深度强化学习及其在军事领域中的应用综述

doi:10.12305/j.issn.1001-506X.2024.04.18

Abstract

Abstract:

With the emergence of a series of new technologies, such as big data, cloud computing, internet of things, artificial intelligence technology has made breakthrough progress continuously. As one of the latest achievements in artificial intelligence field, deep reinforcement learning (DRL) technology is being gradually introduced into the military field, which promotes the military field's informationization and intelligent. In the future war operation mode and military development and construction, networking, informationization, intelligence, and unmanned development will become an irreversible trend. Therefore, on the basis of reviewing the basic principles and main algorithms of DRL, this paper systematically combs and summarizes the current application status of DRL in weapons and equipment, network security, unmanned aerial vehicle (UAV) formation, intelligent decision-making and game, etc. Finally, in view of a series of problems and challenges facing the actual application of DRL technology in the military field, this paper provides some ideas for further research in the future.

Key words: deep reinforcement learning (DRL), military application, intelligent decision-making, develo-pment trend

CLC Number:

N945

Mengyu ZHANG, Yajie DOU, Ziyi CHEN, Jiang JIANG, Kewei YANG, Bingfeng GE. Review of deep reinforcement learning and its applications in military field[J]. Systems Engineering and Electronics, 2024, 46(4): 1297-1308.

Figures/Tables 7

Fig.1

Fig.2

Table 1

Table 2

Fig.3

Table 3

Fig.4

References 78

1	郭若冰, 司光亚, 贺筱媛. 迎接智能化时代军事指挥面临的新挑战——全军"战争复杂性与信息化战争模拟"研讨会观点综述[J]. 中国军事科学, 2016, (5): 149- 156.
	GUO R B , SI G Y , HE X Y . Meet new challenges to military command in the intelligence era-asummary of the PLA symposium on "the complexity of war and the simulation of information-izedwarfare"[J]. China Military Science, 2016, (5): 149- 156.
2	刘志刚. 眺望下一场变革——关于后信息时代军队建设发展的断想[EB/OL]. [2022-03-07]. http://www.81.cn/yw/2021-09/07/content_10086965.html.
	LIU Z G. Overlooking the next revolution-thoughts on the development of military construction in the post information age[EB/OL]. [2022-03-07]. http://www.81.cn/yw/2021-09/07/content_10086965.html.
3	吴明曦. 智能化战争时代正在加速到来[J]. 学术前沿, 2021, (10): 35- 55.
	WU M X . The era of intelligent war is coming rapidly[J]. Frontiers, 2021, (10): 35- 55.
4	LIU S F , WANG Y , YANG X , et al. Deep learning in medical ultrasound analysis: a review[J]. Engineering, 2019, 5 (2): 261- 275. doi: 10.1016/j.eng.2018.11.020
5	POLYDOROS A S , NALPANTIDIS L . Survey of model-based reinforcement learning: applications on robotics[J]. Journal of Intelligent & Robotic Systems, 2017, 86 (2): 153- 173.
6	LI Y X. Deep reinforcement learning: an overview[EB/OL]. [2022-03-20]. https://arXiv.org/abs/1701.07274v5.
7	FRANÇOIS-LAVET V , HENDERSON P , ISLAM R , et al. An introduction to deep reinforcement learning[J]. Foundations and Trends in Machine Learning, 2018, 11 (3/4): 219- 354.
8	AZAR A T , KOUBAA A , MOHAMED N , et al. Drone deep reinforcement learning: a review[J]. Electronics, 2021, 10 (9): 999- 1029. doi: 10.3390/electronics10090999
9	LUONG N C , HOANG D T , GONG S , et al. Applications of deep reinforcement learning in communications and networking: a survey[J]. IEEE Communications Surveys & Tutorials, 2019, 21 (4): 3133- 3174.
10	孔松涛, 刘池池, 史勇, 等. 深度强化学习在智能制造中的应用展望综述[J]. 计算机工程与应用, 2021, 57 (2): 49- 59.
	KONG S T , LIU C C , SHI Y , et al. Review of application prospect of deep reinforcement learning in intelligent manufacturing[J]. Computer Engineering and Applications, 2021, 57 (2): 49- 59.
11	ABIODUN O I , JANTAN A , OMOLARA A E , et al. State-of-the-art in artificial neural network applications: a survey[J]. Heliyon, 2018, 4 (11): e00938. doi: 10.1016/j.heliyon.2018.e00938
12	LECUN. Y , BENGIO Y , HINTON G . Deep learning[J]. Nature, 2015, 521 (7553): 436- 444. doi: 10.1038/nature14539
13	KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[C]//Proc. of the International Conference on Neural Information Processing Systems, 2012: 1097-1105.
14	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//Proc. of the International Conference on Learning Representations, 2015.
15	LIN M, CHEN Q, YAN S C. Network in network[C]//Proc. of the International Conference on Learning Representations, 2014.
16	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
17	SHERSTINSKY A . Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network[J]. Physica D: Nonlinear Phenomena, 2020, 404, 132306. doi: 10.1016/j.physd.2019.132306
18	HOCHREITER S , SCHMIDHUBER J . Long short-term memory[J]. Neural Computation, 1997, 9 (8): 1735- 1780. doi: 10.1162/neco.1997.9.8.1735
19	GREFF K , SRIVASTAVA R K , KOUTNÍK J , et al. LSTM: a search space odyssey[J]. IEEE Trans.on Neural Networks and Learning Systems, 2016, 28 (10): 2222- 2232.
20	SUTTON R S , BARTO A G . Reinforcement learning: an introduction[M]. Cambridge: MIT Press, 2018.
21	HA D, SCHMIDHUBER J. World models[EB/OL]. [2022-03-09]. https://arxiv.53yu.com/abs/1803.10122.
22	RACANIERE S, WEBER T, REICHERT D, et al. Imagination-augmented agents for deep reinforcement learning[C]//Proc. of the 30th Conference on Neural Information Processing Systems, 2017: 5690-5701.
23	CHEN J X . The evolution of computing: AlphaGo[J]. Computing in Science & Engineering, 2016, 18 (4): 4- 7.
24	TIAN Y D, MA J, GONG Q C, et al. ELF OpenGo: an analysis and open reimplementation of AlphaZero[C]//Proc. of the International Conference on Machine Learning, 2019: 6244-6253.
25	SINGH S , JAAKKOLA T , LITTMAN M L , et al. Convergence results for single-step on-policy reinforcement-learning algorithms[J]. Machine Learning, 2000, 38 (3): 287- 308. doi: 10.1023/A:1007678930559
26	WATKINS C J C H , DAYAN P . Q-learning[J]. Machine Learning, 1992, 8 (3): 279- 292.
27	PANOV A I , YAKOVLEV K S , SUVOROV R . Grid path planning with deep reinforcement learning: preliminary results[J]. Procedia Computer Science, 2018, 123, 347- 353. doi: 10.1016/j.procs.2018.01.054
28	熊鑫立, 杨林, 李克超. 基于马尔可夫决策过程的动态目标防御策略优化方法[J]. 武汉大学学报(理学版), 2020, 66 (2): 141- 148.
	XIONG X L , YANG L , LI K C . A strategy optimization model of moving target defense based on Markov[J]. Journal of Wuhan University (Natural Science Edition), 2020, 66 (2): 141- 148.
29	FORTUNATO M, AZAR M G, PIOT B, et al. Noisy networks for exploration[C]//Proc. of the 6th International Conference on Learning Representations, 2018.
30	SUTTON R S , MCALLESTER D , SINGH S , et al. Policy gradient methods for reinforcement learning with function approximation[J]. Advances in Neural Information Processing Systems, 2000, 12, 1057- 1063.
31	MNIH V, KAVUKCUOGLU K, SILVER D, et al. Playing atari with deep reinforcement learning[EB/OL]. [2022-03-20]. https://arXiv.org/abs/1312.5602v1.
32	MNIH V , KAVUKCUOGLU K , SILVER D , et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518 (7540): 529- 533. doi: 10.1038/nature14236
33	VAN H H, GUEZ A, SILVER D. Deep reinforcement learning with double Q-learning[C]//Proc. of the AAAI Conference on Artificial Intelligence, 2016.
34	WANG Z, SCHAUL T, HESSEL M, et al. Dueling network architectures for deep reinforcement learning[C]//Proc. of the International Conference on Machine Learning, 2016: 1995-2003.
35	HUANG Y, WEI G L, WANG Y X. VD D3QN: the variant of double deep Q-learning network with dueling architecture[C]//Proc. of the 37th Chinese Control Conference, 2018: 9130-9135.
36	HESSEL M, MODAYIL J, VAN H H, et al. Rainbow: combining improvements in deep reinforcement learning[C]//Proc. of the 32nd AAAI Conference on Artificial Intelligence, 2018: 3215-3222.
37	LILLICRAP T P, HUNT J J, PRITZEL A, et al. Continuous control with deep reinforcement learning[C]//Proc. of the International Conference on Learning Representations, 2016.
38	HAARNOJA T, ZHOU A, ABBEEL P, et al. Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor[C]//Proc. of the International Conference on Machine Learning, 2018: 1861-1870.
39	SCHULMAN J, LEVINE S, ABBEEL P, et al. Trust region policy optimization[C]//Proc. of the International Conference on Machine Learning, 2015: 1889-1897.
40	SCHULMAN J, WOLSKI F, DHARIWAL P, et al. Proximal policy optimization algorithms[EB/OL]. [2023-03-20]. https://arXiv.org/abs/1707.06347.
41	HEESS N, TB D, SRIRAM S, et al. Emergence of locomotion behaviours in rich environments[EB/OL]. [2023-03-20]. https://arXiv.org/abs/1707.02286.
42	MNIH V, BADIA A P, MIRZA M, et al. Asynchronous methods for deep reinforcement learning[C]//Proc. of the International Conference on Machine Learning, 2016: 1928-1937.
43	SCHULMAN J, WOLSKI F, DHARIWAL P, et al. Proximal policy optimization algorithms[EB/OL]. [2023-03-20]. https://arXiv.org/abs/1707.06347.
44	张骁雄, 葛冰峰, 姜江, 等. 面向能力需求的武器装备组合规划模型与算法[J]. 国防科技大学学报, 2017, 39 (1): 102- 108.
	ZHANG X X , GE B F , JIANG J , et al. Capability requirements oriented weapons portfolio planning model and algorithm[J]. Journal of National University of Defense Technology, 2017, 39 (1): 102- 108.
45	LI J C , GE B F , JIANG J , et al. High-end weapon equipment portfolio selection based on a heterogeneousnetwork model[J]. Journal of Global Optimization, 2020, 78 (4): 743- 761. doi: 10.1007/s10898-018-0687-1
46	豆亚杰. 武器系统组合选择问题与决策方法研究[D]. 长沙: 国防科技大学, 2016.
	DOU Y J. Research on weapon system portfolio selection problems and decision methods[D]. Changsha: National University of Defense Technology, 2016.
47	孙建彬, 邢立宇. 基于遗传算法的武器系统组合优化方法[J]. 价值工程, 2011, 30 (29): 9- 10.
	SUN J B , XING L Y . The method of weapons system combinatorial optimization based on genetic algorithm[J]. Value Engineering, 2011, 30 (29): 9- 10.
48	杜波. 基于代理模型的武器装备体系优化方法研究[D]. 长沙: 国防科技大学, 2010.
	DU B. Research on optimization methods of weapon equipment system of systems based on surrogate model[D]. Changsha: National University of Defense Technology, 2010.
49	张骁雄, 丁松, 李明浩, 等. 强化学习在多阶段装备组合规划问题中的应用[J]. 国防科技大学学报, 2021, 43 (5): 127- 136.
	ZHANG X X , DING S , LI M H , et al. Application of reinforcement learning in multi-period weapon portfolio planning problems[J]. Journal of National University of Defense Technology, 2021, 43 (5): 127- 136.
50	文东日, 陈小虎, 李文, 等. 基于深度强化学习的装备组合运用方法[J]. 指挥控制与仿真, 2021, 43 (6): 135- 140.
	WEN D R , CHEN X H , LI W , et al. Method of equipment combination application based on deep reinforcement learning[J]. Command Control & Simulation, 2021, 43 (6): 135- 140.
51	黄亭飞, 程光权, 黄魁华, 等. 基于DQN的多类型拦截装备复合式反无人机任务分配方法[J]. 控制与决策, 2022, 37 (1): 142- 150.
	HUANG T F , CHENG G Q , HUANG K H , et al. Task assignment method of compound anti-drone based on DQN for multi-type interception equipment[J]. Control and Decision, 2022, 37 (1): 142- 150.
52	杨艳萍, 叶锡庆, 张明安, 等. 战场网络战基本模型研究[J]. 系统仿真学报, 2011, 23 (5): 1015-1020, 1038.
	YANG Y P , YE X Q , ZHANG M A , et al. Research on basic models for battlefield network war[J]. Journal of System Simulation, 2011, 23 (5): 1015-1020, 1038.
53	杨芷柔, 张虎, 刘静, 等. 节点攻击策略下的军事通信网络结构优化算法[J]. 系统工程与电子技术, 2021, 43 (7): 1848- 1855.
	YANG Z R , ZHANG H , LIU J , et al. Optimization algorithm of military communication network structure under node attack strategy[J]. Systems Engineering and Electronics, 2021, 43 (7): 1848- 1855.
54	刘同林, 杨芷柔, 张虎, 等. 基于复杂网络的军事通信网络建模与性能分析[J]. 系统工程与电子技术, 2020, 42 (12): 2892- 2898.
	LIU T L , YANG Z R , ZHANG H , et al. Modeling and performance analysis of military communication network based on complex network[J]. Systems Engineering and Electronics, 2020, 42 (12): 2892- 2898.
55	王梓行, 姜大立, 漆磊, 等. 基于冗余度的复杂网络抗毁性及节点重要度评估模型[J]. 复杂系统与复杂性科学, 2020, 17 (3): 78- 85.
	WANG Z X , JIANG D L , QI L , et al. Complex network invulnerability and node importance evaluation model based on redundancy[J]. Complex Systems and Complexity Science, 2020, 17 (3): 78- 85.
56	ZENG L , SUN Y Z , LIU Y Y , et al. Finding key players in complex networks through deep reinforcement learning[J]. Nature Machine Intelligence, 2020, 2 (6): 317- 324. doi: 10.1038/s42256-020-0177-2
57	XU Z A, FAN Z Q. Topological structure optimization algorithm of military communication network based on genetic algorithm[C]//Proc. of the IEEE International Conference on Computer Engineering and Application, 2021: 11-18.
58	PRAVEENA V , VIJAYARAJ A , CHINNASAMY P , et al. Optimal deep reinforcement learning for intrusion detection in UAVs[J]. CMC-Computers Materials& Continua, 2022, 70 (2): 2639- 2653.
59	郑莹, 段庆洋, 林利祥, 等. 深度强化学习在典型网络系统中的应用综述[J]. 无线电通信技术, 2020, 46 (6): 603- 623.
	ZHENG Y , DUAN Q Y , LIN L X , et al. A survey on the applications of deep reinforcement learning in classical networking systems[J]. Radio Communications Technology, 2020, 46 (6): 603- 623.
60	洪志鹰. 基于深度强化学习的多智能体编队问题研究[D]. 南京: 东南大学, 2020.
	HONG Z Y. Deep reinforcement learning based multi-agent formation methods[D]. Nanjing: Southeast University, 2020.
61	奚之飞, 徐安, 寇英信, 等. 多机协同空战机动决策流程[J]. 系统工程与电子技术, 2020, 42 (2): 381- 389.
	XI Z F , XU A , KOU Y X , et al. Decision process of multi-aircraft cooperative air combat maneuver[J]. Systems Engineering and Electronics, 2020, 42 (2): 381- 389.
62	ZHAO W W , CHU H R , MIAO X K , et al. Research on the multiagent joint proximal policy optimization algorithm controlling cooperative fixed-wing UAV obstacle avoidance[J]. Sensors, 2020, 20 (16): 4546- 4562. doi: 10.3390/s20164546
63	HU J W , WANG L H , HU T M , et al. Autonomous maneuver decision making of dual-UAV cooperative air combat based on deep reinforcement learning[J]. Electronics, 2022, 11 (3): 467- 489. doi: 10.3390/electronics11030467
64	张耀中, 许佳林, 姚康佳, 等. 基于DDPG算法的无人机集群追击任务[J]. 航空学报, 2020, 41 (10): 314- 326.
	ZHANG Y Z , XU J L , YAO K J , et al. Pursuit missions for UAV swarms based on DDPG algorithm[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41 (10): 314- 326.
65	SILVER D , HUANG A , MADDISON C J , et al. Mastering the game of go with deep neural networks and tree search[J]. Nature, 2016, 529 (7587): 484- 489. doi: 10.1038/nature16961
66	SILVER D , SCHRITTWIESER J , SIMONYAN K , et al. Mastering the game of go without human knowledge[J]. Nature, 2017, 550 (7676): 354- 359. doi: 10.1038/nature24270
67	曹雷. 基于深度强化学习的智能博弈对抗关键技术[J]. 指挥信息系统与技术, 2019, 10 (5): 1- 7.
	CAO L . Key technologies of intelligent game confrontation based on deep reinforcement learning[J]. Command Information System and Technology, 2019, 10 (5): 1- 7.
68	WANG Z , LI H , WU H L , et al. Improving maneuver strategy in air combat by alternate freeze games with a deep rein-forcement learning algorithm[J]. Mathematical Problems in Engineering, 2020, 2020 (22): 7180639.
69	ZHANG G Y , LI Y , XU X H , et al. Efficient training techniques for multi-agent reinforcement learning in combat tasks[J]. IEEE Access, 2019, 7, 109301- 109310. doi: 10.1109/ACCESS.2019.2933454
70	BAI S X , SONG S M , LIANG S Y , et al. UAV maneuvering decision-making algorithm based on twin delayed deep deterministic policy gradient algorithm[J]. Journal of Artificial Intelligence and Technology, 2022, 2 (1): 16- 22.
71	KONG W R , ZHOU D Y , YANG Z , et al. UAV autonomous aerial combat maneuver strategy generation with observation error based on state-adversarial deep deterministic policy gradient and inverse reinforcement learning[J]. Electronics, 2020, 9 (7): 1121- 1145. doi: 10.3390/electronics9071121
72	况立群, 李思远, 冯利, 等. 深度强化学习算法在智能军事决策中的应用[J]. 计算机工程与应用, 2021, 57 (20): 271- 278.
	KUANG L Q , LI S Y , FENG L , et al. Application of deep reinforcement learning algorithm on intelligent military decision system[J]. Computer Engineering and Applications, 2021, 57 (20): 271- 278.
73	GHADERMAZI J, HORE S, SHARMA D, et al. Adversarial deep reinforcement learning enabled threat analytics framework for constrained spatio-temporal movement intelligence data[C]//Proc. of the IEEE International Conference on Intelligence and Security Informatics, 2021.
74	KALLSTROM J, HEINTZ F. Agent coordination in air combat simulation using multi-agent deep reinforcement learning[C]//Proc. of the IEEE International Conference on Systems, Man, and Cybernetics, 2020: 2157-2164.
75	FENG H F, ZENG W. Deep reinforcement learning for carrier-borne aircraft support operation scheduling[C]//Proc. of the International Conference on Intelligent Computing, Automation and Applications, 2021: 929-935.
76	YANG Y , LI J T , PENG L L . Multi-robot path planning based on a deep reinforcement learning DQN algorithm[J]. CAAI Transactions on Intelligence Technology, 2020, 5 (3): 177- 183. doi: 10.1049/trit.2020.0024
77	LEI X Y , ZHANG Z A , DONG P F . Dynamic path planning of unknown environment based on deep reinforcement learning[J]. Journal of Robotics, 2018, (12): 1- 10.
78	YAN C , XIANG X J , WANG C . Towards real-time path planning through deep reinforcement learning for a UAV in dynamic environments[J]. Journal of Intelligent & Robotic Systems, 2020, 98 (2): 297- 309.

名称	时间/年份	主要改进	优势
DQN^[31]	2013	引入深度CNN和经验回放	-
Nature DQN^[32]	2015	提出使用两个Q网络	相比DQN更加稳定
Double DQN^[33]	2016	使用不同值函数分别进行动作选择和评估	克服Q学习中过于乐观的值估计
Dueling DQN^[34]	2016	将网络划分为价值网络和优势网络	网络结构和RL算法更好地结合
D3QN^[35]	2018	整合Double DQN和Dueling DQN	收敛速度更快、更稳定
Rainbow DQN^[36]	2018	整合DQN算法中的6种变体	训练效果有巨大进步, 能适用于各种场景

名称	时间/年份	主要改进	优势
DDPG^[37]	2015	引入经验回放、目标值网络和目标策略网络	可以用来解决连续控制RL领域问题
TD3^[38]	2018	使用两套网络表示不同Q值	抑制Q值过高估计
TPRO^[39]	2015	使用优势函数保证持续优化	提高了算法的采样效率
PPO^[40]	2017	利用新旧策略比例限制新策略更新幅度	进一步提升了算法采样效率
DPPO^[41]	2017	网络多线程并行	避免参数训练的震荡
A3C^[42]	2016	不同的智能体并行探索	训练时间短
A2C^[43]	2017	同步控制	训练效果优于A3C

应用领域	文献	基本算法	方法改进创新	具体问题
武器装备	[50]	PPO	-	武器装备组合推荐
武器装备	[51]	DQN、Double DQN	使用当前状态的Q值替换公式中下一状态的Q值	武器装备动态目标分配
网络安全	[56]	FINDER框架(DQN)	归纳式图表式学习、小型合成网络训练	复杂网络结构优化
	[57]	FINDER框架	识别出关键节点后结合遗传算法改进网络结构	军用通信网络结构优化
	[58]	DRL-BWO	利用BWO算法对深度信念网络的参数进行优化	网络入侵检测
无人机编队	[62]	MAJPPO	采用滑动窗口平均计算集中的状态价值函数	多无人机协同编队控制
	[63]	DQN	提出优先采样策略替代传统DQN中的随机采样	无人机避障、编队、对抗
	[64]	DDPG	基于滑动平均值的软更新策略	无人机集群协同
智能决策与博弈	[68]	DQN	周期性冻结策略使智能体与对手智能体交替训练	智能策略对抗
	[69]	DQN、DDPG	战斗规则辅助训练	多智能体作战训练
	[70]	TD3	-	机动决策
	[71]	DDPG	引入正则化器、提出最大熵逆RL算法对奖励进行规划	机动决策
	[72]	DDPG	优先级经验重放、混合双噪声探索、多智能体单训练	多智能体机动决策
情报	[73]	DQN	结合机器学习分类器学习模式	威胁识别
仿真训练	[74]	MADDPG	不频繁反馈进行学习、密集奖励系统	飞行员训练
调度	[75]	A2C	状态的图像表示	多资源约束的多项目调度
路径规划	[76]	DQN	先验知识和先验规则改进算法	机器人路径规划
	[77]	Double DQN	随机设置目标位置扩大样本池状态空间分布	机器人路径规划
	[78]	D3QN	ε-贪婪策略和启发式搜索规则相结合对动作选择策略进行改进	无人机路径规划

[1]	Fengguo WU, Wei TAO, Hui LI, Jianwei ZHANG, Chengchen ZHENG. UAV intelligent avoidance decisions based on deep reinforcement learning algorithm [J]. Systems Engineering and Electronics, 2023, 45(6): 1702-1711.
[2]	Jin TANG, Yangang LIANG, Zhihui BAI, Kebo LI. Landing control algorithm of rotor UAV based on DQN [J]. Systems Engineering and Electronics, 2023, 45(5): 1451-1460.
[3]	XIE Hao, GUO Aihuang, SONG Chunlin, JIAO Runze. eNB selection for LTE-V using deep reinforcement learning [J]. Systems Engineering and Electronics, 2019, 41(7): 1652-1657.
[4]	DOU Yajie, XU Xiangqian, ZHOU Zhexuan, XIA Boyuan, YANG Kewei. Analysis of system portfolio selection and typical military application [J]. Systems Engineering and Electronics, 2019, 41(12): 2754-2762.

Review of deep reinforcement learning and its applications in military field

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 78

Related Articles 4

Recommended Articles

Metrics

Comments