Thursday, May 23, 2019

On proximity information systems

The paper discusses the replacement of well-known conception of geo-information systems with a new model based on proximity. Geo-information systems have attracted great attention and have received great development in recent times. The reasons for this are fairly obvious. On the one hand, services are required by users, primarily at their location, and on the other hand, location determination has become easy, especially in connection with the proliferation of smartphones. But at the same time, the actual geographic coordinates are not needed by the majority of such services. Coordinates are used only for searching and organizing data. While the actual assignment of most services is a search for data (services) bound by these coordinates to a spe cific area. In other words, in most cases, service is meant data near the current location. Hence the idea to build services directly on the assessment of proximity, completely bypassing the work with coordinates. It also makes possible completely new services, especially in the technical field (for example, in transport, agriculture, etc.).

from our new paper

Thursday, May 16, 2019

On Content Models for Proximity Services

First time introduced in Release 12 of the 3GPP specifications, Proximity Services (ProSe in the above-mentioned specification) is a Device-to-Device (D2D) technology that allows two devices to detect each other and to communicate directly without traversing the Base Station or core network. In other words, it is a technology that is oriented (ultimately) on the direct connection of two devices. In this article, we are promoting the idea that proximity services are more than just support for a direct connection (in fact, search for candidates for a direct connection). The paper discusses content models (that is, information dissemination models) based on proximity data. In this case, a direct connection is simply one of the possible options for disseminating information.

Our new paper from FRUCT conference

Wednesday, April 17, 2019

Bikes in Smart Cities

Our new paper: On Bikes in Smart Cities

In this paper, we discuss data models and data mining for bicycles in Smart Cities. Mobilityissues (or Smart Mobility) are one of the main components of Smart Cities. Bicycles, as a transportcomponent in the cities, are on the rise all over the world. At least, it is true for all areas where the cli-mate even minimally allows it. The reasons are quite obvious. This is democratic and accessible thistype of transport, it is cheap and environmental friendliness. Of course, the promotion of a healthylifestyle also plays its role. The development of this type of transport (like any other) has many differentaspects. In this paper, we dwell on the issues of tracking the movement of cyclists and planning bike-sharing systems. All this information will serve as a set of metrics for any design in Smart Cities.

Read it here

Tuesday, March 12, 2019

Time series on railways

The article analyzes the patterns of use of railway stations in the Moscow region. The basis for the analysis is the data of smart cards on the entrances and exits of passengers. The technical tool is time series similarity analysis. As a result, the work identifies the main patterns of user behavior on the use of railway stations (railway transport). The results of the work were used in the design of new lines of urban railways. Obviously, the use patterns reflect the current state of the transport system and the urban environment. Accordingly, the recorded changes in usage patterns can serve as indicators and metrics for changes in the urban environment. Our paper in Arxiv

Wednesday, January 16, 2019

Open PhD positions

Announcement: 15 PhD positions fully funded for 3 years within A-WEAR Joint Doctorate Network

Target audience: fresh MSc graduates in various engineering fields (who have completed their first master no earlier than Fall 2015 or who will soon complete their MSc) and who are passionate about pursuing a PhD in a research field of high relevance to today’s society (wearable computing & IoT).

Job description: fully funded 36 months PhD positions towards double/joint PhD programs in 5 top European technical universities in Finland, Italy, Spain, Czech republic, and Romania
Gross salary (approx. in EUR/month): 3600 (FI), 2800 (ES), 2000 (RO), 2400 (CZ), 2900 (IT)
Application deadline: 28th of February 2019

Starting time of the PhD: Fall 2019

Selection criteria: Study records Bsc + Msc (20%); Work & research experience (15%); Motivation (20%); Clarity, relevance, innovativeness, and technical soundness of the ’Dissertation Essay’ (25%); Letters of recommendation (10%); Positive attitude, previous mobility experience, good communication skills (10%); English proficiency: fail/pass criterion.

We strive to improve the gender balance in our research groups and encourage female candidates to apply. At the end of the evaluation process, the recruitment committee will decide which candidates to select for each project, taking into account the candidates’ preferences and potential. In case of equal qualifications between a male and a female candidate for the final position, the balance at network level may affect the decision.

More information and link to the application page: or

Tuesday, January 08, 2019

Machine learning in software development

The subject of the article is the “coding style” concept and the main approaches to detecting the individual style of a programmer. The entire process of creating a software product from this point of view and the main features of programming style are analyzed. It emphasizes the relevance and commercial significance of the problem in terms of product support, plagiarism, work of a large developer’s community in a single repository, an evolution of developer skills. Computational stylometry issues, a possibility of using programming paradigms as an additional factor of style identification are considered. It offers the idea of creating a software tool that allows to identify the style of the author who wrote a particular program fragment and allows less experienced developers to follow the rules accepted in the major part of the repository and determined by coding style of "experts", which leads the code to a uniform format that is easier to maintain and make adjustments. Globally, this stage of analyzing the original (and then the modified code) allows improving the existing algorithms for automatic synthesis of programs.

Our new paper: Using Machine Learning Methods to Establish Program Authorship

Friday, December 14, 2018

Data Mining on the Use of Railway Stations

Our new paper: Data Mining on the Use of Railway Stations

This article deals with the processing of data on the entrances and exits of passengers for railway stations in Moscow and the suburbs. Smart transport cards are used worldwide in transport applications as a payment tool. So, for railways (cities) its usage creates the big and constantly updated collections of transactions data from cards validation equipment. The deployment model for railways in Moscow region allows us to know exactly the starting and ending points of the each route. This detailed information allows us to obtain generalized information on the modes (models) of the actual use of the railway transport. The detected travel patterns could be mapped to the model of the social and economic behavior of residents of the capital region. And vice versa, we can use known artifacts of the behavior of the inhabitants of the region as the search patterns for transport data.The conclusion that mobility is one of the main characteristics and one of the key components of a smart city is a well-known fact.

Tuesday, September 04, 2018

On Proximity-Based Information Delivery

In this paper, we propose and discuss one approach to a data sharing among mobile subscribers. Our idea is to use the identification of wireless networks to simulate some analogue for a peer-to-peer network that will work in the absence of telecommunications infrastructure. A single mobile phone (smartphone) will be sufficient both for creating a node of such telecommunications network and for publishing (disseminating) information. Our proposal is the further development of ideas related to context-aware systems based on network proximity principles. The proposed model allows mobile users to create information hubs directly at the location of the mobile phone of the publisher, which will distribute information for mobile subscribers in the immediate vicinity of it. Our new paper.

Friday, August 10, 2018

On transport models

On Passenger Flow Estimation for new Urban Railways

In this paper, we discuss the questions, associated with the forecast for passenger traffic for urban railways. The aim of the study is to select and verify the model for predicting passenger traffic of new urban railways. The article is based on the practical tasks implemented during the project phase for new urban railways in Moscow, Russia. We are considering data sources for building the forecast, as well as practical models that can be used to obtain numerical estimates. Among the discussed data sources, we target migration data that can be collected with the help of telecommunications operators, and information on the use of public transport, obtained from the validation of transport cards. Also, in this paper, we investigate the metrics for traffic along the new city rail line, which can be determined on the basis of the projected passenger traffic. The result of the work was the constructed model of the transport behavior of passengers, taking into account the availability of new urban railways and a set of metrics for assessing the functioning of this transport tool.

Monday, August 06, 2018

Thursday, July 26, 2018

On machine learning speculations

In this paper, we focus on the following four patterns that appear to us to be trending in ML scholarship:

Failure to distinguish between explanation and speculation.
Failure to identify the sources of empirical gains, e.g. emphasizing unnecessary modifications to neural architectures when gains actually stem from hyper-parameter tuning.
Mathiness: the use of mathematics that obfuscates or impresses rather than clarifies, e.g. by confusing technical and non-technical concepts.
Misuse of language, e.g. by choosing terms of art with colloquial connotations or by overloading established technical terms.

from here