| 1. |
- Aagerup, Ulf, 1969-
(författare)
-
To sell or not to sell: overweight users’ effect on fashion assortments
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Overweight people claim to be mistreated by the fashion industry. Fashion companies disagree. Despite the controversy, actual research has been scarce. This study compares the sizes of clothes the four leading mass marketing fashion retailers in Sweden offer to the body sizes of the population. Although branding theory would support the idea of rejecting fat consumers to improve user imagery for fashion brands, such practices were not evident. The main contribution of this paper is that it provides the first quantified empirical evidence on the theory of typical user imagery.In the discussion, it is posited that although mass market fashion brands should be susceptible to negative user imagery related to overweight and obese users, the companies avoid such problems by making garments that are not directly attributable to a specific brand, thus mitigating the negative effect of overweight and obese user imagery.
|
|
| 2. |
- Aagerup, Ulf, 1969-
(författare)
-
User BMI effects on mass market fashion brands
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Purpose: The purpose of this paper is to investigate how the weight of users affects the perception of mass market fashion brands.Design/methodology/approach: This study attempts to show effects of typical - as well as ideal user imagery on fashion brands. An experiment was carried out in which 1848 university students replied to a web survey, rating the brand personality of jeans and shirts according to Aaker’s Big Five construct. The garments were worn by digitally manipulated versions of one person as thin, overweight, and obese.Findings: The findings show that consumers’ impressions of mass market fashion brands are significantly affected by the weight of its users. The effect of male user imagery is ambiguous. For women’s fashion on the other hand, slender users are to be preferred.Research limitations/implications: It is possible, even probable, that high fashion would suffer more from negative typical user imagery than would mass market fashion. It would therefore be interesting to replicate this experiment using clothes of higher fashion grade and price.Practical implications: The demonstrated effects of user imagery support the industry practice of slim ideal female imagery. However, excluding customers to boost brand perception should not be an option for these brands.Social implications: The results inform the debate over skinny models vs. “real women” in advertising as well as the debate over discrimination of overweight consumers through assortment decisions.Originality/value: This is the first time typical user imagery effects are included in a study of this type, and it is the first study to test user imagery effects on fashion.
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
- Alabdallah, Abdallah, 1979-, et al.
(författare)
-
Understanding Survival Models through Counterfactual Explanations
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- The development of black-box survival models has created a need for methods that explain their outputs, just as in the case of traditional machine learning methods. Survival models usually predict functions rather than point estimates. This special nature of their output makes it more difficult to explain their operation. We propose a method to generate plausible counterfactual explanations for survival models. The method supports two options that handle the special nature of survival models' output. One option relies on the Survival Scores, which are based on the area under the survival function, which is more suitable for proportional hazard models. The other one relies on Survival Patterns in the predictions of the survival model, which represent groups that are significantly different from the survival perspective. This guarantees an intuitive well-defined change from one risk group (Survival Pattern) to another and can handle more realistic cases where the proportional hazard assumption does not hold. The method uses a Particle Swarm Optimization algorithm to optimize a loss function to achieve four objectives: the desired change in the target, proximity to the explained example, likelihood, and the actionability of the counterfactual example. Two predictive maintenance datasets and one medical dataset are used to illustrate the results in different settings. The results show that our method produces plausible counterfactuals, which increase the understanding of black-box survival models.
|
|
| 6. |
- Aldrin, Emilia, 1982-
(författare)
-
Äntligen är NoSo här!
- 2021
-
Annan publikation (populärvet., debatt m.m.)
|
|
| 7. |
|
|
| 8. |
- Altarabichi, Mohammed Ghaith, 1981-, et al.
(författare)
-
Improving Concordance Index in Regression-based Survival Analysis : Discovery of Loss Function for Neural Networks
- 2024
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- In this work, we use an Evolutionary Algorithm (EA) to discover a novel Neural Network (NN) regression-based survival loss function with the aim of improving the C-index performance. Our contribution is threefold; firstly, we propose an evolutionary meta-learning algorithm SAGA$_{loss}$ for optimizing a neural-network regression-based loss function that maximizes the C-index; our algorithm consistently discovers specialized loss functions that outperform MSCE. Secondly, based on our analysis of the evolutionary search results, we highlight a non-intuitive insight that signifies the importance of the non-zero gradient for the censored cases part of the loss function, a property that is shown to be useful in improving concordance. Finally, based on this insight, we propose MSCE$_{Sp}$, a novel survival regression loss function that can be used off-the-shelf and generally performs better than the Mean Squared Error for censored cases. We performed extensive experiments on 19 benchmark datasets to validate our findings.
|
|
| 9. |
- Altarabichi, Mohammed Ghaith, 1981-, et al.
(författare)
-
Rolling the Dice for Better Deep Learning Performance : A Study of Randomness Techniques in Deep Neural Networks
- 2024
-
Annan publikation (populärvet., debatt m.m.)abstract
- This paper presents a comprehensive empirical investigation into the interactions between various randomness techniques in Deep Neural Networks (DNNs) and how they contribute to network performance. It is well-established that injecting randomness into the training process of DNNs, through various approaches at different stages, is often beneficial for reducing overfitting and improving generalization. However, the interactions between randomness techniques such as weight noise, dropout, and many others remain poorly understood. Consequently, it is challenging to determine which methods can be effectively combined to optimize DNN performance. To address this issue, we categorize the existing randomness techniques into four key types: data, model, optimization, and learning. We use this classification to identify gaps in the current coverage of potential mechanisms for the introduction of noise, leading to proposing two new techniques: adding noise to the loss function and random masking of the gradient updates.In our empirical study, we employ a Particle Swarm Optimizer (PSO) to explore the space of possible configurations to answer where and how much randomness should be injected to maximize DNN performance. We assess the impact of various types and levels of randomness for DNN architectures applied to standard computer vision benchmarks: MNIST, FASHION-MNIST, CIFAR10, and CIFAR100. Across more than 30\,000 evaluated configurations, we perform a detailed examination of the interactions between randomness techniques and their combined impact on DNN performance. Our findings reveal that randomness in data augmentation and in weight initialization are the main contributors to performance improvement. Additionally, correlation analysis demonstrates that different optimizers, such as Adam and Gradient Descent with Momentum, prefer distinct types of randomization during the training process. A GitHub repository with the complete implementation and generated dataset is available\footnote[1]{https://github.com/Ghaith81/Radnomness\_in\_Neural\_Network}.
|
|
| 10. |
- Andersson, Åsa, et al.
(författare)
-
Effects on serum protein levels from one bout of high intensity interval training in individuals with axial spondyloarthritis and controls
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Background: Axial spondyloarthritis (axSpA) is a chronic inflammatory disease primarily affecting the axial skeleton causing pain, inflammation, and stiffness. Individuals with axSpA are at greater risk of developing cardiovascular disease, which can be counteracted by physical activity. High-intensity interval training (HIIT) has been shown to improve cardiovascular health, but the effect on disease activity and the level of inflammation in axSpA has been less studied. With the aim of investigating how levels of inflammatory cytokines, myokines, and protein markers for bone metabolism are acutely affected by one bout of HIIT, we studied serum from individuals with axSpA and healthy controls (HC). Methods: Ten participants with axSpA and 11 age- and sex-matched HC performed a single HIIT bout on a cycle ergometer: 4x4 minutes intervals with three minutes active rest in between. Blood samples were taken before and one hour after the HIIT bout. Serum proteins (IL-6, IL-17, IL-18, TNFa, CXCL-10, VEGF-A, BDNF, DKK-1, osteoprotegerin, osteocalcin, osteopontin, BMP-7, CRP) were analyzed with a Luminex system or ELISA. Descriptive data are presented as mean with standard deviation. A two-way ANOVA was used for comparisons. Results: A main effect from baseline to one hour post HIIT showed that both groups had a significant increase in serum levels (pg/ml) of IL-6: axSpA 2.2 (3.0) to 3.2 (1.8) and HC 0.4 (0.4) to 1.9 (2.0), p=0.03. VEGF-A (pg/ml) was significantly lower in the axSpA group: 159 (138) vs. HC 326 (184), p=0.03, but was not affected by the HIIT bout. BMP-7 (ng/ml) increased in both groups after the HIIT: axSpA 61.6 (13.1) to 75.2 (20.0) and HC 64.6 (20.8 to 75.0 (17.8), p<0.001. For the other proteins analyzed, there were no significant differences in serum concentrations between individuals with axSpA and HC, or within the two groups before and after one bout of HIIT. Conclusions: One acute bout of HIIT significantly increases the serum concentrations of IL-6 and BMP-7 after 1 hour in both individuals with axSpA and HC.
|
|
