{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T13:26:21Z","timestamp":1783689981403,"version":"3.55.0"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100016974","name":"Quanzhou Normal University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100016974","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.engappai.2026.114285","type":"journal-article","created":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T15:52:12Z","timestamp":1771775532000},"page":"114285","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Layer-dependent dynamic spectral weighting for efficient transformer models"],"prefix":"10.1016","volume":"171","author":[{"given":"Zhigao","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanzhong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyan","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Musheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanfa","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.114285_b1","series-title":"Spectral state space models","author":"Agarwal","year":"2024"},{"key":"10.1016\/j.engappai.2026.114285_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.132398","article-title":"DistilXIDS: Efficient, lightweight and explainable transformer-based language model for real-time network intrusion detection","volume":"668","author":"Ajayan","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.engappai.2026.114285_b3","doi-asserted-by":"crossref","first-page":"88","DOI":"10.58496\/ADSA\/2023\/007","article-title":"Multi-tiered CNN model for motor imagery analysis: Enhancing uav control in smart city infrastructure for industry 5.0","volume":"2023","author":"Al-Qaysi","year":"2023","journal-title":"Appl. Data Sci. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/3005-317X","issn-type":"print"},{"key":"10.1016\/j.engappai.2026.114285_b4","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1016\/j.aej.2025.05.044","article-title":"Hybrid TCN-transformer model for predicting sustainable food supply and ensuring resilience","volume":"127","author":"Alrashdi","year":"2025","journal-title":"Alex. Eng. J."},{"key":"10.1016\/j.engappai.2026.114285_b5","doi-asserted-by":"crossref","DOI":"10.3390\/math13111819","article-title":"Harmonizer: A universal signal tokenization framework for multimodal large language models","author":"Amiri","year":"2025","journal-title":"Mathematics"},{"key":"10.1016\/j.engappai.2026.114285_b6","series-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"10.1016\/j.engappai.2026.114285_b7","series-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"10.1016\/j.engappai.2026.114285_b8","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114285_b9","series-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019"},{"key":"10.1016\/j.engappai.2026.114285_b10","unstructured":"Choromanski, K., Likhosherstov, V., Dohan, D., Song, X., Gane, A., Sarlos, T., Hawkins, P., Davis, J., Mohiuddin, A., Kaiser, L., et al., 2021. Rethinking attention with performers. In: International Conference on Learning Representations (ICLR)."},{"key":"10.1016\/j.engappai.2026.114285_b11","doi-asserted-by":"crossref","unstructured":"Clark, K., Khandelwal, U., Levy, O., Manning, C.D., 2019. What Does BERT Look at? An Analysis of BERT\u2019s Attention. In: Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. pp. 276\u2013286.","DOI":"10.18653\/v1\/W19-4828"},{"key":"10.1016\/j.engappai.2026.114285_b12","series-title":"Universal transformers","author":"Dehghani","year":"2018"},{"key":"10.1016\/j.engappai.2026.114285_b13","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K., 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.engappai.2026.114285_b14","series-title":"Depth-adaptive transformer","author":"Elbayad","year":"2020"},{"key":"10.1016\/j.engappai.2026.114285_b15","doi-asserted-by":"crossref","first-page":"121","DOI":"10.58496\/BJIoT\/2025\/007","article-title":"Integrating AI-driven deep learning for energy-efficient smart buildings in internet of thing-based industry 4.0","volume":"2025","author":"Ghanem","year":"2025","journal-title":"Babylon. J. Internet Things","ISSN":"https:\/\/id.crossref.org\/issn\/3006-1083","issn-type":"print"},{"key":"10.1016\/j.engappai.2026.114285_b16","series-title":"Adaptive computation time for recurrent neural networks","author":"Graves","year":"2016"},{"key":"10.1016\/j.engappai.2026.114285_b17","series-title":"Learning spectral methods by transformers","author":"He","year":"2025"},{"key":"10.1016\/j.engappai.2026.114285_b18","doi-asserted-by":"crossref","unstructured":"Jawahar, G., Sagot, B., Seddah, D., 2019. What does BERT learn about the structure of language?. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. pp. 3651\u20133657.","DOI":"10.18653\/v1\/P19-1356"},{"key":"10.1016\/j.engappai.2026.114285_b19","series-title":"Tinybert: Distilling bert for natural language understanding","author":"Jiao","year":"2020"},{"key":"10.1016\/j.engappai.2026.114285_b20","doi-asserted-by":"crossref","first-page":"72","DOI":"10.58496\/BJAI\/2025\/007","article-title":"The rise of transformers \u2013 redefining the landscape of artificial intelligence","volume":"2025","author":"Ladu","year":"2025","journal-title":"Babylon. J. Artif. Intell.","ISSN":"https:\/\/id.crossref.org\/issn\/3006-5437","issn-type":"print"},{"key":"10.1016\/j.engappai.2026.114285_b21","series-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"Lan","year":"2020"},{"key":"10.1016\/j.engappai.2026.114285_b22","article-title":"Spectral sparsification of neural networks through weight pruning","author":"Lee","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2026.114285_b23","first-page":"38179","article-title":"On the frequency bias of generative models","volume":"35","author":"Li","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114285_b24","article-title":"Comparing and combining pretrained language models in a clinical entity extraction task","volume":"139","author":"Liu","year":"2023","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.engappai.2026.114285_b25","series-title":"Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021"},{"key":"10.1016\/j.engappai.2026.114285_b26","article-title":"Are sixteen heads really better than one?","volume":"32","author":"Michel","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114285_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.jnca.2023.103793","article-title":"TRACE: Transformer-based continuous tracking framework using IoT and MCS","volume":"222","author":"Mohammed","year":"2024","journal-title":"J. Netw. Comput. Appl."},{"key":"10.1016\/j.engappai.2026.114285_b28","doi-asserted-by":"crossref","first-page":"46","DOI":"10.70470\/SHIFRA\/2024\/006","article-title":"Optimizing energy efficiency in smart grids using machine learning algorithms: A case study in electrical engineering","volume":"2024","author":"Nayyef","year":"2024","journal-title":"SHIFRA","ISSN":"https:\/\/id.crossref.org\/issn\/3078-3186","issn-type":"print"},{"key":"10.1016\/j.engappai.2026.114285_b29","series-title":"Compressing transformer-based semantic parsing models using compositional code embeddings","author":"Noach","year":"2020"},{"key":"10.1016\/j.engappai.2026.114285_b30","series-title":"Vision transformer for small-size datasets","author":"Park","year":"2022"},{"key":"10.1016\/j.engappai.2026.114285_b31","first-page":"5301","article-title":"On the spectral bias of neural networks","author":"Rahaman","year":"2019","journal-title":"Int. Conf. Mach. Learn."},{"key":"10.1016\/j.engappai.2026.114285_b32","first-page":"2449","article-title":"Spectral representations for convolutional neural networks","volume":"28","author":"Rippel","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114285_b33","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1162\/tacl_a_00349","article-title":"A primer in bertology: What we know about how BERT works","volume":"8","author":"Rogers","year":"2020","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.engappai.2026.114285_b34","series-title":"Distilbert, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"10.1016\/j.engappai.2026.114285_b35","first-page":"5373","article-title":"Confident adaptive language modeling","volume":"35","author":"Schuster","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"12","key":"10.1016\/j.engappai.2026.114285_b36","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/3381831","article-title":"Green AI","volume":"63","author":"Schwartz","year":"2020","journal-title":"Commun. ACM"},{"key":"10.1016\/j.engappai.2026.114285_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.scs.2024.105882","article-title":"Enhancing road traffic flow in sustainable cities through transformer models: Advancements and challenges","volume":"116","author":"Soudeep","year":"2024","journal-title":"Sustain. Cities Soc."},{"key":"10.1016\/j.engappai.2026.114285_b38","doi-asserted-by":"crossref","unstructured":"Strubell, E., Ganesh, A., McCallum, A., 2019. Energy and policy considerations for deep learning in NLP. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. pp. 3645\u20133650.","DOI":"10.18653\/v1\/P19-1355"},{"issue":"6","key":"10.1016\/j.engappai.2026.114285_b39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3530811","article-title":"Efficient transformers: A survey","volume":"55","author":"Tay","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.engappai.2026.114285_b40","doi-asserted-by":"crossref","unstructured":"Tenney, I., Das, D., Pavlick, E., 2019. BERT rediscovers the classical NLP pipeline. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. pp. 4593\u20134601.","DOI":"10.18653\/v1\/P19-1452"},{"key":"10.1016\/j.engappai.2026.114285_b41","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114285_b42","doi-asserted-by":"crossref","unstructured":"Voita, E., Talbot, D., Moiseev, F., Sennrich, R., Titov, I., 2019. Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. pp. 5797\u20135808.","DOI":"10.18653\/v1\/P19-1580"},{"key":"10.1016\/j.engappai.2026.114285_b43","series-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020"},{"key":"10.1016\/j.engappai.2026.114285_b44","series-title":"Frequency principle: Fourier analysis sheds light on deep neural networks","author":"Xu","year":"2019"},{"key":"10.1016\/j.engappai.2026.114285_b45","first-page":"13276","article-title":"A fourier perspective on model robustness in computer vision","volume":"33","author":"Yin","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114285_b46","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume":"33","author":"Zaheer","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095219762600566X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095219762600566X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:30:33Z","timestamp":1777595433000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095219762600566X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":46,"alternative-id":["S095219762600566X"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114285","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Layer-dependent dynamic spectral weighting for efficient transformer models","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114285","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114285"}}