Browse Items (11855 total)
Sort by:
-
Visual Symphony for Swift and Accurate Object Detection in Choreographed Deck of Cards
The Convolutional Neural Network model used for playing card recognition and categorization, offering trustworthy data regarding the suits of playing cards hearts, diamonds, clubs and spades as well as the corresponding numerical or alphabetical values. The model is built on a sophisticated dataset that guarantees high levels of precision for nearly all sorts of graphical representations and playing card scenarios. A wide range of entertainment andgames bands canuse the CNN idea. As aresult, the CNN-trained model is an excellent alternative for many different kinds of applications, including virtual reality games and card game automation, due to its capacity to extract and retain complex features from card pictures for accurate object identification. As a result, this research has shown how crucial deep learning models like CNNs are for enhancing computervision systems' suitability for real-world scenarios requiring precise and quick identification of objects. As a result, the suggested CNN-based approach offers a great chance to enhance cardidentification system performance and promoteadvancements in memory and gaming technology. 2024 IEEE. -
Analyzing Market Factors for Stock Price Prediction using Deep Learning Techniques
This paper presents a comprehensive study on stock price predictions by integrating market factors and sentiment analysis of news headlines. The research is divided into two modules, each employing distinct methodologies to enhance the accuracy of stock price forecasts. In the first module, market factors are investigated using three advanced algorithms: Long Short-Term Memory (LSTM), Gradient Boosting Decision Trees (GBDT), and Facebook Prophet (FBPROPHET). These algorithms are evaluated based on metric scores such as Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). The analysis focuses on predicting high and low values of market prices for the period from January to June 2021. The comparative assessment of these algorithms provides insights into their effectiveness in capturing market trends and making precise predictions. In the second module, the paper explores the impact of news headlines on stock prices by extracting sentiment using three distinct algorithms: lexical-based analysis, Naive Bayes, and FinBERT. The sentiment analysis aims to gauge the market sentiment reflected in news articles and assess its influence on stock price movements. Prediction accuracy is calculated for each algorithm, highlighting their strengths in capturing sentiment patterns. 2024 IEEE. -
Advancements in Medical Imaging: Detecting Kidney Stones in CT Scans using a ELM-I AdaBoost-RT Model
Kidney stones have been more common in recent years, leading many to believe that the condition is common. The condition's strong relationship with other terrible diseases makes it a major threat to public health. The development of instruments and procedures that facilitate the diagnosis and treatment of this ailment has the potential to enhance the effectiveness and efficiency of health care. Preprocessing, feature extraction, level set segmentation, and model training are the four steps that make up this approach. Part of the preprocessing includes eliminating the skeletal skeleton and soft-organs. Level set segmentation is commonly used for object tracking, motion segmentation, and image segmentation. An extremely effective feature extraction method called Gray level co-occurrence matrix (GLCM) is suggested for extracting the necessary characteristics from the segmented image. That ELM-I-AdaBoost-RT was used all during training. This cutting-edge technique achieves an average accuracy of 95.83%, surpassing both ELM and AdaBoost. 2024 IEEE. -
Impact of Risk Perception on Use and Satisfaction with Online Pharmacies and Proposed Use of IoT to Minimize Risks
This study investigates consumer risk perceptions regarding online pharmacies and their impact on usage frequency and satisfaction. The growing popularity of online pharmacies offers benefits such as accessibility, cost savings, and privacy. However, significant risks, including the potential for counterfeit drugs and insufficient medical oversight, raise concerns. This study has measured consumer perceptions of risk, satisfaction, and usage frequency through a survey conducted in Northeast India, excluding Sikkim (online) and Sikkim (offline). The findings reveal that the fear of receiving counterfeit medications is a significant risk factor, negatively influencing both the frequency of use and consumer satisfaction. Despite this, the impact is relatively weak, suggesting that while risk perception is a concern, it does not significantly deter online pharmacy usage. The study suggests that integrating advanced technologies such as IoT, RFID, and blockchain can mitigate these risks by ensuring the authenticity of medications in the supply chain. 2024 IEEE. -
Enhancing Movie Genre Classification through Emotional Intensity Detection: An Improvised Machine Learning Approach
Movie Genre Classification through Emotion Intensity is a computer vision technique used to identify facial emotion through a sequential neural network model and to get the genre of the movie with it. This paper delves into latest advancements in Emotion Detection, particularly emphasizing neural network models and leveraging face image analysis algorithms for emotion recognition. Grenze Scientific Society, 2024. -
The Effect of Sustainable Development Goals (SDG's) on the Financial Performance of Listed Companies
The corporate sector is emerging as a significant stakeholder in this transformative journey asnations throughout the world work to align their policies and practices with the SDGs. Theincorporation of SDGs into financial planning has made tremendous headway in India, acountry with a rapidly expanding economy and a diverse corporate landscape. The 50companies that made up the Nifty 50 at the end of 2023 are examined in this study. Twosources provided the financial data on these companies: the Bloomberg platform andSecurities and Exchange Commission (SEC) reports. Only thirty of the NIFTY 50 companieswere putting the SDGs into practise on the previously indicated date. There are fourconfigurations in the successful FP model that describe how the SDGs and FP relate to oneanother. The lack of SDGs, when combined with other variables, explains a high ROE in twoof these four configurations. The examination of the data concludes that businesses who havetraditionally attained higher FP (i.e., higher ROE) have not included SDGs into their strategy.Furthermore, the inclusion of SDGs in strategies results in a lower return on equity (ROE).The paper however takes into consideration only size and risk as the main variables tocalculate the ROE. We recommend the future researchers to consider the other financialvariables while doing the analysis to get a more insightful analysis on the effect of SDGs. Grenze Scientific Society, 2024. -
Auto-encoder Convolut?onal Neural Network (AECNN) for Apple Fruit Flower Detection
The yield estimation task altogether relies upon the way toward identifying and checking the quantity of fruits on trees. In production of fruit, basic yield the board choices are guided through the bloom frequency, i.e., the quantity of the flowers that are present in a plantation. The intensity of bloom technique is still commonly assessed by methods for human visual investigation. Mechanized PC vision frameworks for flower recognizable proof depend closely on designed procedures which function just under explicit conditions and with restricted execution. This work comprises four significant advances, (I) system preparing for Fully Convolutional Network (FCN), (ii) preprocessing, (iii) component extraction, (iv) division. Initially, a strategy for assessing high-resolution pictures with deep FCN on Graphics Processing Unit (GPU). Then, non-linear and linear algorithms are presented for lessening the image noise, so the exact flower identification can be ensured. The next phase of the work handles the highlight extraction for diminishing the quality of the prime assets which are needed for handling without compromising on data applicable. By applying Local Binary Pattern (LBP), surface example likelihood can be summed up into a histogram. At last, isolate an image with high resolution into sub patches, assess all patches with the help of AECNN, at that point apply the refinement calculation on acquired score maps to figure out the final version of the mask segmentation. Trial results are led utilizing two datasets on flower pictures of AppleA and AppleB. Results are estimated regarding the measurements like Precision (P) and Recall (R). The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Real-Time State of Charge Prediction Model for Electric Two-Wheeler
To maximise the efficiency and performance of electric vehicles, traction battery State of Charge (SoC) must be accurately predicted. In this work, a prediction model for traction battery State of Charge estimation is developed in real time. The traction battery powers an electric two-wheeler through a predetermined drive cycle. To produce accurate state-of-charge forecasts, the predictive model considers several input characteristics, such as temperature, voltage, and current. This research is crucial for fostering effective energy management and improving the safety and dependability of electric two-wheelers. Open-circuit voltage (OCV) and coulomb counting are two commonly utilised techniques used to evaluate the state of charge prediction model. These techniques act as standards for assessing the developed Neural Network model prediction, the model's dependability and accuracy. The model's usefulness and its potential to outperform the current State of Charge estimating techniques are demonstrated by comparing the state-of-charge predictions from the model with these standard methods. 2024 IEEE. -
Deep Learning-Based Prediction of Physical Activity Intensity for Athletes
Maximizing training plans for athletes and lowering the risk of injury depends on a precise assessment of the degree of physical activity. Existing system in-use systems often employ simplistic models, which leads to inaccurate projections. The paper presents a deep learning-based system that uses convolutional neural networks (CNNs) to create real-time predictions using wearable sensor data. Because it automatically extracts relevant features from raw sensor data, the technique does not need human feature engineering. Utilizing thorough model training and evaluation, it exceeded the most recent methods in terms of accuracy (0.92), precision (0.90), recall (0.92), F1-score (0.91), and ROC AUC (0.94). Results of cross-validation over many data subsets confirm the resilience of the method. Comparisons of confusion matrices also demonstrate how effectively the algorithm forecasts various activity intensities. Overall, the proposed system represents a breakthrough in accurately estimating how much physical activity athletes do, enhancing the efficacy of their training, and reducing the possibility of damage in sporting settings. 2024 IEEE. -
The Effect of Prediction on Employee Engagement Organizational Commitment and Employee Performance Using Denoised Auto Encoder and SVM Based Model
The purpose of human resources is to ensure that the appropriate people are hired for open positions at appropriate times, that the system receive the necessary training, and that their performance is monitored and their perspective skills are secure through the use of evaluation methods. Despite the importance of this data to decision-makers, it can be difficult to glean useful insights from large datasets. Data mining has made it possible for human resources experts to automate the hitherto tedious task of manually processing enormous data sets. Finding almost perfect outcomes is the main goal of data mining, which is to discover hidden knowledge in data patterns and trends. The proposed method goes as follows: preprocessing is done by data cleaning and data normalization, feature selection using correlation and information theoretic ranking criteria. The last step in training and evaluating the model is using AE-SVM, which stands for Auto Encoder Support Vector Machine. The suggested model is more effective and performs better than two existing models: Support Vector Machine and AE-CNN. The suggested approach attains an accuracy rate of 94%. 2024 IEEE. -
Approach Towards Web for Exploring the Suitable Job for Individuals
In light of future work challenges, true human resource management (HRM) must be rebuilt. This involves over time human resource development; it must also contain the concept of sustainability to move from consuming to generating human resources. The labor market is constantly changing, with nontraditional jobs becoming increasingly important, especially in light of the current COVID-19 legislation. A useful teaching strategy in a variety of academic fields, including career development, is experiential learning. Important elements for establishing experiential learning programs at the institutional level are also covered by researchers. Our framework may assist businesses in identifying the type of experiential learning that best fits their objectives and setting for professional training. It can also help ensure that the training is successfully designed and delivered. 2024 IEEE. -
Comparative Analysis and Development of Recommendations for the Use of Machine Learning Methods to Identify Network Traffic Anomalies in the Development of a Subsystem for User Behavioral Analysis
This article discusses various machine learning methods in order to conduct a more effective analysis of user network traffic using a subsystem for analyzing user behavior and detecting network anomalies, since there is a need to evaluate big data. The methods and techniques used to detect network anomalies are analyzed. In analyzing the methods and technologies used to detect network anomalies, a classification of anomaly detection methods is proposed. To solve these problems, different algorithms can be used, differing in specificity and, as a result, efficiency. The classification of machine learning methods for detecting network anomalies is considered separately, since machine learning algorithms will be the most effective for the task. Various criteria for evaluating the effectiveness of machine learning models in solving the problem of network traffic profiling are considered. In accordance with the specifics of the tasks of user recognition and network anomaly detection, the most appropriate criteria for evaluating the effectiveness of machine learning models have been selected: AUC ROC the area under the error curve. Four stages of the subsystem for analyzing user behavior and detecting network anomalies are highlighted. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Cryptographic Protocols for Securing Internet of Things (IoT)
Cryptographic protocols are used to relax the ever-developing quantity of linked gadgets that make up the net of things (IoT). Those cryptographic protocols have been designed to make certain that IoT tool traffic stays cozy and personal, even while nevertheless allowing tool-to-device and cloud-to-tool communications. Examples of these protocols consist of TLS/SSL, PGP/GPG, IPsec, SSL VPN, and AES encryption. Every one of these protocols enables authentication, message integrity, and confidentiality via encryption and key trade. Moreover, a lot of these protocols are carried out in the form of diverse hardware and software answers, such as smart playing cards and gateways, to make certain that IoT traffic is secured. With the appropriate implementation of those cryptographic protocols, establishments can ensure that their IoT facts are blanketed and securely transmitted. 2024 IEEE. -
Empowering E-commerce: Leveraging Open AI and Sentiment Analysis for Smarter Recommendations
Online product reviews are pivotal in shaping consumer purchasing decisions in today's digital era. Leveraging the wealth of sentiment-rich data available through these reviews, this research proposes an approach to enhance product recommendation systems. This study integrates sentiment analysis techniques into the recommendation process to provide users with more personalized and insightful product recommendations. By analyzing the sentiment expressed in user-generated content, such as reviews and ratings, this system aims to capture not only the explicit preferences but also the underlying sentiments and emotions of users towards products. Furthermore, this system utilizes OpenAI and the power of Langchain to develop a chatbot interface, enabling users to interact naturally and receive personalized product recommendations based on their preferences and sentiment analysis. Through experimentation on real-world datasets, this paper evaluates the effectiveness and performance of the sentiment-enhanced recommendation system compared to traditional recommendation methods. The results demonstrate the potential of sentiment analysis in improving the relevance, accuracy, and user satisfaction of product recommendations. 2024 IEEE. -
FDI in Developing Nations: Unveiling Trends, Determinants and Best Practices for India
In the recent UNCTAD World Investment Report 2023, China has the highest FDI inflows among the developing countries, following Brazil, India, Mexico, and Indonesia. These five developing countries attracted more FDI inflows in the year 2022. However, among these five countries, China and the other four countries have a lot of differences in FDI inflows. So, this study investigates the factors helping China get more FDI inflows by analyzing the trends and determinants of FDI inflows. The study also compares all the selected countries to suggest the best practices India can adopt to enhance its FDI attractiveness. So, the study considered economic indicators like GDP, infrastructure, trade openness, and natural resources. Further, panel data analysis was used to investigate the determinants influencing FDI inflows, utilizing the Panel Autoregressive Distributed Lag (P-ARDL) model for the data from 1990 to 2022. The findings showed that trade openness, market size, and quality of infrastructure explain the attraction of FDI inflows in selected countries in the long run. Thus, it is important to implement policies that encourage international collaboration by raising trade, lowering corporate expenses, and making infrastructural investments. India's availability of a large consumer market, developed infrastructure, and government initiatives like 'Make in India,' and "Skill India"have pulled major FDI inflows. India should prioritize manufacturing, IT, and healthcare while improving infrastructure and streamlining regulations. 2024 IEEE. -
Rating-Based Cyberbullying Detection with Text, Emojis on Social Media
In the dynamic landscape of online interactions, cyberbullying has become pervasive, profoundly impacting user's digital well-being. Public figures, especially celebrities and influencers, face heightened vulnerability to online harassment, exacerbated by the post-pandemic surge in social media usage. To address this challenge, our research adopts a holistic approach to detect cyberbullying in text, considering both textual content and the nuanced expressions conveyed through emojis on social media platforms. We employed a diverse set of machine learning and deep learning models, including Support Vector Classifier, Logistic Regression, Random Forest, XGBoost, LSTM, Bi-LSTM, GRU, and Bi-GRU, to accurately classify non cyberbullying or cyberbullying text. Beyond classification, our study introduces an offensive rating system, assigning severity ratings on a 1-5 scale to identify cyberbullying instances. A critical aspect is the establishment of a threshold value which depends on user security and safety ethics of different social media platforms; texts surpassing this trigger an automatic recommendation to block the user, ensuring a proactive response to minimize harm. This recent contribution not only comprehensively addresses cyberbullying but also empowers society. 2024 IEEE. -
Congestion Avoidance in Vehicular Ad Hoc Network MAC Layer Using Harmony SearchModified Laying Chicken Algorithm (HS-MLCA)
To address congestion in the MAC layer and enhance overall performance, the HS-MLCA is proposed. This algorithm incorporates the principles of both Harmony Search and Laying Chicken Algorithm to optimize resource allocation and congestion control. At the MAC layer, HS-MLCA offers several advantages over traditional congestion control schemes. Firstly, it leverages the Harmony Search algorithm, which is known for its ability to exploit the best outcomes in search processes. By exploring the solution space and exploiting promising regions, HS-MLCA optimizes resource allocation in the MAC layer. The integration of the Laying Chicken Algorithm (LCA) further enhances performance by improving convergence speed and solution accuracy. This hybrid approach leverages the strengths of both Harmony Search (HS) and LCA, resulting in more efficient and effective resource management. The Laying Chicken Algorithm simulates the behavior of laying hens in terms of resource allocation and competition. This approach contributes to provide the solution in quality and convergence speed, as the algorithm adapts to the dynamic nature of the MAC layer and the varying traffic conditions in VANETs. By combining the strengths of Harmony Search and Laying Chicken Algorithm, HS-MLCA offers improved performance in terms of congestion control in the MAC layer. It optimizes resource allocation, minimizes collisions and packet loss, reduces delay, and enhances overall network efficiency. These improvements ultimately lead to better quality of service, increased network capacity, and enhanced user experience in VANETs. It is worth noting that the specific performance improvements and benefits of HS-MLCA may vary depending on the implementation details, network conditions, and the specific VANET scenario. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Investigating Key Contributors to Hospital Appointment No-Shows Using Explainable AI
The healthcare sector has suffered from wastage of resources and poor service delivery due to the significant impact of appointment no-shows. To address this issue, this paper uses explainable artificial intelligence (XAI) to identify major predictors of no-show behaviours among patients. Six machine learning models were developed and evaluated on this task using Area Under the Precision-Recall Curve (AUC-PR) and F1-score as metrics. Our experiment demonstrates that Support Vector Classifier and Multilayer Perceptron perform the best, with both scoring the same AUC-PR of 0.56, but different F1-scores of 0.91 and 0.92, respectively. We analysed the interpretability of the models using Local Interpretable Model-agnostic Explanation (LIME) and SHapley Additive exPlanations (SHAP). The outcome of the analyses demonstrates that predictors such as the patients' history of missed appointments, the waiting time from scheduling time to the appointments, patients' age, and existing medical conditions such as diabetes and hypertension are essential flags for no-show behaviours. Following the insights gained from the analyses, this paper recommends interventions for addressing the issue of medical appointment no-shows. 2024 IEEE. -
Enhancing Stroke Prediction: Leveraging Ensemble Learning for Improved Healthcare
Stroke, a potentially deadly medical disorder, requires excellent prediction and prevention measures to minimize its impact on individuals and healthcare systems. In this study, ensemble learning techniques are employed to enhance the accuracy of stroke prediction. The method combines four different machine learning algorithms, Adaboost, CatBoost, XGBoost, and LightGBM, to produce a strong predictive model. The data was composed of a rich set of demographic, medical, and lifestyle information. The data was preprocessed and features were engineered to maximize predictive performance. Results showed that the stacked ensemble model, which is composed of Adaboost, CatBoost, XGB, LightGBM, and Logistic Regression, meta-model, outperformed other models. The model has the potential to be used as a decision support tool in an early stroke risk assessment system, enhancing clinician decision-making and improving healthcare outcomes. 2024 IEEE. -
Smart Vehicle Recognition System on Indian Roads Under Rainy Conditions
Recognition of vehicles under the different weather condition is very challenging. This work aims to recognize vehicles on Indian road in accordance with their visibility. It is important to recognize the surround roadside objects, particularly front and rare vehicles to avoid the accidents. Especially in raining conditions vehicle recognition is rate traffic surveillance cameras get decreases due to water droplets. Hence, we proposed a method for recognition of vehicles on road in rainy condition using image processing in computer vision techniques to improve the recognition rate. In the proposed method, an instance segmentation technique is used to segment the vehicles in Indian road scene and the visual noise and texture features are analysed and computed in the segmented images to recognize the vehicles more accurately in rainy conditions. By integrating the visual noise features with the texture feature and instance segmentation, the accuracy of vehicle recognition is improved. The experimental findings demonstrated that the suggested approach could more accurately predict the visibility of vehicles in rainy weather conditions. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.