Browse Items (2150 total)
Sort by:
-
Pneumonia Detection using Ensemble Transfer Learning
Pneumonia is among the most common illnesses and causes to death among the young children worldwide. It is more serious in under-developed countries as it is hard to diagnose due to the absence of specialists. Chest X-ray images have essentially been utilized in the diagnosis of this disease. Examining chest X-rays is a difficult task, even for an experienced radiologist. Information Technology, especially Artificial Intelligence, have started contributing to accurate diagnosis of pneumonia from chest X-ray images. In this work, we used deep learning, transfer learning, and ensemble voting to increase the accuracy of pneumonia detection. The models utilized are VGG16, MobileNetV2, and InceptionV3, all pre-trained on ImageNet, and used the Kaggle RSNA CXR image dataset. The results from these models are ensembled using the weighted average ensemble approach to achieve better accuracy and obtained 98.63% test accuracy. The results are promising, and the proposed model can assist doctors in detecting pneumonia quickly and accurately from Chest X-Ray. 2022 IEEE. -
Small signal stability in a Microgrid using PSO based Battery storage system
This papers covers, modelling and analysis of a small microgrid with Battery Storage System (BSS). A sample microgrid is considered, it is analyzed for small signal stability, with and without BSS. Voltage, frequency and current THD which are considered to be the major attributes of stability in a microgrid, the behavior of these attributes is observed with and without BSS. The Battery storage system is connected to the considered microgrid through PV array, using PSO algorithm, which improves the stability of the system. Simulation is carried out using MATAB/ Simulink and the results are presented. Microgrid considered consists of PV array, Diesel Generator and Battery storage system. These sources are modelled according to the loads connected to the microgrid. BSS acts as emergency backup to the considered system and also provides small signal stability to the microgrid. Simulation is carried out with BSS and without Battery Storage in the Islanded mode. The obtained results show that microgrid with BSS is more stable during small disturbances and also acts as backup power supply. A Properly modelled microgrid can act as power backup for industries. 2022 IEEE. -
DKMI: Diversification ofWeb Image Search Using Knowledge Centric Machine Intelligence
Web Image Recommendation is quite important in the present-day owing to the large scale of the multimedia content on the World Wide Web (WWW) specifically images. Recommendation of the images that are highly pertinent to the query with diversified yet relevant query results is a challenge. In this paper the DKMI framework for web image recommendation has been proposed which is mainly focused on ontology alignment and knowledge pool derivation using standard crowd-sourced knowledge stores like Wikipedia and DBpedia. Apart from this the DKMI model encompasses differential classification of the same dataset using the GRU and SVM, which are two distinct differential classifiers at two different levels. GRU being a Deep Learning classifier and the SVM being a Machine Learning classifier, enhances the heterogeneity and diversity in the results. Semantic similarity computation using Cosine Similarity, PMI and SOC-PMI at several phases ensures strong relevance computation in the model. The DKMI model yields overall Precision of 97.62% with an accuracy of 98.36% along with the lowest FDR score of 0.03 and is much better than the other models that are considered to be the baseline models. 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
Deep Convolution Neural Network for RBC Images
The suggested study's objectives are to develop an unique criterion-based method for classifying RBC pictures and to increase classification accuracy by utilizing Deep Convolutional Neural Networks instead of Conventional CNN Algorithm. Materials and Procedures A dataset-master image dataset of 790 pictures is used to apply Deep Convolutional Neural Network. Convolutional Neural Network and Deep Convolutional Neural Network comparison using deep learning has been suggested and developed to improve classification accuracy of RBC pictures. Using Gpower, the sample size was calculated to be 27 for each group. Results: When compared to Convolutional Neural Network, Deep Convolutional Neural Network had the highest accuracy in classifying blood cell pictures (95.2%) and the lowest mean error (85.8 percent). Between the classifiers, there is a statistically significant difference of p=0.005. The study demonstrates that Deep Convolutional Neural Networks perform more accurately than Conventional Neural Networks while classifying photos of blood cells[1]. 2022 IEEE. -
Analysis of Flexoelectricity with Deformed Junction in Two Distinct Piezoelectric Materials Using Wave Transmission Study
Analysis of flexoelectricity in distinct piezoelectric (PE) materials bars (PZT-7A, PZT-6B) with deformed interface in stick over Silicon oxide layer is studied analytically with the help of Love-type wave vibrations. Using the numerical data for PE material, then research achieves the noteworthy fallouts of flexoelectric effect (FE) and PE. The effect of flexoelectricity is compared first between biomaterials of piezoelectric ceramics. Dispersion expressions are procured logically for together electrically unlocked/locked conditions under the influence of deformed interface in the complex form which is transcendental. Fallouts of the research identify that contexture consisting of FE has a noteworthy impact on the acquired dispersion expressions. Existence of FE displays that the unreal section of the phase velocity rises monotonically. Competitive consequences are displayed diagrammatically and ratified with published outcomes. The outcomes of the present research done on both the real and imaginary section of the wave velocity. The comparative study between the two piezo-ceramics bars helps us to understand the properties of one piezo-material over the another and as an outcomes the significance of the present study helps in structural health monitoring, bioengineering for optimizing the detection sensitivity in the smart sensors. 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
Analysis of Workloads for Cloud Services
Capturing best quality datasets for a study is the first evidence for better outcomes of research. If the analysis are based on such datasets, then the metrics, the characteristics and few factors determines proof point for well proven theories. Hence it is obvious that we rely on the best possible ways to arrive at such data acquiring sources. It can be either based on historical techniques or from the innovations in application of it to industry. This paper introduces a mapping framework for analyzing, and characterizing data previously used by research community and how they are made to fit for Cloud systems, i.e. using 'workloads' and 'datasets' as the 'refined definitions'. It was contributed in the past two decades within the scientific community setting their own workflow analysis mechanisms. The framework thus is validated by acquiring a sample workload per layer of cloud. The sources are form the literature that are available from existing scientific theories. These workloads are then experimented against the three tiers of the cloud computing ie., IaaS(Infrastructure as a Service), PaaS(Platform as a Service), & SaaS(Software as a Service). The selected data is analyzed by the authors for an offline model presented here based on the Machine Learning tool-kits. There are future studies planned for and to be experimented in a cloud auto scaled environment with online model as well. 2022 IEEE. -
Analysis of error rate for various attributes to obtain the optimal decision tree
The competitiveness and computational intelligence are required to increase the gross profit of the product in a market. The classification algorithm rpart is applied on retail market dataset. The regression rpart decision tree algorithm is implemented with principal component analysis to impute data in the missing part of the dataset. The objective is to obtain an optimal tree by analysing cross validation error, standard deviation error, and number of splits and relative error of various attributes. The results of various attributes by ANOVA method are compared to choose the best optimal tree. The tree with minimum error rate is considered for the optimal tree. Copyright 2022 Inderscience Enterprises Ltd. -
Seismic Activity-based Human Intrusion Detection using Deep Neural Networks
Human intrusion detection systems have found their applications in many sectors including the surveillance of critical infrastructures. Generally, these systems make use of cameras mounted on strategic locations for surveillance purposes. Cameras based detection systems are limited by line-of-sight, need regular maintenance and dependence of electricity for operations. These are all detrimental to the efficiency of these detection systems, especially in remote locations. To overcome these challenges, intrusion detection systems based on seismic activities have been in use. The seismic activities collected through geophones from the human footfalls can act as the input for these detection systems. This also poses a challenge as the data generated by the geophones for the seismic activities produced from footsteps are not always identical and hence not accurate. In this proposed work, a Deep Neural Network based approach has been used on the dataset collected from the geophones to effectively predict the presence of humans. The results gave a success rate with 94.86% accuracy with testing data and 92.00% accuracy with real-time data with the geophones deployed on an area covered with grass. 2022 IEEE. -
Reinforcement Learning based Autoscaling for Kafka-centric Microservices in Kubernetes
Microservices and Kafka have become a perfect match for enabling the Event-driven Architecture and this encourages microservices integration with various opensource platforms in the world of Cloud Native applications. Kubernetes is an opensource container orchestration platform, that can enable high availability, and scalability for Kafkacentric microservices. Kubernetes supports diverse autoscaling mechanisms like Horizontal Pod Autoscaler (HPA), Vertical Pod Autoscaler (VPA) and Cluster Autoscaler (CA). Among others, HPA automatically scales the number of pods based on the default Resource Metrics, which includes CPU and memory usage. With Prometheus integration, custom metrics for an application can be monitored. In a Kafkacentric microservices, processing time and speed depends on the number of messages published. There is a need for auto scaling policy which can be based on the number of messages processed. This paper proposes a new autoscaling policy, which scales Kafka-centric microservices deployed in an eventdriven deployment architecture, using a Reinforcement Learning model. 2022 IEEE. -
An Analysis of Machine Learning and Deep Learning to Predict Breast Cancer
According to the report published by American Cancer Society, breast cancer is currently the most prevalent cancer in women. In addition, it is the second leading cause of death. It needs to be taken into serious consideration. Earlier and faster detection can help in the earlier and easier cure. Normally, medical practitioners take a large amount of time to understand and identify the presence of cancer cells in the human body. This can lead to serious complications even to the death of the individual. Hence there is a need to identify and detect the presence of this disease very accurately and in a shorter span of time. Like every other industry, the medical industry is shifting its paradigm to automation giving excellent results having high accuracy and efficiency, which is achieved using Artificial Intelligence. There are two sets of models developed based on the numerical dataset Wisconsin and image dataset BreakHis. Machine Learning algorithms and Deep Learning algorithms were applied on the Wisconsin dataset. Meanwhile, Deep Learning models were used for analysis of the Breakhis dataset. Machine Learning models- Logistic Regression, K Neighbors, Naive Bayes, Decision tree, Random Forest and Support vector classifiers were used. Deep Learning models- normal deep learning models, Convolutional Neural Network (CNN), VGG16 & VGG19 models. All the models have provided a very good accuracy ranging between 75% and 100%. Since medical research has a requirement for higher accuracy, these models can be considered and embedded into several applications. Grenze Scientific Society, 2022. -
Firefly Algorithm andDeep Neural Network Approach forIntrusion Detection
Metaheuristic optimization has grown in popularity as a way for solving complex issues that are difficult to solve using traditional methods. With fast growth of the available storage space and processing capabilities of the modern computers, the machine learning domain, that can be succinctly formulated as the process of enabling the computers to make successful forecasts based on the previous experiences, has recently been under spectacular growth. This paper presents intrusion detection approach by utilizing hybrid method between firefly algorithm and deep neural network. The basic firefly algorithm, as a frequently employed swarm intelligence method, has several known deficiencies, and to overcome them, an enhanced firefly algorithm was proposed and used in this manuscript. For experimental purposes, KDD Cup 99 and NSL-KDD datasets from Kaggle and UCL repositories were taken and comparison with other frameworks that have been validated for the same datasets was executed. Based on simulation data, proposed method was able to establish better values for accuracy, precision, recall, F-score, sensitivity and specificity metrics than other approaches. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Smart Online Oxygen Supply Management though Internet of Things (IoT)
We are surrounded by oxygen in the air we We cannot even exist without the ability to breathe. The need for oxygen has increased during the COVID19 pandemic, and although there is enough oxygen in our country, the main issue is getting it to hospitals or those in need on time. This is simply due to a significant communication gap between suppliers and hospitals, so we plan to implement an idea that will close this gap using real-time tracking as we can track the movement of oxygen tankers by gathering the requirements. We are using an ESP32 Wi-Fi module, a MEMS pressure sensor that enables the combination of precise sensors, potential processing, and wireless communication, such as Wi-Fi, Bluetooth, IFTTT, and MQTT protocols, to implement it successfully. The pressure sensor publishes the value of oxygen remaining from the location to the MQTT broker. 2022 IEEE. -
Internet of Things and Cloud Computing Involvement Microsoft Azure Platform
The rapid advancement of cloud technology has resulted in the emergence of many cloud service providers. Microsoft Azure is one among them to provide a flexible cloud computing platform that can scale business to exceptional heights. It offers extensive cloud services and is compatible with a wide range of developer tools, databases, and operating systems. In this paper, a detailed analysis of Microsoft Azure in the cloud computing era is performed. For this reason, the three significant Azure services, namely, the Azure AI (Artificial Intelligence) and Machine Learning (ML) Service, Azure Analytics Service and Internet of Things (Io T) are investigated. The paper briefs on the Azure Cognitive Search and Face Service under AI and ML service and explores this service's architecture and security measures. The proposed study also surveys the Data Lake and Data factory Services under Azure Analytics Service. Subsequently, an overview of Azure Io Tservice, mainly Io THub and Io TCentral, is discussed. Along with Microsoft Azure, other providers in the market are Google Compute Engine and Amazon Web Service. The paper compares and contrasts each cloud service provider based on their computing capability. 2022 IEEE. -
Smart Attendance Management System using IoT
Taking student attendance is mandatory in an educational organization, and maintaining those attendance plays a vital role. The conventional way of taking student attendance in any institution is time-consuming and challenging, because in the conventional procedure taking attendance/Roll call is performed manually by calling student names as per their roll numbers and marking 'absent(A)' or 'present(P)' on the attendance/logbook accordingly in every class per day. To improve teaching efficiency/teaching time in classrooms by reducing the time required for Roll call's, we have proposed a biometric student attendance system based on IoT. The proposed system records students' attendance using the facial-based biometric system and stores the attendance details on the server through the internet. In this system, the Raspberry pi camera captures the student face images and compares them with the stored images in the database. If the captured image is comparable with the stored image, then the student's attendance is recorded on the remote server as a present(P) in class; otherwise, attendance is recorded as absent (A). The developed system has been tested for sample classes, and the results proved that the system is simple, cost-effective, and portable for managing students' attendance. 2022 IEEE. -
Review of open space rules and regulations and identification of specificities for plot-level open spaces to facilitate sustainable development: An Indian case
Rapid urbanization and an increase in the alteration of natural resources have led to climate crises, driving the need to promote sustainable development. Urban open space management plays a vital role in such scenarios. Research on urban open spaces has been mainly conducted at regional, municipal, and neighborhood scales. Rarely has the focus been on the plot-level potentials and management of open spaces. Therefore, the study looks into the Indian development control rules and regulations and identifies that although these stipulate the percentage of open space for development on each plot, specificities for open spaces are unclear. Further, the study analyses quantitative and qualitative aspects of open spaces for selected group housing schemes in Pune city. The inquiry shows that per capita open space in Pune is comparatively lower than national standards. The quantitative aspects include FSI, building ground coverage, built-up area, number of floors, and number of dwelling units, and each relates to open spaces in one way or another. The qualitative interpretations disclose that a plot-level open space can significantly impact the regional-level open space network. Hence, the research advocates a bottom-up approach wherein plot-level open space can become the focus in formulating new norms and policies for sustainable development. Published under licence by IOP Publishing Ltd. -
Design of a Decision Making Model for Integrating Dark Data from Hybrid Sectors
The research on Dark data, from its definition to identification and utilization is a widely identified and encountered research problem since 2012 when Gartner defined Dark data as every possible information that an organization collects, process, analyze and store throughout regular business activities, but usually fails to make use of the stored information for other suitable purposes. The presence of dark data and its impact has been experienced by every sector, these data occupy large storage and remain unused. In this paper, we analyze Dark Data and proposed a design model to utilize dark data from multiple sectors and providing a solution to any critical situation a person might be in. For eg: Multiple cash transactions from an organizational bank account in a hospital successively over a period of 2-3 days may indicate a health emergency of any particular employee from that organization. Thus we are considering institutional data, medical data, and banking data in which machine learning algorithms can contribute huge changes in the current system and can help the decision-makers to make better decisions. The paper also proposes a few techniques and methods for the conversion of unstructured dark data to structured one and some extraction techniques for data using NLP and Machine Learning. Grenze Scientific Society, 2022. -
A review on the scope of using calcium fluoride as a multiphase coating and reinforcement material for wear resistant applications
Solid lubricants play a vital role in the smooth and safe operation of many tribological industrial applications like cutting and forming tools, rolling and sliding contact bearings, gears, cams and protective coating in gas turbine engines for aerospace applications. Generally liquid lubricants are widely used for reducing the friction between the contacting parts which reduce the wear rate and increase the life of the parts. However, these liquid lubricants become useless when they are exposed to high temperature, high pressure and vacuum environmental conditions. Solid lubricants are those materials that can suitably reduce the friction and wear between the contacting or sliding surfaces that are in extreme environments like low and high temperature and pressure. Among the different types of solid lubricants, calcium fluoride is widely used owing to its excellent lubricity at elevated temperature. This paper initially describes the criteria for selecting solid lubricant and provides a comprehensive summary on calcium fluoride solid lubricant which can be used as a coating material in various high temperature metal and ceramic matrix composites for wear resistant applications. Further, investigations related to the selection of optimized coating parameters, synerging multiphase solid lubricants and soft metals with optimal percentage, selection of filler materials, mismatch in coefficient of thermal expansion and its impact on coating life are summarised and discussed. Finally, the scope of synthesizing calcium fluoride solid lubricant from discarded eggshell powders is explored. 2022 Elsevier Ltd. All rights reserved. -
A Reliable Method of Predicting Water Quality Using Supervised Machine Learning Model
Water contributes to around 70% of the world's exterior and is perhaps the primary source essential to supporting life. The rapid growth of urban and industrial geographies has prompted a disintegration of the quality of water at a concerning pace, bringing about nerve-racking sicknesses. Water quality has been expectedly assessed through costly and tedious lab and measurable examinations, which render the contemporary thought of continuous observing disputable. The disturbing results of helpless water quality require an elective strategy, which is speedier and more economical. With this inspiration, this exploration investigates a progression of administered AI calculations to appraise the Water Quality Index (WQI), which acts as a unique attribute to express the generic nature of water. The proposed system utilizes multiple info boundaries, specifically, temperature, pH, dissolved O2 concentration, and all-out broken down molecules. Of the multitude of utilized regression calculations and slope boosting, the water quality index can be expected most productively, with an MSE of 0.27. The propositioned study accomplishes acceptable precision by utilizing a minimum number of features to improve the chances of it getting implemented progressively in water quality recognition frameworks. 2022 IEEE. -
Breast Cancer Survival Prediction using Gene Expression Data
Breast cancer is one of the most common forms of cancer in the world.[1]. Breast, skin, colon, pancreatic, and other 100 types of cancer have founded globally. An accurate breast cancer prognosis can save many patients from having unnecessary treatment and the huge medical costs that come with it. Multiple gene mutations can possibly transform a normal cell into a cancerous one. Genomic variations and traits have a significant effect on cancer. Genetic abnormalities caused by various circumstances drive numerous efforts to find biomarkers of breast cancer advancement. Early Detection of Cancer types is the only way to recover the patients from this acute disease. In this paper, a proposed Deep learning algorithm and Machine learning algorithms are used to predict the survival of cancer patients using clinical data and gene expression data. The Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) dataset is split into clinical and gene data for detailed preprocessing. This proposed method gives a better understanding of the condition and assesses how effective treatment methods are by using Deep Learning and Machine Learning models on gene data. Logistic Regression is the most accurate method identified. Grenze Scientific Society, 2022. -
Digitalization of Online Classes Among Higher Secondary Students in the Emerging Shift of Post Covid-19 (Second Wave)
The second wave of COVID-19 in India has left higher secondary school students befuddled, unhappy, and unsure about their future. During the second wave of the COVID-19 epidemic, a number of factors influence the effectiveness of online learning. Hence, the main objective of this research paper is focused on understanding the factors influencing online learning among higher secondary students. Researchers identified variables such as attitude, tools and technology, and quality of teaching and social support through extensive literature review. The research study adopted snowball sampling technique and used a survey-based online questionnaire for collecting the data; responses were obtained from 394 respondents from the state of Kerala in India. PLS-SEM was used to test the proposed hypotheses. The results of the study indicate that quality of teaching is the only factor that impacts the effectiveness of online classes among higher secondary students. Attitude, technology and tools, and social support are observed to have insignificant impact on online learning effectiveness. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.