• Improved Peak Detection Algorithm for Photoplethysmographic Signals
• Algorithm for peak detection in the Skin Conductance Response component of the EDA signals
• Heart Rate Variability calculation methods
• CLAS: A Database for Cognitive Load, Affect and Stress Recognition
• Adaptive Feature Selection through Fisher Discriminant Ratio
• Front-end Processing of Physiological Signals for the Automated Detection of High-arousal Negative Valence Condition
• Automated stress level monitoring in mobile setup
• Overall design of the SLADE data acquisition system
• Technological support to stress-level monitoring
• Constrained attribute selection for stress detection based on physiological signals
• Automated Recognition of Affect and Stress evoked by Audio-Visual stimuli
• Three-step Attribute Selection for Stress Detection based on Physiological Signals
• Detection of Negative Emotions and High-Arousal Negative-Valence States on the Move
• High accuracy design and realization of fixed and variable allpass-based fractional delay digital filters
• Design and realization of efficient IIR digital filter structures based on sensitivity minimizations
• An algorithm for the design of multiplierless IIR filters as a parallel connection of two all-pass filters
• Cascaded multiplierless realizations of low sensitivities allpass based fractional delay filters
  
  

The second edition of International Conference on Biomedical Innovations and Applications - BIA-2021 (to be held September 16 - 19, 2021, Varna, Bulgaria) aims to bring together researchers and professionals active in the fields of Biomedical Engineering and Information and Communications Technology and will offer new opportunities to foster the exchange ideas and international collaborations.

Accepted papers will be submitted for inclusion into IEEE Xplore. All conference papers included in IEEE Xplore will be indexed in the SCOPUS database.

International Conference on Biomedical Innovations and Applications - BIA-2019.

Varna is the third-largest city in Bulgaria and the largest city and seaside resort on the Bulgarian Black Sea Coast. Situated strategically in the Gulf of Varna, the city has been a major economic, social and cultural centre for almost three millennia. Varna, historically known as Odessos, grew from a Thracian seaside settlement to a major seaport on the Black Sea.

The city is referred to as the maritime capital of Bulgaria and headquarters the Bulgarian Navy and merchant marine. In 2008, Varna was designated seat of the Black Sea Euroregion by the Council of Europe. In 2014, Varna was awarded the title of European Youth Capital 2017.

Visit the official tourist website of Varna.

Public Transport in Varna.

The CLAS (Cognitive Load, Affect and Stress) dataset was conceived as a freely accessible repository which is purposely developed to support research on the automated assessment of certain states of mind and the emotional condition of a person. This resource is intended to support RTD activities aiming at the development of intelligent human computer interaction (HCI) interfaces that incorporate functionalities allowing for the automated recognition of human emotions, the automated detection of stress conditions, the automated assessment of the degree of concentration, cognitive load, and momentary cognitive capacity, and can account for some personality traits related to the ability to quickly solve logical and mathematical problems under strict time constraints. These and other related functionalities open additional opportunities in support of the advancement of research on (i) intelligent human-machine interfaces in entertainment, e-Health, e-Learning, e-Government and other applications; (ii) improving the efficiency of human-robot collaboration systems; (iii) risk assessment and management systems in robotics and in high-risk professions (rescue crews, military, miners etc.); and (iv) a wide range of personal applications aiming at the enhancement of health-related quality of life and wellbeing.

The CLAS dataset is a resource of labeled physiological recordings, which contain synchronized ECG, PPG,  EDA and acclerometer signals captured while the test subjects are involved in some purposely designed interactive or perceptive task. Specifically, the interactive tasks are designed to evaluate different aspects of the momentary cognitive load, the degree of attention and concentration, or the cognitive capacity of a person. Specifically, in the interactive tasks the test subject is presented with a set of purposely designed mathematical and logical problems with the strict requirement for prompt response within a short time window.In the perceptive tasks, the test subjects are exposed to a series of carefully selected stimuli which aim to elicit emotions. In the perceptive tasks the test subjects typically receive instructions to simply watch the images or to follow the video clips. More details here.

Although the particular focus of our research is on the states of mind associated with negative emotions, mental strain and high cognitive effort, the CLAS dataset could offer an adequate support to research of a wider scope, such as general studies on attention assessment, cognitive load assessment, emotion recognition, as well as stress detection.

When using the CLAS dataset, please cite: 

Markova, V., Ganchev, T., Kalinkov, K. (2019). CLAS: A Database for Cognitive Load, Affect and Stress Recognition, in Proceedings of the International Conference on Biomedical Innovations and Applications, (BIA-2019), art. no. 8967457,  DOI: 10.1109/BIA48344.2019.8967457. Available on-line: https://ieeexplore.ieee.org/document/8967457

You can freely access a sample (PPG, ECG, EDA, Accelerometer) from here.

For receiving access to the whole CLAS dataset, please follow the procedure bellow:

1. To receive the password for the dataset, please sign the EULA , scan it and send it back via this form or via email available at the Contact page, if the form is not accessible at the time of signing.
2. We will send you the password within three working days
3. Download the CLAS Dataset¹ (password protected).

_{1Compressed size - 2.03 GB, Uncompressed size - 13.9 GB,  we recommend using 7-zip for extraction.}