@article{MichallekGenskeNiehuesetal.2022, author = {Michallek, Florian and Genske, Ulrich and Niehues, Stefan Markus and Hamm, Bernd and Jahnke, Paul}, title = {Deep learning reconstruction improves radiomics feature stability and discriminative power in abdominal CT imaging}, series = {European Radiology}, volume = {32}, journal = {European Radiology}, number = {7}, publisher = {Springer}, address = {New York}, issn = {0938-7994}, doi = {10.1007/s00330-022-08592-y}, pages = {4587 -- 4595}, year = {2022}, abstract = {Objectives To compare image quality of deep learning reconstruction (AiCE) for radiomics feature extraction with filtered back projection (FBP), hybrid iterative reconstruction (AIDR 3D), and model-based iterative reconstruction (FIRST). Methods Effects of image reconstruction on radiomics features were investigated using a phantom that realistically mimicked a 65-year-old patient's abdomen with hepatic metastases. The phantom was scanned at 18 doses from 0.2 to 4 mGy, with 20 repeated scans per dose. Images were reconstructed with FBP, AIDR 3D, FIRST, and AiCE. Ninety-three radiomics features were extracted from 24 regions of interest, which were evenly distributed across three tissue classes: normal liver, metastatic core, and metastatic rim. Features were analyzed in terms of their consistent characterization of tissues within the same image (intraclass correlation coefficient >= 0.75), discriminative power (Kruskal-Wallis test p value < 0.05), and repeatability (overall concordance correlation coefficient >= 0.75). Results The median fraction of consistent features across all doses was 6\%, 8\%, 6\%, and 22\% with FBP, AIDR 3D, FIRST, and AiCE, respectively. Adequate discriminative power was achieved by 48\%, 82\%, 84\%, and 92\% of features, and 52\%, 20\%, 17\%, and 39\% of features were repeatable, respectively. Only 5\% of features combined consistency, discriminative power, and repeatability with FBP, AIDR 3D, and FIRST versus 13\% with AiCE at doses above 1 mGy and 17\% at doses >= 3 mGy. AiCE was the only reconstruction technique that enabled extraction of higher-order features. Conclusions AiCE more than doubled the yield of radiomics features at doses typically used clinically. Inconsistent tissue characterization within CT images contributes significantly to the poor stability of radiomics features.}, language = {en} } @phdthesis{Hecher2021, author = {Hecher, Markus}, title = {Advanced tools and methods for treewidth-based problem solving}, doi = {10.25932/publishup-51251}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-512519}, school = {Universit{\"a}t Potsdam}, pages = {xv, 184}, year = {2021}, abstract = {In the last decades, there was a notable progress in solving the well-known Boolean satisfiability (Sat) problem, which can be witnessed by powerful Sat solvers. One of the reasons why these solvers are so fast are structural properties of instances that are utilized by the solver's interna. This thesis deals with the well-studied structural property treewidth, which measures the closeness of an instance to being a tree. In fact, there are many problems parameterized by treewidth that are solvable in polynomial time in the instance size when parameterized by treewidth. In this work, we study advanced treewidth-based methods and tools for problems in knowledge representation and reasoning (KR). Thereby, we provide means to establish precise runtime results (upper bounds) for canonical problems relevant to KR. Then, we present a new type of problem reduction, which we call decomposition-guided (DG) that allows us to precisely monitor the treewidth when reducing from one problem to another problem. This new reduction type will be the basis for a long-open lower bound result for quantified Boolean formulas and allows us to design a new methodology for establishing runtime lower bounds for problems parameterized by treewidth. Finally, despite these lower bounds, we provide an efficient implementation of algorithms that adhere to treewidth. Our approach finds suitable abstractions of instances, which are subsequently refined in a recursive fashion, and it uses Sat solvers for solving subproblems. It turns out that our resulting solver is quite competitive for two canonical counting problems related to Sat.}, language = {en} } @article{BuechnerDosdall2021, author = {B{\"u}chner, Stefanie and Dosdall, Henrik}, title = {Organisation und Algorithmus}, series = {K{\"o}lner Zeitschrift f{\"u}r Soziologie und Sozialpsychologie : KZfSS}, volume = {73}, journal = {K{\"o}lner Zeitschrift f{\"u}r Soziologie und Sozialpsychologie : KZfSS}, number = {Suppl. 1}, publisher = {Springer VS}, address = {Wiesbaden}, issn = {0023-2653}, doi = {10.1007/s11577-021-00752-0}, pages = {333 -- 357}, year = {2021}, abstract = {This article analyzes how organizations endow algorithms, which we understand as digital formats of observation, with agency, thus rendering them actionable. Our main argument is that the relevance of digital observation formats results from how organizations embed them in their decision architectures. We demonstrate this using the example of the Austrian Public Employment Service (AMS), which introduced an algorithm in 2018 to evaluate the chances of unemployed persons being reintegrated in the labor market. In this regard, the AMS algorithm serves as an exemplary case for the current trend among public organizations to harness algorithms for distributing limited resources in a purportedly more efficient way. To reconstruct how this is achieved, we delineate how the AMS algorithm categorizes, compares, and evaluates persons. Building on this, we demonstrate how the algorithmic model is integrated into the organizational decision architecture and thereby made actionable. In conclusion, algorithmic models like the AMS algorithm also pose a challenge for organizations because they mute chances for realizing organizational learning. We substantiate this argument with regard to the role of coproduction and the absence of clear causality in the field of (re)integrating unemployed persons in the labor market.}, language = {de} } @article{LongdeMeloHeetal.2020, author = {Long, Xiang and de Melo, Gerard and He, Dongliang and Li, Fu and Chi, Zhizhen and Wen, Shilei and Gan, Chuang}, title = {Purely attention based local feature integration for video classification}, series = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {44}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, number = {4}, publisher = {Inst. of Electr. and Electronics Engineers}, address = {Los Alamitos}, issn = {0162-8828}, doi = {10.1109/TPAMI.2020.3029554}, pages = {2140 -- 2154}, year = {2020}, abstract = {Recently, substantial research effort has focused on how to apply CNNs or RNNs to better capture temporal patterns in videos, so as to improve the accuracy of video classification. In this paper, we investigate the potential of a purely attention based local feature integration. Accounting for the characteristics of such features in video classification, we first propose Basic Attention Clusters (BAC), which concatenates the output of multiple attention units applied in parallel, and introduce a shifting operation to capture more diverse signals. Experiments show that BAC can achieve excellent results on multiple datasets. However, BAC treats all feature channels as an indivisible whole, which is suboptimal for achieving a finer-grained local feature integration over the channel dimension. Additionally, it treats the entire local feature sequence as an unordered set, thus ignoring the sequential relationships. To improve over BAC, we further propose the channel pyramid attention schema by splitting features into sub-features at multiple scales for coarse-to-fine sub-feature interaction modeling, and propose the temporal pyramid attention schema by dividing the feature sequences into ordered sub-sequences of multiple lengths to account for the sequential order. Our final model pyramidxpyramid attention clusters (PPAC) combines both channel pyramid attention and temporal pyramid attention to focus on the most important sub-features, while also preserving the temporal information of the video. We demonstrate the effectiveness of PPAC on seven real-world video classification datasets. Our model achieves competitive results across all of these, showing that our proposed framework can consistently outperform the existing local feature integration methods across a range of different scenarios.}, language = {en} } @phdthesis{Shaabani2020, author = {Shaabani, Nuhad}, title = {On discovering and incrementally updating inclusion dependencies}, doi = {10.25932/publishup-47186}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-471862}, school = {Universit{\"a}t Potsdam}, pages = {119}, year = {2020}, abstract = {In today's world, many applications produce large amounts of data at an enormous rate. Analyzing such datasets for metadata is indispensable for effectively understanding, storing, querying, manipulating, and mining them. Metadata summarizes technical properties of a dataset which rang from basic statistics to complex structures describing data dependencies. One type of dependencies is inclusion dependency (IND), which expresses subset-relationships between attributes of datasets. Therefore, inclusion dependencies are important for many data management applications in terms of data integration, query optimization, schema redesign, or integrity checking. So, the discovery of inclusion dependencies in unknown or legacy datasets is at the core of any data profiling effort. For exhaustively detecting all INDs in large datasets, we developed S-indd++, a new algorithm that eliminates the shortcomings of existing IND-detection algorithms and significantly outperforms them. S-indd++ is based on a novel concept for the attribute clustering for efficiently deriving INDs. Inferring INDs from our attribute clustering eliminates all redundant operations caused by other algorithms. S-indd++ is also based on a novel partitioning strategy that enables discording a large number of candidates in early phases of the discovering process. Moreover, S-indd++ does not require to fit a partition into the main memory--this is a highly appreciable property in the face of ever-growing datasets. S-indd++ reduces up to 50\% of the runtime of the state-of-the-art approach. None of the approach for discovering INDs is appropriate for the application on dynamic datasets; they can not update the INDs after an update of the dataset without reprocessing it entirely. To this end, we developed the first approach for incrementally updating INDs in frequently changing datasets. We achieved that by reducing the problem of incrementally updating INDs to the incrementally updating the attribute clustering from which all INDs are efficiently derivable. We realized the update of the clusters by designing new operations to be applied to the clusters after every data update. The incremental update of INDs reduces the time of the complete rediscovery by up to 99.999\%. All existing algorithms for discovering n-ary INDs are based on the principle of candidate generation--they generate candidates and test their validity in the given data instance. The major disadvantage of this technique is the exponentially growing number of database accesses in terms of SQL queries required for validation. We devised Mind2, the first approach for discovering n-ary INDs without candidate generation. Mind2 is based on a new mathematical framework developed in this thesis for computing the maximum INDs from which all other n-ary INDs are derivable. The experiments showed that Mind2 is significantly more scalable and effective than hypergraph-based algorithms.}, language = {en} } @article{HeimHeimZengetal.2019, author = {Heim, D. M. and Heim, Olga and Zeng, P. A. and Zheng, Jeffrey}, title = {Successful Creation of Regular Patterns in Variant Maps from Bat Echolocation Calls}, series = {Variant Construction from Theoretical Foundation to Applications}, journal = {Variant Construction from Theoretical Foundation to Applications}, publisher = {Springer}, address = {Singapore}, isbn = {978-981-13-2282-2}, doi = {10.1007/978-981-13-2282-2_25}, pages = {391 -- 400}, year = {2019}, abstract = {We created variant maps based on bat echolocation call recordings and outline here the transformation process and describe the resulting visual features. The maps show regular patterns while characteristic features change when bat call recording properties change. By focusing on specific visual features, we found a set of projection parameters which allowed us to classify the variant maps into two distinct groups. These results are promising indicators that variant maps can be used as basis for new echolocation call classification algorithms.}, language = {en} } @misc{ShaabaniMeinel2018, author = {Shaabani, Nuhad and Meinel, Christoph}, title = {Improving the efficiency of inclusion dependency detection}, series = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, journal = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-6014-2}, doi = {10.1145/3269206.3271724}, pages = {207 -- 216}, year = {2018}, abstract = {The detection of all inclusion dependencies (INDs) in an unknown dataset is at the core of any data profiling effort. Apart from the discovery of foreign key relationships, INDs can help perform data integration, integrity checking, schema (re-)design, and query optimization. With the advent of Big Data, the demand increases for efficient INDs discovery algorithms that can scale with the input data size. To this end, we propose S-INDD++ as a scalable system for detecting unary INDs in large datasets. S-INDD++ applies a new stepwise partitioning technique that helps discard a large number of attributes in early phases of the detection by processing the first partitions of smaller sizes. S-INDD++ also extends the concept of the attribute clustering to decide which attributes to be discarded based on the clustering result of each partition. Moreover, in contrast to the state-of-the-art, S-INDD++ does not require the partition to fit into the main memory-which is a highly appreciable property in the face of the ever growing datasets. We conducted an exhaustive evaluation of S-INDD++ by applying it to large datasets with thousands attributes and more than 266 million tuples. The results show the high superiority of S-INDD++ over the state-of-the-art. S-INDD++ reduced up to 50 \% of the runtime in comparison with BINDER, and up to 98 \% in comparison with S-INDD.}, language = {en} } @article{CorreDiguetHelleretal.2016, author = {Corre, Youenn and Diguet, Jean-Philippe and Heller, Dominique and Blouin, Dominique and Lagadec, Loic}, title = {TBES: Template-Based Exploration and Synthesis of Heterogeneous Multiprocessor Architectures on FPGA}, series = {ACM transactions on embedded computing systems : TECS}, volume = {15}, journal = {ACM transactions on embedded computing systems : TECS}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1539-9087}, doi = {10.1145/2816817}, pages = {113 -- 122}, year = {2016}, abstract = {This article describes TBES, a software end-to-end environment for synthesizing multitask applications on FPGAs. The implementation follows a template-based approach for creating heterogeneous multiprocessor architectures. Heterogeneity stems from the use of general-purpose processors along with custom accelerators. Experimental results demonstrate substantial speedup for several classes of applications. In addition to the use of architecture templates for the overall system, a second contribution lies in using high-level synthesis for promoting exploration of hardware IPs. The domain expert, who best knows which tasks are good candidates for hardware implementation, selects parts of the initial application to be potentially synthesized as dedicated accelerators. As a consequence, the HLS general problem turns into a constrained and more tractable issue, and automation capabilities eliminate the need for tedious and error-prone manual processes during domain space exploration. The automation only takes place once the application has been broken down into concurrent tasks by the designer, who can then drive the synthesis process with a set of parameters provided by TBES to balance tradeoffs between optimization efforts and quality of results. The approach is demonstrated step by step up to FPGA implementations and executions with an MJPEG benchmark and a complex Viola-Jones face detection application. We show that TBES allows one to achieve results with up to 10 times speedup to reduce development times and to widen design space exploration.}, language = {en} } @phdthesis{Gebser2011, author = {Gebser, Martin}, title = {Proof theory and algorithms for answer set programming}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-55425}, school = {Universit{\"a}t Potsdam}, year = {2011}, abstract = {Answer Set Programming (ASP) is an emerging paradigm for declarative programming, in which a computational problem is specified by a logic program such that particular models, called answer sets, match solutions. ASP faces a growing range of applications, demanding for high-performance tools able to solve complex problems. ASP integrates ideas from a variety of neighboring fields. In particular, automated techniques to search for answer sets are inspired by Boolean Satisfiability (SAT) solving approaches. While the latter have firm proof-theoretic foundations, ASP lacks formal frameworks for characterizing and comparing solving methods. Furthermore, sophisticated search patterns of modern SAT solvers, successfully applied in areas like, e.g., model checking and verification, are not yet established in ASP solving. We address these deficiencies by, for one, providing proof-theoretic frameworks that allow for characterizing, comparing, and analyzing approaches to answer set computation. For another, we devise modern ASP solving algorithms that integrate and extend state-of-the-art techniques for Boolean constraint solving. We thus contribute to the understanding of existing ASP solving approaches and their interconnections as well as to their enhancement by incorporating sophisticated search patterns. The central idea of our approach is to identify atomic as well as composite constituents of a propositional logic program with Boolean variables. This enables us to describe fundamental inference steps, and to selectively combine them in proof-theoretic characterizations of various ASP solving methods. In particular, we show that different concepts of case analyses applied by existing ASP solvers implicate mutual exponential separations regarding their best-case complexities. We also develop a generic proof-theoretic framework amenable to language extensions, and we point out that exponential separations can likewise be obtained due to case analyses on them. We further exploit fundamental inference steps to derive Boolean constraints characterizing answer sets. They enable the conception of ASP solving algorithms including search patterns of modern SAT solvers, while also allowing for direct technology transfers between the areas of ASP and SAT solving. Beyond the search for one answer set of a logic program, we address the enumeration of answer sets and their projections to a subvocabulary, respectively. The algorithms we develop enable repetition-free enumeration in polynomial space without being intrusive, i.e., they do not necessitate any modifications of computations before an answer set is found. Our approach to ASP solving is implemented in clasp, a state-of-the-art Boolean constraint solver that has successfully participated in recent solver competitions. Although we do here not address the implementation techniques of clasp or all of its features, we present the principles of its success in the context of ASP solving.}, language = {en} }