Support vector machines (SVMs) are supervised learning models that analyze data for classification or regression. For classification, SVM is widely used by selecting an optimal hyperplane that separates two classes. SVM has very good accuracy and extremally robust comparing with some other classification methods such as logistics linear regression, random forest, k-nearest neighbor and naïve model. However, working with large datasets can cause many problems such as time-consuming and inefficient results. In this paper, the SVM has been modified by using a stochastic Gradient descent process. The modified method, stochastic gradient descent SVM (SGD-SVM), checked by using two simulation datasets. Since the classification of different ca

Wireless Multimedia Sensor Networks (WMSNs) are a type of sensor network that contains sensor nodes equipped with cameras, microphones; therefore the WMSNS are able to   produce multimedia data such as video and audio streams, still images, and scalar data from the surrounding environment. Most multimedia applications typically produce huge volumes of data, this leads to congestion. To address this challenge, This paper proposes Modify Spike Neural Network control for Traffic Load Parameter with Exponential Weight of Priority Based Rate Control algorithm (MSNTLP with EWBPRC). The Modify Spike Neural Network controller (MSNC) can calculate the appropriate traffi

JM Karhoot, AA Noaimi, WF Ahmad, The Iraqi Postgraduate Medical Journal, 2012 - Cited by 7

Objectives: To determined the levels of lipid profile (TC, TG, HDL-c, LDL-C, VLDL) in diabetic and diabetic neuropathy patients and compare the results with control group. Also, to compare Atherogenic Index of Plasma (AIP) levels in these groups that may be predict prone of patients to cardiovascular disease. Methodology: Ninety subjects were enrolled in this study with aged ranged (40-65) years and BMI with (30-35) Kg/m2 that divided into three groups as follows: group one (G1) consists of 30 healthy individuals as a control group, group two (G2) consists of 30 patients with diabetes and group three (G3) consists of 30 patients with diabetes and neuropathy as complication. Electrochemical Skin Conductance (Feet Mean), Electrochemic

A new Differential Evolution (ARDE) algorithm is introduced that automatically adapt a repository of DE strategies and parameters adaptation schemes of the mutation factor and the crossover rate to avoid the problems of stagnation and make DE responds to a wide range of function characteristics at different stages of the evolution. ARDE algorithm makes use of JADE strategy and the MDE_pBX parameters adaptive schemes as frameworks. Then a new adaptive procedure called adaptive repository (AR) has been developed to select the appropriate combinations of the JADE strategies and the parameter control schemes of the MDE_pBX to generate the next population based on their fitness values. Experimental results have been presented to confirm the reli

Low conversion copolymerization of N-vinyl-2-pyrrolidon M.W = (111.14) VP (monomer-1) has been conducted with acrylic acid AA and methymethacrylate MMA in ethanol at 70ºC , using Benzoyl peroxide BPO as initiator . The copolymer composition has been determined by elemental analysis. The monomer reactivity ratios have been calculated by the Kelen-Tudos and Finman-Ross graphical procedures . The derived reactivity ratios (r1 , r2 ) are : (0.51 , 4.85) for (VP / AA ) systems and (0.34 , 7.58) for (VP , MMA) systems , and found the reactivity ratios of the monomer AA , MMA is mor than the monomer VP in the copolymerization of (VP / AA) and (VP /MMA) systems respectly . The reactivity ratios values were used for microstructures calculation.

            The organation ⁄monomer N-naphthylacrylamide (NAA) was prepared; subsequently the synthesized monomer was successfully copolymerized with acrylicacid (AA) and methylacrylate (MA) by free radical technique using dry benzene as solvent and benzoyl peroxide (BPO) as initiator. The overall conversion was kept low (≤ 10% wt/wt) for all studies copolymers samples. The synthesized monomer and copolymers were characterized using Fourier transform infrared spectroscopy (FT-IR), and their thermal properties were studied by DSC and TGA. The copolymers compositions were determined by elemental analysis. Kelen-Tudes and Finmman-Ross graphical procedures were employed to determine

            The organation ⁄monomer N-naphthylacrylamide (NAA) was prepared; subsequently the synthesized monomer was successfully copolymerized with acrylicacid (AA) and methylacrylate (MA) by free radical technique using dry benzene as solvent and benzoyl peroxide (BPO) as initiator. The overall conversion was kept low (≤ 10% wt/wt) for all studies copolymers samples. The synthesized monomer and copolymers were characterized using Fourier transform infrared spectroscopy (FT-IR), and their thermal properties were studied by DSC and TGA. The copolymers compositions were determined by elemental analysis. Kelen-Tudes and Finmman-Ross graphical procedures were employed to determine the monomers reactivity ratios. The der