Exploring the nonlinear impact of visual environment on residents’ happiness: a computational framework integrating semantic and geometric features by Dongyang Wang, Yandong Wang, Mingxuan Dou, Mengling Qiao, Xiaokang Fu, Yan Zhang

“…Both semantic and geometric features of VE are systematically measured by combining street view images and building footprints through semantic segmentation and isovist analysis. …”
Get full text

Readability Formulas for Elementary School Texts in Mexican Spanish by Daniel Fajardo-Delgado, Lino Rodriguez-Coayahuitl, María Guadalupe Sánchez-Cervantes, Miguel Ángel Álvarez-Carmona, Ansel Y. Rodríguez-González

“…The second was derived through genetic programming (GP), a machine learning technique that evolves symbolic expressions based on training data. Both approaches prioritize interpretability and use standard textual features, such as sentence length, word length, and lexical and syntactic complexity. …”
Get full text

Assessment of the Boron Treatability Level of Lesser-Known Timber Species by the Impregnation Method by Vindhya Bandara, Anura Alwis, Thusitha Bandara, Chaminda Muthumala, Faiz Marikar

Get full text

Adaptive spatial-channel feature fusion and self-calibrated convolution for early maize seedlings counting in UAV images by Zhenyuan Sun, Zhenyuan Sun, Zhenyuan Sun, Zhi Yang, Zhi Yang, Yimin Ding, Yimin Ding, Boyan Sun, Boyan Sun, Saiju Li, Saiju Li, Zhen Guo, Zhen Guo, Lei Zhu, Lei Zhu

“…RC-Dino introduces two innovative components: a novel self-calibrating convolutional layer named RSCconv and an adaptive spatial feature fusion module called ASCFF. The RSCconv layer improves the representation of early maize seedlings compared to non-seedling elements within feature maps by calibrating spatial domain features. …”
Get full text

A high-efficiency modeling method for analog integrated circuits by Dongdong Chen, Yunqi Yang, Xianglong Wang, Di Li, Guoqing Xin, Yintang Yang

“…The CNN model with three convolutional kernels was constructed to extract “transistor-circuit module-integrate circuit” features level by level, which can replace the simulation software to effectively improve the training efficiency and accuracy. …”
Get full text

Multimodal radiomics model with triple -timepoint contrast-enhanced ultrasound for precise diagnosis of C-TIRADS 4 thyroid nodules by Linlin Shao, Lili Zhang, Lifang Liu, Fangfang Sun, Hongyu Li, Tongfeng Liu, Feng Hu, Lirong Zhao

“…ObjectiveThis study aims to construct a multimodal radiomics model based on contrast-enhanced ultrasound (CEUS) radiomic features, combined with conventional ultrasonography (US) images and clinical data, to evaluate its diagnostic efficacy in differentiating benign and malignant thyroid nodules (TNs) classified as C-TIRADS 4, and to assess the clinical application value of the model.MethodsThis retrospective study enrolled 135 patients with C-TIRADS 4 thyroid nodules who underwent concurrent US and CEUS before FNA/surgery. …”
Get full text

基于脑影像及临床特征的机器学习模型预测缺血性卒中后心房颤动 A Machine Learning Model Based on Brain Imaging and Clinical Features for Predicting Atrial Fibrillation Detected after Stroke... by 张栗源1，刘涛2，姜勇1，李子孝1，3，王拥军1，3，杨晓萌1，3(ZHANG Liyuan1, LIU Tao2, JIANG Yong1, LI Zixiao1,3, WANG Yongjun1,3, YANG Xiaomeng1,3 )

“…Abstract: Objective To investigate the predictive value of a machine learning model based on brain imaging and clinical features in patients with atrial fibrillation detected after stroke. …”
Get full text

D2LFS2Net: Multi‐class skin lesion diagnosis using deep learning and variance‐controlled Marine Predator optimisation: An application for precision medicine by Veena Dillshad, Muhammad Attique Khan, Muhammad Nazir, Oumaima Saidani, Nazik Alturki, Seifedine Kadry

“…The top features from the fused feature vector are classified using machine learning classifiers. …”
Get full text

Instance segmentation of oyster mushroom datasets: A novel data sampling methodology for training and evaluation of deep learning models by Christos Charisis, Meiqing Wang, Dimitrios Argyropoulos

“…Also, the study aims to examine the ability of five feature extraction backbone configurations of Mask R-CNN: i) CNN-based (ResNet50, ResNeXt101 and ConvNeXt) and ii) Transformer-based (Swin small and tiny) to accurately detect and segment single mushroom instances within the cluster in the images. …”
Get full text

Exploring the Needs and Preferences of Athletes in Cardiac (Tele)Rehabilitation to Enhance Rehabilitation Outcome: A Qualitative Study by Fruytier L, Serban IB, Van de Sande DA, Colombo S, Houben S, Brombacher A, Kemps H

“…The preferred technological features for a CTR system tailored for athletes include periodic digital consultations with clinicians, home-based training specific to one’s sport, utilization of technology to monitor workouts, data sharing and remote feedback, personalized exercise recommendations and online educational materials.Conclusion: This research explored the user needs and preferences of athlete patients in CR. …”
Get full text

Prognostic and predictive value of pathohistological features in gastric cancer and identification of SLITRK4 as a potential biomarker for gastric cancer by Yuzhe Zhang, Yuhang Xue, Yongju Gao, Ye Zhang

“…Abstract The aim of this study was to develop a quantitative feature-based model from histopathologic images to assess the prognosis of patients with gastric cancer. …”
Get full text

A hybrid approach for intrusion detection in vehicular networks using feature selection and dimensionality reduction with optimized deep learning. by Fayaz Hassan, Zafi Sherhan Syed, Aftab Ahmed Memon, Saad Said Alqahtany, Nadeem Ahmed, Mana Saleh Al Reshan, Yousef Asiri, Asadullah Shaikh

“…We proposed a hybrid approach uses automated feature engineering via correlation-based feature selection (CFS) and principal component analysis (PCA)-based dimensionality reduction to reduce feature matrix size before a series of dense layers are used for classification. …”
Get full text

An enhanced BERT model with improved local feature extraction and long-range dependency capture in promoter prediction for hearing loss by Jing Sun, Yangfan Huang, Jiale Fu, Li Teng, Xiao Liu, Xiaohua Luo

“…The CNN module is able to capture local regulatory features, while the BiLSTM module can effectively model long-distance dependencies, enabling efficient integration of global and local features of promoter sequences. …”
Get full text

Numérique et autonomisation des élèves : quelle formation initiale des enseignants ? by Ghislaine Gueudet, Sophie Joffredo-Le Brun, Antoine Le Bouil, Carole Le Hénaff, Gwenaëlle Riou-Azou, Sabrina Srey

“…In this article we investigate how an initial training based on collective documentation work for designing classroom scenarios can contribute to achieving this objective for trainee teachers. …”
Get full text

A Dynamic Adaptive Framework for Remote Sensing Imagery Superpixel Segmentation and Classification via Dual-Branch Feature Learning by Wangtun Yang, Yang Zhang, Heng Zhang, Liangzhi Li

Get full text

Smart Grid Intrusion Detection for IEC 60870-5-104 With Feature Optimization, Privacy Protection, and Honeypot-Firewall Integration by Pedamallu Sai Mrudula, Rayappa David Amar Raj, Archana Pallakonda, Yanamala Rama Muni Reddy, K. Krishna Prakasha, V. Anandkumar

“…Defences against adversarial attacks use FGSM-based training, feature smoothing, and ensemble-based defences, to reduce susceptibility to evasion tactics. …”
Get full text

Macular form of post-kala-azar dermal leishmaniasis: Clinical features, diagnosis, and significance in the Kala-Azar Elimination Programme by V. Ramesh, Nilay Kanti Das

Get full text

Local-Global Feature Extraction Network With Dynamic 3-D Convolution and Residual Attention Transformer for Hyperspectral Image Classification by Qiqiang Chen, Zhengyang Li, Junru Yin, Wei Huang, Tianming Zhan

“…Currently, convolutional neural network (CNN) and transformer-based hyperspectral image (HSI) classification methods have attracted significant attention owing to their effective feature representation capabilities. …”
Get full text

A hybrid approach for binary and multi-class classification of voice disorders using a pre-trained model and ensemble classifiers by Mehtab Ur Rahman, Cem Direkoglu

“…Our hybrid approach, combines deep learning features with various powerful classifiers. In the first stage, high-level feature embeddings are extracted from voice data spectrograms using a pre-trained VGGish model. …”
Get full text

Advances in Federated Learning: Combining Local Preprocessing With Adaptive Uncertainty Symmetry to Reduce Irrelevant Features and Address Imbalanced Data by Zahraa Khduair Taha, Johnny Koh Siaw Paw, Yaw Chong Tak, Tiong Sieh Kiong, Kumaran Kadirgama, Foo Benedict, Tan Jian Ding, Kharudin Ali, Azher M. Abed

“…On the server side, adaptive thresholding based on uncertainty symmetry is utilized to identify the optimal client for training the global mode. …”
Get full text