Lothar Thiele
YOU?
Author Swipe
View article: PCDCNet: A Surrogate Model for Air Quality Forecasting with Physical-Chemical Dynamics and Constraints
PCDCNet: A Surrogate Model for Air Quality Forecasting with Physical-Chemical Dynamics and Constraints Open
Air quality forecasting (AQF) is critical for public health and environmental management, yet remains challenging due to the complex interplay of emissions, meteorology, and chemical transformations. Traditional numerical models, such as C…
View article: Forget the Data and Fine-Tuning! Just Fold the Network to Compress
Forget the Data and Fine-Tuning! Just Fold the Network to Compress Open
We introduce model folding, a novel data-free model compression technique that merges structurally similar neurons across layers, significantly reducing the model size without the need for fine-tuning or access to training data. Unlike exi…
View article: Pollen Video Library for Benchmarking Detection, Classification, Tracking and Novelty Detection Tasks
Pollen Video Library for Benchmarking Detection, Classification, Tracking and Novelty Detection Tasks Open
Dataset description This dataset contains microscopic images and videos of pollen gathered between Feb. and Aug. 2020 in Graz, Austria. Pollen images of 16 types: ...images_16_types.zip Acer Pseudoplatanus Aesculus Carnea Alnus Anthoxanthu…
View article: Pollen Video Library for Benchmarking Detection, Classification, Tracking and Novelty Detection Tasks
Pollen Video Library for Benchmarking Detection, Classification, Tracking and Novelty Detection Tasks Open
Dataset descriptionThis dataset contains microscopic images and videos of pollen gathered between Feb. and Aug. 2020 in Graz, Austria.Pollen images of 16 types: ...images_16_types.zipAcer PseudoplatanusAes…
View article: MIMONet: Multi-Input Multi-Output On-Device Deep Learning
MIMONet: Multi-Input Multi-Output On-Device Deep Learning Open
Future intelligent robots are expected to process multiple inputs simultaneously (such as image and audio data) and generate multiple outputs accordingly (such as gender and emotion), similar to humans. Recent research has shown that multi…
View article: Localised Adaptive Spatial-Temporal Graph Neural Network
Localised Adaptive Spatial-Temporal Graph Neural Network Open
Spatial-temporal graph models are prevailing for abstracting and modelling spatial and temporal dependencies. In this work, we ask the following question: whether and to what extent can we localise spatial-temporal graph models? We limit o…
View article: Subspace-Configurable Networks
Subspace-Configurable Networks Open
While the deployment of deep learning models on edge devices is increasing, these models often lack robustness when faced with dynamic changes in sensed data. This can be attributed to sensor drift, or variations in the data compared to wh…
View article: Self-triggered Control with Energy Harvesting Sensor Nodes
Self-triggered Control with Energy Harvesting Sensor Nodes Open
Distributed embedded systems are pervasive components jointly operating in a wide range of applications. Moving toward energy harvesting powered systems enables their long-term, sustainable, scalable, and maintenance-free operation. When t…
View article: Hydra: Concurrent Coordination for Fault-tolerant Networking
Hydra: Concurrent Coordination for Fault-tolerant Networking Open
Low-power wireless networks have the potential to enable applications that are of great importance to industry and society. However, existing network protocols do not meet the dependability requirements of many scenarios as the failure of …
View article: Interview: Kalyanmoy Deb Talks about Formation, Development and Challenges of the EMO Community, Important Positions in His Career, and Issues Faced Getting His Works Published
Interview: Kalyanmoy Deb Talks about Formation, Development and Challenges of the EMO Community, Important Positions in His Career, and Issues Faced Getting His Works Published Open
Kalyanmoy Deb was born in Udaipur, Tripura, the smallest state of India at the time, in 1963 [...]
View article: LSR: Energy-Efficient Multi-Modulation Communication for Inhomogeneous Wireless IoT Networks
LSR: Energy-Efficient Multi-Modulation Communication for Inhomogeneous Wireless IoT Networks Open
In many real-world wireless IoT networks, the application dictates the location of the nodes and therefore the link characteristics are inhomogeneous. Furthermore, nodes may in many scenarios only communicate with the Internet-attached gat…
View article: In situ observations of the Swiss periglacial environment using GNSS instruments
In situ observations of the Swiss periglacial environment using GNSS instruments Open
Monitoring of the periglacial environment is relevant for many disciplines including glaciology, natural hazard management, geomorphology, and geodesy. Since October 2022, Rock Glacier Velocity (RGV) is a new Essential Climate Variable (EC…
View article: p-Meta
p-Meta Open
Data collected by IoT devices are often private and have a large diversity\nacross users. Therefore, learning requires pre-training a model with available\nrepresentative data samples, deploying the pre-trained model on IoT devices,\nand a…
View article: Robustness of predictive energy harvesting systems: Analysis and adaptive prediction scaling
Robustness of predictive energy harvesting systems: Analysis and adaptive prediction scaling Open
Internet of Things (IoT) systems can rely on energy harvesting to extend battery lifetimes or even render batteries obsolete. Such systems employ an energy scheduler to optimise their behaviour and thus performance by adapting the system's…
View article: iSpray
iSpray Open
Despite regulations and policies to improve city-level air quality in the long run, there lack precise control measures to protect critical urban spots from heavy air pollution. In this work, we propose iSpray, the first-of-its-kind data a…
View article: Dataflow Driven Partitioning of Machine Learning Applications for Optimal Energy Use in Batteryless Systems
Dataflow Driven Partitioning of Machine Learning Applications for Optimal Energy Use in Batteryless Systems Open
Sensing systems powered by energy harvesting have traditionally been designed to tolerate long periods without energy. As the Internet of Things (IoT) evolves toward a more transient and opportunistic execution paradigm, reducing energy st…
View article: Combating Distribution Shift for Accurate Time Series Forecasting via Hypernetworks
Combating Distribution Shift for Accurate Time Series Forecasting via Hypernetworks Open
Time series forecasting has widespread applications in urban life ranging from air quality monitoring to traffic analysis. However, accurate time series forecasting is challenging because real-world time series suffer from the distribution…
View article: Comment on essd-2021-176
Comment on essd-2021-176 Open
Abstract. Monitoring of the periglacial environment is relevant for many disciplines including glaciology, natural hazard management, geomorphology, and geodesy. Since October 2022, Rock Glacier Velocity (RGV) is a new Ess…
View article: Robust Resource-Aware Self-Triggered Model Predictive Control
Robust Resource-Aware Self-Triggered Model Predictive Control Open
The wide adoption of wireless devices in the Internet of Things requires controllers that are able to operate with limited resources, such as battery life. Operating these devices robustly in an uncertain environment, while managing availa…
View article: HiMap: Fast and Scalable High-Quality Mapping on CGRA via Hierarchical Abstraction
HiMap: Fast and Scalable High-Quality Mapping on CGRA via Hierarchical Abstraction Open
Coarse-grained reconfigurable array (CGRA) has emerged as a promising hardware accelerator due to the excellent balance between reconfigurability, performance, and energy efficiency. The performance of a CGRA strongly depends on the existe…
View article: Robust Resource-Aware Self-triggered Model Predictive Control
Robust Resource-Aware Self-triggered Model Predictive Control Open
The wide adoption of wireless devices in the Internet of Things requires controllers that are able to operate with limited resources, such as battery life. Operating these devices robustly in an uncertain environment, while managing availa…
View article: Joint Energy Management for Distributed Energy Harvesting Systems
Joint Energy Management for Distributed Energy Harvesting Systems Open
Employing energy harvesting to power the Internet of Things supports their long-term, self-sustainable, and maintenance-free operation. These energy harvesting systems have an energy management subsystem to orchestrate the flow of energy a…
View article: STeC
STeC Open
Low-power wireless sensor networks have demonstrated their potential for the detection of rare events such as rockfalls and wildfires, where rapid reporting as well as long-term energy-efficient operation is vital. However, current systems…
View article: Non-Intrusive Distributed Tracing of Wireless IoT Devices with the FlockLab 2 Testbed
Non-Intrusive Distributed Tracing of Wireless IoT Devices with the FlockLab 2 Testbed Open
Testbeds for wireless IoT devices facilitate testing and validation of distributed target nodes. A testbed usually provides methods to control, observe, and log the execution of the software. However, most of the methods used for tracing t…
View article: [Tool] Designing Replicable Networking Experiments With Triscale
[Tool] Designing Replicable Networking Experiments With Triscale Open
When designing their performance evaluations, networking researchers often encounter questions such as: How long should a run be? How many runs to perform? How to account for the variability across multiple runs? What statistical methods s…
View article: Injecting Descriptive Meta-Information into Pre-Trained Language Models with Hypernetworks
Injecting Descriptive Meta-Information into Pre-Trained Language Models with Hypernetworks Open
Pre-trained language models have been widely adopted as backbones in various natural language processing tasks.However, existing pre-trained language models ignore the descriptive meta-information in the text such as the distinction betwee…
View article: Pruning-Aware Merging for Efficient Multitask Inference
Pruning-Aware Merging for Efficient Multitask Inference Open
Many mobile applications demand selective execution of multiple correlated deep learning inference tasks on resource-constrained platforms. Given a set of deep neural networks, each pre-trained for a single task, it is desired that executi…
View article: Memory-Aware Partitioning of Machine Learning Applications for Optimal Energy Use in Batteryless Systems
Memory-Aware Partitioning of Machine Learning Applications for Optimal Energy Use in Batteryless Systems Open
Sensing systems powered by energy harvesting have traditionally been designed to tolerate long periods without energy. As the Internet of Things (IoT) evolves towards a more transient and opportunistic execution paradigm, reducing energy s…
View article: [Tool] Designing Replicable Networking Experiments With Triscale
[Tool] Designing Replicable Networking Experiments With Triscale Open
The raw data can be found in the related Zenodo repository: doi.org/10.5281/zenodo.3451417 The TriScale code is available on GitHub: https://github.com/romain-jacob/triscale Accepted for publication at JSys (public reviews). For more inf…
View article: Using system context information to complement weakly labeled data
Using system context information to complement weakly labeled data Open
Real-world datasets collected with sensor networks often contain incomplete and uncertain labels as well as artefacts arising from the system environment. Complete and reliable labeling is often infeasible for large-scale and long-term sen…