Diabetes is a dreadful disease identified by escalated levels of glucose in the blood Machine learning algorithms help in identification and prediction of diabetes at an early stage The main objective of this study is to predict diabetes mellitus with better accuracy using an ensemble of machine learning algorithms The Pima Indians Diabetes dataset has been considered for experimentation, which gathers details of patients with and without having diabetes The proposed ensemble soft voting classifier gives binary classification and uses the ensemble of three machine learning algorithms viz random forest, logistic regression, and Naive Bayes for the classification Empirical evaluation of the proposed methodology has been conducted with state-of-the-art methodologies and base classifiers such as AdaBoost, Logistic Regression,Support Vector machine, Random forest, Naive Bayes, Bagging, GradientBoost, XGBoost, CatBoost by taking accuracy, precision, recall, F1-score as the evaluation criteria The proposed ensemble approach gives the highest accuracy, precision, recall, and F1_score value with 7904%, 7348%, 7145% and 806% respectively on the PIMA diabetes dataset Further, the efficiency of the proposed methodology has also been compared and analysed with breast cancer dataset The proposed ensemble soft voting classifier has given 9702% accuracy on the breast cancer dataset

An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier

Data mining (DM) is an instrument of pattern detection and retrieval of knowledge from a large quantity of data. Many robust early detection services and other health-related technologies have developed from clinical and diagnostic evidence in both the DM and healthcare sectors. Artificial Intelligence (AI) is commonly used in the research and health care sectors. Classification or predictive analytics is a key part of AI in machine learning (ML). Present analyses of new predictive models founded on ML methods demonstrate promise in the area of scientific research. Healthcare professionals need accurate predictions of the outcomes of various illnesses that patients suffer from. In addition, timing is another significant aspect that affects clinical choices for precise predictions. In this regard, the authors have reviewed numerous publications in this area in terms of method, algorithms, and performance. This review paper summarized the documentation examined in accordance with approaches, styles, activities, and processes. The analyses and assessment techniques of the selected papers are discussed and an appraisal of the findings is presented to conclude the article. Present statistical models of healthcare remedies have been scientifically reviewed in this article. The uncertainty between statistical methods and ML has now been clarified. The study of related research reveals that the prediction of existing forecasting models differs even if the same dataset is used. Predictive models are also essential, and new approaches need to be improved.

Smart healthcare disease diagnosis and patient management: Innovation, improvement and skill development

The large number of vehicles constantly seeking access to congested areas in cities means that finding a public parking place is often difficult and causes problems for drivers and citizens alike. In this context, strategies that guide vehicles from one point to another, looking for the most optimal path, are needed. Most contributions in the literature are routing strategies that take into account different criteria to select the optimal route required to find a parking space. This paper aims to identify the types of smart parking systems (SPS) that are available today, as well as investigate the kinds of vehicle detection techniques (VDT) they have and the algorithms or other methods they employ, in order to analyze where the development of these systems is at today. To do this, a survey of 274 publications from January 2012 to December 2019 was conducted. The survey considered four principal features: SPS types reported in the literature, the kinds of VDT used in these SPS, the algorithms or methods they implement, and the stage of development at which they are. Based on a search and extraction of results methodology, this work was able to effectively obtain the current state of the research area. In addition, the exhaustive study of the studies analyzed allowed for a discussion to be established concerning the main difficulties, as well as the gaps and open problems detected for the SPS. The results shown in this study may provide a base for future research on the subject.

Survey of Smart Parking Systems

The Internet plays an increasingly important role in people's lives, but it also brings security problems. CAPTCHA, which stands for Completely Automated Public Turing Test to Tell Computers and Humans Apart, has been widely used as a security mechanism. This paper outlines the scientific and technological progress in both the design and attack of CAPTCHAs related to these three CAPTCHA categories. It first presents a comprehensive survey of recent developments for each CAPTCHA type in terms of usability, robustness and their weaknesses and strengths. Second, it summarizes the attack methods for each category. In addition, the differences between the three CAPTCHA categories and the attack methods will also be discussed. Lastly, this paper provides suggestions for future research and proposes some problems worthy of further study.

A Survey of Research on CAPTCHA Designing and Breaking Techniques

Smart cities employ modern technology to manage and enhance resources effectively. Urban parking facilities are one of the critical assets that need to be managed. Management of parking and congestion is insufficient and requires further investigation. A smart parking management system has developed to solve parking issues efficiently and apply technical solutions to improve different aspects of smart cities. The overall system architecture and environment are specified to provide the framework for a complete design. The proposed system provides multiple facilities, including searching for parking slots, reservation, payment, receiving notifications, showing statistics and monitoring parking states. It applies concepts of the Internet of Things (IoT) by using supportable hardware and sensors to detect parking availability and recognition to control access processes. This approach is expected to reduce costs and efforts in the long term and improve the standard of living of a city's citizens.

UParking: Developing a Smart Parking Management System Using the Internet of Things

The growing urbanization accompanied by increasingly congested urban spaces and huge growth in the number of urban vehicles, has resulted in the need for secure parking spaces. In this paper, a solution is provided for preventing theft of vehicle from parking using RFID and GSM technology. There is a huge amount of reduction in transaction cost with radio frequency identification technology in automation. This solution includes components like GSM kit, RFID readers, RFID tags, barrier gates, computers, Software and LED lights. This system is used for controlling GSM kit, operating barriers and glowing LEDs in different cases. This system is independent and can work in any kind of organization. This system can prevent theft of the vehicle in an organization. Members of the organization can feel secure for their vehicles. Check-ins and check-outs will be controlled by the software on the basis of smart card and RFID vehicle Tag. Authorized member will be informed in case of any theft activity through SMS and alarm will ring for security alert.

Smart parking system using RFID and GSM technology

Machine Learning Techniques are gaining a lot of momentum in constant improvement of disease diagnosis. In this study, we have investigated the discriminative performance of ensemble learning model for diabetes prediction at an early stage. We have used different machine learning models and then ensemble it to improve the overall prediction accuracy. The dataset used is NHANES 2013-14 comprising of 10,172 samples and 54 feature variables for diabetes section. The feature variables used are in the form of questionnaire, a set of questions suggested by NHANES (National Health and Nutrition Examination Survey). An Ensemble model using majority voting technique was developed by combining the unweighted prediction probabilities of different machine learning models. Also, the model is evaluated and validated for real user input data for user friendliness. The overall performance was improved by Ensemble Model and had an AUC (Area under Curve) of 0.75 indicating high performance.

Early Diabetes Prediction Using Voting Based Ensemble Learning

As this century marked the beginning of new era in the world of Internet, the need for user authentication system becomes a basic requirement to ensure secure communication with confidentiality and integrity. With the development of authentication systems, the techniques for intruding are also developed by hackers in parallel. So, in order to prevent or at least minimize the attacks, many encryption techniques and authentication schemes also came into existence. This paper also describes one such novel scheme using text-based authentication. Firstly, the present scenario in the context of authentication system and different methods of hacking and breaking into the system are demarcated. Then proposed scheme is mentioned along with the discussion of various features and security issues exposed by this scheme. This scheme will be a time-saving and efficient alternative on measures of user-friendliness and convenience to current authentication system. It can be used in bank ATMs, and other public and private organizations. The aim is to provide fast and efficient method at user convenience so that it can be deployed in various activities relating to common users.

One-Tip Secure: Next-Gen of Text-Based Password

Text-based password authentication scheme is vulnerable to many attacks such as shoulder surfing attack and similar kind of attacks like dictionary attack, brute-force attack etc. Many graphic based password authentication schemes are there but they are also quite expensive in deployment and needs more response time at login phase. In this paper, a more secure pattern-key based password authentication scheme is proposed which provides more security using combination of pattern, key, and dummy digits. For this, user needs to recognize and register pattern in the form of location numbers from grid, register key values that maps values to password and add dummy values to password so as to misguide the attacker. After that, to login, user needs to recall the pattern and maps the textual password from pattern with registered key values, creating a password by adding dummy digits. It minimizes the shoulder surfing, brute-force attacks etc due to high complexity of guessing password in multi-levels: first from pattern, then from key and then from dummy values. This scheme is resistant to usability issues such that it does not overload human memory and provides extra security against anonymous attackers.

Secure pattern-key based password authentication scheme

In recent times, there is a pressing needs to develop more robust and efficient user authentication techniques in order to protect the confidentiality and integrity of crucial information. Thus, many new techniques are being developed like graphical passwords, two-step verification, and others. In this domain, the conventional text-based passwords are often criticized and considered less secure but surprisingly they are still the most common authentication technique. This popularity is due to their ease of implementation and use. In this paper, we have proposed new text-based user authentication technique using CAPTCHA. This technique overcomes most of the challenges faced by both conventional and contemporary authentication methods and offers a higher level of security than them. The password is user-friendly, quick and easy to compute, and more secure.

Muneeb Hasan Khan

Papers

Smart parking system using RFID and GSM technology

Early Diabetes Prediction Using Voting Based Ensemble Learning

One-Tip Secure: Next-Gen of Text-Based Password

Secure pattern-key based password authentication scheme

New Text-Based User Authentication Scheme Using CAPTCHA