Charging demand of Plug-in Electric Vehicles: Forecasting travel behavior based on a novel Rough Artificial Neural Network approach

Deep learning-based models have been very successful in achieving state-of-the-art results in many of the computer vision, speech recognition, and natural language processing tasks in the last few years. These models seem a natural fit for handling the ever-increasing scale of biometric recognition problems, from cellphone authentication to airport security systems. Deep learning-based models have increasingly been leveraged to improve the accuracy of different biometric recognition systems in recent years. In this work, we provide a comprehensive survey of more than 120 promising works on biometric recognition (including face, fingerprint, iris, palmprint, ear, voice, signature, and gait recognition), which deploy deep learning models, and show their strengths and potentials in different applications. For each biometric, we first introduce the available datasets that are widely used in the literature and their characteristics. We will then talk about several promising deep learning works developed for that biometric, and show their performance on popular public benchmarks. We will also discuss some of the main challenges while using these models for biometric recognition, and possible future directions to which research in this area is headed.

Biometric Recognition Using Deep Learning: A Survey

Cloud computing and internet of things (IOT) plays an important role in health care services especially in the prediction of diseases in smart cities. IOT devices (digital sensors and etc.) can be used to send big data onto chronic kidney diseases (CKD) to store it in the cloud computing. Therefore, these big data are used to increase the accuracy of prediction of CKD on cloud environment. The prediction of dangerous diseases such as CKD based cloud-IOT is considered a big problem that facing the stakeholders of health cares in smart cities. This paper focuses on predicting of CKD as an example of health care services on cloud computing environment. Cloud computing is supported patients to predict of CKD anywhere and anytime in smart cities. For that, this paper proposes a hybrid intelligent model for predicting CKD based cloud-IOT by using two intelligent techniques, which are linear regression (LR) and neural network (NN). LR is used to determine critical factors that influence on CKD. NN is used to predict of CKD. The results show that, the accuracy of hybrid intelligent model in predicting of CKD is 97.8%. In addition, a hybrid intelligent model is applied on windows azure as an example of a cloud computing environment to predict of CKD to support patients in smart cities. The proposed model is superior to most of the models referred to in the related works by 64%.

A Machine Learning Model for Predicting of Chronic Kidney Disease Based Internet of Things and Cloud Computing in Smart Cities



In most of the countries, students have to select a subject/stream in the secondary
education phase. Selection of subject/stream is crucial for students because further their career
proceeds according to their selection. Mostly subject/stream selection cannot be changed in the
further career. Inappropriate selection of subjects due to parental pressure, lack of information etc.
can lead to limited success in the selected stream. Guidance for subject/stream selection based on information
of successful scholars of their stream and information of students such as interest, family
background, previous education and other associated can enhance the success in career.



Data mining and machine learning based methods were developed on the above information.
Data from the different institutions and students of two different streams were used for training
and testing purposes. Different machine learning algorithms were used and methods with high
accuracy (86.72) were developed.



Developed methods can be extended and used for different subject/stream selection.


Machine Learning Based Support System for Students to Select Stream (Subject)

Building a secure routing protocol in WSN is not trivial process. Thee are two main types of security attacks against WSNs: active and passive. WSN as a new category of computer-based computing platforms and network structures is showing new applications in different areas such as environmental monitoring, health care and military applications. Although there are a lot of secure data transmission schemes designed for data aggregation and transmission over a network, the limited resources and the complex environment make it invisible to be used with WSNs. Furthermore, secure data transmission is a big challenging issue in WSNs especially for the application that uses image as its main data such as military applications. This problem is mainly related to the limited resources and data processing capabilities. This chapter introduces a secure data processing and transmission schema in WSN. The chapter reviewed and critically discussed the most prominent secure clustering routing algorithms that have been developed for WSNs. Then, we explained the guidelines and the steps towards building a simple solution for securing the dynamic cluster network while consuming as little energy as possible and is adapted to a low computing power. Moreover, four phased towards building a secure clustering algorithm for WSN are proposed. These phases are secure cluster head selection, secure cluster formation, secure data aggregation by the cluster head from its cluster nodes, and secure data routing to the base station. Also, the chapter proposes and applies an evaluation criteria for the existing secure clustering algorithms.

Secure Data Transmission in WSN: An Overview

This chapter introduces an offline signature recognition technique using rough neural network and rough set. Rough neural network tries to find better recognition performance to classify the input offline signature images. Rough sets have provided an array of tools which turned out to be especially adequate for conceptualization, organization, classification, and analysis of various types of data, when dealing with inexact, uncertain, or vague knowledge. Also, rough sets discover hidden pattern and regularities in application. This new hybrid technique achieves good results, since the short rough neural network algorithm is neglected by the grid features technique, and then the advantages of both techniques are integrated.

Amir Nabil

Papers

Hybrid Rough Neural Network Model for Signature Recognition