@inbook{52660, abstract = {{Application Programming Interfaces (APIs) are the primary mechanism developers use to obtain access to third-party algorithms and services. Unfortunately, APIs can be misused, which can have catastrophic consequences, especially if the APIs provide security-critical functionalities like cryptography. Understanding what API misuses are, and how they are caused, is important to prevent them, eg, with API misuse detectors. However, definitions for API misuses and related terms in literature vary. This paper presents a systematic literature review to clarify these terms and introduces FUM, a novel Framework for API Usage constraint and Misuse classification. The literature review revealed that API misuses are violations of API usage constraints. To address this, we provide unified definitions and use them to derive FUM. To assess the extent to which FUM aids in determining and guiding the improvement of an API misuses detector’s capabilities, we performed a case study on the state-of the-art misuse detection tool CogniCrypt. The study showed that FUM can be used to properly assess CogniCrypt’s capabilities, identify weaknesses and assist in deriving mitigations and improvements.}}, author = {{Schlichtig, Michael and Sassalla, Steffen and Narasimhan, Krishna and Bodden, Eric}}, booktitle = {{Software Engineering 2023}}, isbn = {{978-3-88579-726-5}}, keywords = {{API misuses API usage constraints, classification framework, API misuse detection, static analysis}}, pages = {{105–106}}, publisher = {{Gesellschaft für Informatik e.V.}}, title = {{{Introducing FUM: A Framework for API Usage Constraint and Misuse Classification}}}, year = {{2023}}, } @inproceedings{31133, abstract = {{Application Programming Interfaces (APIs) are the primary mechanism that developers use to obtain access to third-party algorithms and services. Unfortunately, APIs can be misused, which can have catastrophic consequences, especially if the APIs provide security-critical functionalities like cryptography. Understanding what API misuses are, and for what reasons they are caused, is important to prevent them, e.g., with API misuse detectors. However, definitions and nominations for API misuses and related terms in literature vary and are diverse. This paper addresses the problem of scattered knowledge and definitions of API misuses by presenting a systematic literature review on the subject and introducing FUM, a novel Framework for API Usage constraint and Misuse classification. The literature review revealed that API misuses are violations of API usage constraints. To capture this, we provide unified definitions and use them to derive FUM. To assess the extent to which FUM aids in determining and guiding the improvement of an API misuses detectors' capabilities, we performed a case study on CogniCrypt, a state-of-the-art misuse detector for cryptographic APIs. The study showed that FUM can be used to properly assess CogniCrypt's capabilities, identify weaknesses and assist in deriving mitigations and improvements. And it appears that also more generally FUM can aid the development and improvement of misuse detection tools.}}, author = {{Schlichtig, Michael and Sassalla, Steffen and Narasimhan, Krishna and Bodden, Eric}}, booktitle = {{2022 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)}}, keywords = {{API misuses, API usage constraints, classification framework, API misuse detection, static analysis}}, pages = {{673 -- 684}}, title = {{{FUM - A Framework for API Usage constraint and Misuse Classification}}}, doi = {{https://doi.org/10.1109/SANER53432.2022.00085}}, year = {{2022}}, } @article{48878, abstract = {{Due to the rise of continuous data-generating applications, analyzing data streams has gained increasing attention over the past decades. A core research area in stream data is stream classification, which categorizes or detects data points within an evolving stream of observations. Areas of stream classification are diverse\textemdash ranging, e.g., from monitoring sensor data to analyzing a wide range of (social) media applications. Research in stream classification is related to developing methods that adapt to the changing and potentially volatile data stream. It focuses on individual aspects of the stream classification pipeline, e.g., designing suitable algorithm architectures, an efficient train and test procedure, or detecting so-called concept drifts. As a result of the many different research questions and strands, the field is challenging to grasp, especially for beginners. This survey explores, summarizes, and categorizes work within the domain of stream classification and identifies core research threads over the past few years. It is structured based on the stream classification process to facilitate coordination within this complex topic, including common application scenarios and benchmarking data sets. Thus, both newcomers to the field and experts who want to widen their scope can gain (additional) insight into this research area and find starting points and pointers to more in-depth literature on specific issues and research directions in the field.}}, author = {{Clever, Lena and Pohl, Janina Susanne and Bossek, Jakob and Kerschke, Pascal and Trautmann, Heike}}, issn = {{2076-3417}}, journal = {{Applied Sciences}}, keywords = {{big data, data mining, data stream analysis, machine learning, stream classification, supervised learning}}, number = {{18}}, pages = {{9094}}, publisher = {{{Multidisciplinary Digital Publishing Institute}}}, title = {{{Process-Oriented Stream Classification Pipeline: A Literature Review}}}, doi = {{10.3390/app12189094}}, volume = {{12}}, year = {{2022}}, } @article{21004, abstract = {{Automated machine learning (AutoML) supports the algorithmic construction and data-specific customization of machine learning pipelines, including the selection, combination, and parametrization of machine learning algorithms as main constituents. Generally speaking, AutoML approaches comprise two major components: a search space model and an optimizer for traversing the space. Recent approaches have shown impressive results in the realm of supervised learning, most notably (single-label) classification (SLC). Moreover, first attempts at extending these approaches towards multi-label classification (MLC) have been made. While the space of candidate pipelines is already huge in SLC, the complexity of the search space is raised to an even higher power in MLC. One may wonder, therefore, whether and to what extent optimizers established for SLC can scale to this increased complexity, and how they compare to each other. This paper makes the following contributions: First, we survey existing approaches to AutoML for MLC. Second, we augment these approaches with optimizers not previously tried for MLC. Third, we propose a benchmarking framework that supports a fair and systematic comparison. Fourth, we conduct an extensive experimental study, evaluating the methods on a suite of MLC problems. We find a grammar-based best-first search to compare favorably to other optimizers.}}, author = {{Wever, Marcel Dominik and Tornede, Alexander and Mohr, Felix and Hüllermeier, Eyke}}, issn = {{0162-8828}}, journal = {{IEEE Transactions on Pattern Analysis and Machine Intelligence}}, keywords = {{Automated Machine Learning, Multi Label Classification, Hierarchical Planning, Bayesian Optimization}}, pages = {{1--1}}, title = {{{AutoML for Multi-Label Classification: Overview and Empirical Evaluation}}}, doi = {{10.1109/tpami.2021.3051276}}, year = {{2021}}, } @article{20212, abstract = {{Ideational impact refers to the uptake of a paper's ideas and concepts by subsequent research. It is defined in stark contrast to total citation impact, a measure predominantly used in research evaluation that assumes that all citations are equal. Understanding ideational impact is critical for evaluating research impact and understanding how scientific disciplines build a cumulative tradition. Research has only recently developed automated citation classification techniques to distinguish between different types of citations and generally does not emphasize the conceptual content of the citations and its ideational impact. To address this problem, we develop Deep Content-enriched Ideational Impact Classification (Deep-CENIC) as the first automated approach for ideational impact classification to support researchers' literature search practices. We evaluate Deep-CENIC on 1,256 papers citing 24 information systems review articles from the IT business value domain. We show that Deep-CENIC significantly outperforms state-of-the-art benchmark models. We contribute to information systems research by operationalizing the concept of ideational impact, designing a recommender system for academic papers based on deep learning techniques, and empirically exploring the ideational impact of the IT business value domain. }}, author = {{Prester, Julian and Wagner, Gerit and Schryen, Guido and Hassan, Nik Rushdi}}, journal = {{Decision Support Systems}}, keywords = {{Ideational impact, citation classification, academic recommender systems, natural language processing, deep learning, cumulative tradition}}, number = {{January}}, title = {{{Classifying the Ideational Impact of Information Systems Review Articles: A Content-Enriched Deep Learning Approach}}}, volume = {{140}}, year = {{2021}}, } @inproceedings{24547, abstract = {{Over the last years, several approaches for the data-driven estimation of expected possession value (EPV) in basketball and association football (soccer) have been proposed. In this paper, we develop and evaluate PIVOT: the first such framework for team handball. Accounting for the fast-paced, dynamic nature and relative data scarcity of hand- ball, we propose a parsimonious end-to-end deep learning architecture that relies solely on tracking data. This efficient approach is capable of predicting the probability that a team will score within the near future given the fine-grained spatio-temporal distribution of all players and the ball over the last seconds of the game. Our experiments indicate that PIVOT is able to produce accurate and calibrated probability estimates, even when trained on a relatively small dataset. We also showcase two interactive applications of PIVOT for valuing actual and counterfactual player decisions and actions in real-time.}}, author = {{Müller, Oliver and Caron, Matthew and Döring, Michael and Heuwinkel, Tim and Baumeister, Jochen}}, booktitle = {{8th Workshop on Machine Learning and Data Mining for Sports Analytics (ECML PKDD 2021)}}, keywords = {{expected possession value, handball, tracking data, time series classification, deep learning}}, location = {{Online}}, title = {{{PIVOT: A Parsimonious End-to-End Learning Framework for Valuing Player Actions in Handball using Tracking Data}}}, year = {{2021}}, } @inproceedings{27111, abstract = {{In the industry 4.0 era, there is a growing need to transform unstructured data acquired by a multitude of sources into information and subsequently into knowledge to improve the quality of manufactured products, to boost production, for predictive maintenance, etc. Data-driven approaches, such as machine learning techniques, are typically employed to model the underlying relationship from data. However, an increase in model accuracy with state-of-the-art methods, such as deep convolutional neural networks, results in less interpretability and transparency. Due to the ease of implementation, interpretation and transparency to both domain experts and non-experts, a rule-based method is proposed in this paper, for prognostics and health management (PHM) and specifically for diagnostics. The proposed method utilizes the most relevant sensor signals acquired via feature extraction and selection techniques and expert knowledge. As a case study, the presented method is evaluated on data from a real-world quality control set-up provided by the European prognostics and health management society (PHME) at the conference’s 2021 data challenge. With the proposed method, our team took the third place, capable of successfully diagnosing different fault modes, irrespective of varying conditions.}}, author = {{Aimiyekagbon, Osarenren Kennedy and Muth, Lars and Wohlleben, Meike Claudia and Bender, Amelie and Sextro, Walter}}, booktitle = {{Proceedings of the European Conference of the PHM Society 2021}}, editor = {{Do, Phuc and King, Steve and Fink, Olga}}, keywords = {{PHME 2021, Feature Selection Classification, Feature Selection Clustering, Interpretable Model, Transparent Model, Industry 4.0, Real-World Diagnostics, Quality Control, Predictive Maintenance}}, number = {{1}}, pages = {{527--536}}, title = {{{Rule-based Diagnostics of a Production Line}}}, doi = {{10.36001/phme.2021.v6i1.3042}}, volume = {{6}}, year = {{2021}}, } @inproceedings{2109, abstract = {{In multinomial classification, reduction techniques are commonly used to decompose the original learning problem into several simpler problems. For example, by recursively bisecting the original set of classes, so-called nested dichotomies define a set of binary classification problems that are organized in the structure of a binary tree. In contrast to the existing one-shot heuristics for constructing nested dichotomies and motivated by recent work on algorithm configuration, we propose a genetic algorithm for optimizing the structure of such dichotomies. A key component of this approach is the proposed genetic representation that facilitates the application of standard genetic operators, while still supporting the exchange of partial solutions under recombination. We evaluate the approach in an extensive experimental study, showing that it yields classifiers with superior generalization performance.}}, author = {{Wever, Marcel Dominik and Mohr, Felix and Hüllermeier, Eyke}}, booktitle = {{Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2018, Kyoto, Japan, July 15-19, 2018}}, keywords = {{Classification, Hierarchical Decomposition, Indirect Encoding}}, location = {{Kyoto, Japan}}, publisher = {{ACM}}, title = {{{Ensembles of Evolved Nested Dichotomies for Classification}}}, doi = {{10.1145/3205455.3205562}}, year = {{2018}}, } @article{5617, abstract = {{CAPTCHAs are challenge-response tests that aim at preventing unwanted machines, including bots, from accessing web services while providing easy access for humans. Recent advances in artificial-intelligence based attacks show that the level of security provided by many state-of-the-art text-based CAPTCHAs is declining. At the same time, techniques for distorting and obscuring the text, which are used to maintain the level of security, make text-based CAPTCHAs diffcult to solve for humans, and thereby further degrade usability. The need for developing alternative types of CAPTCHAs which improve both, the current security and usability levels, has been emphasized by several researchers. With this study, we contribute to research through (1) the development of two new face recognition CAPTCHAs (Farett-Gender and Farett-Gender&Age), (2) the security analysis of both procedures, and (3) the provision of empirical evidence that one of the suggested CAPTCHAs (Farett-Gender) is similar to Google's reCAPTCHA and better than KCAPTCHA concerning effectiveness (error rates), superior to both regarding learnability and satisfaction but not effciency.}}, author = {{Schryen, Guido and Wagner, Gerit and Schlegel, Alexander}}, journal = {{Computers & Security}}, keywords = {{CAPTCHA, Usability, Facial features, Gender classiffcation, Age classification, Face recognition reverse Turing test}}, number = {{July}}, pages = {{95--116}}, publisher = {{Elsevier}}, title = {{{Development of two novel face-recognition CAPTCHAs: a security and usability study}}}, volume = {{60}}, year = {{2016}}, } @inproceedings{11816, abstract = {{In this paper, we consider the Maximum Likelihood (ML) estimation of the parameters of a GAUSSIAN in the presence of censored, i.e., clipped data. We show that the resulting Expectation Maximization (EM) algorithm delivers virtually biasfree and efficient estimates, and we discuss its convergence properties. We also discuss optimal classification in the presence of censored data. Censored data are frequently encountered in wireless LAN positioning systems based on the fingerprinting method employing signal strength measurements, due to the limited sensitivity of the portable devices. Experiments both on simulated and real-world data demonstrate the effectiveness of the proposed algorithms.}}, author = {{Hoang, Manh Kha and Haeb-Umbach, Reinhold}}, booktitle = {{38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013)}}, issn = {{1520-6149}}, keywords = {{Gaussian processes, Global Positioning System, convergence, expectation-maximisation algorithm, fingerprint identification, indoor radio, signal classification, wireless LAN, EM algorithm, ML estimation, WiFi indoor positioning, censored Gaussian data classification, clipped data, convergence properties, expectation maximization algorithm, fingerprinting method, maximum likelihood estimation, optimal classification, parameters estimation, portable devices sensitivity, signal strength measurements, wireless LAN positioning systems, Convergence, IEEE 802.11 Standards, Maximum likelihood estimation, Parameter estimation, Position measurement, Training, Indoor positioning, censored data, expectation maximization, signal strength, wireless LAN}}, pages = {{3721--3725}}, title = {{{Parameter estimation and classification of censored Gaussian data with application to WiFi indoor positioning}}}, doi = {{10.1109/ICASSP.2013.6638353}}, year = {{2013}}, } @inproceedings{46388, abstract = {{Understanding the behaviour of well-known algorithms for classical NP-hard optimisation problems is still a difficult task. With this paper, we contribute to this research direction and carry out a feature based comparison of local search and the well-known Christofides approximation algorithm for the Traveling Salesperson Problem. We use an evolutionary algorithm approach to construct easy and hard instances for the Christofides algorithm, where we measure hardness in terms of approximation ratio. Our results point out important features and lead to hard and easy instances for this famous algorithm. Furthermore, our cross-comparison gives new insights on the complementary benefits of the different approaches.}}, author = {{Nallaperuma, Samadhi and Wagner, Markus and Neumann, Frank and Bischl, Bernd and Mersmann, Olaf and Trautmann, Heike}}, booktitle = {{Proceedings of the Twelfth Workshop on Foundations of Genetic Algorithms XII}}, isbn = {{9781450319904}}, keywords = {{approximation algorithms, local search, traveling salesperson problem, feature selection, prediction, classification}}, pages = {{147–160}}, publisher = {{Association for Computing Machinery}}, title = {{{A Feature-Based Comparison of Local Search and the Christofides Algorithm for the Travelling Salesperson Problem}}}, doi = {{10.1145/2460239.2460253}}, year = {{2013}}, } @article{48889, abstract = {{Meta-heuristics are frequently used to tackle NP-hard combinatorial optimization problems. With this paper we contribute to the understanding of the success of 2-opt based local search algorithms for solving the traveling salesperson problem (TSP). Although 2-opt is widely used in practice, it is hard to understand its success from a theoretical perspective. We take a statistical approach and examine the features of TSP instances that make the problem either hard or easy to solve. As a measure of problem difficulty for 2-opt we use the approximation ratio that it achieves on a given instance. Our investigations point out important features that make TSP instances hard or easy to be approximated by 2-opt.}}, author = {{Mersmann, Olaf and Bischl, Bernd and Trautmann, Heike and Wagner, Markus and Bossek, Jakob and Neumann, Frank}}, issn = {{1012-2443}}, journal = {{Annals of Mathematics and Artificial Intelligence}}, keywords = {{2-opt, 90B06, Classification, Feature selection, MARS, TSP}}, number = {{2}}, pages = {{151–182}}, title = {{{A Novel Feature-Based Approach to Characterize Algorithm Performance for the Traveling Salesperson Problem}}}, doi = {{10.1007/s10472-013-9341-2}}, volume = {{69}}, year = {{2013}}, } @inproceedings{48890, abstract = {{With this paper we contribute to the understanding of the success of 2-opt based local search algorithms for solving the traveling salesman problem TSP. Although 2-opt is widely used in practice, it is hard to understand its success from a theoretical perspective. We take a statistical approach and examine the features of TSP instances that make the problem either hard or easy to solve. As a measure of problem difficulty for 2-opt we use the approximation ratio that it achieves on a given instance. Our investigations point out important features that make TSP instances hard or easy to be approximated by 2-opt.}}, author = {{Mersmann, Olaf and Bischl, Bernd and Bossek, Jakob and Trautmann, Heike and Wagner, Markus and Neumann, Frank}}, booktitle = {{Revised Selected Papers of the 6th International Conference on Learning and Intelligent Optimization - Volume 7219}}, isbn = {{978-3-642-34412-1}}, keywords = {{2-opt, Classification, Feature Selection, MARS, TSP}}, pages = {{115–129}}, publisher = {{Springer-Verlag}}, title = {{{Local Search and the Traveling Salesman Problem: A Feature-Based Characterization of Problem Hardness}}}, year = {{2012}}, } @inproceedings{1122, abstract = {{Within this paper, we will describe a new approach to customer interaction management by integrating social networking channels into existing business processes. Until now, contact center agents still read these messages and forward them to the persons in charge of customer’s in the company. But with the introduction of Web 2.0 and social networking clients are more likely to communicate with the companies via Facebook and Twitter instead of filling data in contact forms or sending e-mail requests. In order to maintain an active communication with international clients via social media, the multilingual consumer contacts have to be categorized and then automatically assigned to the corresponding business processes (e.g. technicalservice, shipping, marketing, and accounting). This allows the company to follow general trends in customer opinions on the Internet, but also record two-sided communication for customer relationship management.}}, author = {{Geierhos, Michaela and Lee, Yeong Su and Bargel, Matthias}}, booktitle = {{Multilingual Resources, Multilingual Applications: Proceedings of the Conference of the German Society for Computational Linguistics and Language Technology (GSCL) 2011}}, editor = {{Hedeland, Hanna and Schmidt, Thomas and Wörner, Kai}}, issn = {{0176-599X}}, keywords = {{Classification of Multilingual Customer Contacts, Contact Center Application Support, Social Media Business Integration}}, location = {{Hamburg, Germany}}, pages = {{219--222}}, publisher = {{University of Hamburg}}, title = {{{Processing Multilingual Customer Contacts via Social Media}}}, volume = {{96}}, year = {{2011}}, } @inproceedings{9763, abstract = {{Recent advances in information processing enable new kinds of technical systems, called self-optimizing systems. These systems are able to adapt their objectives and their behavior according to the current situation and influences autonomously. This behavior adaptation is non-deterministic and hence self-optimization is a risk to the system, e.g. if the result of the self-optimization process does not match the suddenly changed situation. In contrary, self-optimization could be used to increase the dependability by pursuing objectives like reliability and availability. In our preceding publications we introduced the so called multi-level dependability concept to cope with this new kind of systems (cf. [6]). This concept comprises the monitoring of the system behavior, the classification of the current situation, and the selection of the appropriate measure, if reliability limits are exceeded. In this paper we present for the first time experimental results. The dependability concept is implemented in the self-optimizing active guidance system of a railway vehicle. The test drives illustrate clearly that the proposed concept is able to cope with, e.g., sensor failures, and is able to increase the reliability and availability of the active guidance module.}}, author = {{Sondermann-Wölke, Christoph and Geisler, Jens and Sextro, Walter}}, booktitle = {{Reliability and Maintainability Symposium (RAMS), 2010 Proceedings - Annual}}, issn = {{0149-144X}}, keywords = {{availability, dependability concept, multilevel dependability concept, railway vehicle, reliability, self optimizing active guidance system, self optimizing railway guidance system, situation classification, system behavior monitoring, optimal control, railways, reliability theory, self-adjusting systems}}, pages = {{1 --6}}, title = {{{Increasing the reliability of a self-optimizing railway guidance system}}}, doi = {{10.1109/RAMS.2010.5448080}}, year = {{2010}}, } @inproceedings{37037, abstract = {{Today we can identify a big gap between requirement specification and the generation of test environments. This article extends the Classification Tree Method for Embedded Systems (CTM/ES) to fill this gap by new concepts for the precise specification of stimuli for operational ranges of continuous control systems. It introduces novel means for continuous acceptance criteria definition and for functional coverage definition.}}, author = {{Krupp, Alexander and Müller, Wolfgang}}, booktitle = {{Proceedings of DATE’10}}, keywords = {{System testing, Automatic testing, Object oriented modeling, Classification tree analysis, Automotive engineering, Mathematical model, Embedded system, Control systems, Electronic equipment testing, Software testing}}, location = {{Dresden}}, publisher = {{IEEE}}, title = {{{A Systematic Approach to Combined HW/SW System Test}}}, doi = {{10.1109/DATE.2010.5457186}}, year = {{2010}}, } @inproceedings{38784, abstract = {{This article presents the classification tree method for functional verification to close the gap from the specification of a test plan to SystemVerilog (Chandra and Chakrabarty, 2001) test bench generation. Our method supports the systematic development of test configurations and is based on the classification tree method for embedded systems (CTM/ES) (Chakrabarty et al., 2000) extending CTM/ES for random test generation as well as for functional coverage and property specification}}, author = {{Krupp, Alexander and Müller, Wolfgang}}, booktitle = {{Proceedings of the Design Automation & Test in Europe Conference}}, isbn = {{3-9810801-1-4}}, keywords = {{Classification tree analysis, System testing, Embedded system, Safety, Automatic testing, Automation}}, publisher = {{IEEE}}, title = {{{Classification Trees for Functional Coverage and Random Test Generation}}}, doi = {{10.1109/DATE.2006.243902}}, year = {{2006}}, } @article{11870, abstract = {{We derive a class of computationally inexpensive linear dimension reduction criteria by introducing a weighted variant of the well-known K-class Fisher criterion associated with linear discriminant analysis (LDA). It can be seen that LDA weights contributions of individual class pairs according to the Euclidean distance of the respective class means. We generalize upon LDA by introducing a different weighting function}}, author = {{Loog, M. and Duin, R.P.W. and Haeb-Umbach, Reinhold}}, journal = {{IEEE Transactions on Pattern Analysis and Machine Intelligence}}, keywords = {{approximate pairwise accuracy, Bayes error, Bayes methods, error statistics, Euclidean distance, Fisher criterion, linear dimension reduction, linear discriminant analysis, pattern classification, statistical analysis, statistical pattern classification, weighting function}}, number = {{7}}, pages = {{762--766}}, title = {{{Multiclass linear dimension reduction by weighted pairwise Fisher criteria}}}, doi = {{10.1109/34.935849}}, volume = {{23}}, year = {{2001}}, }