Dr.-Ing. Xiang Xie

Lebenslauf

Bachelorstudium der Mechatronik an der Tongji Universität, Shanghai
- Bachelorarbeit: Konzipierung und Umsetzung einer autarken Software zur automatisierten Auswertung und Darstellung von Messdaten bei der VW AG in Wolfsburg
Masterstudium der Elektro- und Informationstechnik am KIT
- Masterarbeit: Evaluierung und Optimierung des Filter-Ansatzes zur Merkmalsselektion basierend auf Evaluationsdatensätzen
Wissenschaftlicher Mitarbeiter am ITIV seit Juli 2019
Promotion abgeschlossen im Januar 2023: "Artificial Intelligence for Spectral Analysis: a Comprehensive Framework"

Betreute abgeschlossene studentische Arbeiten (Auswahl)

MA: "Conception and Optimization of an X-Ray Flouresence based Thickness and Concentration Measurement Method of Coating using Neural Networks and Meta Learning Techniques"
MA: "Implementation, Optimization and Evaluation of a Feature Selection Method with Evolutionary Algorithm"
MA: "Application of Reinforcement Learning Algorithms in Spectral Analysis"
MA: "Implementierung und Evaluation von Deep Reinforcement Learning Algorithmen sowie deren Generalisierungsfähigkeit in einer virtuellen Umgebung (Implementation and Evaluation of Deep Reinforcement Learning Algorithms and their Abilty to Generalize in a Virtual Environment)"
MA: "Implementation and Evaluation of a Recommender System based on Multi-Label Classication Algorithms for the Identication of Composition of Unknown Alloys"
MA: "Feature-Selection-Based Iterative Pruning for Neural Network Compression"
MA: "Automatic Calibration of Neural-Network-Based X-Ray fluorescence Analysis Using Meta-Learning Techniques"
MA: "Anpassung und Erweiterung von Deep Reinforcement Learning Algorithmen zur Anwendbarkeit an einem TurtleBot3"

Studentische Arbeiten
Titel	Typ	Datum
Deep Learning-Ansatz zur Fahrverhaltensvorhersage mit Datenfusion	Masterarbeit	ab 03 / 2023
Meta-Learning: learning to learn. Generalisierung der Fähigkeit von neuronalen Netzen für Aufgabenserien	Bachelor-/ Masterarbeit	ab 03 / 2023
Machine Learning Algorithmen für Multi-Label Klassifikationsprobleme	Bachelor-/ Masterarbeit	ab 03 / 2023
Feature selection and model compression: fast, efficient and explainable machine learning	Bachelor-/ Masterarbeit	ab 03 / 2023
Cross-platform deployment and update of neural networks	Bachelor-/ Masterarbeit	ab 03 / 2023
Train your own AI agent with Reinforcement Learning: Gaming, dynamic controlling like a pro	Bachelor-/ Masterarbeit	ab 03 / 2023

HiWi-Stellen
Titel	Eintrittstermin
Aufbau eines Deep-Learning Frameworks zur Fahrverhaltensvorhersage mit Datenfusion	ab 03 / 2023

Publikationen

2023

Dissertationen

Artificial Intelligence for Spectral Analysis: a Comprehensive Framework. Dissertation
Xie, X.
2023, April 19. Karlsruher Institut für Technologie (KIT). doi:10.5445/IR/1000157893

Proceedingsbeiträge

LETSCOPE: Lifecycle Extensions Through Software-Defined Predictive Control of Power Electronics
Chu, A.; Hermann, C. M.; Silz, J.; Pfau, J.; Barón, K. M.; Anantharajaiah, N.; Schmidt, P.; Hotfilter, T.; Xie, X.; Becker, J.; Kallfass, I.; Roth-Stielow, J.; Stork, W.
2023. IEEE EUROCON 2023 - 20th International Conference on Smart Technologies, 665–670, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/EUROCON56442.2023.10199076

2022

Zeitschriftenaufsätze

RGB Image- and Lidar-Based 3D Object Detection Under Multiple Lighting Scenarios
Chen, W.; Tian, W.; Xie, X.; Stork, W.
2022. Automotive Innovation, 5 (3), 251–259. doi:10.1007/s42154-022-00176-2

Proceedingsbeiträge

PA-DCGAN: Efficient Spectrum Generation using Physics-Aware Deep Convolutional Generative Adversarial Network with Latent Physical Characteristics and Constraints
Xie, X.; Gao, Y.; Stork, W.
2022. 2022 IEEE Symposium Series on Computational Intelligence (SSCI), Singapore, Singapore, 04-07 December 2022, 1164–1171, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/SSCI51031.2022.10022246

Efficient Comprehensive Element Identification in Large Scale Spectral Analysis with Interpretable Dimension Reduction
Xie, X.; Stork, W.
2022. IEEE International Conference on Big Data (Big Data), Osaka, Japan, 17th-20th December 2022, 5623–5631, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/BigData55660.2022.10020993

Enabling Real-Time Low-Cost Spectral Analysis on Edge Devices with Deep Neural Networks: a Robust Hybrid Approach
Xie, X.; Chen, T.; Stork, W.
2022. IEEE International Conference on Big Data (Big Data), Osaka, Japan, 17th-20th December 2022, 2431–2436, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/BigData55660.2022.10020541

Minimal Cost Device Calibration in Spectral Analysis via Meta Learning: Towards Efficient Deployment of Deep Neural Networks in Industry
Xie, X.; Jin, M.; Chu, A.; Stork, W.
2022. IEEE International Conference on Big Data (Big Data), Osaka, Japan, 17th-20th December 2022, 2123–2132, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/BigData55660.2022.10020366

Efficient Network Pruning via Feature Selection
Xie, X.; Chen, T.; Chu, A.; Stork, W.
2022. 2022 26th International Conference on Pattern Recognition (ICPR), 1843–1850, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/ICPR56361.2022.9956190

Large-Scale Spectral Analysis for Element Quantification using Deep Neural Networks
Xie, X.; Stork, W.
2022. 2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy, 18-23 July 2022, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/IJCNN55064.2022.9891970

2020

Proceedingsbeiträge

Watermelon: a Novel Feature Selection Method Based on Bayes Error Rate Estimation and a New Interpretation of Feature Relevance and Redundancy
Xie, X.; Stork, W.
2020. Proceedings of ICPR 2020 25th International Conference on Pattern Recognition, Milan, 10 – 15 January 2021, 1360–1367, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/ICPR48806.2021.9413262