1. Explainable anomaly detection of 12-Lead ECG signals using denoising autoencoderRok Hribar, Drago Torkar, 2024, independent scientific component part or a chapter in a monograph Abstract: The basic idea was to create a proof of concept demonstrating that the indoor navigation and localisation is possible using only passive tags. For this purpose, a smartphone navigation app was developed to be used in inner parts of the buildings and which can operate with no satellite positioning service available and no communication network present. The satellite navigation systems (GPS, GLONASS, Galileo, BeiDou, QZSS, IRNSS) inside buildings, at least on lower floors and cellars, in central parts, and away from windows, usually do not work, or their accuracy is very reduced due to a small number of visible satellites. The communication networks (WiFi, LTE, 5G…) might not be available in some circumstances such as catastrophic incidents, power reductions, or similar, which disables the localisation systems based on them. The purpose of the smartphone app was twofold. First, to develop a reliable, simple-to-use, and cheap indoor navigation system that could be used in large buildings like hospitals, shopping malls, trade centres, fairs, etc. where no other positioning service is available. Second, to develop an indoor position reporting system that can be used in accidents and mass-casualty incidents for reporting triage decisions to the server. Both functionalities are based on the QR codes [1] holding all the information needed.
Keywords: internet thinks, indoor navigation, systems, QR codes
Published in DiRROS: 02.07.2024; Views: 81; Downloads: 34
 Full text (931,78 KB)
This document has many files! More... |
2. Models for forecasting the traffic flow within the city of LjubljanaGašper Petelin, Rok Hribar, Gregor Papa, 2023, original scientific article Abstract: Efficient traffic management is essential in modern urban areas. The development of intelligent traffic flow prediction systems can help to reduce travel times and maximize road capacity utilization. However, accurately modeling complex spatiotemporal dependencies can be a difficult task, especially when real-time data collection is not possible. This study aims to tackle this challenge by proposing a solution that incorporates extensive feature engineering to combine historical traffic patterns with covariates such as weather data and public holidays. The proposed approach is assessed using a new real-world data set of traffic patterns collected in Ljubljana, Slovenia. The constructed models are evaluated for their accuracy and hyperparameter sensitivity, providing insights into their performance. By providing practical solutions for real-world scenarios, the proposed approach offers an effective means to improve traffic flow prediction without relying on real-time data.
Keywords: traffic modeling, time-series forecasting, traffic-count data set, machine learning, model comparison
Published in DiRROS: 28.09.2023; Views: 485; Downloads: 218
Full text (5,05 MB)
This document has many files! More... |
3. |
4. |
5. A comparison of models for forecasting the residential natural gas demand of an urban areaRok Hribar, Primož Potočnik, Jurij Šilc, Gregor Papa, 2019, original scientific article Abstract: Forecasting the residential natural gas demand for large groups of buildings is extremely important for efficient logistics in the energy sector. In this paper different forecast models for residential natural gas demand of an urban area were implemented and compared. The models forecast gas demand with hourly resolution up to 60 h into the future. The model forecasts are based on past temperatures, forecasted temperatures and time variables, which include markers for holidays and other occasional events. The models were trained and tested on gas-consumption data gathered in the city of Ljubljana, Slovenia. Machine-learning models were considered, such as linear regression, kernel machine and artificial neural network. Additionally, empirical models were developed based on data analysis. Two most accurate models were found to be recurrent neural network and linear regression model. In realistic setting such trained models can be used in conjunction with a weather-forecasting service to generate forecasts for future gas demand.
Keywords: demand forecasting, buildings, energy modeling, forecast accuracy, machine learning
Published in DiRROS: 15.03.2019; Views: 2416; Downloads: 1112
Full text (968,06 KB) |
