Browse Items (11809 total)
Sort by:
-
Transformative Insights: Unveiling the Potential of Artificial Intelligence in the Treatment of Sleep Disorders - A Comprehensive Review
Disruptions to sleep have a substantial influence on people's overall health and quality of life. The conventional techniques for diagnosing and managing sleep disorders usually rely on subjective assessments and qualitative evaluations, that may have some accuracy and efficacy limitations. Nevertheless, recent developments in the field of artificial intelligence (AI) have presented new opportunities for better diagnosing and treating problems with insomnia. The paper reviews in depth the uses of AI in the domain of medical sleep medicine. We look at the use of algorithmic techniques for deep learning and machine learning for identifying indicators of sleep-related issues, the assessment of sleep quality, sleep tracking, and the establishment of individualized sleep therapeutics. We also discuss how AI is being used to construct forecasting models that may be used to identify individuals who are at risk of experiencing sleep issues and improve treatment strategies. In addition, we talk about the challenges and potential outcomes of incorporating AI-based techniques into clinical practice. Overall, our research highlights how AI has the potential to transform the field of sleeping medicine and improve outcomes for people with sleep-related conditions. 2023 IEEE. -
Sentiment and Emotion Analysis of Significant Diseases in India and Russia
Healthcare organizations need this information to understand and treat the patient's concerns. The motivation for this kind of analysis is how patients provide this information while wrapping it in their thoughts and emotions. It is less practicable to manually study all the free and abundant health-related knowledge accessible online to arrive at decisions that might contribute to an immediate and beneficial decision. Sentiment analysis methods perform this function through automated procedures with minimal human intervention. In this paper, an investigation is conducted to compare the region-wise, language-wise, and sentiment analysis of the tweets collected from Russia and India. The results obtained through research have shown some significant characteristics of the language models used for language detection. The inferenc and analysis obtained from the observations are included in this paper. 2023 IEEE. -
Adoption of Fintech Towards Asset and Wealth Management: Understanding the Recent Scenario in India
The finance sector as a whole has seen a significant transformation as a result of technological advances, which has impacted how financial institutions function and how financial activities are carried out. Fintech is currently a facilitator and a disruptor. Today Fintech companies have the greatest influence on the wealth management industry financial technology, or Fintech, began with nimbler start-ups upending banks with their innovative methods, and later developed into the latter forging partnerships with banks to strengthen the whole financial services ecosystem. At the intersection of both money and technology, the term wealthtech was developed. Any digital solution designed to simplify wealth management procedures is referred to as digital wealth management solutions. The fintech sector, which also encompasses digital payments, regulatory technology, insurance technology, etc., includes wealthtech. Fintech in wealth management has created a paradigm change in the investing sector. Wealthtech's technology is disrupting the wealth management industry. This study analyses the recent development of the wealth management industry and financial investment in the digital Indian age. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023. -
Preprocessing Big Data using Partitioning Method for Efficient Analysis
Big data collection is the process of gathering unprocessed and unstructured data from disparate sources. As data deluge, the large volume of data collected and integrated consist missing values, outliers, and redundant records. This makes the big dataset insignificant for processing and mining knowledge. Also, it unnecessarily consumes large amount of valuable storage for storing redundant data and meaningless data. The result obtained after applying mining techniques in this insignificant data lead to wrong inferences. This makes it inevitable to preprocess data in order to store and process big dataset effectively and draw correct inferences. When data is preprocessed before analytics the storage consumption is less and computation and communication complexity is reduced. The analytics result is of high quality and the needed time for processing is considerably reduced. Preprocessing data is inevitable for applying any analytics algorithm to obtain valuable pattern. The quality of knowledge mined from large volume of big data depends on the quality of input data used for processing. The major steps in big data preprocessing include data integration from disparate sources, missing value imputation, outlier detection and treatment, and handling redundant data. The process of integration includes steps such as extraction, transformation, and loading. The data extraction step gathers useful data used for analytics and the transformation process organize the collected data in structured format suitable for analytics. The role of load process is to store transformed data into secured storage so that data can be obtained and processed effectively in future. This work provides preprocessing techniques for big data that deals with missing values and outliers and results in obtaining quality data partitions. 2023 IEEE. -
Sentiment Analysis on Educational Tweets: A Case of National Education Policy 2020
Due to COVID-19 pandemic lockdowns, the transition from traditional class-room-based approaches, there has been rise in online education. There is a growing need to adopt the best global academic and innovative practices and implement the National Education Policy-2020 (NEP) in Indian education. This study uses a dataset, NEPEduset, created by gathering tweets about education. An attempt has been made in this study to examine the tweets by preprocessing, generating labels or sentiments using standard tools and libraries in Python language, applying and comparing various machine learning (ML) algorithms. ML approaches are powerful and used in various applications ranging from sentiment analysis, text analysis, natural language processing (NLP), image processing, object detection. ML methods are widely used in sentiment analysis tasks and text annotations. This work uses Text-Blob, Valence Aware Dictionary for Sentiment Reasoning (VADER), and a Customized method, SentiNEP to analyze the sentiment score of tweets' text. SentiNEP method is shown is produce better results for various experiments conducted for the dataset, NEPEduset. Various supervised ML models have been applied for text classification of user sentiment. Word2Vec feature extraction technique has been applied to build and evaluate the models. Performance metrics such as precision, accuracy, F1 score and recall have been used to evaluate the ML models. The results reveal that the support vector machine and random forest classifiers achieve higher accuracy with Word2Vec. The performance results have been compared with VADER, TextBlob and SentiNEP. It has been found that the SentiNEP method produces better results. 2023 IEEE. -
Controlling the Accuracy and Efficiency of Collision Detection in 2d Games using Hitboxes
Collision detection is a process in game development that involves checking if two or more objects have intersected or collided with each other. It is a fundamental aspect of game mechanics that cannot be overlooked. Games invloves assets/sprites, which tend to be drawn digitally with the help of a computer program. This paper discusses controlling and detecting collisions in games that make use of PNG images as game assets. The conventional way to detect collision in a game is to check if the object is within the bounding box of another object or asset. However, such a method lacks realism and doesn't work well with much complex shapes as the game might register a hit when another object collides with the transparent part of the object being checked for collision. In order to overcome these limitations, the proposed algorithm divides the entire image into smaller rectangles and stores its coordinates in an array. The array is then pruned by removing coordinates with no translucent or opaque elements. Collision is detected by checking if any of the points of the collision object is inside the image array. 2023 IEEE. -
Deep Learning-Based Optimised CNN Model for Early Detection and Classification of Potato Leaf Disease
After rice and wheat, potatoes are the third-largest crop grown for human use worldwide. The different illnesses that can harm a potato plant and lower the quality and quantity of the yield cause potato growers to suffer significant financial losses every year. While determining the presence of illnesses in potato plants, consider the state of the leaves. Early blight and late blight are two prevalent illnesses. A certain fungus causes early blight, while a specific bacterium causes late blight. Farmers can avoid waste and financial loss if they can identify these diseases early and treat them successfully. Three different types of data were used in this study's identification technique: healthy leaves, early blight, and late blight. In this study, I created a convolutional neural network (CNN) architecture-based system that employs deep learning to categorise the two illnesses in potato plants based on leaf conditions. The results of this experiment demonstrate that CNN outperforms every task currently being performed in the potato processing facility, which needed 32 batch sizes and 50 epochs to obtain an accuracy of about 98%. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Crowd Monitoring System Using Facial Recognition
The World Health Organization (WHO) suggests social isolation as a remedy to lessen the transmission of COVID-19 in public areas. Most countries and national health authorities have established the 2-m physical distance as a required safety measure in shopping malls, schools, and other covered locations. In this study, we use standard CCTV security cameras to create an automated system for people detecting crowds in indoor and outdoor settings. Popular computer vision algorithms and the CNN model are implemented to build up the system and a comparative study is performed with algorithms like Support Vector Machine and KNN algorithm. The created model is a general and precise people tracking and identifying the solution that may be used in a wide range of other study areas where the focus is on person detection, including autonomous cars, anomaly detection, crowd analysis, and manymore. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Conceptual Framework for AI Governance in Public Administration - A Smart Governance Perspective
With the public governance lagging behind the fast evolving of AI in their attempts to yield sufficient governance, corresponding principles are necessary to be in par with this dynamic advancement. As AI becomes more pervasive and integrated into various domains, there is a growing need for AI governance models that can ensure that the development and deployment of AI systems align with ethical, legal, and social standards. There are some answers that literature puts forward to the question onthe way the government and public administration has to react to the huge concerns related to AI and usage of policies to avoid the emerging challenges. In this survey, AI problems and the prior AI regulation techniques are analyzed. In this research study, a governance model for AI is proposed by combining all the facets and also implements a new procedure for governing AI. This study will help the decision makers to make smart government a reality by using AI governance framework. 2023 IEEE. -
Machine Learning Algorithms for Prediction of Mobile Phone Prices
The drastic growth of technology helps us to reduce the man work in our day-to-day life. Especially mobile technology has a vital role in all areas of our lives today. This work focused on a data-driven method to estimate the price of a new smartphone by utilizing historical data on smartphone pricing, and key feature sets to build a model. Our goal was to forecast the cost of the phone by using a dataset with 21 characteristics related to price prediction. Logistic regression (LR), decision tree (DT), support vector machine (SVM), Naive Bayes algorithm (NB), K-nearest neighbor (KNN) algorithm, XGBoost, and AdaBoost are only a few of the popular machine learning techniques used for the prediction. The support vector machine achieved the highest accuracy (97%) compared to the other four classifiers we tested. K-nearest neighbors 94% accuracy was close to that of the support vector machine. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Brain Tumor Detectin Using Deep Learning Model
Brain tumor is a life-threatening disease that can disrupt normal brain functioning and have a significant impact on a patient's quality of life. Early detection and diagnosis are crucial for effective treatment. In recent years, deep learning techniques for image analysis and detection have played a vital role in the medical field, supplying more accurate and reliable results. Segmentation, the process of distinguishing between normal and abnormal brain cells or tissues, is a critical step in the detection of brain tumors. In this research, we aim to investigate various techniques for brain tumor detection and segmentation using Magnetic Resonance Imaging (MRI) images. The detection process begins by analyzing the symmetric and asymmetric shape of the brain to identify abnormalities. We will then classify the cells as either Tumored or non-Tumored. This research is aimed at finding a more accurate and efficient method for detecting brain tumors. Four Keras models are compared side by side to find out the best deep learning model for providing a suitable outcome. The models are ResNet50, DenseNet201, Inception V3 and MobileNet. These models gave training accuracy of 85.30%, 78%, 78%, and 77.12% respectively. 2023 IEEE. -
Performance Analysis of YOLOv7 and YOLOv8 Models for Drone Detection
Drone detection techniques are used to detect unmanned aerial systems (UAS) also commonly known as drones. A rapid increase in these drones has limited the airspace safety and so the research for drone detection has emerged. This study compares between the two widely used deep-learning models, previously used YOLOv7 and the latest YOLOv8. The overall finding of this study suggests that the YOLOv8 deep-learning model appears to be more promising and may make valuable contributions on their own. We got the result that for 10 epochs YOLOv8 gave 50.16% accuracy while YOLOv7 gave 48.16% accuracy making YOLOv8 more promising for the task. As a practical application for future work, we intend to deploy YOLOv8 on edge devices to achieve real-time drone detection in critical security applications. 2023 IEEE. -
Deploying NLP Techniques for Earnings Call Transcripts for Financial Analysis: A Reverse Phenomenon Paradigm
This study analyses the influence of quarterly board room discussions conducted in the form of "Earnings Call Transcripts"and company's stock price changes in the subsequent periods. In this study, sentiments were extracted from the "textual quarterly transcripts"of three major software companies for the last ten years. The extracted sentiments were statistically analyzed for patterns and types. The study led to the development of a new response variable called the 'Inverse Effect'. The 'Inverse Effect' simply refers to the discordance between the sentiment in the boardroom discussions available in the document form and changes in the stock price movements. If the sentiment for the current quarter is positive and the changes in the stock price movements is also positive in the subsequent quarter, it is considered as "concordance"and if the changes in the stock price movements is opposite to the sentiments it will be called as "discordance"which is the inverse effect. The study basically looks at the areas where the Weak Market Hypothesis (WMH) is not valid.The findings emerged from the study suggest a possible causality between the sentiments in the transcripts and the stock price changes. It was also found that sentiment polarity, three-quarter average stock price and the previous quarter stock price are the key determinants of the 'Inverse Effect'. Based on the findings from the study, appropriate machine learning models were developed and evaluated to predict the 'Inverse Effect' on the performance of individual stocks of a few select companies. 2023 IEEE. -
Securing International Law Against Cyber Attacks through Blockchain Integration
Cyber-attacks have become a growing concern for governments, organizations, and individuals worldwide. In this paper, we explore the use of blockchain technology to secure international law against cyber-attacks. We discuss the advantages of blockchain technology in providing secure and transparent data storage and transmission, and how it can enhance the security of international law. We also review the current state of international law regarding cyber-attacks and the need for a robust and effective legal framework to address cyber threats. The study proposes a blockchain-based approach to secure international law against cyber-attacks. We examine the potential of blockchain technology in providing a decentralized and tamper-proof database that can record and track the implementation of international laws related to cyber-attacks. We also discuss how smart contracts can be utilized to automate compliance with international laws and regulations related to cybersecurity. The study also discusses the challenges and limitations of using blockchain technology to secure international law against cyber-attacks. These include the need for interoperability between different blockchain networks, the high energy consumption of blockchain technology, and the need for international cooperation in implementing and enforcing international laws related to cybersecurity. Overall, this study provides a comprehensive overview of the potential of blockchain technology in securing international law against cyber-attacks. It highlights the need for a robust legal framework to address cyber threats and emphasizes the importance of international cooperation in implementing and enforcing international laws related to cybersecurity. 2023 IEEE. -
Design and Simulation of a Multi-purpose Adjustable Modular Robot for Precision Agriculture
Global population growth, climate change, and labor shortages all represent substantial obstacles to meeting global food needs, and agricultural robots provide a possible solution. This work uses a survey to evaluate user behavior toward using agricultural wheel robots on small farms. The survey was conducted in various parts of India (Coimbatore, Bhubaneswar, and Silchar), where 250 large and medium commercial farmers participated. After the survey, a new robotic system architecture is a multi-purpose, adjustable, modular, and affordable robotic platform designed for precision agriculture. A unique feature is added to the design, which helps the robot to adjust by itself based on the row distances and crop heights. The software was designed using the Fusion 360, and simulation is carried out in GAZEBO and Robot Operating System (ROS). 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
An Predictive Deep Learning Model is used to Identify Human Tissue-Specific Regulatory Variations For Diabetes
A predictive deep learning model is designed to predict a target variable based on a set of input variables to diagnose the tissue base regulatory variants in the human islets. In this article, the identification on human tissue-specific regulatory variations for Diabetes using the Pima dataset converting data into images, and then the input variables may include genetic data, gene expression data, and the proposed model uses Pima Indian dataset with the attributes such as age, sex, and BMI to predict whether a person has Diabetes or not. And this dataset is incorporated a combination two layered ResNet18 + ResNet50 and SVM classifier. The results obtained are compared with KNN, Naive bayes, SVM Random Forest, Gradient descent and the accuracy achieved is 98%. 2023 IEEE. -
The Efficiency of Ensemble Machine Learning Models on Network Intrusion Detection using KDDCup 99 Dataset
With the advent of data communication the increased usage of the technologies results in network intrusions and associated attacks. Consequently, the data violation rates are increased abundantly and that sacrifices Confidentiality, Integrity and Availability. This article focused on the network Intrusion Detection System (IDS) that detects various attacks and types. Machine learning (ML) has the potential to spot known-experience and Zero-day attacks. Consequently, the article has considered ML and ensembled models for the various attack classification. The major contributions of the current article are 3-fold. Initially, to understand the relevance and sufficiency of the dataset through exploratory data analysis. Second, the comprehensive understanding of the various attacks, its nature, various types and classifications and finally, the empirical analysis of the dataset through the potential of various ML models. The article utilized various discriminative models for the execution and all of the models have shown better accuracy. The tree-based ensemble model, Random Forest has outperformed the rest of the models with higher accuracy in the training and testing samples of 99.997 % and 99.969 % respectively. 2023 IEEE. -
Structural Health Monitoring Using Machine Learning Techniques
Environmental factors, particularly vibrations and temperature can damage the structural health of the building. To avoid heavy damage to the building and to maintain the building's structural health this paper suggests monitoring of building using machine learning algorithms. Machine learning algorithms are used to predict temperature and vibration damages in buildings. Temperature and vibration values are obtained through the grove vibration sensor and NTC thermistor attached to Raspberry Pi 3B plus. In the Raspberry pi, Machine learning algorithms are executed. The activation functions used are Relu, Sigmoid, and Tanh. The experimental results reveal that the Sigmoid activation function gives the best results in terms of metrics with accuracy 94.25, Precision 0.951, Recall 0.912, and F1 score 0.388. The sigmoid function is used in machine learning algorithms for predicting temperature and vibrations. Predicted temperature and vibrations damages are sent to the server and viewed through the user mobile. K- Nearest Neighbor algorithm produced best results with an accuracy rate of 85.50, Precision of 0.922, Sensitivity of 0.830, Specificity of 0.840 and F1 score of 0.873. 2023 IEEE. -
Analysis of Fraud Prediction and Detection Through Machine Learning
In today's world the rate of fraudulent activities has significantly elevated, because of which a need for a competent system is required. Among all the fraudulent activities insurance fraud has the most dominating rate of growth. Fraud studies have suggested, that upon identifying the similar characteristics of a fraudulent claim with the claimants, a system of forensic and data-mining technologies for fraud detection can be set up. In this, seek to define fraud and fraudster, and look at the types of fraud and followed by the consequences of fraud to financial systems. As fraud is getting widespread these days epically in the health care insurance system, dealing with this problem has become a necessity. Unsupervised machine learning algorithms such as K-Means clustering along with supervised algorithms used in machine learning, like support vector machines, logistic regression, design trees etc. can play a very vital role in binary class classifications, which would ultimately help in identifying and outreaching the desired goal of fraudulent detection. In the end, this paper specifies the best or the most appropriate model that could be used in the given dataset to produce the most accurate results, based on certain parameters of confusion metrics like accuracy, precision, and specificity. 2023 IEEE. -
Deep Convolutional Neural Networks Network with Transfer Learning for Image-Based Malware Analysis
The complexity of classifying malware is high since it may take many forms and is constantly changing. With the help of transfer learning and easy access to massive data, neural networks may be able to easily manage this problem. This exploratory work aspires to swiftly and precisely classify malware shown as grayscale images into their various families. The VGG-16 model, which had already been trained, was used together with a learning algorithm, and the resulting accuracy was 88.40%. Additionally, the Inception-V3 algorithm for classifying malicious images into family members did significantly improve their unique approach when compared with the ResNet-50. The proposed model developed using a convolution neural network outperformed the others and correctly identified malware classification 94.7% of the time. Obtaining an F1-score of 0.93, our model outperformed the industry-standard VGG-16, ResNet-50, and Inception-V3. When VGG-16 was tuned incorrectly, however, it lost many of its parameters and performed poorly. Overall, the malware classification problem is eased by the approach of converting it to images and then classifying the generated images. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.