Refine
Year of publication
- 2021 (65) (remove)
Document Type
- Article (40)
- Doctoral Thesis (13)
- Monograph/Edited Volume (6)
- Postprint (5)
- Conference Proceeding (1)
Language
- English (65)
Keywords
- MOOC (3)
- blockchain (3)
- business process management (3)
- machine learning (3)
- smart contracts (3)
- 3D-Visualisierung (2)
- Feature selection (2)
- Gene expression (2)
- OptoGait (2)
- Prior knowledge (2)
Institute
- Hasso-Plattner-Institut für Digital Engineering GmbH (65) (remove)
Anomaly detection in process mining aims to recognize outlying or unexpected behavior in event logs for purposes such as the removal of noise and identification of conformance violations. Existing techniques for this task are primarily frequency-based, arguing that behavior is anomalous because it is uncommon. However, such techniques ignore the semantics of recorded events and, therefore, do not take the meaning of potential anomalies into consideration. In this work, we overcome this caveat and focus on the detection of anomalies from a semantic perspective, arguing that anomalies can be recognized when process behavior does not make sense. To achieve this, we propose an approach that exploits the natural language associated with events. Our key idea is to detect anomalous process behavior by identifying semantically inconsistent execution patterns. To detect such patterns, we first automatically extract business objects and actions from the textual labels of events. We then compare these against a process-independent knowledge base. By populating this knowledge base with patterns from various kinds of resources, our approach can be used in a range of contexts and domains. We demonstrate the capability of our approach to successfully detect semantic execution anomalies through an evaluation based on a set of real-world and synthetic event logs and show the complementary nature of semantics-based anomaly detection to existing frequency-based techniques.
The noble way to substantiate decisions that affect many people is to ask these people for their opinions. For governments that run whole countries, this means asking all citizens for their views to consider their situations and needs.
Organizations such as Africa's Voices Foundation, who want to facilitate communication between decision-makers and citizens of a country, have difficulty mediating between these groups. To enable understanding, statements need to be summarized and visualized. Accomplishing these goals in a way that does justice to the citizens' voices and situations proves challenging. Standard charts do not help this cause as they fail to create empathy for the people behind their graphical abstractions. Furthermore, these charts do not create trust in the data they are representing as there is no way to see or navigate back to the underlying code and the original data. To fulfill these functions, visualizations would highly benefit from interactions to explore the displayed data, which standard charts often only limitedly provide.
To help improve the understanding of people's voices, we developed and categorized 80 ideas for new visualizations, new interactions, and better connections between different charts, which we present in this report. From those ideas, we implemented 10 prototypes and two systems that integrate different visualizations. We show that this integration allows consistent appearance and behavior of visualizations. The visualizations all share the same main concept: representing each individual with a single dot. To realize this idea, we discuss technologies that efficiently allow the rendering of a large number of these dots. With these visualizations, direct interactions with representations of individuals are achievable by clicking on them or by dragging a selection around them. This direct interaction is only possible with a bidirectional connection from the visualization to the data it displays. We discuss different strategies for bidirectional mappings and the trade-offs involved. Having unified behavior across visualizations enhances exploration. For our prototypes, that includes grouping, filtering, highlighting, and coloring of dots. Our prototyping work was enabled by the development environment Lively4. We explain which parts of Lively4 facilitated our prototyping process. Finally, we evaluate our approach to domain problems and our developed visualization concepts.
Our work provides inspiration and a starting point for visualization development in this domain. Our visualizations can improve communication between citizens and their government and motivate empathetic decisions. Our approach, combining low-level entities to create visualizations, provides value to an explorative and empathetic workflow. We show that the design space for visualizing this kind of data has a lot of potential and that it is possible to combine qualitative and quantitative approaches to data analysis.
In recent years, computer vision algorithms based on machine learning have seen rapid development. In the past, research mostly focused on solving computer vision problems such as image classification or object detection on images displaying natural scenes. Nowadays other fields such as the field of cultural heritage, where an abundance of data is available, also get into the focus of research. In the line of current research endeavours, we collaborated with the Getty Research Institute which provided us with a challenging dataset, containing images of paintings and drawings. In this technical report, we present the results of the seminar "Deep Learning for Computer Vision". In this seminar, students of the Hasso Plattner Institute evaluated state-of-the-art approaches for image classification, object detection and image recognition on the dataset of the Getty Research Institute. The main challenge when applying modern computer vision methods to the available data is the availability of annotated training data, as the dataset provided by the Getty Research Institute does not contain a sufficient amount of annotated samples for the training of deep neural networks. However, throughout the report we show that it is possible to achieve satisfying to very good results, when using further publicly available datasets, such as the WikiArt dataset, for the training of machine learning models.
Confidence Counts
(2021)
The increasing reliance on online learning in higher education has been further expedited by the on-going Covid-19 pandemic. Students need to be supported as they adapt to this new learning environment. Research has established that learners with positive online learning self-efficacy beliefs are more likely to persevere and achieve their higher education goals when learning online. In this paper, we explore how MOOC design can contribute to the four sources of self-efficacy beliefs posited by Bandura [4]. Specifically, we will explore, drawing on learner reflections, whether design elements of the MOOC, The Digital Edge: Essentials for the Online Learner, provided participants with the necessary mastery experiences, vicarious experiences, verbal persuasion, and affective regulation opportunities, to evaluate and develop their online learning self-efficacy beliefs. Findings from a content analysis of discussion forum posts show that learners referenced three of the four information sources when reflecting on their experience of the MOOC. This paper illustrates the potential of MOOCs as a pedagogical tool for enhancing online learning self-efficacy among students.
CrashNet
(2021)
Destructive car crash tests are an elaborate, time-consuming, and expensive necessity of the automotive development process. Today, finite element method (FEM) simulations are used to reduce costs by simulating car crashes computationally. We propose CrashNet, an encoder-decoder deep neural network architecture that reduces costs further and models specific outcomes of car crashes very accurately. We achieve this by formulating car crash events as time series prediction enriched with a set of scalar features. Traditional sequence-to-sequence models are usually composed of convolutional neural network (CNN) and CNN transpose layers. We propose to concatenate those with an MLP capable of learning how to inject the given scalars into the output time series. In addition, we replace the CNN transpose with 2D CNN transpose layers in order to force the model to process the hidden state of the set of scalars as one time series. The proposed CrashNet model can be trained efficiently and is able to process scalars and time series as input in order to infer the results of crash tests. CrashNet produces results faster and at a lower cost compared to destructive tests and FEM simulations. Moreover, it represents a novel approach in the car safety management domain.
Viper
(2021)
Key-value stores (KVSs) have found wide application in modern software systems. For persistence, their data resides in slow secondary storage, which requires KVSs to employ various techniques to increase their read and write performance from and to the underlying medium. Emerging persistent memory (PMem) technologies offer data persistence at close-to-DRAM speed, making them a promising alternative to classical disk-based storage. However, simply drop-in replacing existing storage with PMem does not yield good results, as block-based access behaves differently in PMem than on disk and ignores PMem's byte addressability, layout, and unique performance characteristics. In this paper, we propose three PMem-specific access patterns and implement them in a hybrid PMem-DRAM KVS called Viper. We employ a DRAM-based hash index and a PMem-aware storage layout to utilize the random-write speed of DRAM and efficient sequential-write performance PMem. Our evaluation shows that Viper significantly outperforms existing KVSs for core KVS operations while providing full data persistence. Moreover, Viper outperforms existing PMem-only, hybrid, and disk-based KVSs by 4-18x for write workloads, while matching or surpassing their get performance.
Viper
(2021)
Key-value stores (KVSs) have found wide application in modern software systems. For persistence, their data resides in slow secondary storage, which requires KVSs to employ various techniques to increase their read and write performance from and to the underlying medium. Emerging persistent memory (PMem) technologies offer data persistence at close-to-DRAM speed, making them a promising alternative to classical disk-based storage. However, simply drop-in replacing existing storage with PMem does not yield good results, as block-based access behaves differently in PMem than on disk and ignores PMem's byte addressability, layout, and unique performance characteristics. In this paper, we propose three PMem-specific access patterns and implement them in a hybrid PMem-DRAM KVS called Viper. We employ a DRAM-based hash index and a PMem-aware storage layout to utilize the random-write speed of DRAM and efficient sequential-write performance PMem. Our evaluation shows that Viper significantly outperforms existing KVSs for core KVS operations while providing full data persistence. Moreover, Viper outperforms existing PMem-only, hybrid, and disk-based KVSs by 4-18x for write workloads, while matching or surpassing their get performance.
TransPipe
(2021)
Online learning environments, such as Massive Open Online Courses (MOOCs), often rely on videos as a major component to convey knowledge. However, these videos exclude potential participants who do not understand the lecturer’s language, regardless of whether that is due to language unfamiliarity or aural handicaps. Subtitles and/or interactive transcripts solve this issue, ease navigation based on the content, and enable indexing and retrieval by search engines. Although there are several automated speech-to-text converters and translation tools, their quality varies and the process of integrating them can be quite tedious. Thus, in practice, many videos on MOOC platforms only receive subtitles after the course is already finished (if at all) due to a lack of resources. This work describes an approach to tackle this issue by providing a dedicated tool, which is closing this gap between MOOC platforms and transcription and translation tools and offering a simple workflow that can easily be handled by users with a less technical background. The proposed method is designed and evaluated by qualitative interviews with three major MOOC providers.
Learning During COVID-19
(2021)
During the COVID-19 pandemic, learning in higher education and beyond shifted en masse to online formats, with the short- and long-term consequences for Massive Open Online Course (MOOC) platforms, learners, and creators still under evaluation. In this paper, we sought to determine whether the COVID-19 pandemic and this shift to online learning led to increased learner engagement and attainment in a single introductory biology MOOC through evaluating enrollment, proportional and individual engagement, and verification and performance data. As this MOOC regularly operates each year, we compared these data collected from two course runs during the pandemic to three pre-pandemic runs. During the first pandemic run, the number and rate of learners enrolling in the course doubled when compared to prior runs, while the second pandemic run indicated a gradual return to pre-pandemic enrollment. Due to higher enrollment, more learners viewed videos, attempted problems, and posted to the discussion forums during the pandemic. Participants engaged with forums in higher proportions in both pandemic runs, but the proportion of participants who viewed videos decreased in the second pandemic run relative to the prior runs. A higher percentage of learners chose to pursue a certificate via the verified track in each pandemic run, though a smaller proportion earned certification in the second pandemic run. During the pandemic, more enrolled learners did not necessarily correlate to greater engagement by all metrics. While verified-track learner performance varied widely during each run, the effects of the pandemic were not uniform for learners, much like in other aspects of life. As such, individual engagement trends in the first pandemic run largely resemble pre-pandemic metrics but with more learners overall, while engagement trends in the second pandemic run are less like pre-pandemic metrics, hinting at learner “fatigue”. This study serves to highlight the life-long learning opportunity that MOOCs offer is even more critical when traditional education modes are disrupted and more people are at home or unemployed. This work indicates that this boom in MOOC participation may not remain at a high level for the longer term in any one course, but overall, the number of MOOCs, programs, and learners continues to grow.
MOOCs have been produced using a variety of instructional design approaches and frameworks. This paper presents experiences from the instructional approach based on the ADDIE model applied to designing and producing MOOCs in the Erasmus+ strategic partnership on Open Badge Ecosystem for Research Data Management (OBERRED). Specifically, this paper describes the case study of the production of the MOOC “Open Badges for Open Science”, delivered on the European MOOC platform EMMA. The key goal of this MOOC is to help learners develop a capacity to use Open Badges in the field of Research Data Management (RDM). To produce the MOOC, the ADDIE model was applied as a generic instructional design model and a systematic approach to the design and development following the five design phases: Analysis, Design, Development, Implementation, Evaluation. This paper outlines the MOOC production including methods, templates and tools used in this process including the interactive micro-content created with H5P in form of Open Educational Resources and digital credentials created with Open Badges and issued to MOOC participants upon successful completion of MOOC levels. The paper also outlines the results from qualitative evaluation, which applied the cognitive walkthrough methodology to elicit user requirements. The paper ends with conclusions about pros and cons of using the ADDIE model in MOOC production and formulates recommendations for further work in this area.
The COVID-19 pandemic emergency has forced a profound reshape of our lives. Our way of working and studying has been disrupted with the result of an acceleration of the shift to the digital world. To properly adapt to this change, we need to outline and implement new urgent strategies and approaches which put learning at the center, supporting workers and students to further develop “future proof” skills. In the last period, universities and educational institutions have demonstrated that they can play an important role in this context, also leveraging on the potential of Massive Open Online Courses (MOOCs) which proved to be an important vehicle of flexibility and adaptation in a general context characterised by several constraints. From March 2020 till now, we have witnessed an exponential growth of MOOCs enrollments numbers, with “traditional” students interested in different topics not necessarily integrated to their curricular studies. To support students and faculty development during the spreading of the pandemic, Politecnico di Milano focused on one main dimension: faculty development for a better integration of digital tools and contents in the e-learning experience. The current discussion focuses on how to improve the integration of MOOCs in the in-presence activities to create meaningful learning and teaching experiences, thereby leveraging blended learning approaches to engage both students and external stakeholders to equip them with future job relevance skills.
In the field of Business Process Management (BPM), modeling business processes and related data is a critical issue since process activities need to manage data stored in databases. The connection between processes and data is usually handled at the implementation level, even if modeling both processes and data at the conceptual level should help designers in improving business process models and identifying requirements for implementation. Especially in data -and decision-intensive contexts, business process activities need to access data stored both in databases and data warehouses. In this paper, we complete our approach for defining a novel conceptual view that bridges process activities and data. The proposed approach allows the designer to model the connection between business processes and database models and define the operations to perform, providing interesting insights on the overall connected perspective and hints for identifying activities that are crucial for decision support.
In the context of the Fostering Women to STEM MOOCs (FOSTWOM) project, we present here the general ideas of a gender balance Toolkit, i.e. a collection of recommendations and resources for instructional designers, visual designers, and teaching staff to apply while designing and preparing storyboards for MOOCs and their visual components, so that future STEM online courses have a greater chance to be more inclusive and gender-balanced. Overall, The FOSTWOM project intends to use the inclusive potential of Massive Open Online Courses to propose STEM subjects free of stereotyping assumptions on gender abilities. Moreover, the consortium is interested in attracting girls and young women to science and technology careers, through accessible online content, which can include role models’ interviews, relevant real-world situations, and strong conceptual frameworks.
Universitat Politècnica de València’s Experience with EDX MOOC Initiatives During the Covid Lockdown
(2021)
In March 2020, when massive lockdowns started to be enforced around the world to contain the spread of the COVID-19 pandemic, edX launched two initiatives to help students around the world providing free certificates for its courses, RAP, for member institutions and OCE, for any accredited academic institution. In this paper we analyze how Universitat Poltècnica de València contributed with its courses to both initiatives, providing almost 14,000 free certificate codes in total, and how UPV used the RAP initiative as a customer, describing the mechanism used to distribute more than 22,000 codes for free certificates to more than 7,000 UPV community members, what led to the achievement of more than 5,000 free certificates. We also comment the results of a post initiative survey answered by 1,612 UPV members about 3,241 edX courses, in which they communicated a satisfaction of 4,69 over 5 with the initiative.
An ever-increasing number of prediction models is published every year in different medical specialties. Prognostic or diagnostic in nature, these models support medical decision making by utilizing one or more items of patient data to predict outcomes of interest, such as mortality or disease progression. While different computer tools exist that support clinical predictive modeling, I observed that the state of the art is lacking in the extent to which the needs of research clinicians are addressed. When it comes to model development, current support tools either 1) target specialist data engineers, requiring advanced coding skills, or 2) cater to a general-purpose audience, therefore not addressing the specific needs of clinical researchers. Furthermore, barriers to data access across institutional silos, cumbersome model reproducibility and extended experiment-to-result times significantly hampers validation of existing models. Similarly, without access to interpretable explanations, which allow a given model to be fully scrutinized, acceptance of machine learning approaches will remain limited. Adequate tool support, i.e., a software artifact more targeted at the needs of clinical modeling, can help mitigate the challenges identified with respect to model development, validation and interpretation. To this end, I conducted interviews with modeling practitioners in health care to better understand the modeling process itself and ascertain in what aspects adequate tool support could advance the state of the art. The functional and non-functional requirements identified served as the foundation for a software artifact that can be used for modeling outcome and risk prediction in health research. To establish the appropriateness of this approach, I implemented a use case study in the Nephrology domain for acute kidney injury, which was validated in two different hospitals. Furthermore, I conducted user evaluation to ascertain whether such an approach provides benefits compared to the state of the art and the extent to which clinical practitioners could benefit from it. Finally, when updating models for external validation, practitioners need to apply feature selection approaches to pinpoint the most relevant features, since electronic health records tend to contain several candidate predictors. Building upon interpretability methods, I developed an explanation-driven recursive feature elimination approach. This method was comprehensively evaluated against state-of-the art feature selection methods. Therefore, this thesis' main contributions are three-fold, namely, 1) designing and developing a software artifact tailored to the specific needs of the clinical modeling domain, 2) demonstrating its application in a concrete case in the Nephrology context and 3) development and evaluation of a new feature selection approach applicable in a validation context that builds upon interpretability methods. In conclusion, I argue that appropriate tooling, which relies on standardization and parametrization, can support rapid model prototyping and collaboration between clinicians and data scientists in clinical predictive modeling.
Despite advances in machine learning-based clinical prediction models, only few of such models are actually deployed in clinical contexts. Among other reasons, this is due to a lack of validation studies. In this paper, we present and discuss the validation results of a machine learning model for the prediction of acute kidney injury in cardiac surgery patients initially developed on the MIMIC-III dataset when applied to an external cohort of an American research hospital. To help account for the performance differences observed, we utilized interpretability methods based on feature importance, which allowed experts to scrutinize model behavior both at the global and local level, making it possible to gain further insights into why it did not behave as expected on the validation cohort. The knowledge gleaned upon derivation can be potentially useful to assist model update during validation for more generalizable and simpler models. We argue that interpretability methods should be considered by practitioners as a further tool to help explain performance differences and inform model update in validation studies.
Peer assessment in MOOCs
(2021)
We report on a systematic review of the landscape of peer assessment in massive open online courses (MOOCs) with papers from 2014 to 2020 in 20 leading education technology publication venues across four databases containing education technology-related papers, addressing three research issues: the evolution of peer assessment in MOOCs during the period 2014 to 2020, the methods used in MOOCs to assess peers, and the challenges of and future directions in MOOC peer assessment. We provide summary statistics and a review of methods across the corpus and highlight three directions for improving the use of peer assessment in MOOCs: the need for focusing on scaling learning through peer evaluations, the need for scaling and optimizing team submissions in team peer assessments, and the need for embedding a social process for peer assessment.
Massive Open Online Courses (MOOCs) offer online courses at low cost for anyone with an internet access. At its early days, the MOOC movement raised the flag of democratizing education, but soon enough, this utopian idea collided with the need to find sustainable business models. Moving from open access to a new financially sustainable certification and monetization policy in December 2015 we aim at this change-point and observe the completion rates before and after this monetary change. In this study we investigate the impact of the change on learners from countries of different development status. Our findings suggest that this change has lowered the completion rates among learners from developing countries, increasing gaps that already existed between global learners from countries of low and high development status. This suggests that more inclusive monetization policies may help MOOCs benefits to spread more equally among global learners.