In many real-world applications today, it is critical to continuously record and monitor certain machine or system health indicators to discover malfunctions or other abnormal behavior at an early... Show moreIn many real-world applications today, it is critical to continuously record and monitor certain machine or system health indicators to discover malfunctions or other abnormal behavior at an early stage and prevent potential harm. The demand for such reliable monitoring systems is expected to increase in the coming years. Particularly in the industrial context, in the course of ongoing digitization, it is becoming increasingly important to analyze growing volumes of data in an automated manner using state-of-the-art algorithms. In many practical applications, one has to deal with temporal data in the form of data streams or time series. The problem of detecting unusual (or anomalous) behavior in time series is commonly referred to as time series anomaly detection. Anomalies are events observed in the data that do not conform to the normal or expected behavior when viewed in their temporal context.This thesis focuses on unsupervised machine learning algorithms for anomaly detection in time series. In an unsupervised learning setup, a model attempts to learn the normal behavior in a time series — which might already be contaminated with anomalies — without any external assistance. The model can then use its learned notion of normality to detect anomalous events. Show less
Hanse, G.; Winter, R. de; Stein, B. van; Bäck, T.H.W. 2022
The research topic of the thesis is the extension of evolutionary multi-objective optimization for real-world scheduling problems. Several novel algorithms are proposed: the diversity indicator... Show moreThe research topic of the thesis is the extension of evolutionary multi-objective optimization for real-world scheduling problems. Several novel algorithms are proposed: the diversity indicator-based multi-objective evolutionary algorithm (DI-MOEA) can achieve a uniformly distributed solution set; the preference-based MOEA can obtain preferred solutions; the edge-rotated cone can improve the performance of MOEAs for many-objective optimization; and dynamic MOEA takes the stability as an extra objective. Besides the classical flexible job shop scheduling, the thesis proposes solutions for the novel problem domain of vehicle fleet maintenance scheduling optimization (VFMSO). The problem originated from the CIMPLO (Cross-Industry Predictive Maintenance Optimization Platform) project and the project partners Honda and KLM. The VFMSO problem is to determine the maintenance schedule for the vehicle fleet, meaning to find the best maintenance order, location and time for each component in the vehicle fleet based on the predicted remaining useful lifetimes of components and conditions of available workshops. The maintenance schedule is optimized to bring business advantages to industries, i.e., to reduce maintenance time, increase safety and save repair expenses. After formulating the problem as a scalable benchmark in an industrially relevant setting, the proposed algorithms have been successfully used to solve VFMSO problem instances. Show less
Through the quantification of physical activity energy expenditure (PAEE), health care monitoring has the potential to stimulate vital and healthy ageing, inducing behavioural changes in older... Show moreThrough the quantification of physical activity energy expenditure (PAEE), health care monitoring has the potential to stimulate vital and healthy ageing, inducing behavioural changes in older people and linking these to personal health gains. To be able to measure PAEE in a health care perspective, methods from wearable accelerometers have been developed, however, mainly targeted towards younger people. Since elderly subjects differ in energy requirements and range of physical activities, the current models may not be suitable for estimating PAEE among the elderly. Furthermore, currently available methods seem to be either simple but non-generalizable or require elaborate (manual) feature construction steps. Because past activities influence present PAEE, we propose a modeling approach known for its ability to model sequential data, the recurrent neural network (RNN). To train the RNN for an elderly population, we used the growing old together validation (GOTOV) dataset with 34 healthy participants of 60 years and older (mean 65 years old), performing 16 different activities. We used accelerometers placed on wrist and ankle, and measurements of energy counts by means of indirect calorimetry. After optimization, we propose an architecture consisting of an RNN with 3 GRU layers and a feedforward network combining both accelerometer and participant-level data. Our efforts included switching mean to standard deviation for down-sampling the input data and combining temporal and static data (person-specific details such as age, weight, BMI). The resulting architecture produces accurate PAEE estimations while decreasing training input and time by a factor of 10. Subsequently, compared to the state-of-the-art, it is capable to integrate longer activity data which lead to more accurate estimations of low intensity activities EE. It can thus be employed to investigate associations of PAEE with vitality parameters of older people related to metabolic and cognitive health and mental well-being. Show less
Vermetten, D.L.; Stein, B. van; Kononova, A.V.; Caraffini, F. 2022
Differential Evolution is a popular optimisation method with a small number of parameters. However, different hyper-parameters and Differential Evolution variants such as different mutation... Show moreDifferential Evolution is a popular optimisation method with a small number of parameters. However, different hyper-parameters and Differential Evolution variants such as different mutation operators and the F and Cr parameter may introduce structural bias. Structural bias is a form of bias where artefacts in the algorithm lead to a preference to particular regions in the search space regardless of the objective function. Many algorithm configurations suffer from structural bias, but it is very hard to automatically detect it and even harder to detect what kind of structural bias is involved and what component might be the cause of it. A comprehensive study of the occurrence and type of structural bias in Differential Evolution configurations has not yet been carried out till now. In this chapter, we systematically evaluate 10980 Differential Evolution configurations on structural bias with the open-source BIAS toolbox. Using this toolbox we identify which configurations cause bias and what type of bias it is. In addition, we analyse the results to make clear recommendations on which components and parameters can be used in Differential Evolution to ensure unbiased behaviour within reasonable computational budget. Show less
Early-stage disease indications are rarely recorded in real-world domains, such as Agriculture and Healthcare, and yet, their accurate identification is critical in that point of time. In this type... Show moreEarly-stage disease indications are rarely recorded in real-world domains, such as Agriculture and Healthcare, and yet, their accurate identification is critical in that point of time. In this type of highly imbalanced classification problems, which encompass complex features, deep learning (DL) is much needed because of its strong detection capabilities. At the same time, DL is observed in practice to favor majority over minority classes and consequently suffer from inaccurate detection of the targeted early-stage indications. In this work, we extend the study done by [11], showing that the final BN layer, when placed before the softmax output layer, has a considerable impact in highly imbalanced image classification problems as well as undermines the role of the softmax outputs as an uncertainty measure. This current study addresses additional hypotheses and reports on the following findings: (i) the performance gain after adding the final BN layer in highly imbalanced settings could still be achieved after removing this additional BN layer in inference; (ii) there is a certain threshold for the imbalance ratio upon which the progress gained by the final BN layer reaches its peak; (iii) the batch size also plays a role and affects the outcome of the final BN application; (iv) the impact of the BN application is also reproducible on other datasets and when utilizing much simpler neural architectures; (v) the reported BN effect occurs only per a single majority class and multiple minority classes – i.e., no improvements are evident when there are two majority classes; and finally, (vi) utilizing this BN layer with sigmoid activation has almost no impact when dealing with a strongly imbalanced image classification tasks. Show less
Hollander, D. den; Dirkson, A.; Verberne, S.; Kraaij, W.; Oortmerssen, G. van; Gelderblom, H.; ... ; Husson, O. 2022
Scientific data analyses often combine several computational tools in automated pipelines, or workflows. Thousands of such workflows have been used in the life sciences, though their composition... Show moreScientific data analyses often combine several computational tools in automated pipelines, or workflows. Thousands of such workflows have been used in the life sciences, though their composition has remained a cumbersome manual process due to a lack of standards for annotation, assembly, and implementation. Recent technological advances have returned the long-standing vision of automated workflow composition into focus. This article summarizes a recent Lorentz Center workshop dedicated to automated composition of workflows in the life sciences. We survey previous initiatives to automate the composition process, and discuss the current state of the art and future perspectives. We start by drawing the "big picture" of the scientific workflow development life cycle, before surveying and discussing current methods, technologies and practices for semantic domain modelling, automation in workflow development, and workflow assessment. Finally, we derive a roadmap of individual and community-based actions to work toward the vision of automated workflow development in the forthcoming years. A central outcome of the workshop is a general description of the workflow life cycle in six stages: 1) scientific question or hypothesis, 2) conceptual workflow, 3) abstract workflow, 4) concrete workflow, 5) production workflow, and 6) scientific results. The transitions between stages are facilitated by diverse tools and methods, usually incorporating domain knowledge in some form. Formal semantic domain modelling is hard and often a bottleneck for the application of semantic technologies. However, life science communities have made considerable progress here in recent years and are continuously improving, renewing interest in the application of semantic technologies for workflow exploration, composition and instantiation. Combined with systematic benchmarking with reference data and large-scale deployment of production-stage workflows, such technologies enable a more systematic process of workflow development than we know today. We believe that this can lead to more robust, reusable, and sustainable workflows in the future. Show less
We provide a sound and relatively complete Hoare logic for reasoning about partial correctness of recursive procedures in presence of local variables and the call-by-value parameter mechanism and... Show moreWe provide a sound and relatively complete Hoare logic for reasoning about partial correctness of recursive procedures in presence of local variables and the call-by-value parameter mechanism and in which the correctness proofs support contracts and are linear in the length of the program. We argue that in spite of the fact that Hoare logics for recursive procedures were intensively studied, no such logic has been proposed in the literature. Show less
Neonatal sepsis is a major cause of death and disability in newborns. Commonly used biomarkers for diagnosis and evaluation of treatment response lack sufficient sensitivity or specificity.... Show moreNeonatal sepsis is a major cause of death and disability in newborns. Commonly used biomarkers for diagnosis and evaluation of treatment response lack sufficient sensitivity or specificity. Additionally, new targets to treat the dysregulated immune response are needed, as are methods to effectively screen drugs for these targets. Available research methods have hitherto not yielded the breakthroughs required to significantly improve disease outcomes, we therefore describe the potential of zebrafish (Danio rerio) larvae as preclinical model for neonatal sepsis. In biomedical research, zebrafish larvae combine the complexity of a whole organism with the convenience and high-throughput potential of in vitro methods. This paper illustrates that zebrafish exhibit an immune system that is remarkably similar to humans, both in terms of types of immune cells and signaling pathways. Moreover, the developmental state of the larval immune system is highly similar to human neonates. We provide examples of zebrafish larvae being used to study infections with pathogens commonly causing neonatal sepsis and discuss known limitations. We believe this species could expedite research into immune regulation during neonatal sepsis and may hold keys for the discovery of new biomarkers and novel treatment targets as well as for screening of targeted drug therapies. Show less
Information cascade size prediction is one of the primary challenges for understanding the diffusion of information. Traditional feature-based methods heavily rely on the quality of handcrafted... Show moreInformation cascade size prediction is one of the primary challenges for understanding the diffusion of information. Traditional feature-based methods heavily rely on the quality of handcrafted features, requiring extensive domain knowledge and hard to generalize to new domains. Recently, inspired by the success of deep learning in computer vision and natural language processing, researchers have developed neural network-based approaches for tackling this problem. However, existing deep learning-based methods either focused on modeling the temporal characteristics of cascades but ignored the structural information or failed to take the order-scale and position-scale into consideration in modeling structures of information propagation. This paper proposed a novel graph neural network-based model, called MUCas, to learn the latent representations of cascade graphs from a multi-scale perspective, which can make full use of the direction-scale, high-order-scale, position-scale, and dynamic-scale of cascades via a newly designed MUlti-scale Graph Capsule Network (MUG-Caps) and the influence-attention mechanism. Extensive experiments conducted on two real-world data sets demonstrate that our MUCas significantly outperforms the state-of-the-art approaches. Show less
Zwaard, S. van der; Koppens, T.F.P.; Weide, G.; Levels, K.; Hofmijster, M.J.; Koning, J.J. de; Jaspers, R.T. 2021
In this thesis it is posed that the central object of preference discovery is a co-creative process in which the Other can be represented by a machine. It explores efficient methods to enhance... Show moreIn this thesis it is posed that the central object of preference discovery is a co-creative process in which the Other can be represented by a machine. It explores efficient methods to enhance introverted intuition using extraverted intuition's communication lines. Possible implementations of such processes are presented using novel algorithms that perform divergent search to feed the users' intuition with many examples of high quality solutions, allowing them to take influence interactively. The machine feeds and reflects upon human intuition, combining both what is possible and preferred. The machine model and the divergent optimization algorithms are the motor behind this co-creative process, in which machine and users co-create and interactively choose branches of an ad hoc hierarchical decomposition of the solution space.The proposed co-creative process consists of several elements: a formal model for interactive co-creative processes, evolutionary divergent search, diversity and similarity, data-driven methods to discover diversity, limitations of artificial creative agents, matters of efficiency in behavioral and morphological modeling, visualization, a connection to prototype theory, and methods to allow users to influence artificial creative agents. This thesis helps putting the human back into the design loop in generative AI and optimization. Show less
In today's volatile market environments, companies must be able to continuously innovate. In this context, innovation does not only refer to the development of new products or business models but... Show moreIn today's volatile market environments, companies must be able to continuously innovate. In this context, innovation does not only refer to the development of new products or business models but often also affects the entire organization, which has to transform its structures, processes, and ways of working.Corporate entrepreneurship (CE) programs are often used by established companies to address these innovation and transformation challenges. In general, they are understood as formalized entrepreneurial activities to (1) support internal corporate ventures or (2) work with external startups. The organizational design and value creation of CE programs exhibit a high degree of heterogeneity. On the one hand, this heterogeneity makes CE programs a valuable management tool that can be used for many purposes. On the other hand, it can be seen as a reason for the current challenges that companies experience in effectively using and managing CE programs.By systematically analyzing 54 different cases in established companies in Germany, Switzerland, and Austria, this study contributes to a better understanding of the heterogeneity of CE programs. The taxonomic approach provides clearly defined types of CE programs that are distinguished according to their organizational design and the outputs they generate. Show less
