| 1. |
- Lu, Zhihan, et al.
(författare)
-
Multimodal Hand and Foot Gesture Interaction for Handheld Devices
- 2014
-
Ingår i: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP). - : Association for Computing Machinery (ACM). - 1551-6857 .- 1551-6865. ; 11:1
-
Tidskriftsartikel (refereegranskat)abstract
- We present a hand-and-foot-based multimodal interaction approach for handheld devices. Our method combines input modalities (i.e., hand and foot) and provides a coordinated output to both modalities along with audio and video. Human foot gesture is detected and tracked using contour-based template detection (CTD) and Tracking-Learning-Detection (TLD) algorithm. 3D foot pose is estimated from passive homography matrix of the camera. 3D stereoscopic and vibrotactile are used to enhance the immersive feeling. We developed a multimodal football game based on the multimodal approach as a proof-of-concept. We confirm our systems user satisfaction through a user study.
|
|
| 2. |
- Sutinen, Martti, et al.
(författare)
-
Web-Based Analytical Decision Support System
- 2010
-
Ingår i: Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10. - : IEEE conference proceedings. - 9781424481347 - 9781424481354 ; , s. 575-579
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a web-application supporting structured decision modelling and analysis. The application allows for decision modelling with respect to different preferences and views, allowing for numerically imprecise and vague background probabilities, values, and criteria weights, which further can be adjusted in an interactive fashion when considering calculated decision outcomes. The web-application is based on a decision tool that has been used in a large number of different domains over the last 15 years, ranging from investment decision analysis for companies to public decision support for local governments.
|
|
| 3. |
- Grünloh, Christiane, 1980-, et al.
(författare)
-
"why do they need to check me?" patient participation through ehealth and the doctor-patient relationship : Qualitative study
- 2018
-
Ingår i: Journal of Medical Internet Research. - : J M I R Publications, Inc.. - 1438-8871. ; 20:1
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Roles in the doctor-patient relationship are changing and patient participation in health care is increasingly emphasized. Electronic health (eHealth) services such as patient accessible electronic health records (PAEHRs) have been implemented to support patient participation. Little is known about practical use of PAEHR and its effect on roles of doctors and patients. Objective: This qualitative study aimed to investigate how physicians view the idea of patient participation, in particular in relation to the PAEHR system. Hereby, the paper aims to contribute to a deeper understanding of physicians' constructions of PAEHR, roles in the doctor-patient relationship, and levels and limits of involvement. Methods: A total of 12 semistructured interviews were conducted with physicians in different fields. Interviews were transcribed, translated, and a theoretically informed thematic analysis was performed. Results: Two important aspects were identified that are related to the doctor-patient relationship: roles and involvement. The physicians viewed their role as being the ones to take on the responsibility, determining treatment options, and to be someone who should be trusted. In relation to the patient's role, lack of skills (technical or regarding medical jargon), motives to read, and patients' characteristics were aspects identified in the interviews. Patients were often referred to as static entities disregarding their potential to develop skills and knowledge over time. Involvement captures aspects that support or hinder patients to take an active role in their care. Conclusions: Literature of at least two decades suggests an overall agreement that the paternalistic approach in health care is inappropriate, and a collaborative process with patients should be adopted. Although the physicians in this study stated that they, in principle, were in favor of patient participation, the analysis found little support in their descriptions of their daily practice that participation is actualized. As seen from the results, paternalistic practices are still present, even if professionals might not be aware of this. This can create a conflict between patients who strive to become more informed and their questions being interpreted as signs of critique and mistrust toward the physician. We thus believe that the full potential of PAEHRs is not reached yet and argue that the concept of patient empowerment is problematic as it triggers an interpretation of "power" in health care as a zero-sum, which is not helpful for the maintenance of the relationship between the actors. Patient involvement is often discussed merely in relation to decision making; however, this study emphasizes the need to include also sensemaking and learning activities. This would provide an alternative understanding of patients asking questions, not in terms of "monitoring the doctor" but to make sense of the situation.
|
|
| 4. |
- Hansson, Karin, et al.
(författare)
-
A framework for evaluation of flood management strategies
- 2008
-
Ingår i: Journal of Environmental Management. - : Elsevier BV. - 0301-4797 .- 1095-8630. ; 86:3, s. 465-480
-
Tidskriftsartikel (refereegranskat)abstract
- The resulting impact of disasters on society depends on the affected country's economic strength prior to the disaster. The larger the disaster and the smaller the economy, the more significant is the impact. This is clearest seen in developing countries, where weak economics become even weaker afterwards. Deliberate strategies for the sharing of losses from hazardous events may aid a country or a community in efficiently using scarce prevention and mitigation resources, thus being better prepared for the effects of a disaster. Nevertheless, many governments lack an adequate institutional system for applying cost effective and reliable technologies for disaster prevention, early warnings, and mitigation. Modelling by event analyses and strategy models is one way of planning ahead, but these models have so far not been linked together. An approach to this problem was taken during a large study in Hungary, the Tisza case study, where a number of policy strategies for spreading of flood loss were formulated. In these strategies, a set of parameters of particular interest were extracted from interviews with stakeholders in the region. However, the study was focused on emerging economies, and, in particular, on insurance strategies. The scope is now extended to become a functional framework also for developing countries. In general, they have a higher degree of vulnerability. The paper takes northern Vietnam as an example of a developing region. We identify important parameters and discuss their importance for flood strategy formulations. Based on the policy strategies in the Tisza case, we extract data from the strategies and propose a framework for loss spread in developing and emerging economics. The parameter set can straightforwardly be included in a simulation and decision model for policy formulation and evaluation, taking multiple stakeholders into account.
|
|
| 5. |
- Johansson, Ronnie, et al.
(författare)
-
A Study on Class-Specifically Discounted Belief for Ensemble Classifiers
- 2008
-
Ingår i: 2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. - : IEEE. - 9781424421442 - 9781424421435 ; , s. 614-619
-
Konferensbidrag (refereegranskat)abstract
- Ensemble classifiers are known to generally perform better than their constituent classifiers. Whereas a lot of work has been focusing on the generation of classifiers for ensembles, much less attention has been given to the fusion of individual classifier outputs. One approach to fuse the outputs is to apply Shafer’s theory of evidence, which provides a flexible framework for expressing and fusing beliefs. However, representing and fusing beliefs is non-trivial since it can be performed in a multitude of ways within the evidential framework. In a previous article, we compared different evidential combination rules for ensemble fusion. The study involved a single belief representation which involved discounting (i.e., weighting) the classifier outputs with classifier reliability. The classifier reliability was interpreted as the classifier’s estimated accuracy, i.e., the percentage of correctly classified examples. However, classifiers may have different performance for different classes and in this work we assign the reliability of a classifier output depending on the classspecific reliability of the classifier. Using 27 UCI datasets, we compare the two different ways of expressing beliefs and some evidential combination rules. The result of the study indicates that there is indeed an advantage of utilizing class-specific reliability compared to accuracy in an evidential framework for combining classifiers in the ensemble design considered.
|
|
| 6. |
- Johansson, Ulf, et al.
(författare)
-
Conformal Prediction Using Decision Trees
- 2013
-
Ingår i: IEEE 13th International Conference on Data Mining (ICDM). - : IEEE Computer Society. - 9780769551081 ; , s. 330-339
-
Konferensbidrag (refereegranskat)abstract
- 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.
|
|
| 7. |
- Johansson, Ulf, et al.
(författare)
-
Evolved Decision Trees as Conformal Predictors
- 2013
-
Ingår i: 2013 IEEE Congress on Evolutionary Computation (CEC). - : IEEE. - 9781479904532 ; , s. 1794-1801
-
Konferensbidrag (refereegranskat)abstract
- 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.
|
|
| 8. |
- Johansson, Ulf, et al.
(författare)
-
Extending Nearest Neighbor Classification with Spheres of Confidence
- 2008
-
Ingår i: Proceedings of the Twenty-First International FLAIRS Conference (FLAIRS 2008). - : AAAI Press. - 9781577353652 ; , s. 282-287
-
Konferensbidrag (refereegranskat)abstract
- The standard kNN algorithm suffers from two major drawbacks: sensitivity to the parameter value k, i.e., the number of neighbors, and the use of k as a global constant that is independent of the particular region in which theexample to be classified falls. Methods using weighted voting schemes only partly alleviate these problems, since they still involve choosing a fixed k. In this paper, a novel instance-based learner is introduced that does not require kas a parameter, but instead employs a flexible strategy for determining the number of neighbors to consider for the specific example to be classified, hence using a local instead of global k. A number of variants of the algorithm are evaluated on 18 datasets from the UCI repository. The novel algorithm in its basic form is shown to significantly outperform standard kNN with respect to accuracy, and an adapted version of the algorithm is shown to be clearlyahead with respect to the area under ROC curve. Similar to standard kNN, the novel algorithm still allows for various extensions, such as weighted voting and axes scaling.
|
|
| 9. |
- Johansson, Ulf, et al.
(författare)
-
Overproduce-and-Select : The Grim Reality
- 2013
-
Ingår i: 2013 IEEE Symposium on Computational Intelligence and Ensemble Learning (CIEL). - : IEEE. - 9781467358538 ; , s. 52-59
-
Konferensbidrag (refereegranskat)abstract
- 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.
|
|
| 10. |
- Johansson, Ulf, et al.
(författare)
-
Random Brains
- 2013
-
Ingår i: The 2013 International Joint Conference on Neural Networks (IJCNN). - : IEEE. - 9781467361286 ; , s. 1-8
-
Konferensbidrag (refereegranskat)abstract
- 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.
|
|
