TFNet: point cloud Semantic Segmentation Network based on Triple feature extraction by Yong Li, Falin Chen, Qi Lin, Zhen Li, Dongxu Gao, Jingchao Yang

“…To address these challenges, we propose TFNet, an end-to-end deep neural network specifically designed to enhance local geometric feature extraction and improve performance on density variations. …”
Get full text

Partial feature reparameterization and shallow-level interaction for remote sensing object detection by Minh Tai Pham Nguyen, Quoc Duy Nam Nguyen, Hoang Viet Anh Le, Minh Khue Phan Tran, Tadashi Nakano, Thi Hong Tran

“…As a result, our proposed detector obtains a competitive performance that outperforms most of the other large-size models and SOTA works. …”
Get full text

Transformer-based multi-task learning for table tennis motion feature recognition by Tianfang Ma

“…This model adopts a grouped attention structure to enhance the extraction ability of local features, and adds the spatial information embedding and temporal information embedding modules to enhance the extraction of spatial and temporal features by the original Transformer model. …”
Get full text

MOBCSA: Multi-Objective Binary Cuckoo Search Algorithm for Features Selection in Bioinformatics by Hudhaifa Mohammed Abdulwahab, S. Ajitha, Mufeed Ahmed Naji Saif, Belal Abdullah Hezam Murshed, Fahd A. Ghanem

“…Therefore, an effective feature selection (FS) technique is crucial to mitigate dimensionality, thereby enhancing the performance and accuracy of medical diagnosis. …”
Get full text

Features of B cell subsets in primary Sjogren’s syndrome and systemic lupus erythematosus by S. S. Benevolenskaya, I. V. Kudriavtsev, M. K. Serebriakova, I. N. Grigor’yeva, E. S. Kuvardin, A. I. Budkova, S. V. Koniakhin, D. B. Zammoeva, D. B. Motorin, A. Yu. Zaritskey, I. Z. Gaydukova, E. K. Gaydukova, S. V. Lapin, A. L. Maslyanskiy

“…During ROC analysis, performed for the differential diagnosis of healthy and sick patients, this discriminant model had a sensitivity of 70.6% and a specificity of 85.7%, the area under the curve (AUC) – 0.91 (p<0.001). …”
Get full text

Features of the cytogram and cytokine profile of bronchoalveolar lavage fluid in experimental metabolic syndrome by O. V. Voronkova, J. G. Birulina, V. V. Ivanov, E. E. Buyko, I. E. Esimova, A. V. Grigorieva, I. A. Osikhov, N. A. Chernyshov, E. A. Motlokhova

“…The aim of the study was to identify the features of the cellular composition and cytokine profile of bronchoalveolar lavage fluid in rats in a model of diet-induced metabolic syndrome.Materials and methods. …”
Get full text

Machine Learning Approaches for Fault Detection in Internal Combustion Engines: A Review and Experimental Investigation by A. Srinivaas, N. R. Sakthivel, Binoy B. Nair

“…Additionally, this study incorporates advanced deep learning techniques, including a deep neural network (DNN), a one-dimensional convolutional neural network (1D-CNN), Transformer and a hybrid Transformer and DNN model which demonstrate superior performance in fault detection compared to traditional machine learning methods.…”
Get full text

Cell-phone origin identification based on spectral features of device self-noise by Anshan PEI, Rangding WANG, Diqun YAN

“…With the widespread availability of cell-phone recording devices and the availability of various powerful and easy-to-use digital media editing software,source cell-phone identification has become a hot topic in multimedia forensics.A novel cell-phone identification method was proposed based on the recorded speech.Firstly,device self-noise (DSN) was considered as the fingerprint of the cell-phone and estimated from the silent segments of the speech.Then,the mean of the noise's spectrum was extracted as the identification.Principal components analysis (PCA) was applied to reduce the feature dimension.Support vector machine (SVM) was adopted as the classifier to determine the source of the detecting speech.Twenty-four popular models of the cell-phones were evaluated in the experiment.The experimental results show that the average identification accuracy and recall of the method can reach up to 99.24% and demonstrate that the self-noise feature has more superior performance than the MFCC feature.…”
Get full text

Enhanced multi-object tracking via appearance feature gating using UMAP by Ken Arioka, Yuichi Sawada

“…Unlike other methods that require pre-trained appearance feature models, our approach supports online comparison without the need for pre-trained. …”
Get full text

The unique hypertrophic and fibrotic features of neonatal right ventricle in response to pressure overload by Yingying Xiao, Yiting Xue, Debao Li, Lincai Ye, Zheng Wang, Sixie Zheng, Peisen Ruan, Hao Chen, Haifa Hong

“…Abstract Pediatric heart failure (HF) research remains in its infancy partly due to the lack of neonatal rat/mouse models of HF. The aim of the study is to introduce a neonatal rat/mouse model of right ventricular (RV) pressure overload (RVPO), a significant cause of pediatric HF, and to uncover the molecular features of RVPO-induced RV hypertrophy and fibrosis—the two most important transitional pathological states between normal and dysfunctional RV. …”
Get full text

Multi-Sensor Heterogeneous Signal Fusion Transformer for Tool Wear Prediction by Ju Zhou, Xinyu Liu, Qianghua Liao, Tao Wang, Lin Wang, Pin Yang

“…In this paper, we propose a Multi-Sensor Multi-Domain feature fusion Transformer (MSMDT) model that achieves precise tool wear prediction through innovative feature engineering and cross-modal self-attention mechanisms. …”
Get full text

Characteristics of gut and lung microbiota in patients with lung masses and their relationship with clinical features by Yanping Yang, Jiacheng Shen, Sulan Wei, Maosong Ye, Xing Zhao, Jian Zhou, Lin Tong, Jie Hu, Yuanlin Song, Shengdi Wu, Nuo Xu

“…We explored the distinct composition of the gut and lung microbiota and their associations with clinical features. The diagnostic models were constructed using microbial features identified through two approaches: random forest algorithm with five-fold cross-validation and comparative analysis of significantly differential taxa. …”
Get full text

Multi-task feature integration and interactive active learning for scene image resizing by Ludan Shi, Xianhua Yan, Sen Wang

“…By employing LIAL, we methodically represent a GSP for every scene and calculate its corresponding deep features by a multi-layer aggregating algorithm. The deeply-learned GSP representations are subsequently encoded to a Gaussian mixture model (GMM), serving as the basis for scenic image retargeting. …”
Get full text

Image Processing Using Feature-Based Segmentation Techniques for the Analysis of Medical Images by Christodoss Prasanna Ranjith, Krishnamoorthy Natarajan, Sindhu Madhuri, Mahesh Thylore Ramakrishna, Chandrasekhar Rohith Bhat, Vinoth Kumar Venkatesan

“…Unlike classic K-means, which requires you to choose the number of clusters before executing the algorithm, adaptive K-means identifies the best number of clusters based on the features of the data. The proposed model works as follows. …”
Get full text

Multi-Dimensional Feature Fusion and Enhanced Attention Streaming Movie Prediction Algorithm by Hanqing Hu, Tianmu Tian, Chengjing Liu, Xueyuan Bai

“…Second, an attention mechanism was applied to dynamically assign importance to different time steps and features, enabling the model to focus on the most critical information based on time periods and movie types. …”
Get full text

Multiscale Feature Filtering Network for Image Recognition System in Unmanned Aerial Vehicle by Xianghua Ma, Zhenkun Yang, Shining Chen

“…Experimental results on CIFAR100 and Tiny ImageNet datasets reflect that the MFFNet achieves very competitive results in comparison with previous baseline models. Further ablation experiments verify that the MFFNet can achieve consistent performance gains in image classification and object detection tasks.…”
Get full text

Machine Learning-Based Diabetes Risk Prediction Using Associated Behavioral Features by Ayodeji O. J. Ibitoye, Joseph D. Akinyemi, Olufade F. W. Onifade

“…The models’ performances were evaluated using accuracy, precision, recall and F1-score and NN presented the best performance overall achieving an F1-score of 85% for the correlated feature pairs (CF) and 75% for the direct feature pairs. …”
Get full text

Speech Databases, Speech Features, and Classifiers in Speech Emotion Recognition: A Review by G. H. Mohmad Dar, Radhakrishnan Delhibabu

“…This review seeks to provide an in-depth examination of current methodologies in speech emotion recognition (SER), with a focus on databases, feature extraction techniques, and classification models. …”
Get full text

CIA-UNet: An Attention-Enhanced Multi-Scale U-Net for Single Tree Crown Segmentation by Jiapeng Duan, Chuanzhao Tian, Wansi Liu, Lixiang Cao, Teng Feng, Xiaomin Tian

“…Additionally, the Attention Gate module is utilized to improve the model’s sensitivity to foreground pixels, adjust the weighting of skip connection features and prevent segmentation errors due to semantic mismatches. …”
Get full text

Tire Pressure Monitoring System Using Feature Fusion and Family of Lazy Classifiers by Arpit Pandey, Sridharan Naveen Venkatesh, Prabhakaranpillai Sreelatha Anoop, B. R. Manju, Vaithiyanathan Sugumaran

“…By integrating these features, the study aims to optimize predictive modeling of TPMS. …”
Get full text