A Machine Learning Approach to Detect Student Dropout at University

In universities, student dropout is a major concern that reflects the university's quality. Some characteristics cause students to drop out of university. A high dropout rate of students affects the university's reputation and the student's careers in the future. Therefore, there's a requirement for student dropout analysis to enhance academic plan and management to scale back student's drop out from the university also on enhancing the standard of the upper education system. The machine learning technique provides powerful methods for the analysis and therefore the prediction of the dropout. This study uses a dataset from a university representative to develop a model for predicting student dropout. In this work, machine- learning models were used to detect dropout rates. Machine learning is being more widely used in the field of knowledge mining diagnostics. Following an examination of certain studies, we observed that dropout detection may be done using several methods. We've even used five dropout detection models. These models are Decision tree, Naïve bayes, Random Forest Classifier, SVM and KNN. We used machine-learning technology to analyze the data, and we discovered that the Random Forest classifier is highly promising for predicting dropout rates, with a training accuracy of 94% and a testing accuracy of 86%.

Malware Detection Approaches and Analysis for the Internet of Medical Things Enabled Healthcare Systems

The advancement of information and communications technology has changed an IoMT-enabled healthcare system. The Internet of Medical Things (IoMT) is a subset of the Internet of Things (IoT) that focuses on smart healthcare (medical) device connectivity. While the Internet of Medical Things (IoMT) communication environment facilitates and supports our daily health activities, it also has drawbacks such as password guessing, replay, impersonation, remote hijacking, privileged insider, denial of service (DoS), and man-in-the-middle attacks, as well as malware attacks. Malware botnets cause assaults on the system's data and other resources, compromising its authenticity, availability, confidentiality and, integrity. In the event of such an attack, crucial IoMT communication data may be exposed, altered, or even unavailable to authorised users. As a result, malware protection for the IoMT environment becomes critical. In this paper, we provide several forms of malware attacks and their consequences. We also go through security, privacy, and different IoMT malware detection schemes

Analysis and Prediction of Graduate Admissions Based on Pre-COVID and post-COVID Scenario

Graduate admissions is one of the events that attracts a lot of attraction from prospective students and universities alike. Be it the university conducting graduate admissions or an aspiring student; both yearn for a prediction system to aid in the process of selecting admits. On one hand, the university can get an insight on the probability of a student's admit thus aiding the graduate admissions office in their workload, and on the other hand the student can get a forecast on the chance of admit and can take preemptive decisions to facilitate the process. However, due to the COVID-19 pandemic, the graduate admissions has seen a slight change in paradigm. This change creates confusion among the related masses. A probing analysis on this change serves as a reference to act upon. In this study, prediction models are built with an extra parameter signifying whether a record in the dataset belongs to the COVID-19 pandemic period. Various models such as Logistic Regression, Decision Tree, Random Forest, Gaussian Naive Bayes and Artificial Neural Networks are used to determine the change in probability of admission due to the effect of the pandemic. All the models provide an accuracy score in the range of about 55% to 80%, with the Neural Network outperforming all the other models with a test accuracy score of 79.03%. The effect of the pandemic has caused an ambiguous response to various factors, but it can be stated the chances of admits of students have generally increased likely due to the lower number of applicants

Smart System for Detecting Anomalies In Crude Oil Prices Using Long Short-Term Memory

Crude oil is leading globally, as it represents roughly about 33% of the total energy consumed globally. It is one of the most significant exchanged resources in the world, oil in one way or the other affects our day to day routines, like transportation, cooking and power, and other numerous petrochemical items going from the things we use to the things we wear. The increment sought after for petroleum derivatives is on a persistent ascent, making it vital for the oil and gas industry to think of new methodologies for further developing activity. This paper presents a smart system for detecting anomalies in crude oil prices. The experimental process of the proposed system is of two phases. The first phase has to do with the pre-processing stage, and the training stage while the second phase of the experiment has to do with the building/training of the Long Short-Term Memory algorithm. The experimental result shows that LSTM model had an accuracy result of 98%. The result further shows that our proposed model is under fitting since the training loss is lesser than the validation loss. The proposed model was saved and was used in detecting anomalies of the crude oil prices ranging from 1990 to 2020.

Framework for Digital Technology Application in Sustainable Waste Management

This paper provides a novel framework for envisioning digital technology application in sustainable waste management. The approach inclines on a mini-conceptual framework, which is rooted in the bourgeoning of diverse software innovation, which offers numerous digitalization of waste management recess. It first concedes that digital age brings to fore some enabling technology that offer a lift to transform traditional waste management to an unprecedented quick and cleaner dimension. Although not exhaustive, it highlights some popular digital apparatuses available for individuals, organisations and the government to take advantage for reforming traditional waste management techniques. These include ultrasonic trash can sensor, solar-powered trash compactor, image-based trash can sensors, toogoodtogo, digital mapping and cloud-based life-cycle waste cost calculator. Accordingly, this mini-framework for digital application to waste management provides a stepping ground to enable further expansion of the framework for enhanced policy, practice and scholarship

Ontology of Heterogeneous Image File Formats and their Disparate Applications

Different image formats are available in the world today which are used for various purposes, this paper elaborates the Ontology of different Image File Formats and their various applications. Digital images are saved in various Image File Formats which have different properties and features which are ideal for a particular use. A digital image is primarily classified into two types, raster or vector type. Image format elucidate how the information in the image will be stored. Image file format is a systematic way of storing and arranging digital images. Image file format can store data in compressed format (which may be lossy or lossless), uncompressed format or a vector format. Some Image format are suitable for a particular purpose while some are not. TIFF Image type is good for printing whereas PNG or JPG, are best for web. Analysis of the basic Image File Format have been carried out practically and the result is displayed in the coming section

A Systematic Survey on Multi-document Text Summarization

Automatic text summarization is a technique of generating short and accurate summary of a longer text document. Text summarization can be classified based on the number of input documents (single document and multi-document summarization) and based on the characteristics of the summary generated (extractive and abstractive summarization). Multi-document summarization is an automatic process of creating relevant, informative and concise summary from a cluster of related documents. This paper does a detailed survey on the existing literature on the various approaches for text summarization. Few of the most popular approaches such as graph based, cluster based and deep learning-based summarization techniques are discussed here along with the evaluation metrics, which can provide an insight to the future researchers.

User Engagement and User Design on Online Shopping Apps

Most people nowadays use mobile phones, and they do a lot of things with this device, including online shopping through an app since it saves a lot of time, and they can choose a broad range of products even with just a small screen. User engagement is one of the factors that affect the design of an app. Referring to the quality of the user that emphasizes the interaction between the user and the app. Numerous studies internationally have studied user engagement and app design but not specifically with the user engagement towards shopping apps design. We conducted this study to assess the effectiveness of user engagement towards online shopping apps design. Also, the purpose of this study is to identify user engagement factors that will produce a successful good shopping app design. The results show a high level of user engagement and online shopping apps design. It has also been found that among the indicators of user engagement, attention and satisfaction are the two predictors of the design of online shopping apps

Soil Properties Classification Using Support Vector Machine for Raver Tehsil

Soil properties are dynamic in nature and different factors are affecting to the soil quality. It is directly consequence on soil productivity and soil fertility. The heavy use of fertilizers, heavy rain fall, various agricultural practices are responsible for soil quality degradation. The soil assessment is require to maintain the soil quality. The spectroscopic techniques using Remote sensing and GIS gives the fast and accurate results as compare to traditional soil testing methods. The present study is conducted for classification of soil physicochemical properties in pre monsoon and post monsoon season. Soil samples are collected where Organic, Chemical and Mixed fertilizers treatments were applied to banana and cotton crops sites from Raver tehsil of Jalgaon district. Total 220 soil specimens are collected in pre monsoon and post monsoon season for two year respectively. ASD FieldSpec4 spectroradiometer device were used for data acquisition in the controlled laboratory environment. Acquired spectral data were processed for conversion in numeric format then various statistical methods were used for quantitative analysis of the physiochemical soil properties. The support vector machine is used for classification of the collected soil samples in pre-monsoon and post-monsoon season and classification were performed on the basis of training and testing datasets. The soil samples are divide in pre-monsoon training, pre-monsoon testing and post –monsoon training and post-monsoon testing class with support vector. The hyper plane is used for separation of pre-monsoon and post-monsoon soil samples. Misclassification rate and Mean Squared Error were calculated in the SVM classification.

Mathematical Investigation and Computers Simulation of Plant Protection Process Taking into Account the Temporary Age Structure and Arbitrary Tropic Functions

The problem of describing the process of protecting agricultural crops in mathematical modeling is relevant. Today, the problem of plant protection attracts the attention of a large circle of scientists in connection with its promising use in priority areas of development of science, technology and agriculture. Mathematical modeling of the process of protecting the planned crop is one of the main tools in predicting the state of natural systems and managing them. One of the most important national economic, social and environmental problems at present is the improvement of systems for protecting agricultural crops from pests. Mathematical modeling of the process of protecting the planned harvest obliges to improve regional systems for protecting cotton on the basis of a targeted ecological and biological study, revealing the specifics of the formation and development of agro ecosystems in intensive crop production. The main task of the integrated method of combating agricultural pests of the plant protection process is the management of agrocenoses of “harmful insects” and “beneficial insects” of species based on the use of biological, chemical methods as a means or a management tool.The use of mathematical methods and computer software products to solve the problem of protecting the planned crop significantly increases the efficiency of planned and economic work and ensure optimal results. In this paper, we consider a mathematical model of the plant protection process, taking into account the temporal age structure and arbitrary trophic functions, formulate the task of plant protection. Necessary and sufficient conditions for the solvability of the plant protection problem with arbitrary trophic functions are found