Personal vid Högskolan
Slawomir Nowaczyk
Professor
( School of Information Technology )
Working with
Research Interests: Artificial Intelligence, Machine Learning and Data Mining, especially for Streaming Big Data, with a focus on Knowledge Representation and Weakly-Supervised Models.
Practical Interests:
* Predictive maintenance, Prognostics, Diagnostics, Data-driven fault detection methods;
* Information-driven Healthcare, Machine Learning for Health;
* Smart Industry, Smart Cities, Smart Energy, Smart Transport, and more.
***
In my research, I focus on the discovery of interesting patterns and relations, where the "interestingness" can be treated as a metric and quantitatively measured. In this respect, we are evaluating of both the data and the extracted knowledge. In many applications, it is not feasible to store all the data, and therefore a preliminary decision needs to be made as to what are the most useful subsets to use in further analysis. We aim for interestingness metrics that are suitable for evaluating partial results in distributed environments. An important feature, however, is that they should be adaptable to different tasks and domains, as well as work for both supervised and unsupervised learning.
Specifically on the topic of self-organisation and self-awareness, beyond solutions that work well for specific application domains, we aim to obtain a deeper understanding of fundamental concepts, allowing us to build a general theory on top of those successful application examples. This often involves guiding the learning process using (both structured and semi-structured) expert and historic knowledge. In particular, this can be done before the learning starts, but also later, as a way to evaluate results and have the user guide the process in an interactive way. I am working towards designing knowledge representation models that allow for efficient learning, while being flexible enough to capture different aspects of the data simultaneously.
***
Special Assignments: I am Research Leader for School of Information Technology.
Supervision: I currently supervise six PhD students, and co-supervise another one (both academic and industrial). I have supervised four students until their PhD dissertation, and another four until their Lic degrees.
Current Teaching: I am course responsible and examiner for the Master of Science thesis for Master and Civilingenjör programmes. I am also teaching is several other courses, such as Applied Data Mining, Big Data Parallel Programming, Data Mining, Introduction to Programming, and
Personal
Latest publications
Artikel i tidskrift
Article in journal
Towards personalized cardiometabolic risk prediction : A fusion of exposome and AI
(2025) PublishedContext Discovery for Anomaly Detection
(2025) PublishedFuzzy Particle Filtering Based Approach for Battery RUL Prediction With Uncertainty Reduction Strategies
(2025) PublishedSpatial Clustering Approach for Vessel Path Identification
(2024) PublishedRolling The Dice For Better Deep Learning Performance : A Study Of Randomness Techniques In Deep Neural Networks
(2024) PublishedExploring classical machine learning for identification of pathological lung auscultations
(2024) PublishedEnhancing Air Quality Forecasting Using Machine Learning Techniques
(2024) PublishedDynamic Causal Explanation Based Diffusion-Variational Graph Neural Network for Spatiotemporal Forecasting
(2024) PublishedA Knowledge-Based AI Framework for Mobility as a Service
(2023) PublishedEnhancing Energy Efficiency in Connected Vehicles for Traffic Flow Optimization
(2023) PublishedSemantics-aware Dynamic Graph Convolutional Network for Traffic Flow Forecasting
(2023) PublishedDEED : DEep Evidential Doctor
(2023) PublishedInformation-gathering in latent bandits
(2023) PublishedFast Genetic Algorithm for feature selection — A qualitative approximation approach
(2023) PublishedMulti-Domain Adaptation for Regression under Conditional Distribution Shift
(2023) PublishedMaterial handling machine activity recognition by context ensemble with gated recurrent units
(2023) PublishedAttention Horizon as a Predictor for the Fuel Consumption Rate of Drivers
(2022) PublishedSmaller is smarter : A case for small to medium-sized smart cities
(2022) PublishedWhy Is Multiclass Classification Hard?
(2022) PublishedWisdom of the contexts : active ensemble learning for contextual anomaly detection
(2022) PublishedLong-term Evaluation of the State-of-Health of Traction Lithium-ion Batteries in Operational Buses
(2022) Published
Konferensbidrag
Conference paper
Health Data Security Using PRI : Enhancing Remote Deep Learning for Pervasive Health Monitoring
(2025)Mind the Data, Measuring the Performance Gap Between Tree Ensembles and Deep Learning on Tabular Data
(2024)A Review of Randomness Techniques in Deep Neural Networks
(2024)Invariant Feature Selection for Battery State of Health Estimation in Heterogeneous Hybrid Electric Bus Fleets
(2024)Evaluating Multi-task Curriculum Learning for Forecasting Energy Consumption in Electric Heavy-duty Vehicles
(2024)Deep Learning for Generating Synthetic Traffic Data
(2024)Analysis of characteristic functions on Shapley values in Machine Learning
(2024)Explainable Federated Learning by Incremental Decision Trees
(2024)EcoShap : Save Computations by only Calculating Shapley Values for Relevant Features
(2024)Improving Concordance Index in Regression-based Survival Analysis : Discovery of Loss Function for Neural Networks
(2024)Effective Elements of Climate Change Videos on the YouTube Platform
(2024)Higher-order Spatio-temporal Physics-incorporated Graph Neural Network for Multivariate Time Series Imputation
(2024)Towards Explainable Deep Domain Adaptation
(2024)curr2vib : Modality Embedding Translation for Broken-Rotor Bar Detection
(2023)Incorporating Physics-based Models into Data-Driven Approaches for Air Leak Detection in City Buses
(2023)Fast Genetic Algorithm For Feature Selection — A Qualitative Approximation Approach
(2023)Data-Centric Perspective on Explainability Versus Performance Trade-Off
(2023)XAI for Predictive Maintenance
(2023)Data-Driven Explainable Artificial Intelligence for Energy Efficiency in Short-Sea Shipping
(2023)Analysis of Statistical Data Heterogeneity in Federated Fault Identification
(2023)Toward Solving Domain Adaptation with Limited Source Labeled Data
(2023)AID4HAI : Automatic Idea Detection for Healthcare-Associated Infections from Twitter, A Framework based on Active Learning and Transfer Learning
(2023)A systematic approach for tracking the evolution of XAI as a field of research
(2023)An Explainable Knowledge-based AI Framework for Mobility as a Service
(2022)Filtering Misleading Repair Log Labels to Improve Predictive Maintenance Models
(2022)Domain Adaptation in Predicting Turbocharger Failures Using Vehicle's Sensor Measurements
(2022)A Fault Detection Framework Based on LSTM Autoencoder : A Case Study for Volvo Bus Data Set
(2022)
Rapport
Report
OSMaaS Toolkit : Designing Open and Self Organising Mechanisms for Sustainable Mobility as a Service
(2024)
Kapitel i bok, del av antologi
Chapter in book
Message from Kurt Tutschku and Slawomir Nowaczyk, FMEC Chairs
(2024)
