In today's era of information, there is gigantic amount of data available from various sources. Not only does the enormous volumes pose problems, searching of required information becomes a very difficult task. It...
详细信息
ISBN:
(数字)9781538681138
ISBN:
(纸本)9781538681145
In today's era of information, there is gigantic amount of data available from various sources. Not only does the enormous volumes pose problems, searching of required information becomes a very difficult task. It is the need of the hour to have smaller but significant representation of large, bulky pieces of information in order to obtain the desired details. Text summarization is the process of condensing text documents into shorter and accurate representation conveying the meaning of the text precisely. It has found applications in numerous fields. In this paper, a process for extractive text summarization using fuzzy logic has been discussed meticulously. It takes various properties into account for identifying the most significant sentences for the formation of summary from a given text. The model proposed in this paper has been tested on BBC News Summary dataset and the results have been compared using the ROUGE measures. The obtained results indicate that the proposed model shows enhanced performance with improved f-measure values.
In the current command and control (C2) supernetwork model it is difficult to quantify and describe the complex relationships in C2 networks accurately. This paper presents a new modeling method for C2 supernetworks b...
详细信息
The purpose of this paper is to identify a problem in Grid resource discovery models that affect the overall performance of grid computing. Since, Grid resources are scattered in different geographical locations on he...
详细信息
This document focuses on the development of a learning tools for the dynamic model of a steam turbine 20MW capacity type able to accommodate the different variations of the machine's operating parameters. Consider...
详细信息
ISBN:
(纸本)9781538659823
This document focuses on the development of a learning tools for the dynamic model of a steam turbine 20MW capacity type able to accommodate the different variations of the machine's operating parameters. Considering all the advantages and disadvantages of the optimization methods that we have studied (genetic algorithm and neural networks), the neuro-fuzzy option was remarkable in view of the results obtained in the modeling of the systems. The ANFIS model (Adaptive Neuro-Fuzzy Inference System), known for its performance in the learning domain of complex non-linear systems, is chosen for a better approximation of functions fir modeling. The active power depending of the high pressure steam flow inlet turbine and the low pressure steam flow extraction as well as the voltage across the generator depending of the power factor and the active power shall be controlled from 2 ANFIS models mounted in parallel, their outputs acting respectively on the control of the HP (High Pressure) steam inlet valve opening for the variation of the HP steam flow inlet and the rotor excitation current for the variation of the voltage across the alternator. The dynamic model thus obtained from the adjustment of the parameters of the membership functions describes the behavior of the turbine to stabilize its operating point in the face of any disturbance.
Evolutionary algorithms (EAs) are powerful tools for solving complex engineering applications problems, however, the function evaluations of the real-world problems are often time-consuming, which hinders the applicat...
详细信息
ISBN:
(数字)9781728144849
ISBN:
(纸本)9781728144856
Evolutionary algorithms (EAs) are powerful tools for solving complex engineering applications problems, however, the function evaluations of the real-world problems are often time-consuming, which hinders the application of EAs to solve these problems. To address this challenge, surrogate-assisted EAs (SAEAs) have been widely studied over the past decades. Model management can help obtain solutions under limited computational budget to accelerate the convergence of the optimization process. In this paper, we propose a SAEA based on social learning particle swarm optimization (SL-PSO), a space reduction strategy and a global model search strategy are developed to search for the best and most uncertain solutions. In the proposed algorithm, the space reduction strategy is used to search for the optimal solution based on the surrogates and the global model search strategy is used to search for the most uncertain solution. The evolutionary search using the space strategy switches to the global search once on further improvement can be observed, and vice versa. Experimental results comparing the proposed algorithm with other two algorithms on several benchmark problems that the proposed algorithm is able to achieve better or competitive solutions.
Two distinctive features of challenging control engineering problems are commonly taken into consideration in design of dynamical, mechatronics systems, namely operation ranges, of such systems with nonlinear effects,...
详细信息
Deep reinforcement learning has recently provided promising results on the traffic light control optimization problem, by training neural network agents to select the traffic light phase. These agents learn complex mo...
详细信息
ISBN:
(纸本)9781538670255
Deep reinforcement learning has recently provided promising results on the traffic light control optimization problem, by training neural network agents to select the traffic light phase. These agents learn complex models by optimizing a simple objective, such as the average traffic speed, but are considered opaque when it comes to explaining their decisions. Nevertheless, explanations are required in transferring this technology in the real world, especially in complex scenarios with nontrivial phases, such as in the case of signalized roundabouts with entry and circulatory traffic lights. In this paper, after training a Policy Gradient agent on a signalized roundabout with 11 phases and real traffic data, we analyze the relation between the agent phase preferences and the actual traffic, and we assess the agent capability of reacting to the current detectors state. Then, we estimate the effect of the road detectors state on the agent selected phases, through the SHAP model-agnostic technique, using Shapley values recovered from a linear explanation model. The results show that it is possible to extract meaningful explanations on the decision taken by a complex policy, in relation to both the traffic volumes and the lanes occupancy.
Small drones with total mass of a few kilograms are becoming more and more popular in many applications increasing the probability of occurrence of emergency situations caused by an equipment failure or a human error....
详细信息
ISBN:
(纸本)9789073802995
Small drones with total mass of a few kilograms are becoming more and more popular in many applications increasing the probability of occurrence of emergency situations caused by an equipment failure or a human error. In case of a fall from a high altitude very often it is possible to use parachute rescue systems, which however require relatively long time for deployment and development of braking forces. The touchdown velocity may be large enough to exceed limit accelerations for UAV equipment. The paper presents the concept of deployable airbag systems, in particular with adaptive flow control, which provides a possible solution to the above-mentioned problems. The paper discusses the overall control and adaptation strategy. Simplified methods for mathematical modeling are proposed and formulated for an example on a cylindrical airbag. The conceptual part is concluded with the presentation of the methodology of experimental verification and results of initial tests of the integrated airbag system.
Typical Tethered Space Robot (TSR) composed of main satellite, operation robot and joined tether has an important prospect in active debris capture and removal applications. Targeting the safe, stable and economical n...
详细信息
ISBN:
(纸本)9781538670576
Typical Tethered Space Robot (TSR) composed of main satellite, operation robot and joined tether has an important prospect in active debris capture and removal applications. Targeting the safe, stable and economical nonplanar orbital transfer mission, the dynamic modeling and tracking control algorithm problems during the towing process have been studied in this paper, providing a theoretical basis for the tether towing deorbit technical verification and engineering. On the basis of optimal feedback control theory, the control problem during nonplanar orbital transfer mission of TSR is studied. For eliminating the effect of mismatch of system model and external disturbance, an optimal feedback controller in closed-loop form is proposed. The established optimal feedback controller is essentially composed of multiple computations by an open-loop optimal controller. Based on the state feedback matrix collected at the sampling interval, taking advantage of fast convergence speed and high precision characteristics inherited from Gauss-Pseudospectral method, the finite horizon open-loop optimal control problem at each sampling interval is discretized and solved. And the first part of each control sequence generated by the controller is imposed on the controlled model. Finally, the effectiveness of the proposed scheme is demonstrated via numerical case studies.
This article describes the positioning system of defectoscopic equipment for non-destructive examination of complex shaped parts made of polymer composite materials. The purpose of the system and features of the inves...
详细信息
ISBN:
(纸本)9781538643075
This article describes the positioning system of defectoscopic equipment for non-destructive examination of complex shaped parts made of polymer composite materials. The purpose of the system and features of the investigated objects are described. The rationale for the development of the system and the range of problems it solves are presented. The solution of the kinematics problem for a 5-DOF manipulator is considered. The original algorithms for solving the kinematics problem are demonstrated. Methods for resolving collisions for a manipulator system are described. The results obtained in the course of experiments and studies are presented. The study was supported by the RSF grant 16-19-00155 "The robotic system of multi-angle microfocus radiography for aircraft parts and assemblies made of polymer composite materials with complex impact."
暂无评论