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

Gingival crevicular fluid (GCF) may reflect the events associated with orthodontic tooth movement. Attempts have been conducted to identify biomarkers reflecting optimum orthodontic force, unwanted sequallea (i.e. root resorption) and accelerated tooth movement. The aim of the present study is to find out a standardized GCF collection, storage and total protein extraction method from apparently healthy gingival sites with orthodontics that is compatible with further high-throughput proteomics. Eighteen patients who required extractions of both maxillary first premolars were recruited in this study. These teeth were randomly assigned to either heavy (225g) or light force (25g), and their site specific GCF was collected at baseline and aft

In the image processing’s field and computer vision it’s important to represent the image by its information. Image information comes from the image’s features that extracted from it using feature detection/extraction techniques and features description. Features in computer vision define informative data. For human eye its perfect to extract information from raw image, but computer cannot recognize image information. This is why various feature extraction techniques have been presented and progressed rapidly. This paper presents a general overview of the feature extraction categories for image.

This work describes the development of new spectrophotometric techniques for 3-aminophenol assessment. The first technique involves using benzidine in an alkaline solution to convert 3-aminophenol into a colored complex. The produced complex has a red color with an absorbance of 462 nm. Between the concentration range 5–14 μg mL−1, Beer's law is obeyed with a correlation coefficient (R2) of 0.99781, a limit of detection (LOD) of 0.0423 μg mL−1, and a limit of quantification (LOQ) of 0.1411 μg mL−1. The recovery was between 87.2–95.43%, the relative standard deviation (%RSD) was 2.40–3.31% and the molar absorptivity was 3.545 × 103 L mol−1 cm−1. Secondly, cloud point extraction (CPE) was used to determ

Oil from Brassca campestris (local variety) was extracted with hexane using Soxhlet. The extracted oil was characterized and its antimicrobial activity was determined as well. The content of extracted oil was 40% with 0.5% of volatile oil .Oil was immiscible with polar solvent such as ethanol, acetone and water, while it was easily miscible with chloroform due to its hydrophobicity. The result of organoleptic tests revealed that the oil is clear yellow in color and odorless with acceptable taste. The oil was stable at 4 -25 C? for a month. Refractive index (RI) of oil was 1.4723 with density of 0.914, [both at 4-25 C?]. Boiling point 386 C?. Infra red spectroscopy (IR) indicated the presence of different chemical groups (C=C

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

The Purpose of this study is mainly to improve the competitive position of products economic units using technique target cost and method reverse engineering and through the application of technique and style on one of the public sector companies (general company for vegetable oils) which are important in the detection of prices accepted in the market for items similar products and processing the problem of high cost which attract managerial and technical leadership to the weakness that need to be improved through the introduction of new innovative solutions which make appropriate change to satisfy the needs of consumers in a cheaper way to affect the decisions of private customer to buy , especially of purchase private economic units to

A simple, environmental friendly and selective sample preparation technique employing porous membrane protected micro-solid phase extraction (μ-SPE) loaded with molecularly imprinted polymer (MIP) for the determination of ochratoxin A (OTA) is described. After the extraction, the analyte was desorbed using ultrasonication and was analyzed using high performance liquid chromatography. Under the optimized conditions, the detection limits of OTA for coffee, grape juice and urine were 0.06 ng g−1, 0.02 and 0.02 ng mL−1, respectively while the quantification limits were 0.19 ng g−1, 0.06 and 0.08 ng mL−1, respectively. The recoveries of OTA from coffee spiked at 1, 25 and 50 ng g−1, grape juice and urine samples at 1, 25 and 50 ng mL

Its well known that understanding human facial expressions is a key component in understanding emotions and finds broad applications in the field of human-computer interaction (HCI), has been a long-standing issue. In this paper, we shed light on the utilisation of a deep convolutional neural network (DCNN) for facial emotion recognition from videos using the TensorFlow machine-learning library from Google. This work was applied to ten emotions from the Amsterdam Dynamic Facial Expression Set-Bath Intensity Variations (ADFES-BIV) dataset and tested using two datasets.