A general insight into the effect of neuron structure on classification

This paper gives a general insight into how the neuron structure in a multilayer perceptron (MLP) can affect the ability of neurons to deal with classification. Most of the common neuron structures are based on monotonic activation functions and linear input mappings. In comparison, the proposed neuron structure utilizes a nonmonotonic activation function and/or a nonlinear input mapping to increase the power of a neuron. An MLP of these high power neurons usually requires a less number of hidden nodes than conventional MLP for solving classification problems. The fewer number of neurons is equivalent to the smaller number of network weights that must be optimally determined by a learning algorithm. The performance of learning algorithm is usually improved by reducing the number of weights, i.e., the dimension of the search space. This usually helps the learning algorithm to escape local optimums, and also, the convergence speed of the algorithm is increased regardless of which algorithm is used for learning. Several 2-dimensional examples are provided manually to visualize how the number of neurons can be reduced by choosing an appropriate neuron structure. Moreover, to show the efficiency of the proposed scheme in solving real-world classification problems, the Iris data classification problem is solved using an MLP whose neurons are equipped by nonmonotonic activation functions, and the result is compared with two well-known monotonic activation functions.     

A dual‐broadband circularly polarized halved falcate‐shape printed monopole antenna

A halved falcate‐shape dual‐broadband circularly polarized printed monopole antenna is proposed. To generate the equal amplitude orthogonal modes, two halved falcate‐shaped antenna are used. Also, to provide the 90° phase difference between the two modes, three stubs are used in the ground plane of the antenna. The proposed antenna provides 22.6 (1.36–1.72 GHz) and 44.4% (5.25–8.25 GHz) 3 dB axial ratio bandwidth over the lower and upper bands, respectively. By adjusting the parameters of the antenna, the lower and upper band center frequencies can be tuned individually. The proposed antenna is fabricated, and results are compared with those of the simulation. © 2011 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2011.     

Observer‐based adaptive optimal output containment control problem of linear heterogeneous Multiagent systems with relative output measurements

This paper develops a relative output‐feedback–based solution to the containment control of linear heterogeneous multiagent systems. A distributed optimal control protocol is presented for the followers to not only assure that their outputs fall into the convex hull of the leaders' output but also optimizes their transient performance. The proposed optimal solution is composed of a feedback part, depending of the followers' state, and a feed‐forward part, depending on the convex hull of the leaders' state. To comply with most real‐world applications, the feedback and feed‐forward states are assumed to be unavailable and are estimated using two distributed observers. That is, a distributed observer is designed to measure each agent's states using only its relative output measurements and the information that it receives by its neighbors. Another adaptive distributed observer is designed, which uses exchange of information between followers over a communication network to estimate the convex hull of the leaders' state. The proposed observer relaxes the restrictive requirement of having access to the complete knowledge of the leaders' dynamics by all the followers. An off‐policy reinforcement learning algorithm on an actor‐critic structure is next developed to solve the optimal containment control problem online, using relative output measurements and without requiring the leaders' dynamics. Finally, the theoretical results are verified by numerical simulations.     

Fabrication and characterization of robust hydrophobic lotus leaf-like surface on Si3N4 porous membrane via polymer-derived SiNCO inorganic nanoparticle modification

Robust hydrophobic surface was produced by modifying the surface of porous Si₃N₄ membrane, via aminolysis and pyrolysis process, with organosilane-derived inorganic SiNCO nanoparticles, which are tightly adhered to the Si₃N₄ grains. The resultant material had a high water contact angle of 142°, attributed to -Si-CH₃ surface terminal groups and a lotus leaf-like hierarchical structure of the nanoparticles, which had a frame structure with Si-N and Si-O covalent bonds in their bulk. The hydrophobic behavior remained practically unchanged after exposure of the produced membranes to aqueous solutions of humic acid, HCl and NaOH, to benzene, as well as to stirring abrasive slurry with SiC particles, and after exposure at high temperatures, up to 500?°C, to air. The inorganic membrane can be considered for use in a broad range of applications which require robust hydrophobic surfaces.     

Toward a better understanding of multifunctional cement-based materials: The impact of graphite nanoplatelets (GNPs)

The impact of graphite nanoplatelets (GNPs) on the physical and mechanical properties of cementitious nanocomposites was investigated. A market-available premixed mortar was modified with 0.01% by weight of cement of commercial GNPs characterized by two distinctively different aspect ratios.The rheological behavior of the GNP-modified fresh admixtures was thoroughly evaluated. Hardened cementitious nanocomposites were investigated in terms of density, microstructure (Scanning Electron Microscopy, SEM and micro–Computed Tomography, μ-CT), mechanical properties (three-point bending and compression tests), and physical properties (electrochemical impedance spectroscopy, EIS and thermal conductivity measurements). At 28 days, all GNP-modified mortars showed about 12% increased density. Mortars reinforced with high aspect ratio GNPs exhibited the highest compressive and flexural strength: about 14% and 4% improvements compared to control sample, respectively. Conversely, low aspect ratio GNPs led to cementitious nanocomposites characterized by 36% decreased electrical resistivity combined with 60% increased thermal conductivity with respect to the control sample.     

Short-term wind power forecasting using ridgelet neural network

Rapid growth of wind power generation in many countries around the world in recent years has highlighted the importance of wind power prediction. However, wind power is a complex signal for modeling and forecasting. Despite the performed research works in the area, more efficient wind power forecast methods are still demanded. In this paper, a new prediction strategy is proposed for this purpose. The forecast engine of the proposed strategy is a ridgelet neural network (RNN) owning ridge functions as the activation functions of its hidden nodes. Moreover, a new differential evolution algorithm with novel crossover operator and selection mechanism is presented to train the RNN. The efficiency of the proposed prediction strategy is shown for forecasting of both wind power output of wind farms and aggregated wind generation of power systems.     

Recent Developments for Prediction of Power of Aromatic and Non‐Aromatic Energetic Materials along with a Novel Computer Code for Prediction of Their Power

The explosive power or strength of an energetic material shows its capacity for doing useful work. This work reviews recent developments for prediction of power of energetic compounds. A new user‐friendly computer code is also introduced to predict the relative power of a desired energetic compound as compared to 2,4,6‐trinitrotoluene (TNT). It is based on the best available methods, which can be used for different types of energetic compounds including nitroaromatics, nitroaliphatics, nitramines, and nitrate esters. The computed relative powers are consistent with the measured data for some new materials containing complex molecular structures.