A Machine Learning Based GNSS Performance Prediction for Urban Air Mobility Using Environment Recognition

Işık, Oğuz; Petrunin, Ivan; Tsourdos, Antonios; Tsourdos, Antonios; Moreno, Ricardo Verdeguer; Grech, Reuben

doi:10.1109/dasc52595.2021.9594434

Cited by 5 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recorded trajectories include sections with: (i) open sky conditions (cut-off elevation angle < 10°. The multipath effect is negligible) [28], (ii) urban environment with narrow streets and high-rise buildings (cut-off elevation angle 10° to 30°. Multipath has medium impact) [28], and (iii) semi-urban segments with tall trees of dense foliage, resulting in severe attenuation and partial blockage of the satellite signal (Cut-off elevation 20° to 60°.…”

Section: Simulations Scenario / Criteria Valuesmentioning

confidence: 99%

“…Multipath has medium impact) [28], and (iii) semi-urban segments with tall trees of dense foliage, resulting in severe attenuation and partial blockage of the satellite signal (Cut-off elevation 20° to 60°. Strong multipath impact) [28]. Each vehicle is equipped with a low-cost or middle-range GNSS receiver connected with a patch antenna placed at the top of the vehicles.…”

Section: Simulations Scenario / Criteria Valuesmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Optimal Vehicle Selection for Cooperative Positioning Using Low-Cost GNSS Receivers

Mpimis,

Kapsis,

Gikas

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The recent developments in the Global Navigation Satellite Systems (GNSS) and the advent of Intelligent Transportation Systems (ITS) have accelerated the need for accurate, reliable, and robust land vehicle positioning. Current low-cost, single-frequency GNSS receivers are universally available and have already been employed in a variety of urban mobility applications. However, low-cost GNSS receivers provide low (5-15 m) accuracy that deteriorates rapidly in deep urban and harsh environments imposing significant impact on the effectiveness and the reliability of critical ITS services. In this paper, a novel vehicle ranking and selection methodology for cooperative positioning (CP) is developed aiming at capitalizing on low-cost GNSS receivers' potential and for maximizing their benefits in safety-critical vehicular applications. The proposed method is based on the Multi-attribute Decision-Making (MADM) theory and provides a prioritization of the neighbouring vehicles in the vicinity of a target vehicle using criteria related to position accuracy and reliability. By selecting the optimal neighbour vehicle for CP, the low-cost receiver of the target vehicle enhances its location-awareness, and hence, its absolute/relative positioning accuracy. The proposed optimal vehicle selection process was inspired by the Cooperative-Differential GNSS (C-DGNSS) technique. An additional contribution of the proposed methodology is the expansion of the "moving base station" concept for use in ITS. Various MADM algorithms are considered and are simulated employing real experimental data from multiple, low-cost GNSS receivers. The optimal MADM algorithm proposed is TOPSIS because the derived rankings offer maximum stability and similarity with Average Correlation Index (ACI) = 0.78, thus satisfying the requirements for critical applications.INDEX TERMS Accuracy improvement, cooperative positioning, global navigation satellite system (GNSS), intelligent transportation systems (ITS), low-cost gnss, multi-attribute decision-making (MADM), nmea, ranking methods, rtcm, topsis, vanets, vehicular networks.

show abstract

Section: Simulations Scenario / Criteria Valuesmentioning

confidence: 99%

Section: Simulations Scenario / Criteria Valuesmentioning

confidence: 99%

Dynamic Optimal Vehicle Selection for Cooperative Positioning Using Low-Cost GNSS Receivers

Mpimis,

Kapsis,

Gikas

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

Predicting Landslide Using Machine Learning Techniques

Patel,

Chavda,

Patel

et al. 2024

ITM Web Conf.

View full text Add to dashboard Cite

In mountainous areas prone to landslides, it’s crucial to map out where these hazardous events are likely to occur to mitigate risks effectively. This study focuses employing an integrated approach to assess landslide susceptibility using Random Forest (RF), Stacking, Vote, AdaBoostM1, and Bagging. 13 factors influencing landslide occurrence are identified for modeling purposes. To evaluate and compare the models’ performance, multiple statistical methods are employed. The analysis highlights the effectiveness of employing machine learning models, Random Forest (RF), Stacking, Bagging, and Vote methods. The results demonstrate the efficiency of the models in accurately predicting landslide susceptibility. The study suggests that similar hybrid models can be effectively utilized in other sensitive regions with comparable geo-environmental conditions for landslide susceptibility studies. By integrating various techniques and leveraging ensemble algorithms, these models offer improved accuracy and reliability in assessing landslide hazards. This comprehensive approach provides valuable insights for disaster management and risk reduction efforts in landslideprone areas worldwide.

show abstract

Challenges and Future Applications for IRNSS with Machine Learning Algorithms

Patel,

Shah

2024

2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI)

View full text Add to dashboard Cite

A Machine Learning Based GNSS Performance Prediction for Urban Air Mobility Using Environment Recognition

Cited by 5 publications

References 9 publications

Dynamic Optimal Vehicle Selection for Cooperative Positioning Using Low-Cost GNSS Receivers

Dynamic Optimal Vehicle Selection for Cooperative Positioning Using Low-Cost GNSS Receivers

Predicting Landslide Using Machine Learning Techniques

Challenges and Future Applications for IRNSS with Machine Learning Algorithms

Contact Info

Product

Resources

About