https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4/Head
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
http://www.nanopub.org/nschema#hasAssertion
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4/assertion
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
http://www.nanopub.org/nschema#hasProvenance
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4/provenance
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
http://www.nanopub.org/nschema#hasPublicationInfo
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4/pubinfo
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
http://www.w3.org/1999/02/22-rdf-syntax-ns#type
http://www.nanopub.org/nschema#Nanopublication
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4/assertion
https://ieeexplore.ieee.org/document/10365540
http://purl.org/dc/terms/creator
https://orcid.org/0000-0001-9487-5622
https://ieeexplore.ieee.org/document/10365540
http://purl.org/dc/terms/creator
https://orcid.org/0000-0003-2911-8558
https://ieeexplore.ieee.org/document/10365540
http://purl.org/dc/terms/publisher
https://ror.org/01n002310
https://ieeexplore.ieee.org/document/10365540
http://purl.org/dc/terms/subject
http://edamontology.org/topic_3316
https://ieeexplore.ieee.org/document/10365540
http://www.w3.org/1999/02/22-rdf-syntax-ns#type
https://w3id.org/fair/ff/terms/article
https://ieeexplore.ieee.org/document/10365540
http://www.w3.org/1999/02/22-rdf-syntax-ns#type
https://w3id.org/fdof/ontology#FAIRDigitalObject
https://ieeexplore.ieee.org/document/10365540
http://www.w3.org/2000/01/rdf-schema#comment
Accurate uncertainty quantification is necessary to enhance the reliability of deep learning (DL) models in real-world applications. In the case of regression tasks, prediction intervals (PIs) should be provided along with the deterministic predictions of DL models. Such PIs are useful or “high-quality (HQ)” as long as they are sufficiently narrow and capture most of the probability density. In this article, we present a method to learn PIs for regression-based neural networks (NNs) automatically in addition to the conventional target predictions. In particular, we train two companion NNs: one that uses one output, the target estimate, and another that uses two outputs, the upper and lower bounds of the corresponding PI. Our main contribution is the design of a novel loss function for the PI-generation network that takes into account the output of the target-estimation network and has two optimization objectives: minimizing the mean PI width and ensuring the PI integrity using constraints that maximize the PI probability coverage implicitly. Furthermore, we introduce a self-adaptive coefficient that balances both objectives within the loss function, which alleviates the task of fine-tuning. Experiments using a synthetic dataset, eight benchmark datasets, and a real-world crop yield prediction dataset showed that our method was able to maintain a nominal probability coverage and produce significantly narrower PIs without detriment to its target estimation accuracy when compared to those PIs generated by three state-of-the-art neural-network-based methods. In other words, our method was shown to produce higher quality PIs. Major findings:The DualAQD framework produces "prediction intervals" that inform users of the confidence level associated with an AI model's specific estimate. This method generates narrower and more accurate confidence ranges than existing methods while maintaining high overall target accuracy. The system successfully identifies regions of high uncertainty in crop yield predictions, increasing the reliability of deep learning models for high-stakes decision-making.
https://ieeexplore.ieee.org/document/10365540
http://www.w3.org/2000/01/rdf-schema#label
Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generation
https://ieeexplore.ieee.org/document/10365540
https://schema.org/funder
https://ror.org/02w0trx84
https://ieeexplore.ieee.org/document/10365540
https://w3id.org/fdof/ontology#hasMetadata
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
https://ieeexplore.ieee.org/document/10365540
https://www.w3.org/ns/dcat#contactPoint
john.sheppard@montana.edu
https://ieeexplore.ieee.org/document/10365540
https://www.w3.org/ns/dcat#endDate
2023
https://ieeexplore.ieee.org/document/10365540
https://www.w3.org/ns/dcat#startDate
2022
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4/provenance
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4/assertion
http://www.w3.org/ns/prov#wasAttributedTo
https://orcid.org/0009-0008-8411-2742
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4/pubinfo
https://orcid.org/0009-0008-8411-2742
http://xmlns.com/foaf/0.1/name
Emily Regalado
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
http://purl.org/dc/terms/created
2026-01-14T06:36:11.632Z
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
http://purl.org/dc/terms/creator
https://orcid.org/0009-0008-8411-2742
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
http://purl.org/dc/terms/license
https://creativecommons.org/licenses/by/4.0/
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
http://purl.org/nanopub/x/introduces
https://ieeexplore.ieee.org/document/10365540
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
http://purl.org/nanopub/x/wasCreatedAt
https://nanodash.knowledgepixels.com/
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
https://w3id.org/np/o/ntemplate/wasCreatedFromProvenanceTemplate
https://w3id.org/np/RA7lSq6MuK_TIC6JMSHvLtee3lpLoZDOqLJCLXevnrPoU
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
https://w3id.org/np/o/ntemplate/wasCreatedFromPubinfoTemplate
https://w3id.org/np/RA0J4vUn_dekg-U1kK3AOEt02p9mT2WO03uGxLDec1jLw
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
https://w3id.org/np/o/ntemplate/wasCreatedFromPubinfoTemplate
https://w3id.org/np/RAukAcWHRDlkqxk7H2XNSegc1WnHI569INvNr-xdptDGI
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
https://w3id.org/np/o/ntemplate/wasCreatedFromTemplate
https://w3id.org/np/RArM5GTwgxg9qslGX-XiQ-KTTUwdoM0KB1YqmT4GqTizA
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4/sig
http://purl.org/nanopub/x/hasAlgorithm
RSA
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4/sig
http://purl.org/nanopub/x/hasPublicKey
MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAxzr6UBGMW6c8tegz0babaledWUEQ0PLDE4tp7Iinbe2DZtAtY5JUptKYuStWDZx+QER4808P8dejNWRnBDzgthYJm/AyNSXflHSJhz2+NC+h7RylOLxbwLEQocmyKKiYxa2gT85m6ajVL2M6TnfG67nnK+K2f7iCGL6wYXRITD1q+7+5SWqBdDXIV921W4IKWaD2GJk+NRBoOqQhbsrk8Tn5XsNd7DMYVHk47oMDGbeBnrOIoRPsbBgAcoCsxxhiB9yN6Lf8EUbnlXVEDzJuZk048L1BDZL+6nkA8btTQGP2ijUFWA7rTrod3LjUDQWLZS95njjl867dtmv/znYkzwIDAQAB
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4/sig
http://purl.org/nanopub/x/hasSignature
Ua+ab/C3ccCV5+svbErFiU6f4iySULKm/Lx0PrQToUMA6Y7yBDvU6ejniPSen++yI408022sAufIcDULMofwJKidxSms/5Si/rWrcoTQ+YegrJYqlReZjW9zUKpRHBOKaMyTk/jtzy0kYgX2ayWsgwmFjh64zPRd9NsbtbQoVrE0vJxmO91V8H92wgzTtDImUxTPUy42gLIOaXtxLtsY79M5nPKlijOT4g/J08MBpC0c56rgLWFCb6MilEwvoJZ0Zfr/HTyZGCEQVk7pnA3KzGBFkIoiB+5/WKxRkPx+9+OUIDuJnQdVgzezIZXQ2TAloaRxT7lWt6JuVNp7HUYp5Q==
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4/sig
http://purl.org/nanopub/x/hasSignatureTarget
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4
https://w3id.org/np/RAAnumXKqMyA6FRjwlI0AWDgFT8rnYBqvgCwOHWrrhxT4/sig
http://purl.org/nanopub/x/signedBy
https://orcid.org/0009-0008-8411-2742