Applied Sciences

Research

Jump to: Review

16 pages, 5147 KiB

Open AccessArticle

Evolutionary Algorithm with Deep Auto Encoder Network Based Website Phishing Detection and Classification

by Hamed Alqahtani, Saud S. Alotaibi, Fatma S. Alrayes, Isra Al-Turaiki, Khalid A. Alissa, Amira Sayed A. Aziz, Mohammed Maray and Mesfer Al Duhayyim

Appl. Sci. 2022, 12(15), 7441; https://doi.org/10.3390/app12157441 - 25 Jul 2022

Cited by 2 | Viewed by 2168

Abstract

Website phishing is a cyberattack that targets online users for stealing their sensitive data containing login credential and banking details. The phishing websites appear very similar to their equivalent legitimate websites for attracting a huge amount of Internet users. The attacker fools the [...] Read more.

Website phishing is a cyberattack that targets online users for stealing their sensitive data containing login credential and banking details. The phishing websites appear very similar to their equivalent legitimate websites for attracting a huge amount of Internet users. The attacker fools the user by offering the masked webpage as legitimate or reliable for retrieving its important information. Presently, anti-phishing approaches necessitate experts to extract phishing site features and utilize third-party services for phishing website detection. These techniques have some drawbacks, as the requirement of experts for extracting phishing features is time consuming. Many solutions for phishing websites attack have been presented, such as blacklist or whitelist, heuristics, and machine learning (ML) based approaches, which face difficulty in accomplishing effectual recognition performance due to the continual improvements of phishing technologies. Therefore, this study presents an optimal deep autoencoder network based website phishing detection and classification (ODAE-WPDC) model. The proposed ODAE-WPDC model applies input data pre-processing at the initial stage to get rid of missing values in the dataset. Then, feature extraction and artificial algae algorithm (AAA) based feature selection (FS) are utilized. The DAE model with the received features carried out the classification process, and the parameter tuning of the DAE technique was performed using the invasive weed optimization (IWO) algorithm to accomplish enhanced performance. The performance validation of the ODAE-WPDC technique was tested using the Phishing URL dataset from the Kaggle repository. The experimental findings confirm the better performance of the ODAE-WPDC model with maximum accuracy of 99.28%. Full article

(This article belongs to the Special Issue Computational Methods for Medical and Cyber Security)

► Show Figures

Figure 1

21 pages, 4510 KiB

Open AccessArticle

Factors Affecting Cybersecurity Awareness among University Students

by Mohammed A. Alqahtani

Appl. Sci. 2022, 12(5), 2589; https://doi.org/10.3390/app12052589 - 02 Mar 2022

Cited by 14 | Viewed by 12107

Abstract

One of the essential stages in increasing cyber security is implementing an effective security awareness program. This work studies the present level of security knowledge among Imam Abdulrahman Bin Faisal University college students. A module was created to assist the students in becoming [...] Read more.

One of the essential stages in increasing cyber security is implementing an effective security awareness program. This work studies the present level of security knowledge among Imam Abdulrahman Bin Faisal University college students. A module was created to assist the students in becoming more informed. The main contribution of this work is an assessment of cybersecurity awareness among the university students based on three essential aspects: password security, browser security, and social media. Numerous questions were designed and sent to them to evaluate their awareness. The current survey received as many as 450 responses with their answers. Various statistical analyses were applied to the responses, including the validity and reliability test, feasibility test of a variable, correlation test, multicollinearity test, multiple regression, and heteroskedasticity test, carried out using SPSS. Furthermore, a multiple linear regression model and coefficient of determination, a hypothesis test, ANOVA test, and a partial test using ANOVA were also carried out. The hypothesis investigated here concerns password security, browser security, and social media. The results of partial hypothesis testing using a t-test showed that the password security variable significantly affects cybersecurity awareness (p-value = 0.0001). The regression coefficient of the password security variable in the multiple linear regression model was found to have a beta value of 0.147. In addition, the browser security variable significantly affects awareness, with a p-value = 0.0001. The regression coefficient of the password security variable had a beta value of 0.188. The social media activities variable significantly affects cybersecurity awareness (p-value = 0.0001). The regression coefficient of the social media activities variable had a beta value of 0.241. Based on the research conducted, it is concluded that knowledge of password security, browser security, and social media activities significantly influences cybersecurity awareness in students. Overall, students have realized the importance of cybersecurity awareness. Full article

(This article belongs to the Special Issue Computational Methods for Medical and Cyber Security)

► Show Figures

Figure 1

21 pages, 4873 KiB

Open AccessArticle

Secure Healthcare Record Sharing Mechanism with Blockchain

by Ghulam Qadar Butt, Toqeer Ali Sayed, Rabia Riaz, Sanam Shahla Rizvi and Anand Paul

Appl. Sci. 2022, 12(5), 2307; https://doi.org/10.3390/app12052307 - 23 Feb 2022

Cited by 26 | Viewed by 3355

Abstract

The transfer of information is a demanding issue, particularly due to the presence of a large number of eavesdroppers on communication channels. Sharing medical service records between different clinical jobs is a basic and testing research topic. The particular characteristics of blockchains have [...] Read more.

The transfer of information is a demanding issue, particularly due to the presence of a large number of eavesdroppers on communication channels. Sharing medical service records between different clinical jobs is a basic and testing research topic. The particular characteristics of blockchains have attracted a large amount of attention and resulted in revolutionary changes to various business applications, including medical care. A blockchain is based on a distributed ledger, which tends to improve cyber security. A number of proposals have been made with respect to the sharing of basic medical records using a blockchain without needing earlier information or the trust of patients. Specialist service providers and insurance agencies are not secure against data breaches. The safe sharing of clinical records between different countries, to ensure an incorporated and universal medical service, is also a significant issue for patients who travel. The medical data of patients normally reside on different healthcare units around the world, thus raising many concerns. Firstly, a patient’s history of treatment by different physicians is not accessible to the doctor in a single location. Secondly, it is very difficult to secure widespread data residing in different locations. This study proposed record sharing in a chain-like structure, in which every record is globally connected to the others, based on a blockchain under the suggestions and recommendations of the HL7 standards. This study focused on making medical data available, especially of patients who travel in different countries, for a specific period of time after validating the required authentication. Authorization and authentication are performed on the Shibboleth identity management system with the involvement of patient in the sanction process, thereby revealing the patient data for the specific period of time. The proposed approach improves the performance with respect to other record sharing systems, e.g., it reduces the time to read, write, delete, and revoke a record by a noticeable margin. The proposed system takes around three seconds to upload and 7.5 s to download 250 Mb of data, which can contain up to sixteen documents, over a stable network connection. The system has a latency of 413.76 ms when retrieving 100 records, compared to 447.9 and 459.3 ms in previous systems. Thus, the proposed system improved the performance and ensured seclusion by using a blockchain. Full article

(This article belongs to the Special Issue Computational Methods for Medical and Cyber Security)

► Show Figures

Figure 1

15 pages, 5192 KiB

Open AccessArticle

Detecting Small Anatomical Structures in 3D Knee MRI Segmentation by Fully Convolutional Networks

by Mengtao Sun, Li Lu, Ibrahim A. Hameed, Carl Petter Skaar Kulseng and Kjell-Inge Gjesdal

Appl. Sci. 2022, 12(1), 283; https://doi.org/10.3390/app12010283 - 28 Dec 2021

Cited by 6 | Viewed by 1743

Abstract

Accurately identifying the pixels of small organs or lesions from magnetic resonance imaging (MRI) has a critical impact on clinical diagnosis. U-net is the most well-known and commonly used neural network for image segmentation. However, the small anatomical structures in medical images cannot [...] Read more.

Accurately identifying the pixels of small organs or lesions from magnetic resonance imaging (MRI) has a critical impact on clinical diagnosis. U-net is the most well-known and commonly used neural network for image segmentation. However, the small anatomical structures in medical images cannot be well recognised by U-net. This paper explores the performance of the U-net architectures in knee MRI segmentation to find a relative structure that can obtain high accuracies for both small and large anatomical structures. To maximise the utilities of U-net architecture, we apply three types of components, residual blocks, squeeze-and-excitation (SE) blocks, and dense blocks, to construct four variants of U-net, namely U-net variants. Among these variants, our experiments show that SE blocks can improve the segmentation accuracies of small labels. We adopt DeepLabv3plus architecture for 3D medical image segmentation by equipping SE blocks based on this discovery. The experimental results show that U-net with SE block achieves higher accuracy in parts of small anatomical structures. In contrast, DeepLabv3plus with SE block performs better on the average dice coefficient of small and large labels. Full article

(This article belongs to the Special Issue Computational Methods for Medical and Cyber Security)

► Show Figures

Figure 1

14 pages, 359 KiB

Open AccessArticle

Columns Occurrences Graph to Improve Column Prediction in Deep Learning Nlidb

by Shanza Abbas, Muhammad Umair Khan, Scott Uk-Jin Lee and Asad Abbas

Appl. Sci. 2021, 11(24), 12116; https://doi.org/10.3390/app112412116 - 20 Dec 2021

Cited by 1 | Viewed by 2091

Abstract

Natural language interfaces to databases (NLIDB) has been a research topic for a decade. Significant data collections are available in the form of databases. To utilize them for research purposes, a system that can translate a natural language query into a structured one [...] Read more.

Natural language interfaces to databases (NLIDB) has been a research topic for a decade. Significant data collections are available in the form of databases. To utilize them for research purposes, a system that can translate a natural language query into a structured one can make a huge difference. Efforts toward such systems have been made with pipelining methods for more than a decade. Natural language processing techniques integrated with data science methods are researched as pipelining NLIDB systems. With significant advancements in machine learning and natural language processing, NLIDB with deep learning has emerged as a new research trend in this area. Deep learning has shown potential for rapid growth and improvement in text-to-SQL tasks. In deep learning NLIDB, closing the semantic gap in predicting users’ intended columns has arisen as one of the critical and fundamental problems in this research field. Contributions toward this issue have consisted of preprocessed feature inputs and encoding schema elements afore of and more impactful to the targeted model. Various significant work contributed towards this problem notwithstanding, this has been shown to be one of the critical issues for the task of developing NLIDB. Working towards closing the semantic gap between user intention and predicted columns, we present an approach for deep learning text-to-SQL tasks that includes previous columns’ occurrences scores as an additional input feature. Overall exact match accuracy can also be improved by emphasizing the improvement of columns’ prediction accuracy, which depends significantly on column prediction itself. For this purpose, we extract the query fragments from previous queries’ data and obtain the columns’ occurrences and co-occurrences scores. Column occurrences and co-occurrences scores are processed as input features for the encoder–decoder-based text to the SQL model. These scores contribute, as a factor, the probability of having already used columns and tables together in the query history. We experimented with our approach on the currently popular text-to-SQL dataset Spider. Spider is a complex data set containing multiple databases. This dataset includes query–question pairs along with schema information. We compared our exact match accuracy performance with a base model using their test and training data splits. It outperformed the base model’s accuracy, and accuracy was further boosted in experiments with the pretrained language model BERT. Full article

(This article belongs to the Special Issue Computational Methods for Medical and Cyber Security)

► Show Figures

Figure 1

19 pages, 2142 KiB

Open AccessArticle

Predicting Academic Performance Using an Efficient Model Based on Fusion of Classifiers

by Ansar Siddique, Asiya Jan, Fiaz Majeed, Adel Ibrahim Qahmash, Noorulhasan Naveed Quadri and Mohammad Osman Abdul Wahab

Appl. Sci. 2021, 11(24), 11845; https://doi.org/10.3390/app112411845 - 13 Dec 2021

Cited by 32 | Viewed by 3562

Abstract

In the past few years, educational data mining (EDM) has attracted the attention of researchers to enhance the quality of education. Predicting student academic performance is crucial to improving the value of education. Some research studies have been conducted which mainly focused on [...] Read more.

In the past few years, educational data mining (EDM) has attracted the attention of researchers to enhance the quality of education. Predicting student academic performance is crucial to improving the value of education. Some research studies have been conducted which mainly focused on prediction of students’ performance at higher education. However, research related to performance prediction at the secondary level is scarce, whereas the secondary level tends to be a benchmark to describe students’ learning progress at further educational levels. Students’ failure or poor grades at lower secondary negatively impact them at the higher secondary level. Therefore, early prediction of performance is vital to keep students on a progressive track. This research intended to determine the critical factors that affect the performance of students at the secondary level and to build an efficient classification model through the fusion of single and ensemble-based classifiers for the prediction of academic performance. Firstly, three single classifiers including a Multilayer Perceptron (MLP), J48, and PART were observed along with three well-established ensemble algorithms encompassing Bagging (BAG), MultiBoost (MB), and Voting (VT) independently. To further enhance the performance of the abovementioned classifiers, nine other models were developed by the fusion of single and ensemble-based classifiers. The evaluation results showed that MultiBoost with MLP outperformed the others by achieving 98.7% accuracy, 98.6% precision, recall, and F-score. The study implies that the proposed model could be useful in identifying the academic performance of secondary level students at an early stage to improve the learning outcomes. Full article

(This article belongs to the Special Issue Computational Methods for Medical and Cyber Security)

► Show Figures

Figure 1

21 pages, 1155 KiB

Open AccessArticle

Cognitive Biases on the Iran Stock Exchange: Unsupervised Learning Approach to Examining Feature Bundles in Investors’ Portfolios

by Adele Ossareh, Mohammad Saeed Pourjafar and Tomasz Kopczewski

Appl. Sci. 2021, 11(22), 10916; https://doi.org/10.3390/app112210916 - 18 Nov 2021

Cited by 2 | Viewed by 2091

Abstract

This paper innovatively analyses the joint occurrence of cognitive biases in groups of stock exchange investors. It considers jointly a number of common fallacies: confirmation bias, loss aversion, gambler’s fallacy, availability cascade, hot-hand fallacy, bandwagon effect, and Dunning–Kruger effect, which have hitherto been [...] Read more.

This paper innovatively analyses the joint occurrence of cognitive biases in groups of stock exchange investors. It considers jointly a number of common fallacies: confirmation bias, loss aversion, gambler’s fallacy, availability cascade, hot-hand fallacy, bandwagon effect, and Dunning–Kruger effect, which have hitherto been studied separately. The paper aims to highlight the diverse range of investor’s profiles which are characterised by such fallacies, and the considerable differences observed based on their age, stock market experience and perception of market trends. The analysis is based on k-means and hierarchical clustering, feature importance and Principal Component Analysis, which were applied to data from the Tehran Stock Exchange. There are a few essential findings which contribute to the existing literature. Firstly, the results show that gender does not have a role to play in diversifying the investors’ profiles. Secondly, cognitive biases are bundled, and we distinguish four investors’ profiles; thus, they should be analysed jointly, not separately. Thirdly, the exposure to cognitive biases differs significantly due to the individual features of investors. The group most vulnerable to almost all analysed biases are inexperienced investors, who are pessimistic about market developments and have invested a large amount. Fourthly, the ages of investors are essential only in connection with other factors such as experience, market perception and investment exposure. Young (20–40 years), experienced investors with huge investments (+1000 mln rials/+24,000 USD) are mostly less exposed to all biases and much less risk-averse. Additionally, older (50+) and experienced investors (5–10 years) who are more optimistic about trends (hot hand bias) were affected much less by cognitive biases, only showing vulnerability to the Dunning–Kruger effect. Fifthly, more than 40% of investors apply consultation and technical analysis approaches to succeed in trading. Finally, from a methodological perspective, this study shows that unsupervised learning methods are effective in profiling investors and bundling similar behaviours. Full article

(This article belongs to the Special Issue Computational Methods for Medical and Cyber Security)

► Show Figures

Figure 1

18 pages, 2653 KiB

Open AccessArticle

Machine Translation in Low-Resource Languages by an Adversarial Neural Network

by Mengtao Sun, Hao Wang, Mark Pasquine and Ibrahim A. Hameed

Appl. Sci. 2021, 11(22), 10860; https://doi.org/10.3390/app112210860 - 17 Nov 2021

Cited by 3 | Viewed by 1688

Abstract

Existing Sequence-to-Sequence (Seq2Seq) Neural Machine Translation (NMT) shows strong capability with High-Resource Languages (HRLs). However, this approach poses serious challenges when processing Low-Resource Languages (LRLs), because the model expression is limited by the training scale of parallel sentence pairs. This study utilizes adversary [...] Read more.

Existing Sequence-to-Sequence (Seq2Seq) Neural Machine Translation (NMT) shows strong capability with High-Resource Languages (HRLs). However, this approach poses serious challenges when processing Low-Resource Languages (LRLs), because the model expression is limited by the training scale of parallel sentence pairs. This study utilizes adversary and transfer learning techniques to mitigate the lack of sentence pairs in LRL corpora. We propose a new Low resource, Adversarial, Cross-lingual (LAC) model for NMT. In terms of the adversary technique, LAC model consists of a generator and discriminator. The generator is a Seq2Seq model that produces the translations from source to target languages, while the discriminator measures the gap between machine and human translations. In addition, we introduce transfer learning on LAC model to help capture the features in rare resources because some languages share the same subject-verb-object grammatical structure. Rather than using the entire pretrained LAC model, we separately utilize the pretrained generator and discriminator. The pretrained discriminator exhibited better performance in all experiments. Experimental results demonstrate that the LAC model achieves higher Bilingual Evaluation Understudy (BLEU) scores and has good potential to augment LRL translations. Full article

(This article belongs to the Special Issue Computational Methods for Medical and Cyber Security)

► Show Figures

Figure 1

20 pages, 1755 KiB

Open AccessArticle

Selection of the Right Undergraduate Major by Students Using Supervised Learning Techniques

by Alhuseen Omar Alsayed, Mohd Shafry Mohd Rahim, Ibrahim AlBidewi, Mushtaq Hussain, Syeda Huma Jabeen, Nashwan Alromema, Sadiq Hussain and Muhammad Lawan Jibril

Appl. Sci. 2021, 11(22), 10639; https://doi.org/10.3390/app112210639 - 11 Nov 2021

Cited by 13 | Viewed by 3887

Abstract

University education has become an integral and basic part of most people preparing for working life. However, placement of students into the appropriate university, college, or discipline is of paramount importance for university education to perform its role. In this study, various explainable [...] Read more.

University education has become an integral and basic part of most people preparing for working life. However, placement of students into the appropriate university, college, or discipline is of paramount importance for university education to perform its role. In this study, various explainable machine learning approaches (Decision Tree [DT], Extra tree classifiers [ETC], Random forest [RF] classifiers, Gradient boosting classifiers [GBC], and Support Vector Machine [SVM]) were tested to predict students’ right undergraduate major (field of specialization) before admission at the undergraduate level based on the current job markets and experience. The DT classifier predicts the target class based on simple decision rules. ETC is an ensemble learning technique that builds prediction models by using unpruned decision trees. RF is also an ensemble technique that uses many individual DTs to solve complex problems. GBC classifiers and produce strong prediction models. SVM predicts the target class with a high margin, as compared to other classifiers. The imbalanced dataset includes secondary school marks, higher secondary school marks, experience, and salary to select specialization for students in undergraduate programs. The results showed that the performances of RF and GBC predict the student field of specialization (undergraduate major) before admission, as well as the fact that these measures are as good as DT and ETC. Statistical analysis (Spearman correlation) is also applied to evaluate the relationship between a student’s major and other input variables. The statistical results show that higher student marks in higher secondary (hsc_p), university degree (Degree_p), and entry test (etest_p) play an important role in the student’s area of specialization, and we can recommend study fields according to these features. Based on these results, RF and GBC can easily be integrated into intelligent recommender systems to suggest a good field of specialization to university students, according to the current job market. This study also demonstrates that marks in higher secondary and university and entry tests are useful criteria to suggest the right undergraduate major because these input features most accurately predict the student field of specialization. Full article

(This article belongs to the Special Issue Computational Methods for Medical and Cyber Security)

► Show Figures

Figure 1

Review

Jump to: Research

25 pages, 5659 KiB

Open AccessReview

A Comparative Analysis of Big Data Frameworks: An Adoption Perspective

by Madiha Khalid and Muhammad Murtaza Yousaf

Appl. Sci. 2021, 11(22), 11033; https://doi.org/10.3390/app112211033 - 22 Nov 2021

Cited by 11 | Viewed by 4965

Abstract

The emergence of social media, the worldwide web, electronic transactions, and next-generation sequencing not only opens new horizons of opportunities but also leads to the accumulation of a massive amount of data. The rapid growth of digital data generated from diverse sources makes [...] Read more.

The emergence of social media, the worldwide web, electronic transactions, and next-generation sequencing not only opens new horizons of opportunities but also leads to the accumulation of a massive amount of data. The rapid growth of digital data generated from diverse sources makes it inapt to use traditional storage, processing, and analysis methods. These limitations have led to the development of new technologies to process and store very large datasets. As a result, several execution frameworks emerged for big data processing. Hadoop MapReduce, the pioneering framework, set the ground for forthcoming frameworks that improve the processing and development of large-scale data in many ways. This research focuses on comparing the most prominent and widely used frameworks in the open-source landscape. We identify key requirements of a big framework and review each of these frameworks in the perspective of those requirements. To enhance the clarity of comparison and analysis, we group the logically related features, forming a feature vector. We design seven feature vectors and present a comparative analysis of frameworks with respect to those feature vectors. We identify use cases and highlight the strengths and weaknesses of each framework. Moreover, we present a detailed discussion that can serve as a decision-making guide to select the appropriate framework for an application. Full article

(This article belongs to the Special Issue Computational Methods for Medical and Cyber Security)

► Show Figures

Figure 1

19 pages, 1535 KiB

Open AccessReview

Trends and Directions of Financial Technology (Fintech) in Society and Environment: A Bibliometric Study

by Adeel Nasir, Kamran Shaukat, Kanwal Iqbal Khan, Ibrahim A. Hameed, Talha Mahboob Alam and Suhuai Luo

Appl. Sci. 2021, 11(21), 10353; https://doi.org/10.3390/app112110353 - 04 Nov 2021

Cited by 23 | Viewed by 6387

Abstract

The contemporary innovations in financial technology (fintech) serve society with an environmentally friendly atmosphere. Fintech covers an enormous range of activities from data security to financial service deliverables that enable the companies to automate their existing business structure and introduce innovative products and [...] Read more.

The contemporary innovations in financial technology (fintech) serve society with an environmentally friendly atmosphere. Fintech covers an enormous range of activities from data security to financial service deliverables that enable the companies to automate their existing business structure and introduce innovative products and services. Therefore, there is an increasing demand for scholars and professionals to identify the future trends and directions of the topic. This is why the present study conducted a bibliometric analysis in social, environmental, and computer sciences fields to analyse the implementation of environment-friendly computer applications to benefit societal growth and well-being. We have used the ‘bibliometrix 3.0’ package of the r-program to analyse the core aspects of fintech systematically. The study suggests that ‘ACM International Conference Proceedings’ is the core source of published fintech literature. China leads in both multiple and single country production of fintech publications. Bina Nusantara University is the most relevant affiliation. Arner and Buckley provide impactful fintech literature. In the conceptual framework, we analyse relationships between different topics of fintech and address dynamic research streams and themes. These research streams and themes highlight the future directions and core topics of fintech. The study deploys a co-occurrence network to differentiate the entire fintech literature into three research streams. These research streams are related to ‘cryptocurrencies, smart contracts, financial technology’, ‘financial industry stability, service, innovation, regulatory technology (regtech)’, and ‘machine learning and deep learning innovations’. The study deploys a thematic map to identify basic, emerging, dropping, isolated, and motor themes based on centrality and density. These various themes and streams are designed to lead the researchers, academicians, policymakers, and practitioners to narrow, distinctive, and significant topics. Full article

(This article belongs to the Special Issue Computational Methods for Medical and Cyber Security)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Computational Methods for Medical and Cyber Security

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (11 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI