Cardiovascular diseases are considered as the most life-threatening syndromes with the highest mortality rate globally. Over a period of time, they have become very common and are now overstretching the healthcare systems of countries. The major factors of cardiovascular diseases are high blood pressure, family history, stress, age, gender, cholesterol, Body Mass Index (BMI), and unhealthy lifestyle. Based on these factors, researchers have proposed various approaches for early diagnosis. However, the accuracy of proposed techniques and approaches needs certain improvements due to the inherent criticality and life threatening risks of cardiovascular diseases. In this article, a MaLCaDD (Machine Learning based Cardiovascular Disease Diagnosis) framework is proposed for the effective prediction of cardiovascular diseases with high precision. Particularly, the framework first deals with the missing values (via mean replacement technique) and data imbalance (via Synthetic Minority Over-sampling Technique -SMOTE). Subsequently, Feature Importance technique is utilized for feature selection. Finally, an ensemble of Logistic Regression and K-Nearest Neighbor (KNN) classifiers is proposed for prediction with higher accuracy. The validation of framework is performed through three benchmark datasets (i.e. Framingham, Heart Disease and Cleveland) and the accuracies of 99.1%, 98% and 95.5 % are achieved respectively. Finally, the comparative analysis prove that MaLCaDD predictions are more accurate (with reduced set of features) as compared to the existing state-of-the-art approaches. Therefore, MaLCaDD is highly reliable and can be applied in real environment for the early diagnosis of cardiovascular diseases.

Code cloning refers to the duplication of source code. It is the most common way of reusing source code in software development. If a bug is identified in one segment of code, all the similar segments need to be checked for the same bug. Consequently, this cloning process may lead to bug propagation that significantly affects the maintenance cost. By considering this problem, code clone detection (CCD) appears as an active area of research. Consequently, there is a strong need to investigate the latest techniques, trends, and tools in the domain of CCD. Therefore, in this paper, we comprehensively inspect the latest tools and techniques utilized for the detection of code clones. Particularly, a systematic literature review (SLR) is performed to select and investigate 54 studies pertaining to CCD. Consequently, six categories are defined to incorporate the selected studies as per relevance, i.e., textual approaches (12), lexical approaches (8), tree-based approaches (3), metric-based approaches (7), semantic approaches (7), and hybrid approaches (17). We identified and analyzed 26 CCD tools, i.e., 13 existing and 13 proposed/developed. Moreover, 62 open-source subject systems whose source code is utilized for the CCD are presented. It is concluded that there exist several studies to detect type1, type2, type3, and type4 clones individually. However, there is a need to develop novel approaches with complete tool support in order to detect all four types of clones collectively. Furthermore, it is also required to introduce more approaches to simplify the development of a program dependency graph (PDG) while dealing with the detection of the type4 clones.

Due to the rising popularity of the Internet of Things (IoT), interconnected infrastructures with better flexibility and efficiency are being developed for industry 4.0. The use of IoT in industry 4.0 introduces a new term “Industrial IoT (IIoT)”, which allows remote monitoring of wide-ranging industrial processes. IIoT tends to function with a large number of heterogeneous devices, therefore, data interoperability is the biggest challenge in achieving seamless real-time communication. To achieve data interoperability, there is a need to integrate various IoT application layer protocols; separately, as well as, with other data acquisition protocols along with hardware/software platforms. Although such integrations are frequently presented in the state-of-the-art, a comprehensive investigation and analysis of such approaches in single research work are hard to find. Therefore, in this article, a Systematic Literature Review (SLR) is presented by investigating 34 influential research works, published during 2014-2020, where interoperability of application layer protocols is performed for IIoT. Consequently, the selected research studies are divided into three categories: 1) Integration of IoT application layer protocols— 13 papers; 2) Integration of IoT and data acquisition protocols—6 papers; 3) Integration of IoT protocols with hardware/software platforms—15 papers to resolve interoperability issues. Moreover, nineteen (19) tools used for integration in the selected research works are identified. Furthermore, leading approaches to perform such integrations are recognized, e.g., Gateways. It has been concluded that although researchers frequently propose centralized (e.g., gateway or protocol converter) and distributed intermediator (e.g., Middleware) to achieve required interoperability for IIoT, it is a need of a day to develop a device level solution without the involvement of intermediator. This will solve different interoperability problems in industries like scalability, load balancing, and a single point of failure.

Automation of any business process primarily requires the identification of clear and precise requirements. However, the initially collected business requirements are usually expressed in natural language that creates ambiguities among different stakeholders. To overcome this problem, various business process modeling languages (BPMLs) have been introduced to represent the business requirements graphically. In this context, event-driven process chain (EPC) is a well-known BPML that supports the modeling and verification of business requirements in early automation phases. Although EPC is frequently researched to improve its modeling and verification capabilities, there is no study available yet to the best of our knowledge that examines and summarizes the latest EPC developments. Therefore, in this article, we comprehensively investigate the latest EPC approaches, trends, and tools for the modeling and verification of business requirements. Particularly, a systematic literature review is carried out to select and analyze 73 research studies published during 1998-2017. Consequently, the selected studies are classified into six categories, i.e., modeling (14), transformation (13), verification (17), general (20), semantics (5), and requirement (4). Moreover, latest EPC modeling approaches are identified and analyzed, i.e., UML (2), meta-model (3), integration (5), and EPC notations (4). Furthermore, EPC verification methods are also investigated, i.e., EPC (6), petri-nets (8), and other languages (3). Finally, 25 leading EPC tools have been presented, i.e., existing tools (14), proposed/developed tools, (5) and additional tools (6). It has been concluded that EPC provides adequate approaches and tool support for the modeling and verification of simple business requirements through atomic events. However, the complex business requirements cannot be modeled and verified through EPC due to the lack of complex event processing. Consequently, there is a strong need to include the support for the modeling and verification of complex events in EPC to manage multifaceted business requirements.