Multi-Criteria Decision-Making Approach based on Neutrosophic Sets for Evaluating Sustainable Supplier Selection in the Industrial 4.0

Mahmoud; Mahmoud

doi:https://doi.org/10.54216/AJBOR.070204

Fusion: Practice and Applications | 2022

Opinion mining for Arabic dialect in social media data fusion platforms: A systematic review

The huge text generated on social media in Arabic, especially the Arabic dialect becomes more attractive for Natural Language Processing (NLP) to extract useful and structured information that benefits many domains. The more challenging point is that this content is mostly written in an Arabic dialect with a big data fusion challenge, and the problem with these dialects it has no written rules like Modern Standard Arabic (MSA) or traditional Arabic, and it is changing slowly but unexpectedly. One of the ways to benefit from this huge data fusion is opinion mining, so we introduce this systematic review for opinion mining from Arabic text dialect for the years from 2016 until 2019. We have found that Saudi, Egyptian, Algerian, and Jordanian are the most studied dialects even if it is still under development and need a bit more effort, nevertheless, dialects like Mauritanian, Yemeni, Libyan, and somalin have not been studied in this period. Many data fusion models that show a good result is the last four years have been discussed.

groups

Hani D. Hejazi mail -

Ahmed A. Khamees mail

link https://doi.org/10.54216/FPA.090101

Volume & Issue

Vol. Volume 9 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2022

Uniform and Nonuniform Filter Banks Design Based on Fusion Optimization

One of the important schemes for modern communication is Filter Bank Multi-Carrier with Offset Quadrature Amplitude Modulation (FBMC/ OQAM), as it provides better spectral efficiency with small inter-symbol and inter-carrier interference specially in data fusion platforms.  Unfortunately, the design of filter banks in FBMC is difficult and complex to achieve the requirement due to complexity of handling the data fusion issues.  This paper presents a proposed method to design a uniform and nonuniform filter banks using a data fusion optimization technique.  The design process represented as an objective function describes the amplitude in the stop band, and the goal is to minimize the objective function.  Different examples are provided to illustrate the efficiency of the proposed design method.

groups

Mohamed Saber mail -

Pushan K. Dutta mail

link https://doi.org/10.54216/FPA.090102

Volume & Issue

Vol. Volume 9 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2022

Blog Feedback Prediction based on Ensemble Machine Learning Regression Model: Towards Data Fusion Analysis

The last decade lead to an unbelievable growth of the importance of social media. Due to the huge amounts of documents appearing in social media, there is an enormous need for the automatic analysis of such documents. In this work, we proposed various regression models for the blog feedback prediction to be used in the data fusion environment. These models include decision tree regressor, MLP regressor, SVR, random forest regressor, and K-Neighbors regressor. The models are enhanced by average ensemble and ensemble using K-Neighbors regressor. The Blog Feedback dataset is used for training and evaluating the proposed models. The results show that there is a decrease in RMSE, MAE, MBE, R, R2, RRMSE, NSE, and WI when compared to the traditional methods.

groups

Hamzah A. Alsayadi mail -

El-Sayed M. El-Kenawy mail -

Abdelhameed Ibrahim mail -

Marwa M. Eid mail -

Abdelaziz A. Abdelhamid mail

link https://doi.org/10.54216/FPA.090103

Volume & Issue

Vol. Volume 9 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2022

Intelligent Data Fusion Model for Electrocardiogram Classification for Efficient Decision Making in the Healthcare Sector

Automatic classification of biomedical signals helps to perform decision making in the healthcare sector. Electrocardiogram (ECG) is a commonly employed 1-dimensional biomedical signal that can be utilized for the detection and classification of cardiovascular diseases. The recently developed deep learning (DL) models find useful for the detection and classification of ECG signals for cardiovascular diseases. With this motivation, this study develops an intelligent electrocardiogram classification using sailfish optimization algorithm with gated recurrent unit (SFOA-GRU) technique. The goal of the SFOA-GRU model is to detect the existence of cardiovascular disease by the classification of ECG signals. The SFOA-GRU model initially undergoes data pre-processing step to transform the actual values into useful format. Besides, GRU model is applied for the detection and classification of ECG signals. For improving the classification outcomes of the GRU model, the SFOA has been utilized to optimally adjust the hyper parameters involved in it. A wide-ranging experimental analysis is carried out to demonstrate the enhanced outcomes of the SFOA-GRU model. A comprehensive comparative study highlighted the promising performance of the SFOA-GRU model over the other recent approaches using different measures parameters.

groups

Mahmoud A. Zaher mail -

Nabil M. Eldakhly mail

link https://doi.org/10.54216/FPA.090104

Volume & Issue

Vol. Volume 9 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2022

Multi-objective Decision Making Model for Stock Price Prediction Using Multi-source Heterogeneous Data Fusion

Stock exchanges are developed as an essential component of economies, as they can promote financial and capital gain. The stock market is network of economic connections where share is bought and sold. Stock Market Prediction (SMP) is quite useful to investors. An effective forecast of stock prices is offer shareholders with suitable help in making appropriate decisions regarding if sell or purchase shares. The employ of Machine Learning (ML) and Sentiment Analysis (SA) on data in microblogging sites are developed as a famous approach to SMP. However, the heterogenous data fusion in stock market field is a big challenge. This paper introduces an effective Cat Swarm Optimization with Machine Learning Enabled Microblogging Sentiment Analysis for Stock Price Prediction technique. The presented model investigates the social media sentiments to foresee SPP. Firstly, the proposed model executes data pre-processing and Glove word embedding approach. Next, the weighted extreme learning machine approach was utilized for the classification of sentiments for SPP. Lastly, the CSO system was exploited for optimal adjustment of the parameters related to the WELM model. The experimental validation of the proposed approach was executed using microblogging data. The results show that the proposed method outperforms the previous studies.

groups

Noura Metawa mail -

Maha Mutawea mail

link https://doi.org/10.54216/FPA.090105

Volume & Issue

Vol. Volume 9 / Iss. Issue 1

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2022

Automatic Speech Recognition for Qur’an Verses using Traditional Technique

Deep learning is the one of approaches of machine learning that uses algorithms for building a model based on complex unstructured data. The Muslims Holy Qur’an book is written using Arabic diacritized text. In this paper, a traditional method to build a robust Qur’an versus recognition is proposed. The MFCC is used to extract features. These features are adapted using minimum phone error (MPE) as a discriminative model. The acoustic model was built using the deep neural network (DNN) model. We present an n-gram language model (LM). The dataset of Qur’an verses is used for training and evaluating the proposed model, consisting of 10 hours of .wav recitations performed by 60 reciters. The Experimental results showed that the proposed DNN model achieved a significantly low character error rate (CER) of 4.09% and a word error rate (WER) of 8.46%.

groups

Hamzah A. Alsayadi mail -

Mohammed Hadwan mail

link https://doi.org/10.54216/JAIM.010202

Volume & Issue

Vol. Volume 1 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2021

Interpretable Machine Learning Fusion and Data Analytics Models for Anomaly Detection

Explainable artificial intelligence received great research attention in the past few years during the widespread of Black-Box techniques in sensitive fields such as medical care, self-driving cars, etc. Artificial intelligence needs explainable methods to discover model biases. Explainable artificial intelligence will lead to obtaining fairness and Transparency in the model. Making artificial intelligence models explainable and interpretable is challenging when implementing black-box models. Because of the inherent limitations of collecting data in its raw form, data fusion has become a popular method for dealing with such data and acquiring more trustworthy, helpful, and precise insights. Compared to other, more traditional-based data fusion methods, machine learning's capacity to automatically learn from experience with nonexplicit programming significantly improves fusion's computational and predictive power. This paper comprehensively studies the most explainable artificial intelligent methods based on anomaly detection. We proposed the required criteria of the transparency model to measure the data fusion analytics techniques. Also, define the different used evaluation metrics in explainable artificial intelligence. We provide some applications for explainable artificial intelligence. We provide a case study of anomaly detection with the fusion of machine learning. Finally, we discuss the key challenges and future directions in explainable artificial intelligence.

groups

Ahmed Abdelmonem mail -

Nehal N. Mostafa mail

link https://doi.org/10.54216/FPA.030104

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2021

Deep Neural Network-based Fusion and Natural Language Processing in Additive Manufacturing for Customer Satisfaction

Modern Machine learning fusion approaches tend to extract features depending on two techniques (hand-crafted feature and representation learning). Hand-crafted features can waste time and are not sufficient for downstream tasks. Unlike representation learning, we automatically learn features with minimum time and effort and are suitable for downstream tasks. In our paper, we provide work on graph neural network methods with details on classical graph embedding approaches and the different methods in neural graph networks such as graph filtering, graph pooling, and the learning parameter for graph following each technique with a general framework or mathematical proof for customer satisfaction. To satisfy customer's feel, this research employs NLP techniques. We describe the adversarial attacks and defenses on graph representation approaches. Also, advanced application of neural graph networks is reviewed, such as combinational optimization, learning program representation, physical system modeling, and natural language processing. Finally, the challenges in geometric neural networks and future research work have been introduced.

groups

Abedallah Z. Abualkishik mail -

Rasha Almajed mail

link https://doi.org/10.54216/FPA.030105

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2021

Fusion of Machine learning for Detection of Rumor and False Information in Social Network

In recent years, spreading social media platforms and mobile devices led to more social data, advertisements, political opinions, and celebrity news proliferating fake news. Fake news can cause harm to networks, communications, and users and cause trust issues toward government, healthcare, or social media platforms. This inspired many researchers to implement models to detect falsified information content. But there are still many issues that need to be discussed and explored. In our paper, we introduce categories of fake news detection methods and compare these methods. After that, the promising applications for false news detection are extensively discussed in terms of fake account detection, bot detection, bullying detection, and security and privacy of social media. After all, A thorough discussion of the potential of machine learning approaches for fake news detection and interventions in social networks along with the state-of-the-art challenges, opportunities, and future search prospects. This article seeks to aid the readers and researchers in explaining the motive and role of the different machine learning fusion paradigms to offer them a comprehensive realization of unexplored issues related to false information and other scenarios of social networks.

groups

Nehal Mostafa mail -

IBRAHIM EL-HENAWY mail -

Ahmed Sleem mail

link https://doi.org/10.54216/FPA.040105

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

American Journal of Business and Operations Research | 2022

Multi-Criteria Decision-Making Approach based on Neutrosophic Sets for Evaluating Sustainable Supplier Selection in the Industrial 4.0

Sustainability in supply chain management can be achieved by integrating its applications with Industry 4.0 platforms.  Considering the Sustainability and Industry 4.0 criteria for supplier selection, this research creates a new integrated model to improve the performance of the applicatios.  The choice of suppliers is evaluated using a two-stage neutrosophic sets and the EDAS method.  The first step of this research is to define all of the terms associated with Industry 4.0 and Sustainability.  The neutrosophic EDAS determines the relative relevance of each criterion.  The neutrosophic VIKOR method is used to rank the suppliers.  The suppliers' performance in meeting the sustainability and Industry 4.0 standards is then nominated in a two-stage neutrosophic sets.  A case study of a textile firm is offered to illustrate the usefulness of our integrated approach.  The effectiveness of the suggested integrated method is then evaluated via a series of sensitivity assessments.  Of the things we learned was that it's best to build a decision-making framework that uses Industry 4.0 and sustainability criteria to assess suppliers individually rather than in a relative fashion in a hazy setting.

groups

Mahmoud Ismail mail -

Mahmoud Ibrahiem mail

link https://doi.org/10.54216/AJBOR.070204

Volume & Issue

Vol. Volume 7 / Iss. Issue 2

Details open_in_new