Browse Items (11808 total)
Sort by:
-
Comparison of Gradient Boosting and Extreme Boosting Ensemble Methods for Webpage Classification
Web page classification is an important task in various areas like web content filtering, contextual advertising and maintaining or expanding web directories etc. Machine Learning methods have been found to perform well to classify web pages, and ensemble models have been used to improve the results obtained from single classifiers. The Gradient Boosting and Extreme Boosting ensemble models are used in this work for binary classification. The dataset containing URLs of web pages have been collected manually. The comparison between the two boosting algorithms validated the improvement in accuracy and speed obtained through Extreme boosting. Extreme boosting has been found to be around ten times faster than Gradient boosting and also shows improvement in accuracy. The effect of three preprocessing techniques; lemmatization, stop words removal and regular expressions shows that these preprocessing techniques improves the accuracy of the results but not significantly. 2020 IEEE. -
Effect of phonon-substrate scattering on lattice thermal conductivity of monolayer MoS2
The effect of phonon-substrate scattering on lattice thermal conductivity (LTC) of supported MoS2 MLs is investigated over a wide temperature range (1 -
Design, analysis and fabrication of EV with level-1 autonomous vehicle capability
The fact to this day remains true and the same for over a hundred years the Automobile industry and vehicles, in general, have become the pivoting point in our day to day lives. We might as well call it a necessary evil. Although it is very true that they have made our lives more convenient when we speak in terms of transportation; the pollution that conventional IC engine vehicles produce hasn't done much to create a cleaner environment especially with Global warming on the rise as we speak. The simplest remedy would be is to replace IC engine vehicles with Electric one, EV. A Problem common to both conventional IC engine vehicles and EV's alike is the accidents occurring due to collision caused by human error on-road. While safety measures have greatly been taken in order to reduce the damage done to the driver and passengers in the event of a collision it would be far better to avoid the collision altogether. Thus having at least, a Level-1 Autonomous Vehicles capability where the system alerts the driver in the event of a crash or collision and deploy full braking capability. Thanks to increasing urbanization and the advent of modern technology the need of the hour of the 21st century has given rise to high demands for employment in the motorized transport sectors. The authors were successfully able to design, analyze and fabricate an EV with Level-1 Autonomous Vehicles capability. The successful implementation of this project will help in reducing not only pollution and accidents occurring on-road due to vehicle collision but also pave paths in alimenting Level-1 Autonomous Vehicles capability in EV's inexpensively. 2020 Author(s). -
Natural Language Processing on Diverse Data Layers through Microservice Architecture
With the rapid growth in Natural Language Processing (NLP), all types of industries find a need for analyzing a massive amount of data. Sentiment analysis is becoming a more exciting area for the businessmen and researchers in Text mining NLP. This process includes the calculation of various sentiments with the help of text mining. Supplementary to this, the world is connected through Information Technology and, businesses are moving toward the next step of the development to make their system more intelligent. Microservices have fulfilled the need for development platforms which help the developers to use various development tools (Languages and applications) efficiently. With the consideration of data analysis for business growth, data security becomes a major concern in front of developers. This paper gives a solution to keep the data secured by providing required access to data scientists without disturbing the base system software. This paper has discussed data storage and exchange policies of microservices through common JavaScript Object Notation (JSON) response which performs the sentiment analysis of customer's data fetched from various microservices through secured APIs. 2020 IEEE. -
Constraint Governed Association Rule Mining for Identification of Strong SNPs to Classify Autism Data
Autism is a heterogeneous neuro developmental disorder found among all age groups. Nowadays more patients are detected with autism but very less awareness is prevailing in the society related to it. This paved a way for many researchers to carry out serious study on autism and its characteristics. Studying behavior and characteristics of Autistic patients is very important for diagnosing the level of autism. Classifying the association of different characteristic in autistic patients at gene level using machine learning techniques can give an important insight to the doctors and the care takers of the patients. Research is being carried out to identify the genes responsible for autism. The changes in gene sequence may lead to different characteristics in different people. Thus genotypic research is found to reveal well defined insight about various characteristics in autistic patients and their associations with genes. Single Nucleotide Polymorphism (SNP) being high in features indicate human genome variability and is associated with identification of traits for many human diseases including autism. The main aim of the proposed work is to identify SNP sequences which are responsible for carrying the autistic traits. This paper explore the application of Constraint Governed Association Rule Mining (CGARM) technique on SNP data for dimensionality reduction and thereby selecting the strong predominant SNP features which are relevant enough to accomplish classification with high accuracy. The research work incorporates the application of CGARM and is carried out in two stages. In the first stage CGARM was used to choose significant SNP features resulting in dimensionality reduction. In the second stage classification was carried out by subjecting the selected features to Artificial Neural Network (ANN) algorithm. The main advantage of the proposed work is its ability to reduce the dimensions without compromising the quality i.e. using CGARM strong SNPs were selected by applying various constraints like Syntactical constraints, Semantical constraints and Dimensionality Constraints resulting in higher accuracy. The CGARM technique is applied on Autism data collected from National Center for Biotechnology Information (NCBI) repository. The data is divided into a set of 118 features, out of 118 features CGARM contributed in identifying 22 predominant SNPs. Further by applying forward selection method top 17 features were selected and were given as input to ANN. The 10 fold cross validation resulted in 76.9% accuracy which was found to be 50% more than that of original features. The proposed work contributed in reducing the dimension by 85% and provided 76.9% accuracy with the help of only 15% features. 2020 IEEE. -
Accuracy Enhancement of Portrait Segmentation by Ensembling Deep Learning Models
Portrait segmentation is widely used as a preprocessing step in multiple applications. The accuracy of portrait segmentation models indicates its reliability. In recent times, portrait segmentation using deep learning models have achieved significant success in performance and accuracy. However, these portrait segmentation models are limited to a single model. In this paper, we propose ensemble approach using multiple portrait segmentation models to improve the segmentation accuracy. The result of experiment shows that the proposed ensemble approach produces better accuracy than individual models. Accuracy of single models and proposed ensemble approach were compared with Intersection over Union (IoU) metric and false prediction rate to evaluate the accuracy performance. The result shows reduced false negative rate and false discovery rate, this reduction in false prediction has enabled ensemble approach to produce segmented images with optimized error and improved result of segmentation in portrait area of human body than individual portrait segmentation models 2020 IEEE. -
The effect of non-thermal argon plasma treatment on material properties and photo-catalytic behavior of TiO2 nanoparticles
In this paper, a brief study on the effect of non-thermal plasma generated with argon carrier on material properties and photo-catalytic reduction behavior of TiO2 is presented. Commercially available TiO2 nanoparticles (20 nm size) were subjected to Ar cold plasma at different time durations. Then the plasma treated materials were explored for chemical reduction of carbon dioxide (CO2) into methane (CH4) using sunlight as photo-irradiation source. The results show that the non-thermal plasma affects the material properties of TiO2 such as UV-visible absorption, XRD patterns and Raman scattering significantly and also the enhancement of CH4 yields in CO2photo-chemical reduction. 2020 American Institute of Physics Inc.. All rights reserved. -
A Study of Segmentation Techniques to Detect Leukaemia in Microscopic Blood Smear Images
In medical image processing, the segmentation of the image is considered to be a vital stage and is effectively used to extract the region of interest. Automated diagnosis of leukaemia is highly associated with the accurate segmentation of the cell nucleus. The purpose of this paper is to review and analyze literature related to some of the major segmentation techniques used in the field of Acute lymphoblastic leukaemia (ALL) detection. This paper presents an overview of segmentation methods along with the experimental results of six implemented methods and highlights some of the advantages and disadvantages of implemented segmentation techniques. 2020 IEEE. -
A miniaturized antenna array for direct air-to-ground communication of aircrafts
In this paper, a miniaturized, high directivity low-cost antenna array is presented. The uniqueness of the proposed array (PA) exists in the feed mechanism designed using Dolph-Chebyshev non-uniform excitations. Authors simulated the designed antenna array using ANSYS EM 18.2 (HFSS) software and characterization is carried out in a fully established anechoic chamber. The simulated array antenna is operating at 2.4 GHz with a gain of 8.12 dB and a reflection coefficient of -28.45 dB having a bandwidth of 110 MHz. On contrast with the traditional array (TA), PA exhibits enhanced resonance characteristics by maintaining the same radiation characteristics. The bandwidth is increased by 37.5%, maintaining the same gain of 8.12 dB. In contrast, there is a remarkable reduction in the size compared to the traditional corporate feed array antenna with non-uniform excitation. The overall size of the PA antenna is 242.5 mm 58.8 mm, which is 33.73% less compared to the TA. Published under licence by IOP Publishing Ltd. -
Employing Deep Learning in Intraday Stock Trading
Accurate stock price prediction is a significant benefit to the Stock investors. The future Stock value of any company is determined by Stock market prediction. A successful prediction of the stock's future price could result in a significant profit; Hence investors prefer a precise Stock price prediction. Although there are many different approaches to helps in forecasting stock prices, this paper will briefly look into the deep learning models and compare LSTM model and its variants. The key intention of this study is to propose a model that is best suitable and can be implemented to forecasting trend of stock prices. This paper focuses on binary classification problem, predicting the next-minute price movement of SPDR SP 500 index The testing experiments performed on the SPDR SP 500 index reveals that the variants of LSTM models, Slim LSTM1, slim LSTM2, and Slim LSTM3 with less parameters, provide better performance when compared to the Standard LSTM Model. 2020 IEEE. -
Low cost ANN based MPPT for the mismatched PV modules
Due to manufacturing dispersal, the photovoltaic (PV) panels of similar rating and manufacturer have distinctive characteristics in practical. As the maximum power point tracking (MPPT) becomes essential to optimally utilize the solar PV panel, distributed maximum power point tracking (DMPPT) is considered in this paper to follow the MPP of each panel. As the common MPP value is used in the existing DMPPT method to control all the panels, it fails to consider the uniqueness of each panel. By considering the uniqueness of each panel, the ANN based MPPT is implemented in this paper. As the ANN is trained using the actual characteristics of each panel based on the operating current, voltage and temperature, it is able to track the actual MPP. Due to the solar irradiance free MPPT, the costly pyranometer is not required in the actual PV system for MPPT. It reduces the cost of the system and also provides the interruption free tracking due to its independent nature on Voc and Isc values. Also, because of the looping free behaviour of the proposed algorithm, it is capable of following the MPP at rapidly varying condition. The proposed technique and the verified outcomes are discussed here in detail. Published under licence by IOP Publishing Ltd. -
Rotor Dynamics of TurbineGenerator Shaft with Dampers During Subsynchronous Resonance Generated by Series Capacitors
Purpose In this paper, an electromechanical approach to study the turbinegenerator shaft stability with and without dampers is made. The shaft is subjected to electrical disturbances created by series capacitors. The high power capacitors help the electric power system to improve the reactive power in high voltage transmission lines. Methods Finite element method is used to study the stability of the shaft under subsynchronous resonance when compared to the traditional methods like eigenvalue analysis, frequency scanning method and digital time simulation techniques. At the same time, it leads to subsynchronous resonance. Results Electromechanical stress in the rotating shaft arises when the resonance is created in the system. Maximum stress and strain of the shaft are calculated with other necessary parameters to prove the system instability. In order to maintain stability, dampers are installed at an optimum location. Conclusion Best location of installing damper is found using ANSYS 16.0 by modal analysis, harmonic and phase response analysis. The damper installed at the point reduces the stress caused by subsynchronous resonance and maintains the stability of the system. 2021, Springer Nature Singapore Pte Ltd. -
Experimental Approach and CFD Analysis on Flow Devices
This paper deals with the study of experimental approach and investigation by using computational fluid dynamics (CFD) on various flow devices. An orifice meter, venturimeter and a nozzle meter are the most common type of measuring devices used for rate of flow by creating the differences in velocity and pressure. Pressure drop is an important parameter occurring in these flow devices, which is due to restricted passage of flow, properties, diameter ratio, etc. The focus here is to calculate the coefficient of discharge and other flow parameters to analyze theoretically with the application of Bernoullis equation. The main objective of this paper is to analyze the variations across the sections of orifice meter, venturimeter and nozzle meter. Comparison of results by both experimental and computational methods was clearly understood, and also, the flow level was calibrated by calculating the coefficient of discharge in both the methods. 2021, Springer Nature Singapore Pte Ltd. -
Regression Analysis on Macroeconomic Factors and Dividend Yield on Bank Nifty Index Returns
The study has examined an impact of macroeconomic variables and dividend yield on Bank NIFTY Index. It analyses the relationship amongst macroeconomic variables and dividend yield. The study used quarterly data from 1 January 2010 to 31 December 2019. It employed statistical measures like regression analysis to analyse the impact of independent variables (macroeconomic factors and dividend yield) on the dependent variable (Bank NIFTY returns) and multicollinearity tests to understand the relationship amongst the independent variables. The observations concluded that GDP, government bond yield and dividend yield have a significant impact on Bank NIFTY returns but CPI does not have a significant impact on Bank NIFTY returns. We can also conclude that all the independent variables are not correlated to each other. The study suggested to policy makers, in India, that they should maintain economic stability through policies of growth that will eventually boost the banking sector and the economy. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Diagnosis of Retinal Disease Using Retinal Blood Vessel Extraction
The eye is one of the important organs of the human body. In recent times, major parts of the eye are damaged due to various retinal diseases. Major diseases related to the retina are glaucoma, papilledema, retinoblastoma, diabetic retinopathy, and macular degeneration. These diseases can be detected using image processing techniques. These diseases can cause damage to the eye; hence the early diagnosis can prevent the loss of vision. Thus the early stage of rectification may lead to smaller damage than the risky ones. By extracting the blood vessels, various retinal diseases can be identified, and the severity of the disease can also be identified. Some of these diseases in the retina will occur due to hypertension, blood pressure, and diabetics. Thus, the tear in the blood vessels leads to the loss of visuality in human beings. The proposed work consists of image processing techniques such as segmentation, feature extraction, and boundary extraction which lead to the identification of various retinal diseases with a certain level of accuracy, sensitivity, and specificity by using image processing techniques. The training and testing of retinal images are carried out by using the artificial neural network (ANN) classifier for glaucoma detection and support vector machine (SVM) classifier for detecting diabetic retinopathy. 2021, Springer Nature Switzerland AG. -
An iot based wearable device for healthcare monitoring
Nowadays IoT (Internet of Things) devices are popularly used to monitor humans remotely in the healthcare sector. There are many IoT devices that are being introduced to collect data from human beings in a different scenario. These devices are embedded with sensors and controllers in them to collect data. These devices help to support many applications like a simple counting step to an advanced rehabilitation for athletes. In this research work, a mini wearable device is designed with multiple sensors and a controller. The sensors sense the environment and the controller collects data from all the sensors and sends them to the cloud in order to do the analysis related to the application. The implemented wearable device is a pair of footwear, that consists of five force sensors, one gyroscope, and one accelerometer in each leg. This prototype is built using a Wi-Fi enabled controller to send the data remotely to the cloud. The collected data can be downloaded as xlsx file from the cloud and can be used for different analyses related to the applications. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021. -
Effect of different base isolation techniques in multistoried rc regular and irregular building
Base confinement system for a structure is acquainted to decouple the building structure from possible movement incited by the movement of the seismic tremor, keeping the building superstructures from retaining the quake vitality. Base isolator increases the regular time period of the general structure and diminishes its shear increasing speed reaction to the seismic movement. In this explanatory examination, a ten-storey reinforced concrete (RC) building with lead elastic bearing, high damping elastic bearing and triple-contact pendulum framework bearing is acquainted with the structures, and correlation is made between fixed base and the base-secluded structures. Demonstrating and investigation are conveyed utilizing ETABS 2015 v15.2.2. The investigation examination is performed to check the ampleness of the working against the lateral displacement, inter-storey drift, story shear and story acceleration. It is found from the investigation that reaction of working to lateral load diminishes, while modular period is expanded in both X and Y bearings. Furthermore, it was reasoned that triple grating pendulum bearing is increasingly compelling in examination of different direction utilized in this investigation. Springer Nature Singapore Pte Ltd 2021. -
Asset productivity in organisations at the intersection of big data analytics and supply chain management
A close investigation is required on the fundamental instruments of an establishments big data analytics usage. This research paper mainly addresses how is an organizations value creation affected due to big data analytics usage, what is big data analytics, and what are its key antecedents in an organization to understand the aspects that influence the actual usage of big data analytics. Hence, the technology, organization, and environment framework are used. The review data collected from Indian founded corporations confirm that: organizational value creation is significantly affected by big data analytics usage in that organization; organizational BDA usage is indirectly influenced by environmental factors, technological factors, and organizational factors through top management support. Collectively, this research study will guide the business managers on the usage of big data analytics, and a theory-based comprehensive analysis of big data analytics usage and its key antecedents. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021. -
Steganography using Improved LSB Approach and Asymmetric Cryptography
Steganography deals with the craft of obscuring private data inside a spread media. In confidential data communication security is a vital issue. In this paper, we use a two-layer security. At first, data encryption is achieved by the method of RSA algorithm of asymmetric cryptography, and later the ciphered data is hidden into host image by an innovative embedding technique. To hide our ciphered data into host image, we modify the existing LSB technique and use a mapping function that ensures a secure and confidential image steganography resulting in a stego image. Here cryptography is blended with steganography and provides two level security in the confidential data transmission over the internet. 2020 IEEE. -
Hybrid Approach for Predicting Heart Disease Using Optimization Clustering and Image Processing
Heart disease (cardiovascular disease) is one of the core issues prevalent in this generation. Every year, millions of people die due to various heart diseases. The problem occurs due to hereditary or changes in life styles. Various data mining techniques are used in order to predict heart diseases. Data mining increases the accuracy, precision, and sensitivity of the model being used. In the proposed hybrid approach for predicting heart disease using optimization clustering and image processing (Hy-OCIP) model, a hybrid approach is used to predict heart diseases with the help of optimization, clustering, and image processing. After the heart image is being processed, centroid clustering is used for clustering the processed imaged into a set of chromosomes for optimization. The optimization method used for our model is genetic algorithm. The same methods are performed for both, a healthy and a heart patient. As a result, the model used in this research is able to distinguish between a normal patient and a heart patient by a hybrid combination of image processing, clustering, and optimization. 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.