| 1. |
- Norlund, Tobias, 1991, et al.
(författare)
-
Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it?
- 2021
-
Ingår i: Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pp. 149-162, Punta Cana, Dominican Republic. - : Association for Computational Linguistics.
-
Konferensbidrag (refereegranskat)abstract
- Large language models are known to suffer from the hallucination problem in that they are prone to output statements that are false or inconsistent, indicating a lack of knowledge. A proposed solution to this is to provide the model with additional data modalities that complements the knowledge obtained through text. We investigate the use of visual data to complement the knowledge of large language models by proposing a method for evaluating visual knowledge transfer to text for uni- or multimodal language models. The method is based on two steps, 1) a novel task querying for knowledge of memory colors, i.e. typical colors of well-known objects, and 2) filtering of model training data to clearly separate knowledge contributions. Additionally, we introduce a model architecture that involves a visual imagination step and evaluate it with our proposed method. We find that our method can successfully be used to measure visual knowledge transfer capabilities in models and that our novel model architecture shows promising results for leveraging multimodal knowledge in a unimodal setting.
|
|
| 2. |
- Al Sabbagh, Khaled, 1987, et al.
(författare)
-
Improving Data Quality for Regression Test Selection by Reducing Annotation Noise
- 2020
-
Ingår i: Proceedings - 46th Euromicro Conference on Software Engineering and Advanced Applications, SEAA 2020. ; , s. 191-194
-
Konferensbidrag (refereegranskat)abstract
- Big data and machine learning models have been increasingly used to support software engineering processes and practices. One example is the use of machine learning models to improve test case selection in continuous integration. However, one of the challenges in building such models is the identification and reduction of noise that often comes in large data. In this paper, we present a noise reduction approach that deals with the problem of contradictory training entries. We empirically evaluate the effectiveness of the approach in the context of selective regression testing. For this purpose, we use a curated training set as input to a tree-based machine learning ensemble and compare the classification precision, recall, and f-score against a non-curated set. Our study shows that using the noise reduction approach on the training instances gives better results in prediction with an improvement of 37% on precision, 70% on recall, and 59% on f-score.
|
|
| 3. |
- Fredriksson, Teodor, 1992, et al.
(författare)
-
Machine learning models for automatic labeling: A systematic literature review
- 2020
-
Ingår i: ICSOFT 2020 - Proceedings of the 15th International Conference on Software Technologies. - : SCITEPRESS - Science and Technology Publications. ; , s. 552-566
-
Konferensbidrag (refereegranskat)abstract
- Automatic labeling is a type of classification problem. Classification has been studied with the help of statistical methods for a long time. With the explosion of new better computer processing units (CPUs) and graphical processing units (GPUs) the interest in machine learning has grown exponentially and we can use both statistical learning algorithms as well as deep neural networks (DNNs) to solve the classification tasks. Classification is a supervised machine learning problem and there exists a large amount of methodology for performing such task. However, it is very rare in industrial applications that data is fully labeled which is why we need good methodology to obtain error-free labels. The purpose of this paper is to examine the current literature on how to perform labeling using ML, we will compare these models in terms of popularity and on what datatypes they are used on. We performed a systematic literature review of empirical studies for machine learning for labeling. We identified 43 primary studies relevant to our search. From this we were able to determine the most common machine learning models for labeling. Lack of unlabeled instances is a major problem for industry as supervised learning is the most widely used. Obtaining labels is costly in terms of labor and financial costs. Based on our findings in this review we present alternate ways for labeling data for use in supervised learning tasks.
|
|
| 4. |
- Brunetta, Carlo, 1992
(författare)
-
Cryptographic Tools for Privacy Preservation
- 2021
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Data permeates every aspect of our daily life and it is the backbone of our digitalized society. Smartphones, smartwatches and many more smart devices measure, collect, modify and share data in what is known as the Internet of Things. Often, these devices don’t have enough computation power/storage space thus out-sourcing some aspects of the data management to the Cloud. Outsourcing computation/storage to a third party poses natural questions regarding the security and privacy of the shared sensitive data. Intuitively, Cryptography is a toolset of primitives/protocols of which security prop- erties are formally proven while Privacy typically captures additional social/legislative requirements that relate more to the concept of “trust” between people, “how” data is used and/or “who” has access to data. This thesis separates the concepts by introducing an abstract model that classifies data leaks into different types of breaches. Each class represents a specific requirement/goal related to cryptography, e.g. confidentiality or integrity, or related to privacy, e.g. liability, sensitive data management and more. The thesis contains cryptographic tools designed to provide privacy guarantees for different application scenarios. In more details, the thesis: (a) defines new encryption schemes that provide formal privacy guarantees such as theoretical privacy definitions like Differential Privacy (DP), or concrete privacy-oriented applications covered by existing regulations such as the European General Data Protection Regulation (GDPR); (b) proposes new tools and procedures for providing verifiable computation’s guarantees in concrete scenarios for post-quantum cryptography or generalisation of signature schemes; (c) proposes a methodology for utilising Machine Learning (ML) for analysing the effective security and privacy of a crypto-tool and, dually, proposes a secure primitive that allows computing specific ML algorithm in a privacy-preserving way; (d) provides an alternative protocol for secure communication between two parties, based on the idea of communicating in a periodically timed fashion.
|
|
| 5. |
- Laaber, C., et al.
(författare)
-
Applying test case prioritization to software microbenchmarks
- 2021
-
Ingår i: Empirical Software Engineering. - : Springer Science and Business Media LLC. - 1382-3256 .- 1573-7616. ; 26:6
-
Tidskriftsartikel (refereegranskat)abstract
- Regression testing comprises techniques which are applied during software evolution to uncover faults effectively and efficiently. While regression testing is widely studied for functional tests, performance regression testing, e.g., with software microbenchmarks, is hardly investigated. Applying test case prioritization (TCP), a regression testing technique, to software microbenchmarks may help capturing large performance regressions sooner upon new versions. This may especially be beneficial for microbenchmark suites, because they take considerably longer to execute than unit test suites. However, it is unclear whether traditional unit testing TCP techniques work equally well for software microbenchmarks. In this paper, we empirically study coverage-based TCP techniques, employing total and additional greedy strategies, applied to software microbenchmarks along multiple parameterization dimensions, leading to 54 unique technique instantiations. We find that TCP techniques have a mean APFD-P (average percentage of fault-detection on performance) effectiveness between 0.54 and 0.71 and are able to capture the three largest performance changes after executing 29% to 66% of the whole microbenchmark suite. Our efficiency analysis reveals that the runtime overhead of TCP varies considerably depending on the exact parameterization. The most effective technique has an overhead of 11% of the total microbenchmark suite execution time, making TCP a viable option for performance regression testing. The results demonstrate that the total strategy is superior to the additional strategy. Finally, dynamic-coverage techniques should be favored over static-coverage techniques due to their acceptable analysis overhead; however, in settings where the time for prioritzation is limited, static-coverage techniques provide an attractive alternative.
|
|
| 6. |
- Petersson, Jesper, 1974, et al.
(författare)
-
Off the record: The invisibility work of doctors in a patient-accessible electronic health record information service.
- 2021
-
Ingår i: Sociology of health & illness. - : Wiley. - 1467-9566 .- 0141-9889. ; 43:5, s. 1270-1285
-
Tidskriftsartikel (refereegranskat)abstract
- In this article, we draw on Michael Lipsky's work on street-level bureaucrats and discretion to analyse a real case setting comprising an interview study of 30 Swedish doctors regarding their experiences of changes in clinical work following patients being given access to medical records information online. We introduce the notion of invisibility work to capture how doctors exercise discretion to preserve the invisibility of their work, in contrast to the well-established notion of invisible work, which denotes work made invisible by parties other than those performing it. We discuss three main forms of invisibility work in relation to records: omitting information, cryptic writing and parallel note writing. We argue that invisibility work is a way for doctors to resolve professional tensions arising from the political decision to provide patients with online access to record information. Although invisibility work is understood by doctors as a solution to government-initiated visibility, we highlight how it can create difficulties for doctors concerning accountability towards patients, peers and authorities.
|
|
| 7. |
- Rexhepi, Hanife, 1984-, et al.
(författare)
-
Cancer patients’ information seeking behavior related to online electronic healthcare records
- 2021
-
Ingår i: Health Informatics Journal. - : Sage Publications. - 1460-4582 .- 1741-2811. ; 27:3, s. 1-12
-
Tidskriftsartikel (refereegranskat)abstract
- Patients’ online access to their EHR together with the rapid proliferation of medical information on the Internet has changed how patients use information to learn about their health. Patients’ tendency to turn to the Internet to find information about their health and care is well-documented. However, little is known about patients’ information seeking behavior when using online EHRs. By using information horizons as an analytical tool this paper aims to investigate the information behavior of cancer patients who have chosen to view their EHRs (readers) and to those who have not made that option (non-readers). Thirty interviews were conducted with patients. Based on information horizons, it seems that non-reading is associated with living in a narrower information world in comparison to readers. The findings do not suggest that the smallness would be a result of active avoidance of information, or that it would be counterproductive for the patients. The findings suggest, however, that EHRs would benefit from comprehensive linking to authoritative health information sources to help users to understand their contents. In parallel, healthcare professionals should be more aware of their personal role as a key source of health information to those who choose not to read their EHRs.
|
|
| 8. |
- Frid, Emma, 1988-, et al.
(författare)
-
Perceptual Evaluation of Blended Sonification of Mechanical Robot Sounds Produced by Emotionally Expressive Gestures : Augmenting Consequential Sounds to Improve Non-verbal Robot Communication
- 2021
-
Ingår i: International Journal of Social Robotics. - : Springer Nature. - 1875-4791 .- 1875-4805.
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents two experiments focusing on perception of mechanical sounds produced by expressive robot movement and blended sonifications thereof. In the first experiment, 31 participants evaluated emotions conveyed by robot sounds through free-form text descriptions. The sounds were inherently produced by the movements of a NAO robot and were not specifically designed for communicative purposes. Results suggested no strong coupling between the emotional expression of gestures and how sounds inherent to these movements were perceived by listeners; joyful gestures did not necessarily result in joyful sounds. A word that reoccurred in text descriptions of all sounds, regardless of the nature of the expressive gesture, was “stress”. In the second experiment, blended sonification was used to enhance and further clarify the emotional expression of the robot sounds evaluated in the first experiment. Analysis of quantitative ratings of 30 participants revealed that the blended sonification successfully contributed to enhancement of the emotional message for sound models designed to convey frustration and joy. Our findings suggest that blended sonification guided by perceptual research on emotion in speech and music can successfully improve communication of emotions through robot sounds in auditory-only conditions.
|
|
| 9. |
- Latupeirissa, Adrian Benigno, et al.
(författare)
-
Exploring emotion perception in sonic HRI
- 2020
-
Ingår i: 17th Sound and Music Computing Conference. - Torino : Zenodo. ; , s. 434-441
-
Konferensbidrag (refereegranskat)abstract
- Despite the fact that sounds produced by robots can affect the interaction with humans, sound design is often an overlooked aspect in Human-Robot Interaction (HRI). This paper explores how different sets of sounds designed for expressive robot gestures of a humanoid Pepper robot can influence the perception of emotional intentions. In the pilot study presented in this paper, it has been asked to rate different stimuli in terms of perceived affective states. The stimuli were audio, audio-video and video only and contained either Pepper’s original servomotors noises, sawtooth, or more complex designed sounds. The preliminary results show a preference for the use of more complex sounds, thus confirming the necessity of further exploration in sonic HRI.
|
|
| 10. |
- Hujainah, Fadhl Mohammad Omar, 1987, et al.
(författare)
-
SRPTackle: A semi-automated requirements prioritisation technique for scalable requirements of software system projects
- 2021
-
Ingår i: Information and Software Technology. - : Elsevier BV. - 0950-5849. ; 131
-
Tidskriftsartikel (refereegranskat)abstract
- Context Requirement prioritisation (RP) is often used to select the most important system requirements as perceived by system stakeholders. RP plays a vital role in ensuring the development of a quality system with defined constraints. However, a closer look at existing RP techniques reveals that these techniques suffer from some key challenges, such as scalability, lack of quantification, insufficient prioritisation of participating stakeholders, overreliance on the participation of professional expertise, lack of automation and excessive time consumption. These key challenges serve as the motivation for the present research. Objective This study aims to propose a new semiautomated scalable prioritisation technique called ‘SRPTackle’ to address the key challenges. Method SRPTackle provides a semiautomated process based on a combination of a constructed requirement priority value formulation function using a multi-criteria decision-making method (i.e. weighted sum model), clustering algorithms (K-means and K-means++) and a binary search tree to minimise the need for expert involvement and increase efficiency. The effectiveness of SRPTackle is assessed by conducting seven experiments using a benchmark dataset from a large actual software project. Results Experiment results reveal that SRPTackle can obtain 93.0% and 94.65% as minimum and maximum accuracy percentages, respectively. These values are better than those of alternative techniques. The findings also demonstrate the capability of SRPTackle to prioritise large-scale requirements with reduced time consumption and its effectiveness in addressing the key challenges in comparison with other techniques. Conclusion With the time effectiveness, ability to scale well with numerous requirements, automation and clear implementation guidelines of SRPTackle, project managers can perform RP for large-scale requirements in a proper manner, without necessitating an extensive amount of effort (e.g. tedious manual processes, need for the involvement of experts and time workload).
|
|
