Data Mining - Concepts and Techniques.

Impact of Trust and Privacy Concerns on Technology Acceptance in Healthcare: An Indian Perspective

We may not be able to make you love reading, but software measurement and estimation a practical approach will lead you to love reading starting from now. Book is the window to open the new world. The world that you want is in the better stage and level. World will always guide you to even the prestige stage of the life. You know, this is some of how reading will give you the kindness. In this case, more books you read more knowledge you know, but it can mean also the bore is full.

Software Measurement and Estimation: A Practical Approach

The healthcare industry gathers gigantic volumes of healthcare data, which can be turned into useful information by using different Data mining techniques. This knowledge can then be useful in many different decision making environments like Finance, Marketing, Healthcare sector. In health care industry, cardiovascular disease is one of the most significant but difficult task that needs to be done very swiftly, efficiently and the correct automation is desirable. In this regard, different Heart Disease Prediction systems have been reviewed and the work done previously have applied different numbers of medical parameters and risk factors with different data mining techniques. Accuracy claimed in each of those papers depends upon the number of parameters and data mining techniques applied. However, the number of the parameters and datasets to perform experiments was very small to claim high accuracy. We employed K-nearest neighbor classifier to achieve an accuracy of approximately 80% by using 14 attributes. Moreover, a number of predominant classifiers have been evaluated to highlight the supremacy of k-NN classifier based heart disease prediction system.

Efficient Heart Disease Prediction System using K-Nearest Neighbor Classification Technique

Heart diseases are currently a major cause of death in the world. This problem is severe in developing countries in Africa and Asia. A heart disease predicted at earlier stages not only helps the patients prevent it, but I can also help the medical practitioners learn the major causes of a heart attack and avoid it before its actual occurrence in patient. In this paper, we propose a method named CardioHelp which predicts the probability of the presence of cardiovascular disease in a patient by incorporating a deep learning algorithm called convolutional neural networks (CNN). The proposed method is concerned with temporal data modeling by utilizing CNN for HF prediction at its earliest stage. We prepared the heart disease dataset and compared the results with state-of-the-art methods and achieved good results. Experimental results show that the proposed method outperforms the existing methods in terms of performance evaluation metrics. The achieved accuracy of the proposed method is 97%.

Prediction of Heart Disease Using Deep Convolutional Neural Networks

Sustainable learning and education (SLE) is a relatively new ideology based on sustainability principles and developed in response to the United Nations’ recently proclaimed Sustainable Development Goals (SDGs). As a result, technologies should be adopted to equip educational institutions with the tools necessary to attain SLE. Recently, the coronavirus (COVID-19) pandemic has affected educational systems globally, leading them to embrace more innovative technological methods to meet academic demands while maintaining SLE principles. Mobile learning apps (MLA) refers to using the unique capabilities of mobile apps to engage and collaborate towards establishing robust online learning. However, the effectiveness of MLA depends on learners’ acceptance. Therefore, the purpose of this study is to investigate the factors that could affect MLA acceptance. In order to analyze the collected data from 415 Jordanian students among schools and universities, structural equation modeling (SEM) was used. The empirical findings confirm that perceived usefulness and perceived ease of use are significantly influenced by self-efficacy and perceived compatibility. Furthermore, perceived usefulness is significantly influenced by perceived convenience and perceived ease of use. Additionally, perceived enjoyment significantly influences the behavioral intention to use MLA. On the other hand, perceived compatibility has no significant influence on perceived enjoyment. Finally, perceived ease of use, perceived usefulness, and perceived compatibility have no significant effect on behavioral intention to use MLA. This study addresses a critical research gap in the distance learning acceptance literature by proposing an exhaustive model in the post-COVID-19 era that can help to improve students’ performance and outcomes in Jordanian schools and universities.

/pdf/an-empirical-investigation-of-reasons-influencing-student-2m9uqevv.pdf

An Empirical Investigation of Reasons Influencing Student Acceptance and Rejection of Mobile Learning Apps Usage

Improving the precision of heart diseases detection has been investigated by many researchers in the literature. Such improvement induced by the overwhelming health care expenditures and erroneous diagnosis. As a result, various methodologies have been proposed to analyze the disease factors aiming to decrease the physicians practice variation and reduce medical costs and errors. In this paper, our main motivation is to develop an effective intelligent medical decision support system based on data mining techniques. In this context, five data mining classifying algorithms, with large datasets, have been utilized to assess and analyze the risk factors statistically related to heart diseases in order to compare the performance of the implemented classifiers (e.g., Naive Bayes, Decision Tree, Discriminant, Random Forest, and Support Vector Machine). To underscore the practical viability of our approach, the selected classifiers have been implemented using MATLAB tool with two datasets. Results of the conducted experiments showed that all classification algorithms are predictive and can give relatively correct answer. However, the decision tree outperforms other classifiers with an accuracy rate of 99.0% followed by Random forest. That is the case because both of them have relatively same mechanism but the Random forest can build ensemble of decision tree. Although ensemble learning has been proved to produce superior results, but in our case the decision tree has outperformed its ensemble version.

A Comparative Study for Predicting Heart Diseases Using Data Mining Classification Methods.

Recent years have witnessed a widespread availability of electronic healthcare data record (EHR) systems. Vast amounts of health data were generated in the process of treatment in medical centers such hospitals, clinics, or other institutions. To improve the quality of healthcare service, EHRs could be potentially shared by a variety of users. This results in significant privacy issues that should be addressed to make the use of EHR practical. In fact, despite the recent research in designing standards and regulations directives concerning security and privacy in EHR systems, it is still, however, not completely settled out the privacy challenges. In this paper, a systematic literature review was conducted concerning the privacy issues in electronic healthcare systems. More than 50 original articles were selected to study the existing security approaches and figure out the used security models. Also, a novel Context-aware Access Control Security Model (CARE) is proposed to capture the scenario of data interoperability and support the security fundamentals of healthcare systems along with the capability of providing fine-grained access control.

/pdf/security-and-privacy-issues-in-ehealthcare-systems-towards-5b6l2mnltj.pdf

Security and Privacy Issues in Ehealthcare Systems: Towards Trusted Services

Patients taking medical treatment in distinct healthcare institutions have their information deeply fragmented between very different locations. All this information --- probably with different formats --- may be used or exchanged to deliver professional healthcare services. As the exchange of information/ interoperability is a key requirement for the success of healthcare process, various predefined e-health standards have been developed. Such standards are designed to facilitate information interoperability in common formats. Fast Healthcare Interoperability Resources (FHIR) is a newly open healthcare data standard that aims to providing electronic healthcare interoperability. FHIR was coined in 2014 to address limitations caused by the ad-hoc implementation and the distributed nature of modern medical care information systems. Patient’s data or resources are structured and standard in FHIR through a highly readable format such as XML or JSON. However, despite the unique features of FHIR, it is not a security protocol, nor does it provide any security-related functionality. In this paper, we propose a security specification model (SecFHIR) to support the development of intuitive policy schemes that are mapping directly to the healthcare environment. The formal semantics for SecFHIR are based on the well-established typing and the independent platform properties of XML. Specifically, patients’ data are modeled in FHIR using XML documents. In our model, we assume that these XML resources are defined by a set of schemes. Since XML Schema is a well-formed XML document, the permission specification can be easily integrated to the schema itself, then the specified permissions are applied to instance objects without any change. In other words, our security model (SecFHIR) defines permissions on XML schemes level, which implicitly specify the permissions on XML resources. Using these schemes, SecFHIR can combine them to support complex constraints over XML resources. This will result in reusable permissions, which efficiently simplify the security administration and achieve fine-grained access control. We also discuss the core elements of the proposed model, as well as the integration with the FHIR framework

/pdf/secfhir-a-security-specification-model-for-fast-healthcare-3suluac0sq.pdf

SecFHIR: A Security Specification Model for Fast Healthcare Interoperability Resources

Our social life and the way of people communicate are greatly affected by the social media technologies. The variety of stand-alone and built-in social media services such as Facebook, Twitter, LinkedIn, and alike facilitate users to create highly interactive platforms. However, these overwhelming technologies made us sank in an enormous amount of information. Recently, Facebook exposed data on 50 million Facebook unaware users for analytical purposes. Fake profiles are also used by Scammers to infiltrate networks of friends to wreak all sorts of havoc as stealing valuable information, financial fraud, or entering other user's social graph. In this paper, we turn our focus to Facebook fake profiles, and proposed a smart system (FBChecker) that enables users to check if any Facebook profile is fake. To achieve that, FBChecker utilizes the data mining approach to analyze and classify a set of behavioral and informational attributes provided in the personal profiles. Specifically, we empirically examine these attributes using four supervised data mining algorithms (e.g., k-NN, decision tree, SVM, and naive Bayes) to determine how successfully we can recognize the fake profiles. To demonstrate the validity of our conceptual work, the selected classifiers have been implemented using RapidMiner data science platform with a dataset of 200 profiles collected from the authors’ profile and a honeypot page. Two experiments are developed; in the first one, the k-NN schema is applied as an estimator model for imputation the missing data with substituted values, whereas in the second experiment a filtering operator is applied to exclude the profiles with missing values. Results showed high accuracy rate with the all classifiers, however, the SVM outperforms other classifiers with an accuracy rate of 98.0% followed by Naive Bayes.

/pdf/an-empirical-study-for-detecting-fake-facebook-profiles-5beqvbr3wk.pdf

Ahmad Mousa Altamimi

Papers

An Empirical Investigation of Reasons Influencing Student Acceptance and Rejection of Mobile Learning Apps Usage

A Comparative Study for Predicting Heart Diseases Using Data Mining Classification Methods.

Security and Privacy Issues in Ehealthcare Systems: Towards Trusted Services

SecFHIR: A Security Specification Model for Fast Healthcare Interoperability Resources

An Empirical Study for Detecting Fake Facebook Profiles Using Supervised Mining Techniques