On a formal verification of machine learning systems

The paper deals with the issues of formal verification of machine learning systems. With the growth of the introduction of systems based on machine learning in the so-called critical systems (systems with a very high cost of erroneous decisions and actions), the demand for confirmation of the stability of such systems is growing. How will the built machine learning system perform on data that is different from the set on which it was trained? Is it possible to somehow verify or even prove that the behavior of the system, which was demonstrated on the initial dataset, will always remain so? There are different ways to try to do this. The article provides an overview of existing approaches to formal verification. All the considered approaches already have practical applications, but the main question that remains open is scaling. How applicable are these approaches to modern networks with millions and even billions of parameters? - from our new paper

A Survey of Adversarial Attacks and Defenses for image data on Deep Learning

This article provides a detailed survey of the so-called adversarial attacks and defenses. These are special modifications to the input data of machine learning systems that are designed to cause machine learning systems to work incorrectly. The article discusses traditional approaches when the problem of constructing adversarial examples is considered as an optimization problem - the search for the minimum possible modifications of correlative data that ”deceive” the machine learning system. As tasks (goals) for adversarial attacks, classification systems are almost always considered. This corresponds, in practice, to the so-called critical systems (driverless vehicles, avionics, special applications, etc.). Attacks on such systems are obviously the most dangerous. In general, sensitivity to attacks means the lack of robustness of the machine (deep) learning system. It is robustness problems that are the main obstacle to the introduction of machine learning in the management of critical systems. - from our new paper

Inaugural Issue JoSCaS

Journal of Smart Cities and Society

All articles are Open Access, the publisher is considering making the whole year Open Access for free to promote the newly created journal. Another incentive to submit reports on your research.

Analysis and Traffic Management in Smart Cities

This article examines the issues of traffic management in the city. It is well known that cars are a significant contributor to urban air pollution. Accordingly, the management of transport in the city is one of the imperative tasks in terms of supporting the environment and ensuring urban development. Such management is impossible without collecting information on traffic flows in the city. It is logical to assume that there should be a single data source (information store) that contains information about all shipments. Urban governance, of course, involves not only collecting and analyzing data, but also managing this process. This article is devoted to the discussion of such systems. - from our paper

On Trajectories in Moscow Subway

Along with the continuous growth of megacities, their transportation systems have become increasingly large and complex. The use of transportation systems by passengers directly reflects the changes that occur in the urban environment - for this reason, the study of urban mobility is an important task of digital urbanism. In particular, this paper is devoted to the study of spatial patterns (repetitive routes) in transportation systems with the case study on the Moscow subway. A brief review of data mining approaches to transportation systems data in general and to the task of spatial patterns extraction, in particular, is presented. A simple method for pattern extraction is proposed and applied to the Moscow subway data. As a result of the deployment of the proposed method the list of patterns was obtained - the graph of spatial patterns of the transport system under study was constructed based on it.

from our paper The Analysis of Trajectories in Moscow Subway

On robust machine learning

Our review for ongoing robust machine learning projects

Journal of Smart Cities and Society

You are welcome to submit your papers: Journal of Smart Cities and Society

How to build a hyper-local Internet

The paper describes the model of hyper-local Internet. This refers to a set of Internet resources that are, to one degree or another,relevant (useful) for users located in a certain limited area. For example,these resources discuss the functioning of a housing complex, an educational institution, contain information about local services, etc. The paper proposes both a model for organizing the markup of such areas based on the use of wireless technologies and a scheme for describing (presenting) resources. Collections of this kind can be dynamically created and maintained by any users. The result of the work is the presentation of a working model of spatial marking of the Internet, which allows you to combine existing resources together in the spatial community of their content. As a technological basis for such services, a new model of using Wi-Fi Direct is advocated.

On the New Architecture of Location-Based Services

This article discusses an alternative programming model for services that use location information. The paper proposes a new architecture for such services, which does not require users to share information about their location with service providers (services). This architecture is based on the author's proposed network spatial proximity model, where geocomputation is replaced by direct proximity measurement. This approach explicitly assumes that most services, using location information, describe (provide) some local services. Accordingly, geo-coordinates are used only for calculating proximity when searching (selecting) offers. It opens up the possibility of replacing geo-coordinates with direct measurement of proximity. Within the network proximity model, geo-computation is replaced by direct proximity definitions. And it is proposed to form this measurement of proximity based on the physical availability of signals of wireless network nodes, thus building cyber-physical systems.

from our paper

On One D2D Usage Model for 5G Networks

This article discusses a new model for using D2D interaction and proximity services (ProSe). This model allows telecommunications operators to offer their customers a micro-positioning system that will allow users (customers) of the service to offer information services (information services) to mobile subscribers who find themselves in a certain specified area. Applications of this kind of services include retail, office centers, campuses, and transport infrastructure systems. These sorts of systems will allow telecommunications operators to compete in providing these sorts of solutions with systems using wireless network approaches in the unlicensed spectrum. This work examines the software component of such a service. The proposed approach focuses on security. DOI: 10.23919/FRUCT50888.2021.9347632

International Conference on Sustainability and Climate Change

City railways – who are their passengers?

In this paper, the approaches to forecasting of passenger flows for new lines of the city railway are analyzed. The article analyzes the experience gained in designing of Moscow central diameters, in the modeling and analysis of their integration with the Moscow Metro and ground urban passenger transport. The main attention is paid to how modern telecommunication technologies make it possible to measure various movements of mobile subscribers, who are passengers, quite accurately. It is the development of telecommunication technologies that is changing the approaches to solving transport problems. What used to be seen as a goal for most transport tasks and was a forecasting goal has now become raw data and can be accurately measured. The article considers what the analysis of transport flows in a modern city now looks like.

Information System Cyber Threats

Information System Cyber Threats and Telecommunications Engineering Courses

The article discusses the issue of training of telecommunications engineers. The architecture of telecommunications solutions is changing very quickly. Obviously, training programmes must also change. Cybersecurity issues are one of the main drivers of change in telecommunications solutions and, therefore, training programmes. They have become the main issues in all processes related to digital transformation. At the same time, it is clear that the development of education in telecommunications clearly lags behind modern requirements. Such issues come to the fore in relation to the development of digital economy programmes. Cyber security issues for military telecommunications solutions are discussed separately.

See details here

On Mobile Applications Based on Proximity

The article discusses mobile applications based on the concept of proximity. On the one hand, this can be considered as a special (private) class of geo-information systems, since we are talking about services (services) that are located in a certain geographically limited area. On the other hand, the abandonment of geo-computations and the use of special metrics for direct measurement of proximity opens up possibilities for completely new services that were not available in traditional models of geo-informatics. The paper discusses issues related to the measurement of proximity, new models of services and provides examples of specific implementations.

from our new paper

COVID-19 epidemic development

In this work, mathematical modelling of the dynamics of coronavirus COVID-19 is performed for China. The outbreak of coronavirus in China can be considered as public health emergency of international concern. The number of infected is increasing daily. Cases of COVID-19 virus have been detected in nearly 200 countries. Many sporting events, festivals, exhibitions and tournaments have been canceled or postponed. The pandemic has affected education systems around the world, leading to the massive closure of schools and universities. Viral incubation period of this virus is quite long, it ranges from 1 to 14 days. The danger of a new disease also lies in the fact that it is easily confused with a common cold or flu. Therefore, the spread of coronavirus COVID-19 is a serious threat for international health and economics. A mathematical description of the dynamics of virus allows to study the nature of the disease thoughtfully, to analyze statistical and model data, to make hypotheses concerning the future dynamics of coronavirus and to evaluate the effectiveness of the measures undertaken. For mathematical modelling of coronavirus COVID-19, the authors use a modified system of differential equations constructed according to the SIR compartmental model. The optimal values of the model parameters, that describe the statistical data precisely, were found. The analysis of the current situation of the COVID-19 coronavirus epidemic in China was made, which led to the efficiency mark of the existing measures to struggle against the virus.

from INJOIT