Showing papers in "Computers & Electrical Engineering in 2018"

TL;DR: This paper proposes a three layer patient-driven Healthcare architecture for real-time data collection, processing and transmission that gives insights to the end users for the applicability of fog devices and gateways in Healthcare 4.0 environment for current and future applications.

TL;DR: This paper brings convolutional neural networks power to DR detection, which includes 3 major difficult challenges: classification, segmentation and detection, and adopts AlexNet, VggNet, GoogleNet, ResNet, and analyze how well these models do with the DR image classification.

TL;DR: The security requirements are reviewed, descriptions of several severe cyber-attacks are provided, and a cyber-security strategy to detect and counter these attacks are proposed.

TL;DR: This paper will focus and explore the security challenges that are faced by cloud entities, focusing on the crypto-cloud that constitutes of different Communication, Computation, and Service Level Agreement.

TL;DR: The experimental result reveals that the proposed nature-inspired algorithm finds an optimal subset of features, maximizing the accuracy and minimizing a number of features selected and is more stable.

TL;DR: DAMF could be successfully removed SAP noise at all densities and was compared with other methods by using Peak Signal to Noise Ratio (PSNR) and Structural Similarity (SSIM) for some images such as Cameraman and Lena.

TL;DR: This article proposes a grey wolf optimization based clustering algorithm for VANETs that replicates the social behaviour and hunting mechanism of grey wolfs for creating efficient clusters, and provides optimal outcomes that lead to a robust routing protocol for clustering of VANets.

TL;DR: This paper introduces three layers of IoT, i.e., perception layer, network layer and application layer, then corresponding security problems of three layers are introduced and a high-level security management scheme based on blockchain is proposed for different IoT devices in the full life cycle.

TL;DR: This paper reviews the most relevant Fog-enabled CoT system models and proposes an energy-aware allocation strategy for placing application modules (tasks) on Fog devices, and the performance of the proposed strategy is evaluated in comparison with the default allocation and Cloud-only policies, using the iFogSim simulator.

TL;DR: An effort to automate characterization of breast cancer from ultrasound images using multi-fractal dimensions and backpropagation neural networks is presented.

TL;DR: The result shows that MOPSO yields positive performance and the proposed system is recommended as the best substitute to improve electric energy utilization in remote areas.

TL;DR: A new compromise algorithm for multi-objective transportation problem (MO-TP) is developed, which is inspired by Zimmermann's fuzzy programming and the neutrosophic set terminology, and is superior to fuzzy and different approaches.

TL;DR: A hybrid algorithm using the Taguchi parameter design method was developed based on an improved Max-Min Ant System to solve well-known test problems and large-sized instances and Computational results show high efficiency for the proposed algorithm.

TL;DR: A machine learning based method to silently and continuously profile the driver by analyzing built-in vehicle sensors is proposed, finding the most relevant features able to discriminate the car owner by an impostor.

TL;DR: An adaptive decision based kriging interpolation technique for the removal of high density salt and pepper noise in images is proposed and was found to exhibit good of quantitative evaluation and visual quality.

TL;DR: The experimental results demonstrate that change metrics have a positive impact on the performance of fault prediction models, and high-performance models can be built with several change metrics.

TL;DR: The efficacy of proposed DA over different reported algorithms is established in terms of convergence rate, minimum fitness value and dynamic performance of the system, and the robustness of the 3-DOF PID-controller is ascertained.

TL;DR: This study shows that Nikooghadam etal's proposed authentication and key agreement protocol is susceptible to insider, replay, and password-guessing attacks, and proposes a more secure authentication system that can withstand discrete attacks.

TL;DR: A scalable SIoV architecture based on Restful web technology is presented, emphasizing the importance of web technology to meet the required interoperability to support the composition of numerous services.

TL;DR: A metaheuristic procedure based on an Adaptive Large Neighborhood Search (ALNS) algorithm is proposed to solve the Dynamic Vehicle Routing Problem (DVRP) with limited vehicles and hard-time windows and shows that the present approach can solve real-time problems within a very short time while improving the quality of the solution.

TL;DR: The maximum entropy model (Maxent) was adopted as the base classifier in the transfer learning model and experimental results showed that good classification performance was obtained based on the transferLearning model.

TL;DR: A hybrid approach of improved binary particle swarm optimization and shuffled frog leaping algorithm are proposed to decrease high dimensionality of the feature set and to select optimized feature subsets to help customers in ignoring fake reviews and enhances the classification performance by providing trustworthy reviews.

TL;DR: From the simulations carried out in this work, it is observed that the proposed routing algorithm provides better performance in terms of residual energy and network lifetime when it is compared with other existing grid and cluster based routing protocols.

TL;DR: A line voltage stability index ( LVSI) has been proposed to assess voltage stability state and stress condition of lines and may be used to estimate the stability margin of the power system in terms of mega volt amp (MVA).

TL;DR: A novel algorithm which leverages both flat and hierarchical routing schemes for maximizing energy efficiency is proposed, and results indicate that it outperforms other protocols for network characteristics like energy minimization and scalability.

TL;DR: An electroencephalogram (EEG) feature extraction method that leverages empirical mode decomposition and Approximation Entropy is proposed that achieves an improved accuracy that is highly competitive to the state-of-the-art methods.

TL;DR: An Enhanced Hybrid Semantic Algorithm that computes the semantic similarity and establishes dynamic OntoPath for easing the web image recommendation has been proposed and focuses on generating unique classes of images as an initial recommendation set.

TL;DR: A novel method for secure data prediction in WSN has been proposed by using a Time Series Trust Model (TSTM) based on Toeplitz matrix and a Trust based Auto Regressive (TAR) process.

TL;DR: This paper analyzes the performance of Kubernetes achieved through a Petri net-based performance model, and can be exploited for supporting capacity planning and designing Kubernets-based elastic applications.

TL;DR: A combination of two swarming algorithms is proposed called the artificial bee colony with firefly (ABC-FF) algorithm, which operates on control variables, such as load reactance and voltage and transformer tap settings, which are varied to achieve optimum results.