Browse Items (2150 total)
Sort by:
-
A real time fog computing applications their privacy issues and solutions
Edge Computing (EC) has brought cloud technology to the channel's edge. It inherits some qualities from cloud services, but it also has some distinctive features such as geo-distribution, network connectivity, and reduced power. Along with the genetic inheritance, it also acquires the issues and concerns cloud computing services, such as renewable energy and resource allocation. This work provides a critical analysis of the fog architectural design in terms of security. Since 2018, the state of the artwork has been critically analyzed in terms of security mechanisms and security threats. The existing security methods are classified based on the security objectives they achieved. It would provide a complete and coherent difference between both the security areas investigated and those that have not. 2021 IEEE. -
Co-MoS2 nanoflower coated carbon fabric as a flexible electrode for supercapacitor
Cobalt doped MoS2 (Co-MoS2) nanoflowers have been successfully synthesized via a simple one-step hydrothermal method for supercapacitor applications. To identify the crystalline nature and morphology, the as-prepared material is characterized by XRD, SEM, and TEM measurements. The material exhibits a specific capacitance value of 86 F g-1 at a current density of 1 Ag-1 in symmetric two-electrode configuration with excellent cyclic stability of 98.5% even after 10,000 chargedischarge cycles. The results suggest the suitability of Co-MoS2 as an efficient electrode material for supercapacitors. 2021 Elsevier Ltd. All rights reserved. -
Application of Machine Learning in Customer Churn Prediction
Retaining customers is the central component of a company's growth strategy. It is evident that several industries are experiencing a surge in customer churn due to the global pandemic. As a result, customer retention that lies at the core of customer relationship management, has become the foundation for every industry to plan for future growth. By reducing customer churn, a company can maximize its profit. Studies suggest that significant advancements are made in the field of customer churn prediction in domains like telecom, banking, e-commerce and energy sector. The focus of the paper is to present a detailed review of the various machine learning techniques applied to address churn. Fifty-five papers related to churn classification published between 2004 and 2020 are collected and analyzed. The reviewed papers are categorized into five main themes. These themes are feature selection techniques, methods to handle class imbalance, experimentation with machine learning algorithms, hybrid models and ensemble models respectively. Finally, few suggestions are presented as direction for future research. 2021 IEEE. -
Alzheimer's Disease Detection using Machine Learning: A Review
Alzheimer's is a progressive brain disorder which is an untreatable, and inoperable and mostly affect the elderly people. There is a new case of Alzheimer's disease being discovered globally in every four seconds. The outcome is fatal, as it results in death. Timely identification of Alzheimer's disease can be beneficial for us to get necessary care and possibly even avert brain tissue damage by the time. Effective automated techniques are required for detecting Alzheimer's disease at very early stage. Researchers use a variety of novel approaches to classify Alzheimer's disease. machine learning, an AI branch use probabilistic technique that allow system to acquire knowledge from huge amount of data. In this paper we represent a analysis report of the work which is done by researcher in this field. Research has achieved quite promising prediction accuracies however they were evaluated the the non-existent datasets from various imaging modalities which makes it difficult to make the fair comparison with the other methods comparison among them. In this paper, we conducted a study on the effectiveness of using human brain MRI scans to detect Alzheimer's disease and ended with a future discussion of Alzheimer's research trends. 2021 IEEE. -
The effect of cutting fluid in improving the machinability of Inconel 718 using ceramic AS20 tool
Industries demand a vast usage of superalloys in heat resistant and high temperature applications. These include nozzle of rocket fuel engines, throttle valve of turbojet engines, turbine blade discs of aerospace industries, rivets and fittings of chemical and production industries, biomedical applications in super strength resistive steels. These superalloys such as Inconel 718 finds its vast applications in all such industries. To machine such materials a lot of wear and tear occurs at the cutting tool. Hence, cutting fluid helps in reduction of tool wear and improving surface roughness. In this paper, two cutting fluids Koolkut 40 and Hicut 590 have been used in emulsified form during the machining of Inconel 718 with Ceramic cutting tool. Hicut 590 has been seen a better heat resistive cutting fluid in reducing the tool wear and thus improving the life of the tool. 2021 Elsevier Ltd. All rights reserved. Selection and Peer-review under responsibility of the scientific committee of the Global Conference on Recent Advances in Sustainable Materials 2021. -
Distributed DoS Detection in IoT Networks Using Intelligent Machine Learning Algorithms
The threat of a Distributed Denial of Service (DDoS) attack on web-based services and applications is grave. It only takes a few minutes for one of these attacks to cripple these services, making them unavailable to anyone. The problem has further persisted with the widespread adoption of insecure Internet of Things (IoT) devices across the Internet. In addition, many currently used rule-based detection systems are weak points for attackers. We conducted a comparative analysis of ML algorithms to detect and classify DDoS attacks in this paper. These classifiers compare Nave Bayes with J48 and Random Forest with ZeroR ML as well as other machine learning algorithms. It was found that using the PCA method, the optimal number of features could be found. ML has been implemented with the help of the WEKA tool. 2021 IEEE. -
Green and Sustainable Software Model for IT Enterprises
The present study is based on developing a Green and Sustainable software because in the present-day computing devices are used for all kinds of purposes and they consume a lot of energy to perform these services. The ICT sector itself consumes a lot of energy so there is a need to think of alternatives that can reduce the level of energy consumption, thus, green ICT practice can be a good option. There is, however, a scarcity of researches that explains how the maintenance of green knowledge in ICT software development may be implemented. Since we recognize that software development process (SDL) plays an essential role in enabling the ICT community, uncontrolled green knowledge in developing software that would lead to the dilemma of failing to satisfy both the community's business and environmental requirements. Therefore, this research will concentrate on presenting a methodology applying an innovative model for managing the green software development and implementation. Keeping this concern in mind the present paper is going to provide a Green and Sustainable software model which can be used in green ICT practices and will be helpful in reducing the energy consumption used by computers. 2021 IEEE. -
Application of AI in video games to improve game building
Video Games Industry has been welcoming AI like any other industry for various tasks, AI in gaming helps to convey a much more realistic gaming experience, amplify player interaction and satisfaction over extensive periods. Additionally, the gaming industry is utilizing Artificial Intelligence to liberate its staff by making game development automated, quicker, and less expensive. In this work an experiment is described using Deep Neural Network and Statistical techniques for forecasting the location of an object in future frames of a video, it focuses on the engineering phase of the game, the proposed model combines future prediction of object location which helps to build the infinite universe in the videogame without any additional videos frames of the input video or hard coding any scenes to build the scenes further. 2021 IEEE. -
A Relative Analysis on the Spotting of Cardiovascular Disease Employing Machine Learning Techniques
Heart is one of the significant segments in the human body since it powers blood to the all the pieces of the body. Blood courses through the vein. Cardiovascular sickness is corresponded with the blockage of vein. The sign of heart sickness depends whereupon condition is impacting an individual. The term coronary illness is ordinarily utilized instead of cardiovascular infection. Dilated cardiomyopathy, Heart failure, Arrhythmia, Pulmonary stenosis, Mitral regurgitation, Coronary artery disease, Myocardial infraction, Mitral valve prolapse, Hypertrophic cardiomyopathy are the sorts of coronary illness. The several machine learning techniques are analyzed to spot heart disease. This paper gives relative investigation of coronary illness expectation utilizing machine learning. 2021 IEEE. -
HydroIoT: An IoT and Edge Computing based Multi-Level Hydroponics System
The depleting area of cultivable lands is increasing demands for implementing improved techniques that could use less space and produce more than traditional farming. This situation is common in all the developing and under developed countries. With a motivation to contribute towards providing solution to this growing problem of food scarcity, a Multi-Level Hydroponics System is proposed. The proposed system combines best of all trending technologies like IoT, Edge Computing and Computer Vision and applies it to Hydroponics. A cultivation estimation system based on image processing is implemented and accuracy of the same is tested with actual produce. The crop used for the proposed system is corn as it serves as best fodder for cattle. It was observed that with proposed system up to 95% accuracy in estimating fodder produce was achieved. 2021 IEEE. -
Zero Trust-Based Adaptive Authentication using Composite Attribute Set
Rapid evolution of internet-oriented applications has increased the threats to confidential data. Single-factor authentication approaches are no longer sufficient to ensure user credibility. Multi-factor authentication schemes are also not tamper-proof. A Zero Trust, adaptive authentication-based approach that uses the user's past behavior can offer protection in this scenario. This paper proposes a system that collects a composite attribute set that includes the user behavior, attributes of the application through which the user is requesting access, and the device used. The enhanced collection allows the creation of detailed context that allows granular variance calculation and risk score. 2021 IEEE. All Rights Reserved. -
An Intelligent System to Forecast COVID-19 Pandemic using Hybrid Neural Network
A current outbreak known as COVID-19 has been discovered from the coronavirus was informed by WHO. COVID-19 is a universal pandemic that has brought out the best and the worst of humanity. Due to an increase in the cases daily, COVID-19 is creating a menace to public health and establishes a disruption of the social and economic development of the countries. The problem is the hospitals are not able to provide proper facilities and treatments on time due to the lack of facilities in India. The purpose of this project to build an efficient hybrid deep learning model for forecasting the COVID-19 pandemic with multiple features that are responsible for the spread of COVID-19 in the top five states in India. In particular, a hybrid model that incorporates Auto-Regressive Integrated Moving Average and Long-term Short Memory is been used to forecast confirmed cases. The linear and non-linear dependencies in the dataset is been dealt with by an ARIMA-LSTM hybrid model. As a result, when compared to the outcomes of ARIMA, LSTM models independently, the hybrid model was giving better results and was performing well in forecasting COVID-19 cases. Through this, the policymakers will get prior information on COVID-19 cases in states which will help the government and healthcare departments to take prominent measures to prevent it. 2021 IEEE. -
Classification Algorithms Used in the Study of EEG-Based Epileptic Seizure Detection
Epilepsy is a neurological illness that has become more frequent around the world. Nearly 80% of epileptic seizure sufferers live in low- and middle-income nations. In persons with encephalopathy, the risk of dying prematurely is three times higher than in the general population. Three-quarters of people with brain illnesses in low-income countries do not receive the treatment they require. Recurrent seizures are a symptom of epilepsy, characterized by strange bursts of excess energy in mind. Experts agree that most people diagnosed with epilepsy may be managed successfully, provided the episodes are discovered early on. As a result, machine learning plays an essential role in seizure detection and diagnosis. Support Vector Machine(SVM), Extreme Gradient Boosting(Xgboost), Decision Tree Classifier, Linear Discriminant Analysis(LDA), Perceptron, Naive Bayes Classifier, k-Nearest Neighbor(k-NN), and Logistic Regression are eight of the most widely used machine learning classification algorithms used to classify EEG based mostly Epileptic Seizures. Almost all classifiers, according to the study, give an efficient process. Despite this, the results show that SVM is the most effective method for detecting epileptic seizures, with a 96.84% accuracy rate. For diagnosing Epileptic Seizures using EEG signals, the perceptron model has a lower accuracy of 76.21% percent. 2021 IEEE. -
Concept Drift Detection for Social Media: A Survey
The research over information retrieval from social media data has progressed for streaming data since the last decade. Recently, academic researchers have witnessed users' changing topics, trends, and intent on social media. This change of information with time takes into account the temporal attribute for real-time data, and thus, advances in this domain are exponentially growing. Although concept drift is still not explored due to a shortage of available datasets, concept drift for social media is minimally explored. This manuscript makes attempts to identify the types of concept drift for social media data, discuss the historical perspective of concept drift on social media, and enlist the possible research directions. 2021 IEEE. -
Online Health Information Behavior: A study based on PLS-SEM
In this digital era, internet provides a speedy, economical and convenient platform for seeking information on health. Moreover, the presence of audio visual resources for health and option to get expert opinion directly makes online health information seeking behaviour more adaptable among the health consumers. The major purpose of this study is to investigate the relationship between online health information seeking behaviour and the consequences of post-search. For doing the analysis, Smart PLS2 is used to execute structural equation modelling technique to understand the relationship between variables under study. The results of the study recommend that one's intention to search health information online is a significant predictor of post-search behavior in terms of altering health condition, visiting physician or sharing the same information with others. The present study gives a strong indication to the health care practitioners to understand the mechanism of desires and intentions of a healthcare consumer towards online health information seeking behavior. 2021 IEEE. -
Smart Tracker Device for Women Safety
Internet of Things (IoT) technologies assists by which machines, circuits, and many types of devices and interfaces communicate with one another. This IoT technology is useful for several purposes, especially in the field of Networking and Run-time data storage. Considering Women safety as our primary objective, we have used this technology and some other hardwares, including Raspberry Pi, to help the user in case of any emergency. Here also, with the help of IoT we are trying to make a device which can track the runtime location and the live, exact and efficient coordinates of the system which is in track. In the above context, in case of emergencies, it is very important to know the right place for the person to perform several important and critical actions whatsoever present at the right time.The GPS coordinates can be used to solve and analyse this problem. Additionally, we intend to add a voice recorder in case the women want to record any suspicious activity or information that can be helpful in the future for evidence purposes. In this paper, IoT is acting directly by receiving a person's GPS links from his server. Furthermore, we are combining the web interface with Google Maps on a single server so that the user's location can be tracked immediately using real-time coordinates.Our application can be used for wildlife, school-aged children, parent safety, and transportation services where location is a key factor. Although there are several direct and indirect usages of this project, the main use to which the project is concentrated is the use of this device to help our loved ones in the time of need. 2021 IEEE. -
Cloudsim exploration: A knowledge framework for cloud computing researchers
This paper aims to help find solutions for questions an early researcher may have to set up experiments in their development environment. Simultaneously, while identifying the steps required for experimenting, the authors narrowed on an experimenting toolkit for Cloud Computing as an area of their study. Because of such simulators, the cloud computing environment itself is available easily at the comfort of ones desktop resources instead of visiting an actual physical data center to collect trace and log files as data sets for real workloads. This paper acts as an experience sharing to naive researchers who are interested in how to go about to start cloud computing setups. A new framework called Cloud Computing Simulation Environment (CCSE) is presented with inspiration from Procure Apply Consider and Transform (PACT) model to ease the learning process. The literature survey in this paper shares the path taken by researchers for understanding the architecture, technology, and tools required to set up a resilient test environment. This path also depicts the introduced framework CCSE. The parameters found out of the experiments were Virtual Machines (VMs), Cloudlets, Host, and Cores. The appropriate combination of the values of the parameters would be horizontal scaling of VMs. Increasing VMs does not influence the average execution time after a specific limit on the number of VMs allocated. Nevertheless, in vertical scaling, appropriate combinations of the cores and hosts yield better execution times. Thereby maintaining the optimal number of hosts is an ultimate saving of resources in case of VM allocations. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021. -
Machine Learning-based Currency Information Retrieval for Aiding the Visually Impaired People
Paper currency is one of the most in-demand and long-established payment modes across the globe. People suffering from visual disabilities often face difficulties while handling paper currencies. Over the years, assisting technology has been rekindling itself to serve the aged and disabled person more aptly. Image processing methods and other sophisticated technologies, like Artificial Intelligence, Deep Learning, etc., can be employed to identify banknotes and fetch other valuable pieces of information from them. This paper proposes a framework that focuses on an integrated approach to retrieving data from the paper currency's uploaded image. The current version of the framework focuses on identifying the authenticity of the paper currency and classifying it according to its value. This work is an initiative to help visually impaired people to use paper currencies without assistance from other individuals and support them in living independently. 2021 IEEE. -
A Comparative Study on Indian Sign Language Representation
Communication among people can happen with the help of verbal or nonverbal language. Nonverbal communication is shared only among the hearing and speech impaired and is not common among others. Non-verbal communication is also different for different countries around the world. A solution to remove the gap between verbal and non-verbal communicators is to create an automated language translation model that can effortlessly convert sign language to text or audio. This area has been under research for a long time, but an economical and robust system that can efficiently convert signs into speech still does not exist. This paper focuses on different approaches that were put forward to turn Indian sign language into audio signals. The Sign Language Recognition (SLR) system is classified as isolated and continuous sign language models based on its input. 2021 IEEE. -
An AI Approach to Pose-based Sports Activity Classification
Artificial intelligence systems have permeated into all spheres of our life-impacting everything from our food habits to our sleep patterns. One untouched area where such intelligent systems are still in their infancy is sports. There has not been enough indulgence of AI techniques in sports, and most of the works are carried on manually by coaching staff and human appointees. We believe that intelligent systems can make coaching staff's work easier and produce findings that the human eye can often overlook. Here, we have proposed an intelligent system to analyze the beautiful game of tennis. With the use of computer vision architecture Detectron2 and activity-based pose estimation and subsequent classification, it can identify an action from a tennis shot (activity). It can produce a performance score for the player based on pose and movement like forehand and backhand. It can also be used to understand and evaluate the strengths and weaknesses of the player. The proposed approach provides a piece of valuable information for a player's performance and activity detection to be used for better coaching. The study achieves a classification accuracy of 98.60% and outperforms other SOTA CNN models. 2021 IEEE