Chalmers Open Digital Repository

Välkommen till Chalmers öppna digitala arkiv!

Här hittar du:

Studentarbeten utgivna på lärosätet, såväl kandidatarbeten som examensarbeten på grund- och masternivå
Digitala specialsamlingar, som t ex Chalmers modellkammare
Utvalda projektrapporter

Forskningspublikationer, rapporter och avhandlingar hittar du i research.chalmers.se

Enheter i Chalmers ODR

Välj en enhet för att se alla samlingar.

Visar 1 - 2 av 2

Senast publicerade

Detection and Adaptation of Staggered Concept Drift in Federated Online Learning - A Dynamic Cluster-Based Framework for Machine Learning with Distributed Heterogenous Data Streams
(2026) Jakobson, Josef; Forsman, Fabian
Federated Learning (FL) enables collaborative model training across distributed edge devices without requiring the exchange of raw data. However, most FL approaches assume stationary data distributions, whereas real-world environments often exhibit concept drift, where the relationship between input data and target variables changes over time. In federated settings, such drifts may occur independently across clients, creating staggered concept drift that can lead to model poisoning, degraded predictive performance, and ineffective aggregation. This thesis investigates how staggered concept drift can be automatically detected and adapted to in a federated online learning setting under the computational constraints of edge devices. A drift-aware FL framework is proposed in which clients continuously train local online models, monitor prediction errors using lightweight drift detectors, and perform local adaptation when drift is detected. To prevent aggregation of models representing different concepts, a server-side clustering mechanism dynamically groups clients according to their current concepts and maintains separate cluster models for aggregation. Additionally, the framework is evaluated on the computational cost of the edge-level algorithms, the accuracy of the detectors and performance of the global models.
Analysis of High-Dimensional Time-Series Data
(2026) Naumanen, Jonathan; Leiditz Thorsson, Joel
Modern software systems generate large volumes of high-dimensional multivariate time-series data during testing and operation. In industrial settings such as continuous integration and continuous deployment (CI/CD) pipelines, manually diagnosing recurring failures across thousands of performance metrics is time-consuming and error-prone. This thesis investigates whether representation learning can produce stable, interpretable, and diagnostically useful groupings of anomalous behaviour in such data. This allows for recurring behavioural patterns to be identified and related to meaningful system characteristics, thereby supporting failure investigation at scale. We develop and compare several autoencoder architectures, including standard, variational, Long Short-Term Memory-based (LSTM), and Transformer-based variants, against traditional dimensionality reduction baselines and state-of-the-art anomaly detection models. Each architecture encodes multivariate time windows into a compact latent representation, from which reconstruction error is derived as an anomaly score and clustering is subsequently performed. We evaluate these methods across four dimensions: anomaly detection performance, clustering stability under perturbation, interpretability of the resulting cluster structure, and computational cost. Experiments are conducted on three established benchmark datasets: Server Machine Dataset (SMD), Secure Water Treatment System (SWaT), and Soil Moisture Active Passive (SMAP) and an unlabelled industrial dataset from an Ericsson CI/CD testing pipeline. No single model consistently outperforms across all datasets. LSTM-based and probabilistic architectures achieve the highest anomaly detection scores, yet traditional methods retain approximately 90% of peak performance at a fraction of the computational cost. Clustering stability is high on the benchmark datasets, with simpler models frequently matching more complex architectures under perturbation. This means that the models capture meaningful structure instead of noise which is important for downstream analysis. The LSTM encoder combined with Uniform Manifold Approximation and Projection (UMAP) with K-Means clustering produces the most interpretable groupings, with cluster prototypes showing clearly distinct feature-level patterns. In the industrial case study, the approach groups test runs by performance-metric dynamics rather than textual error similarity, offering a complementary perspective for fault diagnosis. Across all tasks, the relationship between model complexity and performance proves non-linear: moving beyond linear projections yields meaningful gains, but further architectural complexity delivers diminishing returns.
Human-Autonomy Teaming: Effects of Autonomy Level and UAV Integration on Operator Decision-Making
(2026) Andersson, Sofie; Othman, Amin
As autonomous systems become increasingly integrated into safety-critical operations, understanding how human operators collaborate with heterogeneous robot teams is essential for effective system design. This thesis investigates how the level of automation (LOA) of an unmanned ground vehicle (UGV) and the integration of unmanned aerial vehicle (UAV) information influence operator state, performance, and decision-making in a human-UGV-UAV team. A controlled experiment was designed, varying UGV automation level — Assisted-Autonomous (AA-LOA), where the operator receives take-over requests (TORs), and Autonomous (A-LOA), where the system operates without operator input — and UAV information type — Conflicting or Non-Conflicting with the UGV sensor data. Thirty-three participants completed video-based simulations, representing logistics transport scenarios in which the UAV flew ahead of the UGV acting as a forward-looking sensor. Quantitative (e.g., operator response time, take-over probability, and eye-tracking gaze) and qualitative (e.g., mental workload and observations) data was collected. Results show that AA-LOA significantly increases perceived responsibility compared to A-LOA, without a corresponding increase in mental workload. Operators integrated the UAV-view throughout the mission, and their subjective estimates of UAV reliance closely matched that of the objective eye-tracking data. Conflicting UAV information increased the likelihood of manual intervention but did not significantly extend decision time. Despite a 50% conflict rate, operators consistently valued the UAV-view for its contextual overview and sense of safety. Demographic factors showed meaningful effects: gamers reported lower mental workload and trended toward faster decisions, while high driving frequency and strong sense of direction were the strongest predictors of longer decision times and greater confidence in own judgment during conflict scenarios. Based on these findings, 15 design guidelines were developed addressing LOA selection, transparency, UAV integration, and temporal awareness — including UAV recap functionality and a time-delta indicator to help operators contextualize temporally misaligned information. A dual-screen operator interface concept design implementing these guidelines is presented. To conclude, the findings in this thesis suggests that assisted-autonomy combined with time-transparent UAV integration provides operators with the best conditions for effective situational awareness and decision-making in heterogeneous human-autonomy systems.
Mapping Flexibility - Data Pipelines, Innovation Ecosystems, and Strategic Decision-making in Distribution Networks
(2026) Ackemo, William; Löfqvist, Axel
Electrification is increasing the pressure on electricity distribution grids, causing congestion and capacity problems, while grid infrastructure is characterized by long planning and construction lead times. Consequently, Distribution System Operators (DSOs) must make better use of the existing grid and its existing resources through flexibility, defined as ability to shift loads away from peaks and reduce congestion risks through different technologies. Thus, a DSO must increasingly rely on flexibility market mechanisms to manage capacity. A central challenge is to identify where, when, and how flexibility in the grid, and how it can be captured and deployed to solve grid related issues. One way to address this challenge is to analyze the large amounts of smart meter data generated by electricity consumption in the city, while also better understanding how the organization can utilize these resources. This thesis examines how data-driven analysis and strategic decision-making jointly shape the deployment of flexibility through an interdisciplinary approach. The study combines advanced quantitative data analysis and clustering techniques with a qualitative organizational and innovation ecosystem study. It examines how interdependent actors jointly enable flexibility in the grid, while creating a data pipeline and identifying relevant use cases and trade-offs based on interviews with key stakeholders within the DSO organization and its surrounding external actor network. The quantitative analysis develops consumption baselines and applies clustering to identify recurring demand patterns among households and small to medium-sized enterprises. The qualitative analysis examines how these analytical outputs can be interpreted, acted upon, and embedded in organizational decision-making and flexibility market development. The findings show that smart meter data can be used to show where, when, and how much flexibility exists. The study also finds that, within the regional flexibility market context, geographical clustering provides limited additional value, allowing analytical efforts to focus instead on clustering customers based on similarities in consumption behavior. Furthermore, the results highlight that clustering outputs must remain operationally actionable, where fewer, clearer, and more explainable customer groups are more useful for decision-making than highly granular segmentations. These findings imply that flexibility deployment is both a technical analytics challenge, and an organizational and ecosystem challenge. By linking advanced data analytics and clustering methods to the practical needs of DSOs, aggregators, and other ecosystem actors, the study shows how smart meter data can support more resource-efficient, lower-risk, and strategically informed flexibility deployment in modern electricity distribution systems.
AI-Powered Recommender System for Clinical Trial Protocol Design - A Tool for Medical Practitioners
Enström, Albin; Khatiri, Robin
Clinical trial endpoint selection is a complex protocol-design task that requires clinical relevance, statistical validity, regulatory awareness, and practical feasibility. In heart failure trials, this is particularly challenging because endpoint descriptions are heterogeneous, clinically nuanced, and often expressed using different terminology. This thesis investigates whether historical clinical trial data can be transformed into structured, terminology-aware representations that support secondary-endpoint recommendation for heart failure protocols. In collaboration with AstraZeneca and Evinova, the study develops an end-to end proof-of-concept pipeline. Starting from 2966 raw ClinicalTrials.gov protocol records, the dataset is reduced to 490 Phase II–III heart-failure-focused protocols containing 878 primary endpoints and 3700 secondary endpoints. Secondary end points form a reviewed hierarchy using semantic embeddings, hierarchical clustering, terminology-assisted standardization, and LLM-assisted review. Protocol and end point information is standardized against NCIt, CDISC, and LOINC for a two-stage recommendation pipeline: Stage 1 predicts relevant endpoint clusters, while Stage 2 ranks concrete secondary endpoint candidates within the predicted cluster context. The results show that hierarchical endpoint structuring provides a more interpretable and model-compatible representation than flat clustering or direct prediction over raw endpoint strings. Standardized terminology codes improved semantic consistency and contributed useful supporting features, but were most effective when combined with the reviewed hierarchy and partial endpoint context. Pairwise leave-one-out formulations were better aligned with the intended recommendation setting than direct multilabel prediction, especially for identifying missing endpoint information from a partially specified endpoint design. Full-pipeline evaluation on unseen protocols showed limited exact-match recovery, but qualitative expert review indicated that many recommendations captured clinically relevant endpoint domains, even when they were not specific enough to replace the held-out endpoint directly. Overall, the thesis demonstrates that historical clinical trial records can be reused more systematically to support endpoint-selection discussions. The proposed pipeline should be interpreted not as a production-ready clinical tool, but as a methodological foundation for AI-assisted endpoint recommendation. Future work should focus on broader therapeutic-area validation, improved terminology resources, stronger expert-labelled evaluation sets, and prospective testing with protocol designers.