Browse Items (2150 total)
Sort by:
-
Brain Tumor Detection and Classification Using a Hyperparameter Tuned Convolutional Neural Network
Brain tumor detection using MRI scans when integrated with a deep learning approach can be immensely applied in identifying the tumor at early stages, with minimum medical professional aid. This research paper aims to develop an advanced predictive model that accurately classify brain tumors as benign or malignant using MRI scans. Here, a novel convolutional neural network (CNN) model is proposed to automate tumor detection and improve diagnosis accuracy. The model used a dataset of around 7000 brain cancer data classified into 4 labels which include glioma, meningioma, pituitary, and no tumor. Data wrangling and pre-processing are then applied to unify the images into a single format and remove any inconsistencies. Further the records are segregated into train and test samples with a 70-30 split. The proposed model recorded an optimum accuracy of 94.82%, precision of 94.2%, recall value of 93.7% and f-score metric of 93.9% respectively. In conclusion, the paper concluded that the proposed model can be applied to enhance the precision of both brain tumor diagnosis and prognosis. 2023 IEEE. -
Study of the Balmer Decrements for Galactic Classical Be Stars Using the Himalayan Chandra Telescope of India
In a recent study, Banerjee et al. (2021) produced an atlas of all major emission lines found in a large sample of 115 Galactic field Be stars using the 2-m Himalayan Chandra Telescope (HCT) facility located at Ladakh, India. This paper presents our further exploration of these stars to estimate the electron density in their discs. Our study using Balmer decrement values indicate that their discs are generally optically thick in nature with electron density (ne) in their circumstellar envelopes (CEs) being in excess of 1013 cm-3 for around 65% of the stars. For another 19% stars, the average ne in their discs probably range between 1012 cm-3 and 1013 cm-3. We noticed that the nature of the H? and H? line profiles might not influence the observed Balmer decrement values (i.e. D34 and D54) of the sample of stars. Interestingly, we also found that around 50% of the Be stars displaying D34 greater than 2.7 are of earlier spectral types, i.e. within B0B3. 2024 Societe Royale des Sciences de Liege. All rights reserved. -
Fine-tuning Language Models for Predicting the Impact of Events Associated to Financial News Articles
Investors and other stakeholders like consumers and employees, increasingly consider ESG factors when making decisions about investments or engaging with companies. Taking into account the importance of ESG today, FinNLP-KDF introduced the ML-ESG-3 shared task, which seeks to determine the duration of the impact of financial news articles in four languages - English, French, Korean, and Japanese. This paper describes our team, LIPIs approach towards solving the above-mentioned task. Our final systems consist of translation, paraphrasing and fine-tuning language models like BERT, Fin-BERT and RoBERTa for classification. We ranked first in the impact duration prediction subtask for French language. 2024 ELRA Language Resource Association. -
Computationally Efficient Machine Learning Methodology for Indian Nobel Laureate Classification
A computationally efficient methodology for Indian Nobel Laureate classification is proposed in this study, emphasizing the optimization of image categorization through supervised learning techniques. Leveraging advancements in Convolutional Neural Networks (CNNs), the research aims to enhance the efficiency and precision of image classification tasks. The study utilizes Logistic Regression for dataset analysis, initially employing browser extensions for mass downloading categorized image data. Haar cascade classifiers are then used for data wrangling, focusing on facial, nose, and mouth recognition. Following this, feature engineering through wavelet transformation reduces image dimensionality, preparing the dataset for the chosen ML model, Logistic Regression. The primary focus is to simplify technology for improved image categorization. Support Vector Machines (SVM), Random Forest, and Logistic Regression are examined, with Logistic Regression emerging as the most effective model, achieving an accuracy rate of 87.5%. A thorough evaluation using Confusion Matrices reveals Logistic Regression's superior performance in classifying images of Indian Nobel laureates. A strategic up-sampling approach is implemented to address dataset inconsistencies, ensuring balanced representation across classes. The Haar wavelet transform is then applied for feature extraction, optimizing the dataset for ML models. The dataset is split into training and testing sets (80-20), and the three models are trained and evaluated for accuracy. Logistic Regression proves to be the best performer, offering insights into prominent leaders' identification. The research offers a detailed pipeline for data preprocessing, feature engineering, and model assessment, culminating in a robust image categorization system. Logistic Regression emerges as a reliable method for biographical picture identification, demonstrating superior accuracy over SVM and Random Forest. This research underscores the importance of efficient and accurate image classification methodologies for practical applications in real-world scenarios, particularly in recognizing influential leaders. 2024 IEEE. -
Rice Yield Forecasting in West Bengal Using Hybrid Model
Agriculture in India is the primary source of revenue, yet farmers still face challenges. The primary goal of agricultural development is to produce a high crop yield. The Datasets collected for the study of real-world time series include a blend of linear and nonlinear patterns. A mixture of linear and non - linear models, rather than a single linear or non - linear model, gives a more precise forecasting models for time series data. The ARIMA and ANN prediction models are combined in this paper to create a Hybrid model. This model is used to predict rice yield for all 18 West Bengal districts during the Kharif season, based on 20years of information(20002019) collected from various sources such as India Meteorological Department, Area, and production Statistics, DAV from NASA, etc. The hybrid model aims to enhance efficiency indicators such as MSE, MAE, and MAPE, demonstrating excellent performance for rice yield prediction in all the districts of West Bengal. In the future, it can be applied to other crops that can support farmers in their farming. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Multiple Approaches in Retail Analytics to Augment Revenues
Knowledge is power. The retail sector has been revolutionized around the clock by the plentiful product knowledge available to customers. Today, customers can use the knowledge available online at any time to study, compare and purchase products from anywhere. Retail companies can stay ahead of shopper trends by using retail information analytics to discover and analyze online and in-store shopper patterns. A product recommender will suggest products from a wide selection that would otherwise be very difficult to locate for the customer. The algorithm would recommend various products, increase the sales of items that would otherwise be difficult to sell. Market basket analysis is a common use scenario for the search for frequent patterns, which involves analyzing the transactional data of a retail store to decide which items are bought together. To do so data from online resource has been taken, which is analyzed and several conclusions were made. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
An Innovative Method for Fuel Consumption and Maintenance Cost of Heavy-Duty Vehicles based on SR-GRU-CNN Algorithm
A heavy-duty vehicle's fuel usage, and thus its carbon dioxide emissions, are significantly impacted by the driver's behavior. The average fuel economy of a car varies by about 28% between drivers. Fuel efficiency can be improved by driver education, monitoring, and feedback. Fuel efficiency-based incentives are one form of feedback that can be provided. The largest challenge for transportation companies implementing such incentive programs is how to accurately evaluate drivers' fuel consumption. The processes of preprocessing, feature extraction, and model training are all utilized in the suggested method. Principal component analysis (PCA) is widely utilized in data science's preprocessing stage. GMM is used for feature extraction. Afterwards, SR-GRU-CNN is used to train the models based on the selected features. When compared to the two most popular alternatives, CNN and SR-GRU, the proposed methodexcels. 2023 IEEE. -
Cluster analysis for european neonatal jaundice
The objective of this paper is to propose and analyze clustering techniques for neonatal jaundice which will help in grouping the babies of similar symptoms. A variety of methods have been introduced in the literature for neonatal jaundice classification and feature selection. As far as we know, clustering techniques are not used for neonatal jaundice data set. This paper studies and proposes clustering techniques such as K-Means, Genetic K-Means and Bat K-Means for jaundice disease. To find the number of clusters elbow method is used. The clusters are validated using RMSE, SI and HI. The experimental results carried out in this paper shows bat k-means clustering performs better than K-means and genetic K-means. 2018, Springer International Publishing AG. -
Detecting Infectious Disease Based on Social Media Data Using BERT Model
Seasonal diseases are those diseases that are widespread during a particular time of the year including monsoons, winter etc. In the absence of preventative measures, the human race remains vulnerable to the hazardous effects of seasonal diseases following regular patterns of increased inci- dence and transmission which remains a global concern. Dengue, Influenza, etc. are such types of diseases where every year many people get affected globally. The primary focus of this research paper is to understand the opinion of people regarding the seasonal diseases. The research paper covers sentiment analysis on textual data from social media where people have vocalized their sentiments or thinking regarding seasonal diseases and seasonal infectious diseases. Influenza, Dengue, Malaria, Japanese Encephalitis, and Chikungunya are the seasonal diseases that have been covered in this research paper. To achieve this, the language model Bidirectional Encoder Representations from Transformers (BERT) was used to verify the sentiments about the seasonal diseases. The result of the investigation hold the potential to significantly enhance our comprehension of societal sentiments, discerning between states of tranquility and concern among individuals. The outcome of the study will help healthcare department to plan the necessary actions. 2024 IEEE. -
A critical review of determinants of financial innovation in global perspective
Financial innovation is the widely accepted process across the globe. 'What forces drive the financial innovation?' is the research question since long. Many studies were conducted in the past to answer and each study identified some or other factors that prominently driving financial innovation landscape in their respective economy. The present study critically review existing Literatures to suggest a comprehensive list of determinants. The study uses descriptive research design. A sample of 54 literatures focusing on financial innovation and it's determinants during the time period 1983 to 2018 is included in the study. Further, content analysis and descriptive statistics are used to explore the determinants. The study identified 23 different determinants of financial innovation and classify those under two bases. First, on the basis of influencing power and second on the basis of nature of the determinant. The study found that technological development, competition, firm size and regulations are the major sources of financial innovation from different categories. The study also raised the research agenda to study determinants of financial innovation in Asian context, as there are scanty literature covering Asian economies. 2021 Elsevier Ltd. All rights reserved. -
Deep Learning Enabled Parent Involvement and Its Influence on Student Academic Achievement Analysis
Studying the substantial effect that Deep Learning Enabled Parent Involvement (DLEPI) has on kid academic success. Using a made-up data set and a neural network model, we find that parents' level of involvement, as measured by the Parental Involvement Score (PIS), is positively correlated with their children's academic performance. DLEPI, driven by cutting-edge deep learning algorithms, equips parents with unique insights and suggestions regardless of where they live, therefore promoting educational equality and diversity. This study underlines the potential of technology to reduce performance inequalities and highlights its central role in increasing parental participation. Critical elements for future study include ethical issues, real-world validation, effect evaluations over time, and chances for personalization. This research lays the groundwork for reinventing education in a future where DLEPI improves student outcomes and offers a more inclusive and personalized educational environment. 2024 IEEE. -
Artificial Intelligence Influence on Leadership Styles in Human Resource Management for Employee Engagement
In this work, we investigate how the revolutionary effects of AI on leadership styles in the field of human resource management (HRM) have impacted employee motivation. To investigate the intricate relationship between AI adoption, HR management, and employee morale, we use a mixed-method approach, combining quantitative survey data with qualitative interview results. Both Leadership Style Change (LS-Change) and Employee Engagement (EE) show a statistically significant positive correlation with AI adoption. In the new AI-enabled HRM environment, HR executives are shifting their methods of leadership, adopting more flexible styles, giving workers more autonomy, and improving lines of communication. This research links theory and practice by providing actionable advice to HR managers and business owners. In order to further develop the topic of AI-enhanced HRM, future studies should investigate longitudinal dynamics, cross-industry variances, cultural and ethical issues, cutting-edge AI applications, and employee perspectives. 2024 IEEE. -
UAV Security Analysis Framework
This study presents a framework that allows for various types of checks to detect weaknesses in UAV subsystems. The UAV testing process is automated and allows the operator only to select the types of checks or types of structural and functional characteristics that the operator wants to test. To ensure the possibility of automated verification, implemented databases are used, which include a catalog of structural characteristics, threats, vulnerabilities, and attacks. These catalogs are many-to-many related, and thanks to these links, it is possible to identify threats or vulnerabilities specific to a particular structural characteristic. In essence, such an architecture is a knowledge base based on an ontological model. Thanks to this architecture of the system, it is enough for the operator to determine what types of structural characteristics need to be checked and the system will give him information about the vulnerabilities of the UAV. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Analysis of the UAV Flight Logs in Order to Identify Information Security Incidents
The article discusses issues related to the analysis of the UAV flight logs to identify information security incidents that occurred during flights. Existing methods and tools for analyzing logs are described, and sources for obtaining logs are presented. In the main part of the article, first, the parameters important for the analysis are highlighted. The features of analyzing the values in the flight logs for the detection of two types of attacksGPS Spoofing and GPS Jamming are also given. For this purpose, the parameters that are most important for the detection of each of these attacks have been identified, systems of equations have been compiled to analyze these parameters, the calculations of which make it possible to detect the fact of attacks with high efficiency. The paper also presents the developed software that implements a number of functions that allow automating the analysis of flight logs, as well as determining the presence of information security incidents that occurred during the flight. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Leveraging and Deployment of AI / ML to Simplify Business Operations among Diverse Sectors during Covid-19 Battle
During the evolution of the COVID-19 outbreak, the necessity for companies to re-evaluate and restructure themselves is still not greater. It will make sense for things to change in the business operations. Most companies redesigned current existing ways of running business operations and capacity to make choices to benefit. The present condition sees Artificial Intelligence as a significant facilitator for companies to make their existing situation better (recover from their economic crisis), reconsider (prepare for a long-term change) and reinvent (completely re-engineer) their business model for long-term gain. Automated bots that could identify items and carry out duties that were previously reserved for people would make companies and other infrastructures operational around the clock, through more significant numbers, and at a lower cost. Simulated actual working conditions, including labour forces, would be created by using Artificial intelligence platforms. Businesses would use machine learning and sophisticated business intelligence to use artificial intelligence to explore better market dynamics and provide consumers with "hyper-personalized" goods. Some of the most compelling case studies can have human intelligence and expertise mixed with AI. Many firms should revamp current business processes and capacity to benefit the company in the near future. In this research paper, we have showcased how artificial intelligence would benefit businesses as they adopt with these current developments and during a condition of pandemic without inhibiting their activities. The research is carried in a descriptive way, choosing the diverse sectors in the economy like Banking & Finance, Manufacturing, Education, Retail, Telecommunications, Entertainment and media to make the research more robust and reliable. 2022 American Institute of Physics Inc.. All rights reserved. -
Talent retention, job involvement satisfaction, and commitment towards the organization in the IT sector
Even if there is presently much need for improvement, the information technology (IT) sector plays a key role in the nation's financial development. With enormous growth potential, India's IT sector is up against fierce competition. Numerous participants are competing with one another for resources and jobs inside the company. The direction of events and the manageability of the IT industry depend on capable employees and their responsibilities and participation. Additionally, there is a grouping of the representatives who possess the capacity. Between duty and association and ability maintenance, work fulfilment plays a crucial guiding role. The goal of the current study is to comprehend the effects of talent retention, job satisfaction, and organizational commitment in the IT industry. In this research, we looked at the variables factor analysis. In Bangalore, we chose to survey workers in the IT industry. To understand the results of Talent Retention, Job Involvement, and Commitment for IT Sector Employees, we collected the data using a questionnaire (Likert-scale), which we then analyzed using spss26. 2023 Author(s). -
Forecasting the Academic Horizon: Machine Learning Models Unraveling the Complex Web of Student Well-being Determinants
In the contemporary academic landscape, the well-being of students is pivotal not only for their individual success but also for the broader educational ecosystem. This study meticulously delves into a rich dataset encompassing diverse student attributes, academic performance metrics, and economic indicators to discern patterns and predictors affecting student well-being. Leveraging a multi-faceted research methodology, we employed various machine learning models, ranging from logistic regression to advanced ensemble methods, aiming to forecast and comprehend the intricate determinants of student outcomes. The research design, underpinned by rigorous exploratory data analysis, revealed intriguing correlations between economic conditions, academic achievements, and students' well-being. The Gradient Boosting model, in particular, showed a significant improvement post hyperparameter tuning, with an accuracy reaching up to 77.63%. On the other hand, models like the Random Forest achieved a base accuracy of 77.29%. These insights highlight the potential of data-driven methodologies in understanding and predicting student well-being. As we stride into an era where data-driven decisions in education are paramount, our findings offer a robust foundation for future endeavors in this realm. Future directions of this study encompass refining prediction models with more granular data, exploring the psychological facets of student well-being, and devising actionable interventions based on the identified predictors. 2023 IEEE. -
A Study on Student Cyber Safety Consciousness in the Light of Online Learning
Our world online and networked is immersed under a wave of populism; populism spreads on the wings of internet. The recent technological advancements like the use of social media platforms and different applications made the information exchange faster and more efficient making the information access easier. To keep our information, gadgets such as cell phones, laptops, desktops, and tablets and also the internet safe, knowledge of cybersecurity is vital everywhere. In many colleges and Universities who are in to interconnected complex systems, data privacy is a huge challenge among their users. In most of the situations, due to lack of knowledge and awareness, users may engage in data breaches knowingly or unknowingly and the complete interconnected systems among the users may have a consequence of a cybercrime. This article seeks to unpack the rise of cyber-crimes and its relationship to cyber security among student groups during the pandemic where much of their interaction is online. The research aims to inquire in to the level of knowledge and awareness on cybersecurity among students during their online learning interaction using a well-structured questionnaire. The questionnaire will be focused on five parts: Awareness and Knowledge, Monitoring and Privilege, Security and Prevention, Protection from malware s and usage of removable Devices. The study is conducted using quantitative research methodology to quantitatively evaluate the knowledge of cybersecurity and inculcate an awareness against Cybercrime protection among the students. Finally, based on the analysis of collected data we present recommendations which will not forego the safety concerns for e mails, viruses, phishing, pop-up windows and forged ads which is a common problem. Some technological solutions and paths for the regulation of the cybercrimes are suggested to the respondents at the end. 2022 IEEE. -
An Efficient Machine Learning Approach: Analysis of Supervised Machine Learning Methods to Forecast the Diamond Price
Diamond, a found natural process compound of carbon, is one of the hardest and most immensely expensive material known to men, especially more to women. Investments in expensive gems like diamonds are in significant demand. The rate of a diamond, nevertheless, is not as easily calculated as the value of either gold or platinum since so many factors must be taken into account. Because there is such a broad range of diamond dimensions and qualities; as a result, being able to make reliable price predictions is crucial for the diamond industry. Although, making accurate predictions is challenging. In this study, we implemented multiple machine learning techniques employed to the challenge of diamond price forecasting's such as Linear Regression, Random Forest, Decision Tree Random Forest, Cat-Boost Regressor and XGB Regressor. This article's goal is to develop an accurate model for estimating diamond prices based on its characteristics such as weighting factor, cut grade, and dimensions. We compared the sum of estimated values and test values of predicted values with overestimated, underestimated and exact estimations. We applied cross-validation to calculate how much the model deviates from the actual when faced with a difference between the training set and the test set. We predicted values side by side. We performed a comparative analysis of supervised machine learning models with other models to evaluate the model accuracy and performance metrics. The Study's experimental findings show that out of all the supervised machine learning models, Random Forest performs well with R2score and Low RMSE and MAE values and CV Score. 2023 IEEE. -
Gems of Prediction: From Clarity to Carats - Unveiling Diamond Prices with Machine Learning in Waikato Environment for Knowledge Analysis
Background: This research focuses on using Weka's toolkit to test machine learning models for predicting diamond prices. The complexity of diamond value characteristics, such as carat, cut, color, and clarity, motivates the study to find the most accurate models. The goal is to promote fairer market processes and customer education. Methods used: The research rigorously preprocesses a diamond attributes dataset using Weka for analysis. Various machine learning algorithms are examined, including simple algorithms like Decision Stump and ZeroR, sophisticated models like M5P and REP Tree, and advanced ensemble approaches like Bagging with REP Tree. Model performance is evaluated using train/test splits (80-70-60%) and cross-validation (5-fold and 10-fold) with metrics such as Correlation Coefficient, MAE, and RMSE. Results achieved: The research finds that ensemble approaches, particularly Bagging with REP Tree, outperform simple and sophisticated models in diamond price prediction. These techniques demonstrate higher accuracy and lower error rates, highlighting the need for multiple models to capture the complexity of diamond valuation. Simple models provide benchmarks and insights into dataset trends but are less precise. Concluding remarks: This study contributes to the understanding of machine learning algorithms for diamond price prediction, an important economic valuation subject. It demonstrates the effectiveness of complex data analysis methods using Weka. The research also highlights the accessibility and sophistication of machine learning at the crossroads, with Weka's cutting-edge algorithms making complicated analytical methods more accessible for practical, everyday use. This work adds to the knowledge of the dynamics of diamond prices and the role of machine learning in economic research. 2024 IEEE.