The factors complicating the specification of requirements for artificial intelligence systems (AIS) and their verification for the AIS creation and modernization are analyzed. The harmonization of definitions and building of a hierarchy of AIS characteristics for regulation of the development of techniques and tools for standardization, as well as evaluation and provision of requirements during the creation and implementation of AIS, is extremely important. The study aims to develop and demonstrate the use of quality models for artificial intelligence (AI), AI platform (AIP), and AIS based on the definition and ordering of characteristics. The principles of AI quality model development and its sequence are substantiated. Approaches to formulating definitions of AIS characteristics, methods of representation of dependencies, and hierarchies of characteristics are given. The definitions and harmonization options of hierarchical relations between 46 characteristics of AI and AIP are suggested. The quality models of AI, AIP, and AIS presented in analytical, tabular, and graph forms, are described. The so-called basic models with reduced sets of the most important characteristics are presented. Examples of AIS quality models for UAV video navigation systems and decision support systems for diagnosing diseases are described.

No abstract

No abstract

The subject of the research is the models of artificial intelligence (AI) quality. The current paper develops an AI quality model based on the definition and ordering of its characteristics. Objectives: to develop the principles and justify the sequence of analysis and development of AI quality models as ordered sets of characteristics; to offer models of AI quality for further use, first, the evaluation of individual characteristics and quality in general; to demonstrate the profiling of AI quality models for systems using artificial intelligence. The following results were obtained. The sequence of construction of AI quality models is offered. Based on the analysis of references, a list of AI characteristics was formed and their definitions were harmonized. The general model of AI quality is presented with a description of the step-by-step procedure for the realization of its hierarchical construction. A basic model of AI with abbreviated sets of characteristics is proposed due to its importance. Examples of profiling of quality models for two systems - monitoring of engineering communications and recognition of road signs are given. Conclusions. The study's main result is the development of a quality model for artificial intelligence, which is based on the analysis and harmonization of definitions and dependencies of quality characteristics specific to AI. The selection of characteristics and the construction of the quality model were carried out in such a way to exclude duplication, ensure the completeness of the presentation, as well as to determine the specific features of each characteristic. It is extremely difficult to create a model that would fully meet such requirements, so the presented options should be supplemented and improved considering the rapid development of technologies and applications of AI. The proposed quality models are open and can be supplemented and detailed according to the specific purpose and scope of AI.

Motivation. After the Fukushima, nuclear power plant (NPP) accident, an unmanned aerial vehicle (UAV)-enabled wireless network (UEWN) is considered to be used for transmitting the data from monitoring stations (MSs) to the crisis center (CrS) during NPP post-accident monitoring missions. Nevertheless, the popular lightweight UAVs have an endurance of about 20–40 minutes only. The last fact presents a significant barrier to use a UEWN in complex, long-term NPP post-accident monitoring missions. The subject matter of the paper is the process of ensuring the persistent operation of UEWN. This paper aims to propose an approach to ensuring the persistent operation of UEWN during NPP post-accident monitoring missions via automatic battery replacement stations (ABRSs). The objectives of the paper are: to propose a scheme of deployment of a UEWN with ABRSs for the given scenario; to give an example of the proposed scheme application for persistent transmitting the data from a MS to the CrS during Zaporizhzhia NPP (ZNPP) post-accident monitoring missions; to discuss an example of the proposed scheme application. The following results were obtained. A simplified scheme of deployment of a UEWN with ABRSs for transmitting the data from the MS to the CrS during NPP post-accident monitoring missions was developed and described. Two segments within the UEWN were considered: 1) Wi-Fi segment, comprising the WiFi equipment of the MS, the onboard WiFi equipment of the UAVs of a multi-rotor type (MUAVs), and onboard WiFi equipment of the UAV of an airplane-type (AUAV); 2) LoRaWAN segment, comprising the LoRaWAN equipment of the AUAV and the LoRaWAN equipment of the CrS. An example of deployment of a UEWN with ABRSs for transmitting the data from an MS of ZNPP to the CrS was given and described. A shift schedule for 2 MUAV fleets ensuring the persistent operation of the UEWN during post-accident ZNPP monitoring missions was built and analyzed. It was evaluated how the flight distance for the MUAV between its location point in the WiFi segment and the ABRS effects: the duty time for the MUAV fleet; the waiting time for the MUAV to flight to the point of its location in the WiFi segment; the number of the MUAV fleets for ensuring the persistent operation of the UEWN. The new research will aim at developing a scheme of deployment of the UEWN with ABRSs for several WiFi segments