慢性肾病(Chronic Kidney Disease,CKD)是一种进展性疾病,早期若不及时加以治疗会导致病情发展,甚至肾衰竭。为了研究CKD患者从早期发展到终末期的概率,本文提出一种CKD进展概率预测模型:结合蚁群路径优化决策树算法(Decision Tree Ant ...慢性肾病(Chronic Kidney Disease,CKD)是一种进展性疾病,早期若不及时加以治疗会导致病情发展,甚至肾衰竭。为了研究CKD患者从早期发展到终末期的概率,本文提出一种CKD进展概率预测模型:结合蚁群路径优化决策树算法(Decision Tree Ant Path Optimization,DTAPO)和逻辑回归算法(Logistic Regression,LR),将CKD患者数据分为P(进展)和NP(非进展)2类,得到分类精确率和召回率,从而计算CKD患者由3期进展到4期或5期的概率。实验结果表明,当特征数目为13时,结合逻辑回归的蚁群路径优化决策树算法的预测效果最好,其分类精确率为98.84%,由该精确率预测得到的进展患者确实由3期进展到4期或5期的概率为0.9827。展开更多
Path planning is an important issue for autonomous underwater vehicles (AUVs) traversing an unknown environment such as a sea floor, a jungle, or the outer celestial planets. For this paper, global path planning usi...Path planning is an important issue for autonomous underwater vehicles (AUVs) traversing an unknown environment such as a sea floor, a jungle, or the outer celestial planets. For this paper, global path planning using large-scale chart data was studied, and the principles of ant colony optimization (ACO) were applied. This paper introduced the idea of a visibility graph based on the grid workspace model. It also brought a series of pheromone updating rules for the ACO planning algorithm. The operational steps of the ACO algorithm are proposed as a model for a global path planning method for AUV. To mimic the process of smoothing a planned path, a cutting operator and an insertion-point operator were designed. Simulation results demonstrated that the ACO algorithm is suitable for global path planning. The system has many advantages, including that the operating path of the AUV can be quickly optimized, and it is shorter, safer, and smoother. The prototype system successfully demonstrated the feasibility of the concept, proving it can be applied to surveys of unstructured unmanned environments.展开更多
Ant colony optimization (ACO) algorithm was modified to optimize the global path. In order to simulate the real ant colonies, according to the foraging behavior of ant colonies and the characteristic of food, concepti...Ant colony optimization (ACO) algorithm was modified to optimize the global path. In order to simulate the real ant colonies, according to the foraging behavior of ant colonies and the characteristic of food, conceptions of neighboring area and smell area were presented. The former can ensure the diversity of paths and the latter ensures that each ant can reach the goal. Then the whole path was divided into three parts and ACO was used to search the second part path. When the three parts pathes were adjusted, the final path was found. The valid path and invalid path were defined to ensure the path valid. Finally, the strategies of the pheromone search were applied to search the optimum path. However, when only the pheromone was used to search the optimum path, ACO converges easily. In order to avoid this premature convergence, combining pheromone search and random search, a hybrid ant colony algorithm(HACO) was used to find the optimum path. The comparison between ACO and HACO shows that HACO can be used to find the shortest path.展开更多
Geography rectangle is used to reduce signaling overhead of the LEO satellite networks.Moreover,a multi-path routing algorithm based on an improved ant colony system(MPRA-AC) is proposed.Matrix indicating the importan...Geography rectangle is used to reduce signaling overhead of the LEO satellite networks.Moreover,a multi-path routing algorithm based on an improved ant colony system(MPRA-AC) is proposed.Matrix indicating the importance of the link between satellites is introduced into MPRA-AC in order to find the optimal path more quickly.Simulation results show that MPRA-AC reduces the number of iterations to achieve a satisfactory solution.At the same time,the packet delivery ratio of LEO satellite networks when running MPRA-AC and DSR-LSN(dynamic source routing algorithm for LEO satellite networks) is compared.The packet delivery ratio is about 7.9%lower when running DSR-LSN.Moreover,because of the mechanism of active load balancing of MPRA-AC,simulation results show that MPRA-AC outperforms DSR-LSN in link utilization when data packets are transmitted in the networks.展开更多
In the real-world situation,the lunar missions’scale and terrain are different according to various operational regions or worksheets,which requests a more flexible and efficient algorithm to generate task paths.A mu...In the real-world situation,the lunar missions’scale and terrain are different according to various operational regions or worksheets,which requests a more flexible and efficient algorithm to generate task paths.A multi-scale ant colony planning method for the lunar robot is designed to meet the requirements of large scale and complex terrain in lunar space.In the algorithm,the actual lunar surface image is meshed into a gird map,the path planning algorithm is modeled on it,and then the actual path is projected to the original lunar surface and mission.The classical ant colony planning algorithm is rewritten utilizing a multi-scale method to address the diverse task problem.Moreover,the path smoothness is also considered to reduce the magnitude of the steering angle.Finally,several typical conditions to verify the efficiency and feasibility of the proposed algorithm are presented.展开更多
Swarm intelligence inspired by the social behavior of ants boasts a number of attractive features, including adaptation, robustness and distributed, decentralized nature, which are well suited for routing in modern co...Swarm intelligence inspired by the social behavior of ants boasts a number of attractive features, including adaptation, robustness and distributed, decentralized nature, which are well suited for routing in modern communication networks. This paper describes an adaptive swarm-based routing algorithm that increases convergence speed, reduces routing instabilities and oscillations by using a novel variation of reinforcement learning and a technique called momentum.Experiment on the dynamic network showed that adaptive swarm-based routing learns the optimum routing in terms of convergence speed and average packet latency.展开更多
文摘慢性肾病(Chronic Kidney Disease,CKD)是一种进展性疾病,早期若不及时加以治疗会导致病情发展,甚至肾衰竭。为了研究CKD患者从早期发展到终末期的概率,本文提出一种CKD进展概率预测模型:结合蚁群路径优化决策树算法(Decision Tree Ant Path Optimization,DTAPO)和逻辑回归算法(Logistic Regression,LR),将CKD患者数据分为P(进展)和NP(非进展)2类,得到分类精确率和召回率,从而计算CKD患者由3期进展到4期或5期的概率。实验结果表明,当特征数目为13时,结合逻辑回归的蚁群路径优化决策树算法的预测效果最好,其分类精确率为98.84%,由该精确率预测得到的进展患者确实由3期进展到4期或5期的概率为0.9827。
基金Supported by State Key Laboratory of Robotics and System (HIT) under Grant No.SKLRS200706the Heilongjiang Scientific Research Foundation for Postdoctoral Financial Assistance under Grant No.323630221the Project of Harbin Technological Talent Research Foundation under Grant No.RC2006QN009015
文摘Path planning is an important issue for autonomous underwater vehicles (AUVs) traversing an unknown environment such as a sea floor, a jungle, or the outer celestial planets. For this paper, global path planning using large-scale chart data was studied, and the principles of ant colony optimization (ACO) were applied. This paper introduced the idea of a visibility graph based on the grid workspace model. It also brought a series of pheromone updating rules for the ACO planning algorithm. The operational steps of the ACO algorithm are proposed as a model for a global path planning method for AUV. To mimic the process of smoothing a planned path, a cutting operator and an insertion-point operator were designed. Simulation results demonstrated that the ACO algorithm is suitable for global path planning. The system has many advantages, including that the operating path of the AUV can be quickly optimized, and it is shorter, safer, and smoother. The prototype system successfully demonstrated the feasibility of the concept, proving it can be applied to surveys of unstructured unmanned environments.
基金Projects(60234030, 60404021) supported by the National Natural Science Foundation of China
文摘Ant colony optimization (ACO) algorithm was modified to optimize the global path. In order to simulate the real ant colonies, according to the foraging behavior of ant colonies and the characteristic of food, conceptions of neighboring area and smell area were presented. The former can ensure the diversity of paths and the latter ensures that each ant can reach the goal. Then the whole path was divided into three parts and ACO was used to search the second part path. When the three parts pathes were adjusted, the final path was found. The valid path and invalid path were defined to ensure the path valid. Finally, the strategies of the pheromone search were applied to search the optimum path. However, when only the pheromone was used to search the optimum path, ACO converges easily. In order to avoid this premature convergence, combining pheromone search and random search, a hybrid ant colony algorithm(HACO) was used to find the optimum path. The comparison between ACO and HACO shows that HACO can be used to find the shortest path.
基金Supported by the National High Technology Research and Development Programme of China(No.SS2013AA010503)the National Natural Science Foundation of China(No.61271281,61201151,61275158)the Fundamental Research Funds for the Central Universities(No.2482012PTB0004)
文摘Geography rectangle is used to reduce signaling overhead of the LEO satellite networks.Moreover,a multi-path routing algorithm based on an improved ant colony system(MPRA-AC) is proposed.Matrix indicating the importance of the link between satellites is introduced into MPRA-AC in order to find the optimal path more quickly.Simulation results show that MPRA-AC reduces the number of iterations to achieve a satisfactory solution.At the same time,the packet delivery ratio of LEO satellite networks when running MPRA-AC and DSR-LSN(dynamic source routing algorithm for LEO satellite networks) is compared.The packet delivery ratio is about 7.9%lower when running DSR-LSN.Moreover,because of the mechanism of active load balancing of MPRA-AC,simulation results show that MPRA-AC outperforms DSR-LSN in link utilization when data packets are transmitted in the networks.
基金supported by the National Natural Science Foundations of China(No.11772185)Fundamental Research Funds for the Central Universities(No.3072022JC0202)。
文摘In the real-world situation,the lunar missions’scale and terrain are different according to various operational regions or worksheets,which requests a more flexible and efficient algorithm to generate task paths.A multi-scale ant colony planning method for the lunar robot is designed to meet the requirements of large scale and complex terrain in lunar space.In the algorithm,the actual lunar surface image is meshed into a gird map,the path planning algorithm is modeled on it,and then the actual path is projected to the original lunar surface and mission.The classical ant colony planning algorithm is rewritten utilizing a multi-scale method to address the diverse task problem.Moreover,the path smoothness is also considered to reduce the magnitude of the steering angle.Finally,several typical conditions to verify the efficiency and feasibility of the proposed algorithm are presented.
文摘Swarm intelligence inspired by the social behavior of ants boasts a number of attractive features, including adaptation, robustness and distributed, decentralized nature, which are well suited for routing in modern communication networks. This paper describes an adaptive swarm-based routing algorithm that increases convergence speed, reduces routing instabilities and oscillations by using a novel variation of reinforcement learning and a technique called momentum.Experiment on the dynamic network showed that adaptive swarm-based routing learns the optimum routing in terms of convergence speed and average packet latency.