Selpi Selpi
Mina nuvarande forskningsintressen är data-centric AI, multimodalt och multi-view-inlärning), oövervakad inlärning, tolkningsbar AI och deras tillämpningar för t.ex. autonom körning och trafiksäkerhet. Kolla in den här länken för att läsa lite av mitt arbete i EU-projektet PANACEA, och se den här podden för att få lite uppdaterad information.
Visar 38 publikationer
Spatiotemporal Interaction Pattern Recognition and Risk Evolution Analysis During Lane Changes
Potential impact of autonomous vehicles in mixed traffic from simulation using real traffic flow
Cooperative merging strategy between connected autonomous vehicles in mixed traffic
Optimization of Two-Phase Sampling Designs with Application to Naturalistic Driving Studies
Behavioral adaptation of drivers when driving among automated vehicles
Safety benefit of cooperative control for heterogeneous traffic on-ramp merging
Analytical Method of Traffic Conflict at Urban Road Intersections Based on Risk Region
Lane-Level Map Matching based on HMM
Simulation-based impact projection of autonomous vehicle deployment using real traffic flow
Comparison of Car-Following Behavior in Terms of Safety Indicators Between China and Sweden
Safety-centred analysis of transition stages to traffic with fully autonomous vehicles
Characterisation of Motorway Driving Style Using Naturalistic Driving Data
Analysis of SHRP2 Data to Understand Normal and Abnormal Driving Behavior in Work Zones
The Relationship between Different Safety Indicators in Car-following Situations
Economics of Road Safety – What does it imply under the 2030 Agenda for Sustainable Development?
A Review of Research on Driving Styles and Road Safety
The effect of curve geometry on driver behaviour in curves by using naturalistic driving data
Mutual Recognition Methodology Development
Deliverable D5.3: Final delivery of data and answers to questionnaires
Deliverable D11.3: Final Report
Deliverable D3.3: Data management in euroFOT
Automatic real-time FACS-coder to anonymise drivers in eye tracker videos
On data security and analysis platforms for analysis of naturalistic driving data
Predicting functional upstream open reading frames in Saccharomyces cerevisiae
Using mRNA Secondary Structure Predictions Improves Recognition of Known Yeast Functional uORFs
Using Inductive Logic Programming to Predict Functional Upstream Open Reading Frames in Yeast
A First Step towards Learning which uORFs Regulate Gene Expression
Using the Functional Data Model to Store and Query Recursive Biological Data
Pathway and Protein Interaction Data: from XML to FDM Database
Ladda ner publikationslistor
Du kan ladda ner denna lista till din dator.
Filtrera och ladda ner publikationslista
Som inloggad användare hittar du ytterligare funktioner i MyResearch.
Du kan även exportera direkt till Zotero eller Mendeley genom webbläsarplugins. Dessa hittar du här:
Zotero Connector
Mendeley Web Importer
Tjänsten SwePub erbjuder uttag av Researchs listor i andra format, till exempel kan du få uttag av publikationer enligt Harvard och Oxford i .RIS, BibTex och RefWorks-format.
Visar 16 forskningsprojekt
En tolkningsbar, självförklarande metod för trafiksäkerhetsapplikationer
Djupt multimodalt lärande för fordonstillämpningar
PracticAl and Effective tools to moNitor and Assess CommErciAl drivers’ fitness to drive (PANACEA)
Sammanfogande av ontologier inom trafiksäkerhet ovh stadsbyggnad
Körstilar av autonoma fordon i blandad trafik
Heterogeneous Traffic Groups Cooperative Driving Behaviours Research under Mixed Traffic Condition
Public transit shared mobility - connected and safe solutions
Övergång till framtidens transportsystem: Planering av flera nivåer för autonoma fordon
Att skapa en kärn möjliggörare för att utvärdera scenarier av blandad fordonstrafik
Understand Normal and Abnormal Driving Behavior in Work Zones: Phase II
Analysis of SHRP2 Data to Understand Normal and Abnormal Driving Behavior in Work Zones: Phase I
Att bättre förstå körstil från naturalistisk kördata
Driver modelling and cross-cultural analysis of driving styles based on large-scale driving data