The growing number of radio communication devices and limited spectrum resources are drivers for the development of new techniques of dynamic spectrum access and spectrum sharing. In order to make use of the spectrum opportunistically, the concept of cognitive radio was proposed, where intelligent decisions on transmission opportunities are based on spectrum sensing. In this paper, two Machine Learning (ML) algorithms, namely k-Nearest Neighbours and Random Forest, have been proposed to increase spectrum sensing performance. These algorithms have been applied to Energy Detection (ED) and Energy Vector-based data (EV) to detect the presence of a Fourth Generation (4G) Long-Term Evolution (LTE) signal for the purpose of utilizing the available resource blocks by a 5G new radio system. The algorithms capitalize on time, frequency and spatial dependencies in daily communication traffic. Research results show that the ML methods used can significantly improve the spectrum sensing performance if the input training data set is carefully chosen. The input data sets with ED decisions and energy values have been examined, and advantages and disadvantages of their real-life application have been analyzed.

No abstract

Spectrum sensing (SS) is an important tool in finding new opportunities for spectrum sharing. The users, called Secondary Users (SU), who do not have a license to transmit without hindrance, need to employ SS in order to detect and use the spectrum without interfering with the licensed users’ (primary users’ (PUs’)) transmission. Deep learning (DL) has proven to be a good choice as an intelligent SS algorithm that considers radio environmental factors in the decision-making process. It is impossible though for SU to collect the required data and train complex DL models. In this paper, we propose to employ a Federated Learning (FL) algorithm in order to distribute data collection and model training processes over many devices. The proposed method categorizes FL devices into groups by their mean Signal-to-Noise ratio (SNR) and creates a common DL model for each group in the iterative process. The results show that detection accuracy obtained via the FL algorithm is similar to detection accuracy obtained by employing several DL models, namely convolutional neural networks (CNNs), specialized in spectrum detection for a PU signal with a given mean SNR value. At the same time, the main goal of simplification of the SS process in the network is achieved.

Summary:The issue of eating behaviour may be considered both from the perspective of medical and social science. Unhealthy eating habits and lack of physical activity (PA) are well known risk factors for the appearance of many chronic diseases in adulthood. Along with sedentary lifestyle they are the main cause of the increasing prevalence of obesity in adolescents. The aim of this paper is to present eating habits of students in light of Polish and international research within different variables. Polish and international research conducted on a possibly large study material were used for comparison. It can be concluded that there are many irregularities with reference to eating behaviours. The most common nutrition mistakes made by teenagers are not eating breakfast and snacking between meals (usually sweets, chips, fast-food products).

AbstractObjectiveIn this international study, the prevalence of Eating disorders (EDs) was determined among university students and identified associated demographic and behavioral factors predicting disorders using data from three European countries.MethodsThe survey was conducted in Hungary, Poland, and Ukraine in 2018. Registered full-time students completed an online anonymous questionnaire. Students provided data about socioeconomic characteristics, body mass index (BMI), EDs, physical fitness and sport practice, psychological distress (stress, anxiety, depression), life orientation, alcohol, tobacco, and cannabis use. Data were analyzed using SPSS 24.0 software.ResultsFrom the 1965 returned questionnaires 1950 were analyzed, because of the missing data (67.3% female, mean age of the total participant’s 21.40 ± 3.83 years old). EDs were observed in 26.3% of students. In logistic regression, EDs were predicted by female sex, higher BMI, single marital status, elevated psychological distress and limited access to health care.ConclusionEDs are relatively common in university students especially in females. Students with higher distress and BMI, limited access to health care and living without partner are at risk for EDs. This result highlights the need for a public health approach. Universities are the last chance where students can be screened in an organized setting and offer interventions early when treatment is likely to be most effective.

Summary: Physical activity is one of the most important elements of a healthy lifestyle, and its lack or insufficient amounts can lead to serious health disorders. There are many adult diseases which are associated with the behaviour, lifestyle during puberty, including physical inactivity. It was therefore decided in this study to present the physical activity of young people from six countries in the world in the context of different variables. The following countries: Brazil, Spain, Poland, Czech Republic, Norway and Nepal were selected for comparison. Although all studies used the same standardized research tool, ie. the International Physical Activity Questionnaire IPAQ, in the course of analysis, the authors encountered difficulties with comparability, associated with the usage of various methods and data processing, which could result in different or reduced comparability. Consequently, it was decided not to make a detailed comparative analysis of individual research results and the presentation of the key conclusions brought about selected studies worldwide. Analyses of studies which have been conducted in different cultural contexts, confirm once again the thesis of the decline in physical activity levels with age for both girls and boys. Gender quite substantially differentiated physical efforts in adolescents. Girls at the age of adolescence are less physically active than boys. It was also noted that the increase of sedentary behaviour among children and adolescents and their disastrous consequences have an impact on the health and life in this age group, the studies of sedentary lifestyle have become a very important subject of many studies. Girls are still "more sedentary" than boys. Many authors, in order to ensure the reliability and relevance of their research, complied with the objective instrument eg. accelerometer or metabolic analyzer.

No abstract

In future wireless networks, it is crucial to find a way to precisely evaluate the degree of spectrum occupation and the exact parameters of free spectrum band at a given moment. This approach enables a secondary user (SU) to dynamically access the spectrum without interfering primary user's (PU) transmission. The known methods of signal detection or spectrum sensing (SS) enable making decision on spectrum occupancy by SU. The machine learning (ML), especially deep learning (DL) algorithms have already proved their ability to improve classic SS methods. However, SS can be insufficient to use the free spectrum efficiently. As an answer to this issue, the prediction of future spectrum state has been introduced. In this paper, three DL algorithms, namely NN, RNN and CNN have been proposed to accurately predict the 5G spectrum occupation in the time and frequency domain with the accuracy of a single resource block (RB). The results have been obtained for two different datasets: the 5G downlink signal with representation of daily traffic fluctuations and the sensor-network uplink signal characteristic for IoT. The obtained results prove DL algorithms usefulness for spectrum occupancy prediction and show significant improvement in detection and prediction for both low signal-to-noise ratio (SNR) and for high SNR compared with reference detection/prediction method discussed in the paper. Keywords: Spectrum sensing • Spectrum prediction • Machine learning • 5G • LTE • Convolutional neural network • Recurrent neural network • Neural network • Deep learning This work was supported by the DAINA project no. 2017/27/L/ST7/03166 "Cognitive Engine for Radio environmenT Awareness In Networks of the future" (CERTAIN) funded by the National Science Centre, Poland.