Adaptive gradient-descent optimizers are the standard choice for training neural network models. Despite their faster convergence than gradient-descent and remarkable performance in practice, the adaptive optimizers a...
详细信息
As global digitization continues to grow, technology becomes more affordable and easier to use, and social media platforms thrive, becoming the new means of spreading information and news. Communities are built around...
详细信息
As global digitization continues to grow, technology becomes more affordable and easier to use, and social media platforms thrive, becoming the new means of spreading information and news. Communities are built around sharing and discussing current events. Within these communities, users are enabled to share their opinions about each event. Using Sentiment Analysis to understand the polarity of each message belonging to an event, as well as the entire event, can help to better understand the general and individual feelings of significant trends and the dynamics on online social networks. In this context, we propose a new ensemble architecture, EDSAEnsemble (Event Detection Sentiment Analysis Ensemble), that uses Event Detection and Sentiment Analysis to improve the detection of the polarity for current events from Social Media. For Event Detection, we use techniques based on Information Diffusion taking into account both the time span and the topics. To detect the polarity of each event, we preprocess the text and employ several Machine and Deep Learning models to create an ensemble model. The preprocessing step includes several word representation models: raw frequency, TFIDF, Word2Vec, and Transformers. The proposed EDSA-Ensemble architecture improves the event sentiment classification over the individual Machine and Deep Learning models. Authors
Formation control of fixed-wing aerial vehicles is an important yet rarely addressed problem because of their complex dynamics and various motion constraints,such as nonholonomic and velocity *** guidance-route-based ...
详细信息
Formation control of fixed-wing aerial vehicles is an important yet rarely addressed problem because of their complex dynamics and various motion constraints,such as nonholonomic and velocity *** guidance-route-based strategy has been demonstrated to be applicable to fixed-wing ***,it requires a global coordinator and there exists control lag,due to its own *** this reason,this paper presents a fully distributed guidance-route-based formation approach to address the aforementioned ***,a hop-count scheme is introduced to achieve distributed implementation,in which each aircraft chooses a neighbor with the minimum hop-count as a reference to generate its guidance route using only local ***,the model predictive control algorithm is employed to eliminate the control lag and achieve precise formation shape *** addition,the stall protection and collision avoidance are also ***,three numerical simulations demonstrate that our proposed approach can implement precise formation shape control of fixed-wing aircraft in a fully distributed manner.
A novel framework in multi-agent system networks is introduced and analyzed in this article, namely coupled output synchronization over directed graph topologies. Under assumptions of a rooted spanning tree, we design...
详细信息
Trajectory planning method is a research hotspot in autonomous driving. Existing reinforcement learning-based trajectory planning methods suffer from unstable performance due to the strong randomness of network weight...
详细信息
Trajectory planning method is a research hotspot in autonomous driving. Existing reinforcement learning-based trajectory planning methods suffer from unstable performance due to the strong randomness of network weight parameter updates during the training process. Therefore, this paper proposes a novel trajectory planning method based on deep reinforcement learning trust region policy optimization (TRPO). Firstly, in order to enhance the robustness of the trajectory planning method based on deep reinforcement learning TRPO, a TRPO-LSTM based decision model was proposed. More specifically, a long short term memory (LSTM) based state feature extraction network was designed and embeded into a TRPO-based decision model to enhance the ability of TRPO to extract information from the environmental state space. Secondly, in order to make the planned trajectory adaptive to the dynamic changes of traffic environment, we presented a novel TRPO-LSTM trajectory fitting algorithm. To the best of our knowledge, this is the first work aiming at applying the TRPO-LSTM based decision model in the trajectory fitting process to search the optimal longitudinal trajectory speed. Finally, the proposed trajectory planning method was implemented and simulated on the CARLA simulator. The experimental results show that, compared with existing trajectory planning methods based on deep reinforcement learning algorithms, our proposed method achieves a cumulative reward improvement of over 28.9% in the scenario of four lane highway, and has better robustness. Meanwhile, the proposed method can achieve a lower collision rate of 0.93% while improving the average speed and comfort of vehicle driving. IEEE
Dear Editor,This letter focuses on leveraging the object information in images to improve the performance of the U-Net based change *** detection is fundamental to many computer vision *** existing solutions based on ...
详细信息
Dear Editor,This letter focuses on leveraging the object information in images to improve the performance of the U-Net based change *** detection is fundamental to many computer vision *** existing solutions based on deep neural networks are able to achieve impressive results.
The robotic airship can provide a promising aerostatic platform for many potential *** applications require a precise autonomous trajectory tracking control for *** has a nonlinear and uncertain *** is prone to wind d...
详细信息
The robotic airship can provide a promising aerostatic platform for many potential *** applications require a precise autonomous trajectory tracking control for *** has a nonlinear and uncertain *** is prone to wind disturbances that offer a challenge for a trajectory tracking control *** paper addresses the airship trajectory tracking problem having time varying reference path.A lumped parameter estimation approach under model uncertainties and wind disturbances is opted against distributed *** uses extended Kalman filter(EKF)for uncertainty and disturbance *** estimated parameters are used by sliding mode controller(SMC)for ultimate control of airship trajectory *** comprehensive algorithm,EKF based SMC(ESMC),is used as a robust solution to track airship *** proposed estimator provides the estimates of wind disturbances as well as model uncertainty due to the mass matrix variations and aerodynamic model *** stability and convergence of the proposed method are investigated using the Lyapunov stability *** simulation results show that the proposed method efficiently tracks the desired *** method solves the stability,convergence,and chattering problem of SMC under model uncertainties and wind disturbances.
Algorithms of class activation maps are used to provide visual explanations for CNN models to reduce the black-box nature and are widely used for model evaluation and optimization. However, it is not common to apply s...
详细信息
The spatiotemporal motion characteristics of the kilowatt argon microwave plasma torch with the air carrier gas(kW-AC-ArMPT)and the behavior of the plasma filaments are investigated with a digital single-lens reflex(S...
详细信息
The spatiotemporal motion characteristics of the kilowatt argon microwave plasma torch with the air carrier gas(kW-AC-ArMPT)and the behavior of the plasma filaments are investigated with a digital single-lens reflex(SLR)camera and a high-speed *** with the introduction of the air,both the volume of the central channel and the rotational frequency of the plasma filament are ***,the excitation temperature(Texc),rotational temperature(Trot),and density of electron number(ne)of the kW-AC-ArMPT are measured with optical *** is clearly shown that the introduction of air contributed to the rise of Trot and ne of the plasma,which is beneficial to improving the analytical performance of the *** the detection limits of some heavy metal elements are measured by kW-AC-ArMPT,which are in the ppb *** experimental results show that the kW-ArMPT has a high tolerance to air injection at least 1.0 L/min,which allows the direct extraction of air from the environment for analysis and therefore has the potential for online and in-situ detection of ambient air quality and industrial exhaust gases.
The paper is devoted to corrective agents dispensing controlsystems for thermal power plants, namely, hydrazine dispensing control system and phosphates dispensing control system. The systems mentioned are single-loo...
详细信息
暂无评论