{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:52:48Z","timestamp":1766137968110,"version":"3.37.3"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2022,4,9]],"date-time":"2022-04-09T00:00:00Z","timestamp":1649462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,4,9]],"date-time":"2022-04-09T00:00:00Z","timestamp":1649462400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100007053","name":"Korea Institute of Energy Technology Evaluation and Planning","doi-asserted-by":"publisher","award":["20204010600220"],"award-info":[{"award-number":["20204010600220"]}],"id":[{"id":"10.13039\/501100007053","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","award":["2020R1A2C1012389"],"award-info":[{"award-number":["2020R1A2C1012389"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1007\/s11227-022-04478-4","type":"journal-article","created":{"date-parts":[[2022,4,9]],"date-time":"2022-04-09T10:02:50Z","timestamp":1649498570000},"page":"14794-14812","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing gas detection-based swarming through deep reinforcement learning"],"prefix":"10.1007","volume":"78","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2554-2749","authenticated-orcid":false,"given":"Sangmin","family":"Lee","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5118-0572","authenticated-orcid":false,"given":"Seongjoon","family":"Park","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4322-8518","authenticated-orcid":false,"given":"Hwangnam","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,4,9]]},"reference":[{"key":"4478_CR1","doi-asserted-by":"crossref","unstructured":"Abraham L, Biju S, Biju F, Jose J, Kalantri R, Rajguru S (2019) Swarm robotics in disaster management. In: 2019 International Conference on Innovative Sustainable Computational Technologies (CISCT). IEEE, pp 1\u20135","DOI":"10.1109\/CISCT46613.2019.9008139"},{"key":"4478_CR2","unstructured":"Babaeizadeh M, Frosio I, Tyree S, Clemons J, Kautz J (2016) Reinforcement learning through asynchronous advantage actor-critic on a gpu. arXiv preprintarXiv:1611.06256"},{"key":"4478_CR3","unstructured":"Beni G (1988) The concept of cellular robotic system. In: Proceedings IEEE International Symposium on Intelligent Control 1988. IEEE, pp 57\u201362"},{"key":"4478_CR4","doi-asserted-by":"crossref","unstructured":"Beni G, Wang J (1993) Swarm intelligence in cellular robotic systems. In: Robots and Biological Systems: Towards a New Bionics? Springer, pp 703\u2013712","DOI":"10.1007\/978-3-642-58069-7_38"},{"issue":"1","key":"4478_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11721-012-0075-2","volume":"7","author":"M Brambilla","year":"2013","unstructured":"Brambilla M, Ferrante E, Birattari M, Dorigo M (2013) Swarm robotics: a review from the swarm engineering perspective. Swarm Intell 7(1):1\u201341","journal-title":"Swarm Intell"},{"issue":"2\u20133","key":"4478_CR6","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/S0925-4005(01)00854-1","volume":"79","author":"A Cabot","year":"2001","unstructured":"Cabot A, Dieguez A, Romano-Rodr\u0131guez A, Morante J, Barsan N (2001) Influence of the catalytic introduction procedure on the nano-sno2 gas sensor performances: where and how stay the catalytic atoms? Sensors Actuators B: Chem 79(2\u20133):98\u2013106","journal-title":"Sensors Actuators B: Chem"},{"issue":"1","key":"4478_CR7","doi-asserted-by":"publisher","DOI":"10.1088\/2516-1091\/ab22d5","volume":"1","author":"H Ceylan","year":"2019","unstructured":"Ceylan H, Yasa IC, Kilic U, Hu W, Sitti M (2019) Translational prospects of untethered medical microrobots. Progr Biomed Eng 1(1):012002","journal-title":"Progr Biomed Eng"},{"key":"4478_CR8","doi-asserted-by":"crossref","unstructured":"Clark D (1988) The design philosophy of the darpa internet protocols. In: Symposium Proceedings on Communications Architectures and Protocols, pp 106\u2013114","DOI":"10.1145\/52325.52336"},{"key":"4478_CR9","doi-asserted-by":"crossref","unstructured":"Dayan P (2002) Reinforcement learning. Stevens\u2019 Handbook of Experimental Psychology","DOI":"10.1002\/0471214426.pas0303"},{"key":"4478_CR10","doi-asserted-by":"crossref","unstructured":"Dickerson JP, Kagan V, Subrahmanian V (2014) Using sentiment to detect bots on twitter: Are humans more opinionated than bots? In: 2014 IEEE\/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014). IEEE, pp 620\u2013627","DOI":"10.1109\/ASONAM.2014.6921650"},{"issue":"1","key":"4478_CR11","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/3477.484436","volume":"26","author":"M Dorigo","year":"1996","unstructured":"Dorigo M, Maniezzo V, Colorni A (1996) Ant system: optimization by a colony of cooperating agents. IEEE Trans Syst Man Cybern Part B (Cybern) 26(1):29\u201341","journal-title":"IEEE Trans Syst Man Cybern Part B (Cybern)"},{"issue":"1","key":"4478_CR12","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1039\/C1LC20663J","volume":"12","author":"N Dossi","year":"2012","unstructured":"Dossi N, Toniolo R, Pizzariello A, Carrilho E, Piccin E, Battiston S, Bontempelli G (2012) An electrochemical gas sensor based on paper supported room temperature ionic liquids. Lab Chip 12(1):153\u2013158","journal-title":"Lab Chip"},{"key":"4478_CR13","doi-asserted-by":"crossref","unstructured":"Eberhart R, Kennedy J (1995) A new optimizer using particle swarm theory. In: MHS\u201995. Proceedings of the Sixth International Symposium on Micro Machine and Human Science. IEEE, pp 39\u201343","DOI":"10.1109\/MHS.1995.494215"},{"key":"4478_CR14","unstructured":"Ehang egret\u2019s 1374 drones dancing over the city wall of xi\u2019an, achieving a guinness world records title. http:\/\/www.ehang.com\/news\/365.html. Accessed 24 May 2019"},{"key":"4478_CR15","unstructured":"Fan J, Wang Z, Xie Y, Yang Z (2020) A theoretical analysis of deep q-learning. In: Learning for Dynamics and Control. PMLR, pp 486\u2013489"},{"key":"4478_CR16","doi-asserted-by":"crossref","unstructured":"Gilpin K, Knaian A, Rus D (2010) Robot pebbles: one centimeter modules for programmable matter through self-disassembly. In: 2010 IEEE international Conference on Robotics and Automation. IEEE, pp 2485\u20132492","DOI":"10.1109\/ROBOT.2010.5509817"},{"key":"4478_CR17","unstructured":"Gu S, Holly E, Lillicrap T, Levine S (2016) Deep reinforcement learning for robotic manipulation. arXiv preprintarXiv:1610.00633, 1"},{"key":"4478_CR18","unstructured":"Haarnoja T, Zhou A, Abbeel P, Levine S (2018) Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning. PMLR, pp 1861\u20131870"},{"key":"4478_CR19","unstructured":"H\u00f6rtner H, Gardiner M, Haring R, Lindinger C, Berger F (2012) Spaxels, pixels in space. In: Proceedings of the International Conference on Signal Processing and Multimedia Applications and Wireless Information Networks and Systems. pp 19\u201324"},{"issue":"3","key":"4478_CR20","doi-asserted-by":"publisher","first-page":"2580","DOI":"10.3390\/s110302580","volume":"11","author":"W-J Hwang","year":"2011","unstructured":"Hwang W-J, Shin K-S, Roh J-H, Lee D-S, Choa S-H (2011) Development of micro-heaters with optimized temperature compensation design for gas sensors. Sensors 11(3):2580\u20132591","journal-title":"Sensors"},{"key":"4478_CR21","unstructured":"Intel drone light shows. https:\/\/inteldronelightshows.com\/. Accessed 11 July 2020"},{"issue":"6","key":"4478_CR22","doi-asserted-by":"publisher","first-page":"1939","DOI":"10.3390\/s18061939","volume":"18","author":"J Jung","year":"2018","unstructured":"Jung J, Yoo S, La WG, Lee DR, Bae M, Kim H (2018) Avss: airborne video surveillance system. Sensors 18(6):1939","journal-title":"Sensors"},{"key":"4478_CR23","doi-asserted-by":"crossref","unstructured":"Kennedy J (2006) Swarm intelligence. In: Handbook of Nature-Inspired and Innovative Computing. Springer, pp 187\u2013219","DOI":"10.1007\/0-387-27705-6_6"},{"key":"4478_CR24","unstructured":"Larochelle H, Bengio Y, Louradour J, Lamblin P (2009) Exploring strategies for training deep neural networks. J Mach Learn Res 10(1)"},{"key":"4478_CR25","doi-asserted-by":"crossref","unstructured":"Levin E, Pieraccini R, Eckert W (1998) Using markov decision process for learning dialogue strategies. In: Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP\u201998 (Cat. No. 98CH36181), vol\u00a01. IEEE, pp 201\u2013204","DOI":"10.1109\/ICASSP.1998.674402"},{"key":"4478_CR26","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971"},{"issue":"7","key":"4478_CR27","doi-asserted-by":"publisher","first-page":"9635","DOI":"10.3390\/s120709635","volume":"12","author":"X Liu","year":"2012","unstructured":"Liu X, Cheng S, Liu H, Hu S, Zhang D, Ning H (2012) A survey on gas sensing technology. Sensors 12(7):9635\u20139665","journal-title":"Sensors"},{"key":"4478_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.swevo.2016.12.005","volume":"33","author":"M Mavrovouniotis","year":"2017","unstructured":"Mavrovouniotis M, Li C, Yang S (2017) A survey of swarm intelligence for dynamic optimization: algorithms and applications. Swarm Evol Comput 33:1\u201317","journal-title":"Swarm Evol Comput"},{"key":"4478_CR29","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602"},{"issue":"10","key":"4478_CR30","doi-asserted-by":"publisher","first-page":"1475","DOI":"10.1007\/s12541-017-0175-4","volume":"18","author":"S Park","year":"2017","unstructured":"Park S, Oh Y, Hong D (2017) Disaster response and recovery from the perspective of robotics. Int J Precis Eng Manuf 18(10):1475\u20131482","journal-title":"Int J Precis Eng Manuf"},{"key":"4478_CR31","doi-asserted-by":"crossref","unstructured":"Park S, Kim HT, Kim H (2020) Vmcs: elaborating apf-based swarm intelligence for mission-oriented multi-uv control. IEEE Access","DOI":"10.1109\/ACCESS.2020.3044055"},{"key":"4478_CR32","unstructured":"Plappert M, Houthooft R, Dhariwal P, Sidor S, Chen RY, Chen X, Asfour T, Abbeel P, Andrychowicz M (2017) Parameter space noise for exploration. arXiv preprint arXiv:1706.01905"},{"key":"4478_CR33","doi-asserted-by":"publisher","first-page":"116044","DOI":"10.1016\/j.energy.2019.116044","volume":"188","author":"C Qin","year":"2019","unstructured":"Qin C, Yan Q, He G (2019) Integrated energy systems planning with electricity, heat and gas using particle swarm optimization. Energy 188:116044","journal-title":"Energy"},{"issue":"4","key":"4478_CR34","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/0250-6874(85)80031-7","volume":"8","author":"A Ricco","year":"1985","unstructured":"Ricco A, Martin S, Zipperian T (1985) Surface acoustic wave gas sensor based on film conductivity changes. Sensors Actuators 8(4):319\u2013333","journal-title":"Sensors Actuators"},{"key":"4478_CR35","doi-asserted-by":"crossref","unstructured":"Rubenstein M, Shen W-M (2010) Automatic scalable size selection for the shape of a distributed robotic collective. In: 2010 IEEE\/RSJ International Conference on Intelligent Robots and Systems. IEEE, pp 508\u2013513","DOI":"10.1109\/IROS.2010.5650906"},{"issue":"2","key":"4478_CR36","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/S0925-4005(01)00890-5","volume":"80","author":"G Sakai","year":"2001","unstructured":"Sakai G, Matsunaga N, Shimanoe K, Yamazoe N (2001) Theory of gas-diffusion controlled sensitivity for thin film semiconductor gas sensor. Sensors Actuators B: Chem 80(2):125\u2013131","journal-title":"Sensors Actuators B: Chem"},{"key":"4478_CR37","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347"},{"issue":"1","key":"4478_CR38","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1162\/089892999563184","volume":"11","author":"RS Sutton","year":"1999","unstructured":"Sutton RS, Barto AG (1999) Reinforcement learning. J Cogn Neurosci 11(1):126\u2013134","journal-title":"J Cogn Neurosci"},{"key":"4478_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103237","volume":"290","author":"MC Thrun","year":"2021","unstructured":"Thrun MC, Ultsch A (2021) Swarm intelligence for self-organized clustering. Artif Intell 290:103237","journal-title":"Artif Intell"},{"key":"4478_CR40","unstructured":"Tilley J (2017) Automation, robotics, and the factory of the future. McKinsey. https:\/\/www.mckinsey.com\/business-functions\/operations\/our-insights\/automation-robotics-and-the-factory-of-the-future"},{"issue":"4","key":"4478_CR41","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1109\/JSAC.2010.100505","volume":"28","author":"LFM Vieira","year":"2010","unstructured":"Vieira LFM, Lee U, Gerla M (2010) Phero-trail: a bio-inspired location service for mobile underwater sensor networks. IEEE J Selected Areas Commun 28(4):553\u2013563","journal-title":"IEEE J Selected Areas Commun"},{"issue":"3\u20134","key":"4478_CR42","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams RJ (1992) Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach learn 8(3\u20134):229\u2013256","journal-title":"Mach learn"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-022-04478-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-022-04478-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-022-04478-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T15:06:06Z","timestamp":1659971166000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-022-04478-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,9]]},"references-count":42,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["4478"],"URL":"https:\/\/doi.org\/10.1007\/s11227-022-04478-4","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2022,4,9]]},"assertion":[{"value":"17 March 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}