Browse Items (2150 total)
Sort by:
-
Cross-Modal Ingredient Recognition and Recipe Suggestion using Computer Vision and Predictive Modeling
This paper is focused on the development of a novel system known as 'IngredEye.' It involves various approaches that can be grouped into categories, such as computer vision, including YOLOv8, a KNN prediction model, and a Flutter framework that hosts all of them in a mobile application environment. Previous studies have analyzed the application of computer vision and OpenCV recognition in cooking and proved that such approaches could enhance the level of convenience in the culinary field. This paper addresses issues like changes in lighting, occlusions, and other factors that have to be solved by the algorithms envisaged for real applications. The objective of this paper solely relies on integrating the OpenCV object detection method with comprehensive machine learning techniques specialized for the culinary field. Presenting the end-user with recipe recommendations based on the visual input they have given. 2024 IEEE. -
Leveraging Ensemble Methods for Accurate Prediction of Customer Spending Scores in Retail
This study primarily aims to estimate consumer spending trends in a retail context. The goal is to identify the best model for predicting Purchasing Scores, which indicate customer loyalty and potential income, using demographic and financial data. The dataset included information about customers' age, gender, and annual income, and the objective was to analyze their Spending Scores. Several regression models were tested, including Linear Regression, Random Forest, Gradient Boosting, K-Nearest Neighbors (KNN), and Lasso Regression. To improve the models, we engineered features like Age Squared, Income per Age, and Spending Score per Income. Each model was trained and tested using 3fold cross-validation. We evaluated their performance with Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R2) metrics. The results showed significant differences in model performance. The Random Forest model stood out, with the lowest Mean Absolute Error (MAE) of 0.33, Root Mean Square Error (RMSE) of 0.52, and the highest R-squared (R22) score of 0.9997. Gradient Boosting also performed well, achieving a Mean Absolute Error (MAE) of 1.77, Root Mean Square Error (RMSE) of 2.41, and an Rsquared (R2) score of 0.9930. While Linear Regression showed moderate accuracy, KNN and Lasso Regression had higher errors and lower R2 values, indicating less reliable predictions. The findings suggest that ensemble methods, particularly Random Forest, excel at predicting customer Spending Scores. The high accuracy and reliability of this model point to its potential for customer segmentation and targeted marketing strategies, ultimately enhancing customer relationship management and boosting business value. Further refinement and exploration of additional features could further improve these prediction capabilities. 2024 IEEE. -
Predicting and Analyzing Early Onset of Stroke Using Advanced Machine Learning Classification Technique
Around the world, stroke is the leading cause of death. When blood vessels in the brain rupture, they cause damage. Alternatively, blockage in a blood vessel that supplies oxygen and other nutrients may also lead to this disease. This study uses various machine learning models to predict whether someone will have a stroke or not. Different physiological features were taken into account by this study while using Logistic Regression; Decision Tree Classification; Random Forest Classification; K-Nearest Neighbors (KNN); Support Vector Machine (SVM); Nae Bayes classifier algorithm; and XGBoost classification algorithm - these were used for six different models to ensure accurate predictions are made. We will accomplish the finest exactness with Bayes cv look which may be a hyper-tuning classifier with 92.87%. This consideration can be utilized for future work by doing the increase and include designing on the dataset. It is constrained to literary information, so it might not continuously be right for foreseeing stroke. so utilize the datasets that contain pictures and work on those datasets. 2024 IEEE. -
Advanced Sentiment Analysis: From Lexicon-Enhanced BERT to Dimensionality Reduction Using NLP
Social media platforms serve as vital connections for communication, generating massive quantities of data that represent an array of perspectives. Efficient sentiment analysis is necessary for understanding public opinion, particularly in domains such as product reviews and socio-political discussion. This paper develops a novel sentiment analysis model that is customized for social media data by integrating machine learning algorithms, language processing techniques with part-of-speech tagging, and dimensionality reduction methods. The model will improve sentiment analysis performance by tackling challenges like noise and data domain variations. To further improve sentiment representation, it includes convolutional neural networks (CNNs), BERT embeddings, N-grams, and sentiment lexicons. The model's effectiveness is determined on a variety of datasets, which enhances sentiment analysis in social media discussion. This paper goes beyond sentiment analysis in code-mixed, multilingual text and highlights the importance of careful data before treatment and an extensive variety of ML algorithms. This study attempts to explain the nuances of sentiment analysis and its use in social media discussions through methodical research. 2024 IEEE. -
Diabetes Mellitus Classification Using Machine Learning Algorithms with Hyperparameter Tuning
Diabetes Mellitus is a prevalent condition globally, marked by elevated blood sugar levels resulting from either insufficient production of insulin or the body cells' inability to respond appropriately to released insulin. For people with diabetes to lead healthy, normal lives, early identification and treatment of the condition are essential. With the need to move away from current traditional procedures, towards a noninvasive methodology, machine learning and data mining technologies can be very useful in the classification of diabetes. Creating an effective machine learning model for the classification of diabetes mellitus was the primary goal of this research. This work is primarily carried out on combined Pima Indian diabetes dataset and German Frankfurt diabetes dataset. The class imbalance issue has been resolved using Synthetic Minority Oversampling Technique. One-hot encoding is applied to convert categorial features to numerical and various single and ensemble classifiers with the best hyperparameters obtained using GridSearchCV method were employed on the pre-processed dataset. With an AUC of 0.98 and maximum accuracy of 98.79%, the Random Forest ensemble technique outperformed the other models, according to the experimental results. As a result, the algorithm might be used to predict diabetes and alert doctors to serious cases that call for emergency care. 2024 IEEE. -
Harnessing Machine Learning for Mental Health: A Study on Classifying Depression-Related Social Media Posts
This study is of particular relevance in the way it identifies depression-related content on social media using a machine learning model to classify posts and comments. This dataset, encompassing around 6500 entries from various platforms including Facebook, was rigorously annotated by four proficient English-speaking undergraduate students together with the final label which is established via majority voting. Data Preprocessing, initial cleaning, normalization and TF-IDF feature creation through vectorization for the output of POS tags. The different machine learning models that were trained and tested are Logistic Regression, Random Forest, SVM (Support Vector Machine), Naive Bayes Gradient Boosting Algorithm K-NN (K nearest Neighbors) AdaBoost Decision Tree. Authors evaluated the models and measured their accuracy, precision score, recall rate (also known as sensitivity) in addition to F1-score. Gradient Boost, Random Forest, and SVM were top performers among which Gradient boosting was found to be an overall best one with almost 98.5%. They show that machine learning model can successfully predict the label of social media posts, as a way for accurately identifying depression from text data. This detailed model performance evaluation is useful in understanding what each approach does well and poorly, shedding light into whether they are / would be actually suitable for real-world applications. This study not only developed discriminative classifiers, but also included detailed analysis of their performance which should hopefully guide future work and help in practical implementations for real-time mental health monitoring. Through this work, this study aim to facilitate timely identification of depression-related posts, ultimately supporting mental health awareness and intervention efforts on social media platforms. 2024 IEEE. -
Decoding Big Data: The Essential Elements Shaping Business Intelligence
In today's Business Intelligence (BI) world, Big Data Analytics integration has become critical, transforming company strategy and decision-making processes. This study investigates the complex influence of Big Data on business intelligence, focusing on important drivers of this transition. It investigates how Big Data's improved data processing capabilities, integration of advanced analytics techniques such as machine learning, and real-time data insights enable businesses to make more informed decisions and achieve a competitive advantage. Furthermore, the paper emphasizes the importance of personalized consumer insights, operational savings, and strategic benefits obtained from predictive analytics when adopting Big Data for BI. 2024 IEEE. -
Impact of Variable Viscosity and Gravity Variations on Rayleigh-Bard Instabilities of Viscoelastic Liquids in Energy Sustainable System
Energy sustainability systems are vital for transitioning to a low-carbon economy, addressing climate change, and ensuring a sustainable future for all. Rayleigh-Bard convection (RBC) in viscoelastic liquids is a crucial phenomenon in various industrial and environmental applications, including energy sustainability systems where fluid dynamics play a pivotal role in optimizing heat transfer and system efficiency. The study deals with the combined influence of variable viscosity and variable gravity on RBC in viscoelastic liquids. The influence of space-dependent gravity on the onset of convection is considered. The results are analyzed against the background of constant gravity RBC in viscoelastic/Newtonian liquids with constant/variable viscosity. The possibility of variable gravity accelerating/decelerating the onset of convective instability is examined in this paper. 2024 IEEE. -
Sentiment Analysis on Live Webscraped YouTube Comments Using VADER Sentiment Analyzer
After the covid disease came in the beginning of 2020s, the amount of people using social medias has increased dramatically. So as an effect of that, the viewers and engagement in one of the worlds largest platform by google called YouTube also increased. So many new content creators also born during these times. So this project is getting the sentiment from the audience or user to the content creators by which they can improve their content quality. This research holds promise in harnessing the power of sentiment analysis to enhance the overall YouTube experience and inform content creators and platform administrators in their decision-making processes. Understanding these trends is vital for content creators, as it can offer invaluable insights into viewer engagement and preferences. By gaining a deeper understanding of how viewers react to content, creators can refine their strategies, tailor their content to their audience, and enhance the overall quality of videos. By incorporating sentiment information into recommendations, the platform can suggest videos that resonate more effectively with users, thereby increasing engagement and satisfaction. The identification of negative sentiment and harmful comments enables YouTubes content moderation systems to proactively address issues such as hate speech, harassment, and toxicity. This, in turn, contributes to a safer and more welcoming space for users to share their thoughts and opinions. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Machine Learning Insights into Mobile Phone Usage and Its Effects on Student Health and Academic Achievement
The research intends to find how students' health and academic performance are affected by their smartphone use. Considering how widely smartphones are used among students, it is important to know how they could affect health and learning results. This study aims to create prediction models that can spot trends and links between smartphone usage, health ratings, and academic achievement, thereby offering insightful information for teachers and legislators to encourage better and more efficient use among their charges. Data on students' mobile phone use, health evaluations, and academic achievement were gathered for the study. Preprocessing of the dataset helped to translate categorical variables into numerical forms and manage missing values. Trained and assessed were many machine learning models: Random Forest, SVM, Decision Tree, Gradient Boosting, Logistic Regression, AdaBoost, and K-Nearest Neighbors (KNN). The models' performance was evaluated in line with their accuracy in influencing performance effects and health ratings. Predictive accuracy was improved by use of feature engineering and model optimization methods. With 63.33% of accuracy for estimating health ratings, the SVM model was most successful in capturing the link between smartphone usage and health results. With an accuracy of 50%, logistic regression performed very well in forecasting performance effect, therefore stressing important linear connections between consumption habits and academic success. Random Forest and Decision Tree models were less successful for performance impact even if they showed strong performance in health forecasts. These results highlight the need of customized treatments to reduce the detrimental consequences of too high mobile phone use on students' academic performance and health. 2024 IEEE. -
AdvanDNN: Deep Neural Network Analysis of Neuroimaging for Identifying Vulnerable Brain Regions in Autism Spectrum Disorder
Exploring the neurological framework of autism spectrum disorder (ASD) presents a significant challenge due to its diverse manifestations and cognitive impacts. This study introduces an innovative deep learning approach, employing an advanced deep neural network (AdvanDNN) model to identify and analyze brain regions vulnerable to ASD. Utilizing the AAL116 brain atlas for anatomical standardization, our model processes a comprehensive set of neuroimaging data, including structural and functional MRI scans, to discern distinct neural patterns associated with ASD. The AdvanDNN model, with its robust deep learning architecture, was meticulously trained and validated, demonstrating a notable accuracy of 91.17% in distinguishing between ASD-affected individuals and controls. This marks an improvement over the state of the art, contributing a significant advance to the diagnostic processes. Notably, the model identified a pronounced anticorrelation in brain function between anterior and posterior regions, corroborating existing empirical evidence of disrupted connectivity within ASD neurology. The analysis further pinpointed critical regions, such as the prefrontal cortex, amygdala, and temporal lobes, that exhibit significant deviations from typical developmental patterns. These findings illustrate the potential of deep learning in enhancing early detection and providing pathways for intervention. The application of the AdvanDNN model offers a promising direction for personalized treatment strategies and underscores the value of precision medicine in addressing neurodevelopmental disorders. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Utilizing Deep Learning Techniques for Lung Cancer Detection
Deep learning can extract meaningful insights from complex biomedical statistics, which includes Radiographs and virtual tomosynthesis. Traits in contemporary deep studying architectures have enabled faster and more correct mastering of the functions gifted in clinical imagery, main to better accuracy and precision in medical analysis and imaging. Deep studying strategies may be used to pick out patterns within the pics which may be indicative of illnesses like lung cancer. Those ailment patterns, which include small lung nodules, can be used for early detection and prognosis of the sickness. Recent studies have employed deep learning strategies consisting of Convolutional Neural Networks (CNNs) and switch learning to come across most lung cancers in CT pictures. The first step in this manner is to generate datasets of pictures of the lungs, each from wholesome people and those with most lung cancers. Those datasets can then be used to teach a deep knowledge of a set of rules that may be optimized to it should locate those styles. Once educated, the version can be used to come across styles indicative of lung most cancers from new take a look at images with high accuracy. For further accuracy and reliability, extra up-processing techniques, along with segmentation and records augmentation, may be used. Segmentation can be used to detect a couple of lung nodules in a photo, and records augmentation can be used to lessen fake high quality outcomes. 2024 IEEE. -
Exploring Shopping Opportunities and Elevating Customer Experiences Through AI-Powered E-Commerce Strategies
This research explores the efficacy of clustering algorithms in enhancing customer experiences within the e-commerce landscape. Through experiment trials utilizing K-means and DBSCAN clustering techniques, valuable insights have been gleaned. The trials yielded silhouette scores ranging from 0.55 to 0.72, indicating moderate to good clustering quality across different experiments. In K-means clustering, the number of clusters varied from 3 to 6, with inertia values spanning approximately 722.41456.8. Conversely, DBSCAN clustering resulted in varying cluster numbers, ranging from 2 to 4, contingent on the combinations of epsilon and min_samples values explored. These findings underscore the significance of judiciously selecting clustering algorithms and parameter settings to achieve meaningful segmentation of e-commerce data. Effective utilization of clustering algorithms empowers businesses to discern valuable insights into customer behavior, preferences, and patterns. Consequently, businesses can tailor their strategies to deliver personalized experiences, targeted marketing campaigns, and optimized product recommendations. This research propels the exploration of additional clustering techniques and parameter refinements for enhanced clustering performance in e-commerce applications. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Data Mining Techniques to Enhance Customer Segmentation and Targeted Marketing Strategies
The retail industry is facing an ever-increasing challenge of effectively identifying and targeting its customers. Using traditional segmentation techniques to fully capture the intricate and ever-changing character of customer behavior is difficult. This project will examine sales data from a general shop using an assortment of data mining technologies in order give insights into customer habits and purchasing trends. Retail sales records builds the dataset. K-means clustering, association rule mining, and regency, the frequency, and monetary (RFM) analysis will all be employed to look into the data. This study contributes to create something of focused marketing strategies and consumer segmentation by identifying high-value and atrisk clients. Association rule mining illuminates consumer taste and actions by identifying hidden patterns and correlations in large datasets. These discoveries extend the scope of our comprehension of consumer purchasing habits and offer data for more targeted advertising initiatives. Additionally, the K-means clustering algorithm divides customers according to their purchasing habits and behavior, allowing profound knowledge to enhance marketing and sales strategies. Findings from the research will give an extensive awareness of customer behavior and purchasing dynamics, which will improve the efficacy of the general store's marketing and sales campaigns. The most effective technique for exploiting insights from sales data will be discovered by contrasting the outcomes of RFM analysis, K-means clustering, and association rule mining. This work promises to make substantial improvements to data mining and buyer behavior research algorithms, and it has the capacity to be implemented across an extensive selection of corporate restrictions intended to improve their sales strategies. 2024 IEEE. -
High-Speed Parity Number Detection Algorithm inRNS Based onAkushsky Core Function
The Residue Number System is widely used in cryptography, digital signal processing, image processing systems and other areas where high-performance computation is required. One of the computationally expensive operations in the Residue Number System is the parity detection of a number. This paper presents a high-speed algorithm for parity detection of numbers in Residue Number System based on Akushsky core function. The proposed approach for parity detection reduces the average time by 20.39% compared to the algorithm based on the Chinese Remainder Theorem. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Impact of Artificial Intelligence on Business Strategy and Decision-Making
Market analysis as knowledge-enhancement function, its use in internal politics, its abuse, and its ability to generate market understanding were recognised as the four key performance variables in market analysis. Profitability and bottom line may be increased, inefficiencies in corporate processes can be reduced, and other hidden insights can be uncovered by analyzing financial accounting transactions. The research focuses on the business strategy in decision-making using artificial intelligence. Reviewing existing research and providing recommendations. In this study, firstly collect the dataset finance data from Kaggle for the better-trained model. After that perform the pre-processing data for outlier removal. The implementation work is complete on the Python programming language. The results showed that the proposed KNN, the Decision tree model, achieved high accuracy. Businesses and organisations working in the field of artificial intelligence (AI) might greatly benefit from this research in terms of narrowing down the profiles that are certain to avoid in the future. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Multi-Agent Deep Reinforcement Learning for Hybrid Motion Planning in Dynamic Environments
This research presents a novel approach to addressing the challenges of gesture forecasting in impenetrable and dynamic atmospheres by integrating a hybrid algorithm within a multi-agent system framework. Traditional methods such as Force-based motion planning (FMP) & deep reinforcement learning (RL) often struggle to handle complex scenarios involving multiple autonomous agents due to their inherent limitations. To overcome these challenges, we propose a hybrid algorithm that seamlessly combines the strengths of RL and FMP while leveraging the coordination capabilities of a multi-agent system. By integrating this hybrid algorithm into a multi-agent framework, we demonstrate its effectiveness in enabling multiple agents to navigate densely populated environments with dynamic obstacles. Through extensive simulation studies, we illustrate the superior performance of our approach compared to traditional methods, achieving higher success rates and improved efficiency in scenarios involving simultaneous motion planning for multiple agents. A hybrid motion planning algorithm is also introduced in this very research. Performance Comparison of Hybrid Algorithm, Deep RL, and FMP are also discussed in the result section. This research paves the way for the development of robust and scalable solutions for motion planning in real-world applications such as collaborative robotics, autonomous vehicle fleets, and intelligent transportation systems. 2024 IEEE. -
Investigating the Use of Natural Language Processing in Electronic Medical Record
Natural language processing (NLP) implemented in digital scientific records (EMRs) can substantially enhance the nice and efficiency of affected person care. The purpose of NLP implemented in EMRs is to extract applicable facts from affected persons' notes written in a human language together with English. This information can then be stored in a suitable structured form for further evaluation and records mining. NLP has been carried out in the clinical field for the reason that Fifties as a green approach for retrieving textual content-based data and reading interactions among affected persons and healthcare professionals. With the arrival of electronic facts, NLP has come to be extra extensively applied for the diffusion of purposes, inclusive of automatic coding, scientific choice aid, and medical doctor order access. This summary makes a of exploring the usage of NLP in EMRs. The scope of this research consists of an evaluate of present NLP technologies and their software in EMRs. It additionally outlines a number of the present-day demanding situations inside the use of NLP for clinical information and shows capability answers. Finally, the potential applications of NLP-driven EMRs are discussed, inclusive of making use of in-health practitioner order entry, scientific choice assistance, and population health control. 2024 IEEE. -
An Integrated Scalable Healthcare Management System Using IOT
Healthcare management is the challenging task of maintaining the patients medical-related data and images. Pervasive computing, which consists of a wireless network, is an innovative medium for medical data transmission. Here, we propose SHMS (Scalable Healthcare Management System) and interoperability, an available and user-friendly platform. It utilizes a huge amount of data and medical images that must be managed and stored for processing and further investigation. In our work, data like heartbeat, temperature, blood pressure, and ECG readings are collected using different sensors and in one gateway protocol. This design is used for transferring, managing, and accessing documents containing health-related information, which is scattered across different system and organization domains. It is scalable because cloud platforms provide communication APIs, the web service interfaces ensure interoperability, the availability makes patients, doctors, or administrators able to access medical-related data anywhere, and Android OS makes it user-friendly. The security of the data collected can be achieved by authenticating storage using a cryptographic ECC algorithm. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Integrating AI and Cybersecurity: Advancing Autonomous Vehicle Security and Response Mechanisms
The rapid evolution of autonomous and connected vehicles has led to their integration with numerous technologies and software, rendering them vulnerable targets for cybersecurity attacks. While efforts have traditionally focused on preventing these attacks, the escalating risk underscores the importance of also vindicating their wallop. Nevertheless, this procedure is often onerous & facade scalability confronted, particularly due to connectivity issues in automobiles. This research advises a vehicle-based vibrant imposition response scheme, enabling swift responses to a variety of incidents and reducing reliance on external security centers. The classification encompasses an inclusive range of probable retorts, a procedure for evaluating retorts, & innumerable assortment approaches. Implemented on an embedded platform, the solution was evaluated using two distinct cyberattack use cases, highlighting its adaptability, responsiveness, volume for dynamic arrangement constraint alterations & nominal memory trail. Concurrently, this paper presents an innovative (AVSF) that synergistically integrates (AI) and cybersecurity techniques to fortify AV resilience against evolving threats. Additionally, the framework incorporates advanced cybersecurity measures such as encryption, authentication, and intrusion detection to mitigate vulnerabilities and safeguard critical AV systems. The fusion of AI and cybersecurity not only enhances AV security posture but also enables intelligent cyber threat monitoring and response capabilities. Extensive simulations and experimental evaluations demonstrate the efficacy of the AVSF in real-time scenarios, contributing to the development of robust security solutions for autonomous vehicle deployment and advancing safer transportation systems in the era of AI-driven mobility. 2024 IEEE.