Multi-domain Stain Normalization for Digital Pathology (MELC Images)


Open topic to research domain-specific or stain-invariant normalization techniques on high dimensional data (MELC Images).


  • PyTorch
  • Python
  • Interest in pathology images

Unsupervised Contextual Anomaly Detection in Frequency Converter Data

Thesis Description

Anomaly detection is a widely researched topic and is already extensively used in many different domains such as fraud detection for credit cards, intrusion detection for cyber-security or fault detection in safety critical systems [1]. Various anomaly detection techniques are also applied in the industry where electric motors are one of the most important components which is underlined by the fact that they account for approximately 40% of global electricity consumption. Being able to detect anomalies in their sensor data can help predicting errors and therefore avoiding expensive reactive maintenances which will save a lot of cost for unplanned downtime [2].

As it is difficult to come up with general anomaly detection techniques and since different domains have different requirements regarding performance and other limitations, a wide range of methods such as Neural Networks, Rule-based techniques, Clustering, Nearest Neighbor, Statistical models and more exist. The different techniques have certain limitations what kind of anomaly they can detect (such as point, contextual or collective anomaly) and what labels need to be available. To give an example, a nearest neighbor anomaly detection would be able to detect point anomalies without needing labeled data, which makes it an unsupervised algorithm. In general it is exceptionally hard to get labeled data in some domains and therefore in such cases an unsupervised solution is preferable [1].

In this thesis the focus is on unlabeled multivariate timeseries data coming from a SINAMIC frequency converter, that is used to convert the mains voltage to a suitable signal powering an electric motor [3]. A partial timeframe of this data is declared as reference measurement and assumed to be mostly regular without anomalies. The frequency converters have a set of sensor parameters that can be extracted and processed using the Siemens Industrial Edge Device [4]. State of the art methods for this problem include calculating the distance metric between timeseries using Dynamic Time Warping and applying the Local Outlier Factor algorithm as shown in [5], using a neural network consisting of stacked autoencoders that will classify sequences based on whether they can be reconstructed by the autoencoder [2] or using a Generative Adversarial Network (GAN) including LSTMs (Long Short Term Memory) to capture temporal correlation as demonstrated in [6].

Especially Autoencoders, that encode an input into a compact hidden representation that is then decoded with the aim of reconstructing the original input, are commonly used [7]. The idea is that since the hidden representation is reduced, it will only be able to represent regular data patterns and not the patterns in anomalies. If an anomaly is fed through the autoencoder it is expected to generate a higher reconstruction error than usual. However, the approach suffers, if the training data contains anomalies, since their patterns might be learned in this case. And indeed, this applies to many real-world applications [8].

In this thesis the unlabeled data of industry motors will be analyzed and different solutions for anomaly detection in multivariate timeseries data will be tested. Since the computation power of the edge device is limited, the algorithms will be evaluated regarding their performance. Classification of anomalies would be desirable but highly depend on the application domain and is therefore not feasible in a general anomaly detection approach.

For summarization the thesis will deal with the following points:

  1. Data analysis
    (a) Statistics
    (b) (manual) identification of anomalies
  2. Development of various models for anomaly detection
  3. Model evaluation regarding to different metrics at least including the following
    (a) Accuracy
    (b) Training performance
    (c) Runtime performance
  4. Optional: Classification

[1] Varun Chandola, Arindam Banerjee, and Vipin Kumar. Anomaly detection: A survey. ACM Comput. Surv.,
41(3), jul 2009.
[2] Sean Givnan, Carl Chalmers, Paul Fergus, Sandra Ortega-Martorell, and Tom Whalley. Anomaly detection
using autoencoder reconstruction upon industrial motors. Sensors, 22(9), 2022.
[3] Siemens AG. Converter, 2022. Accessed on 14.12.2022.
[4] Siemens AG. Industrial edge / production machines, 2022. Accessed on 14.12.2022.
[5] Wang Yong, Mao Guiyun, Chen Xu, and Wei Zhengying. Anomaly detection of semiconductor processing
data based on dtw-lof algorithm. In 2022 China Semiconductor Technology International Conference
(CSTIC), pages 1–3, 2022.
[6] Alexander Geiger, Dongyu Liu, Sarah Alnegheimish, Alfredo Cuesta-Infante, and Kalyan Veeramachaneni.
Tadgan: Time series anomaly detection using generative adversarial networks. CoRR, abs/2009.07769, 2020.
[7] Ane Bl´azquez-Garc´ia, Angel Conde, Usue Mori, and Jos´e Antonio Lozano. A review on outlier/anomaly
detection in time series data. CoRR, abs/2002.04236, 2020.
[8] Tung Kieu, Bin Yang, Chenjuan Guo, Razvan-Gabriel Cirstea, Yan Zhao, Yale Song, and Christian S.
Jensen. Anomaly detection in time series with robust variational quasi-recurrent autoencoders. In 2022
IEEE 38th International Conference on Data Engineering (ICDE), pages 1342–1354, 2022.

Machine Learning Based Analysis of EEG Data Recorded during Stimulation with Continuous Speech

Motif analysis of resting-state and stimulus driven fMRI networks with special focus on functional role of the motifs

Adaptive Training of Heat Demand Prediction using Continual Learning

One of the primal challenges faced by utility companies is ensuring efficient supply with minimal greenhouse gas emissions. On the track of facilitating the energy transition and mitigating the anthropomorphic climate change, framework for heat demand forecast poses the basis for different applications, impacting the operational as well as the economical efficiency of a utility company. More concretely, VK Energy [1] optimize combined heat and power (CHP) generation systems to increase their overall efficiency and flexibility. In order to operate the CHP system in heating networks with heat storage adaptively to the demand of the electricity system, a real-time, accurate, robust and user friendly (i.e., ideally without extensive hyperparameter tuning) forecast of the heat demand in the respective heating network is indispensable.

As heat demand forecast is an on-going research topic, numerous methods [2-5] have been proposed in the recent years. Although advanced machine learning (ML) and deep learning (DL) methods proposed in the state-of-the-arts demonstrate tremendous capability to predict the heat demand accurately, their performance is limited by the training data. As the heat consumption strongly depends on the weather condition, which is a dynamic environment, ML/DL models trained initially may not be valid anymore with changing consumption behavior and climate. Therefore, continual learning paradigm [6] should be considered to improve the applicability of ML/DL algorithms for heat demand forecast.

In this thesis, following aspects need to be considered:

  • Literature review of heat consumption prediction and continual learning.
  • Development and implementation of a continual learning framework for heat demand prediction comprising different forecasting methos and retraining mechanism.
  • Comprehensive evaluation of the performance of the implemented framework w.r.t. accuracy, robustness, run-time, and potentially usability.


[2] Y. Zhao, Y. Shen, Y. Zhu and J. Yao, “Forecasting Wavelet Transformed Time Series with Attentive Neural Networks,” 2018 IEEE International Conference on Data Mining (ICDM), 2018, pp. 1452-1457, doi: 10.1109/ICDM.2018.00201.

[3] Chatterjee, Satyaki and Bayer, Siming and Maier, Andreas K “Prediction of Household-level Heat-Consumption using PSO enhanced SVR Model”, NeurIPS 2021 Workshop on Tackling Climate Change with Machine Learning, 2021,

[4] Kováč, Szabolcs and Micha’čonok, German and Halenár, Igor and Važan, Pavel,” Comparison of Heat Demand Prediction Using Wavelet Analysis and Neural Network for a District Heating Network”, Special Issue “Artificial Intelligence in the Energy Industry”,

[5] Chatterjee S., Ramachandran A., Neergaard TF., Maier A., Bayer S., Heat Demand Forecasting with Multi-Resolutional Representation of Heterogeneous Temporal Ensemble. In: NeurIPS 2022 Workshop Tackling Climate Change with Machine Learning, 2022


Optical Character Recognition on Technical Drawings using Deep Learning

Offline-to-Online Handwriting Translation using Cyclic Consistency

Emotion Recognition in Comic Scenes with Multimodal Classifiers

Multi-View CBCT Projections Generation Using Conditional Score-Based Generative Model

Improving Breast Abnormality Analysis in Mammograms using CycleGAN