Browse Items (11808 total)
Sort by:
-
CloudML: Privacy-Assured Healthcare Machine Learning Model for Cloud Network
Cloud computing is the need of the twenty-first century with an exponential increase in the volume of data. Compared to any other technologies, the cloud has seen fastest adoption in the industry. The popularity of cloud is closely linked to the benefits it offers which ranges from a group of stakeholders to huge number of entrepreneurs. This enables some prominent features such as elasticity, scalability, high availability, and accessibility. So, the increase in popularity of the cloud is linked to the influx of data that involves big data with some specialized techniques and tools. Many data analysis applications use clustering techniques incorporated with machine learning to derive useful information by grouping similar data, especially in healthcare and medical department for predicting symptoms of diseases. However, the security of healthcare data with a machine learning model for classifying patients information and genetic data is a major concern. So, to solve such problems, this paper proposes a Cloud-Machine Learning (CloudML) Model for encrypted heart disease datasets by employing a privacy preservation scheme in it. This model is designed in such a way that it does not vary in accuracy while clustering the datasets. The performance analysis of the model shows that the proposed approach yields significant results in terms of Communication Overhead, Storage Overhead, Runtime, Scalability, and Encryption Cost. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Pragmatic Study on Movie Recommender Systems Using Hybrid Collaborative Filtering
The Movie Recommendation System (MRS) is part of a comprehensive class of recommendation systems, which categorizes information to predict user preferences. The sum of movies is increasing tremendously day by day, and a reliable recommender system should be developed to increase the user satisfaction. Most of the approaches are made to prevent cold-start, first-rater drawbacks, and gray sheep user problems, nevertheless, in order to recommend the related items, various methods are available in the literature. Firstly, content-based method has some drawbacks like data of similar user could not be achieved, and what category of these items the user likes or dislikes are also not known. Secondly, this paper discusses about collaborative filtering to find both user and item attributes that have been considered. Since there exist some issues pictured with collaborative filtering, so this paper further aims into hybrid collaborative filtering and deep learning with KNN algorithm of ratings of top K-nearest neighbors. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Analysis of Market Behavior Using Popular Digital Design Technical Indicators and Neural Network
Forecasting the future price movements and the market trend with combinations of technical indicators and machine learning techniques has been a broad area of study and it is important to identify those models which produce results with accuracy. Technical analysis of stock movements considers the price and volume of stocks for prediction. Technical indicators such as Relative Strength Index (RSI), Stochastic Oscillator, Bollinger bands, and Moving Averages are used to find out the buy and sell signals along with the chart patterns which determine the price movements and trend of the market. In this article, the various technical indicator signals are considered as inputs and they are trained and tested through machine learning techniques to develop a model that predicts the movements accurately. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Enhanced Energy-Efficient Routing for Wireless Sensor Network Using Extended Power-Efficient Gathering in Sensor Information Systems (E-PEGASIS) Protocol
Recent technological advancements in wireless communication and sensors made Wireless Sensor Networks (WSNs) as one of the demanding platforms in the current scenario. In WSN, tiny sensor nodes are collecting and monitoring the biological data or physical data or environmental data and transmits to the Base Station (BS) through gateway routers. These data can be accessed anywhere and anytime. Usually, sensor nodes have restrained battery power which creates the rigorous lifetime duration issues in WSN. Sensor nodes can transmit the data with each other using various routing protocols. Data transmission devours more amounts of energy and power. So, energy preservation is an important factor in WSN. There are plenty of researches going on in designing less energy consuming protocols for data transmission which helps to increase the lifetime of WSN. In this manuscript, we have proposed Extended Power-Efficient Gathering in Sensor Information Systems (E-PEGASIS) protocol for enhanced energy-efficient data transmission based on PEGASIS protocol. In this proposed method, the average distance between the sensor nodes is considered as the criterion for chaining and fixing the outermost nodes radio range value to the base station. Later it chains the related nodes available in the radio range. Consequently, the chained node checks their distance with the next nearest end node to go on with the chaining procedure which will enhance the performance of data transmission amid the base station and sensor node. The simulation of the proposed work shows that lifetime of the network is increased when compared to the LEACH and PEGASIS protocol. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Lateral Load Behavior of Unreinforced Masonry Spandrels
Spandrels, are usually classified as secondary elements and even though their behaviour has not received adequate focus unlike piers, they significantly affect the seismic capacity of the structure. Masonry spandrels are often damaged and the first structural components that crack within Unreinforced Masonry structures. Despite this, existing analytical methods typically consider a limit case in which the strength of spandrels is either neglected, considered to be infinitely rigid and strong or treated as rotated piers. It is clearly evident that such an assumption is not plausible. Hence, reliable predictive strength models are required. This thesis attempts to re-examine the flexural behaviour of spandrels and proposes an analytical model. The model is based on the interlocking phenomena of the joints at the end-sections of the spandrel and the contiguous masonry. The proposed analytical model is incorporated within a simplified approach to account for the influence of spandrel response on global capacity estimate of URM buildings. 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
Natural Disaster Prediction by Using Image Based Deep Learning and Machine Learning
In recent years, diseases and disaster have become more unpredictable. The advent of technology has not only making our lives easier but also technology-dependent. Nevertheless, the natural disasters cause great adversity by disrupting considerable human lives. Also, the disasters obstruct and affect many industries and services either directly or indirectly. Hence, it is necessary to study and observe data patterns and warning signs that lead to a natural disaster, its potential risk and its ability to resolve management strategies, which can be implemented immediately to minimize the socio-economic loss. This article reviews the state-of-the-art research works and findings through a technological perspective on data analysis, natural disaster prediction, and the utilization of technology for deploying management strategy. Also, this paper focuses on investigating the today's Industry 4.0 that utilizes cognitive computing. The primary aim of this article is to review the research ideas that leverage big data and data mining to observe and track patterns, which can impelment predictive analysis to anticipate the forthcoming disasters. Furthermore, this research work analyzed the posed predictive models by specifically using ANN (Artificial Neural Networks), sentiment model, and smart disaster prediction application (SDPA) to predict the flash flood. 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
A Novel Approach for Web Mining Taxonomy for High-Performance Computing
Web mining is a central part of data analysis. The fetching and discovering knowledge from the different web data in data mining mechanism is more important nowadays. Web usage mining customs data mining practice for the investigation of custom decoration from different data storages. In this article paper, introducing a new approach for web mining taxonomy for high-performance computing. The primary motivation of this research is on the data collection in different real-time web servers for implementation and analysis. This article is focussed the WebLog Expert lite 9.3 tools for our study. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Survey on Domain-Specific Summarization Techniques
Automatic text summarization using different natural language processing techniques (NLP) has gained much momentum in recent years. Text summarization is an intensive process of extracting representative gist of the contents present in a document. Manual summarization of structured and unstructured text is a tedious task that involves immense human effort and time. There are quite a number of successful text summarization algorithms for generic documents. But when it comes specialized for a particular domain, the generic training of algorithms does not suffice the purpose. Hence, context-aware summarization of unstructured and structured text using various algorithms needs specific scoring techniques to supplement the base algorithms. This paper is an attempt to give an overview of methods and algorithms that are used for context-aware summarization of generic texts. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Predictive Analysis of the Recovery Rate from Coronavirus (COVID-19)
Estimation of recovery rate of COVID-19 positive persons is significant to measure the severity of the disease for mankind. In this work, prediction of the recovery rate is estimated based on machine learning technology. Standard data set of Kaggle has been used for experimental purpose, and the data sets of COVID cases in Italy, China and India for these countries are considered. Based on that data set and the present scenario, the proposed technique predicts the recovery rate. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Currency Exchange Rate Prediction Using Multi-layer Perceptron
Financial forecasting is an estimate of a future financial outcome and this outcome is related to some kind of value. We can measure this outcome for a company to predict its future stock or to detect the viability of a human for the sanction of a loan. In all these cases, we want to estimate the future outcome based on historical data. Various methods have been developed lately, to make time series predictions. In this work, we have used Multi-layer perceptron algorithm to predict the Currency Exchange rate between US dollar and EURO. The training network has been compiled using TensorFlow. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Security Aspects for Mutation Testing in Mobile Applications
Due to the increase in the number of Android Platform Devices, there are more and more applications being developed across various domains. It is interesting to see the involvement of bugs/crashes even in the deployed applications even though it has been through various test phases. Unit tests are essential in a well-trusted testing environment; however, it does not guarantee that the range of test caries every component of the application. This writes up discusses the overview of mutation testing method concerning Android Applications. Even though mutation testing is found out to be very effective in other applications, it is not that easy to implement the same for an Android Developed Application because of additional resources it would hold. Further, various measures for mutation testing are discussed with types of mutant operators, tools etc. The current studies of mutation analysis mainly focus on testing all the functionalities irrespective of the resource usage. However, the target of the future mutation tests must be also to evaluate the efficiency of the applications under the same test cases. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
An Econometric Approach Towards Exploring the Impact of Workers Remittances on Inflation: Empirical Evidence from India
This paper attempts to study short and long run impact of increased workers remittances on general price level. It uses the real GDP growth, real effective exchange rate (REER), M3 (broad money), fiscal deficit to gauge the impact of foreign remittances on inflation. The study makes use of VAR/VECM framework to gauge the impact of workers remittances on inflation. Inflation is measured in terms of CPI and WPI, real income or GDP at constant prices is taken as a measure of GDP growth, REER is used for exchange rates and M3 is taken as a proxy for money supply. Monthly data of all these variables has been taken from Bloomberg and World Bank data base. The findings provide important insights into the nature of association between remittances and inflation suggesting causality between inflation, remittances, real GDP, real effective exchange rates and money supply due to increased workers remittances. The findings have policy implications for decisions to channelize workers remittances in a way to increase real GDP growth and money supply while at the same time not causing the general price levels to soar. The present study focuses on how increased (decreased) workers remittances is leading to increase (decrease) in general price levels in India. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Analysis of Kidney Ultrasound Images Using Deep Learning and Machine Learning Techniques: A Review
Ultrasonography is the most accepted and widely used imaging technique due to its non-invasive and radiation-free nature. The heterogeneous structure of kidney makes the disease detection a difficult task. Hence, more efficient models and methods are required to assist radiologists in making precise decisions. Since ultrasound imaging is considered to be the initial step in the diagnosis, more efficient processing techniques are needed in the interpretation of images. The presence of speckle noise is a challenge task in image processing. It diminishes the clarity of the images. In this article, an in-depth review has been performed on various machine learning and deep learning techniques, which are helping to improve the quality of images. The pre-processing, segmentation, feature extraction, and classification are described in detail using kidney cyst, stone, tumor, and normal kidney images. Deep learning techniques are enhancing the quality of the images with better accuracy. The remaining challenges and directions for future research are also explored. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
On Combinatorial Handoff Strategies for Spectrum Mobility in Ad Hoc Networks: A Comparative Review
Technological advancements have made communication on-the-go seamless. Spectrum mobility is a networking concept that involves access technologies that allow highly mobile nodes to communicate with each other. Ad-hoc networks are formed between mobile nodes where fixed infrastructure is not used. Due to the lack of such fixed access points for connectivity, the nodes involved make use of the best network available to transmit data. Due to heterogeneous networks involvement, the mobile nodes may face trouble finding the most optimal network for transmission. Existing technologies allow the nodes to select available networks, but the selection process is not optimized, leading to frequent switching. This leads to packet loss, low data rates, high delay, etc. Many researchers have proposed optimal strategies for performing handoff in wireless networks. This paper reviews combinatorial strategies that make use of multiple techniques to perform a handoff. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Effect of Halloysite Nanotubes on Physico-Mechanical Properties of Silk/Basalt Fabric Reinforced Epoxy Composites
Natural fiber reinforced polymer composites have become more attractive due to their high specific strength, light weight and environmental concern. However, some limitations such as low modulus and poor moisture resistance were reported. This paper presents the role of halloysite nanotubes (HNTs) on physico-mechanical properties of bidirectional silk and basalt fiber reinforced epoxy (SF-BF/Ep) hybrid composites. Vacuum bagging and ultra-sonication method were used for the fabrication of hybrid composite slabs. The effect of HNT loadings (1.5, 3 and 4.5 wt. %) on physico-mechanical characteristics like density, hardness, flexural and impact properties of SF-BF/Ep composites were determined according to ASTM standards. Experimental results revealed that the incorporation of HNTs improves the mechanical properties. The impact strength of SF-BF/Ep is predominant at 3 wt. % HNT loading where the impact strength surges to 568.67 J/m, which may render HNT filled SF-BF/Ep desirable for various toughness-critical structural applications. The test results demonstrated that SF-BF/Ep-3HNT coded composites exhibited improved mechanical properties among the all composites. 2022 Trans Tech Publications Ltd, Switzerland. -
A Neural Network Based Customer Churn Prediction Algorithm for Telecom Sector
For telecommunication service providers, a key method for decreasing costs and making revenue is to focus on retaining existing subscribers rather than obtaining new customers. To support this strategy, it is significant to understand customer concerns as early as possible to avoid churn. When customers switch to another competitive service provider, it results in the instant loss of business. This work focuses on building a classification model for predicting customer churn. Four different deep learning models are designed by applying different activation functions on different layers for classifying the customers into two different categories. A comparison of the performance of the different models is done by using various performance measures such as accuracy, precision, recall, and area under the curve (AUC) to determine the best activation function for the model among tanh, ReLU, ELU, and SELU. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Depth Comparison of Objects in 2D Images Using Mask RCNN
Getting distance of an object from a single 2D image has always been a task. Due to various reasons, it was difficult to compare from images whether an object is closer or farther from camera. In this paper, we propose an idea to compare multiple images taken from same focal length cameras and specifying the distance of an object in those images with respect to each other. Our dataset contains images of palm of hand with particular distance from camera, and the output difference can specify in which image the palm is closer to camera as compared to others and vice versa. For this model, we are using Mask RCNN to recognize the object; in our case, it has been trained to identify palm, and then giving the output of masked RCNN to a depth identifier model to specify the distance of the palm from the camera. Directly using depth identifier model cannot give correct output as distance of background from camera results in different value for distance of targeted object in different images. So, we will be using mask RCNN to specify which part of image depth model should find distance from the camera. In the final step, we take the output of the depth model and take the mean of the output generated by it and compare the means of various images to specify relative distance from each other. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Classification Framework for Fraud Detection Using Hidden Markov Model
Machine learning is described as a computer program that learns from experience E with regard to some task T and some performance measure P, if its performance on T improves with E as measured by P. Suppose we have a credit card fraud detection which watches which transactions we mark as fraud or not, and on the basis, it knows how to filter better fraudulent transactions then, E is watching your transactions is fraud or not, T is classifying your transactions as fraud or not, P is number of transactions correctly differentiated as spam or not spam. Machine learning has two types: supervised learning and unsupervised learning. Supervised learning is the type of machine learning where machine is provided with input mapped with its output, and these inputs and outputs are used to make a machine learn a particular function from the trained dataset. There are two branches of supervised learning, i.e., classification and regression. In unsupervised learning, we do not supervise model instead we allow machine to work on its own to discover information. Clustering is type of unsupervised learning. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Review of Algorithms for Mental Stress Analysis Using EEG Signal
Mental stress is an enduring problem in human life. The level of stress increases exponentially with an increase in the complexity of work life. Hence, it is imperative to understand the causes of stress, a prerequisite of which is the ability to determine the level of stress. Electroencephalography (EEG) has been the most widely used signal for understanding stress levels. However, EEG signal is useful only when appropriate algorithms can be used to extract the properties relevant to stress analysis. This paper reviews algorithms for preprocessing, feature extraction and learning, and classification of EEG, and reports on their advantages and disadvantages for stress analysis. This review will help researchers to choose the most effective pipeline of algorithms for stress analysis using EEG signals. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Factors Affecting the Growing Economic Inequality: An Empirical Study with Reference to BRICS Countries
Economic inequality refers to the uneven distribution ofearningsand opportunity between various groups in society and is a point of major concern in almost all the nations in the world. This study aims to analyse the effect of various factors over the increasing inequality in BRICS nations. The study takes into consideration factors like trade openness, credit, net foreign assets and health and tries to assess their impact as a driving force behind the increasing inequality in these countries. The augmented DickeyFuller test for stationarity has been applied followed by multiple regression. To explore causality, Granger causality test is applied. All the models are tested for autocorrelation using the BreuschGodfrey Lagrange Multiplier test. Wald test is applied to examine the significance of independent variables. The study provides statistical evidence about the positive and negative effects of trade openness, healthcare finance, net foreign assets and healthcare expenditure on income inequality in BRICS nations. Findings may help to work intensively on the relevant causes of inequality for these five countries. This paper will add to the already present literature on inequality which is one of the important problems of the countries across the world. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.