One of the significant issues that the world has faced in recent decades has been the estimation of water quality and location where safe drinking water is available. Due to the unexpected nature of the mode of water contamination, it is not easy to analyze the quality and maintain it. Some machine-learning techniques are used for predicting contaminating factors but there is no technique that can predict the contamination using latitude, longitude, and elevation. The main aim of this paper is to put factors such as water body location and elevation, which are used as inputs, into the different machine-learning techniques that predict the contamination. The results are reviewed and analyzed according to groundwater contamination and the chemical composition of the groundwater location. Non-changeable factors such as latitude, longitude, and elevation are used to predict pH, temperature, turbidity, dissolved oxygen hardness, chlorides, alkalinity, and chemical oxygen demand. Such a study has not been conducted in the past where location-based factors are used to predict the water contamination of any area. This research focuses on creating a relationship between the location base factors affecting the water contamination in a given area.

The academic institutions are focusing more on improving the performance of students using various data mining techniques. Prediction models are designed to predict the performance of students at a very early stage so that preventive measures can be taken beforehand. Various parameters (academic as well as non-academic) are considered to predict the student performance using different classifiers. Normally, academic parameters are given more weightage in predicting the academic performance of a student. This paper compares the two models: one built using academic parameters only and another using both academic and non-academic (demographic) parameters. The primary data set of students has been taken from a technical college in India, which consists of data of 6,807 students containing attributes. Synthetic minority oversampling technique filter is applied to deal with the skewed data set. The models are built using eight classification algorithms that are then compared to find the parameters that help to give the most appropriate model to classify a student based on his performance.

Wind speed forecasting is the term used for predicting speed of wind to generate wind power. Deep learning, which is the subfield of machine learning and is used to implement on a large data sets and predictions made using deep learning with LSTM can increases the accuracy rate to the great extent. The combination of deep learning with LSTM can enhances the prediction rate as due to the property of LSTM of pattern remembrance for longer duration of time. This survey discusses the existing functionality measures of different approaches by partitioning them into various methodologies: models of very small time gap, small time gap, and longtime gap. All these approaches include certain models with various parameters, advantages and disadvantages are discussed. The focus of this survey is to present a better and efficient evaluation of various approaches to help the researcher to select best model out of all present models.

Purpose: Recently, blockchain technology (BT) has resolved healthcare data management challenges. It helps healthcare providers automate medical records and mining to aid in data sharing and making more accurate diagnoses. This paper attempts to identify the critical success factors (CSFs) for successfully implementing BT in healthcare.Design/methodology/approach: The paper is methodologically structured in four phases. The first phase leads to identifying success factors by reviewing the extant literature. In the second phase, expert opinions were solicited to authenticate the critical success factors required to implement BT in the healthcare sector. Decision Making Trial and Evaluation Laboratory (DEMATEL) method was employed to find the cause-and-effect relationship among the third phase’s critical success factors. In phase 4, the authors resort to validating the final results and findings.Findings: Based on the analysis, 21 CSFs were identified and grouped under six dimensions. After applying the DEMATEL technique, nine factors belong to the causal group, and the remaining 12 factors fall under the effect group. The top three influencing factors of blockchain technology implementation in the healthcare ecosystem are data transparency, track and traceability and government support, whereas; implementation cost was the least influential.Originality/value: This study provides a roadmap and may facilitate healthcare professionals to overcome contemporary challenges with the help of BT.

In computer networks, Intrusion Detection has become a major concern. In network security, various traditional techniques like intrusion prevention, cryptography and user authentication are unable to detect establishment of novel attacks. An intrusion detection system is helpful in detecting an unusual intruder which cracks into the system or genuine user mistreating the system. Intrusion Detection System continually runs in the background and when any suspicious or obtrusive event occurs then it warns the user. To implement these systems various researchers introduced numerous machine learning techniques like Decision Trees, Support Vector Machines, Artificial Neural Networks, Linear Genetic Programming, Genetic Algorithms, Fuzzy Inference Systems, Rule Based Approach and their ensemble approaches with the intent to predict the data either normal or abnormal. In this paper genetic programming with K-Nearest Neighbor classifier is proposed so as to build an efficient Intrusion Detection Model. Optimal feature selection task is performed by genetic programming whereas the data mining classifier which performs the classification process is K-Nearest Neighbour. The main aim of genetic programming is to aid K-Nearest Neighbour. The experimental result shows that the validation accuracy for detecting attacks is 99.6%.

In the software industry, where the quality of the output is based on human performance, fatigue can be a reason for performance degradation. Fatigue not only degrades quality, but is also a health risk factor. Sleep disorders, depression, and stress are all results of fatigue which can contribute to fatal problems. This article presents a comparative study of different techniques which can be used for detecting fatigue of programmers and data miners who spent lots of time in front of a computer screen. Machine learning can used for worker fatigue detection also, but there are some factors which are specific for software workers. One of such factors is screen illumination. Screen illumination is the light of the computer screen or laptop screen that is casted on the workers face and makes it difficult for the machine learning algorithm to extract the facial features. This article presents a comparative study of the techniques which can be used for general fatigue detection and identifies the best techniques.