“全灾种、大应急”背景下消防救援场景复杂多变，消防救援人员在高温环境下长时间进行救援面临巨大的体力、心理和认知水平负担，严重威胁消防救援人员的生命安全。针对消防救援人员效能评估难以定量的问题，构建基于多源信息融合的“生理-心理”的消防救援人员效能评估模型，为保障消防救援人员生命安全与科学救援提供模型算法支撑。

本文在支持向量机-DS证据理论（SVM-DS）融合算法的基础上对算法进行优化。特别是，通过SVM后验概率转换和距离函数加权优化证据权重，根据决策规则输出最终消防救援人员效能评估结果，建立基于SVM-IDS的消防救援人员效能评估模型，并通过文献数据进行模型精度验证；随后，结合14名健康受试者（年龄24.36±1.98岁，BMI 24.11±1.32）在人工气候室（温度25℃/35℃±0.5℃，湿度60%±5%）的交叉实验设计，通过可穿戴传感器同步采集核心温度、皮肤温度、心率等参数，解析时间-参数交互作用对生理心理的复合影响并进行安全工作时间预测；最后，采用定性与定量相结合的方法，系统解析高温环境下救援人员作业效能变化规律及其敏感性影响因素。

研究结果如下：1）模型案例验证表明，SVM-IDS模型对消防救援人员生理应激指数和心理疲劳的预测准确率较原SVM-DS模型分别提升68.58%和19%，综合评估MAPE值为13.89%；2）实验结果表明，穿戴个人防护装备的受试者生理参数较对照组呈极显著差异（p<0.001），高温环境下在30分钟时受试者各工况生理指标均呈现显著变化；3）模型实验验证表明，定性表征（准确率94.10%）与定量表征（准确率73.11%）效能评估性能较原SVM-DS模型分别提升9.1%和3.63%，其中定量实验中实时自我效能感量表信度优异（α>0.99）；通过决策树分类实现动态分级，定性数据驱动下输出：高效能[0-0.456]、低效能(0.456-1]二级分类，定量数据驱动下扩展为：高效能[0-0.015]、中效能(0.015-0.943]、低效能(0.943-1]）三级分类。

本研究揭示了热应激与心理负荷的动态耦合机制，提出了基于SVM-IDS融合的救援人员效能评估模型，并通过分级阈值与敏感性主导因子的精准定位，为个体化防护装备热管理优化、智能指挥系统实时决策提供了可量化依据。研究成果为实现科学救援和提升灾害应对能力提供理论基础数据，更为“全灾种、大应急”背景下应急救援效能的科学化、精准化评估提供了理论支撑，未来可进一步拓展至多灾种耦合场景的动态风险评估与跨部门协同响应实践。

To address the evolving complexity of firefighting rescue scenarios under the “All-hazards, all-emergency” framework, firefighters operating in prolonged high-temperature environments were imposed to significant physiological, psychological, and cognitive burdens, resulting in severe risks to safety and health. To resolve the challenge of quantitatively evaluating firefighter working efficiency, a “physiological-psychological” efficiency assessment model based on multi-source information fusion was developed, providing algorithmic support for ensuring rescuer safety and enabling scientific rescue operations.

Based on the Support Vector Machine-Dempster-Shafer (SVM-DS) evidence theory fusion algorithm, optimization was performed. Specifically, posterior probabilities generated by SVM were converted into Basic Probability Assignment functions, and evidence weights were refined through distance function-based weighting. Final working efficiency evaluation results were derived using decision rules, establishing an SVM-Improved Dempster-Shafer (SVM-IDS) model, with model accuracy validated against literature data. Subsequently, a crossover experimental design involving 14 healthy participants (age: 24.36±1.98 years, BMI: 24.11±1.32) was implemented in an artificial climate chamber (temperature: 25°C/35°C±0.5°C, humidity: 60%±5%). Core temperature, skin temperature, and heart rate parameters were synchronously collected via wearable sensors to analyze time-parameter interactions and predict safe working durations under thermal stress. Finally, a hybrid qualitative-quantitative approach was adopted to systematically decode degradation patterns of working efficiency and identify sensitivity-dominant factors in high-temperature environments.

The results showed the following: 1) To validate model performance, the SVM-IDS model was demonstrated to improve prediction accuracy for physiological stress indices and psychological fatigue by 68.58% and 19%, respectively, compared to the original SVM-DS model, achieving a comprehensive mean absolute percentage error of 13.89%; 2) To assess physiological impacts, statistically significant differences (p<0.001) in parameters were observed between participants wearing personal protective equipment (PPE) and controls, with marked physiological deviations detected across all conditions at 30-minute intervals under high temperatures. 3) To refine classification accuracy, qualitative characterization (94.10%) and quantitative characterization (73.11%) exhibited improvements of 9.1% and 3.63%, respectively, over the original SVM-DS model. Real-time self-efficacy scales demonstrated exceptional reliability (α>0.99). To enable dynamic efficiency grading, decision tree classification defined two-tier qualitative levels (high [0–0.456], low (0.456–1]) and three-tier quantitative categories (high [0–0.015], medium (0.015–0.943], low (0.943–1]).

To elucidate mechanisms, the dynamic coupling between thermal stress and psychological load was revealed. An SVM-IDS-integrated assessment framework was proposed to guide practical applications, with quantifiable thresholds and sensitivity-dominant factors established to optimize personalized PPE thermal management and support intelligent command systems. To advance scientific rescue practices, theoretical foundations were provided for enhancing disaster response capabilities and achieving precision efficiency evaluation under the “All-hazards, all-emergency” paradigm. To extend future research, dynamic risk assessment in multi-hazard coupling scenarios and cross-departmental collaborative response systems are recommended.

[1] 山西消防. 2023年全国消防共接报处置各类警情213万余起, 营救和疏散人员39.5万人 [EB/OL]. 澎湃新闻, 2024-01-07.

[2] 戴越. 国家消防救援局: 上半年全国接报火灾55万起, 死亡959人 [EB/OL]. 澎湃新闻, 2023-07-18.

[3] 曾文甫. 国家消防救援局, 今年全国共接报火灾45万起、亡947人 [EB/OL]. 国家消防救援局, 2024-05-30.

[4] 陈观秋. 2023年上半年全国日均火灾超3000起 消防救援装备行业深度调研 [EB/OL]. 国家消防救援局, 2024-04-05.

[5] 战训处. 2023年已有13名消防员牺牲，均龄28岁 [EB/OL]. 消防员之家V, 2023-12-28.

[6] 曹刚. 国家消防局年度预算公布：人均工资福利等支出约19万元！人均被装购置约5138元！ [EB/OL]. 消防员之家V, 2024-04-07.

[7] POPA M, ARGESANU V, POPA A, et al. Real-time monitoring and processing of human physiological parameters [C] //2009 7th International Symposium on Intelligent Systems and Informatics. IEEE. Subotica, Serbia, 2009: 203-208.

[8] CHENG Q, JUEN J, LI Y, et al. GaitTrack: Health monitoring of body motion from spatio-temporal parameters of simple smart phones [C] //BCB'13: Proceedings of the International Conference on Bioinformatics, Computational Biology and Biomedical Informatics. Wshington DC, USA: Association for Computing Machinery, 2013: 897-906.

[9] SHEN Y, WANG T, LI C. Study on real-time wearable monitoring system for human heat and cold stresses [J]. Sheng wu yi xue Gong Cheng xue za zhi= Journal of Biomedical Engineering= Shengwu Yixue Gongchengxue Zazhi, 2013, 30(1): 80-94.

[10] ZHOU C, TU C, TIAN J, et al. A low power miniaturized monitoring system of six human physiological parameters based on wearable body sensor network [J]. Sensor Review, 2015, 35(2): 210-218.

[11] TEKGUN D, UDDIN W, LEE K-S, et al. Real-Time High-Frequency Impedance Monitoring of Human Skin Through Magnetic Coupling [J]. IEEE Sensors Journal, 2017, 17(19): 6167-6174.

[12] SIMON B-C, ONIGA S, PAP I A. Activity and health monitoring systems [J]. Carpathian Journal of Electronic and Computer Engineering, 2018, 11(1): 11-14.

[13] BORA D J, KUMAR N, DUTTA R. Implementation of wireless MEMS sensor network for detection of gait events [J]. IET Wireless Sensor Systems, 2019, 9(1): 48-52.

[14] SUN X, CHEN W. Design of a human-body health monitoring system based on Android [J]. Journal of Physics: Conference Series, 2019, 1176(2): 022026.

[15] KHONDAKAR K R, KAUSHIK A. Role of wearable sensing technology to manage long COVID [J]. Biosensors, 2022, 13(1): 62.

[16] GUO Y, TONG X, SHEN Y, et al. Wearable Optical Fiber Beat Frequency Digital Sensing System for Real-Time Non-Invasive Multiple Human Physiological Parameters Monitoring [J]. Journal of Lightwave Technology, 2023, 41(9): 2911-2920.

[17] ZHAO L, GUO X, PAN Y, et al. Triboelectric gait sensing analysis system for self‐powered IoT-based human motion monitoring [J]. InfoMat, 2024, 6(5): e12520.

[18] WANG D, CHAHL J. Simulating cardiac signals on 3D human models for photoplethysmography development [J]. Frontiers in Robotics and AI, 2024, 10(1): 1266535.

[19] GOTO G, ARIGA K, TANAKA N, et al. Clinical Significance Of Pose Estimation Methods Compared With Radiographic Parameters In Adolescent Patients With Idiopathic Scoliosis [J]. Spine Surgery and Related Research, 2024, 8(5): 485-493.

[20] SÄRESTÖNIEMI M, SINGH D, DESSAI R, et al. Realistic 3d phantoms for validation of microwave sensing in health monitoring applications [J]. Sensors, 2024, 24(6): 1975.

[21] NEKUI O D, WANG W, LIU C, et al. IoT-Based Heartbeat Rate-Monitoring Device Powered by Harvested Kinetic Energy [J]. Sensors, 2024, 24(13): 4249.

[22] ZHOU L, LIU X, ZHONG W, et al. Wearable Smart Silicone Belt for Human Motion Monitoring and Power Generation [J]. Polymers, 2024, 16(15): 2146.

[23] ZHAI Y, WANG X, NIU H, et al. Fuzzy comprehensive evaluation of human work efficiency in a high-temperature thermal-radiation environment [J]. Sustainability, 2022, 14(21): 13959.

[24] ZHENG G, LI K, BU W, et al. The effects of indoor high temperature on circadian rhythms of human work efficiency [J]. International journal of environmental research and public health, 2019, 16(5): 759.

[25] HARRINGTON C, BROWN M, WANG L, et al. Self-Reporting of Firefighter Vital Signs in Emergency Situations [J]. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 2013, 57(1): 1678-1682.

[26] STORER T W, DOLEZAL B A, ABRAZADO M L, et al. Firefighter health and fitness assessment: a call to action [J]. The Journal of Strength & Conditioning Research, 2014, 28(3): 661-671.

[27] KAPLAN G, BARELL V, LUSKY A. Subjective state of health and survival in elderly adults [J]. Journal of gerontology, 1988, 43(4): 114-120.

[28] SCHMIER J K, HALPERN M T. Patient recall and recall bias of health state and health status [J]. Expert review of pharmacoeconomics & outcomes research, 2004, 4(2): 159-163.

[29] TADJBAKHSH S. Human Security: Concepts and Implications [M]. London: Routledge, 2007: 150-156.

[30] QU Z-Y, LI Y-Y. A network security situation evaluation method based on DS evidence theory[C] //2010 The 2nd Conference on Environmental Science and Information Application Technology. Wuhan, China: IEEE, 2010: 496-499.

[31] KOOPMANS L, BERNAARDS C M, HILDEBRANDT V H, et al. Conceptual frameworks of individual work performance: A systematic review [J]. Journal of occupational and environmental medicine, 2011, 53(8): 856-866.

[32] CAMPBELL J P, WIERNIK B M. The modeling and assessment of work performance [J]. Annu Rev Organ Psychol Organ Behav, 2015, 2(1): 47-74.

[33] WU H-C, WANG M-J J. Relationship between maximum acceptable work time and physical workload [J]. Ergonomics, 2002, 45(4): 280-289.

[34] BERGH U, KANSTRUP I, EKBLOM B. Maximal oxygen uptake during exercise with various combinations of arm and leg work [J]. Journal of applied physiology, 1976, 41(2): 191-196.

[35] AFSHARI D, MORADI S, ANGALI K A, et al. Estimation of heat stress and maximum acceptable work time based on physiological and environmental response in hot-dry climate: a case study in traditional bakers [J]. The international journal of occupational and environmental medicine, 2019, 10(4): 194.

[36] WINDISCH S, SEIBERL W, SCHWIRTZ A, et al. Relationships between strength and endurance parameters and air depletion rates in professional firefighters [J]. Scientific reports, 2017, 7(1): 44590.

[37] JAGIM A R, LUEDKE J A, DOBBS W C, et al. Physiological Demands of a Self-Paced Firefighter Air-Management Course and Determination of Work Efficiency [J]. Journal of Functional Morphology and Kinesiology, 2023, 8(1): 21.

[38] RAS J, SMITH D L, SOTERIADES E S, et al. A pilot study on the relationship between cardiovascular health, musculoskeletal health, physical fitness and occupational performance in firefighters [J]. European Journal of Investigation in Health, Psychology and Education, 2022, 12(11): 1703-1718.

[39] NAZARI G, MACDERMID J C, SINDEN K E, et al. The relationship between physical fitness and simulated firefighting task performance [J]. Rehabilitation research and practice, 2018, 2018(1): 3234176.

[40] SANTIAGO D, CORDEIRO A, ALMEIDA G. Integration of remote interfaces for industrial automation applications[C] //; 2021 International Young Engineers Forum (YEF-ECE). Caparica / Lisboa, Portugal: IEEE, 2021: 69-74.

[41] TIAN Z, QIU Y, MA W, et al. On resource pooling technology of highly integrated onboard equipment[C]//Seventh Asia Pacific Conference on Optics Manufacture and 2021 International Forum of Young Scientists on Advanced Optical Manufacturing (APCOM and YSAOM 2021). SPIE, 2022, 12166: 1288-1296.

[42] BUZZARD C, DRAGER J, SALTZBERG B. Transaction networks, telephones, and terminals: Communication network and equipment [J]. Bell System Technical Journal, 1978, 57(10): 3349-3369.

[43] KANG Z, YING Z, XU S, et al. Research on intelligent troubleshooting of power communication equipment based on RPA technology[C]//International Conference on Green Communication, Network, and Internet of Things (GCNIoT 2021). SPIE, 2021, 12085: 272-277.

[44] MO L, WEI G. Load analysis of roof photovoltaic arrays and evaluation of structural bearing capacity[C]//2nd International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2022). SPIE, 2022, 12244: 500-503.

[45] ARTUR R, VASYL P, DMYTRO R. Optimization of fire station locations to increase the efficiency of firefighting in natural ecosystems [J]. Journal of Environmental Research, Engineering and Management, 2022, 78(1): 97-104.

[46] LIU P, YU H, CANG S, et al. Robot-assisted smart firefighting and interdisciplinary perspectives [C] //2016 22nd international conference on automation and computing (ICAC). Colchester, UK: IEEE, 2016: 395-401.

[47] SCHNEIDER F E, WILDERMUTH D. Using robots for firefighters and first responders: Scenario specification and exemplary system description [C] //2017 18th International Carpathian Control Conference (ICCC). 2017: IEEE, 2017: 216-221.

[48] MORRIS C E, CHANDER H. The impact of firefighter physical fitness on job performance: A review of the factors that influence fire suppression safety and success [J]. Safety, 2018, 4(4): 60.

[49] CHOU J-S, CHENG M-Y, HSIEH Y-M, et al. Optimal path planning in real time for dynamic building fire rescue operations using wireless sensors and visual guidance [J]. Automation in construction, 2019, 99(3): 1-17.

[50] ZHANG C, HONG W-H, BAE Y-H. Fire safety knowledge of firefighting equipment among local and foreign university students [J]. International journal of environmental research and public health, 2022, 19(19): 12239.

[51] 张志. 多传感器信息融合及其应用研究 [D]. 西安: 西安电子科技大学, 2017.

[52] WALTZ E. Multisensor Data Fusion [M]. Boston: Artech House, 1990:8.

[53] HALL D L, MCMULLEN S A. Mathematical techniques in multisensor data fusion [M]. Norwood, MA,United States: Artech House, 2004: 20.

[54] BAR-SHALOM Y, BLACKMAN S S, FITZGERALD R J. Dimensionless score function for multiple hypothesis tracking [J]. IEEE Transactions on Aerospace and Electronic Systems, 2007, 43(1): 392-400.

[55] MAHLER R. Statistical multisource-multitarget information fusion [M]. United States: Artech House, 2007:60.

[56] KHALEGHI B, KHAMIS A, KARRAY F O, et al. Multisensor data fusion: A review of the state-of-the-art [J]. Information fusion, 2013, 14(1): 28-44.

[57] ZHANG P, LI T, YUAN Z, et al. A data-level fusion model for unsupervised attribute selection in multi-source homogeneous data [J]. Information Fusion, 2022, 80(4): 87-103.

[58] PENG X, WANG L, WANG X, et al. Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice [J]. Computer Vision and Image Understanding, 2016, 150(9): 109-125.

[59] MANJÓN J V, COUPÉ P. volBrain: an online MRI brain volumetry system [J]. Frontiers in neuroinformatics, 2016, 10(7): 30.

[60] RAMACHANDRAM D, TAYLOR G W. Deep multimodal learning: A survey on recent advances and trends [J]. IEEE signal processing magazine, 2017, 34(6): 96-108.

[61] GRAVINA R, ALINIA P, GHASEMZADEH H, et al. Multi-sensor fusion in body sensor networks: State-of-the-art and research challenges [J]. Information Fusion, 2017, 35(3): 68-80.

[62] ZADEH A B, LIANG P P, PORIA S, et al. Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph[C] //Iryna Gurevych, Yusuke Miyao. 56th Annual Meeting of the Association for Computational Linguistics. Melbourne, Australia: Association for Computational Linguistics, 2018: 2236-2246.

[63] MENG T, JING X, YAN Z, et al. A survey on machine learning for data fusion [J]. Information Fusion, 2020, 57(3): 115-129.

[64] HUANG S-C, PAREEK A, SEYYEDI S, et al. Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines [J]. NPJ digital medicine, 2020, 3(1): 136.

[65] SHAFER G. Dempster-shafer theory [J]. Encyclopedia of artificial intelligence, 1992, 1(1): 330-331.

[66] DEMPSTER A P. Upper and lower probabilities induced by a multivalued mapping [M]. Classic works of the Dempster-Shafer theory of belief functions. Springer. 2008: 57-72.

[67] YANG J-B, SINGH M G. An evidential reasoning approach for multiple-attribute decision making with uncertainty [J]. IEEE Transactions on systems, Man, and Cybernetics, 1994, 24(1): 1-18.

[68] XU H, HSIA Y-T, SMETS P. Transferable belief model for decision making in the valuation-based systems [J]. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 1996, 26(6): 698-707.

[69] YAGER R R. On the Dempster-Shafer framework and new combination rules [J]. Information sciences, 1987, 41(2): 93-137.

[70] 孙全, 叶秀清, 顾伟康. 一种新的基于证据理论的合成公式 [J]. 电子学报, 2000, 28(8): 117.

[71] 邓勇, 施文康, 朱振福. 一种有效处理冲突证据的组合方法 [J]. 红外与毫米波学报, 2004, 23(1): 27-32.

[72] MURPHY C K. Combining belief functions when evidence conflicts [J]. Decision support systems, 2000, 29(1): 1-9.

[73] BASIR O, YUAN X. Engine fault diagnosis based on multi-sensor information fusion using Dempster–Shafer evidence theory [J]. Information fusion, 2007, 8(4): 379-386.

[74] LI X, SEIGNEZ E, LAMBERT A, et al. Real-time driver drowsiness estimation by multi-source information fusion with Dempster–Shafer theory [J]. Transactions of the Institute of Measurement and Control, 2014, 36(7): 906-915.

[75] 张钰曼, 吴海淼, 侯红娟. 基于 DS 证据理论和模糊理论的工业机器人健康状态评估 [J]. 机床与液压, 2022, 50(8): 198-203.

[76] CHE X, MI J, CHEN D. Information fusion and numerical characterization of a multi-source information system [J]. Knowledge-Based Systems, 2018, 145(4): 121-133.

[77] 周志华. 《机器学习》 [J]. 中国民商, 2016, 21(3): 93.

[78] BOTTOU L. Large-scale machine learning with stochastic gradient descent[C] //Proceedings of COMPSTAT'2010: 19th International Conference on Computational StatisticsParis France. August 22-27, 2010 Keynote: Springer, 2010: 177-186.

[79] BOSER B E, GUYON I M, VAPNIK V N. A training algorithm for optimal margin classifiers[C] // Association for Computing Machinery. Proceedings of the fifth annual workshop on Computational learning theory. Pittsburgh, Pennsylvania, USA: Association for Computing Machinery, 1992: 144-152.

[80] ZHANG M, LI H, TIAN S. Visual analysis of machine learning methods in the field of ergonomics—Based on Cite Space V [J]. International Journal of Industrial Ergonomics, 2023, 93(1): 103395.

[81] CHAI X, LEE B-G, PIKE M, et al. Pre-Impact Firefighter Fall Detection Using Machine Learning on the Edge [J]. IEEE Sensors Journal, 2023, 23(13): 14997-5009.

[82] CHEN W, ZHANG L. Resilience assessment of regional areas against earthquakes using multi-source information fusion [J]. Reliability Engineering & System Safety, 2021, 215(11): 107833.

[83] ZHANG X, MAHADEVAN S, LAU N, et al. Multi-source information fusion to assess control room operator performance [J]. Reliability Engineering & System Safety, 2020, 194(2): 106287.

[84] CHANG Z, LIAO X, LIU Y, et al. Research of decision fusion for multi-source remote-sensing satellite information based on SVMs and DS evidence theory[C] //The Fourth International Workshop on Advanced Computational Intelligence. Wuhan, China: IEEE, 2011: 416-420.

[85] 李小珍, 蒋银芬, 刘励军, 等. 重度烧伤患者核心温度的监测 [J]. 江苏医药, 2016, 42(4): 460-461.

[86] AGOSTINELLI P J, LINDER B A, FRICK K A, et al. Validity of heart rate derived core temperature estimation during simulated firefighting tasks [J]. Scientific Reports, 2023, 13(1): 22503.

[87] 全军热射病防治专家组. 军事训练防治中暑/热射病降温方法专家共识 [J]. 解放军医学杂志, 2023, 48(8): 871-878.

[88] 杨杰, 王倩, 贺治超, 等. 基于环境与生理参数的应急救援人员作业效能评估 [J]. 消防科学与技术, 2024, 43(12): 1745-1752.

[89] 全刘辉, 李玉香, 澹台梦阳, 等. 基于无线通信的视觉识别自动救生系统的设计 [J]. 电脑知识与技术, 2024, 20(9): 96-98.

[90] LI Y, BAI K, WANG H, et al. Research on improved FAWT signal denoising method in evaluation of firefighter training efficacy based on sEMG [J]. Biomedical Signal Processing and Control, 2022, 72(4): 103336.

[91] 杨三军, 王昆, 高笛, 等. 应急救援人群高强度功能训练的应用效果与作用机制研究进展 [J]. 体育科学, 2023, 43(3): 58-68.

[92] LIČINA V F, CHEUNG T, ZHANG H, et al. Development of the ASHRAE global thermal comfort database II [J]. Building and Environment, 2018, 142(9): 502-512.

[93] 张丹, 徐新洁, 刘希东, 等. 某轻卡乘员舱热舒适性分析 [J]. 汽车工程学报, 2020, 10(6): 448-457.

[94] JUNG D, KIM H, AN J, et al. Thermoregulatory responses of young and elderly adults under temperature ramps [J]. Building and Environment, 2023, 244(10): 110760.

[95] 章明超, 邹佳庆, 周健, 等. 汽车驾驶员热感觉预测及其影响因素分析 [J]. 建筑热能通风空调, 2022, 41(8): 37-41.

[96] DEO R C, WEN X, QI F. A wavelet-coupled support vector machine model for forecasting global incident solar radiation using limited meteorological dataset [J]. Applied Energy, 2016, 168(4): 568-593.

[97] CHEN J, LIU Y. Locally linear embedding: a survey [J]. Artificial Intelligence Review, 2011, 36(1): 29-48.

[98] RAITOHARJU J, KIRANYAZ S, GABBOUJ M. Feature synthesis for image classification and retrieval via one-against-all perceptrons [J]. Neural Computing and Applications, 2018, 29(4): 943-957.

[99] WANG Z, WANG X, TONG Y, et al. Impact of structure and flow-path on in situ synthesis of AlN: Dynamic microstructural evolution of Al-AlN-Si materials [J]. Sci China Mater, 2018, 61(1): 948-960.

[100] JOUSSELME A-L, GRENIER D, BOSSé É. A new distance between two bodies of evidence [J]. Information fusion, 2001, 2(2): 91-101.

[101] 李志伟, 曹乐. 基于SVM-DS证据理论融合决策的故障诊断方法 [J]. 噪声与振动控制, 2023, 43(05): 148-153.

[102] PLATT J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods [J]. Advances in large margin classifiers, 1999, 10(3): 61-74.

[103] CHINEVERE T D, CADARETTE B S, GOODMAN D A, et al. Efficacy of body ventilation system for reducing strain in warm and hot climates [J]. European journal of applied physiology, 2008, 103(6): 307-314.

[104] BAFNA T. Replication Data for: Smooth-pursuit eye movement to detect mental fatigue [DB]. 2021,

[105] LARSEN B, SNOW R, VINCENT G, et al. Multiple days of heat exposure on firefighters’ work performance and physiology [J]. PloS one, 2015, 10(9): e0136413.

[106] METZ C E. Basic principles of ROC analysis [J]. Seminars in nuclear medicine, 1978 8(4): 283-298.

[107] BAFNA T, BæKGAARD P, HANSEN J P. Mental fatigue prediction during eye-typing [J]. Plos one, 2021, 16(2): e0246739.

[108] HINTZE J L, NELSON R D. Violin plots: a box plot-density trace synergism [J]. The American Statistician, 1998, 52(2): 181-184.

[109] 关爱科, 杨杰. 基于 SVM-DS 融合算法的消防员效能评估方法[J]. 消防科学与技术, 2024, 43(12): 1772-1777.

[110] CVIRN M, SMITH B, JAY S, et al. The impact of temperature on the sleep characteristics of volunteer firefighters during a wildland fireground tour simulation [J]. The Time of Your Life Australasian Chronobiology Society, Melbourne, Australia, 2015, 1(1): 18-24.

[111] LARSEN B, SNOW R, AISBETT B. Effect of heat on firefighters' work performance and physiology [J]. Journal of thermal biology, 2015, 53(7): 1-8.

[112] VINCENT G E, AISBETT B, LARSEN B, et al. The impact of heat exposure and sleep restriction on firefighters’ work performance and physiology during simulated wildfire suppression [J]. International journal of environmental research and public health, 2017, 14(2): 180.

[113] Li J , Cheng J H , Shi J Y ,et al.Brief Introduction of Back Propagation (BP) Neural Network Algorithm and Its Improvement[C]//Springer Berlin Heidelberg.Springer Berlin Heidelberg, 2012: 553-558.

[114] CHICCO D, WARRENS M J, JURMAN G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation [J]. Peerj computer science, 2021, 7(7): e623.

[115] HEMMATJO R, MOTAMEDZADE M, ALIABADI M, et al. The effect of practical cooling strategies on physiological response and cognitive function during simulated firefighting tasks [J]. Health promotion perspectives, 2017, 7(2): 66.

[116] ABRARD S, BERTRAND M, DE VALENCE T, et al. Physiological, cognitive and neuromuscular effects of heat exposure on firefighters after a live training scenario [J]. International Journal of Occupational Safety and Ergonomics, 2021, 1(1): 185-193.

[117] HUNTER A L, SHAH A S, LANGRISH J P, et al. Fire simulation and cardiovascular health in firefighters [J]. Circulation, 2017, 135(14): 1284-1295.

[118] ENSARI I, MOTL R W, KLAREN R E, et al. Firefighter exercise protocols conducted in an environmental chamber: developing a laboratory-based simulated firefighting protocol [J]. Ergonomics, 2017, 60(5): 657-668.

[119] PHILLIPS M, NETTO K, PAYNE W, et al. Frequency, intensity and duration of physical tasks performed by Australian rural firefighters during bushfire suppression[C] //Australasian Fire Authorities/Bushfire Co-Operative Research Center Annual Conference: Bushfire Cooperative Research Centre, 2011: 205-213.

[120] TANAKA H, MONAHAN K D, SEALS D R. Age-predicted maximal heart rate revisited [J]. Journal of the american college of cardiology, 2001, 37(1): 153-156.

[121] YANG J, ZHANG Y, HUANG Y, et al. Effects of liquid cooling garment on physiological and psychological strain of firefighter in hot and warm environments [J]. Journal of Thermal Biology, 2023, 112(2): 103487.

[122] STEVENS C J, MAUGER A R, HASSMèN P, et al. Endurance performance is influenced by perceptions of pain and temperature: theory, applications and safety considerations [J]. Sports medicine, 2018, 48(3): 525-537.

[123] XU J, CHEN G, WANG X, et al. Novel design of a personal liquid cooling vest for improving the thermal comfort of pilots working in hot environments [J]. Indoor Air, 2023, 33(1): 6666182.

[124] 蔡毅, 邢岩, 胡丹. 敏感性分析综述 [J]. 北京师范大学学报(自然科学版), 2008, 44(1): 9-16.