scispace - formally typeset
Search or ask a question

Showing papers in "Applied Computing and Informatics in 2020"


Journal ArticleDOI
TL;DR: To classify the patients into diabetic and non-diabetic the authors have developed and analyzed five different predictive models using R data manipulation tool and used supervised machine learning algorithms namely linear kernel support vector machine (SVM-linear), radial basis function (RBF) kernel supportvector machine, k-nearest neighbour (k-NN), artificial neural network (ANN) and multifactor dimensionality reduction (MDR).

154 citations


Journal ArticleDOI
TL;DR: A deep learning approach for aspect extraction from text and analysis of users sentiment corresponding to the aspect is proposed and a seven layer deep convolutional neural network is used to tag each aspect in the opinionated sentences.

85 citations


Journal ArticleDOI
TL;DR: An aspect-based sentiment analysis hybrid approach that integrates domain lexicons and rules to analyse the entities smart apps reviews and classify the corresponding sentiments has achieved higher accuracy than other SVM models.

78 citations


Journal ArticleDOI
TL;DR: A hybrid model combining machine-learning methods with statistical method outperformed a hybrid model that only combines machine- learning models without statistical method for more accurate prediction of future solar power generation from renewable energy plants.

78 citations


Journal ArticleDOI
TL;DR: This study provides a review of the traditional feature-selection algorithms and then scrutinizes the current algorithms that use streaming feature selection to determine their strengths and weaknesses and sheds light on the ongoing challenges in big-data research.

53 citations


Journal ArticleDOI
TL;DR: This paper focused on security and privacy considerations by analyzing some potential challenges and risks that need to be resolved in the CoT by investigating the architecture and existing applications.

47 citations


Journal ArticleDOI
TL;DR: The aim of this study is to experiment the possibility of fine-tuning CNNs for underwater imagery analysis, the opportunity of using different datasets for pre-training models, and the possibility to design an ensemble using the same architecture with small variations in the training procedure.

46 citations


Journal ArticleDOI
TL;DR: This paper adopted the Fb-Prophet ML model because it can predict the epidemic trend and derive an epidemic curve and highlighted that by late September, the estimated outbreak can reach 7.22 million cases in the USA, Brazil, India and Russia, respectively.

33 citations


Journal ArticleDOI
TL;DR: An audio encryption algorithm based on permutation of audio samples using discrete modified Henon map followed by substitution operation with keystream generated from the modified Lorenz-Hyperchaotic system is introduced.

33 citations


Journal ArticleDOI
TL;DR: Experimental tests show that tree-based models particularly Random Forest performed better in terms of accuracy, precision and recall metrics when compared to probabilistic and statistical models.

32 citations


Journal ArticleDOI
TL;DR: Three regression based machine learning techniques were developed to predict machining force, cutting power and cutting pressure in the turning of AISI 1045, and a metaheuristic approach based on a neural network algorithm was utilized to perform an efficient multi-objective optimization of process parameters for both cutting environment.

Journal ArticleDOI
TL;DR: The random forest model achieved the best accuracy classification, followed by the decision tree, and logistic regression shows the lowest classification accuracy.

Journal ArticleDOI
TL;DR: The proposed routing algorithms seek to prolong the lifetime of sensor nodes in the relatively unexplored area of 3D WSNs by using chain-based routing technique PEGASIS as basis and employing genetic algorithm to build the chain instead of the greedy algorithm.

Journal ArticleDOI
TL;DR: The particle swarm optimization algorithm in conjuction with the fuzzy logic method is presented to achieve an optimized tuning of a proportional integral derivative controller (PID) in the DTC control loops of dual star induction motor (DSIM).

Journal ArticleDOI
TL;DR: A hybrid recommendation model is described that orchestrates and manages the available information and the specific recommendation needs, in order to determine the recommendation algorithms to be used.

Journal ArticleDOI
TL;DR: An enhanced model is proposed for ensuring lifelong spam classification model and the overall performance of the suggested model is contrasted against various other stream mining classification techniques to prove the success of the proposed model as a lifelong spam emails classification method.

Journal ArticleDOI
TL;DR: A novel feature selection method named as Feature Selection Based on Weighted Conditional Mutual Information (WCFR) is introduced and Experimental results on ten datasets show that the proposed method has higher classification accuracy.

Journal ArticleDOI
TL;DR: The developed mobile application could be effectively used as a tool to support elderly farmers to distribute their agricultural products in the one-stop service supply chain which emphasizes marketing, distribution and location-based logistics for elderly farmers and consumers with respect to Thailand 4.0.

Journal ArticleDOI
TL;DR: With the significance of Identification, Social Interaction Ties and Norm of Reciprocity on Trust, SNS developers are tasked to offer SNS features that proliferate the formation of these factors as well as shared interpretations.

Journal ArticleDOI
TL;DR: It is suggested that four stages need to be considered by starts-up for a successful market readiness, including the time of entry and overcoming market entry barriers, product attributes, product development process, and commercialization.

Journal ArticleDOI
TL;DR: End-to-end security of location and motion data from smartphone sensors are ensured using the proposed security scheme which ensures encryption and authentication of sensed data using Advanced Encryption Standard 256-Galois Counter Mode.

Journal ArticleDOI
TL;DR: A Distributed Data Predictive Model (DDPM) was proposed to extend the network lifetime by decreasing the consumption in the energy of sensor nodes and upgraded the performance of the sensory network by about 19.5%.

Journal ArticleDOI
TL;DR: The results demonstrated that follow-up of strict measures such that country lockdown along with high testing is making Italy practically a pandemic-free country.

Journal ArticleDOI
TL;DR: A fresh call is made for more attention to be paid to change as part of preparatory measures towards the adoption of HIT in Ghana using the five cardinal approaches identified as a guide.

Journal ArticleDOI
TL;DR: This work presents a novel approach by considering teaching learning based optimization (TLBO) and radial basis function neural networks (RBFNs) for building a classifier for the databases with missing values and irrelevant features.

Journal ArticleDOI
TL;DR: This paper presents, in this paper, the resolution of conflict at the instance level into two stages: references reconciliation and data fusion, and defines first the conflicts classification, the strategies for dealing with conflicts and the implementing conflict management strategies.

Journal ArticleDOI
TL;DR: In this article, the authors used Frei-Chen bases technique and Modified Run Length Encoding (RLE) to compress images, where the average subspace is applied at the first stage in which the blocks with the highest energy are replaced by a single value that represents the average value of the pixels in the corresponding block.

Journal ArticleDOI
TL;DR: The proposed hybrid GA-ACO approach (hAG) runs both GA and ACO simultaneously, and the better performing one is selected as the primary algorithm in the hybrid approach.

Journal ArticleDOI
TL;DR: This article presents the experience and the results of collecting, analyzing, and classifying Twitter data from affiliated members of ISIS, as well as sympathizers, and used artificial intelligence and machine learning classification algorithms to categorize the tweets, as terror-related, generic religious, and unrelated.

Journal ArticleDOI
TL;DR: This paper attempts to adapt COSMIC Function Point and Unified Modeling Language (UML) techniques to estimate the size of a given mobile application to get the functional size of mobile application using Mobile Complex Factors as an input.