The convolutional neural networks (CNN) are among the most utilized neural networks in various applications, including deep learning. In recent years, the continuing extension of CNN into increasingly complicated domains has made its training process more difficult. Thus, researchers adopted optimized hybrid algorithms to address this problem. In this work, a novel chaotic black hole algorithm-based approach was created for the training of CNN to optimize its performance via avoidance of entrapment in the local minima. The logistic chaotic map was used to initialize the population instead of using the uniform distribution. The proposed training algorithm was developed based on a specific benchmark problem for optical character recognition applications; the proposed method was evaluated for performance in terms of computational accuracy, convergence analysis, and cost.
In this study, doped thin cadmium peroxide films were prepared by pulsed laser deposition with different doping concentrations of aluminium of 0.0, 0.1, 0.3, and 0.5 wt.% for CdO2(1-X)Al(X) and thicknesses in the range of 200 nm. XRD patterns suggest the presence of cubic CdO2 and the texture factor confirms that the (111) plane was the preferential growth plane, where the texture factor and the grain size decreased from 2.02 to 9.75 nm, respectively, in the pure sample to 1.88 and 5.65 nm, respectively, at a concentration of 0.5 wt%. For the predominant growth plane, the deviation of the diffraction angle Δθ and interplanar distance Δd from the standard magnitudes was 2.774° and 0.318 Å, respectively, for the pure sample decreased to
... Show MoreIn this research, the study effect of irradiation on structural and optical properties of thin film (CdO) by spray pyrolysis method, which deposited on glasses substrates at a thickness of (350±20)nm , The flow rate of solution was 5 ml/min and the substrate temperature was held constant at 400˚C.The investigation of (XRD) indicates that the (CdO) films are polycrystalline and type of cubic. The results of the measuring of each sample from grain size, micro strain, dislocation density and number of crystals the grain size decreasing after irradiation with gamma ray from(27.41, 26.29 ,23.63)nm . The absorbance and transmittance spectra have been recorded in the wavelength range (300-1100) nm in order to study the optical properties. the op
... Show MoreThis work describes, selenium (Se) films were deposited on clean glass substrates by dc planar magnetron sputtering technique.The dependence of sputtering deposition rate of Se film deposited on pressure and DC power has been studied. The optimum argon pressure has range (4x10-1 -8x10-2 )mbar. The optical properties such as absorption coefficient (α) was determined using the absorbance and transmission measurement from UnicoUV-2102 PC spectrophotometer, at normal incidence of light in the wavelength range of 200-850 nm. And also we calculated optical constants(refractive index (n), dielectric constant (εi,r), and Extinction coefficient (κ) for selenium films.
Cadmium sulfide (CdS) nanocrystalline thin films have been prepared by chemical bath deposition (CBD) technique on commercial glass substrates at 70ºC temperature. Cadmium chloride (CdCl2) as a source of cadmium (Cd), thiourea (CS(NH2)2) as a source of sulfur and ammonia solution (NH4OH) were added to maintain the pH value of the solution at 10. The characterization of thin films was carried out through the structural and optical properties by X-ray diffraction (XRD) and UV-VIS spectroscopy. A UV-VIS optical spectroscopy study was carried out to determine the band gap of the nanocrystalline CdS thin film and it showed a blue shift with respect to the bulk value (from 3.9 - 2.4eV). In present w
... Show MoreIn this work, Titanium oxide thin films doped with different concentration of CuO (0,5,10, 15,20) %wt were prepared by pulse laser deposition(PLD) technique on glass substrates at room temperature with constant deposition parameter such as : pulse (Nd:YAG), laser with λ=1064 nm, constant energy 800 mJ , repetition rate 6 Hz and No. of pulse (500). The structure , optical and electrical properties were studied . The results of X-ray diffraction( XRD) confirmed that the film grown by this technique have good crystalline tetragonal mixed anatase and rutile phase structure, The preferred orientation was along (110) direction for Rutile phase. The optical properties of the films were studied by UV-VIS spectrum in the range of (360-1100)
... Show MoreIn the last few years, the literature conferred a great interest in studying the feasibility of using memristive devices for computing. Memristive devices are important in structure, dynamics, as well as functionalities of artificial neural networks (ANNs) because of their resemblance to biological learning in synapses and neurons regarding switching characteristics of their resistance. Memristive architecture consists of a number of metastable switches (MSSs). Although the literature covered a variety of memristive applications for general purpose computations, the effect of low or high conductance of each MSS was unclear. This paper focuses on finding a potential criterion to calculate the conductance of each MMS rather t
... Show MoreSoftware-defined networks (SDN) have a centralized control architecture that makes them a tempting target for cyber attackers. One of the major threats is distributed denial of service (DDoS) attacks. It aims to exhaust network resources to make its services unavailable to legitimate users. DDoS attack detection based on machine learning algorithms is considered one of the most used techniques in SDN security. In this paper, four machine learning techniques (Random Forest, K-nearest neighbors, Naive Bayes, and Logistic Regression) have been tested to detect DDoS attacks. Also, a mitigation technique has been used to eliminate the attack effect on SDN. RF and KNN were selected because of their high accuracy results. Three types of ne
... Show MoreBP algorithm is the most widely used supervised training algorithms for multi-layered feedforward neural net works. However, BP takes long time to converge and quite sensitive to the initial weights of a network. In this paper, a modified cuckoo search algorithm is used to get the optimal set of initial weights that will be used by BP algorithm. And changing the value of BP learning rate to improve the error convergence. The performance of the proposed hybrid algorithm is compared with the stan dard BP using simple data sets. The simulation result show that the proposed algorithm has improved the BP training in terms of quick convergence of the solution depending on the slope of the error graph.