A5053277804- Face and Expression Recognition
- Matrix Theory and Algorithms
- Gene expression and cancer classification
- Text and Document Classification Technologies
- Fuzzy Logic and Control Systems
- Multi-Criteria Decision Making
- Tensor decomposition and applications
- Machine Learning and ELM
- Model Reduction and Neural Networks
- Electromagnetic Scattering and Analysis
- Rough Sets and Fuzzy Logic
- Machine Learning and Data Classification
- Neural Networks and Applications
- Artificial Intelligence in Healthcare
- Domain Adaptation and Few-Shot Learning
- Data Mining Algorithms and Applications
- Bioinformatics and Genomic Networks
- Hydraulic flow and structures
- Numerical methods for differential equations
- Advanced Image and Video Retrieval Techniques
- Hydrology and Sediment Transport Processes
- Image Retrieval and Classification Techniques
- Evolutionary Algorithms and Applications
- Advanced Numerical Methods in Computational Mathematics
- Machine Learning in Bioinformatics
Graduate University of Advanced Technology
2016-2024
Institut für Biomedizinische Analytik und NMR Imaging (Germany)
2023
Gene expression data have become increasingly important in machine learning and computational biology over the past few years. In field of gene analysis, several matrix factorization-based dimensionality reduction methods been developed. However, such can still be improved terms efficiency reliability. this paper, an innovative approach to feature selection, called Dual Regularized Unsupervised Feature Selection Based on Matrix Factorization Minimum Redundancy (DR-FS-MFMR), is introduced....
Existence of debris structures inevitably ascends the rate scour process around bridge piers and flow area not only lead into remarkable deviation but also increase velocity piers. A myriad experimental field studies to understand effective parameters on depth with effects were conducted. To reach permissible values for practical uses, relationships extracted in previous investigations suffer from lack generalization data ranges. In this way, neuro-fuzzy group method handling (NF-GMDH)-based...
In this research, group method of data handling (GMDH) as a one the self-organized approaches is utilized to predict three-dimensional free span expansion rates around pipeline due waves. The GMDH network developed using gene-expression programming (GEP) algorithm. way, GEP was performed in each neuron instead polynomial quadratic neuron. Effective parameters on scour include sediment size, geometry, and wave characteristics upstream pipeline. Four-dimensionless are considered input...
Community detection has become an important research topic in machine learning due to the proliferation of network data. However, most existing methods have been developed based on only exploiting topology structures network, which can result missing advantage using nodes' attribute information. As a result, it is expected that much valuable information could be used improve quality discovered communities will ignored. To solve this limitation, we propose novel Augment Graph Regularization...
Subspace distance is an invaluable tool exploited in a wide range of feature selection methods. The power subspace that it can identify representative subspace, including group features efficiently approximate the space original features. On other hand, employing intrinsic statistical information data play significant role process. Nevertheless, most existing methods founded on are limited properly fulfilling this objective. To pursue void, we propose framework takes into account which...
Summary This paper deals with studying some of well‐known iterative methods in their tensor forms to solve a Sylvester equation. More precisely, the form Arnoldi process and full orthogonalization method are derived by using product between two tensors. Then conjugate gradient nested algorithms also presented. Rough estimation required number operations for is obtained, which reveals advantage handling based on format over classical general. Some numerical experiments examined, confirm...
The extraction of predictive features from the complex high-dimensional multi-omic data is necessary for decoding and overcoming therapeutic responses in systems pharmacology. Developing computational methods to reduce space vitro, vivo clinical essential discover evolution mechanisms drug resistance. In this paper, we have utilized matrix factorization (MF) as a modality high dimensionality reduction respect, proposed three novel feature selection using mathematical conception basis...
Spectral clustering is a powerful technique for high-dimensional data, utilizing graph-based representations to detect complex, non-linear structures and non-convex clusters. The construction of similarity graph essential ensuring accurate effective clustering, making structure learning (GSL) central enhancing spectral performance in response the growing demand scalable solutions. Despite advancements GSL, there lack comprehensive surveys specifically addressing its role within clustering....
Abstract One of the most critical challenges in managing complex diseases like COVID-19 is to establish an intelligent triage system that can optimize clinical decision-making at time a global pandemic. The presentation and patients’ characteristics are usually utilized identify those patients who need more care. However, evidence shows unmet determine accurate optimal biomarkers under condition crisis. Here we have presented machine learning approach find group indicators from blood tests...
Recently many neural network methods have been proposed for multi-label classification in the literature. One of these recent researches is multi-layer extreme learning machines (ML-ELM) which stack auto encoders used tuning weights. However, ML-ELM suffers from three primary drawbacks: First, input weights and biases are chosen randomly. Second, pseudo-inverse solution calculating output will cause to increase reconstruction error. Third, memory execution time transformation matrices...