Image classification is the process of finding common features in images from various classes and applying them to categorize and label them. The main problem of the image classification process is the abundance of images, the high complexity of the data, and the shortage of labeled data, presenting the key obstacles in image classification. The cornerstone of image classification is evaluating the convolutional features retrieved from deep learning models and training them with machine learning classifiers. This study proposes a new approach of “hybrid learning” by combining deep learning with machine learning for image classification based on convolutional feature extraction using the VGG-16 deep learning model and seven class

Image classification is the process of finding common features in images from various classes and applying them to categorize and label them. The main problem of the image classification process is the abundance of images, the high complexity of the data, and the shortage of labeled data, presenting the key obstacles in image classification. The cornerstone of image classification is evaluating the convolutional features retrieved from deep learning models and training them with machine learning classifiers. This study proposes a new approach of “hybrid learning” by combining deep learning with machine learning for image classification based on convolutional feature extraction using the VGG-16 deep learning model and seven class

In this paper, two types of iron oxide nanomaterial (Fe3O4) and nanocomposite (T-Fe3O4) were created from the bio-waste mass of tangerine peel. These two materials were utilized for adsorption tests to remove cefixime (CFX) from an aqueous solution. Before the adsorption application, both adsorbents have been characterized by various characterizations such as XRD, FTIR, VSM, TEM, and FESEM. The mesoporous nano-crystalline structure of Fe3O4 and T-Fe3O4 nanocomposite with less than 100-nm diameter is confirmed. The adsorption of the obtained adsorbents was evaluated for CFX removal by adjusting several operation parameters to optimize the removal. The optimal conditions for CFX removal were found to be an initial concentration of 40 and 50 m

The objective of this study is to investigate the application of advanced oxidation processes (AOPs) in the treatment of wastewater contaminated with furfural. The AOPs investigated is the homogeneous photo-Fenton (UV/H₂O₂/Fe⁺²) process. The experiments were conducted by using cylindrical stainless steel batch photo-reactor. The influence of different variables: initial concentration of H₂O₂ (300-1300mg/L), Fe⁺²(20-70mg/L), pH(2-7) and initial concentration of furfural (50-300 mg/L) and their relationship with the mineralization efficiency were studied.

 Complete mineralization for the system UV/H₂O₂/Fe⁺² was achieved at: initi

Crude soybean peroxidase (SBP), isolated from soybean seed coats (hulls) at unusually low concentrations, catalyses the oxidative polymerisation of hazardous aqueous benzidine and its 3,3′-dichloro, 3,3′-dimethyl and 3,3′-dimethoxy derivatives in the presence of hydrogen peroxide. The optimum operating conditions for oxidation of 0·10 mM benzidine were investigated. At pH 5, the hydrogen peroxide-to-substrate concentration ratio was 1·5 and the minimum SBP concentration required to achieve at least 95% conversion of the benzidine in synthetic wastewater was 0·43 mU/ml. Progress curves were established for the conversion of the four substrates, and apparent first-order rate constants were derived. Enzyme-catalysed polym

In this study, phytoplankton density, chlorophyll-a, and selected physico- chemical parameters were investigated in Erbil wastewater channel. The surveys were carried out monthly from May 2003 to April 2004. Samplings were established on three sites from headwaters to the mouth. The results showed that pH was in alkaline side of neutrality, with significant differences (P<0.05) between sites 1 and 3. TSS concentration decreased from site 1 toward site 2 (mean value, 80.15 to 25.79 mg.l-1). A clear gradual increase in mineral content (TDS) observed from site one of the channel towards the mouthpart. Soluble reactive phosphate has a concentration maximum mean value reached 48.4 µg.l-1 which is recorded in site 2. A high positive relat

This paper describes a new proposed structure of the Proportional Integral Derivative (PID) controller based on modified Elman neural network for the DC-DC buck converter system which is used in battery operation of the portable devices. The Dolphin Echolocation Optimization (DEO) algorithm is considered as a perfect on-line tuning technique therefore, it was used for tuning and obtaining the parameters of the modified Elman neural-PID controller to avoid the local minimum problem during learning the proposed controller. Simulation results show that the best weight parameters of the proposed controller, which are taken from the DEO, lead to find the best action and unsaturated state that will stabilize the Buck converter system performan