Activity recognition (AR) is a new interesting and challenging research area with many applications (e.g. healthcare, security, and event detection). Basically, activity recognition (e.g. identifying user’s physical activity) is more likely to be considered as a classification problem. In this paper, a combination of 7 classification methods is employed and experimented on accelerometer data collected via smartphones, and compared for best performance. The dataset is collected from 59 individuals who performed 6 different activities (i.e. walk, jog, sit, stand, upstairs, and downstairs). The total number of dataset instances is 5418 with 46 labeled features. The results show that the proposed method of ensemble boost-based classif

The increasing drinking water demand in many countries leads to an increase in the use of desalination plants, which are considered a great solution for water treatment processes. Reverse osmosis (RO) and electro-dialysis (ED) systems are the most popular membrane processes used to desalinate water at high salinity. Both systems work by separating the ionic contaminates and disposing of them as a brine solution, but ED uses electrical current as a driving force while RO uses osmotic pressure. A direct comparison of reverse osmosis and electro-dialysis systems is needed to highlight process development similarities and variances. This work aims to provide an overview of previous studies on reverse osmosis and electro-dial

Offline handwritten signature is a type of behavioral biometric-based on an image. Its problem is the accuracy of the verification because once an individual signs, he/she seldom signs the same signature. This is referred to as intra-user variability. This research aims to improve the recognition accuracy of the offline signature. The proposed method is presented by using both signature length normalization and histogram orientation gradient (HOG) for the reason of accuracy improving. In terms of verification, a deep-learning technique using a convolution neural network (CNN) is exploited for building the reference model for a future prediction. Experiments are conducted by utilizing 4,000 genuine as well as 2,000 skilled forged signatu

During the course of fixed orthodontic therapy, patients should be instructed to eat specific food stuffs and beverages in order to maintain good health for the dentition and supporting structures and prevent frequent attachment debonding that prolong the treatment duration. After searching and collecting articles from 1930 till July 2021, the current review was prepared to emphasize various types of foods that should be taken during the course of fixed orthodontic therapy and to explain the effect of various food stuffs and beverages on the growth and development of craniofacial structures, tooth surfaces, root resorption, tooth movement, retention and stability after orthodontic treatment and the effect on the components of fixed ortho

Background: The first and second choice for vascular access in patients with end stage renal disease (ESRD) is radio cephalic and brachio cephalic arteriovenous fistula (AVF).In patients with failed previous AVF e or poorly visualized or impalpable cephalic veins, the basilic vein can be mobilized and superficialized to create an AVF with the brachial artery.Objective: The aim of this study is to report our experience at the Vascular Surgery Department/ Surgical Specialty Hospital in brachio-basilic (BB) vascular access for hemodialysis.Methods: From January 2006 to December 2009, 31 patients with ESRD whose cephalic veins were thrombosed or impalpable or had previous unsuccessful vascular access procedures were referred to the Vascular

This study proposed a biometric-based digital signature scheme proposed for facial recognition. The scheme is designed and built to verify the person’s identity during a registration process and retrieve their public and private keys stored in the database. The RSA algorithm has been used as asymmetric encryption method to encrypt hashes generated for digital documents. It uses the hash function (SHA-256) to generate digital signatures. In this study, local binary patterns histograms (LBPH) were used for facial recognition. The facial recognition method was evaluated on ORL faces retrieved from the database of Cambridge University. From the analysis, the LBPH algorithm achieved 97.5% accuracy; the real-time testing was done on thirty subj

Numeral recognition is considered an essential preliminary step for optical character recognition, document understanding, and others. Although several handwritten numeral recognition algorithms have been proposed so far, achieving adequate recognition accuracy and execution time remain challenging to date. In particular, recognition accuracy depends on the features extraction mechanism. As such, a fast and robust numeral recognition method is essential, which meets the desired accuracy by extracting the features efficiently while maintaining fast implementation time. Furthermore, to date most of the existing studies are focused on evaluating their methods based on clean environments, thus limiting understanding of their potential a