Dmitry Georzhevich Korzun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Dmitry Georzhevich Korzun has a total of 104 co-authors. Here are the top co-authors by number of shared publications:
- Andrei Gurtov
Department of Computer and Information Science, Linkping University, Linkping, Sweden
16 shared publications - Sergey Balandin
FRUCT Oy
12 shared publications - Alexander Yurievitch Meigal
Petrozavodsk State University (PetrSU), Petrozavodsk, Russia
11 shared publications - Alexander Borodin
Petrozavodsk State University (PetrSU), Petrozavodsk, Russia
7 shared publications - Alexey Kashevnik
ITMO University
7 shared publications Ivan V. Galov
Petrozavodsk State University (PetrSU), Petrozavodsk, Russia
7 shared publications
Latest Publications
- 13 March 2025
- Published by Taylor & Francis in Biological Rhythm Research
- Vol. 56 (7) , 465-472
The potential of using actimetry to identify objective markers of depression
- 13 March 2025
- Published by Taylor & Francis in Biological Rhythm Research
- Vol. 56 (7) , 465-472
The potential of using actimetry to identify objective markers of depression
- Open Access
Entropy-Based Machine Learning Model for Fast Diagnosis and Monitoring of Parkinson’s Disease
This study presents the concept of a computationally efficient machine learning (ML) model for diagnosing and monitoring Parkinson’s disease (PD) using rest-state EEG signals (rs-EEG) from 20 PD subjects and 20 normal control (NC) subjects at a sampling rate of 128 Hz. Based on the comparative analysis of the effectiveness of entropy calculation methods, fuzzy entropy showed the best results in diagnosing and monitoring PD using rs-EEG, with classification accuracy (ARKF) of ~99.9%. The most important frequency range of rs-EEG for PD-based diagnostics lies in the range of 0–4 Hz, and the most informative signals were mainly received from the right hemisphere of the head. It was also found that ARKF significantly decreased as the length of rs-EEG segments decreased from 1000 to 150 samples. Using a procedure for selecting the most informative features, it was possible to reduce the computational costs of classification by 11 times, while maintaining an ARKF ~99.9%. The proposed method can be used in the healthcare internet of things (H-IoT), where low-performance edge devices can implement ML sensors to enhance human resilience to PD.
Open AccessEntropy-Based Machine Learning Model for Fast Diagnosis and Monitoring of Parkinson’s Disease
This study presents the concept of a computationally efficient machine learning (ML) model for diagnosing and monitoring Parkinson’s disease (PD) using rest-state EEG signals (rs-EEG) from 20 PD subjects and 20 normal control (NC) subjects at a sampling rate of 128 Hz. Based on the comparative analysis of the effectiveness of entropy calculation methods, fuzzy entropy showed the best results in diagnosing and monitoring PD using rs-EEG, with classification accuracy (ARKF) of ~99.9%. The most important frequency range of rs-EEG for PD-based diagnostics lies in the range of 0–4 Hz, and the most informative signals were mainly received from the right hemisphere of the head. It was also found that ARKF significantly decreased as the length of rs-EEG segments decreased from 1000 to 150 samples. Using a procedure for selecting the most informative features, it was possible to reduce the computational costs of classification by 11 times, while maintaining an ARKF ~99.9%. The proposed method can be used in the healthcare internet of things (H-IoT), where low-performance edge devices can implement ML sensors to enhance human resilience to PD.
- 23 May 2023
- Published by New Technologies Publishing House in Programmnaya Ingeneria
- Vol. 14 (5)
Applying the Random Backoff Algorithm for Active Information Exchange Control in Smart Internet Environment Server
The information exchange-as a way of interaction for participants in an Internet environment-is a fundamental function of a distributed system within the computing paradigms of Internet of Things, Cyber-Physical Systems, Ambient Intelligence etc. Participants in an Internet environment are represented by software agents running typically on low-performance edge computing devices. Interaction is implemented through exchange of information collected by the participants in a shared information store that implements the «intelligence» of this environment. The organization of agents access to the shared information and of their interaction uses a semantic information broker that manages information flows between participants. With an increase in the number, diversity, and activity of participants, the workload on the broker and the data transmission network increases. In this paper, a novel method is proposed to reduce the workload by delegating part of the control of the information exchange to the participants themselves. The subscription mechanism is modified for information changes in a shared information store. Instead of the passive option, when the broker must notify all agents who have subscribed to the information being changed, the active option is used, when agents themselves can check for information changes. A new two-component control method based on the well-known backoff algorithm in combination with the well-known adaptive strategy for choosing the time of sending the next request from an agent to a broker for the presence of information changes is proposed. The control capabilities are studied experimentally using a simulated Internet environment.
- 23 May 2023
- Published by New Technologies Publishing House in Programmnaya Ingeneria
- Vol. 14 (5)
Applying the Random Backoff Algorithm for Active Information Exchange Control in Smart Internet Environment Server
The information exchange-as a way of interaction for participants in an Internet environment-is a fundamental function of a distributed system within the computing paradigms of Internet of Things, Cyber-Physical Systems, Ambient Intelligence etc. Participants in an Internet environment are represented by software agents running typically on low-performance edge computing devices. Interaction is implemented through exchange of information collected by the participants in a shared information store that implements the «intelligence» of this environment. The organization of agents access to the shared information and of their interaction uses a semantic information broker that manages information flows between participants. With an increase in the number, diversity, and activity of participants, the workload on the broker and the data transmission network increases. In this paper, a novel method is proposed to reduce the workload by delegating part of the control of the information exchange to the participants themselves. The subscription mechanism is modified for information changes in a shared information store. Instead of the passive option, when the broker must notify all agents who have subscribed to the information being changed, the active option is used, when agents themselves can check for information changes. A new two-component control method based on the well-known backoff algorithm in combination with the well-known adaptive strategy for choosing the time of sending the next request from an agent to a broker for the presence of information changes is proposed. The control capabilities are studied experimentally using a simulated Internet environment.
- Open Access
Artificial Neural Networks for IoT-Enabled Smart Applications: Recent Trends
In the age of neural networks and the Internet of Things (IoT), the search for new neural network architectures capable of operating on devices with limited computing power and small memory size is becoming an urgent agenda
Open AccessArtificial Neural Networks for IoT-Enabled Smart Applications: Recent Trends
In the age of neural networks and the Internet of Things (IoT), the search for new neural network architectures capable of operating on devices with limited computing power and small memory size is becoming an urgent agenda
- Open Access
Machine Learning Sensors for Diagnosis of COVID-19 Disease Using Routine Blood Values for Internet of Things Application
Healthcare digitalization requires effective applications of human sensors, when various parameters of the human body are instantly monitored in everyday life due to the Internet of Things (IoT). In particular, machine learning (ML) sensors for the prompt diagnosis of COVID-19 are an important option for IoT application in healthcare and ambient assisted living (AAL). Determining a COVID-19 infected status with various diagnostic tests and imaging results is costly and time-consuming. This study provides a fast, reliable and cost-effective alternative tool for the diagnosis of COVID-19 based on the routine blood values (RBVs) measured at admission. The dataset of the study consists of a total of 5296 patients with the same number of negative and positive COVID-19 test results and 51 routine blood values. In this study, 13 popular classifier machine learning models and the LogNNet neural network model were exanimated. The most successful classifier model in terms of time and accuracy in the detection of the disease was the histogram-based gradient boosting (HGB) (accuracy: 100%, time: 6.39 sec). The HGB classifier identified the 11 most important features (LDL, cholesterol, HDL-C, MCHC, triglyceride, amylase, UA, LDH, CK-MB, ALP and MCH) to detect the disease with 100% accuracy. In addition, the importance of single, double and triple combinations of these features in the diagnosis of the disease was discussed. We propose to use these 11 features and their binary combinations as important biomarkers for ML sensors in the diagnosis of the disease, supporting edge computing on Arduino and cloud IoT service.
Open AccessMachine Learning Sensors for Diagnosis of COVID-19 Disease Using Routine Blood Values for Internet of Things Application
Healthcare digitalization requires effective applications of human sensors, when various parameters of the human body are instantly monitored in everyday life due to the Internet of Things (IoT). In particular, machine learning (ML) sensors for the prompt diagnosis of COVID-19 are an important option for IoT application in healthcare and ambient assisted living (AAL). Determining a COVID-19 infected status with various diagnostic tests and imaging results is costly and time-consuming. This study provides a fast, reliable and cost-effective alternative tool for the diagnosis of COVID-19 based on the routine blood values (RBVs) measured at admission. The dataset of the study consists of a total of 5296 patients with the same number of negative and positive COVID-19 test results and 51 routine blood values. In this study, 13 popular classifier machine learning models and the LogNNet neural network model were exanimated. The most successful classifier model in terms of time and accuracy in the detection of the disease was the histogram-based gradient boosting (HGB) (accuracy: 100%, time: 6.39 sec). The HGB classifier identified the 11 most important features (LDL, cholesterol, HDL-C, MCHC, triglyceride, amylase, UA, LDH, CK-MB, ALP and MCH) to detect the disease with 100% accuracy. In addition, the importance of single, double and triple combinations of these features in the diagnosis of the disease was discussed. We propose to use these 11 features and their binary combinations as important biomarkers for ML sensors in the diagnosis of the disease, supporting edge computing on Arduino and cloud IoT service.
- Open Access
Machine Learning Sensors for Diagnosis of COVID-19 Disease Using Routine Blood Values for Internet of Things Application
Healthcare digitalization requires effective applications of human sensors, when various parameters of the human body are instantly monitored in everyday life due to the Internet of Things (IoT). In particular, machine learning (ML) sensors for the prompt diagnosis of COVID-19 are an important option for IoT application in healthcare and ambient assisted living (AAL). Determining a COVID-19 infected status with various diagnostic tests and imaging results is costly and time-consuming. This study provides a fast, reliable and cost-effective alternative tool for the diagnosis of COVID-19 based on the routine blood values (RBVs) measured at admission. The dataset of the study consists of a total of 5296 patients with the same number of negative and positive COVID-19 test results and 51 routine blood values. In this study, 13 popular classifier machine learning models and the LogNNet neural network model were exanimated. The most successful classifier model in terms of time and accuracy in the detection of the disease was the histogram-based gradient boosting (HGB) (accuracy: 100%, time: 6.39 sec). The HGB classifier identified the 11 most important features (LDL, cholesterol, HDL-C, MCHC, triglyceride, amylase, UA, LDH, CK-MB, ALP and MCH) to detect the disease with 100% accuracy. In addition, the importance of single, double and triple combinations of these features in the diagnosis of the disease was discussed. We propose to use these 11 features and their binary combinations as important biomarkers for ML sensors in the diagnosis of the disease, supporting edge computing on Arduino and cloud IoT service.
Open AccessMachine Learning Sensors for Diagnosis of COVID-19 Disease Using Routine Blood Values for Internet of Things Application
Healthcare digitalization requires effective applications of human sensors, when various parameters of the human body are instantly monitored in everyday life due to the Internet of Things (IoT). In particular, machine learning (ML) sensors for the prompt diagnosis of COVID-19 are an important option for IoT application in healthcare and ambient assisted living (AAL). Determining a COVID-19 infected status with various diagnostic tests and imaging results is costly and time-consuming. This study provides a fast, reliable and cost-effective alternative tool for the diagnosis of COVID-19 based on the routine blood values (RBVs) measured at admission. The dataset of the study consists of a total of 5296 patients with the same number of negative and positive COVID-19 test results and 51 routine blood values. In this study, 13 popular classifier machine learning models and the LogNNet neural network model were exanimated. The most successful classifier model in terms of time and accuracy in the detection of the disease was the histogram-based gradient boosting (HGB) (accuracy: 100%, time: 6.39 sec). The HGB classifier identified the 11 most important features (LDL, cholesterol, HDL-C, MCHC, triglyceride, amylase, UA, LDH, CK-MB, ALP and MCH) to detect the disease with 100% accuracy. In addition, the importance of single, double and triple combinations of these features in the diagnosis of the disease was discussed. We propose to use these 11 features and their binary combinations as important biomarkers for ML sensors in the diagnosis of the disease, supporting edge computing on Arduino and cloud IoT service.
- 4 February 2022
- Published by IGI Global Scientific Publishing
- p. 836-862
Ambient Assisted Living At-Home Laboratory for Motor Status Diagnostics in Parkinson's Disease Patients and Aged People
The chapter summarizes the authors' development on the concept of “at-home lab” (AHL). The concept employs the methods of artificial intelligence (AI), smart internet of things (IoT) technologies, and data mining techniques. The aim is at support for patients with Parkinson's disease and aged people to continuously monitor and evaluate their motor and cognitive status using own smartphone (in particular, IMU as wearable sensor, apps for testing cognitive status, camera for motor tracking). In addition, other devices in the IoT environment can participate in creating the information assistance support for people. This chapter presents and discuss the AHL concept as a further development step of AI in respect with human evolution (NeoNeoCortex). The focus is on evolutionary, environmental, and biological aspects of AI.
- 4 February 2022
- Published by IGI Global Scientific Publishing
- p. 836-862
Ambient Assisted Living At-Home Laboratory for Motor Status Diagnostics in Parkinson's Disease Patients and Aged People
The chapter summarizes the authors' development on the concept of “at-home lab” (AHL). The concept employs the methods of artificial intelligence (AI), smart internet of things (IoT) technologies, and data mining techniques. The aim is at support for patients with Parkinson's disease and aged people to continuously monitor and evaluate their motor and cognitive status using own smartphone (in particular, IMU as wearable sensor, apps for testing cognitive status, camera for motor tracking). In addition, other devices in the IoT environment can participate in creating the information assistance support for people. This chapter presents and discuss the AHL concept as a further development step of AI in respect with human evolution (NeoNeoCortex). The focus is on evolutionary, environmental, and biological aspects of AI.
- 1 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 367-375
Case Study of Using Virtual and Augmented Reality in Industrial System Monitoring
- 1 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 367-375
Case Study of Using Virtual and Augmented Reality in Industrial System Monitoring