Utilisation of Machine Learning Techniques in Testing and Training of Different Medical Datasets

On our planet, chemical waste increases day after day, the emergence of new types of it, as well as the high level of toxic pollution, the difficulty of daily life, the increase in the psychological state of humans, and other factors all have led to the emergence of many diseases that affect humans, including deadly once like COVID-19 disease. Symptoms may appear on a person, and sometimes they may not; some people may know their condition, and others may neglect their health status due to lack of knowledge that may lead to death, or the disease may be chronic for life. In this regard, the author executes machine learning techniques (Support Vector Machine, C5.0 Decision Tree, K-Nearest Neighbours, and Random Forest) due to their influence in medical sciences to identify the best technique that gives the highest level of accuracy in detecting diseases. Thus, this technique will help to recognise symptoms and diagnose them correctly. This article covers a dataset from the UCI machine learning repository, namely the Wisconsin Breast Cancer dataset, Chronic Kidney disease dataset, Immunotherapy dataset, Cryotherapy dataset, Hepatitis dataset and COVID-19 dataset. In the results section, a comparison is made between the execution of each technique to find out which one is the best and which one is the worst in the performance of analysis related to the dataset of each disease.

Task Scheduling Management for Load Balancing Using Task Grouping Based on Cloud Computing

Managing task scheduling management in cloud computing is an essential part for the landscape of complex procedure tasks based on various resources in a proficient and scalable path. The aim of this research is to dynamically optimize the aforesaid issue of task scheduling. The task management improvises the imperfection algorithm by pursue on weighted fair queuing model, which is significantly effective compared to the existing method. A task scheduling model has been created to demonstrate the proposed scheduler management. Study shows the improvement in the adaptation of round robin and shortest job first algorithm performing better than the existing algorithm according to the differentiate execution measurements such as, turnaround time, task size and average waiting time. In addition, context switches play an important role in algorithm by sharing between multiple tasks and running task in the scheduler. Altogether, a significant improvement between existing algorithm and proposed studies follows up accordingly to a specific context switching takes place.

Computer Self-Efficacy and Facilitating Conditions as Correlates of Behavioural Intention to Use Electronic Information Resources by Master of Business Administration Students in Federal Universities in Nigeria

The focus of this research work was to investigate computer self-efficacy and facilitating conditions as correlates of behavioural intention to use electronic information resources by MBA students in Nigeria federal universities. Cluster sampling technique was adopted for the study and systematic sampling technique was used to select 60% of the total population of the MBA students across the ten federal universities offering the programme based on probability and proportionate size. Data were collected using questionnaire designed to elicit response from respondents and analysed using Pearson Product Moment Correlation Analysis, Multiple Regression Analysis using Partial Lease Square Method (PLSEM), Mean, Standard Deviation and Percentages. However, out of one thousand two hundred and seventy (1,270) copies of questionnaire administered to the respondents, one thousand and fifteen copies (1,015) were returned which represents 79.9% response rate for the study. Findings revealed that the level computer self-efficacy and facilitating conditions of MBA students towards use of electronic information resources in Nigeria federal universities was high. However, the study concluded that university managements and librarians should ensure rapid adoption and diffusion of ICTs and be proactive by developing relevant ICT policies and strategies toward effective and sustainable electronic information resources development in Nigerian universities, as well as promoting the use of relevant electronic information resources by MBA students to improve their quality of research and global competitiveness.

Software Functional Complexity Using a New Set of Criteria

With the rapid technology advances, there is an emerging consensus that the size and complexity of software designs are increasing so rapidly that they proportionally affect the magnitude of administrative and development efforts. An important consideration is how to estimate software complexity. This subject continues to be a research topic in the literature. The software design process researched here uses the Unified Modeling Language (UML) diagrams and the database design for extracting pertinent information. The Entity Relationship (ER) model of Peter Chen (of MIT) is a conceptual method of describing the data in a relational structure. An Entity Relationship Diagram (ERD) and an Entity Relationship Schema (ERS) represents the ER model, containing the entities, attributes, primary and foreign keys, and the relationships between the entities. Extending this ERS modeling construct, this paper uses an additional enhanced schema, called the Object Relationship Schema (ORS), which, together with the existing ERS, creates an enhanced view of the requirements and the design of the database. In addition, functional dependency, security, computational complexity, use cases, component structure and interpretations are considered for estimating functional complexity of modern software systems which is very valuable in higher education for new workforce development.

Credit Card Fraud Detection in Payment Using Machine Learning Classifiers

The fraud detection in payment is a classification problem that aims to identify fraudulent transactions based individually on the information it contains and on the basis that a fraudster's behaviour patterns differ significantly from that of the actual customer. In this context, the authors propose to implement machine learning classifiers (Naïve Bayes, C4.5 decision trees, and Bagging Ensemble Learner) to predict the outcome of regular transactions and fraudulent transactions. The performance of these classifiers is judged by the following ways: precision, recall rate, and precision-recall curve (PRC) area rate. The dataset includes more than 297K transactions via credit cards in September 2013 and November 2017 that have been collected from Kaggle platform, of which 3293 are frauds. The performance PRC ratio of machine learning classifiers is between 99.9% and 100%, which confirms that these classifiers are very good at identifying binary classes 0 in the dataset. The results of the tests have proved that the best classifier is C4.5 decision trees. This classifier has the best accuracy of 94.12% in prediction of fraudulent transactions.

A Hybrid Relational Database Model for Uncertain and Imprecise Information

Recent years, many fuzzy or probabilistic database models have been built for representing and handling imprecise or uncertain information of objects in real-world applications. However, relational database models combining the relevance and strength of both fuzzy set and probability theories have rarely been proposed. This paper introduces a new relational database model, as a hybrid one combining consistently fuzzy set theory and probability theory for modeling and manipulating uncertain and imprecise information, where the uncertainty and imprecision of a relational attribute value are represented by a fuzzy probabilistic triple, the computation and combination of relational attribute values are implemented by using the probabilistic interpretation of binary relations on fuzzy sets, and the elimination of redundant data is dealt with by coalescing e-equivalent tuples. The basic concepts of the classical relational database model are extended in this new model. Then the relational algebraic operations are formally defined accordingly. A set of the properties of the relational algebraic operations is also formulated and proven.

Character Segmentation Of Degraded Odia Script

Optical Character Recognition (OCR) is a field which converts printed text into computer understandable format that is editable in nature. Odia is a regional language used in Odisha, West Bengal & Jharkhand. It is used by over forty million people and still counting. With such large dependency on a language makes it important, to preserve its script, get a digital editable version of odia script. We propose a framework that takes computer printed odia script image as an input & gives a computer readable & user editable format of same, which eventually recognizes the characters printed in input image. The system uses various techniques to improve the image & perform Line segmentation followed by word segmentation & finally character segmentation using horizontal & vertical projection profile.

Adaptive Electrocardiogram Steganography Based on 2D Approach with Predetermined Rules

Based on two-dimensional (2D) bit-embedding/-extraction approach, we propose a simple data hiding for electrocardiogram (ECG) signal. The patient’s sensitive (diagnostic) data can be efficiently hidden into 2D ECG host via the proposed decision rules. The performance of the proposed method using various sizes of the host bundles was demonstrated. Simulations have confirmed that the average SNR of the proposed method with a host bundle of size 3 ´ 3 is superior to that of existing techniques, while our payload is competitive to theirs. In addition, our method with a host bundle of size 2 ´  2 generated the best SNR values, while that with a host bundle of size 4 ´  4 provided the largest payload among the compared methods. Moreover, the proposed method provides robustness performance better than existing ECG steganography. Namely, our method provides high hiding capacity and robust against the attacks such as cropping, inversion, scaling, translation, truncation, and Gaussian noise-addition attacks. Since the proposed method is simple, it can be employed in real-time applications such as portable biometric devices.

Analysis of Mobile App Revenue Models Used in the most Popular Games of the Tower Defense Genre on Google Play

This paper analyzes the revenue models of the most popular games of the Tower Defense genre on Google Play. A special look is taken at the quantitative distribution of the app sale model and the free model in terms of quality and download numbers. Additionally, this paper considers the qualitative implementation of the “free” model in the most popular games. First, the usual revenue models of mobile apps will be discussed and then the Tower Defense genre will be explained. Following that, the quantitative distribution of revenue models and an analysis of the most popular apps’ respective revenue models will be addressed. The analysis also identifies and explains two modifications of established revenue models. The most popular revenue model for mobile apps in the Tower Defense genre are in-app purchases. This distinguishes the genre from many other genres and games. A wide range of Tower Defense games utilizes the revenue models app sale and free. It becomes apparent that revenue models for mobile apps must be analyzed and considered specifically for their respective sector, and that no single promising revenue model for apps exists.

Ergonomics and Ergonomic Analysis of Driving Education System by Personal Car-2

The subject of IT-supported car training/education system was selected for the research below in the previous article. For the well-known hypothesis, out of the three existing parts, the driver-machine-car subsystem was first selected to handle the theoretical hypothesis; presented later. Thus, the following eight subsystems or parts for human participants are listed: nerve area; sense of sight or visual organ of the eye; hearing aid or hearing organ ear; motion observations; psychological factors, mental and psychomotor properties; individuals' reactions and causes of reactions; types of drivers; the influence of alcohol on road safety. In the practical part of the article, based on the vast amount of data, several analyzes were conducted. The vast amount of data requires multiple publication of the complete content of the thesis, where each new content unit / article must have both parts, both theoretically and practically. To our knowledge, a unique list of 19 types of errors was made, with a detailed description of them. The terms of different types of driving are explained in particular: polygon, city traffic and examinations, as well as the differences between them. In the series of analysis, the terms driving type, teaching unit, candidate and driving hours were taken as the independent variable, while the error types with the predominant frequency characteristic were taken as the dependent variable. Practical parts are supported with IT processing. Appropriate ideas and measures for improvement have been proposed. The articles gratefully acknowledges Prof. B.Sc. Marijan Biščanić and prof. Ph.D. Dragutin Mikšić for their contribution.