Browse Items (2150 total)
Sort by:
-
Detection of Various Security Threats in IoT and Cloud Computing using Machine Learning
Due to the growth of internet technology, there is a sharp rise in the growth of IoT enabled devices. IoT (Internet of Things) refers to the connection of various embedded devices with limited processing and memory. With the heavy adoption of IoT applications, cloud computing is gaining traction with the ever-increasing demand to process and compute a massive amount of data coming from various devices. Hence, cloud computing and IoT are often related to each other. However, there are two challenges in deploying the IoT and cloud computing frameworks: security and Privacy. This article discusses various types of security threats affecting IoT and cloud computing, and threats are classified using machine learning (ML). ML has gained much momentum in recent years and is applied in various domains. One of the main subdomains of machine learning is used in IoT and cloud security. A machine learning model can be trained with data based on which the model can predict the impending security threats. Popular security techniques to protect IoT devices from hackers are IoT authentication, access control, malware detection, and secure overloading. Supervised learning algorithms can be used to detect malware in the runtime behavior of applications. The malware is detected from network traffic and is labeled based on its suspicious behavior. Post identification of malware, the application data is stored in a database trained via an ML classifier algorithm (KNN or Random Forest). With increased training, the model can identify malware applications with higher accuracy. 2022 IEEE. -
Implementing Ensemble Machine Learning Techniques for Fraud Detection in Blockchain Ecosystem
A new era of digital innovation, notably in the area of financial transactions, has been conducted in by the rise pertaining to block-chain technology. Although the decentralized nature of blockchain technology renders it prone to fraud, it has been praised for its capacity to offer a safe and transparent platform for financial transactions. The integrity of the entire blockchain network may be compromised by fraudulent transactions, which may also damage user and stakeholder trust. This study aims to assess machine learning's efficacy in detecting fraudulent transactions within blockchain networks and identifying the most effective model. To achieve its objectives, this study used a combination of data collection, data preprocessing, and machine learning techniques. The data used in this study was dataset of blockchain transactions and pre-processed using techniques such as feature engineering and normalization. Then trained and evaluated using several machine learning models, including Logistic Regression (LR), Naive Bayes (NB), SVM, XGboost, LightGBM, Random Forest(RF), and Stacking, in order to determine their effectiveness in detecting fraudulent transactions. XGBoost demonstrated the highest accuracy of 0.944 in the stacking model, establishing it as the top-performing model, closely followed by Light GBM. The study's discoveries offer significant practical implications for advancing fraud detection methods in blockchain networks. By pinpointing the most efficient machine learning model and crucial predictive fraud features, this research provides vital insights for refining precise detection algorithms, enhancing blockchain network security, and broadening their reliability across various applications. 2023 IEEE. -
Brain Tumor Localization Using Deep Ensemble Classification and Fast Marching Segmentation
A brain tumor is an unusual and excessive growth of brain cells, which can be cancerous (malignant) or noncancerous (benign). These growths can be risky as they press on healthy brain tissue or expand in the brain. Detecting brain tumors early is tough for radiologists. A typical brain tumor can double in size in just 25days, and without the right treatment, patients often have limited chances of survival, about six months. Initial symptoms can be confused with other illnesses, and brain cancer is difficult to diagnose because of the complex nature of the brain and tumor locations. In this study, we propose a strategy where we first sort medical images based on the presence of a brain tumor. Then, we pinpoint the part of the image containing the tumor through segmentation. We use a combined model of MobileNet-V3 and EfficientNetV2 for image classification. To segment the tumor in the image, we use a fast marching method. The combined model's classification accuracy is 98%, and the segmentation accuracy is 99.6%. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
A Implementation of Integration of AI and IOT Along with Metaverse Technology in the Field of Healthcare Industry
In the evolving panorama of healthcare, the appearance of Metaverse technology emerges as a transformative pressure, redefining traditional paradigms of healthcare shipping and education. This systematic assessment delves into the multifaceted impact of Metaverse technology, encapsulating their role in revolutionizing healthcare through modern-day academic frameworks, patient care interventions, and groundbreaking enhancements in medical imaging. Through an in-depth assessment of present-day literature, this observe illuminates the Metaverse's potential to facilitate immersive mastering tales, allow far flung interventions, and enhance the pleasant of scientific diagnostics and treatment making plans with its 3 -dimensional virtual environments. The findings underscore a burgeoning growth in Metaverse packages inner healthcare, highlighting its capability to noticeably beautify healthcare outcomes, affected person engagement, and expert abilities. Consequently, this evaluate advocates for the prolonged integration of Metaverse generation in healthcare, urging stakeholders to embody the ones enhancements and adapt to the following digital transformation in healthcare services and education. 2024 IEEE. -
GLANCEGuided Language Through Autoregression Establishing Natural and Classifier-Free Editing
In this study, researchers aimed to simplify text conversion into images using the latest text-to-image generation methods. While these methods have improved the quality and relevance of generated images, certain crucial questions remained unanswered, limiting their practicality and overall quality. To address these issues, the researchers introduced a novel text-to-image method. This method allows for better control of the scene depicted in the image through text, enhances the tokenization process by incorporating specific knowledge about key image regions such as faces and important objects, and provides guidance to the transformer model without needing a classifier. The outcome of this work was a model that achieved state-of-the-art results in terms of image quality and human evaluation, enabling the generation of high-fidelity 512?512-pixel images. Moreover, this method introduced new capabilities, including scene editing, text editing with reference scenes, handling out-of-distribution text prompts, and generating story illustrations. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Factors Influencing Online Shopping Behaviour: An Empirical Study of Bangalore
Online shopping is growing rapidly in India, predominantly driven by tremendous and substantial divulgatory activities among millennial consumers. Online shopping is becoming more popular and attracts significant attention because it has excellent potential for both consumers and vendors. The convenience of online shopping makes it more successful and makes it an emerging trend among consumers. When all the companies are striving against one another, certain factors influence the behavior of customers. This paper analyses the relationship between the critical, independent variables, including consumer behavior, cultural, social, personal, psychological, and marketing mix factors. The results revealed that the influence of Brand as a factor had positively influenced the customers decisions in shopping online and evaluates the customers level of satisfaction with Online shopping. Results provided in this research could be employed as reference information for Ecommerce app builders and marketers regarding such issues in the city. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Enhancing Medical Decision Support Systems withtheTwo-Parameter Logistic Regression Model
The logistic regression model is an invaluable tool for predicting binary response variables, yet it faces a significant challenge in scenarios where explanatory variables exhibit multicollinearity. Multicollinearity hinders the models ability to provide accurate and reliable predictions. To address this critical issue, this study introduces innovative combinations of Ridge and Liu estimators tailored for the two-parameter logistic regression model. To evaluate the effectiveness of the combination of ridge and Liu estimators under the two-parameter logistic regression, a real-world dataset from the medical domain is utilized, and Mean Squared Errors are employed as a performance metric. The findings of our investigation revealed that the ridge estimator, denoted as k4, outperforms other Liu estimators when multicollinearity is present in the data. The significance of this research lies in its potential to enhance the reliability of predictions for binary outcome variables in the medical domain. These novel estimators offer a promising solution to the multicollinearity challenge, contributing to more accurate and trustworthy results, ultimately benefiting medical practitioners and researchers alike. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Impact of Corporate Announcement of Green Innovation on Automaker's Market Value -An Event Study Methodology
The aim of this paper is to analyse the effects of the Green Innovation event and corporate announcements regarding green innovation on the stock price of the Automobile Industry and the performance of firms. The authors also aim to assess the impact of these events on business performance and identify the effective innovation strategy influenced by the type of corporate announcement. The study focuses on the corporate announcements made by the automobile industry and their impact on company performance, specifically in relation to the application of green innovation methods. Furthermore, there is no universally agreed upon standard for defining and categorising corporate announcements. The writers also exclude the impact of media and other events that occur during the event window when categorising these announcements. The findings of this study have important practical consequences. They suggest that the release of green innovations, which aim to protect the environment, can have an impact on an organization's stock market success. Specifically, the type of innovation and the trade segment in which the organisation operates can influence its stock market performance. Grenze Scientific Society, 2024. -
Machine Learning Model for Depression Prediction during COVID-19 Pandemic
Depression is an unfamous mental health disorder that has affected half the population worldwide. In December 2019, the break of the COVID-19 pandemic was first spotted in Wuhan, China, and later spread to 212 countries and territories worldwide, impacting half the population. It took a significant toll on their physical health and their mental health. Many among the population lost their loved ones, businesses, and being in quarantine for years, completely shifted to the online mode made everyone's life miserable. Many may be dealing with escalated levels of alcohol and drug use, sleeplessness, and an anxious state of mind. So, the need to address this and help the severely affected ones is significant. Self-quarantine also causes additional stress and challenges the mental health of citizens. This paper intends to identify the people who were mentally affected by the pandemic using machine learning techniques. A survey was conducted among college-going students and professionals. The paper used classification techniques such as Naive Bayes, KNN, Random Forest, Logistic Regression, k-fold cross-validation to get results. Support Vector Machine gave the maximum accuracy of 99.35%. 2022 IEEE. -
Regression Analysis using Machine Learning Algorithms to Predict CO2 Emissions
Precise measurement of fuel consumption and emissions plays an important role in evaluating the environmental effects of materials and stringent emission control methods, especially within the transportation sector. This sector represents a substantial contributor to both global greenhouse gas emissions and the release of hazardous pollutants, making accurate assessment imperative for addressing climate change. The primary objective is to construct accurate predictive models that estimate CO2 emissions based on vehicle attributes, fostering a deeper understanding of the environmental impact of vehicular activities. Leveraging the 'CO2 Emissions-Canada.csv' dataset, the paper embarks on an extensive journey of data preprocessing, exploratory data analysis, and model training. These algorithms are meticulously fine-tuned and evaluated through metrics such as R-squared and mean absolute percentage error, rendering insights into their predictive accuracies. In essence, this paper pioneers a pathway towards environmentally responsible mobility solutions, capitalizing on the fusion of data science and environmental conservation. 2024 Bharati Vidyapeeth, New Delhi. -
Modern Technology Usage for Education Field during COVID-19: Statistical Analysis
The COVID-19 pandemic has had vast effects on the concept of education as a whole. During the pandemic, students had no access to physical teaching practices, which had been adapted worldwide as the principal way of education since the 1800's. Due to the restrictions imposed to garner safety from the spread of the virus, this methodology had to be modified based on the situation at hand. Alternatives through the usage of Virtual Learning Platforms (VLP), Online Tutoring Platforms (OTP), Web Conferencing Platforms (WCP) and multiple assessment tools like plagiarism checker, poll sites, quiz platforms, online proctored examinations (OPE) started gaining popularity among all institutes to cope with the limitations levied. The technologies molded a path for student-teacher interaction, performance assessments, document sharing and online tutoring. This research highlights the lack of online tutoring equipment, educators' limited expertise with online learning, the knowledge gap, a inimical atmosphere for independent study, equity, and academic success in postsecondary learning. The goal of this review is to present an overview of available technologies for online teaching that can be used to improve the quality of education during COVID-19. 2022 IEEE. -
Theoretical performance evaluation of linear impairments in optical WDM networks with ITU-T defined fibers
This article investigates the performance degradation, in terms of Quality-factor (Q-factor), due to the combined effect of linear impairments, in an optical Wavelength Division Multiplexed (WDM) star network using various ITU-T compliant fibers (G.652, G. 652D, G. 653, G. 654 and G.655), based on the optical frequency grid defined by the ITU-T Recommendation G.692. The simulation results obtained through the developed mathematical model show that in presence of the deleterious effects of the combined linear impairments, compared to other fiber types, Q-factor performance of a G.653 and G.654 fiber is the 'best' and 'worst'. The results also verify that with the use of a fiber having high value of dispersion and attenuation, it may not be possible to obtain the desired performance. 2016 IEEE. -
Deep CNN Based Interpolation Filter for High Efficiency Video Coding
Video coding is a current focus in research area as the world focus more on multimedia transfer. High Efficiency Video Coding (HECV) is prominent among existing one. The interpolation in HEVC with fixed half-pel interpolation filter uses fixed interpolation filter derived from traditional signal processing methods. Some research came up with CNN based interpolation filter too, here we are proposing a deep learning-based interpolation filter to perform interpolation in inter prediction in HEVC. The network extracts the low-resolution image and extract the patch and feature in that to predict a high-resolution image. The network is trained to predict the HR image for the given patch, it can be repeated to generate the full frame in the HEVC. The system uses cleave approach to reduce the computational complexity. The trained network is validated and tested for different inputs. The results show an improvement of 2.38% in BD-bitrate saving for low delay configuration. 2024 IEEE. -
Barriers to Smart Home Technologies in India
Smart home technologies (SHT) are critical for effectively managing homes in a digital society. However, SHTs face challenges related to their limited use in developing country contexts. This study investigates the factors that act as barriers to SHT adoption among individuals in Bengaluru, India. The roles of perceived risk, performance and after-sale service, and demographics in using smart home technologies (SHT). This study used the data from the primary survey of 133 respondents. The collected data were analyzed using regression analysis. The results supported five of the proposed hypotheses, namely, perceived performance risk, perceived financial risk, perceived psychological risk, and technological uncertainty, which influence the Behavioral intention to adopt SHT. However, service intangibility is influenced by performance risk. Income and age influence the psychological risk and adoption of SHT. The study identifies the barriers to SHT adoption. The supportive environment for SHT needs to be strengthened to reduce the associated risks. IFIP International Federation for Information Processing 2024. -
Human activity recognition using wearable sensors
The advancement of the internet coined a new era for inventions. Internet of Things (IoT) is one such example. IoT is being applied in all sectors such as healthcare, automobile, retail industry etc. Out of these, Human Activity Recognition (HAR) has taken much attention in IoT applications. The prediction of human activity efficiently adds multiple advantages in many fields. This research paper proposes a HAR system using the wearable sensor. The performance of this system is analyzed using four publicly available datasets that are collected in a real-time environment. Five machine learning algorithms namely Decision tree (DT), Random Forest (RF), Logistics Regression (LR), K-Nearest Neighbor (kNN), and Support Vector Machine (SVM) are compared in terms of recognition of human activities. Out of this SVM responded well on all four datasets with the accuracy of 77%, 99%, 98%, and 99% respectively. With the support of four datasets, the obtained results proved that the performance of the proposed method is better for human activity recognition. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021. -
Hyperledger Fabric as a Secure Blockchain Solution for Healthcare 4.0 Framework
The healthcare sector deals with extremely sensitive information that must be administered in a safe and confidential way. The objective of the proposed framework is to utilize Blockchain Technology (BT) for tracking medical prescriptions and the implementation is carried out using the Hyperledger Fabric platform, an enterprise-grade open-source distributed ledger technology platform designed for Bigdata applications. Multiple entities, including patients, e-pharmacies, pharmacies, doctors and hospitals can establish connections by introducing several nodes in the Fabric chain. A web-centered application is provided for doctors, connecting them with participating pharmacies, hospitals and e-pharmacies through which, they can share patient prescription. Pharmacies and e-pharmacies have access to this data and can notify patients about the availability of prescribed medicines. Additionally, reminders for refills, such as heart medication, can be sent for patients requiring long-term medication. Patients can also try with nearby pharmacies and the availability of their prescribed medicines. The inclusion of a wallet feature in the application enables patients to use mobile tokens for making purchases. Patient data is treated with the utmost confidentiality, kept private, and accessed only upon request and with the consent of the concerned parties. This privacy is ensured through the use of zero-knowledge proof. Patients retain access to their complete medical history, facilitating interactions with doctors without the need for repetitive information sharing. 2023 IEEE. -
Smart Embedded Framework of Real-Time Pollution Monitoring and Alert System
The sustainability and progress of humanity depend on a clean, pollution-free environment, which is essential for good health and hygiene. Huge indoor auditorium does not have proper ventilation for air flow so when the auditorium is crowded the carbon di-oxide is emitted and it stays there for many days this may be a chance to spreading of COVID-19 and other infectious diseases. Without proper ventilation virus may present in the indoor auditorium. In the proposed system, emissions are detected by air, noise, and dust sensors. If the signal limit is exceeded, a warning is given to the authorities via an Android application and WiFi, and data is stored in cloud networks. In this active system, CO2 sensor, noise sensor, dust sensor, Microcontroller and an exhaust fan are used. This ESP-32 based system is developed in Arduino Integrated Development Environment (Aurdino IDE) to monitor air, dust and noise pollution in an indoor auditorium to prevent unwanted health problems related to noise and dust. More importantly, using IoT Android Application is developed in Embedded C, which continuously records the variation in levels of 3 parameters mentioned above in cloud and display in Android screen. Also, it sends an alert message to the users if the level of parameters exceeds the minimum and maximum threshold values with more accuracy and sensitivity. Accuracy and sensitivity of this products are noted which is very high for various input values. 2022 IEEE. -
IoT Based Enhanced Safety Monitoring System for Underground Coal Mines Using LoRa Technology
Extracting coal from Underground mine is a hazardous and tough job that needs continuous monitoring of environmental conditions to protect workers health and safety. Though some research works have explored wireless monitoring devices for underground mining, such as ZigBee and Wi-Fi technologies, they come with inherent restraints for instance restricted coverage, susceptibility to interference, reliability issues, security concerns, and high-power consumption. An Enhanced Safety Monitoring System for coal extraction from Underground Mines, employing LoRa communication technology for the effectual transmission of collected data to overcome existing challenges is discussed in this paper. The proposed system consists of two subsystems, one for monitoring the status of miners and another for comprehensive monitoring. LoRaWAN (Long Range Wide Area Network) is a multipoint protocol and this media access control (MAC) enables low-power devices to establish communication with Internet of Things (IoT) applications over extended wireless connections for long-range networks. LoRaWAN operates on lower radio frequencies, thereby providing a longer range of communication. This technology is known for its efficiency in optimizing LPWAN, offering extended range, extended battery life, robustness, and cost-effectiveness, making it highly suitable for industrial mining applications. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
IoT Based Risk Monitoring System
The Internet of things (IoT) aims at connecting different objects, things using internet. The IoT is expanding rapidly and this motivates to apply for the food preservation domain such as preserve the standard of the veggies and fruits. In this paper we have worked on a cold storage system to analyze the environmental conditions under which the food item is being stored. The proposed system senses the temperature, moisture, gas parameters of surrounding environment as these parameters affect nutritional values of food items. An Arduino-based system is created and put into operation; it serves as both a central hub and a network layer for the refrigerated holding tank. It is also linked to the cloud, where an open-source application server supports digital storage functions. By establishing a connection to the database (DB) via its IP address, the measured variables are delivered to the base station (BS) from the cloud and stored there. Then, a cooperative sensing model that uses many observed information as input and one merged informational item or action to be performed as output is tried. As a result, numerous inputs, such as temperature and humidity, were combined and averaged to provide a tightly integrated result. Last, the system integrated an android mobile application which is used to facilitate user interaction and connect through IoT based system that is station or gateway and the internet. GPS is Used to track the remote cold storage and transport container live locations. 2022 IEEE. -
Enhancing Kubernetes Auto-Scaling: Leveraging Metrics for Improved Workload Performance
Kubernetes is an open-source production-grade container orchestration platform, that can enable high availability and scalability for various types of workloads. Maximizing the performance and reducing the cost are two major challenges modern applications encounter. To achieve this, resource management and proactively deploying resources to meet specific application requirements becomes utmost important. Adopting Kubernetes auto-scaler to fit one's needs are important to maximize the performance. This study aims to perform a comprehensive analysis of Kubernetes auto-scaling policies. This paper also lists out the various parameters considered for auto-scaling, and prediction methods used to efficiently handle resource requirements of applications. The research findings reveal a scarcity in the existing work regarding the variety of workload based auto-scaling and custom metrics. This paper provides a concise overview of a forthcoming research endeavor that explores the utilization of custom metrics in conjunction with auto-scaling. 2023 IEEE.