Alexey Kashevnik

Russian Academy of Sciences | RAS · CAIS

In this research, we delve into the analysis of non-verbal cues and their impact on evaluating job performance estimation and hireability by analyzing video interviews. We study a variety of non-verbal cues, which can be extracted from video interviews and can provide a framework that utilizes the extracted features, and we combine them with person...

The detection of the human mental fatigue state holds immense significance due to its direct impact on work efficiency, specifically in system operation control. Numerous approaches have been proposed to address the challenge of fatigue detection, aiming to identify signs of fatigue and alert the individual. This paper introduces an approach to hum...

Modern mental fatigue detection methods include many parameters for evaluation. For example, many researchers use human subjective evaluation or driving parameters to assess this human condition. Development of a method for detecting the functional state of mental fatigue is an extremely important task. Despite the fact that human operator support...

In this research, we introduce a novel framework for assessing participants’ abilities and job performance through analyzing personality traits and nonverbal cues. We introduce a comprehensive analysis of the correlation between nonverbal features and job performance, shedding light on the most nonverbal cues noticed by the interviewers through the...

Heart rate is an essential vital sign to evaluate human health. Remote heart monitoring using cheaply available devices has become a necessity in the twenty-first century to prevent any unfortunate situation caused by the hectic pace of life. In this paper, we propose a new method based on the transformer architecture with a multi-skip connection b...

This paper presents a computer vision-based approach to chronic subdural hematoma segmentation that can be performed by one click. Chronic subdural hematoma is estimated to occur in 0.002–0.02% of the general population each year and the risk increases with age, with a high frequency of about 0.05–0.06% in people aged 70 years and above. In our res...

The database of brain CT studies with segmented chronic subdural haematomas consists of 53 studies (21 patients) containing CT slices of the human brain. Some of these slices present chronic subdural haematomas, which were segmented manually by an expert examiner in the OsiriX DICOM Viewer system. The studies were performed both for diagnosis and i...

The software allows to automate the process of CT scan processing by a doctor, which will significantly accelerate the time of its processing and reduce the influence of human factor. The software package includes trained neural network models for haematoma segmentation. Neural network models are based on UNet architecture and two implementations a...

Emotional speech recognition is a challenging task for modern systems. The presence of emotions significantly changes the characteristics of speech. In this paper, we propose a novel approach for emotional speech recognition (EMO-AVSR). The proposed approach uses visual speech data to detect a person’s emotion first, followed by processing of speec...

Driving behaviour analysis has drawn much attention in recent years due to the dramatic increase in the number of traffic accidents and casualties, and based on many studies, there is a relationship between the driving environment or behaviour and the driver’s state. To the best of our knowledge, these studies mostly investigate relationships betwe...

Detection of fatigue is extremely important in the development of different kinds of preventive systems (such as driver monitoring or operator monitoring for accident prevention). The presence of fatigue for this task should be determined with physiological and objective behavioral indicators. To develop an effective model of fatigue detection, it...

In this paper, we propose a dataset for personality traits detection based on human face videos. Ground truth data have been annotated using the IPIP-50 personality test that every participant is implementing. To collect the dataset, we developed a web-based platform that allows us to acquire spontaneous answers for predefined questions from the re...

In this paper, we introduce our proposed method for estimating the potential sales ability of a person based on interview analysis. A deep learning model was built and trained to estimate the major personality traits according to the OCEAN model. The model utilizes CNNs and LSTMs to extract and learn features from the sequence of the frames for eac...

One of the most essential physiological indicators for a human health is oxygen saturation level (SpO2). It is the primary determinant of how efficiently the body transfers oxygen from the lungs to blood cells. SpO2 is typically measured with a pulse oximeter, however, non-contact SpO2 estimate approaches based on face or hand videos have gained po...

Driver assistant systems have approved their essential role in increasing safety in the driving environment. One of their main features is the ability to provide information about location of the vehicle so that the driver can understand how and where to go. Moreover, automatically report the emergency in case of accidents to accelerate the rescue...

One of the most effective vital signs of health conditions is blood pressure. It has such an impact that changes your state from completely relaxed to extremely unpleasant, which makes the task of blood pressure monitoring a main procedure that almost everyone undergoes whenever there is something wrong or suspicious with his/her health condition....

Blueprints are documents that contain the drawing of a design and the information that explains this design. Recently, the task to automatically recognize the information in the blueprint documents has become required. Segmenting the frame and tables in the blueprint is the first step of understanding the blueprint document. In this paper, we expla...

During the last 20 years the world has been meeting digitalization challenges in many areas of life and business. Companies convert their business processes to digital form as much as possible, what allows reducing costs and increasing profits. The paper considers a case of the company aimed at manufacturing and servicing spare parts for mining equ...

One of the key functions of driver monitoring systems is the evaluation of the driver’s state, which is a key factor in improving driving safety. Currently, such systems heavily rely on the technology of deep learning, that in turn requires corresponding high-quality datasets to achieve the required level of accuracy. In this paper, we introduce a...

Using predefined speed limits on roads had huge positive safety effects on decreasing the vehicle accident rate. On the other hand using these static limits was the 20th-century solution. With the recent evolution of machine learning, driver assistant systems, and autonomous driving the necessity for dynamic speed limits are raised. In this paper w...

In this paper, we present a two stages solution to 3D vehicle detection and segmentation. The first stage depends on the combination of EfficientNetB3 architecture with multiparallel residual blocks (inspired by CenterNet architecture) for 3D localization and poses estimation for vehicles on the scene. The second stage takes the output of the first...

Measuring vital signs is usually done by sensors attached to the human body. In clinical cases, the patients are being monitored by contacted devices that alert the medical staff when the patient situation becomes unstable. However, in non-clinical cases, there are situations when vital signs measurements can be used to prevent dangerous situations...

Developing a driver monitoring system that can assess the driver’s state is a prerequisite and a key to improving the road safety. With the success of deep learning, such systems can achieve a high accuracy if corresponding high-quality datasets are available. In this paper, we introduce DriverMVT (Driver Monitoring dataset with Videos and Telemetr...

The problem of forecasting volatile sparse demand is rather different from forecasting mass sales. The paper is devoted to finding a solution for analyzing the dependencies between demands for various goods in a shopping basket for mining industry. Mining equipment is usually characterized by high price and stock costs, rare sales per item, and ava...

Driver distraction and fatigue have become one of the leading causes of severe traffic accidents. Hence, the systems that implement driver monitoring systems are crucial. Usually such systems used a monocular camera to recognize driver behavior. Even with the growing development of advanced driver assistance systems and the introduction of third-le...

This paper presents an approach and a case study for threat detection during human–computer interaction, using the example of driver–vehicle interaction. We analyzed a driver monitoring system and identified two types of users: the driver and the operator. The proposed approach detects possible threats for the driver. We present a method for threat...

The work is devoted to finding the optimal solution for predicting the sales of spare parts for a supplier of mining equipment. Various methods and approaches were analyzed such as Croston’s method, zero forecast, naive forecast, moving average forecast to forecasting sales of commodity items with variable demand. The market of commercial offers on...

Stock planning is an essential part of supply management. Mistaken planning can lead to high costs and expenses. So, the correct plans are required, which should satisfy sales demand at any time. Forecasting is one of the planning techniques. This paper aims to present the sales forecasting models for the mining equipment details based on the histo...

This paper aims to investigate the physio-emotional state of the driver in the vehicle cabin using a multimodal approach, comprising context, motion, visual, and audio data, collected beforehand. Driver behavior monitoring is implemented upon the data gained from different types of sensors, including accelerometer, magnetometer, gyroscope, GPS, fro...

The paper analyzes modern methods of driver fatigue. There are a huge variety of methods for assessing the functional states of a person. The detection of the dynamic behavior of the driver in recent years has become an increasingly popular area of research. Dynamic assessment of driver behavior includes long-term monitoring, which allows determini...

This work presents a scalable solution to speaker-dependent visual command recognition in vehicle cabin. The goal of this work is to recognize a limited number of most frequent driver’s requests based on his/her lip movements. Unlike previous works that have focused on automated lip-reading in controlled laboratory environment, we tackle this probl...

COVID-19 has greatly affected the tourist industry and ways of travel. According to the UNTWO predictions, the number of international tourist arrivals will be slowly growing by the end of 2021. One of the ways to keep tourists safe during travel is to use a personal car or car-sharing service. The sensor-based information collected from the touris...

Meditation practice is mental health training. It helps people to reduce stress and suppress negative thoughts. In this paper, we propose a camera-based meditation evaluation system, that helps meditators to improve their performance. We rely on two main criteria to measure the focus: the breathing characteristics (respiratory rate, breathing rhyth...

Detection of the drivers drowsy state is still an actual task since it is a reason for a significant number of traffic accidents. The carried out literature review showed that a significant number of approaches rely on special equipment for driver state identification. At the same time, efficient operation of computer vision-based techniques heavil...

The paper presented a state-of-the-art analysis of modern drowsiness detection algorithms based on computer vision technologies as well as consider the problem of yawning detection for the vehicle driver. Based on the literature analysis we classify drowsiness detection techniques into three groups: the driving pattern of the vehicle; psychophysiol...

Driver inattention and distraction are the main causes of road accidents, many of which result in fatalities. To reduce road accidents, the development of information systems to detect driver inattention and distraction is essential. Currently, distraction detection systems for road vehicles are not yet widely available or are limited to specific c...

This paper introduces a new methodology aimed at comfort for the driver in-the-wild multimodal corpus creation for audio-visual speech recognition in driver monitoring systems. The presented methodology is universal and can be used for corpus recording for different languages.We present an analysis of speech recognition systems and voice interfaces...

A variety of information processing and decision support tasks (especially in the context of smart city or smart tourist destination) rely both on the automated and human-based procedures. The article proposes a multi-layer cloud environment that, first, unifies various kinds of resources used by these information processing and decision-support sc...

The paper presents head angle recognition problem which has been widely studied in computer vision and takes an important role in different applications. We consider the driver monitoring application that uses the head angle detection for distraction dangerous state detection. Base method that can be used is embedded to Dlib but unfortunately, it p...

The tourism industry has been rapidly growing over the last years and IT technologies have had a great affect on tourists as well. Tourist behaviour analysis has been the subject of different research studies in recent years. This paper presents the digital pattern of life concept which simplifies the tourist behaviour models’ construction and usag...

The paper presents an approach to machine service process automation by a collaborative robot aimed at software code generation for the robot. The approach is based on the pattern-oriented programming and allows to take into account both various scenarios of part processing and input parameters.

Driving a vehicle is an indispensable part of their everyday life for many people. However, sometimes this everyday life does not go as expected, as a lot of accidents happen on the public roads, and most of these accidents are due to inattentive driver behavior. Modern driver monitoring systems evaluate driver behavior by means of distinctive sens...

This paper presents an analysis of modern research related to potential threats in a vehicle cabin, which is based on situation monitoring during vehicle control and the interaction of the driver with intelligent transportation systems (ITS). In the modern world, such systems enable the detection of potentially dangerous situations on the road, red...

The paper presents the context-based approach for monitoring in-vehicle driver behavior based on the audiovisual analysis with aid of smartphone sensors, essentially utilizing front-facing camera and microphone. We propose the approach of driver monitoring system focused on recognizing situations whether the driver is drowsy or distracted, and redu...

This paper presents a study related to human psychophysiological activity estimation based on a smartphone camera and sensors. In recent years, awareness of the human body, as well as human mental states, has become more and more popular. Yoga and meditation practices have moved from the east to Europe, the USA, Russia, and other countries, and the...

Last years more and more physiologists say about importance of human physical activities. Wherein physical activities as well as mindfulness is a key factor for human successfulness and productiveness. Last years, different kinds of yoga practice and meditation techniques becomes more and more popular and migrating from east countries to Europe. Ho...

Seat belt fastness detection in vehicles is the important factor due to the high protection role in case an accident occurs. Modern vehicles usually have belt fastness detection systems that can be simply tricked. There are also algorithms that can recognise seat belt fastness based on driver visual monitoring. Unfortunately, the existing algorithm...

Smart city concept becomes more and more popular last years for research and development. A lot of technologies appear every day that allows to automate the human life. Modern intelligent transportation systems provide possibilities to automate the driver process and increase the safety in the public roads. However, information and telecommunicatio...

The paper presents an approach and case study of a distributed driver monitoring system. The system utilizes smartphone sensors for detecting dangerous states for a driver in a vehicle. We use a mounted smartphone on a vehicle windshield directed towards the driver’s face tracked by the front-facing camera. Using information from camera video frame...

The paper proposes the context model and the dangerous state recognition scheme for intelligent driver assistant system. The system is aimed at utilization of smartphone’s front-facing camera and other sensors for dangerous states reignition to prevent emergency and reduce the accidents probability. The proposed context model is divided into follow...

Popularity of research in the area of robotics over the last years opens new tasks to develop in the area of intelligent behavior of robots for coalition creation and joint tasks solving by them. The article presents an approach to ontology-based mobile robots interaction for coalition creation. The approach is based on cyber-physical-social system...

The chapter presents an approach to agent indirect interaction in smart space based on the publication/subscription mechanism. It is proposed to describe every agent with an ontology and support the ontology matching between ontologies of different agents in smart space to enrich the semantic interoperability between them. When the agents reach the...

This paper deals with the question of how software enabling participatory enterprise modeling on a multi-touch table should be designed. We will present a pre-selection of existing HCI patterns addressing the requirements which come along with collaboratively creating enterprise models on a shared workspace. Moreover, we examined a software prototy...

This paper aims at investigating the usage of smartphone sensor data and machine learning methods to identify abnormal driver behavior. For this reason, a literature review was carried out in order to get insights into current studies of this field. Different machine learning approaches as well as different sensor data are used and from the finding...

The paper proposes an approach to driver support in vehicle cabin oriented to dangerous states determination and recommendation generation. To determine dangerous states, we propose to analyze images from smartphone front-facing camera as well as analyze information from accessible sensors. We identified two main dangerous states that are most impo...

Decentralization, immutability and transparency make of Blockchain one of the most innovative technology of recent years. This paper presents an overview of solutions based on Blockchain technology for multi-agent robotic systems, and provide an analysis and classification of this emerging field. The reasons for implementing Blockchain in a multi-r...

This paper presents a methodology and mobile application for driver monitoring, analysis, and recommendations based on detected unsafe driving behavior for accident prevention using a personal smartphone. For the driver behavior monitoring, the smartphone's cameras and built-in sensors (accelerometer, gyroscope, GPS, and microphone) are used. A dev...

Personal mobility devises become more and more popular last years. Gyroscooters, two wheeled self-balancing vehicles, wheelchair, bikes, and scooters help people to solve the first and last mile problems in big cities. To help people with navigation and to increase their safety the intelligent rider assistant systems can be utilized that are used t...

The possibilities of decentralization and immutabil-ity make blockchain probably one of the most breakthrough and promising technological innovations in recent years. This paper presents an overview, analysis, and classification of possible blockchain solutions for practical tasks facing multi-agent robotic systems. The paper discusses blockchain-b...

Smart spaces provide a platform for cooperative service construction by many devices in the Internet of Things (IoT) environments. When a service is constructed the service needs delivering to appropriate clients, which is typically implemented using the subscription operation (i.e., information-driven service construction). The passive form of sub...