The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Neural networks have demonstrated promising results for a wide range of applications. The proposed techniques employ different architectures and objective functions to adapt to the application while enabling a feasible implementation. Commonly used objective functions for network optimization are based on the cross entropy between the empirical distribution of the training data and the model distribution...
Surface registration is an inevitable step for solving the correspondence problem in statistical shape modeling and useful for automatic 3D segmentation of objects of a certain shape. Common techniques for a pairwise surface registration rely either on a point-based or a mesh-based representation of the source (moving) and the target (fixed) surface. Iterative closest point (ICP) algorithms operate...
A comparative analysis of the plug-in fuel cell vehicles (PFCV) is studied regarding different topologies, drive cycles and control strategies. To improve the performance of the PFCV, an optimization strategy is proposed at first by regulating the power distribution between the battery and the PEMFC system. Then, a direct multiple shooting (DMS) algorithm is used to solve this nonlinear programming...
Deep neural networks (DNN) achieve very good performance in many machine learning tasks, but are computationally very demanding. Hence, there is a growing interest on model reduction methods for DNN. Model reduction allows to reduce the number of computations needed to evaluate a trained DNN without a significant performance degradation. In this paper, we study layerwise reduction methods that reduce...
Due to the explosive growth of visual data and the raised urgent needs for more efficient nearest neighbor search methods, hashing methods have been widely studied in recent years. However, parameter optimization of the hash function in most available approaches is tightly coupled with the form of the function itself, which makes the optimization difficult and consequently affects the similarity preserving...
This paper proposed a modified bacterial foraging optimization (MBFO) algorithm to solve the problem in decentralized control of sensors-based swarm robots. The MFBO algorithm is used to solve the problems of target detecting and trapping for swarm robots. In the beginning, local coordinate system is established by initial position and the target area of the swarm robots. Then the target area is divided...
As a special form of mobile ad hoc network (MANET), vehicular ad-hoc network (VANET) is expected to support communication between vehicles, and between vehicles and stationary infrastructures, such as access points (APs). However, due to the highly mobile characteristics of VANET, the direct connection between source vehicles (SVs) and APs might be inaccessible. In this case, relay vehicles (RVs)...
A novel fast heuristic algorithm for operating reliability constrained unit commitment is proposed in this paper. The loss-of-load probability constraints are fulfilled by the iteration between the traditional spinning reserve constrained unit commitment and the operating reliability estimation. The features of the approach are the fastness of the algorithm and the robustness of the results. Even...
In this paper we study the path choice problem of material transportation in emergency based on the analysis of fuzzy concept. The effect of fuzzy factors on road is mainly considered to obtain an optimal calculation of path choice. A routing model with random probability for emergency rescue center is proposed with utilization of the theory of uncertain programming with fuzzy probability. The uncertain...
This paper focuses on the optimization of the 2D geometry of sensor arrays for 2D direction-of-arrival (DOA) estimation. Such arrays can be used for radar imaging purposes. Due to the optimization, the number of array channels can be kept quite small, which reduces hardware costs, while highly accurate DOA estimation accuracy can be achieved. Therefore, we derive a very simple expression of the 2D...
As a comparatively new developed stochastic method particle swarm optimization (PSO), it is widely applied to various kinds of optimization problems especially of nonlinear, non-differentiable or non-convex types. In this paper, a modified guaranteed converged particle swarm algorithm (MGCPSO) is proposed in this paper, which is inspired by guaranteed converged particle swarm algorithm (GCPSO) proposed...
Particle Swarm Optimization (PSO) is a new paradigm of Swarm Intelligence which proposes that the co-operation of individuals promotes the evolution of the swarm. Recently, a modified Particle Swarm Optimizer (MLPSO) has been succeeded in solving truss topological optimization problems with continuous design variable and competitive results were obtained. Since most of structural problems involve...
Based on the principle of thermodynamics and heat and mass transfer, a set of mathematical models on solar water heating system are founded. Solar water heating system (SWHS) is simulated by TRNSYS software to investigate whole-year transient performance of system. Different factors, such as collector area, tank volume, load temperature, shelter, daily hot water consumption pattern, are analyzed in...
This paper focuses on the estimation of the direction-of-arrival (DOA) of signals impinging on a linear sensor array. In contrast to conventional arrays, where the number of channels equals the number of sensors, we use tapered subarray structures. For this type of array, each channel consists of several sensor elements with different amplitude tapering. By this means, a pre-focussing can be achieved...
One-dimensional cutting-stock is one of the classic NP-hard problems in combinatorial optimization. It is widely applied in engineering technology and industrial production. In this paper, an improved ant colony optimization is proposed based on the optimized one-dimensional cutting-stock model. Aiming at the specific characteristics of the problem, a series of improvement strategies are proposed,...
In LFMCW (linear frequency modulated continuous wave) radar, there is a nonzero probability for mismatches to occur under certain conditions. This probability strongly depends on the modulation employed as well as on the distribution of targets in the radar's field of view, i.e. the application of the radar sensor. Hence to reduce mismatches in a given application, an effective approach is to carefully...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.