Results 61 to 70 of about 427,913 (167)

Supervised Learning via Unsupervised Sparse Autoencoder

IEEE Access, 2018
Dimensionality reduction is commonly used to preprocess high-dimensional data, which is an essential step in machine learning and data mining. An outstanding low-dimensional feature can improve the efficiency of subsequent learning tasks.
Jianran Liu, Chan Li, Wenyuan Yang
doaj   +1 more source

Spectral Graph-based Features for Recognition of Handwritten Characters: A Case Study on Handwritten Devanagari Numerals

Journal of Intelligent Systems, 2018
Interpretation of different writing styles, unconstrained cursiveness and relationship between different primitive parts is an essential and challenging task for recognition of handwritten characters.
Bhat Mohammad Idrees, Sharada B.
doaj   +1 more source

Automatic J–A Model Parameter Tuning Algorithm for High Accuracy Inrush Current Simulation

Energies, 2017
Inrush current simulation plays an important role in many tasks of the power system, such as power transformer protection. However, the accuracy of the inrush current simulation can hardly be ensured.
Xishan Wen, Jingzhuo Zhang, Hailiang Lu
doaj   +1 more source

Filtered local pattern descriptor for face recognition and infrared pedestrian detection

The Journal of Engineering, 2017
In recent decades, the local pattern descriptor has achieved tremendous success in the field of face recognition, pedestrian detection, and image texture analysis. This study presents a generic approach, called the filtered local pattern descriptor (FLPD)
Ning Sun, Hengchao Yan, Hengchao Yan, Jixin Liu, Guang Han   +4 more
doaj   +1 more source

Feature Incay for Representation Regularization

, 2017
Softmax loss is widely used in deep neural networks for multi-class classification, where each class is represented by a weight vector, a sample is represented as a feature vector, and the feature vector has the largest projection on the weight vector of the correct category when the model correctly classifies a sample. To ensure generalization, weight
Yuan, Yuhui, Yang, Kuiyuan, Zhang, Chao
openaire   +2 more sources

DeepCCDS: Interpretable Deep Learning Framework for Predicting Cancer Cell Drug Sensitivity through Characterizing Cancer Driver Signals

Advanced Science
Accurate characterization of cellular states is the foundation for precise prediction of drug sensitivity in cancer cell lines, which in turn is fundamental to realizing precision oncology.
Jiashuo Wu, Jiyin Lai, Xilong Zhao, Ziyi Wang, Yongbao Zhang, Liqiang Wang, Yinchun Su, Yalan He, Siyuan Li, Ying Jiang, Junwei Han   +10 more
doaj   +1 more source

A Robust Tie-Points Matching Method with Regional Feature Representation for Synthetic Aperture Radar Images

Remote Sensing
The precise tie-points (TPs) on synthetic aperture radar (SAR) images are a critical cornerstone in the global digital elevation model (DEM) and digital ortho map (DOM) production process. While there are abundant studies on SAR TPs matching, improvement
Yifan Zhang, Yan Zhu, Liqun Liu, Xun Du, Kun Han, Junhui Wu, Zhiqiang Li, Lingshuai Kong, Qiwei Lin   +8 more
doaj   +1 more source

Feature Representation for ICU Mortality

, 2015
Good predictors of ICU Mortality have the potential to identify high-risk patients earlier, improve ICU resource allocation, or create more accurate population-level risk models. Machine learning practitioners typically make choices about how to represent features in a particular model, but these choices are seldom evaluated quantitatively.
openaire   +2 more sources

Histopathological Image Deep Feature Representation for CBIR in Smart PACS. [PDF]

J Digit Imaging, 2023
Tommasino C, Merolla F, Russo C, Staibano S, Rinaldi AM.   +4 more
europepmc   +1 more source

Adaptive law-based feature representation for time series classification. [PDF]

Sci Rep
Kurbucz MT, Hajós B, Halmos BP, Molnár VÁ, Jakovác A.   +4 more
europepmc   +1 more source