Publications by authors named "Andrey Somov"
Computer vision systems have been integrated into facilities dealing with the sorting of household waste. This solution allows for the sorting efficiency improvement and cost reduction. However, challenges associated with the poor annotation quality of existing waste segmentation datasets, unsuitable environment for recognition on a conveyor belt, or limited data for creating an effective and cost-efficient sorting system using visible range cameras significantly limit the application efficiency of computer vision systems.
View Article and Find Full Text PDFArticle Synopsis
- Crying in infants serves as a crucial signal indicating various states like discomfort, hunger, or sickness, but caregivers often struggle to interpret these cues effectively.
- This study explores advanced audio feature representations, such as time-domain features (zero-crossing rate and root mean square), frequency-domain features (Mel-spectrogram), and time-frequency-domain features (Mel-frequency cepstral coefficients), to analyze infant cries for better understanding.
- The research employs machine learning classifiers, notably a random forest classifier, achieving an accuracy of 96.39% in identifying the meaning behind cries, surpassing current state-of-the-art methods.
Food quality control is an important task in the agricultural domain at the postharvest stage for avoiding food losses. The latest achievements in image processing with deep learning (DL) and computer vision (CV) approaches provide a number of effective tools based on the image colorization and image-to-image translation for plant quality control at the postharvest stage. In this article, we propose the approach based on Generative Adversarial Network (GAN) and Convolutional Neural Network (CNN) techniques to use synthesized and segmented VNIR imaging data for early postharvest decay and fungal zone predictions as well as the quality assessment of stored apples.
View Article and Find Full Text PDFThe emerging progress of video gaming and eSports lacks the tools for ensuring high-quality analytics and training in professional and amateur eSports teams. We report on an Artificial Intelligence (AI) enabled solution for predicting the eSports player in-game performance using exclusively the data from sensors. For this reason, we collected the physiological, environmental, and the smart chair data from professional and amateur players.
View Article and Find Full Text PDFAnalysis of Video Game Players' Emotions and Team Performance: An Esports Tournament Case Study.
IEEE J Biomed Health Inform
August 2022
Video gaming and eSports is a quickly developing industry already involving billions of players worldwide. Gaming and eSports tournaments require strong mental abilities to avoid severe stress and other negative consequences upon completing the game. In this article, we report on the impact of emotions on a team performance.
View Article and Find Full Text PDFPurpose: This paper is aimed at investigating the feasibility of developing a personal dosimeter of cumulative radiation dose which would incorporate the following features: 1) a small size compared to that of a proximity ID card; 2) instant dose readout; 3) no power source; 4) moderate cost. The dosimeter is proposed as a potential replacement for TLD and OSL dosimeters used by nuclear industry workers and some medical staff groups.
Methods: An original detector design is developed containing a two-color LED, two photodetectors located in one plane covered with a mirror coating.