A5005214237- Handwritten Text Recognition Techniques
- Natural Language Processing Techniques
- Topic Modeling
- EEG and Brain-Computer Interfaces
- Vehicle License Plate Recognition
- Parkinson's Disease Mechanisms and Treatments
- Metaheuristic Optimization Algorithms Research
- Fuzzy Logic and Control Systems
- Neural dynamics and brain function
- Data Stream Mining Techniques
- Blind Source Separation Techniques
- Advanced Computational Techniques in Science and Engineering
- Text and Document Classification Technologies
- Neurological disorders and treatments
- Network Security and Intrusion Detection
- Machine Learning and Data Classification
- Statistical and Computational Modeling
- Neurological Disorders and Treatments
- Computational Drug Discovery Methods
- Advanced Scientific Research Methods
- Healthcare Systems and Public Health
- Evolutionary Algorithms and Applications
- Neural Networks and Applications
- Emotion and Mood Recognition
- Neuroscience and Neural Engineering
Tomsk Scientific Research Institute of Balneology and Physiotherapy
2023
Tomsk State University of Control Systems and Radio-Electronics
2021-2023
This article presents SVC-onGoing1, an on-going competition for on-line signature verification where researchers can easily benchmark their systems against the state of art in open common platform using large-scale public databases, such as DeepSignDB2 and SVC2021_EvalDB3, standard experimental protocols. SVC-onGoing is based on ICDAR 2021 Competition On-Line Signature Verification (SVC 2021), which has been extended to allow participants anytime. The goal evaluate limits popular scenarios...
Finding low-cost and insightful methods to reinforce the diagnosis of Parkinson's disease is a major challenge today, using dynamic handwritten data may be one solutions. Artificial intelligence machine learning can used create predictive models for diagnosis. In case models, in addition maximising their accuracy, it important ensure that prediction explain results. The fuzzy classifiers set IF-THEN statements with terms often natural discourse suit this purpose. This study proposes...
A promising approach to overcome the various shortcomings of password systems is use biometric authentication, in particular electroencephalogram (EEG) data. In this paper, we propose a subject-independent learning method for EEG-based biometrics using Hilbert spectrograms The proposed neural network architecture treats spectrogram as collection one-dimensional series and applies dilated convolutions over them, multi-similarity loss was used function learning. tested on publicly available...
Coronavirus infection causes long-term post-Covid syndrome, which determines the need for medical rehabilitation. The use of modern machine learning technologies to predict effectiveness rehabilitation can personalize process providing assistance. Aim: To create a method constructing model patients who have suffered COVID-19. Material and Methods. study included 64 admitted inpatient after average age was 56.92±9.29 years. obtain information about patients' health status, physical...
In this paper we propose modifications of the well-known algorithm particle swarm optimization (PSO). These changes affect mapping motion particles from continuous space to binary for searching in it, which is widely used solve problem feature selection. The modified PSO variations were tested on dataset SVC2004 dedicated user authentication based dynamic features a handwritten signature. example k-nearest neighbours (kNN), experiments carried out find optimal subset features. search was...
Abstract The paper presents the results of a study in application electroencephalography (EEG) for user authentication using discrete wavelet transform. Leipzig Study Mind-Body-Emotion Interactions dataset (LEMON) was used. Mean value, standard deviation, and root mean square value are used as features. Feature selection methods based on correlation, mutual information, χ2 criterion reduce feature space. SVM model is classification. efficiency constructed classifier has been tested...
Biometric systems have numerous advantages over traditional authentication methods and should be taken into account: uniqueness, fraud-resistance, portability, convenience of use, scalability, possibility reliable attendance recording. Use electroencephalography (EEG) data as biometric factor can keep all these benefits add new ones. This paper provides insight how EEG based biometrics identification ability affected by the number participants, their gender age. In order to study...
Abstract In this paper, clustering-based rule generation methods for fuzzy classifier using non-parametric Autonomous Data Partitioning algorithm have been proposed. ADP-algorithm is used to determine the number of clusters use in various k-means-like clustering algorithms. Proposed method contributes solving problem determining optimal clusters/rules. The efficiency classifiers with rules constructed by specified algorithms has tested on data sets from KEEL repository. Experimental results...
Диагностика болезни Паркинсона является дорогостоящей процедурой, включающей в себя транскраниальную сонографию и томографию головного мозга. В связи с этим актуальными являются простые точные скрининговые методы диагностики. Рассматриваются вопросы анализа рукописных статичных рисунков спиралей меандров методами машинного обучения для диагностики на основе общедоступного набора данных HandPD. Построены нечёткие классификаторы помощью оригинальных методов, способные по рисунку определять...
This article presents SVC-onGoing, an on-going competition for on-line signature verification where researchers can easily benchmark their systems against the state of art in open common platform using large-scale public databases, such as DeepSignDB and SVC2021_EvalDB, standard experimental protocols. SVC-onGoing is based on ICDAR 2021 Competition On-Line Signature Verification (SVC 2021), which has been extended to allow participants anytime. The goal evaluate limits popular scenarios...
This paper describes the experimental framework and results of ICDAR 2021 Competition on On-Line Signature Verification (SVC 2021). The goal SVC is to evaluate limits on-line signature verification systems popular scenarios (office/mobile) writing inputs (stylus/finger) through large-scale public databases. Three different tasks are considered in competition, simulating realistic as both random skilled forgeries simultaneously each task. obtained prove high potential deep learning methods....