Abstract: The article reflects the use of neural network technologies to determine the facts of falsification of the contents of video sequences. In the modern world, new technologies have become an integral part of the multimedia environment, but their proliferation has also created a new threat – the possibility of misuse to falsify the contents of video sequences. This leads to serious problems, such as the spread of fake news and misinformation of society. The scientific article examines this problem and determines the need to use neural networks to solve it. In comparison with other existing models and approaches, neural networks have high efficiency and accuracy in detecting video data falsification due to their ability to extract complex features and learn from large amounts of source data, which is especially important when reducing the resolution of the analyzed video sequence. Within the framework of this work, a mathematical model for identifying the falsification of audio and video sequences in video recordings is presented, as well as a model based on a three-dimensional convolutional neural network to determine the fact of falsification of a video sequence by analyzing the contents of individual frames. Within the framework of this work, it was proposed to consider the problem of identifying falsifications in video recordings as a joint solution to two problems: identification of falsification of audio and video sequences, and the resulting problem itself was transformed into a classical classification problem. Any video recording can be assigned to one of the four groups described in the work. Only the videos belonging to the first group are considered authentic, and all the others are fabricated. To increase the flexibility of the model, probabilistic classifiers have been added, which allows to take into account the degree of confidence in the predictions. The peculiarity of the resulting solution is the ability to adjust the threshold values, which allows to adapt the model to different levels of rigor depending on the task. The architecture of a three-dimensional convolutional neural network, including a preprocessing layer and a neural network layer, is proposed to determine fabricated photoreceads. The resulting model has a sufficient degree of accuracy in determining falsified video sequences, taking into account a significant decrease in frame resolution. Testing of the model on a training dataset showed the proportion of correct detection of video sequence falsification above 70%, which is noticeably better than guessing. Despite the sufficient accuracy, the model can be refined to more significantly increase the proportion of correct predictions.

Abstract: In the modern information society, the volume of data is constantly growing, and its effective processing is becoming key for enterprises. The transmission and storage of this data also plays a critical role. Big data used in analytics systems is most often transmitted in one of two popular formats: CSV for structured data and JSON for unstructured data. However, existing file formats may not be effective or flexible enough for certain data analysis tasks. For example, they may not support complex data structures or provide sufficient control over metadata. Alternatively, analytical tasks may require additional information about the data, such as metadata, data schema, etc. Based on the above, the subject of this study is a data format based on the combined use of CSV and JSON for processing and analyzing large amounts of information. The option of sharing the designated data types for the implementation of a new data format is proposed. For this purpose, designations have been introduced for the data structure, which includes CSV files, JSON files, metadata and a dependency graph. Various types of functions are described, such as aggregating, transforming, filtering, etc. Examples of the application of these functions to data are given. The proposed approach is a technique that can significantly facilitate the processes of information analysis and processing. It is based on a formalized approach that allows you to establish clear rules and procedures for working with data, which contributes to their more efficient processing. Another aspect of the proposed approach is to determine the criteria for choosing the most appropriate data storage format. This criterion is based on the mathematical principles of information theory and entropy. The introduction of a criterion for choosing a data format based on entropy makes it possible to evaluate the information content and compactness of the data. This approach is based on the calculation of entropy for selected formats and weights reflecting the importance of each data value. By comparing entropies, you can determine the required data transmission format. This approach takes into account not only the compactness of the data, but also the context of their use, as well as the possibility of including additional meta-information in the files themselves and supporting data ready for analysis.