Non-Exemplar Incremental ISAR Target Classification via Mix-Mamba Feature Adjustment Network by Ruihang Xue, Caipin Li, Wencan Peng, Xueru Bai, Feng Zhou

“…Then, the feature adjustment network facilitates knowledge transfer between base and incremental classes by dynamically maintaining a prototype for each target class. …”
Get full text

Weighted K-NN Classification Method of Bearings Fault Diagnosis With Multi-Dimensional Sensitive Features by Qingfeng Wang, Shuai Wang, Bingkun Wei, Wenwu Chen, Yufei Zhang

“…In this paper, we propose a weighted k-nearest neighbor (WKNN) fault diagnosis model based on multi-dimensional sensitive features, and propose a fault diagnosis method for rolling bearings that adapts to different equipment and different operating conditions. …”
Get full text

Manual Acupuncture Manipulation Recognition Method via Interactive Fusion of Spatial Multiscale Motion Features by Jiyu He, Chong Su, Jie Chen, Jinniu Li, Jingwen Yang, Cunzhi Liu

“…First, this paper presents an optical flow-based hand motion contour global feature extraction method for acupuncture hand shape. …”
Get full text

Visualizing Relaxation in Wearables: Multi-Domain Feature Fusion of HRV Using Fuzzy Recurrence Plots by Puneet Arya, Mandeep Singh, Mandeep Singh

“…HRV data were collected from 60 participants during spontaneous and slow-paced breathing sessions. Features were extracted from five domains: time, frequency, non-linear, geometric, and image-based. …”
Get full text

Lateralised memory networks may explain the use of higher-order visual features in navigating insects. by Giulio Filippi, James Knight, Andrew Philippides, Paul Graham

“…Whilst we understand the basic visual pathway to the memory centres (Optic Lobes to Mushroom Bodies) involved in the storage of visual information, it is still largely unknown what type of representation of visual scenes underpins view-based navigation in ants. Several experimental studies have suggested ants use "higher-order" visual information - that is features extracted across the whole extent of a visual scene - which raises the question as to how these features might be computed. …”
Get full text

Automated data processing and feature engineering for deep learning and big data applications: A survey by Alhassan Mumuni, Fuseini Mumuni

“…Today, end-to-end automated data processing systems based on automated machine learning (AutoML) techniques are capable of taking raw data and transforming them into useful features for big data tasks by automating all intermediate processing stages. …”
Get full text

An Improved YOLOP Lane-Line Detection Utilizing Feature Shift Aggregation for Intelligent Agricultural Machinery by Cundeng Wang, Xiyuan Chen, Zhiyuan Jiao, Shuang Song, Zhen Ma

“…For lane-line detection tasks, we also propose an improved YOLOP lane-line detection algorithm based on feature shift aggregation. Homemade datasets were used for training and testing. …”
Get full text

SFG-Net: A Scattering Feature Guidance Network for Oriented Aircraft Detection in SAR Images by Qingyang Ke, Youming Wu, Wenchao Zhao, Qingbiao Meng, Tian Miao, Xin Gao

“…Additionally, a feature scattering center-based label assignment (FLA) strategy is introduced, which utilizes the spatial distribution of scattering information to adaptively adjust the sample coverage and ensure that strong scattering regions are prioritized during training. …”
Get full text

Machine-Learning Classification of Port Wine Stain With Quantitative Features of Optical Coherence Tomography Image by Shengnan Ai, Chengming Wang, Wenxin Zhang, Wenchao Liao, Juicheng Hsieh, Zhenyu Chen, Bin He, Xiao Zhang, Ning Zhang, Ying Gu, Ping Xue

“…We use both full feature set and simplified feature set for training. …”
Get full text

Semi-Supervised Underwater Image Enhancement Method Using Multimodal Features and Dynamic Quality Repository by Mu Ding, Gen Li, Yu Hu, Hangfei Liu, Qingsong Hu, Xiaohua Huang

“…In this study, we proposed a semi-supervised underwater image enhancement method, MCR-UIE, which utilized multimodal contrastive learning and a dynamic quality reliability repository to leverage the unlabeled data during training. This approach used multimodal feature contrast regularization to prevent the overfitting of incorrect labels, and secondly, introduced a dynamic quality reliability repository to update the output as pseudo ground truth. …”
Get full text

Reconstructing missing data of damaged buildings from post-hurricane reconnaissance data using XGBoost by Hyunje Yang, Jun-Whan Lee, Steven Klepac, Armando Ulises Santos Cruz, Arthriya Subgranon, Junfeng Jiao

“…XGBoost models were trained based on the reconnaissance datasets collected from four regions affected by Hurricanes. …”
Get full text

Improving speaker-independent visual language identification using deep neural networks with training batch augmentation by Jacob L. Newman

“…The main challenge associated with VLID is the speaker-dependency of image based visual recognition features, which bear little meaningful correspondence between speakers.In this work, we examine a novel VLID task using video of 53 individuals reciting the Universal Declaration of Human Rights in their native languages of Arabic, English or Mandarin. …”
Get full text

Effectiveness of zoom-based online sessions in developing research skills among geographically distant participants: a cross-sectional study by Masood Jawaid, Zainab Aqeel Khan, Zubia Masood, Rehan Ahmed Khan

Get full text

Teaching Machines on Snoring: A Benchmark on Computer Audition for Snore Sound Excitation Localisation by Kun QIAN, Christoph JANOTT, Zixing ZHANG, Jun DENG, Alice BAIRD, Clemens HEISER, Winfried HOHENHORST, Michael HERZOG, Werner HEMMERT, Björn SCHULLER

“…Experimental results demonstrate that, wavelet packet transform energy can outperform most other features. A deep neural network trained with subband energy ratios reaches the highest performance achieving an unweighted average recall of 72.8% from four types for snoring.…”
Get full text

Distilling knowledge from graph neural networks trained on cell graphs to non-neural student models by Vasundhara Acharya, Bülent Yener, Gillian Beamer

“…We also examined the differences in feature importance between student models trained with the teacher’s logits and their counterparts trained on hard labels. …”
Get full text

Swift prediction of personalized head and chest organ doses from CT examinations via neural networks with optimized quantity of hidden layers and radiomics features by Wencheng Shao, Xin Lin, Ying Huang, Liangyong Qu, Weihai Zhuo, Haikuan Liu

“…Objective: To utilize radiomics features to enhance the prediction of personalized organ doses from CT scans, in order to explore methods for improving neural network-based models. …”
Get full text

Detection of insect-damaged sunflower seeds using near-infrared hyperspectral imaging and machine learning by Bright Mensah, Jarrad Prasifka, Brent Hulke, Ewumbua Monono, Xin Sun

“…Machine learning techniques, specifically multilayer perceptron (MLP), support vector machine (SVM), random forest (RF), light gradient boosting machine (LGBM), extreme gradient boosting (XGB), gradient boosting (GB), and partial least squares discriminant analysis (PLS-DA), were trained and evaluated based on the spectral features. …”
Get full text

Fine-Grained Feature Extraction in Key Sentence Selection for Explainable Sentiment Classification Using BERT and CNN by Thennakoon Mudiyanselage Anupama Udayangani Gunathilaka, Jinglan Zhang, Yuefeng Li

“…First, the BERT pre-trained language model captures global features through a feature vector representation. …”
Get full text

THE EFFICIENCY IMPROVING OF PILOTS AND CADETS TRAINING TO SAFETY CONTROL USING THE MODIFICATIONS OF CLASSICAL METHOD OF "ROY" (PSO) by V. V. Yurasov, L. A. Yurasova

“…The article explains the use of modifications the classical method PSO to optimize the training pilots task on aircraft simulators. Model is based on the identification of the specific guarantee of safety in the task of training pilots of the features of simulation with the use of modern optimization models for long-term quantitative forecast of random processes. …”
Get full text

Classification of chest radiographs into healthy/pneumonia using Harris-Hawks Algorithm optimized deep-features by K. Vijayakumar, Mohammad Nazmul Hasan Maziz, Swaetha Ramadasan, Seifedine Kadry, S. Arunmozhi

“…Along with the traditional deep-features based classification using the SoftMax, this work also considered Harris-Hawks Algorithm (HHA) algorithm based features optimization and serial features integration to generate fused-features vector (FFV). …”
Get full text