Sökning: "MIMO"

Visar resultat 11 - 15 av 225 uppsatser innehållade ordet MIMO.

1. 11. Real-time uncertainty estimation for deep learning

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Árni Dagur Guðmundsson; [2023]
   Nyckelord :Machine Learning; Deep Learning; Uncertainty Estimation; Evidential Deep Learning; Computer Vision; Maskininlärning; Djupinlärning; Osäkerhetsuppskattning; Evidential Deep Learning; Datorseende; Vélnám; Djúptauganet; Óvissumat; Evidential Deep Learning; Tölvusjón;

   Sammanfattning : Modern deep neural networks do not produce well calibrated estimates of their own uncertainty, unless specific uncertainty estimation techniques are applied. Common uncertainty estimation techniques such as Deep Ensembles and Monte Carlo Dropout necessitate multiple forward pass evaluations for each input sample, making them too slow for real-time use. LÄS MER

3. 12. A Travelling Wave Slot Array based on a Double-Layer Lens for 77 GHz Automotive Radar

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Ashray Ugle; [2023]
   Nyckelord :Automotive radar; Double-layer lens; Gap waveguide technology; Waveguide slot; Antenna array; Lens-beamforming.; Bilradar; Dubbelskiktslins; Gap-vågledarteknik; Waveguide-kortplats; Antennuppsättning; Lens-beamforming.;

   Sammanfattning : Automotive radars have gained considerable interest in recent years for applications of road safety for vulnerable road users. The use of multipleinput and multiple-output (MIMO) technology in automotive radar has helped in realising a virtual aperture greater than the physical aperture of the antenna which has reduced the size of the overall radar module. LÄS MER

4. 13. Surface Reconstruction using Multipath Propagation in Indoor MIMO Radar

   Master-uppsats, Lunds universitet/Matematisk statistik

   Författare :Elias Olson; Jakob Henningsson; [2023]
   Nyckelord :Multiple-input multiple-output MIMO radar; multipath recognition; geometry reconstruction; Mathematics and Statistics;

   Sammanfattning : Using active radar for localization in indoor environments is challenging. By signal reflection off walls and other static objects, false targets occur, referred to as multipath "ghosts". These are a significant hinder in interpreting the data. LÄS MER

5. 14. Machine Learning-based MIMO Indoor Positioning

   Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknik

   Författare :Qiyi Chen; [2023]
   Nyckelord :Technology and Engineering;

   Sammanfattning : The most widely used positioning system is Global Navigation Satellite System (GNSS), which uses traditional positioning techniques and cannot achieve satisfactory positioning performance in indoor scenarios due to Non-Line-of-Sight (NLoS) transmission. Fingerprinting is a non-traditional positioning technique that is robust to NLoS transmission in indoor scenarios. LÄS MER

7. 15. Vibration Avoidance Based on Model-Based Control Incorporating Input Shaping

   Master-uppsats, KTH/Skolan för industriell teknik och management (ITM)

   Författare :Chenqi Ma; [2023]
   Nyckelord :Multi-joint industrial robot; Vibration avoidance; Path deviation; Input shaping; Extended flexible joint model; Nonlinear gray-box identification; Fleraxlade industrirobotar; Vibrationsdämpning; Banavvikelse; Ingångsformning; Utökad flexibel axelmodell; Icke-linjär gray-box modell;

   Sammanfattning : VIBRATION AVOIDANCE, a technique to proactively remove unwanted or excessive vibrations in multi-joint industrial robots, has shown to be desired in various applications. A trade-off between vibration avoidance performance and path deviation has been thekey criteria for assessing the effectiveness and quality of an approach. LÄS MER