Patrick Langer

Patrick Langer

Doctoral Researcher

ETH Zurich

About me

I am a Machine Learning Researcher. I currently work as a Doctoral Researcher at ETH Zurich, focusing on advancing healthcare with ML-based Digital Biomarkers. My research interests lie at the intersection of AI/ML, medicine, mobile applications and ubiquitous computing.

Having discovered a passion for programming and engineering at age 11, I have acquired diverse skills in various programming languages, systems, and frameworks over the years. I completed multiple projects and applications in the fields of Machine Learning, Computer Vision, Healthcare and Embedded Systems.

I am one of the winners and national finalists of Jugend forscht in 2016. Further, I support the lecture Developing Digital Biomarkers as a teaching assistant, and have supervised around 20 students in their semester, bachelor and master theses.

Interests
  • Machine Learning Systems
  • Explainable Artificial Intelligence
  • Mobile- & WearableAI
  • Digital Biomarkers & Healthcare
  • Realtime ML Applications
  • Embedded- & Distributed Systems
  • Computer Vision
Education
  • PhD in Machine Learning & Applied Computer Science, 2025 (expected)

    ETH Zurich - Swiss Federal Institute of Technology

  • MSc in Computer Science - Machine Learning & Medical Technologies, 2021

    Ilmenau University of Technology

  • BSc in Computer Science, 2020

    Ilmenau University of Technology

Experience

 
 
 
 
 
ETH Zurich, Centre for Digital Health Interventions
Doctoral Researcher (Machine Learning & Computer Science)
May 2022 – Present Zurich

I am currently a third year PhD researcher, focusing on machine learning in healthcare as well as on mobile- and edge devices. My research topics include:

  • Cross-platform, mobile-, wearable- & edge AI: CLAID
  • Explainable AI (xAI) for healthcare, especially Explainable Deep Learning Extrinsic Regression Methods
  • Machine-learning based Digital Biomarkers for chronic diseases (e.g., Asthma)

Additionally, I am a teaching assistant for the lecture Developing Digital Biomarkers.

 
 
 
 
 
Self-employed
Freelancer - Machine Learning & Embedded Engineering
Self-employed
July 2022 – Present Remote

I completed various projects for different clients worldwide, especially in the fields of:

  • Computer vision (human activity recognition, change detection)
  • Machine learning Apps (on-device image analysis)
  • Embedded engineering (UltraZED platforms, PetaLinux, VitisAI).

List of clients and projects under NDA.

 
 
 
 
 
Leibniz Institute for Innovative Microelectronics
Research Engineer (Machine Learning, Medical devices)
Leibniz Institute for Innovative Microelectronics
June 2018 – April 2022 Germany

As a research engineer, I worked on machine learning applications in medicine (especially Parkinson), and embedded applications for space- and high radiation environments.

  • Trained Neural Networks such as Temporal Convolution Networks (TCNS), Time-Delay Neural Networks (TDNNs) and LSTMs for Freezing of Gait (FoG) detection
  • Implemented FoG detection models on embedded devices and FPGAs, adhering to strict realtime requirements
  • Developed a generic FPGA-based test platform for Radiation Hardness tests (RadHard) of custom ICs, such as shift registers and memory
 
 
 
 
 
IMMS - Institute for Microelectronics and Mechatronic Systems
Research Engineer (Machine Learning, Biosensors)
IMMS - Institute for Microelectronics and Mechatronic Systems
October 2021 – April 2022 Germany

As a research engineer, I worked on medical sensors and medical applications.

  • Worked on the digital design and implementation of biosensors to detect and analyze diseases, e.g. cytokine release syndrome or tuberculosis
  • Implemented a smartphone App for the detection of skin cancer from images using CNNs
 
 
 
 
 
Bosch Corporate Research
Research Intern (Computer Vision)
Bosch Corporate Research
October 2019 – February 2020 Germany

Optimized a proprietary FPGA hardware accelerator implementation for Convolutional Neural Networks and computer vision algorithms for person detection and -segmentation from RGB videos in the context of autonomous driving on a SoC platform.

  • Reduced combined CPU pre- and postprocessing times from 800ms per frame to 55ms per frame by speeding up calculations using SIMD (Arm NEON)
  • Reduced inference time of the FPGA hardware accelerator (written in HLS) from 240ms to 140ms per frame by redesigning the accelerator from the ground up in order to use an optimized memory layout and achieve better resource utilization (increased utilization of DSP-Units from 70% to 95%)
 
 
 
 
 
Ilmenau University of Technology
Research Assistant (Computer Vision, Robotics)
Ilmenau University of Technology
April 2017 – September 2021 Germany

Worked on indoor robotic applications in the context of patient-assistance, rehabilitation and elderly care.

  • Implemented models for person detection and pose recognition
  • Integrated hardware acceleration and optimizations for computer vision models into a robotic middleware leveraging TensorRT and ONNXRuntime
  • Developed computer vision algorithms and a 3D mapping framework for semantic mapping
  • Explored automatic conversion of computer vision models to FPGA implementations for power-efficient hardware acceleration as an alternative to embedded GPUs

Projects & Research Overview

*
TSXAI - Explainable Deep Learning Time-Series Extrinsic Regression Methods in Health

TSXAI - Explainable Deep Learning Time-Series Extrinsic Regression Methods in Health

Explainable deep-learning time series extrinsic regression methods based on counterfactual approaches and evolutionary algorithms. The goal is to generate recommendations for improving general health using time-series models (TCNs) for biological age estimation.

Alex - Design, Development and Evaluation of a Digital Health Assistant for Paediatric Asthma

Alex - Design, Development and Evaluation of a Digital Health Assistant for Paediatric Asthma

Development of a Health Asistant for asthma. Using 5 digital sensors and AI methods to passively assess track symptons and predict exacerbations in a 1-year-long study with 160 participants.

CROCO - Using Commercial Wearables for Circadian Rhythm Home Monitoring

CROCO - Using Commercial Wearables for Circadian Rhythm Home Monitoring

Longitudinal tracking of circadian rhythms of individuals using commercial devices in a 14-day study with 36 participants.

CLAID - Closing the Loop on AI & Data Collection

CLAID - Closing the Loop on AI & Data Collection

An open-source cross-platform, cross-language framework for machine-learning- and data collection applications across cloud, edge, mobile and wearable devices. Supports to run ML models directly in Python, even on Android and WearOS.

Open Source AI-enabled Smart Inhaler for Asthmatic Patients

Open Source AI-enabled Smart Inhaler for Asthmatic Patients

Development of a novel open source smart inhaler compatible with the three most common inhaler types (MDI, Turbuhaler and Diskus). Using passive sensors such as accelerometers to infer inhaler usage using machine learning.

Visual Scene Change Detection from RGB Images

Visual Scene Change Detection from RGB Images

Implementation of an outdoor Visual Scene Change Detection (VSCD) using deep learning computer vision models, outperforming state of the art approaches by pretraining on much larger indoor datasets (ChangeSim).

Realtime-capable Human Activity Recognition

Realtime-capable Human Activity Recognition

Implemention of realtime capable Human Activity Recognition (HAR) approach based on deep learning models SlowFast and PoseC3D. A major challenge was slow the inference speed of current state-of-the-art models. Several improvements have been made to achieve realtime inference (10+ FPS).

Grand Theft Data Five

Grand Theft Data Five

Modification of a popular video game to extract high-quality synthetic data for autonomous driving scenarios, such as road sign annotations, person pose estimation and object segmentation. Segmentations were extracted by hijacking the rendering pipelines of the game and extracting images at various stages of the rendering process.

FPGA-Based Realtime Detection of Freezing of Gait in Parkinson Patients Using Neural Networks

FPGA-Based Realtime Detection of Freezing of Gait in Parkinson Patients Using Neural Networks

Trained and implemented Temporal Convolutional Neural Networks (TCNs) for detecting Freezing of Gait. Deployed the neural networks on FPGAs using VitisAI, adhering to strict realtime requirements.

Acceleration of CNNs for Person Detection in Autonomous Driving using FPGA's and SIMD

Acceleration of CNNs for Person Detection in Autonomous Driving using FPGA’s and SIMD

Implemented a hardware accelerator for Convolutional Neural Networks for person detection on FPGAs using HLS. Implemented highly optimized pre- and postprocesing of images using SIMD on a microcontroller. Outperformed previous results by 5x (1040ms to 195ms per frame).

Efficient Semantic 3D Mapping for Indoor Environments

Efficient Semantic 3D Mapping for Indoor Environments

Implementation of a realtime-capable 3D semantic mapping framework based on Normal Distribution Transform (NDT) and semantic histogram maps. Mapping leverages hardware acceleration on embedded devices using TensorRT.

Signapse - Realtime Road Sign Recognition on Smartphones

Signapse - Realtime Road Sign Recognition on Smartphones

A realtime road sign recognition App for smartphones incorporating object detection and classification (SSDLite, MobileNet), optionally using hardware acceleration (CoreML, TensorFlow). Currently standing at 5000+ downloads.

Biopotential based Human-Machine-Interaction

Biopotential based Human-Machine-Interaction

Designed and built (PCB, soldering, programming) from the ground up a device capable to record and analyze biosignals via electromyografie using electrodes. Allows to play games and write texts. Presented at the Jugend forscht national finals 2016.

Awards & Honors

Designed and built from the ground up a human-computer interface based on Electromyography (EMG), allowing handicapped people to write texts or play games using action potentials digitalized via an Arduino. First prize in regional & federal state finals, special prize “Innovation for people with handicaps”
Christoffel Blindenmission
Innovation for People with Handicaps
Awarded a special prize for a device allowing handicapped people (e.g., ALS patients) to play games or write texts using electrical muscle activity.
Association of German Engineers in Brandenburg
Outstanding Engineering
Awarded a special prize for outstanding engineering from the association of German Engineers in Brandenburg for the construction of a device for electromyography (EMG).

Contact

  • planger@ethz.ch
  • ETH Zurich, Centre for Digital Health Interventions, Room G214, Weinbergstrasse 56/58, Zurich, ZH 8006