@article{GenskeJahnke2022, author = {Genske, Ulrich and Jahnke, Paul}, title = {Human observer net}, series = {Radiology}, volume = {303}, journal = {Radiology}, number = {3}, publisher = {Radiologgical soc North America (RSNA)}, address = {Oak brook}, issn = {0033-8419}, doi = {10.1148/radiol.211832}, pages = {524 -- 530}, year = {2022}, abstract = {Background: Current software applications for human observer studies of images lack flexibility in study design, platform independence, multicenter use, and assessment methods and are not open source, limiting accessibility and expandability. Purpose: To develop a user-friendly software platform that enables efficient human observer studies in medical imaging with flexibility of study design. Materials and Methods: Software for human observer imaging studies was designed as an open-source web application to facilitate access, platform-independent usability, and multicenter studies. Different interfaces for study creation, participation, and management of results were implemented. The software was evaluated in human observer experiments between May 2019 and March 2021, in which duration of observer responses was tracked. Fourteen radiologists evaluated and graded software usability using the 100-point system usability scale. The application was tested in Chrome, Firefox, Safari, and Edge browsers. Results: Software function was designed to allow visual grading analysis (VGA), multiple-alternative forced-choice (m-AFC), receiver operating characteristic (ROC), localization ROC, free-response ROC, and customized designs. The mean duration of reader responses per image or per image set was 6.2 seconds 6 4.8 (standard deviation), 5.8 seconds 6 4.7, 8.7 seconds 6 5.7, and 6.0 seconds 6 4.5 in four-AFC with 160 image quartets per reader, four-AFC with 640 image quartets per reader, localization ROC, and experimental studies, respectively. The mean system usability scale score was 83 6 11 (out of 100). The documented code and a demonstration of the application are available online (https://github.com/genskeu/HON, https://hondemo.pythonanywhere.com/). Conclusion: A user-friendly and efficient open-source application was developed for human reader experiments that enables study design versatility, as well as platform-independent and multicenter usability.}, language = {en} } @article{PuriVardeMelo2023, author = {Puri, Manish and Varde, Aparna S. and Melo, Gerard de}, title = {Commonsense based text mining on urban policy}, series = {Language resources and evaluation}, volume = {57}, journal = {Language resources and evaluation}, publisher = {Springer}, address = {Dordrecht [u.a.]}, issn = {1574-020X}, doi = {10.1007/s10579-022-09584-6}, pages = {733 -- 763}, year = {2023}, abstract = {Local laws on urban policy, i.e., ordinances directly affect our daily life in various ways (health, business etc.), yet in practice, for many citizens they remain impervious and complex. This article focuses on an approach to make urban policy more accessible and comprehensible to the general public and to government officials, while also addressing pertinent social media postings. Due to the intricacies of the natural language, ranging from complex legalese in ordinances to informal lingo in tweets, it is practical to harness human judgment here. To this end, we mine ordinances and tweets via reasoning based on commonsense knowledge so as to better account for pragmatics and semantics in the text. Ours is pioneering work in ordinance mining, and thus there is no prior labeled training data available for learning. This gap is filled by commonsense knowledge, a prudent choice in situations involving a lack of adequate training data. The ordinance mining can be beneficial to the public in fathoming policies and to officials in assessing policy effectiveness based on public reactions. This work contributes to smart governance, leveraging transparency in governing processes via public involvement. We focus significantly on ordinances contributing to smart cities, hence an important goal is to assess how well an urban region heads towards a smart city as per its policies mapping with smart city characteristics, and the corresponding public satisfaction.}, language = {en} } @article{BonnetDongNaumannetal.2021, author = {Bonnet, Philippe and Dong, Xin Luna and Naumann, Felix and T{\"o}z{\"u}n, P{\i}nar}, title = {VLDB 2021}, series = {SIGMOD record}, volume = {50}, journal = {SIGMOD record}, number = {4}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {0163-5808}, pages = {50 -- 53}, year = {2021}, abstract = {The 47th International Conference on Very Large Databases (VLDB'21) was held on August 16-20, 2021 as a hybrid conference. It attracted 180 in-person attendees in Copenhagen and 840 remote attendees. In this paper, we describe our key decisions as general chairs and program committee chairs and share the lessons we learned.}, language = {en} } @article{HagedornSerthMeinel2023, author = {Hagedorn, Christiane and Serth, Sebastian and Meinel, Christoph}, title = {The mysterious adventures of Detective Duke}, series = {Frontiers in education}, volume = {7}, journal = {Frontiers in education}, publisher = {Frontiers Media}, address = {Lausanne}, issn = {2504-284X}, doi = {10.3389/feduc.2022.1016401}, pages = {22}, year = {2023}, abstract = {About 15 years ago, the first Massive Open Online Courses (MOOCs) appeared and revolutionized online education with more interactive and engaging course designs. Yet, keeping learners motivated and ensuring high satisfaction is one of the challenges today's course designers face. Therefore, many MOOC providers employed gamification elements that only boost extrinsic motivation briefly and are limited to platform support. In this article, we introduce and evaluate a gameful learning design we used in several iterations on computer science education courses. For each of the courses on the fundamentals of the Java programming language, we developed a self-contained, continuous story that accompanies learners through their learning journey and helps visualize key concepts. Furthermore, we share our approach to creating the surrounding story in our MOOCs and provide a guideline for educators to develop their own stories. Our data and the long-term evaluation spanning over four Java courses between 2017 and 2021 indicates the openness of learners toward storified programming courses in general and highlights those elements that had the highest impact. While only a few learners did not like the story at all, most learners consumed the additional story elements we provided. However, learners' interest in influencing the story through majority voting was negligible and did not show a considerable positive impact, so we continued with a fixed story instead. We did not find evidence that learners just participated in the narrative because they worked on all materials. Instead, for 10-16\% of learners, the story was their main course motivation. We also investigated differences in the presentation format and concluded that several longer audio-book style videos were most preferred by learners in comparison to animated videos or different textual formats. Surprisingly, the availability of a coherent story embedding examples and providing a context for the practical programming exercises also led to a slightly higher ranking in the perceived quality of the learning material (by 4\%). With our research in the context of storified MOOCs, we advance gameful learning designs, foster learner engagement and satisfaction in online courses, and help educators ease knowledge transfer for their learners.}, language = {en} } @phdthesis{Halfpap2024, author = {Halfpap, Stefan}, title = {Integer linear programming-based heuristics for partially replicated database clusters and selecting indexes}, doi = {10.25932/publishup-63361}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-633615}, school = {Universit{\"a}t Potsdam}, pages = {iii, 185}, year = {2024}, abstract = {Column-oriented database systems can efficiently process transactional and analytical queries on a single node. However, increasing or peak analytical loads can quickly saturate single-node database systems. Then, a common scale-out option is using a database cluster with a single primary node for transaction processing and read-only replicas. Using (the naive) full replication, queries are distributed among nodes independently of the accessed data. This approach is relatively expensive because all nodes must store all data and apply all data modifications caused by inserts, deletes, or updates. In contrast to full replication, partial replication is a more cost-efficient implementation: Instead of duplicating all data to all replica nodes, partial replicas store only a subset of the data while being able to process a large workload share. Besides lower storage costs, partial replicas enable (i) better scaling because replicas must potentially synchronize only subsets of the data modifications and thus have more capacity for read-only queries and (ii) better elasticity because replicas have to load less data and can be set up faster. However, splitting the overall workload evenly among the replica nodes while optimizing the data allocation is a challenging assignment problem. The calculation of optimized data allocations in a partially replicated database cluster can be modeled using integer linear programming (ILP). ILP is a common approach for solving assignment problems, also in the context of database systems. Because ILP is not scalable, existing approaches (also for calculating partial allocations) often fall back to simple (e.g., greedy) heuristics for larger problem instances. Simple heuristics may work well but can lose optimization potential. In this thesis, we present optimal and ILP-based heuristic programming models for calculating data fragment allocations for partially replicated database clusters. Using ILP, we are flexible to extend our models to (i) consider data modifications and reallocations and (ii) increase the robustness of allocations to compensate for node failures and workload uncertainty. We evaluate our approaches for TPC-H, TPC-DS, and a real-world accounting workload and compare the results to state-of-the-art allocation approaches. Our evaluations show significant improvements for varied allocation's properties: Compared to existing approaches, we can, for example, (i) almost halve the amount of allocated data, (ii) improve the throughput in case of node failures and workload uncertainty while using even less memory, (iii) halve the costs of data modifications, and (iv) reallocate less than 90\% of data when adding a node to the cluster. Importantly, we can calculate the corresponding ILP-based heuristic solutions within a few seconds. Finally, we demonstrate that the ideas of our ILP-based heuristics are also applicable to the index selection problem.}, language = {en} } @article{BlaesiusFriedrichLischeidetal.2022, author = {Bl{\"a}sius, Thomas and Friedrich, Tobias and Lischeid, Julius and Meeks, Kitty and Schirneck, Friedrich Martin}, title = {Efficiently enumerating hitting sets of hypergraphs arising in data profiling}, series = {Journal of computer and system sciences : JCSS}, volume = {124}, journal = {Journal of computer and system sciences : JCSS}, publisher = {Elsevier}, address = {San Diego}, issn = {0022-0000}, doi = {10.1016/j.jcss.2021.10.002}, pages = {192 -- 213}, year = {2022}, abstract = {The transversal hypergraph problem asks to enumerate the minimal hitting sets of a hypergraph. If the solutions have bounded size, Eiter and Gottlob [SICOMP'95] gave an algorithm running in output-polynomial time, but whose space requirement also scales with the output. We improve this to polynomial delay and space. Central to our approach is the extension problem, deciding for a set X of vertices whether it is contained in any minimal hitting set. We show that this is one of the first natural problems to be W[3]-complete. We give an algorithm for the extension problem running in time O(m(vertical bar X vertical bar+1) n) and prove a SETH-lower bound showing that this is close to optimal. We apply our enumeration method to the discovery problem of minimal unique column combinations from data profiling. Our empirical evaluation suggests that the algorithm outperforms its worst-case guarantees on hypergraphs stemming from real-world databases.}, language = {en} } @article{SchlosserChenavazDimitrov2021, author = {Schlosser, Rainer and Chenavaz, R{\´e}gis Y. and Dimitrov, Stanko}, title = {Circular economy}, series = {International journal of production economics}, volume = {236}, journal = {International journal of production economics}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0925-5273}, doi = {10.1016/j.ijpe.2021.108117}, pages = {13}, year = {2021}, abstract = {In a circular economy, the use of recycled resources in production is a key performance indicator for management. Yet, academic studies are still unable to inform managers on appropriate recycling and pricing policies. We develop an optimal control model integrating a firm's recycling rate, which can use both virgin and recycled resources in the production process. Our model accounts for recycling influence both at the supply- and demandsides. The positive effect of a firm's use of recycled resources diminishes over time but may increase through investments. Using general formulations for demand and cost, we analytically examine joint dynamic pricing and recycling investment policies in order to determine their optimal interplay over time. We provide numerical experiments to assess the existence of a steady-state and to calculate sensitivity analyses with respect to various model parameters. The analysis shows how to dynamically adapt jointly optimized controls to reach sustainability in the production process. Our results pave the way to sounder sustainable practices for firms operating within a circular economy.}, language = {en} } @article{ThienenWeinsteinMeinel2023, author = {Thienen, Julia von and Weinstein, Theresa Julia and Meinel, Christoph}, title = {Creative metacognition in design thinking}, series = {Frontiers in psychology}, volume = {14}, journal = {Frontiers in psychology}, publisher = {Frontiers Research Foundation}, address = {Lausanne}, issn = {1664-1078}, doi = {10.3389/fpsyg.2023.1157001}, pages = {20}, year = {2023}, abstract = {Design thinking is a well-established practical and educational approach to fostering high-level creativity and innovation, which has been refined since the 1950s with the participation of experts like Joy Paul Guilford and Abraham Maslow. Through real-world projects, trainees learn to optimize their creative outcomes by developing and practicing creative cognition and metacognition. This paper provides a holistic perspective on creativity, enabling the formulation of a comprehensive theoretical framework of creative metacognition. It focuses on the design thinking approach to creativity and explores the role of metacognition in four areas of creativity expertise: Products, Processes, People, and Places. The analysis includes task-outcome relationships (product metacognition), the monitoring of strategy effectiveness (process metacognition), an understanding of individual or group strengths and weaknesses (people metacognition), and an examination of the mutual impact between environments and creativity (place metacognition). It also reviews measures taken in design thinking education, including a distribution of cognition and metacognition, to support students in their development of creative mastery. On these grounds, we propose extended methods for measuring creative metacognition with the goal of enhancing comprehensive assessments of the phenomenon. Proposed methodological advancements include accuracy sub-scales, experimental tasks where examinees explore problem and solution spaces, combinations of naturalistic observations with capability testing, as well as physiological assessments as indirect measures of creative metacognition.}, language = {en} } @article{BelaidRabusKrestel2021, author = {Belaid, Mohamed Karim and Rabus, Maximilian and Krestel, Ralf}, title = {CrashNet}, series = {Data mining and knowledge discovery}, volume = {35}, journal = {Data mining and knowledge discovery}, number = {4}, publisher = {Springer}, address = {Dordrecht}, issn = {1384-5810}, doi = {10.1007/s10618-021-00761-9}, pages = {1688 -- 1709}, year = {2021}, abstract = {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.}, language = {en} } @misc{BensonMakaitRabl2021, author = {Benson, Lawrence and Makait, Hendrik and Rabl, Tilmann}, title = {Viper}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {9}, issn = {2150-8097}, doi = {10.25932/publishup-55966}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-559664}, pages = {15}, year = {2021}, abstract = {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.}, language = {en} }