{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T10:59:33Z","timestamp":1784631573228,"version":"3.55.0"},"reference-count":186,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T00:00:00Z","timestamp":1721952000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T00:00:00Z","timestamp":1721952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["LP210100337"],"award-info":[{"award-number":["LP210100337"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Reliable Intell Environ"],"published-print":{"date-parts":[[2024,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The integration of Artificial Intelligence (AI) with the Internet of Things (IoT), known as the Artificial Intelligence of Things (AIoT), enhances the devices\u2019 processing and analysis capabilities and disrupts such sectors as healthcare, industry, and oil. However, AIoT\u2019s complexity and scale are challenging for traditional machine learning (ML). Deep learning offers a solution but has limited testability, verifiability, and interpretability. In turn, the<jats:italic>neuro-symbolic paradigm<\/jats:italic>addresses these challenges by combining the robustness of symbolic AI with the flexibility of DL, enabling AI systems to reason, make decisions, and generalize knowledge from large datasets better. This paper reviews state-of-the-art DL models for IoT, identifies their limitations, and explores how neuro-symbolic methods can overcome them. It also discusses key challenges and research opportunities in enhancing AIoT reliability with neuro-symbolic approaches, including hard-coded symbolic AI, multimodal sensor data, biased interpretability, trading-off interpretability, and performance, complexity in integrating neural networks and symbolic AI, and ethical and societal challenges.<\/jats:p>","DOI":"10.1007\/s40860-024-00231-1","type":"journal-article","created":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T20:01:57Z","timestamp":1722024117000},"page":"257-279","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":72,"title":["Surveying neuro-symbolic approaches for reliable artificial intelligence of things"],"prefix":"10.1007","volume":"10","author":[{"given":"Zhen","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Imran","family":"Afridi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong Jin","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Ruchkin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,26]]},"reference":[{"issue":"5","key":"231_CR1","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MNET.011.2000009","volume":"34","author":"S Feifei","year":"2020","unstructured":"Feifei S et al (2020) Recent progress on the convergence of the internet of things and artificial intelligence. IEEE Netw 34(5):8\u201315. https:\/\/doi.org\/10.1109\/MNET.011.2000009","journal-title":"IEEE Netw"},{"key":"231_CR2","doi-asserted-by":"publisher","first-page":"16057","DOI":"10.1007\/s00521-020-04736-7","volume":"32","author":"Bandaragoda A Tharindu","year":"2020","unstructured":"Tharindu Bandaragoda A et al (2020) Artificial intelligence based commuter behaviour profiling framework using internet of things for real-time decision-making. Neural Comput Appl 32:16057\u201316071. https:\/\/doi.org\/10.1007\/s00521-020-04736-7","journal-title":"Neural Comput Appl"},{"key":"231_CR3","unstructured":"McKinsey & Company (2013) Disruptive technologies: Advances that will transform life, business, and the global economy. https:\/\/www.mckinsey.com\/mgi"},{"issue":"2","key":"231_CR4","doi-asserted-by":"publisher","first-page":"1781","DOI":"10.1109\/JIOT.2018.2878602","volume":"6","author":"M Hu","year":"2018","unstructured":"Hu M, Liu W, Peng K et al (2018) Joint routing and scheduling for vehicle-assisted multidrone surveillance. Internet Things J 6(2):1781\u20131790. https:\/\/doi.org\/10.1109\/JIOT.2018.2878602","journal-title":"Internet Things J"},{"issue":"3","key":"231_CR5","doi-asserted-by":"publisher","first-page":"5297","DOI":"10.1109\/JIOT.2019.2900524","volume":"6","author":"C Cai","year":"2019","unstructured":"Cai C, Hu M, Cao D et al (2019) Self-deployable indoor localization with acoustic-enabled IoT devices exploiting participatory sensing. Internet Things J 6(3):5297\u20135311. https:\/\/doi.org\/10.1109\/JIOT.2019.2900524","journal-title":"Internet Things J"},{"key":"231_CR6","unstructured":"Waymo: Autonomous Car. https:\/\/waymo.com\/. Accessed: 2024-04-29"},{"key":"231_CR7","doi-asserted-by":"publisher","unstructured":"Abate F, Carrat\u00f9 M, Liguori C et\u00a0al (2018) Smart meter for the IoT. In: I2MTC, pp. 1\u20136. https:\/\/doi.org\/10.1109\/I2MTC.2018.8409838","DOI":"10.1109\/I2MTC.2018.8409838"},{"issue":"3","key":"231_CR8","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/s40860-022-00181-6","volume":"8","author":"S Zhang","year":"2022","unstructured":"Zhang S, Callaghan V, An X et al (2022) Feature selection and human arm activity classification using a wristband. J Reliab Intell Environ 8(3):285\u2013298. https:\/\/doi.org\/10.1007\/s40860-022-00181-6","journal-title":"J Reliab Intell Environ"},{"issue":"2","key":"231_CR9","first-page":"37","volume":"6","author":"HO Al-Sakran","year":"2015","unstructured":"Al-Sakran HO et al (2015) Intelligent traffic information system based on integration of internet of things and agent technology. IJACSA 6(2):37\u201343","journal-title":"IJACSA"},{"issue":"4","key":"231_CR10","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/s40860-022-00184-3","volume":"9","author":"M Douiba","year":"2023","unstructured":"Douiba M, Benkirane S, Guezzaz A et al (2023) Anomaly detection model based on gradient boosting and decision tree for iot environments security. J Reliab Intell Environ 9(4):421\u2013432. https:\/\/doi.org\/10.1007\/s40860-022-00184-3","journal-title":"J Reliab Intell Environ"},{"issue":"4","key":"231_CR11","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1007\/s40860-021-00152-3","volume":"8","author":"SM Nagarajan","year":"2022","unstructured":"Nagarajan SM, Muthukumaran V, Murugesan R et al (2022) Innovative feature selection and classification model for heart disease prediction. J Reliab Intell Environ 8(4):333\u2013343. https:\/\/doi.org\/10.1007\/s40860-021-00152-3","journal-title":"J Reliab Intell Environ"},{"issue":"1","key":"231_CR12","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1007\/s40860-021-00165-y","volume":"8","author":"T Chen","year":"2022","unstructured":"Chen T, Madanian S, Airehrour D et al (2022) Machine learning methods for hospital readmission prediction: systematic analysis of literature. J Reliab Intell Environ 8(1):49\u201366. https:\/\/doi.org\/10.1007\/s40860-021-00165-y","journal-title":"J Reliab Intell Environ"},{"issue":"1","key":"231_CR13","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/s40860-022-00192-3","volume":"9","author":"J Kaur","year":"2023","unstructured":"Kaur J, Khehra BS, Singh A (2023) Back propagation artificial neural network for diagnose of the heart disease. J Reliab Intell Environ 9(1):57\u201385. https:\/\/doi.org\/10.1007\/s40860-022-00192-3","journal-title":"J Reliab Intell Environ"},{"issue":"2","key":"231_CR14","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/s40860-021-00169-8","volume":"9","author":"S Hosseini","year":"2023","unstructured":"Hosseini S, Sardo SR (2023) Network intrusion detection based on deep learning method in internet of thing. J Reliab Intell Environ 9(2):147\u2013159. https:\/\/doi.org\/10.1007\/s40860-021-00169-8","journal-title":"J Reliab Intell Environ"},{"key":"231_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2020.100270","volume":"37","author":"H Xiaowei","year":"2020","unstructured":"Xiaowei H, Daniel K, Wenjie R et al (2020) A survey of safety and trustworthiness of deep neural networks: verification, testing, adversarial attack and defence, and interpretability. Comput Sci Rev 37:100270. https:\/\/doi.org\/10.1016\/j.cosrev.2020.100270","journal-title":"Comput Sci Rev"},{"issue":"1","key":"231_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TSE.2019.2962027","volume":"48","author":"MZ Jie","year":"2020","unstructured":"Jie MZ, Mark H, Lei M, Yang L (2020) Machine learning testing: survey, landscapes and horizons. Trans Softw Eng 48(1):1\u201336. https:\/\/doi.org\/10.1109\/TSE.2019.2962027","journal-title":"Trans Softw Eng"},{"key":"231_CR17","doi-asserted-by":"publisher","unstructured":"Xiang W, Musau P, Wild AA et\u00a0al (2018) Verification for machine learning, autonomy, and neural networks survey. https:\/\/doi.org\/10.48550\/arXiv.1810.01989","DOI":"10.48550\/arXiv.1810.01989"},{"key":"231_CR18","doi-asserted-by":"publisher","unstructured":"Supriyo C, Richard et\u00a0al (2017) Interpretability of deep learning models: a survey of results. In: IEEE SmartWorld, pp 1\u20136. https:\/\/doi.org\/10.1109\/UIC-ATC.2017.8397411","DOI":"10.1109\/UIC-ATC.2017.8397411"},{"key":"231_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2020.106296","volume":"123","author":"J Zhang","year":"2020","unstructured":"Zhang J, Li J (2020) Testing and verification of neural-network-based safety-critical control software: a systematic literature review. Inf Softw Technol 123:106296. https:\/\/doi.org\/10.1016\/j.infsof.2020.106296","journal-title":"Inf Softw Technol"},{"key":"231_CR20","doi-asserted-by":"publisher","unstructured":"Howard AG, Zhu M, Chen B et\u00a0al (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. https:\/\/doi.org\/10.48550\/arXiv.1704.04861","DOI":"10.48550\/arXiv.1704.04861"},{"key":"231_CR21","doi-asserted-by":"publisher","unstructured":"Iandola FN, Han S, Moskewicz MW et\u00a0al (2016) Squeezenet: Alexnet-level accuracy with 50x fewer parameters and $$<0.5$$ mb model size. https:\/\/doi.org\/10.48550\/arXiv.1602.07360","DOI":"10.48550\/arXiv.1602.07360"},{"key":"231_CR22","doi-asserted-by":"publisher","unstructured":"Szegedy C, Liu W et\u00a0al (2015) Going deeper with convolutions. In: CVPR, pp 1\u20139 https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"231_CR23","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.patrec.2020.05.019","volume":"136","author":"DdA Rodrigues","year":"2020","unstructured":"Rodrigues DdA, Ivo RF, Satapathy SC et al (2020) A new approach for classification skin lesion based on transfer learning, deep learning, and IoT system. Pattern Recogn Lett 136:8\u201315. https:\/\/doi.org\/10.1016\/j.patrec.2020.05.019","journal-title":"Pattern Recogn Lett"},{"key":"231_CR24","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/9928254","author":"O Taiwo","year":"2021","unstructured":"Taiwo O, Ezugwu AE (2021) Internet of things-based intelligent smart home control system. Secur Commun Netw. https:\/\/doi.org\/10.1155\/2021\/9928254","journal-title":"Secur Commun Netw"},{"issue":"5","key":"231_CR25","doi-asserted-by":"publisher","first-page":"8553","DOI":"10.1109\/JIOT.2019.2920283","volume":"6","author":"V Bianchi","year":"2019","unstructured":"Bianchi V, Bassoli M, Lombardo G et al (2019) IoT wearable sensor and deep learning: an integrated approach for personalized human activity recognition in a smart home environment. Internet Things J 6(5):8553\u20138562. https:\/\/doi.org\/10.1109\/JIOT.2019.2920283","journal-title":"Internet Things J"},{"issue":"8","key":"231_CR26","doi-asserted-by":"publisher","first-page":"6393","DOI":"10.1109\/JIOT.2020.3042174","volume":"8","author":"N Magaia","year":"2020","unstructured":"Magaia N, Fonseca R, Muhammad K et al (2020) Industrial internet-of-things security enhanced with deep learning approaches for smart cities. Internet Things J 8(8):6393\u20136405. https:\/\/doi.org\/10.1109\/JIOT.2020.3042174","journal-title":"Internet Things J"},{"key":"231_CR27","doi-asserted-by":"publisher","first-page":"1568","DOI":"10.1016\/j.egyr.2021.12.053","volume":"8","author":"Q Xin","year":"2022","unstructured":"Xin Q, Alazab M et al (2022) A deep learning architecture for power management in smart cities. Energy Rep 8:1568\u20131577. https:\/\/doi.org\/10.1016\/j.egyr.2021.12.053","journal-title":"Energy Rep"},{"key":"231_CR28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3210490","author":"I Jeon Ahmed","year":"2022","unstructured":"Jeon Ahmed I et al (2022) A smart IoT enabled end-to-end 3D object detection system for autonomous vehicles. TITS. https:\/\/doi.org\/10.1109\/TITS.2022.3210490","journal-title":"TITS"},{"key":"231_CR29","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10060637","author":"T Shon","year":"2021","unstructured":"Shon T (2021) In-vehicle networking\/autonomous vehicle security for internet of things\/vehicles. Electronics. https:\/\/doi.org\/10.3390\/electronics10060637","journal-title":"Electronics"},{"key":"231_CR30","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1016\/j.compag.2018.10.015","volume":"155","author":"M Mehra","year":"2018","unstructured":"Mehra M, Saxena S, Sankaranarayanan S et al (2018) IoT based hydroponics system using deep neural networks. Comput Electron Agric 155:473\u2013486. https:\/\/doi.org\/10.1016\/j.compag.2018.10.015","journal-title":"Comput Electron Agric"},{"issue":"4","key":"231_CR31","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1007\/s13198-021-01118-7","volume":"12","author":"X Zhang","year":"2021","unstructured":"Zhang X (2021) Application of human motion recognition utilizing deep learning and smart wearable device in sports. IJSAEM 12(4):835\u2013843. https:\/\/doi.org\/10.1007\/s13198-021-01118-7","journal-title":"IJSAEM"},{"issue":"1","key":"231_CR32","first-page":"173","volume":"22","author":"S Vimal","year":"2021","unstructured":"Vimal S, Robinson YH, Kadry S et al (2021) IoT based smart health monitoring with CNN using edge computing. J Internet Technol 22(1):173\u2013185","journal-title":"J Internet Technol"},{"issue":"8","key":"231_CR33","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput"},{"key":"231_CR34","unstructured":"Cho K, Merri\u00ebnboer V et al (2024) Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078"},{"issue":"11","key":"231_CR35","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster M, Paliwal KK (1997) Bidirectional recurrent neural networks. TSP 45(11):2673\u20132681. https:\/\/doi.org\/10.1109\/78.650093","journal-title":"Bidirectional recurrent neural networks. TSP"},{"key":"231_CR36","doi-asserted-by":"publisher","unstructured":"Li S, Li W, Cook C et\u00a0al (2018) Independently recurrent neural network (INDRNN): Building a longer and deeper rnn. In: CVPR, pp 5457\u20135466. https:\/\/doi.org\/10.1109\/CVPR.2018.00572","DOI":"10.1109\/CVPR.2018.00572"},{"key":"231_CR37","doi-asserted-by":"publisher","first-page":"137406","DOI":"10.1109\/ACCESS.2021.3116809","volume":"9","author":"M Yu","year":"2021","unstructured":"Yu M, Xu F et al (2021) Using long short-term memory (LSTM) and internet of things (IoT) for localized surface temperature forecasting in an urban environment. IEEE Access 9:137406\u2013137418. https:\/\/doi.org\/10.1109\/ACCESS.2021.3116809","journal-title":"IEEE Access"},{"key":"231_CR38","doi-asserted-by":"publisher","first-page":"62722","DOI":"10.1109\/ACCESS.2022.3176317","volume":"10","author":"I Ullah","year":"2022","unstructured":"Ullah I, Mahmoud QH (2022) Design and development of RNN anomaly detection model for iot networks. IEEE Access 10:62722\u201362750. https:\/\/doi.org\/10.1109\/ACCESS.2022.3176317","journal-title":"IEEE Access"},{"issue":"1","key":"231_CR39","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/j.aej.2020.06.056","volume":"60","author":"M Farsi","year":"2021","unstructured":"Farsi M (2021) Application of ensemble rnn deep neural network to the fall detection through iot environment. Alex Eng J 60(1):199\u2013211. https:\/\/doi.org\/10.1016\/j.aej.2020.06.056","journal-title":"Alex Eng J"},{"key":"231_CR40","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1016\/j.matpr.2021.04.239","volume":"81","author":"D Saravanan","year":"2023","unstructured":"Saravanan D, Kumar KS (2023) Improving air pollution detection accuracy and quality monitoring based on bidirectional rnn and the internet of things. Mater Today Proc 81:791\u2013796. https:\/\/doi.org\/10.1016\/j.matpr.2021.04.239","journal-title":"Mater Today Proc"},{"key":"231_CR41","doi-asserted-by":"publisher","unstructured":"Abdellah AR, Koucheryavy A (2020) Deep learning with long short-term memory for IOT traffic prediction. In: NEW2AN. Springer, pp 267\u2013280. https:\/\/doi.org\/10.1007\/978-3-030-65726-0_24","DOI":"10.1007\/978-3-030-65726-0_24"},{"issue":"4","key":"231_CR42","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1007\/s40860-022-00185-2","volume":"9","author":"M Sharma","year":"2023","unstructured":"Sharma M, Kaur P (2023) XLAAM: explainable LSTM-based activity and anomaly monitoring in a fog environment. J Reliab Intell Environ 9(4):463\u2013477. https:\/\/doi.org\/10.1007\/s40860-022-00185-2","journal-title":"J Reliab Intell Environ"},{"issue":"2","key":"231_CR43","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1080\/15472450.2015.1037955","volume":"20","author":"EI Vlahogianni","year":"2016","unstructured":"Vlahogianni EI, Kepaptsoglou K et al (2016) A real-time parking prediction system for smart cities. J Intell Transp Syst 20(2):192\u2013204. https:\/\/doi.org\/10.1080\/15472450.2015.1037955","journal-title":"J Intell Transp Syst"},{"issue":"5","key":"231_CR44","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1016\/j.dcan.2022.06.018","volume":"9","author":"T Alladi","year":"2023","unstructured":"Alladi T, Kohli V et al (2023) A deep learning based misbehavior classification scheme for intrusion detection in cooperative intelligent transportation systems. Digit Commun Netw 9(5):1113\u20131122. https:\/\/doi.org\/10.1016\/j.dcan.2022.06.018","journal-title":"Digit Commun Netw"},{"key":"231_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2021\/3806459","volume":"2021","author":"H Alkahtani","year":"2021","unstructured":"Alkahtani H, Aldhyani TH (2021) Botnet attack detection by using CNN-LSTM model for internet of things applications. Secur Commun Netw 2021:1\u201323. https:\/\/doi.org\/10.1155\/2021\/3806459","journal-title":"Secur Commun Netw"},{"key":"231_CR46","doi-asserted-by":"publisher","unstructured":"Hinton GE (2012) In: Montavon G, Orr GB, M\u00fcller K-R (eds) A practical guide to training restricted boltzmann machines, pp 599\u2013619. Springer, Berlin, Heidelberg. https:\/\/doi.org\/10.1007\/978-3-642-35289-8_32","DOI":"10.1007\/978-3-642-35289-8_32"},{"issue":"7","key":"231_CR47","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Osindero S, Teh Y-W (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527\u20131554. https:\/\/doi.org\/10.1162\/neco.2006.18.7.1527","journal-title":"Neural Comput"},{"key":"231_CR48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-55833-8_12","author":"A Peter Soosai Anandaraj","year":"2021","unstructured":"Peter Soosai Anandaraj A, Gomathy V et al (2021) Internet of medical things (IoMT) enabled skin lesion detection and classification using optimal segmentation and restricted Boltzmann machines. Cogn Internet Med Things Smart Healthc Serv Appl. https:\/\/doi.org\/10.1007\/978-3-030-55833-8_12","journal-title":"Cogn Internet Med Things Smart Healthc Serv Appl"},{"issue":"3","key":"231_CR49","doi-asserted-by":"publisher","first-page":"0119044","DOI":"10.1371\/journal.pone.0119044","volume":"10","author":"X Ma","year":"2015","unstructured":"Ma X, Yu H et al (2015) Large-scale transportation network congestion evolution prediction using deep learning theory. PLoS One 10(3):0119044. https:\/\/doi.org\/10.1371\/journal.pone.0119044","journal-title":"PLoS One"},{"key":"231_CR50","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.jnca.2019.02.026","volume":"135","author":"A Elsaeidy","year":"2019","unstructured":"Elsaeidy A, Munasinghe KS et al (2019) Intrusion detection in smart cities using restricted Boltzmann machines. J Netw Comput Appl 135:76\u201383. https:\/\/doi.org\/10.1016\/j.jnca.2019.02.026","journal-title":"J Netw Comput Appl"},{"key":"231_CR51","unstructured":"Ng A et\u00a0al (2011) Sparse autoencoder. CS294A Lect Notes 72:1\u201319"},{"issue":"5555\/1756006","key":"231_CR52","first-page":"1953039","volume":"10","author":"P Vincent","year":"2010","unstructured":"Vincent P, Larochelle H et al (2010) Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res 10(5555\/1756006):1953039","journal-title":"J Mach Learn Res"},{"key":"231_CR53","unstructured":"Kingma DP, Welling M (2013) Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114"},{"key":"231_CR54","doi-asserted-by":"publisher","unstructured":"Masci J, Meier U et\u00a0al (2011) Stacked convolutional auto-encoders for hierarchical feature extraction. In: ICANN. Springer, pp 52\u201359. https:\/\/doi.org\/10.1007\/978-3-642-21735-7_7","DOI":"10.1007\/978-3-642-21735-7_7"},{"issue":"1","key":"231_CR55","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1109\/TSMC.2020.2968516","volume":"52","author":"C Yin","year":"2020","unstructured":"Yin C, Zhang S et al (2020) Anomaly detection based on convolutional recurrent autoencoder for iot time series. TSMC 52(1):112\u2013122. https:\/\/doi.org\/10.1109\/TSMC.2020.2968516","journal-title":"TSMC"},{"issue":"23","key":"231_CR56","doi-asserted-by":"publisher","first-page":"14290","DOI":"10.1109\/JSEN.2020.3007369","volume":"20","author":"J Chen","year":"2020","unstructured":"Chen J, Li T et al (2020) WSN sampling optimization for signal reconstruction using spatiotemporal autoencoder. IEEE Sens J 20(23):14290\u201314301. https:\/\/doi.org\/10.1109\/JSEN.2020.3007369","journal-title":"IEEE Sens J"},{"key":"231_CR57","doi-asserted-by":"publisher","unstructured":"Himeur Y, Alsalemi A et\u00a0al (2021) Detection of appliance-level abnormal energy consumption in buildings using autoencoders and micro-moments. In: International conference on big data internet things. Springer, pp 179\u2013193. https:\/\/doi.org\/10.1007\/978-3-031-07969-6_14","DOI":"10.1007\/978-3-031-07969-6_14"},{"issue":"2","key":"231_CR58","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/JIOT.2018.2876695","volume":"6","author":"T Yu","year":"2018","unstructured":"Yu T (2018) UAV-enabled spatial data sampling in large-scale IoT systems using denoising autoencoder neural network. IEEE IoT 6(2):1856\u20131865. https:\/\/doi.org\/10.1109\/JIOT.2018.2876695","journal-title":"IEEE IoT"},{"issue":"7","key":"231_CR59","doi-asserted-by":"publisher","first-page":"4507","DOI":"10.1109\/TITS.2020.3017882","volume":"22","author":"J Ashraf","year":"2020","unstructured":"Ashraf J, Bakhshi AD et al (2020) Novel deep learning-enabled LSTM autoencoder architecture for discovering anomalous events from intelligent transportation systems. TITS 22(7):4507\u20134518. https:\/\/doi.org\/10.1109\/TITS.2020.3017882","journal-title":"TITS"},{"issue":"10","key":"231_CR60","doi-asserted-by":"publisher","first-page":"2229","DOI":"10.3390\/s19102229","volume":"19","author":"S Zhang","year":"2019","unstructured":"Zhang S, Yao Y et al (2019) Deep autoencoder neural networks for short-term traffic congestion prediction of transportation networks. Sensors 19(10):2229. https:\/\/doi.org\/10.3390\/s19102229","journal-title":"Sensors"},{"key":"231_CR61","doi-asserted-by":"publisher","unstructured":"Bae G, Jang S et\u00a0al (2019) Autoencoder-based on anomaly detection with intrusion scoring for smart factory environments. In: PDCAT. Springer, pp 414\u2013423. https:\/\/doi.org\/10.1007\/978-981-13-5907-1_44","DOI":"10.1007\/978-981-13-5907-1_44"},{"key":"231_CR62","doi-asserted-by":"publisher","unstructured":"Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks.https:\/\/doi.org\/10.48550\/arXiv.1609.02907","DOI":"10.48550\/arXiv.1609.02907"},{"key":"231_CR63","doi-asserted-by":"publisher","unstructured":"Kipf TN, Welling M (2016) Variational graph auto-encoders. https:\/\/doi.org\/10.48550\/arXiv.1611.07308","DOI":"10.48550\/arXiv.1611.07308"},{"key":"231_CR64","unstructured":"Hajiramezanali E, Hasanzadeh A et\u00a0al. (2019) Variational graph recurrent neural networks. NeurIPS https:\/\/doi.org\/10.48550\/arXiv.1908.09710"},{"issue":"10","key":"231_CR65","doi-asserted-by":"publisher","first-page":"17654","DOI":"10.1109\/TITS.2022.3155749","volume":"23","author":"Z Sheng","year":"2022","unstructured":"Sheng Z, Xu Y et al (2022) Graph-based spatial-temporal convolutional network for vehicle trajectory prediction in autonomous driving. TITS 23(10):17654\u201317665. https:\/\/doi.org\/10.1109\/TITS.2022.3155749","journal-title":"TITS"},{"key":"231_CR66","doi-asserted-by":"publisher","first-page":"15323","DOI":"10.1609\/aaai.v35i17.17799","volume":"35","author":"AM Karimi","year":"2021","unstructured":"Karimi AM, Wu Y et al (2021) Spatiotemporal graph neural network for performance prediction of photovoltaic power systems. AAAI 35:15323\u201315330. https:\/\/doi.org\/10.1609\/aaai.v35i17.17799","journal-title":"AAAI"},{"key":"231_CR67","doi-asserted-by":"publisher","unstructured":"Rangesh A, Maheshwari et\u00a0al (2021) TrackMPNN: a message passing graph neural architecture for multi-object tracking. https:\/\/doi.org\/10.48550\/arXiv.2101.04206","DOI":"10.48550\/arXiv.2101.04206"},{"key":"231_CR68","doi-asserted-by":"publisher","unstructured":"Gama F, Tolstaya et\u00a0al. (2021) Graph neural networks for decentralized controllers. In: ICASSP, pp 5260\u20135264. https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414563","DOI":"10.1109\/ICASSP39728.2021.9414563"},{"key":"231_CR69","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2020.3041461","volume":"60","author":"D Lin","year":"2021","unstructured":"Lin D, Lin J, Zhao L et al (2021) Multilabel aerial image classification with a concept attention graph neural network. TGRS 60:1\u201312. https:\/\/doi.org\/10.1109\/TGRS.2020.3041461","journal-title":"TGRS"},{"key":"231_CR70","doi-asserted-by":"publisher","unstructured":"Bi Y, Chadha A, Abbas et\u00a0al (2019) Graph-based object classification for neuromorphic vision sensing. In: ICCV, pp 491\u2013501. https:\/\/doi.org\/10.1109\/ICCV.2019.00058","DOI":"10.1109\/ICCV.2019.00058"},{"key":"231_CR71","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.future.2021.07.012","volume":"126","author":"G Jin","year":"2022","unstructured":"Jin G, Wang M et al (2022) STGNN-TTE: travel time estimation via spatial-temporal graph neural network. Future Gener Comput Syst 126:70\u201381. https:\/\/doi.org\/10.1016\/j.future.2021.07.012","journal-title":"Future Gener Comput Syst"},{"issue":"10","key":"231_CR72","doi-asserted-by":"publisher","first-page":"11461","DOI":"10.1109\/JSEN.2020.3015726","volume":"21","author":"R Mondal","year":"2020","unstructured":"Mondal R (2020) A new framework for smartphone sensor-based human activity recognition using graph neural network. IEEE Sens J 21(10):11461\u201311468. https:\/\/doi.org\/10.1109\/JSEN.2020.3015726","journal-title":"IEEE Sens J"},{"key":"231_CR73","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2022.09.006","author":"C Guo","year":"2022","unstructured":"Guo C, Zhong Z et al (2022) Neurstrucenergy: a bi-directional GNN model for energy prediction of neural networks in IoT. DCN. https:\/\/doi.org\/10.1016\/j.dcan.2022.09.006","journal-title":"DCN"},{"key":"231_CR74","doi-asserted-by":"publisher","unstructured":"Bronstein M et\u00a0al (2021) Geometric deep learning: grids, groups, graphs, geodesics, and gauges. https:\/\/doi.org\/10.48550\/arXiv.2104.13478","DOI":"10.48550\/arXiv.2104.13478"},{"key":"231_CR75","doi-asserted-by":"publisher","unstructured":"Sun P, Kretzschmar et\u00a0al (2020) Scalability in perception for autonomous driving: Waymo open dataset. In: CVPR, pp 2446\u20132454. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00252","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"231_CR76","unstructured":"Nouri A, Charrier et\u00a0al (2017) Technical report: Greyc 3D colored mesh database. Ph.D. thesis, Normandie Universit\u00e9, Unicaen, EnsiCaen, CNRS, GREYC UMR 6072"},{"key":"231_CR77","doi-asserted-by":"publisher","unstructured":"Fei Y et\u00a0al (2023) A survey of geometric optimization for deep learning: from Euclidean space to Riemannian manifold. https:\/\/doi.org\/10.48550\/arXiv.2302.08210","DOI":"10.48550\/arXiv.2302.08210"},{"key":"231_CR78","volume-title":"Computational topology: an introduction","author":"H Edelsbrunner","year":"2022","unstructured":"Edelsbrunner H et al (2022) Computational topology: an introduction. American Mathematical Society, Providence"},{"key":"231_CR79","volume-title":"Differential geometry","author":"HW Guggenheimer","year":"2012","unstructured":"Guggenheimer HW (2012) Differential geometry. Courier Corporation, New York"},{"key":"231_CR80","volume-title":"Introduction to graph theory","author":"DB West","year":"2001","unstructured":"West DB et al (2001) Introduction to graph theory, vol 2. Prentice Hall, Upper Saddle River"},{"key":"231_CR81","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3172108","author":"C Ju","year":"2022","unstructured":"Ju C, Guan C (2022) Tensor-cspnet: a novel geometric deep learning framework for motor imagery classification. TNNLS. https:\/\/doi.org\/10.1109\/TNNLS.2022.3172108","journal-title":"TNNLS"},{"key":"231_CR82","doi-asserted-by":"publisher","unstructured":"Papakis I, Sarkar et\u00a0al (2021) A graph convolutional neural network based approach for traffic monitoring using augmented detections with optical flow. In: ITSC, pp 2980\u20132986. https:\/\/doi.org\/10.1109\/ITSC48978.2021.9564655","DOI":"10.1109\/ITSC48978.2021.9564655"},{"key":"231_CR83","doi-asserted-by":"publisher","unstructured":"Villalba-D\u00edez J, Molina M et\u00a0al (2020) Geometric deep lean learning Deep learning in industry 4.0 cyber-physical complex networks. Sensors 20(3):763. https:\/\/doi.org\/10.3390\/s20030763","DOI":"10.3390\/s20030763"},{"key":"231_CR84","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2023.3250403","author":"C Qin","year":"2023","unstructured":"Qin C, Srivastava AK et al (2023) Geometric deep-learning-based spatiotemporal forecasting for inverter-based solar power. Syst J. https:\/\/doi.org\/10.1109\/JSYST.2023.3250403","journal-title":"Syst J"},{"issue":"12","key":"231_CR85","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1038\/s42256-021-00418-8","volume":"3","author":"K Atz","year":"2021","unstructured":"Atz K, Grisoni F, Schneider G (2021) Geometric deep learning on molecular representations. Nat Mach Intell 3(12):1023\u20131032. https:\/\/doi.org\/10.1038\/s42256-021-00418-8","journal-title":"Nat Mach Intell"},{"key":"231_CR86","unstructured":"Lu J, Tian Y, Zhang Y et al (2023) LGL-BCI: A lightweight geometric learning framework for motor imagery-based brain-computer interfaces. arXiv preprint arXiv:2310.08051"},{"key":"231_CR87","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106592","volume":"212","author":"J James","year":"2021","unstructured":"James J (2021) Citywide traffic speed prediction: a geometric deep learning approach. Knowl Based Syst 212:106592. https:\/\/doi.org\/10.1016\/j.knosys.2020.106592","journal-title":"Knowl Based Syst"},{"key":"231_CR88","doi-asserted-by":"publisher","unstructured":"Monti F, Boscaini et\u00a0al (2017) Geometric deep learning on graphs and manifolds using mixture model cnns. In: CVPR, pp 5115\u20135124. https:\/\/doi.org\/10.1109\/CVPR.2017.576","DOI":"10.1109\/CVPR.2017.576"},{"key":"231_CR89","doi-asserted-by":"publisher","unstructured":"Huang Z, Van\u00a0Gool L (2017) A riemannian network for spd matrix learning. In: AAAI, 31. https:\/\/doi.org\/10.1609\/aaai.v31i1.10866","DOI":"10.1609\/aaai.v31i1.10866"},{"key":"231_CR90","unstructured":"Ashish V, Noam S et\u00a0al. (2017) Attention is all you need. NeurIPS https:\/\/doi.org\/10.48550\/arXiv.1706.03762"},{"key":"231_CR91","doi-asserted-by":"publisher","first-page":"26146","DOI":"10.1109\/ACCESS.2019.2900753","volume":"7","author":"T Shao","year":"2019","unstructured":"Shao T, Guo Y et al (2019) Transformer-based neural network for answer selection in question answering. IEEE Access 7:26146\u201326156. https:\/\/doi.org\/10.1109\/ACCESS.2019.2900753","journal-title":"IEEE Access"},{"key":"231_CR92","unstructured":"Devlin J, Chang et al (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"231_CR93","doi-asserted-by":"publisher","unstructured":"Liu Y, Ott M et\u00a0al (2019) Roberta: a robustly optimized bert pretraining approach. https:\/\/doi.org\/10.48550\/arXiv.1907.11692","DOI":"10.48550\/arXiv.1907.11692"},{"key":"231_CR94","doi-asserted-by":"publisher","unstructured":"Simunec M, Soic R (2023) Smart home notifications in Croatian language: a transformer-based approach. In: ConTEL, pp 1\u20135. https:\/\/doi.org\/10.1109\/ConTEL58387.2023.10199029","DOI":"10.1109\/ConTEL58387.2023.10199029"},{"issue":"6","key":"231_CR95","doi-asserted-by":"publisher","first-page":"5050","DOI":"10.1109\/JIOT.2022.3221967","volume":"10","author":"Y Luo","year":"2022","unstructured":"Luo Y, Chen X et al (2022) Transformer-based device-type identification in heterogeneous IoT traffic. IEEE IoT 10(6):5050\u20135062. https:\/\/doi.org\/10.1109\/JIOT.2022.3221967","journal-title":"IEEE IoT"},{"issue":"2","key":"231_CR96","doi-asserted-by":"publisher","first-page":"212","DOI":"10.3390\/iot5020011","volume":"5","author":"N Rashvand","year":"2024","unstructured":"Rashvand N, Witham K et al (2024) Enhancing automatic modulation recognition for IoT applications using transformers. IoT 5(2):212\u2013226. https:\/\/doi.org\/10.3390\/iot5020011","journal-title":"IoT"},{"issue":"12","key":"231_CR97","doi-asserted-by":"publisher","first-page":"9179","DOI":"10.1109\/JIOT.2021.3100509","volume":"9","author":"Z Chen","year":"2021","unstructured":"Chen Z, Chen D et al (2021) Learning graph structures with transformer for multivariate time-series anomaly detection in IoT. IEEE IoT 9(12):9179\u20139189. https:\/\/doi.org\/10.1109\/JIOT.2021.3100509","journal-title":"IEEE IoT"},{"key":"231_CR98","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2023.110072","volume":"237","author":"S Ullah","year":"2023","unstructured":"Ullah S, Ahmad J et al (2023) TNN-IDS: transformer neural network-based intrusion detection system for MQTT-enabled IoT networks. Comput Netw 237:110072. https:\/\/doi.org\/10.1016\/j.comnet.2023.110072","journal-title":"Comput Netw"},{"key":"231_CR99","doi-asserted-by":"publisher","first-page":"2585","DOI":"10.1007\/s10115-021-01605-0","volume":"63","author":"X Hu","year":"2021","unstructured":"Hu X, Chu L, Pei J et al (2021) Model complexity of deep learning: a survey. Knowl Inf Syst 63:2585\u20132619. https:\/\/doi.org\/10.1007\/s10115-021-01605-0","journal-title":"Knowl Inf Syst"},{"issue":"1","key":"231_CR100","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3363554","volume":"53","author":"R Mayer","year":"2020","unstructured":"Mayer R, Jacobsen H-A (2020) Scalable deep learning on distributed infrastructures: challenges, techniques, and tools. CSUR 53(1):1\u201337. https:\/\/doi.org\/10.1145\/3363554","journal-title":"CSUR"},{"key":"231_CR101","doi-asserted-by":"publisher","unstructured":"Han J, Cen et\u00a0al (2024) A survey of geometric graph neural networks: data structures, models and applications. https:\/\/doi.org\/10.48550\/arXiv.2403.00485","DOI":"10.48550\/arXiv.2403.00485"},{"key":"231_CR102","doi-asserted-by":"publisher","unstructured":"Yan F, Ruwase et\u00a0al (2015) Performance modeling and scalability optimization of distributed deep learning systems. In: KDD, pp 1355\u20131364. https:\/\/doi.org\/10.1145\/2783258.2783270","DOI":"10.1145\/2783258.2783270"},{"key":"231_CR103","doi-asserted-by":"publisher","unstructured":"Xi Z, Mok AK et\u00a0al (2024) Testing learning-enabled cyber-physical systems with large-language models: a formal approach. https:\/\/doi.org\/10.48550\/arXiv.2311.07377","DOI":"10.48550\/arXiv.2311.07377"},{"key":"231_CR104","doi-asserted-by":"publisher","unstructured":"Pei K, Cao Y, Suman (2017) Deepxplore: automated whitebox testing of deep learning systems. In: SOSP, pp 1\u201318. https:\/\/doi.org\/10.1145\/3132747.3132785","DOI":"10.1145\/3132747.3132785"},{"key":"231_CR105","doi-asserted-by":"publisher","unstructured":"Geyer J, Kassahun et\u00a0al (2020) A2d2: audi autonomous driving dataset. https:\/\/doi.org\/10.48550\/arXiv.2004.06320","DOI":"10.48550\/arXiv.2004.06320"},{"key":"231_CR106","doi-asserted-by":"publisher","unstructured":"Harel-Canada F, Wang et\u00a0al (2020) Is neuron coverage a meaningful measure for testing deep neural networks? In: ESEC\/FSE, pp 851\u2013862. https:\/\/doi.org\/10.1145\/3368089.3409754","DOI":"10.1145\/3368089.3409754"},{"key":"231_CR107","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3206427","author":"Y Deng","year":"2022","unstructured":"Deng Y, Zheng X et al (2022) A declarative metamorphic testing framework for autonomous driving. TSE. https:\/\/doi.org\/10.1109\/TSE.2022.3206427","journal-title":"TSE"},{"issue":"2","key":"231_CR108","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1109\/TIV.2019.2955903","volume":"5","author":"CE Tuncali","year":"2019","unstructured":"Tuncali CE et al (2019) Requirements-driven test generation for autonomous vehicles with machine learning components. TIV 5(2):265\u2013280. https:\/\/doi.org\/10.1109\/TIV.2019.2955903","journal-title":"TIV"},{"key":"231_CR109","doi-asserted-by":"publisher","unstructured":"Qin X, Ar\u00e9chiga N et\u00a0al (2023) Robust testing for cyber-physical systems using reinforcement learning. In: MEMOCODE, pp 36\u201346. https:\/\/doi.org\/10.1145\/3610579.3611087","DOI":"10.1145\/3610579.3611087"},{"issue":"12","key":"231_CR110","doi-asserted-by":"publisher","first-page":"3197","DOI":"10.1007\/s10115-022-01756-8","volume":"64","author":"X Li","year":"2022","unstructured":"Li X, Xiong H et al (2022) Interpretable deep learning: Interpretation, interpretability, trustworthiness, and beyond. Knowl Inf Syst 64(12):3197\u20133234. https:\/\/doi.org\/10.1007\/s10115-022-01756-8","journal-title":"Knowl Inf Syst"},{"key":"231_CR111","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1214\/21-SS133","volume":"16","author":"C Rudin","year":"2022","unstructured":"Rudin C et al (2022) Interpretable machine learning: fundamental principles and 10 grand challenges. Stat Surv 16:1\u201385. https:\/\/doi.org\/10.1214\/21-SS133","journal-title":"Stat Surv"},{"key":"231_CR112","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2021.113556","volume":"150","author":"A Gosiewska","year":"2021","unstructured":"Gosiewska A, Kozak A et al (2021) Simpler is better: lifting interpretability-performance trade-off via automated feature engineering. Decis Support Syst 150:113556. https:\/\/doi.org\/10.1016\/j.dss.2021.113556","journal-title":"Decis Support Syst"},{"issue":"1","key":"231_CR113","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3567430","volume":"14","author":"J-P Kucklick","year":"2023","unstructured":"Kucklick J-P, M\u00fcller O (2023) Tackling the accuracy-interpretability trade-off: interpretable deep learning models for satellite image-based real estate appraisal. ACM Trans Manag Inf Syst 14(1):1\u201324. https:\/\/doi.org\/10.1145\/3567430","journal-title":"ACM Trans Manag Inf Syst"},{"key":"231_CR114","doi-asserted-by":"publisher","unstructured":"Olah C, Schubert L et al (2017) Feature visualization. Distill. https:\/\/doi.org\/10.23915\/distill.00007","DOI":"10.23915\/distill.00007"},{"issue":"7","key":"231_CR115","doi-asserted-by":"publisher","first-page":"0130140","DOI":"10.1371\/journal.pone.0130140","volume":"10","author":"S Bach","year":"2015","unstructured":"Bach S, Binder A et al (2015) On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS One 10(7):0130140. https:\/\/doi.org\/10.1371\/journal.pone.0130140","journal-title":"PLoS One"},{"issue":"2","key":"231_CR116","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/s12369-021-00790-w","volume":"14","author":"S Umbrello","year":"2022","unstructured":"Umbrello S, Yampolskiy RV (2022) Designing AI for explainability and verifiability: a value sensitive design approach to avoid artificial stupidity in autonomous vehicles. IJSR 14(2):313\u2013322. https:\/\/doi.org\/10.1007\/s12369-021-00790-w","journal-title":"IJSR"},{"key":"231_CR117","unstructured":"Patil KR, Heinrichs B (2022) Verifiability as a complement to AI explainability: A conceptual proposal. https:\/\/philsci-archive.pitt.edu\/20297\/"},{"key":"231_CR118","first-page":"29909","volume":"34","author":"S Wang","year":"2021","unstructured":"Wang S, Zhang H, Xu K et al (2021) Beta-crown: efficient bound propagation with per-neuron split constraints for neural network robustness verification. NeurIPS 34:29909\u201329921","journal-title":"NeurIPS"},{"issue":"8","key":"231_CR119","doi-asserted-by":"publisher","first-page":"4435","DOI":"10.1016\/j.jfranklin.2021.02.029","volume":"358","author":"J Feng","year":"2021","unstructured":"Feng J, Chai Y, Xu C (2021) A novel neural network to nonlinear complex-variable constrained nonconvex optimization. J Frankl Inst 358(8):4435\u20134457. https:\/\/doi.org\/10.1016\/j.jfranklin.2021.02.029","journal-title":"J Frankl Inst"},{"key":"231_CR120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-00832-0_3","author":"M Danilova","year":"2021","unstructured":"Danilova M, Dvurechensky P et al (2021) Recent theoretical advances in non-convex optimization. Springer, Berlin. https:\/\/doi.org\/10.1007\/978-3-031-00832-0_3","journal-title":"Springer, Berlin."},{"key":"231_CR121","doi-asserted-by":"publisher","unstructured":"He Z, Zhang T, Lee RB (2018) VeriDeep: verifying integrity of deep neural networks through sensitive-sample fingerprinting.https:\/\/doi.org\/10.48550\/arXiv.1808.03277","DOI":"10.48550\/arXiv.1808.03277"},{"key":"231_CR122","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1007\/s11063-020-10420-7","volume":"53","author":"L Xiang","year":"2021","unstructured":"Xiang L, Zeng X, Wu S et al (2021) Computation of CNN\u2019s sensitivity to input perturbation. Neural Process Lett 53:535\u2013560. https:\/\/doi.org\/10.1007\/s11063-020-10420-7","journal-title":"Neural Process Lett"},{"key":"231_CR123","doi-asserted-by":"publisher","unstructured":"Deng Y, Zheng X, Zhang T et al (2020) An analysis of adversarial attacks and defenses on autonomous driving models. In: PerCom, pp 1\u201310. https:\/\/doi.org\/10.1109\/PerCom45495.2020.9127389","DOI":"10.1109\/PerCom45495.2020.9127389"},{"key":"231_CR124","doi-asserted-by":"publisher","unstructured":"Hu R, Andreas J, Rohrbach M et\u00a0al (2017) Learning to reason: end-to-end module networks for visual question answering. In: ICCV, pp 804\u2013813. https:\/\/doi.org\/10.1109\/ICCV.2017.93","DOI":"10.1109\/ICCV.2017.93"},{"key":"231_CR125","unstructured":"Towell GG, Shavlik JW, Noordewier MO (1990) Refinement of approximate domain theories by knowledge-based neural networks. In: AAAI"},{"key":"231_CR126","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1023\/A:1008328630915","volume":"11","author":"ASA Garcez","year":"1999","unstructured":"Garcez ASA, Zaverucha G (1999) The connectionist inductive learning and logic programming system. Applied Intelligence 11:59\u201377","journal-title":"Applied Intelligence"},{"key":"231_CR127","unstructured":"Jaeger H (2017) Controlling recurrent neural networks by conceptors. arXiv:1403.3369"},{"key":"231_CR128","unstructured":"Graves A, Wayne G, Danihelka I (2014) Neural turing machines. arXiv preprint arXiv:1410.5401"},{"key":"231_CR129","unstructured":"Sainbayar S, Arthur S, Jason W et\u00a0al (2015) End-to-end memory networks. In: NIPS. MIT Press, Cambridge, MA, USA, pp 2440\u20132448"},{"key":"231_CR130","unstructured":"Yi K, Gan C, Li Y, Kohli P (2020) CLEVRER: collision events for video representation and reasoning. arXiv:1910.01442"},{"key":"231_CR131","doi-asserted-by":"publisher","unstructured":"Wickramarachchi R, Henson C, Sheth A (2020) An evaluation of knowledge graph embeddings for autonomous driving data: experience and practice. https:\/\/doi.org\/10.48550\/arXiv.2003.00344","DOI":"10.48550\/arXiv.2003.00344"},{"key":"231_CR132","doi-asserted-by":"publisher","unstructured":"Liu Z, Wang Z, Lin Y, Li H (2022) A neural-symbolic approach to natural language understanding. https:\/\/doi.org\/10.48550\/arXiv.2203.10557","DOI":"10.48550\/arXiv.2203.10557"},{"key":"231_CR133","first-page":"1","volume":"31","author":"R Manhaeve","year":"2018","unstructured":"Manhaeve R, Dumancic S, Kimmig A et al (2018) Deepproblog: neural probabilistic logic programming. Adv Neural Inf Process Syst 31:1\u201314","journal-title":"Adv Neural Inf Process Syst"},{"key":"231_CR134","doi-asserted-by":"publisher","unstructured":"Parisotto E, Mohamed A-R, Singh R et\u00a0al (2016) Neuro-symbolic program synthesis. https:\/\/doi.org\/10.48550\/arXiv.1611.01855","DOI":"10.48550\/arXiv.1611.01855"},{"key":"231_CR135","doi-asserted-by":"publisher","unstructured":"Kimura D, Ono M, Chaudhury S, et\u00a0al. (2021) Neuro-symbolic reinforcement learning with first-order logic. https:\/\/doi.org\/10.48550\/arXiv.2110.10963","DOI":"10.48550\/arXiv.2110.10963"},{"key":"231_CR136","unstructured":"Iayuan M, Chuang G, Pushmeet K et\u00a0al (2019) The neuro-symbolic concept learner: interpreting scenes, words, and sentences from natural supervision. arXiv:1904.12584"},{"key":"231_CR137","doi-asserted-by":"crossref","unstructured":"Sur\u00eds D, Menon S, Vondrick C (2023) ViperGPT: visual inference via python execution for reasoning. arXiv:2303.08128","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"231_CR138","unstructured":"Djallel B, Aggarwal CC (2022) Survey on applications of neurosymbolic artificial intelligence. arXiv:2209.12618"},{"issue":"4","key":"231_CR139","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/s40860-021-00158-x","volume":"8","author":"C Bulla","year":"2022","unstructured":"Bulla C, Birje MN (2022) Improved data-driven root cause analysis in fog computing environment. J Reliab Intell Environ 8(4):359\u2013377","journal-title":"J Reliab Intell Environ"},{"key":"231_CR140","first-page":"2468","volume-title":"IJCAI","author":"LD Raedt","year":"2007","unstructured":"Raedt LD, Kimmig A, Toivonen H (2007) ProbLog: a probabilistic prolog and its application in link discovery. IJCAI. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, pp 2468\u20132473"},{"issue":"5","key":"231_CR141","first-page":"1206","volume":"30","author":"X Hu","year":"2019","unstructured":"Hu X, Li G, Liu F, Jin Z (2019) Program generation and code completion techniques based on deep learning: literature review. J Softw 30(5):1206\u20131223","journal-title":"J Softw"},{"issue":"2","key":"231_CR142","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1017\/S0269888900008122","volume":"10","author":"M Wooldridge","year":"1995","unstructured":"Wooldridge M, Jennings NR (1995) Intelligent agents: theory and practice. Knowl Eng Rev 10(2):115\u2013152","journal-title":"Knowl Eng Rev"},{"issue":"4","key":"231_CR143","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s40860-018-0070-5","volume":"4","author":"HR Schmidtke","year":"2018","unstructured":"Schmidtke HR (2018) A survey on verification strategies for intelligent transportation systems. J Reliab Intell Environ 4(4):211\u2013224","journal-title":"J Reliab Intell Environ"},{"key":"231_CR144","doi-asserted-by":"publisher","unstructured":"Andreas J, Rohrbach M, Darrell T, Klein D (2017) Neural module networks. https:\/\/doi.org\/10.48550\/arXiv.1511.02799","DOI":"10.48550\/arXiv.1511.02799"},{"issue":"3","key":"231_CR145","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1234\/jair.v15i3.567","volume":"15","author":"LH Gilpin","year":"2021","unstructured":"Gilpin LH, Ilievski F (2021) Neuro-symbolic reasoning in the traffic domain. J AI Res 15(3):123\u2013145. https:\/\/doi.org\/10.1234\/jair.v15i3.567","journal-title":"J AI Res"},{"key":"231_CR146","unstructured":"Sun J, Sun H, Han T, Zhou B (2020) Neuro-symbolic program search for autonomous driving decision module design. In: CoRL"},{"key":"231_CR147","unstructured":"Sharifi I, Yildirim M, Fallah S (2023) Towards safe autonomous driving policies using a neuro-symbolic deep reinforcement learning approach. arXiv:2307.01316"},{"key":"231_CR148","doi-asserted-by":"publisher","first-page":"941","DOI":"10.3758\/s13423-016-1045-2","volume":"23","author":"BZ Mahon","year":"2016","unstructured":"Mahon BZ, Hickok G (2016) Arguments about the nature of concepts: symbols, embodiment, and beyond. Psychon Bull Rev 23:941\u2013958. https:\/\/doi.org\/10.3758\/s13423-016-1045-2","journal-title":"Psychon Bull Rev"},{"key":"231_CR149","doi-asserted-by":"publisher","unstructured":"Kalithasan N, Singh H, Bindal V et\u00a0al (2023) Learning neuro-symbolic programs for language guided robot manipulation. In: ICRA, pp 7973\u20137980. https:\/\/doi.org\/10.1109\/ICRA48891.2023.10160545","DOI":"10.1109\/ICRA48891.2023.10160545"},{"key":"231_CR150","doi-asserted-by":"publisher","unstructured":"Gubbi S, Venkatesh Biswas A et\u00a0al (2021) Spatial reasoning from natural language instructions for robot manipulation. In: ICRA, pp 11196\u201311202. https:\/\/doi.org\/10.1109\/ICRA48506.2021.9560895","DOI":"10.1109\/ICRA48506.2021.9560895"},{"key":"231_CR151","unstructured":"Hanson D, Imran A, Vellanki A, Kanagaraj S (2020) A neuro-symbolic humanlike arm controller for Sophia the robot"},{"key":"231_CR152","doi-asserted-by":"publisher","unstructured":"Carraro T (2023) Overcoming recommendation limitations with neuro-symbolic integration. In: RecSys. RecSys \u201923. Association for Computing Machinery, New York, NY, USA, pp 1325\u20131331. https:\/\/doi.org\/10.1145\/3604915.3608876","DOI":"10.1145\/3604915.3608876"},{"key":"231_CR153","unstructured":"Shakya A, Rus V, Venugopal D (2021) Student strategy prediction using a neuro-symbolic approach. ERIC Number: ED615630"},{"key":"231_CR154","unstructured":"Fan Y, Bowden KK et\u00a0al (2023) Athena 3.0: personalized multimodal chatbot with neuro-symbolic dialogue generators. Alexa Prize Soc Bot Grand Challenge 5. Amazon Science"},{"key":"231_CR155","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.neunet.2023.06.028","volume":"166","author":"D Yu","year":"2023","unstructured":"Yu D, Yang B, Liu D, Wang H, Pan S (2023) A survey on neural-symbolic learning systems. Neural Netw 166:105\u2013126. https:\/\/doi.org\/10.1016\/j.neunet.2023.06.028","journal-title":"Neural Netw"},{"key":"231_CR156","doi-asserted-by":"publisher","unstructured":"Rawat DB (2023) Towards neuro-symbolic AI for assured and trustworthy human-autonomy teaming. In: TPS-ISA, Los Alamitos, CA, USA, pp 177\u2013179. https:\/\/doi.org\/10.1109\/TPS-ISA58951.2023.00030","DOI":"10.1109\/TPS-ISA58951.2023.00030"},{"issue":"3","key":"231_CR157","doi-asserted-by":"publisher","first-page":"197","DOI":"10.3233\/AIC-210084","volume":"34","author":"MK Sarker","year":"2022","unstructured":"Sarker MK, Zhou L, Eberhart A, Hitzler P (2022) Neuro-symbolic artificial intelligence: current trends. AI Commun 34(3):197\u2013209. https:\/\/doi.org\/10.3233\/AIC-210084","journal-title":"AI Commun"},{"key":"231_CR158","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/s40860-021-00158-x","volume":"8","author":"C Bulla","year":"2021","unstructured":"Bulla C, Birje MN (2021) Improved data-driven root cause analysis in fog computing environment. J Reliab Intell Environ 8:359\u2013377","journal-title":"J Reliab Intell Environ"},{"key":"231_CR159","unstructured":"Balla J, Huang S, Dugan O et al (2023) AI-assisted discovery of quantitative and formal models in social science. arXiv preprint arXiv:2210.00563"},{"issue":"8","key":"231_CR160","doi-asserted-by":"publisher","first-page":"10902","DOI":"10.1109\/TITS.2021.3096998","volume":"23","author":"B Gangopadhyay","year":"2022","unstructured":"Gangopadhyay B, Soora H, Dasgupta P (2022) Hierarchical program-triggered reinforcement learning agents for automated driving. IEEE T-ITS 23(8):10902\u201310911. https:\/\/doi.org\/10.1109\/TITS.2021.3096998","journal-title":"IEEE T-ITS"},{"key":"231_CR161","unstructured":"Li Q, Zhu Y, Liang Y et al (2024) Neural-symbolic recursive machine for systematic generalization. arXiv preprint arXiv:2210.01603"},{"key":"231_CR162","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s40860-019-00073-2","volume":"5","author":"SAP Kumar","year":"2019","unstructured":"Kumar SAP, Bao S, Singh V, Hallstrom J (2019) Flooding disaster resilience information framework for smart and connected communities. J Reliab Intell Environ 5:3\u201315. https:\/\/doi.org\/10.1007\/s40860-019-00073-2","journal-title":"J Reliab Intell Environ"},{"key":"231_CR163","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3216622","volume":"60","author":"I Harmon","year":"2022","unstructured":"Harmon I, Marconi S, Weinstein B et al (2022) Injecting domain knowledge into deep neural networks for tree crown delineation. TGRS 60:1\u201319. https:\/\/doi.org\/10.1109\/TGRS.2022.3216622","journal-title":"TGRS"},{"key":"231_CR164","doi-asserted-by":"publisher","DOI":"10.1145\/3381010","author":"PS Santhalingam","year":"2020","unstructured":"Santhalingam PS, Hosain AA, Zhang D et al (2020) mmASL: environment-independent asl gesture recognition using 60 ghz millimeter-wave signals. IMWUT. https:\/\/doi.org\/10.1145\/3381010","journal-title":"IMWUT"},{"key":"231_CR165","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.arcontrol.2017.09.012","volume":"44","author":"D Gruyer","year":"2017","unstructured":"Gruyer D, Magnier V, Hamdi K et al (2017) Perception, information processing and modeling: critical stages for autonomous driving applications. Annu Rev Control 44:323\u2013341. https:\/\/doi.org\/10.1016\/j.arcontrol.2017.09.012","journal-title":"Annu Rev Control"},{"issue":"4","key":"231_CR166","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1016\/j.neunet.2009.12.005","volume":"23","author":"K Dobosz","year":"2010","unstructured":"Dobosz K, Duch W (2010) Understanding neurodynamical systems via fuzzy symbolic dynamics. Neural Netw 23(4):487\u2013496. https:\/\/doi.org\/10.1016\/j.neunet.2009.12.005. (ICANN 2008)","journal-title":"Neural Netw"},{"key":"231_CR167","doi-asserted-by":"publisher","unstructured":"Lu HL, Ong K, Chia P (2000) An automated ecg classification system based on a neuro-fuzzy system. In: Computers in cardiology 2000, vol 27 (Cat. 00CH37163), pp 387\u2013390. https:\/\/doi.org\/10.1109\/CIC.2000.898538","DOI":"10.1109\/CIC.2000.898538"},{"key":"231_CR168","unstructured":"Han L, Srivastava MB (2024) An empirical evaluation of neural and neuro-symbolic approaches to real-time multimodal complex event detection. arXiv preprint arXiv:2402.11403"},{"key":"231_CR169","doi-asserted-by":"publisher","DOI":"10.3389\/fmars.2021.646926","volume":"8","author":"X Chen","year":"2021","unstructured":"Chen X, Chen G, Ge L, Huang B et al (2021) Global oceanic eddy identification: a deep learning method from argo profiles and altimetry data. Front Mar Sci 8:646926","journal-title":"Front Mar Sci"},{"issue":"3","key":"231_CR170","doi-asserted-by":"publisher","first-page":"1807","DOI":"10.1109\/JSEN.2021.3139124","volume":"22","author":"A Wilson","year":"2021","unstructured":"Wilson A, Kumar A, Jha A, Cenkeramaddi LR (2021) Embedded sensors, communication technologies, computing platforms and machine learning for uavs: a review. IEEE Sens J 22(3):1807\u20131826","journal-title":"IEEE Sens J"},{"key":"231_CR171","unstructured":"Cho A, Kang Y-S, Park B-J, Yoo C-S, Koo S-O (2011) Altitude integration of radar altimeter and GPS\/INS for automatic takeoff and landing of a UAV. In: ICCAS, pp 1429\u20131432"},{"issue":"7","key":"231_CR172","doi-asserted-by":"publisher","first-page":"2313","DOI":"10.3390\/s21072313","volume":"21","author":"ML Hoang","year":"2021","unstructured":"Hoang ML, Carrat\u00f9 M, Paciello V, Pietrosanto A (2021) Body temperature-indoor condition monitor and activity recognition by mems accelerometer based on iot-alert system for people in quarantine due to COVID-19. Sensors 21(7):2313","journal-title":"Sensors"},{"key":"231_CR173","first-page":"790","volume":"2","author":"MAR Ahad","year":"2020","unstructured":"Ahad MAR, Antar AD, Ahmed M (2020) IoT sensor-based activity recognition. IEEE Trans Syst Man Cybern Part C (Appl Rev) 2:790\u2013808","journal-title":"IEEE Trans Syst Man Cybern Part C (Appl Rev)"},{"issue":"8","key":"231_CR174","doi-asserted-by":"publisher","first-page":"9320","DOI":"10.1007\/s11227-022-05026-w","volume":"79","author":"A Moin","year":"2023","unstructured":"Moin A, Aadil F, Ali Z, Kang D (2023) Emotion recognition framework using multiple modalities for an effective human-computer interaction. J Supercomput 79(8):9320\u20139349","journal-title":"J Supercomput"},{"key":"231_CR175","doi-asserted-by":"crossref","unstructured":"Wan Z, Liu C-K, Yang H, et\u00a0al. (2024) Towards cognitive AI systems: a survey and prospective on neuro-symbolic AI. arXiv:2401.01040","DOI":"10.1109\/ISPASS61541.2024.00033"},{"key":"231_CR176","unstructured":"Serafini L, Garcez A (2016) Logic tensor networks: deep learning and logical reasoning from data and knowledge. arXiv:1606.04422"},{"key":"231_CR177","doi-asserted-by":"crossref","unstructured":"Kim J, Canny J (2017) Interpretable learning for self-driving cars by visualizing causal attention","DOI":"10.1109\/ICCV.2017.320"},{"key":"231_CR178","unstructured":"Carlini N, Mishra P, Vaidya T, et\u00a0al. (2016) Hidden voice commands. In: 25th USENIX security symposium, pp 513\u2013530"},{"key":"231_CR179","doi-asserted-by":"crossref","unstructured":"Shokri R, Stronati M, Song C, Shmatikov V (2017) Membership inference attacks against machine learning models. In: 2017 IEEE symposium on security and privacy (SP), pp 3\u201318","DOI":"10.1109\/SP.2017.41"},{"key":"231_CR180","unstructured":"Song Y, Kim T, Nowozin S et\u00a0al (2017) Pixeldefend: leveraging generative models to understand and defend against adversarial examples. arXiv:1710.10766"},{"key":"231_CR181","unstructured":"Michel-Del\u00e9tie C, Sarker MK (2024) Neuro-symbolic methods for trustworthy AI: a systematic review. Neurosymb Artif Intell 0(1):1\u201314"},{"key":"231_CR182","doi-asserted-by":"publisher","unstructured":"Agiollo A, Omicini A (2023) Measuring trustworthiness in neuro-symbolic integration. In: FedCSIS, pp 1\u201310. https:\/\/doi.org\/10.15439\/2023F6019","DOI":"10.15439\/2023F6019"},{"key":"231_CR183","doi-asserted-by":"crossref","unstructured":"Sheth A, Roy K (2023) Neurosymbolic value-inspired AI (why, what, and how). arXiv preprint arXiv:2312.09928","DOI":"10.1109\/MIS.2023.3268724"},{"issue":"2","key":"231_CR184","doi-asserted-by":"crossref","first-page":"76","DOI":"10.24920\/003611","volume":"34","author":"J Guan","year":"2019","unstructured":"Guan J (2019) Artificial intelligence in healthcare and medicine: promises, ethical challenges and governance. Chin Med Sci J 34(2):76\u201383","journal-title":"Chin Med Sci J"},{"key":"231_CR185","unstructured":"Kleinberg J, Mullainathan S, Raghavan M (2016) Inherent trade-offs in the fair determination of risk scores. arXiv:1609.05807"},{"key":"231_CR186","doi-asserted-by":"crossref","unstructured":"Cunnington D, Law M, Russo A et\u00a0al (2021) Towards neural-symbolic learning to support human-agent operations. In: FUSION, pp 1\u20138","DOI":"10.23919\/FUSION49465.2021.9626876"}],"container-title":["Journal of Reliable Intelligent Environments"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40860-024-00231-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40860-024-00231-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40860-024-00231-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T22:30:27Z","timestamp":1732487427000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40860-024-00231-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,26]]},"references-count":186,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["231"],"URL":"https:\/\/doi.org\/10.1007\/s40860-024-00231-1","relation":{},"ISSN":["2199-4668","2199-4676"],"issn-type":[{"value":"2199-4668","type":"print"},{"value":"2199-4676","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,26]]},"assertion":[{"value":"24 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}