Like and SKATER Algorithms for Brazilian Public Security by Raydonal Ospina, Alexsandra Gomes De Lima, Cristiano Ferraz, Cecilia Castro, Carlos Martin-Barreiro, Victor Leiva

“…Validation with the Calinski–Harabasz, Dunn, and Davies–Bouldin indices shows that the new Ward–like method provides the strongest compactness and inter–cluster separation, whereas the Gower–based SKATER method achieves the highest variance-based discrimination. …”
Get full text

STA-AgriNet: A Spatio-Temporal Attention Framework for Crop Type Mapping from Fused Multi-Sensor Multi-Temporal SITS by Jayakrishnan Anandakrishnan, Venkatesan Meenkaski Sundaram, Prabhavathy Paneer

“…The spectral spatial feature mapper (SSFM), mixed parallel spatial attention (MPSA), and spatio-temporal attention mapper (STAM) modules of the STA-AgriNet extract key classification-defining, discriminative patterns for semantic segmentation. …”
Get full text

Acoustic cues for person identification using cough sounds by Van-Thuan Tran, Ting-Hao You, Wei-Ho Tsai

“…The proposed architecture, CoughCueNet, is a convolutional recurrent neural network designed to capture both spatial and temporal patterns in cough sounds. The training process incorporates a hybrid loss function that combines supervised contrastive (SC) learning and cross-entropy (CE) loss to enhance feature discrimination. …”
Get full text