The paper considers the estimation problem of the autoregressive parameter in the first-order autoregressive process with Gaussian noises when the noise variance is unknown. We propose a non-asymptotic technique to compensate the unknown variance, and then, to construct a point estimator with any prescribed mean square accuracy. Also a fixed-width confidence interval with any prescribed coverage accuracy is proposed. The results of Monte-Carlo simulations are given.

In this article, the authors assess the methodological reliability of big data processing in sociological research. The authors compare sten score method and cluster analysis as methods of processing the results of socio-psychological tests aimed at identifying groups of young people potentially vulnerable to drug addiction. The survey was conducted in eight universities in a city in Siberia with a large student population where 22884 students aged from 18 to 25 were questioned. First, the obtained results were processed by using the sten score method. Then, cluster analysis was conducted to define a high-risk group of students having a propensity for drug consumption. Advantages and disadvantages of the two methods for processing a large sample of data are compared. The results of this comparison demonstrate that the cluster analysis method is the most appropriate method for this type of research as it produces statistically correct data. The use of cluster analysis makes it possible to work with any type of information, both qualitative and qualitative data. On the other hand, the sten scores method can only be applied in certain conditions, i.e. where the original distribution resembles a normal distribution; where some theoretical basis to expect normal distribution exists, and where there is certainty that the normalization group is sufficiently large and representative to be a true reflection of the population.

In the investigation, we consider the problem of classification of audio samples resulting from the audio beehive monitoring. Audio beehive monitoring is a key component of electronic beehive monitoring (EBM) that can potentially automate the identification of various stressors for honeybee colonies. We propose to use convolutional neural networks (ConvNets) and compare developed ConvNets in classifying audio samples from electronic beehive monitors deployed in live beehives. As a result, samples are placed in one of the three non-overlapping categories: bee buzzing (B), cricket chirping (C), and ambient noise (N). We show that ConvNets trained to classify raw audio samples perform slightly better than ConvNets trained to classify spectrogram images of audio samples. We demonstrate that ConvNets can successfully operate in situ on low voltage devices such as the credit card size raspberry pi computer.

No abstract

CUSUM algorithm for controlling chain state switching in the Markov modulated Poisson process was investigated via simulation. Recommendations concerning the parameter choice were given subject to characteristics of the process. Procedure of the process parameter estimation was described.