A real-time hypothermia and hyperthermia monitoring system with a simple body sensor based on a Convolutional Neural Network (CNN) is presented. The sensor is produced with 3D-printed thermochromic material. Due to the color change feature of thermochromic materials with temperature, 3D-printed thermochromic Polylactic Acid (PLA) material was used to monitor temperature changes visually. In this paper, we have used the transfer learning technique and fine-tuned the AlexNet CNN. Thirty images for each temperature class between 28–44°C and 510 image data were used in the algorithm. We used 80% and 20% of the data for training and validation. We achieved 96.1% accuracy of validation with a fine-tuned AlexNet CNN. The material’s characteristics suggest that it could be employed in delicate temperature sensing and monitoring applications, particularly for hypothermia and hyperthermia.
DiasDPaulo Silva CunhaJ.Wearable health devices—vital sign monitoring, systems and technologies. Sensors (Basel)2018; 18: 2414.
2.
RajbhandaryPLNallathambiG.Feasibility of continuous monitoring of core body temperature using chest-worn patch sensor. Annu Int Conf IEEE Eng Med Biol Soc2020; 2020: 4652–4655.
3.
Del BeneVE.Clinical methods: the history, physical, and laboratory examinations. In: WalkerHKHallWDHurstJW (eds) Clinical methods: the history, physical, and laboratory examinations. Boston: Butterworths, pp. 990–993. http://www.ncbi.nlm.nih.gov/books/NBK331/ (1990, accessed 18 October 2023).
4.
HooperVDAndrewsJO.Accuracy of noninvasive core temperature measurement in acutely ill adults: the state of the science. Biol Res Nurs2006; 8: 24–34.
5.
CampbellI.Body temperature and its regulation. Anaesth Intensive Care Med2008; 9: 259–263.
6.
SuYMaCChenJ, et al. Printable, highly sensitive flexible temperature sensors for human body temperature monitoring: a review. Nanoscale Res Lett2020; 15: 200.
7.
LiuYLiHFengQ, et al. A three-dimensional-printed recyclable, flexible, and wearable device for visualized UV, temperature, and sweat pH sensing. ACS Omega2022; 7: 9834–9845.
8.
ChoiJBandodkarAJReederJT, et al. Soft, skin-integrated multifunctional microfluidic systems for accurate colorimetric analysis of sweat biomarkers and temperature. ACS Sens2019; 4: 379–388.
9.
EddahchouriYPeelenRVKoenemanM, et al. Effect of continuous wireless vital sign monitoring on unplanned ICU admissions and rapid response team calls: a before-and-after study. Br J Anaesth2022; 128: 857–863.
10.
YingzheLChaoranLHaiyangZ, et al. Integrated wearable smart sensor system for real-time multi-parameter respiration health monitoring. Cell Rep Phys Sci2023; 4: 101191.
11.
LivanosN-AHammalSNikolopoulosCD, et al. Design and Interdisciplinary simulations of a hand-held device for internal-body temperature sensing using microwave radiometry. IEEE Sens J2018; 18: 2421–2433.
12.
ChenWDolsSOetomoSB, et al. Monitoring body temperature of newborn infants at neonatal intensive care units using wearable sensors. In: Proceedings of the fifth international conference on body area networks, New York, NY, pp.188–194. Association for Computing Machinery.
13.
SongCZengPWangZ, et al. Wearable continuous body temperature measurement using multiple artificial neural networks. IEEE Trans Ind Inf2018; 14: 4395–4406.
14.
LinJ-WLuM-HLinY-H.A thermal camera based continuous body temperature measurement system. In: 2019 IEEE/CVF international conference on computer vision workshop (ICCVW), Seoul, Korea (South), 2019, pp.1681–1687.
15.
SunGMatsuiTWataiY, et al. Vital-SCOPE: design and evaluation of a smart vital sign monitor for simultaneous measurement of pulse rate, respiratory rate, and body temperature for patient monitoring. J Sens2018; 2018: 1–7.
16.
WangWWuCZhuK, et al. Real-time personal fever alert monitoring by wearable detector based on thermoresponsive hydrogel. ACS Appl Polym Mater2021; 3: 1747–1755.
17.
LiRSmithATadinadaH, et al. Heatguard: an ultra-low-cost three-dimensional-printed sensor for skin temperature alert and reporting system. Proc IMechE, Part H: J Engineering in Medicine2019; 233: 525–534.
18.
HintonGEOsinderoSTehY-W.A fast learning algorithm for deep belief nets. Neural Comput2006; 18: 1527–1554.
19.
SaracogluÖGAlturalH. Color regeneration from reflective color sensor using an artificial intelligent technique. Sensors2010; 10: 8363–8374.
20.
SinghalAShuklaRKankarP, et al. Comparing the capabilities of transfer learning models to detect skin lesion in humans. Proc IMechE, Part H: J Engineering in Medicine2020; 234: 1083–1093.
ZhangYLianJFanM, et al. Deep indicator for fine-grained classification of banana’s ripening stages. EURASIP J Image Video Process2018; 2018: 46.
26.
CoppolaBCappettiNDi MaioL, et al. 3D printing of PLA/clay nanocomposites: influence of printing temperature on printed samples properties. Materials2018; 11: 1947.
27.
BahlSNagarHSinghI, et al. Smart materials types, properties and applications: a review. Mater Today Proc2020; 28: 1302–1306.
28.
SadohAHossainSRavindraNM.Thermochromic polymeric films for applications in active intelligent packaging—an overview. Micromachines2021; 12: 1193.
29.
HakamiASrinivasanSSBiswasPK, et al. Review on thermochromic materials: development, characterization, and applications. J Coat Technol Res2022; 19: 377–402.
HosnyKMKassemMAFoaudMM.Classification of skin lesions using transfer learning and augmentation with Alex-net. PLoS One2019; 14: e0217293.
32.
AlmisrebAAJamilNDinNM.Utilizing AlexNet deep transfer learning for ear recognition. In: 2018 fourth international conference on information retrieval and knowledge management (CAMP), Kota Kinabalu, Malaysia, 2018, pp.1–5.
33.
JiangXHuBChandra SatapathyS, et al. Fingerspelling identification for Chinese sign language via AlexNet-based transfer learning and adam optimizer. Sci Program2020; 2020: e3291426.
34.
ArunnehruJChamundeeswariGBharathiSP.Human action recognition using 3D convolutional neural networks with 3D motion cuboids in surveillance videos. Procedia Comput Sci2018; 133: 471–477.
35.
NairVHintonGE.Rectified linear units improve restricted boltzmann machines. Omnipress, Madison, WI, 2010, pp. 807–814.
36.
KrizhevskyASutskeverIHintonGE.ImageNet classification with deepconvolutional neural networks. ImageNet classification with deep convolutional neural networks. Communications of the ACM60, 2012, pp. 84–90.
37.
KingmaDPBaJ.Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, San Diego, 2014, pp.1–15.
38.
Da Silva CotrimWMinimVPRFelixLB, et al. Short convolutional neural networks applied to the recognition of the browning stages of bread crust. J Food Eng2020; 277: 109916.
