onr:"swepub:oai:DiVA.org:oru-98271"
Search: onr:"swepub:oai:DiVA.org:oru-98271" > Metrics and Evaluat...
- 1 of 1
- Previous record
- Next record
- To hitlist
- Fouladgar, NazaninUmeå universitet,Institutionen för datavetenskap (author)
Metrics and Evaluations of Time Series Explanations : An Application in Affect Computing
- Article/chapterEnglish2022
Publisher, publication year, extent ...
- IEEE,2022
- printrdacarrier
Numbers
- LIBRIS-ID:oai:DiVA.org:oru-98271
- https://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-98271URI
- https://doi.org/10.1109/ACCESS.2022.3155115DOI
- https://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-192976URI
Supplementary language notes
- Language:English
- Summary in:English
Part of subdatabase
- SwePubSwePub
Classification
Notes
- Funding agency:Umeå University
- Explainable artificial intelligence (XAI) has shed light on enormous applications by clarifying why neural models make specific decisions. However, it remains challenging to measure how sensitive XAI solutions are to the explanations of neural models. Although different evaluation metrics have been proposed to measure sensitivity, the main focus has been on the visual and textual data. There is insufficient attention devoted to the sensitivity metrics tailored for time series data. In this paper, we formulate several metrics, including max short-term sensitivity (MSS), max long-term sensitivity (MLS), average short-term sensitivity (ASS) and average long-term sensitivity (ALS), that target the sensitivity of XAI models with respect to the generated and real time series. Our hypothesis is that for close series with the same labels, we obtain similar explanations. We evaluate three XAI models, LIME, integrated gradient (IG), and SmoothGrad (SG), on CN-Waterfall, a deep convolutional network. This network is a highly accurate time series classifier in affect computing. Our experiments rely on data-, metric- and XAI hyperparameter- related settings on the WESAD and MAHNOB-HCI datasets. The results reveal that (i) IG and LIME provide a lower sensitivity scale than SG in all the metrics and settings, potentially due to the lower scale of important scores generated by IG and LIME, (ii) the XAI models show higher sensitivities for a smaller window of data, (iii) the sensitivities of XAI models fluctuate when the network parameters and data properties change, and (iv) the XAI models provide unstable sensitivities under different settings of hyperparameters.
Subject headings and genre
- NATURVETENSKAP Data- och informationsvetenskap Datavetenskap hsv//swe
- NATURAL SCIENCES Computer and Information Sciences Computer Sciences hsv//eng
- Measurement
- Sensitivity
- Data models
- Time series analysis
- Predictive models
- Perturbation methods
- Computational modeling
- Explainable AI
- metrics
- time series data
- deep convolutional neural network
Added entries (persons, corporate bodies, meetings, titles ...)
- Alirezaie, Marjan,1980-Örebro universitet,Institutionen för naturvetenskap och teknik,Centre for Applied Autonomous Sensor Systems (AASS), Örebro, Sweden(Swepub:oru)mjae (author)
- Främling, Kary,1965-Umeå universitet,Institutionen för datavetenskap,Aalto University, School of Science and Technology, Finland(Swepub:umu)kafr0071 (author)
- Umeå universitetInstitutionen för datavetenskap (creator_code:org_t)
Related titles
- In:IEEE Access: IEEE10, s. 23995-240092169-3536
Internet link
- 1 of 1
- Previous record
- Next record
- To hitlist
Find more in SwePub
- By the author/editor
- Fouladgar, Nazan ...
- Alirezaie, Marja ...
- Främling, Kary, ...
- About the subject
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Computer and Inf ...
- and Computer Science ...
- Articles in the publication
- IEEE Access
- By the university
- Örebro University
- Umeå University
Search outside SwePub
- Extend your search to:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - National Library Systems
- LIBRIS.kb.se
