{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:56:56Z","timestamp":1785337016329,"version":"3.55.0"},"reference-count":33,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Form Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Eating is a primary daily activity crucial for maintaining independence and quality of life. Individuals with neuromuscular impairments often struggle with eating due to limitations in current assistive devices, which are predominantly passive and lack adaptive capabilities.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to introduce an adaptive feeding robot that integrates time series decomposition, autoregressive integrated moving average (ARIMA), and feed-forward neural networks (FFNN). The goal is to enhance feeding precision, efficiency, and personalization, thereby promoting autonomy for individuals with motor impairments.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n The proposed feeding robot combines information from sensors and actuators to collect real-time data, that is, facial landmarks, mouth status (open or closed), fork-to-mouth and plate distances, as well as the force and angle required for food handling based on the food type. ARIMA and FFNN algorithms analyze data to predict user behavior and adjust feeding actions dynamically. A strain gauge sensor ensures precise force regulation, an ultrasonic sensor optimizes positioning, and facial recognition algorithms verify safety by monitoring mouth conditions and plate contents.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The combined ARIMA+FFNN model achieved a mean squared error (MSE) of 0.008 and an\n R<\/jats:italic>\n 2<\/jats:sup>\n of 94%, significantly outperforming the standalone ARIMA (MSE=0.015;\n R<\/jats:italic>\n 2<\/jats:sup>\n =85%) and FFNN (MSE=0.012;\n R<\/jats:italic>\n 2<\/jats:sup>\n =88%). Feeding success rate improved from 75% to 90% over 150 iterations (\n P<.<\/jats:italic>\n 001), and response time decreased by 28% (from 3.6 s to 2.2 s). ANOVA revealed significant differences in success rates across scenarios (\n F<\/jats:italic>\n 3,146<\/jats:sub>\n =12.34;\n P<\/jats:italic>\n = .002), with scenario 1 outperforming scenario 3 (\n P<\/jats:italic>\n =.030) and scenario 4 (\n P<\/jats:italic>\n =.010). Object detection showed high accuracy (face detection precision=97%, recall=96%, 95% CI 94%-99%). Force application matched expected ranges with minimal deviation (24 [1]\n N<\/jats:italic>\n for apples; 7 [0\n .<\/jats:italic>\n 5]\n N<\/jats:italic>\n for strawberries).\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Combining predictive algorithms and adaptive learning mechanisms enables the feeding robot to demonstrate substantial improvements in precision, responsiveness, and personalization. These advancements underline its potential to revolutionize assistive technology in rehabilitation, delivering safe and highly personalized feeding assistance to individuals with motor impairments, thereby enhancing their independence.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/69877","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T07:55:07Z","timestamp":1764662107000},"page":"e69877-e69877","source":"Crossref","is-referenced-by-count":2,"title":["Adaptive Feeding Robot With Multisensor Feedback and Predictive Control Using Autoregressive Integrated Moving Average\u2013Feed-Forward Neural Network: Simulation Study"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1443-0330","authenticated-orcid":false,"given":"Shabnam","family":"Sadeghi-Esfahlani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7418-0574","authenticated-orcid":false,"given":"Vahaj","family":"Mohaghegh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2718-9678","authenticated-orcid":false,"given":"Alireza","family":"Sanaei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1687-0608","authenticated-orcid":false,"given":"Zainib","family":"Bilal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5494-1668","authenticated-orcid":false,"given":"Nathon","family":"Arthur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7045-5735","authenticated-orcid":false,"given":"Hassan","family":"Shirvani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,1,27]]},"reference":[{"key":"R1","unstructured":"World Report on Ageing and Health. World Health Organization; 2015. URL: https:\/\/www.who.int\/publications\/i\/item\/9789241565042 [Accessed 16-01-2026] ISBN: 9789241565042"},{"key":"R2","unstructured":"World population ageing. United Nations Department of Economic and Social Affairs. 2015. URL: https:\/\/www.un.org\/en\/development\/desa\/population\/publications\/pdf\/ageing\/WPA2015_Report.pdf"},{"issue":"9968","key":"R3","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1016\/S0140-6736(14)61461-6","article-title":"Towards a comprehensive public health response to population ageing","volume":"385","author":"Beard","journal-title":"Lancet"},{"issue":"2","key":"R4","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2017-018815","article-title":"Scoping review on the use of socially assistive robot technology in elderly care","volume":"8","author":"Abdi","journal-title":"BMJ Open"},{"key":"R5","unstructured":"Loneliness in older people. National Health Service. 2022. URL: https:\/\/www.nhs.uk\/mental-health\/feelings-symptoms-behaviours\/feelings-and-symptoms\/loneliness-in-older-people\/ [Accessed 02-01-2026]"},{"key":"R6","unstructured":"Torres E Pintaric T Penzes A Schmalstieg D . Self-feeding robots for the elderly and disabled. Presented at: In Proceedings of the 1st ACM Conference on Assistive Technologies."},{"issue":"9","key":"R7","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1016\/j.robot.2010.05.007","article-title":"Towards performing everyday manipulation activities","volume":"58","author":"Beetz","journal-title":"Robot Auton Syst"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.103344","article-title":"Active robot-assisted feeding with a general-purpose mobile manipulator: design, evaluation, and lessons learned","volume":"124","author":"Park","journal-title":"Rob Auton Syst"},{"key":"R9","doi-asserted-by":"crossref","unstructured":"Song WK Kim J . Novel assistive robot for self-feeding. In: Robotic Systems-Applications, Control and Programming. InTech; 2012. [doi: 10.5772\/25756]","DOI":"10.5772\/25756"},{"key":"R10","doi-asserted-by":"crossref","unstructured":"Won-Kyung S Won\u2011Jin S Yale K et al. Usability test of KNRC self-feeding robot. Presented at: 2013 IEEE 13th International Conference on Rehabilitation Robotics (ICORR 2013); Jun 24-26, 2013; Seattle, WA, USA. [doi: 10.1109\/ICORR.2013.6650501]","DOI":"10.1109\/ICORR.2013.6650501"},{"key":"R11","unstructured":"Robot assisted feeding. Personal Robotics Lab. URL: https:\/\/robotfeeding.io [Accessed 02-01-2026]"},{"key":"R12","unstructured":"My spoon assistive robot. SECOM. 2007. URL: https:\/\/www.secom.co.jp\/products\/my-spoon [Accessed 02-01-2026]"},{"key":"R13","doi-asserted-by":"crossref","unstructured":"Lee MK Forlizzi J Kiesler S Rybski P Antanitis J Savetsila S . Personalization in HRI: a longitudinal field experiment. Presented at: Proceedings of the Seventh Annual ACM\/IEEE International Conference on Human-Robot Interaction; Mar 5-8, 2012; Boston, Massachusetts, USA. 2012.[doi: 10.1145\/2157689.2157804]","DOI":"10.1145\/2157689.2157804"},{"issue":"2","key":"R14","doi-asserted-by":"publisher","first-page":"168","DOI":"10.3109\/17483107.2011.615374","article-title":"Dusty: an assistive mobile manipulator that retrieves dropped objects for people with motor impairments","volume":"7","author":"King","journal-title":"Disabil Rehabil Assist Technol"},{"key":"R15","unstructured":"Introducing obi 3. Meet Obi. 2022. URL: https:\/\/meetobi.com\/ [Accessed 02-01-2026]"},{"key":"R16","unstructured":"IEat feeding robot. Avant Innovations. 2016. URL: https:\/\/www.avantinnovations.com.au\/products\/ieat-feeding-robot [Accessed 02-01-2026]"},{"key":"R17","unstructured":"M\u00fcller K . Bestic, the eating assistance device. MedicalExpo e-Magazine. 2022. URL: https:\/\/trends.medicalexpo.com\/ medicalexpo-e-magazine\/project-118905-423917.html [Accessed 02-01-2026]"},{"issue":"9","key":"R18","doi-asserted-by":"publisher","first-page":"2535","DOI":"10.1109\/JBHI.2020.2990529","article-title":"Homecare robotic systems for Healthcare 4.0: visions and enabling technologies","volume":"24","author":"Yang","journal-title":"IEEE J Biomed Health Inform"},{"key":"R19","unstructured":"Meal buddy. Evika. 2024. URL: https:\/\/evika.io\/product\/meal-buddy\/?utm_source=chatgpt.com#details [Accessed 02-01-2026]"},{"issue":"2","key":"R20","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1007\/s11370-025-00585-2","article-title":"Simple and effective strategies to pick up foods for a meal assistant robot integrated with an integrated spoon and chopstick mechanism","volume":"18","author":"Chen","journal-title":"Intel Serv Robotics"},{"key":"R21","doi-asserted-by":"crossref","unstructured":"Park D Kim H Hoshi Y Erickson Z Kapusta A Kemp CC . A multimodal execution monitor with anomaly classification for robot-assisted feeding. Presented at: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS); Sep 24-28, 2017; Vancouver, BC, Canada. [doi: 10.1109\/IROS.2017.8206437]","DOI":"10.1109\/IROS.2017.8206437"},{"key":"R22","doi-asserted-by":"crossref","unstructured":"Gordon EK Meng X Bhattacharjee T Barnes M Srinivasa SS . Adaptive robot-assisted feeding: an online learning framework for acquiring previously unseen food items. Presented at: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS); Oct 24, 2020 to Jan 24, 2021; Las Vegas, NV, USA. URL: https:\/\/ieeexplore.ieee.org\/xpl\/mostRecentIssue.jsp?punumber=9340668 [doi: 10.1109\/IROS45743.2020.9341359]","DOI":"10.1109\/IROS45743.2020.9341359"},{"issue":"4","key":"R23","doi-asserted-by":"publisher","DOI":"10.1177\/17298806231183571","article-title":"Assistive feeding robot for upper limb impairment\u2014testing and validation","volume":"20","author":"Mashrur","journal-title":"Int J Adv Robot Syst"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110970","article-title":"Design of an adaptive fuzzy-neural inference system\u2013based control approach for robotic manipulators","volume":"149","author":"Barhaghtalab","journal-title":"Appl Soft Comput"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.11.288","article-title":"Dynamic analysis of a 7 DOF robot using fuzzy logic for inverse kinematics problem","volume":"162","author":"Crengani\u0219","journal-title":"Procedia Comput Sci"},{"key":"R26","doi-asserted-by":"crossref","unstructured":"Esmat M Abdel-Nasser M Saif AWA . Solving inverse kinematics for 3R manipulator using artificial neural networks. Presented at: 2023 20th International Multi-Conference on Systems, Signals & Devices (SSD); Feb 20-23, 2023; Mahdia, Tunisia. [doi: 10.1109\/SSD58187.2023.10411151]","DOI":"10.1109\/SSD58187.2023.10411151"},{"issue":"2","key":"R27","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1007\/s12008-023-01513-3","article-title":"Performance evaluation of an indigenously-designed high performance dynamic feeding robotic structure using advanced additive manufacturing technology, machine learning and robot kinematics","volume":"19","author":"Parikh","journal-title":"Int J Interact Des Manuf"},{"issue":"7","key":"R28","volume":"12","author":"Serrezuela","journal-title":"ARPN J Eng Appl Sci"},{"issue":"19","key":"R29","doi-asserted-by":"publisher","first-page":"10854","DOI":"10.3390\/app131910854","article-title":"Neural network learning algorithms for high-precision position control and drift attenuation in robotic manipulators","volume":"13","author":"Mystkowski","journal-title":"Appl Sci"},{"key":"R30","author":"Gilca","journal-title":"Fiability Durability"},{"issue":"2","key":"R31","doi-asserted-by":"publisher","DOI":"10.1002\/eej.23309","article-title":"Self\u2010feeding assistive 7\u2010DOF robotic arm simulator using solving method of inverse kinematics","volume":"214","author":"Shimabukuro","journal-title":"Electr Eng Jpn"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.1155\/2012\/428060","article-title":"Virtual commissioning of an assembly cell with cooperating robots","volume":"2012","author":"Makris","journal-title":"Adv Decis Sci"},{"key":"R33","unstructured":"Simonyan K Zisserman A . Very deep convolutional networks for large-scale image recognition. Preprint posted online on Dec 23, 2014. [doi: 10.48550\/arXiv.1409.1556]"}],"container-title":["JMIR Formative Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e69877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:58:06Z","timestamp":1782842286000},"score":1,"resource":{"primary":{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e69877"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,27]]},"references-count":33,"URL":"https:\/\/doi.org\/10.2196\/69877","relation":{},"ISSN":["2561-326X"],"issn-type":[{"value":"2561-326X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,27]]},"article-number":"v10i9968e69877"}}