Showing papers in "Future Generation Computer Systems in 2020"

TL;DR: The proposed slime mould algorithm has several new features with a unique mathematical model that uses adaptive weights to simulate the process of producing positive and negative feedback of the propagation wave of slime mould based on bio-oscillator to form the optimal path for connecting food with excellent exploratory ability and exploitation propensity.

TL;DR: This paper first introduces blockchains and smart contracts, then presents the challenges in smart contracts as well as recent technical advances, and gives a categorization of smart contract applications.

TL;DR: A novel framework called HealthFog is proposed for integrating ensemble deep learning in Edge computing devices and deployed it for a real-life application of automatic Heart Disease analysis.

TL;DR: A Blockchain-enabled Intelligent IoT Architecture with Artificial Intelligence that provides an efficient way of converging blockchain and AI for IoT with current state-of-the-art techniques and applications is proposed.

TL;DR: This paper compares security issues between IoT and traditional network, and discusses opening security issues of IoT, and analyzes the cross-layer heterogeneous integration issues and security issues in detail.

TL;DR: The first powerful variant of the Harris hawks optimization (HHO) integrates chaos strategy, topological multi-population strategy, and differential evolution (DE) strategy and is compared with a range of other methods.

TL;DR: A new framework model and a hybrid algorithm to solve the problem of selecting an effective ML algorithm for cyber attacks detection system for IoT security and results show that the proposed model with the algorithm is effective for the selection ML algorithm out of numbers of ML algorithms.

TL;DR: A comprehensive survey of Ponzi schemes on Ethereum, analysing their behaviour and their impact from various viewpoints shows that they still make users lose money, but at least are guaranteed to execute "correctly".

TL;DR: This work considers Bayesian network classifiers to perform sentiment analysis on two datasets in Spanish: the 2010 Chilean earthquake and the 2017 Catalan independence referendum, and adopts a Bayes factor approach, yielding more realistic networks.

TL;DR: This paper presents D I C E T, a transformer-based method for sentiment analysis that encodes representation from a transformer and applies deep intelligent contextual embedding to enhance the quality of tweets by removing noise while taking word sentiments, polysemy, syntax, and semantic knowledge into account.

TL;DR: This survey, an extension of the previous work, reports most relevant contemporary contributions in the field, aiming at assessing suitability of the ABC paradigm for the (current and future) IoT development.

TL;DR: It is indicated that medical institutions need to pay attention to data privacy protection and grasp the use of digital medical data to provide decision support for subsequent medical data analysis.

TL;DR: Efficient Lightweight integrated Blockchain (ELIB) model is developed to meet necessitates of IoT and shows maximum performance under several evaluation parameters, and is deployed in a smart home environment.

TL;DR: A cervical cancer cell detection and classification system based on convolutional neural networks (CNNs) and an extreme learning machine (ELM)-based classifier that achieved 99.5% accuracy in the detection problem and 91.2% in the classification problem.

TL;DR: Experimental results validate the efficiency of the proposed method in accurate detection of faces compared to state-of-the-art face detection and recognition methods, and verify its effectiveness for enhancing law-enforcement services in smart cities.

TL;DR: This work introduces a customized implementation of the genetic algorithm (GA) as a heuristic approach to schedule the IoT requests to achieve the objective of minimizing the overall latency.

TL;DR: There is a need to design an efficient intrusion detection/prevention system that cooperates with dynamic shadow honeypots and enhance the immunity of IoMT against cyber-attacks, and this paper proposes a security solution, which is divided into five different layers to detect and prevent attacks.

TL;DR: The blockchain-based integrity protection framework is built by the virtual machine proxy model, and the unique hash value corresponding to the file generated by the Merkel hash tree is used to monitor the data change by means of the smart contract on the blockchain.

TL;DR: Deep reinforcement learning (DRL) is proposed to solve the offloading problem of multiple service nodes for the cluster and multiple dependencies for mobile tasks in large-scale heterogeneous MEC and the improved IDRQN algorithm has better performance in energy consumption, load balancing, latency and average execution time than other algorithms.

TL;DR: Deep learning is used to classify Spam and Not-Spam text messages using Convolutional Neural Network and Long Short-Term Memory models, which achieved a remarkable accuracy of 99.44% on a benchmark dataset.

TL;DR: The experimental results indicate that this fog-based hierarchical structure performs well in saving network energy, detecting malicious nodes rapidly and recovering misjudgment nodes in an acceptable delay and the reliability of edge nodes is well guaranteed by data analyses in the fog layer.

TL;DR: A reputation scheme is proposed to encourage normal nodes and abnormal nodes both to participate in network collaboration in a good way and can make PoX protocols achieve better consensus states, which would benefit the applications of IIoT with blockchain.

TL;DR: The information feedback models are introduced to improve the ability of NSGA-III to solve large-scale optimization problems and are compared with four state-of-the-art algorithms on 9 test functions to show that the proposed algorithms are highly competitive on test problems.

TL;DR: A high level architecture of a big data platform that can support the creation, development, maintenance and exploitation of smart energy services through the utilisation of cross-domain data is proposed.

TL;DR: The experimental results indicate that the performance of the proposed algorithms is better compared with existing algorithms in terms of overall data processing time, instance cost and network delay, with the increasing number of application submissions.

TL;DR: Simulation experiments have confirmed that implementing a M/M/S queueing system in a cloud can help to reduce the average task response time, and demonstrated that the QEEC approach is the most energy-efficient as compared to other task scheduling policies.

TL;DR: The empirical study based on real-world applications from Pegasus workflow management system reveals that the NN-DNSGA-II algorithm significantly outperforms the other alternatives in most cases with respect to metrics used for DMOPs with unknown true Pareto-optimal front, including the number of non-dominated solutions, Schott’s spacing and Hypervolume indicator.

TL;DR: Important questions on cardiovascular disease (CVD) diagnostics are presented, issues brought by the paradigm shift of AI vis-a-vis DL in CVD diagnostics, possible solutions to potential issues are provided, and the future of the related machine intelligence applications are visions.

TL;DR: An integrated non-dominated sorting genetic algorithm and local chaotic search based image encryption technique is proposed to tune the hyper-parameters of 5 D chaotic map (TFCM).

TL;DR: A self-adaptive resource allocation method that is actually a framework composed of feedback loops, each of which goes through the authors' designed iterative QoS prediction model and PSO-based runtime decision algorithm to improve the predicted QoS value in iterations towards the best one.