Editorial

4 pages, 176 KiB

Open AccessEditorial

Machine Learning Technologies for Big Data Analytics

by Amir H. Gandomi, Fang Chen and Laith Abualigah

Electronics 2022, 11(3), 421; https://doi.org/10.3390/electronics11030421 - 30 Jan 2022

Cited by 41 | Viewed by 8160

Big data analytics is one high focus of data science and there is no doubt that big data is now quickly growing in all science and engineering fields [...] Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

Research

Jump to: Editorial, Review

19 pages, 9299 KiB

Open AccessArticle

Cross-Modal Guidance Assisted Hierarchical Learning Based Siamese Network for MR Image Denoising

by Rabia Naseem, Faouzi Alaya Cheikh, Azeddine Beghdadi, Khan Muhammad and Muhammad Sajjad

Electronics 2021, 10(22), 2855; https://doi.org/10.3390/electronics10222855 - 19 Nov 2021

Cited by 4 | Viewed by 2071

Abstract

Cross-modal medical imaging techniques are predominantly being used in the clinical suite. The ensemble learning methods using cross-modal medical imaging adds reliability to several medical image analysis tasks. Motivated by the performance of deep learning in several medical imaging tasks, a deep learning-based [...] Read more.

Cross-modal medical imaging techniques are predominantly being used in the clinical suite. The ensemble learning methods using cross-modal medical imaging adds reliability to several medical image analysis tasks. Motivated by the performance of deep learning in several medical imaging tasks, a deep learning-based denoising method Cross-Modality Guided Denoising Network

C M G D N e t

for removing Rician noise in T1-weighted (T1-w) Magnetic Resonance Images (MRI) is proposed in this paper.

C M G D N e t

uses a guidance image, which is a cross-modal (T2-w) image of better perceptual quality to guide the model in denoising its noisy T1-w counterpart. This cross-modal combination allows the network to exploit complementary information existing in both images and therefore improve the learning capability of the model. The proposed framework consists of two components: Paired Hierarchical Learning (PHL) module and Cross-Modal Assisted Reconstruction (CMAR) module. PHL module uses Siamese network to extract hierarchical features from dual images, which are then combined in a densely connected manner in the CMAR module to finally reconstruct the image. The impact of using registered guidance data is investigated in removing noise as well as retaining structural similarity with the original image. Several experiments were conducted on two publicly available brain imaging datasets available on the IXI database. The quantitative assessment using Peak Signal to noise ratio (PSNR), Structural Similarity Index (SSIM), and Feature Similarity Index (FSIM) demonstrates that the proposed method exhibits 4.7% and 2.3% gain (average), respectively, in SSIM and FSIM values compared to other state-of-the-art denoising methods that do not integrate cross-modal image information in removing various levels of noise. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

15 pages, 3780 KiB

Open AccessArticle

Recognition of Cursive Pashto Optical Digits and Characters with Trio Deep Learning Neural Network Models

by Muhammad Zubair Rehman, Nazri Mohd. Nawi, Mohammad Arshad and Abdullah Khan

Electronics 2021, 10(20), 2508; https://doi.org/10.3390/electronics10202508 - 15 Oct 2021

Cited by 6 | Viewed by 2539

Abstract

Pashto is one of the most ancient and historical languages in the world and is spoken in Pakistan and Afghanistan. Various languages like Urdu, English, Chinese, and Japanese have OCR applications, but very little work has been conducted on the Pashto language in [...] Read more.

Pashto is one of the most ancient and historical languages in the world and is spoken in Pakistan and Afghanistan. Various languages like Urdu, English, Chinese, and Japanese have OCR applications, but very little work has been conducted on the Pashto language in this perspective. It becomes more difficult for OCR applications to recognize handwritten characters and digits, because handwriting is influenced by the writer’s hand dynamics. Moreover, there was no publicly available dataset for handwritten Pashto digits before this study. Due to this, there was no work performed on the recognition of Pashto handwritten digits and characters combined. To achieve this objective, a dataset of Pashto handwritten digits consisting of 60,000 images was created. The trio deep learning Convolutional Neural Network, i.e., CNN, LeNet, and Deep CNN were trained and tested with both Pashto handwritten characters and digits datasets. From the simulations, the Deep CNN achieved 99.42 percent accuracy for Pashto handwritten digits, 99.17 percent accuracy for handwritten characters, and 70.65 percent accuracy for combined digits and characters. Similarly, LeNet and CNN models achieved slightly less accuracies (LeNet; 98.82, 99.15, and 69.82 percent and CNN; 98.30, 98.74, and 66.53 percent) for Pashto handwritten digits, Pashto characters, and the combined Pashto digits and characters recognition datasets, respectively. Based on these results, the Deep CNN model is the best model in terms of accuracy and loss as compared to the other two models. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

25 pages, 5966 KiB

Open AccessArticle

Data-Driven Deep Learning-Based Attention Mechanism for Remaining Useful Life Prediction: Case Study Application to Turbofan Engine Analysis

by Amgad Muneer, Shakirah Mohd Taib, Sheraz Naseer, Rao Faizan Ali and Izzatdin Abdul Aziz

Electronics 2021, 10(20), 2453; https://doi.org/10.3390/electronics10202453 - 09 Oct 2021

Cited by 28 | Viewed by 4052

Abstract

Accurately predicting the remaining useful life (RUL) of the turbofan engine is of great significance for improving the reliability and safety of the engine system. Due to the high dimension and complex features of sensor data in RUL prediction, this paper proposes four [...] Read more.

Accurately predicting the remaining useful life (RUL) of the turbofan engine is of great significance for improving the reliability and safety of the engine system. Due to the high dimension and complex features of sensor data in RUL prediction, this paper proposes four data-driven prognostic models based on deep neural networks (DNNs) with an attention mechanism. To improve DNN feature extraction, data are prepared using a sliding time window technique. The raw data collected after normalizing is simply fed into the suggested network, requiring no prior knowledge of prognostics or signal processing and simplifying the proposed method’s applicability. In order to verify the RUL prediction ability of the proposed DNN techniques, the C-MAPSS benchmark dataset of the turbofan engine system is validated. The experimental results showed that the developed long short-term memory (LSTM) model with attention mechanism achieved accurate RUL prediction in both scenarios with a high degree of robustness and generalization ability. Furthermore, the proposed model performance outperforms several state-of-the-art prognosis methods, where the LSTM-based model with attention mechanism achieved an RMSE of 12.87 and 11.23 for FD002 and FD003 subset of data, respectively. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

26 pages, 1230 KiB

Open AccessArticle

Sentiment Analysis of before and after Elections: Twitter Data of U.S. Election 2020

by Hassan Nazeer Chaudhry, Yasir Javed, Farzana Kulsoom, Zahid Mehmood, Zafar Iqbal Khan, Umar Shoaib and Sadaf Hussain Janjua

Electronics 2021, 10(17), 2082; https://doi.org/10.3390/electronics10172082 - 27 Aug 2021

Cited by 30 | Viewed by 7130

Abstract

U.S. President Joe Biden took his oath after being victorious in the controversial U.S. elections of 2020. The polls were conducted over postal ballot due to the coronavirus pandemic following delays of the announcement of the election’s results. Donald J. Trump claimed that [...] Read more.

U.S. President Joe Biden took his oath after being victorious in the controversial U.S. elections of 2020. The polls were conducted over postal ballot due to the coronavirus pandemic following delays of the announcement of the election’s results. Donald J. Trump claimed that there was potential rigging against him and refused to accept the results of the polls. The sentiment analysis captures the opinions of the masses over social media for global events. In this work, we analyzed Twitter sentiment to determine public views before, during, and after elections and compared them with actual election results. We also compared opinions from the 2016 election in which Donald J. Trump was victorious with the 2020 election. We created a dataset using tweets’ API, pre-processed the data, extracted the right features using TF-IDF, and applied the Naive Bayes Classifier to obtain public opinions. As a result, we identified outliers, analyzed controversial and swing states, and cross-validated election results against sentiments expressed over social media. The results reveal that the election outcomes coincide with the sentiment expressed on social media in most cases. The pre and post-election sentiment analysis results demonstrate the sentimental drift in outliers. Our sentiment classifier shows an accuracy of 94.58% and a precision of 93.19%. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

15 pages, 1577 KiB

Open AccessArticle

Automatic Categorization of LGBT User Profiles on Twitter with Machine Learning

by Amir Karami, Morgan Lundy, Frank Webb, Hannah R. Boyajieff, Michael Zhu and Dorathea Lee

Electronics 2021, 10(15), 1822; https://doi.org/10.3390/electronics10151822 - 29 Jul 2021

Cited by 6 | Viewed by 5144

Abstract

Privacy needs and stigma pose significant barriers to lesbian, gay, bisexual, and transgender (LGBT) people sharing information related to their identities in traditional settings and research methods such as surveys and interviews. Fortunately, social media facilitates people’s belonging to and exchanging information within [...] Read more.

Privacy needs and stigma pose significant barriers to lesbian, gay, bisexual, and transgender (LGBT) people sharing information related to their identities in traditional settings and research methods such as surveys and interviews. Fortunately, social media facilitates people’s belonging to and exchanging information within online LGBT communities. Compared to heterosexual respondents, LGBT users are also more likely to have accounts on social media websites and access social media daily. However, the current relevant LGBT studies on social media are not efficient or assume that any accounts that utilize LGBT-related words in their profile belong to individuals who identify as LGBT. Our human coding of over 16,000 accounts instead proposes the following three categories of LGBT Twitter users: individual, sexual worker/porn, and organization. This research develops a machine learning classifier based on the profile and bio features of these Twitter accounts. To have an efficient and effective process, we use a feature selection method to reduce the number of features and improve the classifier’s performance. Our approach achieves a promising result with around 88% accuracy. We also develop statistical analyses to compare the three categories based on the average weight of top features. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

52 pages, 7402 KiB

Open AccessArticle

Classifier Performance Evaluation for Lightweight IDS Using Fog Computing in IoT Security

by Belal Sudqi Khater, Ainuddin Wahid Abdul Wahab, Mohd Yamani Idna Idris, Mohammed Abdulla Hussain, Ashraf Ahmed Ibrahim, Mohammad Arif Amin and Hisham A. Shehadeh

Electronics 2021, 10(14), 1633; https://doi.org/10.3390/electronics10141633 - 08 Jul 2021

Cited by 28 | Viewed by 3732

Abstract

In this article, a Host-Based Intrusion Detection System (HIDS) using a Modified Vector Space Representation (MVSR) N-gram and Multilayer Perceptron (MLP) model for securing the Internet of Things (IoT), based on lightweight techniques and using Fog Computing devices, is proposed. The Australian Defence [...] Read more.

In this article, a Host-Based Intrusion Detection System (HIDS) using a Modified Vector Space Representation (MVSR) N-gram and Multilayer Perceptron (MLP) model for securing the Internet of Things (IoT), based on lightweight techniques and using Fog Computing devices, is proposed. The Australian Defence Force Academy Linux Dataset (ADFA-LD), which contains exploits and attacks on various applications, is employed for the analysis. The proposed method is divided into the feature extraction stage, the feature selection stage, and classification modeling. To maintain the lightweight criteria, the feature extraction stage considers a combination of 1-gram and 2-gram for the system call encoding. In addition, a Sparse Matrix is used to reduce the space by keeping only the weight of the features that appear in the trace, thus ignoring the zero weights. Subsequently, Linear Correlation Coefficient (LCC) is utilized to compensate for any missing N-gram in the test data. In the feature selection stage, the Mutual Information (MI) method and Principle Component Analysis (PCA) are utilized and then compared to reduce the number of input features. Following the feature selection stage, the modeling and performance evaluation of various Machine Learning classifiers are conducted using a Raspberry Pi IoT device. Further analysis of the effect of MLP parameters, such as the number of nodes, number of features, activation, solver, and regularization parameters, is also conducted. From the simulation, it can be seen that different parameters affect the accuracy and lightweight evaluation. By using a single hidden layer and four nodes, the proposed method with MI can achieve 96% accuracy, 97% recall, 96% F1-Measure, 5% False Positive Rate (FPR), highest curve of Receiver Operating Characteristic (ROC), and 96% Area Under the Curve (AUC). It also achieved low CPU time usage of 4.404 (ms) milliseconds and low energy consumption of 8.809 (mj) millijoules. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

18 pages, 6283 KiB

Open AccessArticle

Social Media Toxicity Classification Using Deep Learning: Real-World Application UK Brexit

by Hong Fan, Wu Du, Abdelghani Dahou, Ahmed A. Ewees, Dalia Yousri, Mohamed Abd Elaziz, Ammar H. Elsheikh, Laith Abualigah and Mohammed A. A. Al-qaness

Electronics 2021, 10(11), 1332; https://doi.org/10.3390/electronics10111332 - 01 Jun 2021

Cited by 43 | Viewed by 8668

Abstract

Social media has become an essential facet of modern society, wherein people share their opinions on a wide variety of topics. Social media is quickly becoming indispensable for a majority of people, and many cases of social media addiction have been documented. Social [...] Read more.

Social media has become an essential facet of modern society, wherein people share their opinions on a wide variety of topics. Social media is quickly becoming indispensable for a majority of people, and many cases of social media addiction have been documented. Social media platforms such as Twitter have demonstrated over the years the value they provide, such as connecting people from all over the world with different backgrounds. However, they have also shown harmful side effects that can have serious consequences. One such harmful side effect of social media is the immense toxicity that can be found in various discussions. The word toxic has become synonymous with online hate speech, internet trolling, and sometimes outrage culture. In this study, we build an efficient model to detect and classify toxicity in social media from user-generated content using the Bidirectional Encoder Representations from Transformers (BERT). The BERT pre-trained model and three of its variants has been fine-tuned on a well-known labeled toxic comment dataset, Kaggle public dataset (Toxic Comment Classification Challenge). Moreover, we test the proposed models with two datasets collected from Twitter from two different periods to detect toxicity in user-generated content (tweets) using hashtages belonging to the UK Brexit. The results showed that the proposed model can efficiently classify and analyze toxic tweets. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

19 pages, 1199 KiB

Open AccessArticle

A Deep Learning Sentiment Analyser for Social Media Comments in Low-Resource Languages

by Zenun Kastrati, Lule Ahmedi, Arianit Kurti, Fatbardh Kadriu, Doruntina Murtezaj and Fatbardh Gashi

Electronics 2021, 10(10), 1133; https://doi.org/10.3390/electronics10101133 - 11 May 2021

Cited by 29 | Viewed by 5768

Abstract

During the pandemic, when people needed to physically distance, social media platforms have been one of the outlets where people expressed their opinions, thoughts, sentiments, and emotions regarding the pandemic situation. The core object of this research study is the sentiment analysis of [...] Read more.

During the pandemic, when people needed to physically distance, social media platforms have been one of the outlets where people expressed their opinions, thoughts, sentiments, and emotions regarding the pandemic situation. The core object of this research study is the sentiment analysis of peoples’ opinions expressed on Facebook regarding the current pandemic situation in low-resource languages. To do this, we have created a large-scale dataset comprising of 10,742 manually classified comments in the Albanian language. Furthermore, in this paper we report our efforts on the design and development of a sentiment analyser that relies on deep learning. As a result, we report the experimental findings obtained from our proposed sentiment analyser using various classifier models with static and contextualized word embeddings, that is, fastText and BERT, trained and validated on our collected and curated dataset. Specifically, the findings reveal that combining the BiLSTM with an attention mechanism achieved the highest performance on our sentiment analysis task, with an F1 score of 72.09%. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

15 pages, 1281 KiB

Open AccessArticle

Linear Weighted Regression and Energy-Aware Greedy Scheduling for Heterogeneous Big Data

by Suresh Kallam, Rizwan Patan, Tathapudi V. Ramana and Amir H. Gandomi

Electronics 2021, 10(5), 554; https://doi.org/10.3390/electronics10050554 - 26 Feb 2021

Cited by 5 | Viewed by 1712

Abstract

Data are presently being produced at an increased speed in different formats, which complicates the design, processing, and evaluation of the data. The MapReduce algorithm is a distributed file system that is used for big data parallel processing. Current implementations of MapReduce assist [...] Read more.

Data are presently being produced at an increased speed in different formats, which complicates the design, processing, and evaluation of the data. The MapReduce algorithm is a distributed file system that is used for big data parallel processing. Current implementations of MapReduce assist in data locality along with robustness. In this study, a linear weighted regression and energy-aware greedy scheduling (LWR-EGS) method were combined to handle big data. The LWR-EGS method initially selects tasks for an assignment and then selects the best available machine to identify an optimal solution. With this objective, first, the problem was modeled as an integer linear weighted regression program to choose tasks for the assignment. Then, the best available machines were selected to find the optimal solution. In this manner, the optimization of resources is said to have taken place. Then, an energy efficiency-aware greedy scheduling algorithm was presented to select a position for each task to minimize the total energy consumption of the MapReduce job for big data applications in heterogeneous environments without a significant performance loss. To evaluate the performance, the LWR-EGS method was compared with two related approaches via MapReduce. The experimental results showed that the LWR-EGS method effectively reduced the total energy consumption without producing large scheduling overheads. Moreover, the method also reduced the execution time when compared to state-of-the-art methods. The LWR-EGS method reduced the energy consumption, average processing time, and scheduling overhead by 16%, 20%, and 22%, respectively, compared to existing methods. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

29 pages, 514 KiB

Open AccessArticle

Advances in Meta-Heuristic Optimization Algorithms in Big Data Text Clustering

by Laith Abualigah, Amir H. Gandomi, Mohamed Abd Elaziz, Husam Al Hamad, Mahmoud Omari, Mohammad Alshinwan and Ahmad M. Khasawneh

Electronics 2021, 10(2), 101; https://doi.org/10.3390/electronics10020101 - 06 Jan 2021

Cited by 75 | Viewed by 6773

Abstract

This paper presents a comprehensive survey of the meta-heuristic optimization algorithms on the text clustering applications and highlights its main procedures. These Artificial Intelligence (AI) algorithms are recognized as promising swarm intelligence methods due to their successful ability to solve machine learning problems, [...] Read more.

This paper presents a comprehensive survey of the meta-heuristic optimization algorithms on the text clustering applications and highlights its main procedures. These Artificial Intelligence (AI) algorithms are recognized as promising swarm intelligence methods due to their successful ability to solve machine learning problems, especially text clustering problems. This paper reviews all of the relevant literature on meta-heuristic-based text clustering applications, including many variants, such as basic, modified, hybridized, and multi-objective methods. As well, the main procedures of text clustering and critical discussions are given. Hence, this review reports its advantages and disadvantages and recommends potential future research paths. The main keywords that have been considered in this paper are text, clustering, meta-heuristic, optimization, and algorithm. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

Review

Jump to: Editorial, Research

18 pages, 617 KiB

Open AccessReview

Intervention Programs for the Problematic Use of the Internet and Technological Devices: A Systematic Review

by Elizabeth Cañas and Estefanía Estévez

Electronics 2021, 10(23), 2923; https://doi.org/10.3390/electronics10232923 - 25 Nov 2021

Cited by 6 | Viewed by 4069

Abstract

The intensive use of the Internet and communication technologies among adolescents has increased addiction and/or their problematic use. The innovative and revolutionary development of this technology can have negative effects on the mental and physical health of its users, and it seems to [...] Read more.

The intensive use of the Internet and communication technologies among adolescents has increased addiction and/or their problematic use. The innovative and revolutionary development of this technology can have negative effects on the mental and physical health of its users, and it seems to have a greater impact on adolescents. As this is causing a public health problem, the objective of this study was to review the different intervention and prevention programs for this problem in adolescents. A total of 14 programs met the inclusion criteria. The analysis of the programs allows for the identification of effective intervention designs for prevention, and also for the treatment of the current problems derived from the use of the Internet and technological devices among adolescent users. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

38 pages, 1157 KiB

Open AccessFeature PaperReview

A Consolidated Review of Path Planning and Optimization Techniques: Technical Perspectives and Future Directions

by Faiza Gul, Imran Mir, Laith Abualigah, Putra Sumari and Agostino Forestiero

Electronics 2021, 10(18), 2250; https://doi.org/10.3390/electronics10182250 - 13 Sep 2021

Cited by 78 | Viewed by 7454

Abstract

In this paper, a review on the three most important communication techniques (ground, aerial, and underwater vehicles) has been presented that throws light on trajectory planning, its optimization, and various issues in a summarized way. This kind of extensive research is not often [...] Read more.

In this paper, a review on the three most important communication techniques (ground, aerial, and underwater vehicles) has been presented that throws light on trajectory planning, its optimization, and various issues in a summarized way. This kind of extensive research is not often seen in the literature, so an effort has been made for readers interested in path planning to fill the gap. Moreover, optimization techniques suitable for implementing ground, aerial, and underwater vehicles are also a part of this review. This paper covers the numerical, bio-inspired techniques and their hybridization with each other for each of the dimensions mentioned. The paper provides a consolidated platform, where plenty of available research on-ground autonomous vehicle and their trajectory optimization with the extension for aerial and underwater vehicles are documented. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

45 pages, 2597 KiB

Open AccessReview

Cyberstalking Victimization Model Using Criminological Theory: A Systematic Literature Review, Taxonomies, Applications, Tools, and Validations

by Waheeb Abu-Ulbeh, Maryam Altalhi, Laith Abualigah, Abdulwahab Ali Almazroi, Putra Sumari and Amir H. Gandomi

Electronics 2021, 10(14), 1670; https://doi.org/10.3390/electronics10141670 - 13 Jul 2021

Cited by 11 | Viewed by 6392

Abstract

Cyberstalking is a growing anti-social problem being transformed on a large scale and in various forms. Cyberstalking detection has become increasingly popular in recent years and has technically been investigated by many researchers. However, cyberstalking victimization, an essential part of cyberstalking, has empirically [...] Read more.

Cyberstalking is a growing anti-social problem being transformed on a large scale and in various forms. Cyberstalking detection has become increasingly popular in recent years and has technically been investigated by many researchers. However, cyberstalking victimization, an essential part of cyberstalking, has empirically received less attention from the paper community. This paper attempts to address this gap and develop a model to understand and estimate the prevalence of cyberstalking victimization. The model of this paper is produced using routine activities and lifestyle exposure theories and includes eight hypotheses. The data of this paper is collected from the 757 respondents in Jordanian universities. This review paper utilizes a quantitative approach and uses structural equation modeling for data analysis. The results revealed a modest prevalence range is more dependent on the cyberstalking type. The results also indicated that proximity to motivated offenders, suitable targets, and digital guardians significantly influences cyberstalking victimization. The outcome from moderation hypothesis testing demonstrated that age and residence have a significant effect on cyberstalking victimization. The proposed model is an essential element for assessing cyberstalking victimization among societies, which provides a valuable understanding of the prevalence of cyberstalking victimization. This can assist the researchers and practitioners for future research in the context of cyberstalking victimization. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

19 pages, 7517 KiB

Open AccessReview

Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics

by Jianlong Zhou, Amir H. Gandomi, Fang Chen and Andreas Holzinger

Electronics 2021, 10(5), 593; https://doi.org/10.3390/electronics10050593 - 04 Mar 2021

Cited by 205 | Viewed by 23593

Abstract

The most successful Machine Learning (ML) systems remain complex black boxes to end-users, and even experts are often unable to understand the rationale behind their decisions. The lack of transparency of such systems can have severe consequences or poor uses of limited valuable [...] Read more.

The most successful Machine Learning (ML) systems remain complex black boxes to end-users, and even experts are often unable to understand the rationale behind their decisions. The lack of transparency of such systems can have severe consequences or poor uses of limited valuable resources in medical diagnosis, financial decision-making, and in other high-stake domains. Therefore, the issue of ML explanation has experienced a surge in interest from the research community to application domains. While numerous explanation methods have been explored, there is a need for evaluations to quantify the quality of explanation methods to determine whether and to what extent the offered explainability achieves the defined objective, and compare available explanation methods and suggest the best explanation from the comparison for a specific task. This survey paper presents a comprehensive overview of methods proposed in the current literature for the evaluation of ML explanations. We identify properties of explainability from the review of definitions of explainability. The identified properties of explainability are used as objectives that evaluation metrics should achieve. The survey found that the quantitative metrics for both model-based and example-based explanations are primarily used to evaluate the parsimony/simplicity of interpretability, while the quantitative metrics for attribution-based explanations are primarily used to evaluate the soundness of fidelity of explainability. The survey also demonstrated that subjective measures, such as trust and confidence, have been embraced as the focal point for the human-centered evaluation of explainable systems. The paper concludes that the evaluation of ML explanations is a multidisciplinary research topic. It is also not possible to define an implementation of evaluation metrics, which can be applied to all explanation methods. Full article

(This article belongs to the Special Issue Machine Learning Technologies for Big Data Analytics)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Machine Learning Technologies for Big Data Analytics

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (15 papers)

Editorial

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI