Change search
Refine search result
12 1 - 50 of 67
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Atalar, Aras
    et al.
    Chalmers University of Technology.
    Gidenstam, Anders
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Renaud-Goud, Paul
    Chalmers University of Technology.
    Tsigas, Philippas
    Chalmers University of Technology.
    Modeling Energy Consumption of Lock-Free Queue Implementations2015In: 2015 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2015, Hyderabad, India, May 25-29, 2015, IEEE Computer Society, 2015, p. 229-238Conference paper (Refereed)
    Abstract [en]

    This paper considers the problem of modelling the energy behaviour of lock-free concurrent queue data structures. Our main contribution is a way to model the energy behaviour of lock-free queue implementations and parallel applications that use them. Focusing on steady state behaviour we decompose energy behaviour into throughput and power dissipation which can be modeled separately and later recombined into several useful metrics, such as energy per operation. Based on our models, instantiated from synthetic benchmark data, and using only a small amount of additional application specific information, energy and throughput predictions can be made for parallel applications that use the respective data structure implementation. To model throughput we propose a generic model forlock-free queue throughput behaviour, based on combination of the dequeuers' throughput and enqueuers' throughput. To model power dissipation we commonly split the contributions from the various computer components into static, activation and dynamic parts, where only the dynamic part depends on the actual instructions being executed. To instantiate the models a synthetic benchmark explores each queue implementation over the dimensions of processor frequency and number of threads. Finally, we show how to make predictions of application throughput and power dissipation for a parallel application using lock-free queue requiring only a limited amount of information about the application work done between queue operations. Our case study on a Mandelbrot application shows convincing prediction results.

  • 2.
    Dahlbom, Anders
    et al.
    Högskolan i Skövde.
    Maria, Riveiro
    Högskolan i Skövde.
    König, Rikard
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Brattberg, Peter
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Supporting Golf Coaching with 3D Modeling of Swings2014In: Sportinformatik X: Jahrestagung der dvs-Sektion Sportinformatik, Hamburg: Feldhaus Verlag GmbH & Co. KG , 2014, 10, p. 142-148Chapter in book (Refereed)
  • 3.
    Darányi, Sándor
    et al.
    University of Borås, Swedish School of Library and Information Science.
    Wittek, Peter
    University of Borås, Swedish School of Library and Information Science.
    Connecting the Dots: Mass, Energy, Word Meaning, and Particle-Wave Duality2012Conference paper (Refereed)
    Abstract [en]

    With insight from linguistics that degrees of text cohesion are similar to forces in physics, and the frequent use of the energy concept in text categorization by machine learning, we consider the applicability of particle-wave duality to semantic content inherent in index terms. Wave-like interpretations go back to the regional nature of such content, utilizing functions for its representation, whereas content as a particle can be conveniently modelled by position vectors. Interestingly, wave packets behave like particles, lending credibility to the duality hypothesis. We show in a classical mechanics framework how metaphorical term mass can be computed.

  • 4.
    Darányi, Sándor
    et al.
    University of Borås, Swedish School of Library and Information Science.
    Wittek, Peter
    University of Borås, Swedish School of Library and Information Science.
    The gravity of meaning: Physics as a metaphor to model semantic changes2012Conference paper (Refereed)
    Abstract [en]

    Based on a computed toy example, we offer evidence that by plugging in similarity of word meaning as a force plus a small modification of Newton’s 2nd law, one can acquire specific “mass” values for index terms in a Saltonesque dynamic library environment. The model can describe two types of change which affect the semantic composition of document collections: the expansion of a corpus due to its update, and fluctuations of the gravitational potential energy field generated by normative language use as an attractor juxtaposed with actual language use yielding time-dependent term frequencies. By the evolving semantic potential of a vocabulary and concatenating the respective term “mass” values, one can model sentences or longer strings of symbols as vector-valued functions. Since the line integral of such functions is used to express the work of a particle in a gravitational field, the work equivalent of strings can be calculated.

  • 5.
    Gabrielsson, Patrick
    et al.
    University of Borås, School of Business and IT.
    Johansson, Ulf
    University of Borås, School of Business and IT.
    König, Rikard
    University of Borås, School of Business and IT.
    Co-Evolving Online High-Frequency Trading Strategies Using Grammatical Evolution2014Conference paper (Refereed)
    Abstract [en]

    Numerous sophisticated algorithms exist for discovering reoccurring patterns in financial time series. However, the most accurate techniques available produce opaque models, from which it is impossible to discern the rationale behind trading decisions. It is therefore desirable to sacrifice some degree of accuracy for transparency. One fairly recent evolutionary computational technology that creates transparent models, using a user-specified grammar, is grammatical evolution (GE). In this paper, we explore the possibility of evolving transparent entry- and exit trading strategies for the E-mini S&P 500 index futures market in a high-frequency trading environment using grammatical evolution. We compare the performance of models incorporating risk into their calculations with models that do not. Our empirical results suggest that profitable, risk-averse, transparent trading strategies for the E-mini S&P 500 can be obtained using grammatical evolution together with technical indicators.

  • 6.
    Gabrielsson, Patrick
    et al.
    University of Borås, School of Business and IT.
    König, Rikard
    University of Borås, School of Business and IT.
    Johansson, Ulf
    University of Borås, School of Business and IT.
    Evolving Hierarchical Temporal Memory-Based Trading Models2013Conference paper (Refereed)
    Abstract [en]

    We explore the possibility of using the genetic algorithm to optimize trading models based on the Hierarchical Temporal Memory (HTM) machine learning technology. Technical indicators, derived from intraday tick data for the E-mini S&P 500 futures market (ES), were used as feature vectors to the HTM models. All models were configured as binary classifiers, using a simple buy-and-hold trading strategy, and followed a supervised training scheme. The data set was partitioned into multiple folds to enable a modified cross validation scheme. Artificial Neural Networks (ANNs) were used to benchmark HTM performance. The results show that the genetic algorithm succeeded in finding predictive models with good performance and generalization ability. The HTM models outperformed the neural network models on the chosen data set and both technologies yielded profitable results with above average accuracy.

  • 7.
    Gabrielsson, Patrick
    et al.
    University of Borås, School of Business and IT.
    König, Rikard
    University of Borås, School of Business and IT.
    Johansson, Ulf
    University of Borås, School of Business and IT.
    Hierarchical Temporal Memory-based algorithmic trading of financial markets2012Conference paper (Refereed)
    Abstract [en]

    This paper explores the possibility of using the Hierarchical Temporal Memory (HTM) machine learning technology to create a profitable software agent for trading financial markets. Technical indicators, derived from intraday tick data for the E-mini S&P 500 futures market (ES), were used as features vectors to the HTM models. All models were configured as binary classifiers, using a simple buy-and-hold trading strategy, and followed a supervised training scheme. The data set was divided into a training set, a validation set and three test sets; bearish, bullish and horizontal. The best performing model on the validation set was tested on the three test sets. Artificial Neural Networks (ANNs) were subjected to the same data sets in order to benchmark HTM performance. The results suggest that the HTM technology can be used together with a feature vector of technical indicators to create a profitable trading algorithm for financial markets. Results also suggest that HTM performance is, at the very least, comparable to commonly applied neural network models.

  • 8.
    Gidenstam, Anders
    et al.
    University of Borås, School of Business and IT.
    Koldehofe, Boris
    Papatriantafilou, Marina
    Tsigas, Philippas
    Scalable group communication supporting configurable levels of consistency2013In: Concurrency and Computation, ISSN 1532-0626, Vol. 25, no 5, p. 649-671Article in journal (Refereed)
    Abstract [en]

    Group communication is deployed in many evolving Internet-scale cooperative applications such as multiplayer online games and virtual worlds to efficiently support interaction on information relevant to a potentially very large number of users or objects. Especially peer-to-peer based group communication protocols have evolved as a promising approach to allow intercommunication between many distributed peers. Yet, the delivery semantics of robust and scalable protocols such as gossiping is not sufficient to support consistency semantics beyond eventual consistency because no relationship on the order of events is enforced. On the other hand, traditional consistency models provided by reliable group communication providing causal or even total order are restricted to support only small groups. This article proposes the cluster consistency model which bridges the gap between traditional and current approaches in supporting both scalability and ordered event delivery. We introduce a dynamic and fault tolerant cluster management method that can coordinate concurrent access to resources in a peer-to-peer system and can be used to establish fault-tolerant configurable cluster consistency with predictable reliability, running on top of decentralised probabilistic protocols supporting scalable group communication. This is achieved by a general two-layered architecture that can be applied on top of the standard Internet communication layers and offers a modular, layered set of services to the applications that need them. Further, we present a fault-tolerant method implementing causal cluster consistency with predictable reliability, running on top of decentralised probabilistic protocols supporting group communication. This paper provides analytical and experimental evaluation of the properties regarding the fault tolerance of the approach. Furthermore, our experimental study, conducted by implementing and evaluating the two-layered architecture on top of standard Internet transport services, shows that the approach scales well, imposes an even load on the system, and provides high-probability reliability guarantees.

  • 9.
    Gidenstam, Anders
    et al.
    University of Borås, School of Business and IT.
    Papatriantafilou, Marina
    LFTHREADS: a lock-free thread library2008In: SIGARCH Computer Architecture News, Association for Computing Machinery, Inc. , 2008, Vol. 4878, p. 88-92Conference paper (Refereed)
    Abstract [en]

    This extended abstract presents LFTHREADS, a thread library entirely based on lock-free methods, i.e. no spinlocks or similar synchronization mechanisms are employed in the implementation of the multithreading. Since lockfreedom is highly desirable in multiprocessors/multicores due to its advantages in parallelism, fault-tolerance, convoy-avoidance and more, there is an increased demand in lock-free methods in parallel applications, hence also in multiprocessor/multicore system services. LFTHREADS is the first thread library that provides a lock-free implementation of blocking synchronization primitives for application threads; although the latter may sound like a contradicting goal, such objects have several benefits: e.g. library operations that block and unblock threads on the same synchronization object can make progress in parallel while maintaining the desired thread-level semantics and without having to wait for any "low" operations among them. Besides, as no spin-locks or similar synchronization mechanisms are employed, memory contention can be reduced and processors/cores are able to do useful work. As a consequence, applications, too, can enjoy enhanced parallelism and fault-tolerance. For the synchronization in LFTHREADS we have introduced a new method, which we call responsibility hand-off (RHO), that does not need any special kernel support. The RHO method is also of independent interest, as it can also serve as a tool for lock-free token passing, management of contention and interaction between scheduling and synchronization. This paper gives an outline and the context of LFTHREADS. For more details the reader is refered to [7] and [8].

  • 10.
    Gidenstam, Anders
    et al.
    University of Borås, School of Business and IT.
    Papatriantafilou, Marina
    Tsigas, Philippas
    NBmalloc: Allocating Memory in a Lock-Free Manner2010In: Algorithmica, ISSN 0178-4617, E-ISSN 1432-0541, Vol. 58, no 2, p. 304-338Article in journal (Refereed)
    Abstract [en]

    Efficient, scalable memory allocation for multithreaded applications on multiprocessors is a significant goal of recent research. In the distributed computing literature it has been emphasized that lock-based synchronization and concurrency-control may limit the parallelism in multiprocessor systems. Thus, system services that employ such methods can hinder reaching the full potential of these systems. A natural research question is the pertinence and the impact of lock-free concurrency control in key services for multiprocessors, such as in the memory allocation service, which is the theme of this work. We show the design and implementation of NBmalloc, a lock-free memory allocator designed to enhance the parallelism in the system. The architecture of NBmalloc is inspired by Hoard, a well-known concurrent memory allocator, with modular design that preserves scalability and helps avoiding false-sharing and heap-blowup. Within our effort to design appropriate lock-free algorithms for NBmalloc, we propose and show a lock-free implementation of a new data structure, flat-set, supporting conventional “internal” set operations as well as “inter-object” operations, for moving items between flat-sets. The design of NBmalloc also involved a series of other algorithmic problems, which are discussed in the paper. Further, we present the implementation of NBmalloc and a study of its behaviour in a set of multiprocessor systems. The results show that the good properties of Hoard w.r.t. false-sharing and heap-blowup are preserved.

  • 11.
    Gidenstam, Anders
    et al.
    University of Borås, School of Business and IT.
    Sundell, Håkan
    University of Borås, School of Business and IT.
    Tsigas, Philippas
    Cache-Aware Lock-Free Queues for Multiple Producers/Consumers and Weak Memory Consistency2010In: Proceedings of the 14th International Conference on Principles of Distributed Systems (OPODIS) 2010 / [ed] Chenyang Lu, Toshimitsu Masuzawa, Mohamed Mosbah, Springer , 2010, p. 302-317Conference paper (Refereed)
    Abstract [en]

    A lock-free FIFO queue data structure is presented in this paper. The algorithm supports multiple producers and multiple consumers and weak memory models. It has been designed to be cache-aware and work directly on weak memory models. It utilizes the cache behavior in concert with lazy updates of shared data, and a dynamic lock-free memory management scheme to decrease unnecessary synchronization and increase performance. Experiments on an 8-way multi-core platform show significantly better performance for the new algorithm compared to previous fast lock-free algorithms.

  • 12.
    Jansson, Karl
    et al.
    University of Borås, School of Business and IT.
    Sundell, Håkan
    University of Borås, School of Business and IT.
    Boström, Henrik
    gpuRF and gpuERT: Efficient and Scalable GPU Algorithms for Decision Tree Ensembles2014Conference paper (Refereed)
    Abstract [en]

    We present two new parallel implementations of the ensemble learning methods Random Forests (RF) and Extremely Randomized Trees (ERT), called gpuRF and gpuERT, for emerging many-core platforms, e.g., contemporary graphics cards suitable for general-purpose computing (GPGPU). RF and ERT are two ensemble methods for generating predictive models that are of high importance within machine learning. They operate by constructing a multitude of decision trees at training time and outputting a prediction by comparing the outputs of the individual trees. Thanks to the inherent parallelism of the task, an obvious platform for its computation is to employ contemporary GPUs with a large number of processing cores. Previous parallel algorithms for RF in the literature are either designed for traditional multi-core CPU platforms or early history GPUs with simpler architecture and relatively few cores. For ERT, only briefly sketched parallelization attempts exist in the literature. The new parallel algorithms are designed for contemporary GPUs with a large number of cores and take into account aspects of the newer hardware architectures, such as memory hierarchy and thread scheduling. They are implemented using the C/C++ language and the CUDA interface to attain the best possible performance on NVidia-based GPUs. An experimental study comparing the most important previous solutions for CPU and GPU platforms to the novel implementations shows significant advantages in the aspect of efficiency for the latter, often with several orders of magnitude.

  • 13.
    Jansson, Karl
    et al.
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Sundell, Håkan
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Boström, Henrik
    Stockholms Universitet.
    gpuRF and gpuERT: Efficient and Scalable GPU Algorithms for Decision Tree Ensembles2014In: Parallel & Distributed Processing Symposium Workshops (IPDPSW), 2014 IEEE International, 2014, p. 1612-1621Conference paper (Refereed)
  • 14.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    Boström, Henrik
    University of Borås, School of Business and IT.
    Löfström, Tuve
    University of Borås, School of Business and IT.
    Conformal Prediction Using Decision Trees2013Conference paper (Refereed)
    Abstract [en]

    Conformal prediction is a relatively new framework in which the predictive models output sets of predictions with a bound on the error rate, i.e., in a classification context, the probability of excluding the correct class label is lower than a predefined significance level. An investigation of the use of decision trees within the conformal prediction framework is presented, with the overall purpose to determine the effect of different algorithmic choices, including split criterion, pruning scheme and way to calculate the probability estimates. Since the error rate is bounded by the framework, the most important property of conformal predictors is efficiency, which concerns minimizing the number of elements in the output prediction sets. Results from one of the largest empirical investigations to date within the conformal prediction framework are presented, showing that in order to optimize efficiency, the decision trees should be induced using no pruning and with smoothed probability estimates. The choice of split criterion to use for the actual induction of the trees did not turn out to have any major impact on the efficiency. Finally, the experimentation also showed that when using decision trees, standard inductive conformal prediction was as efficient as the recently suggested method cross-conformal prediction. This is an encouraging results since cross-conformal prediction uses several decision trees, thus sacrificing the interpretability of a single decision tree.

  • 15.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    Boström, Henrik
    University of Borås, School of Business and IT.
    Löfström, Tuve
    University of Borås, School of Business and IT.
    Linusson, Henrik
    University of Borås, School of Business and IT.
    Regression conformal prediction with random forests2014In: Machine Learning, ISSN 0885-6125, E-ISSN 1573-0565, Vol. 97, no 1-2, p. 155-176Article in journal (Refereed)
    Abstract [en]

    Regression conformal prediction produces prediction intervals that are valid, i.e., the probability of excluding the correct target value is bounded by a predefined confidence level. The most important criterion when comparing conformal regressors is efficiency; the prediction intervals should be as tight (informative) as possible. In this study, the use of random forests as the underlying model for regression conformal prediction is investigated and compared to existing state-of-the-art techniques, which are based on neural networks and k-nearest neighbors. In addition to their robust predictive performance, random forests allow for determining the size of the prediction intervals by using out-of-bag estimates instead of requiring a separate calibration set. An extensive empirical investigation, using 33 publicly available data sets, was undertaken to compare the use of random forests to existing stateof- the-art conformal predictors. The results show that the suggested approach, on almost all confidence levels and using both standard and normalized nonconformity functions, produced significantly more efficient conformal predictors than the existing alternatives.

  • 16.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    König, Rikard
    University of Borås, School of Business and IT.
    Linusson, Henrik
    University of Borås, School of Business and IT.
    Löfström, Tuve
    University of Borås, School of Business and IT.
    Boström, Henrik
    University of Borås, School of Business and IT.
    Rule Extraction with Guaranteed Fidelity2014Conference paper (Refereed)
    Abstract [en]

    This paper extends the conformal prediction framework to rule extraction, making it possible to extract interpretable models from opaque models in a setting where either the infidelity or the error rate is bounded by a predefined significance level. Experimental results on 27 publicly available data sets show that all three setups evaluated produced valid and rather efficient conformal predictors. The implication is that augmenting rule extraction with conformal prediction allows extraction of models where test set errors or test sets infidelities are guaranteed to be lower than a chosen acceptable level. Clearly this is beneficial for both typical rule extraction scenarios, i.e., either when the purpose is to explain an existing opaque model, or when it is to build a predictive model that must be interpretable.

  • 17.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    König, Rikard
    University of Borås, School of Business and IT.
    Löfström, Tuve
    University of Borås, School of Business and IT.
    Niklasson, Lars
    Using Imaginary Ensembles to Select GP Classifiers2010In: Genetic Programming: 13th European Conference, EuroGP 2010, Istanbul, Turkey, April 7-9, 2010, Proceedings / [ed] A.I. et al. Esparcia-Alcazar, Springer-Verlag Berlin Heidelberg , 2010, p. 278-288Conference paper (Refereed)
    Abstract [en]

    When predictive modeling requires comprehensible models, most data miners will use specialized techniques producing rule sets or decision trees. This study, however, shows that genetically evolved decision trees may very well outperform the more specialized techniques. The proposed approach evolves a number of decision trees and then uses one of several suggested selection strategies to pick one specific tree from that pool. The inherent inconsistency of evolution makes it possible to evolve each tree using all data, and still obtain somewhat different models. The main idea is to use these quite accurate and slightly diverse trees to form an imaginary ensemble, which is then used as a guide when selecting one specific tree. Simply put, the tree classifying the largest number of instances identically to the ensemble is chosen. In the experimentation, using 25 UCI data sets, two selection strategies obtained significantly higher accuracy than the standard rule inducer J48.

  • 18.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    König, Rikard
    University of Borås, School of Business and IT.
    Löfström, Tuwe
    University of Borås, School of Business and IT.
    Boström, Henrik
    University of Borås, School of Business and IT.
    Evolved Decision Trees as Conformal Predictors2013Conference paper (Refereed)
    Abstract [en]

    In conformal prediction, predictive models output sets of predictions with a bound on the error rate. In classification, this translates to that the probability of excluding the correct class is lower than a predefined significance level, in the long run. Since the error rate is guaranteed, the most important criterion for conformal predictors is efficiency. Efficient conformal predictors minimize the number of elements in the output prediction sets, thus producing more informative predictions. This paper presents one of the first comprehensive studies where evolutionary algorithms are used to build conformal predictors. More specifically, decision trees evolved using genetic programming are evaluated as conformal predictors. In the experiments, the evolved trees are compared to decision trees induced using standard machine learning techniques on 33 publicly available benchmark data sets, with regard to predictive performance and efficiency. The results show that the evolved trees are generally more accurate, and the corresponding conformal predictors more efficient, than their induced counterparts. One important result is that the probability estimates of decision trees when used as conformal predictors should be smoothed, here using the Laplace correction. Finally, using the more discriminating Brier score instead of accuracy as the optimization criterion produced the most efficient conformal predictions.

  • 19.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    König, Rikard
    University of Borås, School of Business and IT.
    Niklasson, Lars
    Genetic Rule Extraction Optimizing Brier Score2010In: Genetic and Evolutionary Computation Conference, GECCO 2010, Proceedings of the 12th annual conference on Genetic and evolutionary computation / [ed] Martin Pelikan, Jürgen Branke, ACM , 2010, p. 1007-1014Conference paper (Refereed)
    Abstract [en]

    Most highly accurate predictive modeling techniques produce opaque models. When comprehensible models are required, rule extraction is sometimes used to generate a transparent model, based on the opaque. Naturally, the extracted model should be as similar as possible to the opaque. This criterion, called fidelity, is therefore a key part of the optimization function in most rule extracting algorithms. To the best of our knowledge, all existing rule extraction algorithms targeting fidelity use 0/1 fidelity, i.e., maximize the number of identical classifications. In this paper, we suggest and evaluate a rule extraction algorithm utilizing a more informed fidelity criterion. More specifically, the novel algorithm, which is based on genetic programming, minimizes the difference in probability estimates between the extracted and the opaque models, by using the generalized Brier score as fitness function. Experimental results from 26 UCI data sets show that the suggested algorithm obtained considerably higher accuracy and significantly better AUC than both the exact same rule extraction algorithm maximizing 0/1 fidelity, and the standard tree inducer J48. Somewhat surprisingly, rule extraction using the more informed fidelity metric normally resulted in less complex models, making sure that the improved predictive performance was not achieved on the expense of comprehensibility.

  • 20.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    Löfström, Tuve
    University of Borås, School of Business and IT.
    Boström, Henrik
    University of Borås, School of Business and IT.
    Overproduce-and-Select: The Grim Reality2013Conference paper (Refereed)
    Abstract [en]

    Overproduce-and-select (OPAS) is a frequently used paradigm for building ensembles. In static OPAS, a large number of base classifiers are trained, before a subset of the available models is selected to be combined into the final ensemble. In general, the selected classifiers are supposed to be accurate and diverse for the OPAS strategy to result in highly accurate ensembles, but exactly how this is enforced in the selection process is not obvious. Most often, either individual models or ensembles are evaluated, using some performance metric, on available and labeled data. Naturally, the underlying assumption is that an observed advantage for the models (or the resulting ensemble) will carry over to test data. In the experimental study, a typical static OPAS scenario, using a pool of artificial neural networks and a number of very natural and frequently used performance measures, is evaluated on 22 publicly available data sets. The discouraging result is that although a fairly large proportion of the ensembles obtained higher test set accuracies, compared to using the entire pool as the ensemble, none of the selection criteria could be used to identify these highly accurate ensembles. Despite only investigating a specific scenario, we argue that the settings used are typical for static OPAS, thus making the results general enough to question the entire paradigm.

  • 21.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    Löfström, Tuve
    University of Borås, School of Business and IT.
    Boström, Henrik
    University of Borås, School of Business and IT.
    Random Brains2013Conference paper (Refereed)
    Abstract [en]

    In this paper, we introduce and evaluate a novel method, called random brains, for producing neural network ensembles. The suggested method, which is heavily inspired by the random forest technique, produces diversity implicitly by using bootstrap training and randomized architectures. More specifically, for each base classifier multilayer perceptron, a number of randomly selected links between the input layer and the hidden layer are removed prior to training, thus resulting in potentially weaker but more diverse base classifiers. The experimental results on 20 UCI data sets show that random brains obtained significantly higher accuracy and AUC, compared to standard bagging of similar neural networks not utilizing randomized architectures. The analysis shows that the main reason for the increased ensemble performance is the ability to produce effective diversity, as indicated by the increase in the difficulty diversity measure.

  • 22.
    Johansson, Ulf
    et al.
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Löfström, Tuve
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Sundell, Håkan
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Linnusson, Henrik
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Gidenstam, Anders
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Boström, Henrik
    School of Information and Communication Technology, Royal Institute of Technology, Sweden.
    Venn predictors for well-calibrated probability estimation trees2018In: 7th Symposium on Conformal and Probabilistic Prediction and Applications: COPA 2018, 11-13 June 2018, Maastricht, The Netherlands / [ed] Alex J. Gammerman and Vladimir Vovk and Zhiyuan Luo and Evgueni N. Smirnov and Ralf L. M. Peeter, 2018, p. 3-14Conference paper (Refereed)
    Abstract [en]

    Successful use of probabilistic classification requires well-calibrated probability estimates, i.e., the predicted class probabilities must correspond to the true probabilities. The standard solution is to employ an additional step, transforming the outputs from a classifier into probability estimates. In this paper, Venn predictors are compared to Platt scaling and isotonic regression, for the purpose of producing well-calibrated probabilistic predictions from decision trees. The empirical investigation, using 22 publicly available datasets, showed that the probability estimates from the Venn predictor were extremely well-calibrated. In fact, in a direct comparison using the accepted reliability metric, the Venn predictor estimates were the most exact on every data set.

  • 23.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    Löfström, Tuve
    University of Borås, School of Business and IT.
    Sönströd, Cecilia
    University of Borås, School of Business and IT.
    Locally Induced Predictive Models2011Conference paper (Refereed)
    Abstract [en]

    Most predictive modeling techniques utilize all available data to build global models. This is despite the wellknown fact that for many problems, the targeted relationship varies greatly over the input space, thus suggesting that localized models may improve predictive performance. In this paper, we suggest and evaluate a technique inducing one predictive model for each test instance, using only neighboring instances. In the experimentation, several different variations of the suggested algorithm producing localized decision trees and neural network models are evaluated on 30 UCI data sets. The main result is that the suggested approach generally yields better predictive performance than global models built using all available training data. As a matter of fact, all techniques producing J48 trees obtained significantly higher accuracy and AUC, compared to the global J48 model. For RBF network models, with their inherent ability to use localized information, the suggested approach was only successful with regard to accuracy, while global RBF models had a better ranking ability, as seen by their generally higher AUCs.

  • 24.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    Sönströd, Cecilia
    University of Borås, School of Business and IT.
    König, Rikard
    University of Borås, School of Business and IT.
    Accurate and Interpretable Regression Trees using Oracle Coaching2014Conference paper (Refereed)
    Abstract [en]

    In many real-world scenarios, predictive models need to be interpretable, thus ruling out many machine learning techniques known to produce very accurate models, e.g., neural networks, support vector machines and all ensemble schemes. Most often, tree models or rule sets are used instead, typically resulting in significantly lower predictive performance. The over- all purpose of oracle coaching is to reduce this accuracy vs. comprehensibility trade-off by producing interpretable models optimized for the specific production set at hand. The method requires production set inputs to be present when generating the predictive model, a demand fulfilled in most, but not all, predic- tive modeling scenarios. In oracle coaching, a highly accurate, but opaque, model is first induced from the training data. This model (“the oracle”) is then used to label both the training instances and the production instances. Finally, interpretable models are trained using different combinations of the resulting data sets. In this paper, the oracle coaching produces regression trees, using neural networks and random forests as oracles. The experiments, using 32 publicly available data sets, show that the oracle coaching leads to significantly improved predictive performance, compared to standard induction. In addition, it is also shown that a highly accurate opaque model can be successfully used as a pre- processing step to reduce the noise typically present in data, even in situations where production inputs are not available. In fact, just augmenting or replacing training data with another copy of the training set, but with the predictions from the opaque model as targets, produced significantly more accurate and/or more compact regression trees.

  • 25.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    Sönströd, Cecilia
    University of Borås, School of Business and IT.
    Linusson, Henrik
    University of Borås, School of Business and IT.
    Boström, Henrik
    University of Borås, School of Business and IT.
    Regression Trees for Streaming Data with Local Performance Guarantees2014Conference paper (Refereed)
    Abstract [en]

    Online predictive modeling of streaming data is a key task for big data analytics. In this paper, a novel approach for efficient online learning of regression trees is proposed, which continuously updates, rather than retrains, the tree as more labeled data become available. A conformal predictor outputs prediction sets instead of point predictions; which for regression translates into prediction intervals. The key property of a conformal predictor is that it is always valid, i.e., the error rate, on novel data, is bounded by a preset significance level. Here, we suggest applying Mondrian conformal prediction on top of the resulting models, in order to obtain regression trees where not only the tree, but also each and every rule, corresponding to a path from the root node to a leaf, is valid. Using Mondrian conformal prediction, it becomes possible to analyze and explore the different rules separately, knowing that their accuracy, in the long run, will not be below the preset significance level. An empirical investigation, using 17 publicly available data sets, confirms that the resulting rules are independently valid, but also shows that the prediction intervals are smaller, on average, than when only the global model is required to be valid. All-in-all, the suggested method provides a data miner or a decision maker with highly informative predictive models of streaming data.

  • 26.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    Sönströd, Cecilia
    University of Borås, School of Business and IT.
    Löfström, Tuve
    University of Borås, School of Business and IT.
    One Tree to Explain Them All2011Conference paper (Refereed)
    Abstract [en]

    Random forest is an often used ensemble technique, renowned for its high predictive performance. Random forests models are, however, due to their sheer complexity inherently opaque, making human interpretation and analysis impossible. This paper presents a method of approximating the random forest with just one decision tree. The approach uses oracle coaching, a recently suggested technique where a weaker but transparent model is generated using combinations of regular training data and test data initially labeled by a strong classifier, called the oracle. In this study, the random forest plays the part of the oracle, while the transparent models are decision trees generated by either the standard tree inducer J48, or by evolving genetic programs. Evaluation on 30 data sets from the UCI repository shows that oracle coaching significantly improves both accuracy and area under ROC curve, compared to using training data only. As a matter of fact, resulting single tree models are as accurate as the random forest, on the specific test instances. Most importantly, this is not achieved by inducing or evolving huge trees having perfect fidelity; a large majority of all trees are instead rather compact and clearly comprehensible. The experiments also show that the evolution outperformed J48, with regard to accuracy, but that this came at the expense of slightly larger trees.

  • 27.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    Sönströd, Cecilia
    University of Borås, School of Business and IT.
    Löfström, Tuve
    University of Borås, School of Business and IT.
    Oracle Coached Decision Trees and Lists2010Conference paper (Refereed)
    Abstract [en]

    This paper introduces a novel method for obtaining increased predictive performance from transparent models in situations where production input vectors are available when building the model. First, labeled training data is used to build a powerful opaque model, called an oracle. Second, the oracle is applied to production instances, generating predicted target values, which are used as labels. Finally, these newly labeled instances are utilized, in different combinations with normal training data, when inducing a transparent model. Experimental results, on 26 UCI data sets, show that the use of oracle coaches significantly improves predictive performance, compared to standard model induction. Most importantly, both accuracy and AUC results are robust over all combinations of opaque and transparent models evaluated. This study thus implies that the straightforward procedure of using a coaching oracle, which can be used with arbitrary classifiers, yields significantly better predictive performance at a low computational cost.

  • 28.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    Sönströd, Cecilia
    University of Borås, School of Business and IT.
    Löfström, Tuwe
    University of Borås, School of Business and IT.
    Boström, Henrik
    Obtaining accurate and comprehensible classifiers using oracle coaching2012In: Intelligent Data Analysis, ISSN 1088-467X, E-ISSN 1571-4128, Vol. Volume 16, no Number 2, p. 247-263Article in journal (Refereed)
    Abstract [en]

    While ensemble classifiers often reach high levels of predictive performance, the resulting models are opaque and hence do not allow direct interpretation. When employing methods that do generate transparent models, predictive performance typically has to be sacrificed. This paper presents a method of improving predictive performance of transparent models in the very common situation where instances to be classified, i.e., the production data, are known at the time of model building. This approach, named oracle coaching, employs a strong classifier, called an oracle, to guide the generation of a weaker, but transparent model. This is accomplished by using the oracle to predict class labels for the production data, and then applying the weaker method on this data, possibly in conjunction with the original training set. Evaluation on 30 data sets from the UCI repository shows that oracle coaching significantly improves predictive performance, measured by both accuracy and area under ROC curve, compared to using training data only. This result is shown to be robust for a variety of methods for generating the oracles and transparent models. More specifically, random forests and bagged radial basis function networks are used as oracles, while J48 and JRip are used for generating transparent models. The evaluation further shows that significantly better results are obtained when using the oracle-classified production data together with the original training data, instead of using only oracle data. An analysis of the fidelity of the transparent models to the oracles shows that performance gains can be expected from increasing oracle performance rather than from increasing fidelity. Finally, it is shown that further performance gains can be achieved by adjusting the relative weights of training data and oracle data.

  • 29.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    Sönströd, Cecilia
    University of Borås, School of Business and IT.
    Norinder, Ulf
    Boström, Henrik
    The Trade-Off between Accuracy and Comprehensibility for Predictive In Silico Modeling2011In: Future Medicinal Chemistry, ISSN 1756-8919, E-ISSN 1756-8927, Vol. 3, no 6, p. 647-663Article in journal (Refereed)
  • 30.
    Johansson, Ulf
    et al.
    University of Borås, School of Business and IT.
    Sönströd, Cecilia
    University of Borås, School of Business and IT.
    Norinder, Ulf
    Boström, Henrik
    Löfström, Tuve
    University of Borås, School of Business and IT.
    Using Feature Selection with Bagging and Rule Extraction in Drug Discovery2010Conference paper (Refereed)
    Abstract [en]

    This paper investigates different ways of combining feature selection with bagging and rule extraction in predictive modeling. Experiments on a large number of data sets from the medicinal chemistry domain, using standard algorithms implemented in theWeka data mining workbench, show that feature selection can lead to significantly improved predictive performance.When combining feature selection with bagging, employing the feature selection on each bootstrap obtains the best result.When using decision trees for rule extraction, the effect of feature selection can actually be detrimental, unless the transductive approach oracle coaching is also used. However, employing oracle coaching will lead to significantly improved performance, and the best results are obtainedwhen performing feature selection before training the opaque model. The overall conclusion is that it can make a substantial difference for the predictive performance exactly how feature selection is used in conjunction with other techniques.

  • 31.
    König, Rikard
    University of Borås, School of Business and IT.
    Enhancing genetic programming for predictive modeling2014Doctoral thesis, monograph (Other academic)
  • 32.
    König, Rikard
    et al.
    University of Borås, School of Business and IT.
    Johansson, Ulf
    University of Borås, School of Business and IT.
    Rule Extraction using Genetic Programming for Accurate Sales Forecasting2014Conference paper (Refereed)
    Abstract [en]

    The purpose of this paper is to propose and evaluate a method for reducing the inherent tendency of genetic programming to overfit small and noisy data sets. In addition, the use of different optimization criteria for symbolic regression is demonstrated. The key idea is to reduce the risk of overfitting noise in the training data by introducing an intermediate predictive model in the process. More specifically, instead of directly evolving a genetic regression model based on labeled training data, the first step is to generate a highly accurate ensemble model. Since ensembles are very robust, the resulting predictions will contain less noise than the original data set. In the second step, an interpretable model is evolved, using the ensemble predictions, instead of the true labels, as the target variable. Experiments on 175 sales forecasting data sets, from one of Sweden’s largest wholesale companies, show that the proposed technique obtained significantly better predictive performance, compared to both straightforward use of genetic programming and the standard M5P technique. Naturally, the level of improvement depends critically on the performance of the intermediate ensemble.

  • 33.
    König, Rikard
    et al.
    University of Borås, School of Business and IT.
    Johansson, Ulf
    University of Borås, School of Business and IT.
    Löfström, Tuve
    University of Borås, School of Business and IT.
    Niklasson, Lars
    Improving GP Classification Performance by Injection of Decision Trees2010Conference paper (Refereed)
    Abstract [en]

    This paper presents a novel hybrid method combining genetic programming and decision tree learning. The method starts by estimating a benchmark level of reasonable accuracy, based on decision tree performance on bootstrap samples of the training set. Next, a normal GP evolution is started with the aim of producing an accurate GP. At even intervals, the best GP in the population is evaluated against the accuracy benchmark. If the GP has higher accuracy than the benchmark, the evolution continues normally until the maximum number of generations is reached. If the accuracy is lower than the benchmark, two things happen. First, the fitness function is modified to allow larger GPs, able to represent more complex models. Secondly, a decision tree with increased size and trained on a bootstrap of the training data is injected into the population. The experiments show that the hybrid solution of injecting decision trees into a GP population gives synergetic effects producing results that are better than using either technique separately. The results, from 18 UCI data sets, show that the proposed method clearly outperforms normal GP, and is significantly better than the standard decision tree algorithm.

  • 34.
    König, Rikard
    et al.
    University of Borås, School of Business and IT.
    Johansson, Ulf
    University of Borås, School of Business and IT.
    Niklasson, Lars
    Finding the Tree in the Forest2010In: Proceeding of IADIS International Conference Applied Computing 2010 / [ed] Hans Weghorn, Pedro Isaías, Radu Vasio, IADIS Press , 2010, p. 135-142Conference paper (Refereed)
    Abstract [en]

    Decision trees are often used for decision support since they are fast to train, easy to understand and deterministic; i.e., always create identical trees from the same training data. This property is, however, only inherent in the actual decision tree algorithm, nondeterministic techniques such as genetic programming could very well produce different trees with similar accuracy and complexity for each execution. Clearly, if more than one solution exists, it would be misleading to present a single tree to a decision maker. On the other hand, too many alternatives could not be handled manually, and would only lead to confusion. Hence, we argue for a method aimed at generating a suitable number of alternative decision trees with comparable accuracy and complexity. When too many alternative trees exist, they are grouped and representative accurate solutions are selected from each group. Using domain knowledge, a decision maker could then select a single best tree and, if required, be presented with a small set of similar solutions, in order to further improve his decisions. In this paper, a method for generating alternative decision trees is suggested and evaluated. All in all,four different techniques for selecting accurate representative trees from groups of similar solutions are presented. Experiments on 19 UCI data sets show that it often exist dozens of alternative trees, and that one of the evaluated techniques clearly outperforms all others for selecting accurate and representative models.

  • 35.
    König, Rikard
    et al.
    University of Borås, School of Business and IT.
    Johansson, Ulf
    University of Borås, School of Business and IT.
    Niklasson, Lars
    G-REX: A Versatile Framework for Evolutionary Data Mining2008Conference paper (Refereed)
  • 36.
    König, Rikard
    et al.
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Johansson, Ulf
    Jönköping University.
    Riveiro, Maria
    Högskolan i Skövde.
    Brattberg, Peter
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Modeling Golf Player Skill Using Machine Learning2017In: International Cross-Domain Conference for Machine Learning and Knowledge Extraction: CD-MAKE 2017: Machine Learning and Knowledge Extraction, Calabri, 2017, p. 275-294Conference paper (Refereed)
    Abstract [en]

    In this study we apply machine learning techniques to Modeling Golf Player Skill using a dataset consisting of 277 golfers. The dataset includes 28 quantitative metrics, related to the club head at impact and ball flight, captured using a Doppler-radar. For modeling, cost-sensitive decision trees and random forest are used to discern between less skilled players and very good ones, i.e., Hackers and Pros. The results show that both random forest and decision trees achieve high predictive accuracy, with regards to true positive rate, accuracy and area under the ROC-curve. A detailed interpretation of the decision trees shows that they concur with modern swing theory, e.g., consistency is very important, while face angle, club path and dynamic loft are the most important evaluated swing factors, when discerning between Hackers and Pros. Most of the Hackers could be identified by a rather large deviation in one of these values compared to the Pros. Hackers, which had less variation in these aspects of the swing, could instead be identified by a steeper swing plane and a lower club speed. The importance of the swing plane is an interesting finding, since it was not expected and is not easy to explain.

  • 37.
    Linnusson, Henrik
    et al.
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Johansson, Ulf
    Dept. of Computer Science and Informatics, Jönköping University.
    Boström, Henrik
    School of Electrical Engineering and Computer Science, Royal Institute of Technology.
    Tuve, Löfström
    Dept. of Computer Science and Informatics, Jönköping University.
    Classification With Reject Option Using Conformal Prediction2018Conference paper (Refereed)
    Abstract [en]

    In this paper, we propose a practically useful means of interpreting the predictions produced by a conformal classifier. The proposed interpretation leads to a classifier with a reject option, that allows the user to limit the number of erroneous predictions made on the test set, without any need to reveal the true labels of the test objects. The method described in this paper works by estimating the cumulative error count on a set of predictions provided by a conformal classifier, ordered by their confidence. Given a test set and a user-specified parameter k, the proposed classification procedure outputs the largest possible amount of predictions containing on average at most k errors, while refusing to make predictions for test objects where it is too uncertain. We conduct an empirical evaluation using benchmark datasets, and show that we are able to provide accurate estimates for the error rate on the test set.

  • 38.
    Linusson, Henrik
    et al.
    University of Borås, School of Business and IT.
    Johansson, Ulf
    University of Borås, School of Business and IT.
    Boström, Henrik
    University of Borås, School of Business and IT.
    Löfström, Tuve
    University of Borås, School of Business and IT.
    Efficiency Comparison of Unstable Transductive and Inductive Conformal Classifiers2014Conference paper (Refereed)
    Abstract [en]

    In the conformal prediction literature, it appears axiomatic that transductive conformal classifiers possess a higher predictive efficiency than inductive conformal classifiers, however, this depends on whether or not the nonconformity function tends to overfit misclassified test examples. With the conformal prediction framework’s increasing popularity, it thus becomes necessary to clarify the settings in which this claim holds true. In this paper, the efficiency of transductive conformal classifiers based on decision tree, random forest and support vector machine classification models is compared to the efficiency of corresponding inductive conformal classifiers. The results show that the efficiency of conformal classifiers based on standard decision trees or random forests is substantially improved when used in the inductive mode, while conformal classifiers based on support vector machines are more efficient in the transductive mode. In addition, an analysis is presented that discusses the effects of calibration set size on inductive conformal classifier efficiency.

  • 39.
    Linusson, Henrik
    et al.
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Johansson, Ulf
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Boström, Henrik
    Löfström, Tuwe
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Reliable Confidence Predictions Using Conformal Prediction2016In: Lecture Notes in Computer Science, 2016, Vol. 9651, p. 77-88Conference paper (Refereed)
    Abstract [en]

    Conformal classiers output condence prediction regions, i.e., multi-valued predictions that are guaranteed to contain the true output value of each test pattern with some predened probability. In order to fully utilize the predictions provided by a conformal classier, it is essential that those predictions are reliable, i.e., that a user is able to assess the quality of the predictions made. Although conformal classiers are statistically valid by default, the error probability of the prediction regions output are dependent on their size in such a way that smaller, and thus potentially more interesting, predictions are more likely to be incorrect. This paper proposes, and evaluates, a method for producing rened error probability estimates of prediction regions, that takes their size into account. The end result is a binary conformal condence predictor that is able to provide accurate error probability estimates for those prediction regions containing only a single class label.

  • 40.
    Linusson, Henrik
    et al.
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Norinder, Ulf
    Swetox, Karolinska Institutet.
    Boström, Henrik
    Dept. of Computer Science and Informatics, Stockholm University.
    Johansson, Ulf
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Löfström, Tuve
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    On the Calibration of Aggregated Conformal Predictors2017In: Proceedings of Machine Learning Research, 2017Conference paper (Refereed)
    Abstract [en]

    Conformal prediction is a learning framework that produces models that associate witheach of their predictions a measure of statistically valid confidence. These models are typi-cally constructed on top of traditional machine learning algorithms. An important result ofconformal prediction theory is that the models produced are provably valid under relativelyweak assumptions—in particular, their validity is independent of the specific underlyinglearning algorithm on which they are based. Since validity is automatic, much research onconformal predictors has been focused on improving their informational and computationalefficiency. As part of the efforts in constructing efficient conformal predictors, aggregatedconformal predictors were developed, drawing inspiration from the field of classification andregression ensembles. Unlike early definitions of conformal prediction procedures, the va-lidity of aggregated conformal predictors is not fully understood—while it has been shownthat they might attain empirical exact validity under certain circumstances, their theo-retical validity is conditional on additional assumptions that require further clarification.In this paper, we show why validity is not automatic for aggregated conformal predictors,and provide a revised definition of aggregated conformal predictors that gains approximatevalidity conditional on properties of the underlying learning algorithm.

  • 41.
    Löfström, Tuve
    et al.
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Boström, Henrik
    Stockholm University, Department of Computer and Systems Sciences.
    Linusson, Henrik
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Johansson, Ulf
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Bias Reduction through Conditional Conformal Prediction2015In: Intelligent Data Analysis, ISSN 1088-467X, E-ISSN 1571-4128, Vol. 19, no 6, p. 1355-1375Article in journal (Refereed)
  • 42.
    Löfström, Tuve
    et al.
    University of Borås, School of Business and IT.
    Johansson, Ulf
    University of Borås, School of Business and IT.
    Boström, Henrik
    Comparing Methods for Generating Diverse Ensembles of Artificial Neural Networks2010Conference paper (Refereed)
    Abstract [en]

    It is well-known that ensemble performance relies heavily on sufficient diversity among the base classifiers. With this in mind, the strategy used to balance diversity and base classifier accuracy must be considered a key component of any ensemble algorithm. This study evaluates the predictive performance of neural network ensembles, specifically comparing straightforward techniques to more sophisticated. In particular, the sophisticated methods GASEN and NegBagg are compared to more straightforward methods, where each ensemble member is trained independently of the others. In the experimentation, using 31 publicly available data sets, the straightforward methods clearly outperformed the sophisticated methods, thus questioning the use of the more complex algorithms.

  • 43.
    Löfström, Tuve
    et al.
    University of Borås, School of Business and IT.
    Johansson, Ulf
    University of Borås, School of Business and IT.
    Boström, Henrik
    University of Borås, School of Business and IT.
    Effective Utilization of Data in Inductive Conformal Prediction2013Conference paper (Refereed)
    Abstract [en]

    Conformal prediction is a new framework producing region predictions with a guaranteed error rate. Inductive conformal prediction (ICP) was designed to significantly reduce the computational cost associated with the original transductive online approach. The drawback of inductive conformal prediction is that it is not possible to use all data for training, since it sets aside some data as a separate calibration set. Recently, cross-conformal prediction (CCP) and bootstrap conformal prediction (BCP) were proposed to overcome that drawback of inductive conformal prediction. Unfortunately, CCP and BCP both need to build several models for the calibration, making them less attractive. In this study, focusing on bagged neural network ensembles as conformal predictors, ICP, CCP and BCP are compared to the very straightforward and cost-effective method of using the out-of-bag estimates for the necessary calibration. Experiments on 34 publicly available data sets conclusively show that the use of out-of-bag estimates produced the most efficient conformal predictors, making it the obvious preferred choice for ensembles in the conformal prediction framework.

  • 44.
    Löfström, Tuve
    et al.
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Linnusson, Henrik
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Sönströd, Cecilia
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Johansson, Ulf
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    System Health Monitoring using Conformal Anomaly Detection2015Report (Other (popular science, discussion, etc.))
  • 45.
    Löfström, Tuve
    et al.
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Zhao, Jing
    University of Stockholm.
    Linnusson, Henrik
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Jansson, Karl
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Predicting Adverse Drug Events with Confidence2015In: Thirteenth Scandinavian Conference on Artificial Intelligence / [ed] Sławomir Nowaczyk, IOS Press, 2015Conference paper (Refereed)
    Abstract [en]

    This study introduces the conformal prediction framework to the task of predicting the presence of adverse drug events in electronic health records with an associated measure of statistically valid confidence. The imbalanced nature of the problem was addressed both by evaluating different machine learning algorithms, and by comparing different types of conformal predictors. A novel solution was also evaluated, where different underlying models, each model optimized towards one particular class, were combined into a single conformal predictor. This novel solution proved to be superior to previously existing approaches.

  • 46.
    Löfström, Tuwe
    University of Borås, Faculty of Librarianship, Information, Education and IT. Stockholms universitet, Institutionen för data- och systemvetenskap.
    On Effectively Creating Ensembles of Classifiers: Studies on Creation Strategies, Diversity and Predicting with Confidence2015Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    An ensemble is a composite model, combining the predictions from several other models. Ensembles are known to be more accurate than single models. Diversity has been identified as an important factor in explaining the success of ensembles. In the context of classification, diversity has not been well defined, and several heuristic diversity measures have been proposed. The focus of this thesis is on how to create effective ensembles in the context of classification. Even though several effective ensemble algorithms have been proposed, there are still several open questions regarding the role diversity plays when creating an effective ensemble. Open questions relating to creating effective ensembles that are addressed include: what to optimize when trying to find an ensemble using a subset of models used by the original ensemble that is more effective than the original ensemble; how effective is it to search for such a sub-ensemble; how should the neural networks used in an ensemble be trained for the ensemble to be effective? The contributions of the thesis include several studies evaluating different ways to optimize which sub-ensemble would be most effective, including a novel approach using combinations of performance and diversity measures. The contributions of the initial studies presented in the thesis eventually resulted in an investigation of the underlying assumption motivating the search for more effective sub-ensembles. The evaluation concluded that even if several more effective sub-ensembles exist, it may not be possible to identify which sub-ensembles would be the most effective using any of the evaluated optimization measures. An investigation of the most effective ways to train neural networks to be used in ensembles was also performed. The conclusions are that effective ensembles can be obtained by training neural networks in a number of different ways but that high average individual accuracy or much diversity both would generate effective ensembles. Several findings regarding diversity and effective ensembles presented in the literature in recent years are also discussed and related to the results of the included studies. When creating confidence based predictors using conformal prediction, there are several open questions regarding how data should be utilized effectively when using ensembles. Open questions related to predicting with confidence that are addressed include: how can data be utilized effectively to achieve more efficient confidence based predictions using ensembles; how do problems with class imbalance affect the confidence based predictions when using conformal prediction? Contributions include two studies where it is shown in the first that the use of out-of-bag estimates when using bagging ensembles results in more effective conformal predictors and it is shown in the second that a conformal predictor conditioned on the class labels to avoid a strong bias towards the majority class is more effective on problems with class imbalance. The research method used is mainly inspired by the design science paradigm, which is manifested by the development and evaluation of artifacts. 

  • 47.
    Löfström, Tuwe
    et al.
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Johansson, Ulf
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Balkow, Jenny
    Sundell, Håkan
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    A data-driven approach to online fitting services2018In: Data Science and Knowledge Engineering for Sensing Decision Support / [ed] Jun Liu (Ulster University, UK), Jie Lu (University of Technology Sydney, Australia), Yang Xu (Southwest Jiaotong University, China), Luis Martinez (University of Jaén, Spain) and Etienne E Kerre (University of Ghent, Belgium), 2018, p. 1559-1566Conference paper (Refereed)
    Abstract [en]

    Being able to accurately predict several attributes related to size is vital for services supporting online fitting. In this paper, we investigate a data-driven approach, while comparing two different supervised modeling techniques for predictive regression; standard multiple linear regression and neural networks. Using a fairly large, publicly available, data set of high quality, the main results are somewhat discouraging. Specifically, it is questionable whether key attributes like sleeve length, neck size, waist and chest can be modeled accurately enough using easily accessible input variables as sex, weight and height. This is despite the fact that several services online offer exactly this functionality. For this specific task, the results show that standard linear regression was as accurate as the potentially more powerful neural networks. Most importantly, comparing the predictions to reasonable levels for acceptable errors, it was found that an overwhelming majority of all instances had at least one attribute with an unacceptably high prediction error. In fact, if requiring that all variables are predicted with an acceptable accuracy, less than 5% of all instances met that criterion. Specifically, for females, the success rate was as low as 1.8%.

  • 48.
    Magnusson, Andreas
    University of Borås, School of Engineering.
    Evolutionary optimisation of a morphological image processor for embedded systems2008Doctoral thesis, monograph (Other academic)
    Abstract [en]

    The work presented in this thesis concerns the design, development and implementation of two digital components to be used, primarily, in autonomously operating embedded systems, such as mobile robots. The first component is an image coprocessor, for high-speed morphological image processing, and the second is a hardware-based genetic algorithm coprocessor, which provides evolutionary computation functionality for embedded applications. The morphological image coprocessor, the Clutter-II, has been optimised for efficiency of implementation, processing speed and system integration. The architecture employs a compact hardware structure for its implementation of the morphological neighbourhood transformations. The compact structure realises a significantly reduced hardware resource cost. The resources saved by the compact structure can be used to increase parallelism in image processing operations, thereby improving processing speed in a similarly significant manner. The design of the Clutter-II as a coprocessor enables easy-to-use and efficient access to its image processing capabilities from the host system processor and application software. High-speed input-output interfaces, with separated instruction and data buses, provide effective communication with system components external to the Clutter-II. A substantial part of the work presented in this thesis concerns the practical implementation of morphological filters for the Clutter-II, using the compact transformation structure. To derive efficient filter implementations, a genetic algorithm has been developed. The algorithm optimises the filter implementation by minimising the number of operations required for a particular filter. The experience gained from the work on the genetic algorithm inspired the development of the second component, the HERPUC. HERPUC is a hardware-based genetic algorithm processor, which employs a novel hardware implementation of the selection mechanism of the algorithm. This, in combination with a flexible form of recombination operator, has made the HERPUC an efficient hardware implementation of a genetic algorithm. Results indicate that the HERPUC is able to solve the set of test problems, to which it has been applied, using fewer fitness evaluations and a smaller population size, than previous hardware-based genetic algorithm implementations.

  • 49. Najim, Safa A.
    et al.
    Lim, Ik Soo
    Wittek, Peter
    University of Borås, Faculty of Librarianship, Information, Education and IT.
    Jones, Mark
    FSPE: Visualisation of Hyperspectral Imagery Using Faithful Stochastic Proximity Embedding2015In: IEEE Geoscience and Remote Sensing Letters, ISSN 1545-598X, E-ISSN 1558-0571, Vol. 12, no 1, p. 18-22Article in journal (Refereed)
    Abstract [en]

    Hyperspectral image visualization reduces color bands to three, but prevailing linear methods fail to address data characteristics, and nonlinear embeddings are computationally demanding. Qualitative evaluation of an embedding is also lacking. We propose Faithful Stochastic Proximity Embedding (FSPE), a scalable, nonlinear dimensionality reduction method. FSPE considers the nonlinear characteristics of spectral signatures, yet it avoids the costly computation of geodesic distances that are often required by other nonlinear methods. Furthermore, we introduce a point-wise metric that measures the quality of hyperspectral image visualization at each pixel. FSPE outperforms the state-of-art methods by at least 12% on average, and up to 25% in the proposed qualitative measure. An implementation on Graphics Processing Units (GPUs) is two magnitudes faster than the baseline. Our method opens the path to high-fidelity, real-time analysis of hyperspectral images.

  • 50. Nguyen, Nhan
    et al.
    Tsigas, Philippas
    Sundell, Håkan
    University of Borås, School of Business and IT.
    Brief Announcement: ParMarkSplit: A Parallel Mark-Split Garbage Collector Based on a Lock-Free Skip-List2013Conference paper (Refereed)
    Abstract [en]

    This brief announcement provides a high level overview of a parallel mark-split garbage collector. Our parallel design introduces and makes use of an efficient concurrency control mechanism based on a lock-free skip-list design for handling the list of free memory inter- vals. We have implemented the parallel mark-split garbage collector in OpenJDK HotSpot as a parallel and concurrent garbage collector for the old generation. We experimentally evaluate the collector and compare it with the default concurrent mark-sweep garbage collector in OpenJDK HotSpot, using the DaCapo benchmarks.

12 1 - 50 of 67
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf