Diagnosis of Lumbar Spondylolisthesis Using Optimized Pretrained CNN Models

Spondylolisthesis refers to the slippage of one vertebral body over the adjacent one. It is a chronic condition that requires early detection to prevent unpleasant surgery. The paper presents an optimized deep learning model for detecting spondylolisthesis in X-ray radiographs. The dataset contains a total of 299 X-ray radiographs from which 156 images are showing the spine with spondylolisthesis and 143 images are of the normal spine. Image augmentation technique is used to increase the data samples. In this study, VGG16 and InceptionV3 models were used for the image classification task. The developed model is optimized by utilizing the TFLite model optimization technique. The experimental result shows that the VGG16 model has achieved a 98% accuracy rate, which is higher than InceptionV3's 96% accuracy rate. The size of the implemented model is reduced up to four times so it can be used on small devices. The compressed VGG16 and InceptionV3 models have achieved 100% and 96% accuracy rate, respectively. Our finding shows that the implemented models were outperformed in the diagnosis of lumbar spondylolisthesis as compared to the model suggested by Varcin et al. (which had a maximum of 93% accuracy rate). Also, the developed quantized model has achieved higher accuracy rate than Zebin and Rezvy's (VGG16 + TFLite) model with 90% accuracy. Furthermore, by evaluating the model's performance on other publicly available datasets, we have generalised our approach on the public platform.

A Real-Time Crowd Monitoring and Management System for Social Distance Classification and Healthcare Using Deep Learning

Coronavirus born COVID-19 disease has spread its roots in the whole world. It is primarily spread by physical contact. As a preventive measure, proper crowd monitoring and management systems are required to be installed in public places to limit sudden outbreaks and impart improved healthcare. The number of new infections can be significantly reduced by adopting social distancing measures earlier. Motivated by this notion, a real-time crowd monitoring and management system for social distance classification is proposed in this research paper. In the proposed system, people are segregated from the background using the YOLO v4 object detection technique, and then the detected people are tracked by bounding boxes using the Deepsort technique. This system significantly helps in COVID-19 prevention by social distance detection and classification in public places using surveillance images and videos captured by the cameras installed in these places. The performance of this system has been assessed using mean average precision (mAP) and frames per second (FPS) metrics. It has also been evaluated by deploying it on Jetson Nano, a low-cost embedded system. The observed results show its suitability for real-time deployment in public places for COVID-19 prevention by social distance monitoring and classification.

Wheat Seed Classification: Utilizing Ensemble Machine Learning Approach

Recognizing and authenticating wheat varieties is critical for quality evaluation in the grain supply chain, particularly for methods for seed inspection. Recognition and verification of grains are carried out manually through direct visual examination. Automatic categorization techniques based on machine learning and computer vision offered fast and high-throughput solutions. Even yet, categorization remains a complicated process at the varietal level. The paper utilized machine learning approaches for classifying wheat seeds. The seed classification is performed based on 7 physical features: area of wheat, perimeter of wheat, compactness, length of the kernel, width of the kernel, asymmetry coefficient, and kernel groove length. The dataset is collected from the UCI library and has 210 occurrences of wheat kernels. The dataset contains kernels from three wheat varieties Kama, Rosa, and Canadian, with 70 components chosen at random for the experiment. In the first phase, K-nearest neighbor, classification and regression tree, and Gaussian Naïve Bayes algorithms are implemented for classification. The results of these algorithms are compared with the ensemble approach of machine learning. The results reveal that accuracies calculated for KNN, decision, and Naïve Bayes classifiers are 92%, 94%, and 92%, respectively. The highest accuracy of 95% is achieved through the ensemble classifier in which decision is made based on hard voting.

Self-organizing Maps and Bayesian Regularized Neural Network for Analyzing Gasoline and Diesel Price Drifts

Any nation’s growth depends on the trend of the price of fuel. The fuel price drifts have both direct and indirect impacts on a nation’s economy. Nation’s growth will be hampered due to the higher level of inflation prevailing in the oil industry. This paper proposed a method of analyzing Gasoline and Diesel Price Drifts based on Self-organizing Maps and Bayesian regularized neural networks. The US gasoline and diesel price timeline dataset is used to validate the proposed approach. In the dataset, all grades, regular, medium, and premium with conventional, reformulated, all formulation of gasoline combinations, and diesel pricing per gallon weekly from 1995 to January 2021, are considered. For the data visualization purpose, we have used self-organizing maps and analyzed them with a neural network algorithm. The nonlinear autoregressive neural network is adopted because of the time series dataset. Three training algorithms are adopted to train the neural networks: Levenberg-Marquard, scaled conjugate gradient, and Bayesian regularization. The results are hopeful and reveal the robustness of the proposed model. In the proposed approach, we have found Levenberg-Marquard error falls from − 0.1074 to 0.1424, scaled conjugate gradient error falls from − 0.1476 to 0.1618, and similarly, Bayesian regularization error falls in − 0.09854 to 0.09871, which showed that out of the three approaches considered, the Bayesian regularization gives better results.

A fuzzy multi-criteria decision-making method for purchasing life insurance in India

Life insurance is an agreement between an insured and an insurer, where the insurer pays out a sum of money either on a specific period or the death of the insured. Now a day, People can buy a policy through an online platform. There are a lot of insurance companies available in the market, and each company has various policies. Selecting the best insurance company for purchasing an online term plan is a very complex problem. People may confuse to choose the best insurance company for buying an online term. It is a multi-criteria decision making (MCDM) problem, and the problem consists of different criteria and various alternatives. Here in this paper, a model has been proposed to solve this decision-making problem. In this model, a fuzzy multi-criteria decision-making approach combined with technique for order preference by similarity to ideal solution (TOPSIS) and it has been applied to rank the different insurance companies based on online term plans. The experimental results show that the life insurance corporation of India (LIC) gets the top rank out of 12 companies for purchasing an online term plan. A sensitivity analysis has been performed to validate the proposed model.

COVID-19 Mortality Rate Prediction for India Using Statistical Neural Network Models

The primary aim of this study is to investigate suitable Statistical Neural Network (SNN) models and their hybrid version for COVID-19 mortality prediction in Indian populations and is to estimate the future COVID-19 death cases for India. SNN models such as Probabilistic Neural Network (PNN), Radial Basis Function Neural Network (RBFNN), and Generalized Regression Neural Network (GRNN) are applied to develop the COVID-19 Mortality Rate Prediction (MRP) model for India. For this purpose, we have used two datasets as D1 and D2. The performances of these models are evaluated using Root Mean Square Error (RMSE) and "R," a correlation value between actual and predicted value. To improve prediction accuracy, the new hybrid models have been constructed by combining SNN models and the Non-linear Autoregressive Neural Network (NAR-NN). This is to predict the future error of the SNN models, which adds to the predicted value of these models for getting better MRP value. The results showed that the PNN and RBFNN-based MRP model performed better than the other models for COVID-19 datasets D2 and D1, respectively.

COVID-19 Patient Health Prediction Using Boosted Random Forest Algorithm

Integration of artificial intelligence (AI) techniques in wireless infrastructure, real-time collection, and processing of end-user devices is now in high demand. It is now superlative to use AI to detect and predict pandemics of a colossal nature. The Coronavirus disease 2019 (COVID-19) pandemic, which originated in Wuhan China, has had disastrous effects on the global community and has overburdened advanced healthcare systems throughout the world. Globally; over 4,063,525 confirmed cases and 282,244 deaths have been recorded as of 11th May 2020, according to the European Centre for Disease Prevention and Control agency. However, the current rapid and exponential rise in the number of patients has necessitated efficient and quick prediction of the possible outcome of an infected patient for appropriate treatment using AI techniques. This paper proposes a fine-tuned Random Forest model boosted by the AdaBoost algorithm. The model uses the COVID-19 patient's geographical, travel, health, and demographic data to predict the severity of the case and the possible outcome, recovery, or death. The model has an accuracy of 94% and a F1 Score of 0.86 on the dataset used. The data analysis reveals a positive correlation between patients' gender and deaths, and also indicates that the majority of patients are aged between 20 and 70 years.

A machine learning forecasting model for COVID-19 pandemic in India

Coronavirus disease (COVID-19) is an inflammation disease from a new virus. The disease causes respiratory ailment (like influenza) with manifestations, for example, cold, cough and fever, and in progressively serious cases, the problem in breathing. COVID-2019 has been perceived as a worldwide pandemic and a few examinations are being led utilizing different numerical models to anticipate the likely advancement of this pestilence. These numerical models dependent on different factors and investigations are dependent upon potential inclination. Here, we presented a model that could be useful to predict the spread of COVID-2019. We have performed linear regression, Multilayer perceptron and Vector autoregression method for desire on the COVID-19 Kaggle data to anticipate the epidemiological example of the ailment and pace of COVID-2019 cases in India. Anticipated the potential patterns of COVID-19 effects in India dependent on data gathered from Kaggle. With the common data about confirmed, death and recovered cases across India for over the time length helps in anticipating and estimating the not so distant future. For extra assessment or future perspective, case definition and data combination must be kept up persistently.

Smartphone Confrontational Applications and Security Issues

In today's society, there is a high volume of smartphones, with Android being the most popular and most commonly used smartphones. In the last few years, the Android market has been booming, making lots of developers join the industry so as to create various mobile applications that are a benefit to people's lives. However, its over-popularity has brought many crime issues, including security. One of the major common incidents to mobile users is having their mobile phones lost or stolen. Since most mobile users want to find their lost phones, they are looking for the most reliable features that can help them locate their smartphones. Luckily, there are some developed applications and services that have been designed to track down and locate lost or stolen smartphones. In this work, the authors tried to identify a collection of these applications and the information they send to the user in aiding them to find their phone. Since some applications are able to send location information or a photo, this work will look at what metadata is usually sent with the message.

A novel hybrid approach of SVM combined with NLP and probabilistic neural network for email phishing

Phishing attacks are one of the slanting cyber-attacks that apply socially engineered messages that are imparted to individuals from expert hackers going for tricking clients to uncover their delicate data, the most mainstream correspondence channel to those messages is through clients' emails. Phishing has turned into a generous danger for web clients and a noteworthy reason for money related misfortunes. Therefore, different arrangements have been created to handle this issue. Deceitful emails, also called phishing emails, utilize a scope of impact strategies to convince people to react, for example, promising a fiscal reward or summoning a feeling of criticalness. Regardless of far reaching alerts and intends to instruct clients to distinguish phishing sends, these are as yet a pervasive practice and a worthwhile business. The creators accept that influence, as a style of human correspondence intended to impact others, has a focal job in fruitful advanced tricks. Cyber criminals have ceaselessly propelling their techniques for assault. The current strategies to recognize the presence of such malevolent projects and to keep them from executing are static, dynamic and hybrid analysis. In this work we are proposing a hybrid methodology for phishing detection incorporating feature extraction and classification of the mails using SVM. At last, alongside the chose features, the PNN characterizes the spam mails from the genuine mails with more exactness and accuracy.

Hybrid Machine Learning Approaches for Landslide Susceptibility Modeling

This paper presents novel hybrid machine learning models, namely Adaptive Neuro Fuzzy Inference System optimized by Particle Swarm Optimization (PSOANFIS), Artificial Neural Networks optimized by Particle Swarm Optimization (PSOANN), and Best First Decision Trees based Rotation Forest (RFBFDT), for landslide spatial prediction. Landslide modeling of the study area of Van Chan district, Yen Bai province (Vietnam) was carried out with the help of a spatial database of the area, considering past landslides and 12 landslide conditioning factors. The proposed models were validated using different methods such as Area under the Receiver Operating Characteristics (ROC) curve (AUC), Mean Square Error (MSE), Root Mean Square Error (RMSE). Results indicate that the RFBFDT (AUC = 0.826, MSE = 0.189, and RMSE = 0.434) is the best method in comparison to other hybrid models, namely PSOANFIS (AUC = 0.76, MSE = 0.225, and RMSE = 0.474) and PSOANN (AUC = 0.72, MSE = 0.312, and RMSE = 0.558). Thus, it is reasonably concluded that the RFBFDT is a promising hybrid machine learning approach for landslide susceptibility modeling.

NoSQL Database Classification

The rapid growth in the digital world in form of exponentiation to accommodate huge amount of structured, semi-structured, unstructured and hybrid data received from different sources. By using the conventional data management tools, it is quite impossible to manage this semi-structured and unstructured data for which a non-relational database management system such as NoSQL and NewSQL are used to handle such types of data. These types of semi-structured and structured data are generally considered ‘Big Data.' This article describes the basic characteristics, background and the models of NoSQL used for big data applications. In this work, the authors surveyed different NoSQL characteristics used by the researchers and try to compare the strength and weakness of different NoSQL databases.