AI is impacting humans in ways that have been unheard of. AI applications are now capable of being used in the manufacture and functioning of autonomous weapons, specifically in the Lethal Autonomous Weapons System (L...
详细信息
The parameter control problem is crucial to the performance of genetic algorithms. In this paper, we propose a self-adaptive approach based on entropy and rules of nature to control the parameters of algorithms. This ...
详细信息
ISBN:
(纸本)9781728124858
The parameter control problem is crucial to the performance of genetic algorithms. In this paper, we propose a self-adaptive approach based on entropy and rules of nature to control the parameters of algorithms. This approach utilizes the entropy of both the population and each genetic locus as the feedback to evaluate the state of algorithms. Then, parameters are adjusted according to the state of algorithms and rules of nature. This strategy avoids the impact of randomness when evaluating the status of algorithms and tracks the development of each gene in time to prevent premature and nonconvergence on a certain gene. Furthermore, this method can not only maintain the solutions with good quality but also increase the probability that the solutions with poor quality change. The experimental results demonstrate that the proposed parameter-controlling strategy is valid for the algorithm to enhance the performance for solving a variety of combinatorial optimization problems.
This research aims to provide low cost, efficient automation and security system for home by using Arduino. Home automation means controlling the activities of home appliances and features automatically in a predeterm...
详细信息
ISBN:
(纸本)9781538684399
This research aims to provide low cost, efficient automation and security system for home by using Arduino. Home automation means controlling the activities of home appliances and features automatically in a predetermined technique. It initially involves the control and automation of systems that ensure human comforts such as lighting, fire extinguisher, air conditioning, and security. This smart technology helps to get desired security and brings comfort in daily life. Commercial home automation systems are still not affordable for middle -class families in developing countries. Thankfully, with the availability of cheap microcontrollers, like Arduino, it has enabled an easy implementation of low-cost home automation systems including all the features those are added to those high end and commercial devices for home automation and security management. In this paper, we present a simple, low cost and multi-functional home automation system based on Arduino microcontroller. The whole system can be operated with the help various effective sensors which detect problems and on the other hand, takes a step to fix them. This project also includes a Bluetooth module and Arduino Bluetooth controller application with which the functions are executed.
This paper studies the stationary bipartite consensus problem of a kind of multi-agent systems with second-order dynamics, where the impulsive control approach is utilized to design the control protocol. The impulsive...
详细信息
ISBN:
(纸本)9781728124858
This paper studies the stationary bipartite consensus problem of a kind of multi-agent systems with second-order dynamics, where the impulsive control approach is utilized to design the control protocol. The impulsive control law is only considered by using position-based information, and the structure of control law is induced by a structurally balanced graph. Then, the stationary bipartite consensus problem has been converted to a convergence problem with respect to a finite product of stochastic matrices. By using the norm matrix and convex theory, this convergence problem is proven to be stability, which means that the stationary bipartite consensus problem is ensured. Subsequently, a numerical example is given to show the obtained result.
Crater extraction and recognition is an important research content of deep space planetary science. Traditional crater detection algorithms (CDAs) are mainly based on crater feature construction which relies on high-q...
详细信息
ISBN:
(数字)9781728180281
ISBN:
(纸本)9781728180298
Crater extraction and recognition is an important research content of deep space planetary science. Traditional crater detection algorithms (CDAs) are mainly based on crater feature construction which relies on high-quality data. With the application of deep learning in image recognition and semantic segmentation, new ideas have been brought to meteorite crater extraction. Many crater extraction algorithms based on artificial intelligence have been proposed which greatly simplifies the crater extraction process and improves detection accuracy. However, with the improvement of the accuracy, the convolution kernels become more and more, and the huge parameters and the consumption of storage and computing resources limit the application of these algorithms in mobile device. In order to solve this problem, we propose a compact crater extraction network based on model pruning. In the combination of U-Net and residual block, the network structure is optimized under the premise of retaining the longitude of large model extraction, and the balance of hardware resources and algorithm accuracy is achieved. The experimental results show that we compress the model to 4.9% of raw size and only lose almost 0.5% accuracy. It provides a reference for the application of CDAs on resource constrained platforms.
Distributed average tracking (DAT) problems are investigated for general linear dynamical systems under undirected connected topology in this paper. A kind of distributed event-triggered DAT algorithms with static gai...
详细信息
ISBN:
(纸本)9781728124858
Distributed average tracking (DAT) problems are investigated for general linear dynamical systems under undirected connected topology in this paper. A kind of distributed event-triggered DAT algorithms with static gain is designed by using model-based local sampled state information. The control objective of the considered DAT problem is achieved by using the proposed event-triggered DAT algorithms. Meanwhile, the Zeno behavior is excluded. Finally, a simulation example is presented to validate the proposed control laws.
A linear extended state observer (LESO) based fuzzy fault tolerant control (FTC) scheme is designed for an over-actuated autonomous underwater vehicle (AUV) to address the faults of actuators. In this scheme, both the...
详细信息
ISBN:
(纸本)9781728124858
A linear extended state observer (LESO) based fuzzy fault tolerant control (FTC) scheme is designed for an over-actuated autonomous underwater vehicle (AUV) to address the faults of actuators. In this scheme, both the faults of the actuators and other immeasurable disturbances are lumped into a generalized total disturbance, which is then estimated by a LESO. Next, the thruster forces of the over-actuated system are reallocated to keep the AUV tracking of the desired trajectory. To tune the parameters of the proposed scheme, a fuzzy logic controller is developed to make sure the parameters of the scheme achieve online self-tuning.
This paper proposes a scene frame prediction system based on digital twin technology. The system is mainly composed of an unmanned perception module, a communication link module, a command center module that provides ...
详细信息
This paper proposes a scene frame prediction system based on digital twin technology. The system is mainly composed of an unmanned perception module, a communication link module, a command center module that provides intelligent computing services, and an interaction and visualization module for human operators. These modules together constitute a system for predicting and recovery the time-series matrix composed of scene frames and object frames. At the same time, in view of the current problems of lack of real-time information and long response time in the maritime search and rescue (SAR) field, this paper instantiates the above system to improve the existing SAR system. Satellites and unmanned vehicles perceive part of the scene data of the real cyber-physical system in real-time and divide them into multiple frames according to the timestamps. In addition, this paper also proposes an environmental graph-attention network (Env-GAT) to achieve efficient and reliable frame predicting. Finally, this paper verifies that the performance of the spatiotemporal attention graph network model has reached the optimal level through computational experiments.
The multi-population method is a common method for solving dynamic optimization problems. However, to design an efficient multi-population method, one of the challenging issues is how to allocate computational resourc...
详细信息
In this paper, the stabilization problem of chaotic system is investigated via fuzzy sampled control. To reduce the unnecessary sampled packet transmissions, the event-triggered communication architecture is applied. ...
详细信息
ISBN:
(纸本)9781728124858
In this paper, the stabilization problem of chaotic system is investigated via fuzzy sampled control. To reduce the unnecessary sampled packet transmissions, the event-triggered communication architecture is applied. Based on the discrimination between the membership functions at sampled data transmission instant and at non-transmission instant is universal, in order to well compensate it, the fuzzy time-dependent Lyapunov functional is introduced. Moreover, the further stabilization result is given and the fuzzy sampled controller is also presented. Finally, a simulation result is presented to illustrated the effectiveness and practicability of our results.
暂无评论