Objects features extraction by singular projections of data tensor to matrices
Article Sidebar
Open full text
Published:
Sep 30, 2025
Issue Vol. 15 No. 3 (2025)
Articles
-
Objects features extraction by singular projections of data tensor to matrices
5-9
-
A hybrid approach combining generalized normal distribution optimization algorithm and fuzzy C-means with Calinski-Harabasz index for clustering optimization
10-14
-
Method of hybrid logical classification trees based on group selection of discrete features
15-21
-
Optimal control of electric energy quality, based on lexicographic approach
22-28
-
Implementation of energy-saving modes for electro-radiation drying of oil-containing material using automation tools
29-32
-
Methods and means of laser layer Jones matrix mapping of polycrystalline films of biological fluids
33-37
-
Alzheimer’s disease classification from MRI using vision transformer
38-44
-
Enhancing early Parkinson’s disease diagnosis through handwriting analysis
45-49
-
Biomechanical foundations and benefits of active orthoses in the treatment of idiopathic scoliosis
50-54
-
Application of facial recognition technologies for enhancing control in information security systems
55-58
-
IoT system with frequency converters of physical quantities on FPGA
59-66
-
Research on the possibility of reducing the error in measuring the phase shift of radio signals
67-72
-
Implementation of fiber-optic sensing systems in structural health monitoring of concrete
73-76
-
Modelling the working cycle of a heat pump scroll compressor
77-80
-
Modeling of interception parking lots
81-86
-
Development and research of W-parameters of potentially unstable four-poles based on the mathematical model of W-parameters of field-effect transistors in the high-frequency range
87-90
-
Detection confidential information by large language models
91-99
-
Ethical simulation of a phishing attack
100-104
-
The effectiveness of machine learning in detecting phishing websites
105-109
-
Contemporary approaches to integrating AI agents into library information processes
110-116
-
Development of a reinforcement learning-based adaptive scheduling algorithm for commercial smart kitchens
117-122
-
Optimizing deep learning techniques with stacking BiLSTM and BiGRU models for gold price prediction
123-130
-
Websites with virtual church tours in Poland – usability and accessibility analysis
131-137
-
Study of feed granulation process based on system analysis – justification of optimization criteria
138-142
Main Article Content
DOI
Authors
Abstract
The problem of multidimensional tensor objects features extraction in a manner of matrices is considered. The tensor’ elements Higher Order Singular Value Decomposition (SVD) is presented as the d-SVD which includes SVD of the tensor reshaped as a matrix and SVDs of reduced size of the previous SVDs vectors reshaped as matrices. The decomposition allows to create Singular Projections of tensor to a sum of one-rank tensors in selected dimensions. The projections of tensor to matrices by weighted and direct averaging in SVD’ vectors subspace is investigated numerically. The extracted by projection features of a series of image objects are used to develop the optimized Inverse Feature Filters for the objects recognition.
Keywords:
high order singular value decomposition, singular projection, objects recognition, optimized inverse features filters
Article Details
Bunyak, Y., Kvуetnyy R., Sofina, O., & Kotsiubynskyi, V. (2025). Objects features extraction by singular projections of data tensor to matrices. Informatyka, Automatyka, Pomiary W Gospodarce I Ochronie Środowiska, 15(3), 5–9. https://doi.org/10.35784/iapgos.6912
