The Evolution of Cryptocurrencies: Analysis of Bitcoin, Ethereum, Bit connect and Dogecoin in Comparison

2022 IEEE 7th International conference for Convergence in Technology (I2CT), Journal Year: 2024, Volume and Issue: unknown

Published: April 5, 2024

Cryptocurrency is a novel form of digital or virtual currency that employs cryptographic techniques to guarantee secure financial transactions, control the creation new units, and verify transfer assets. signifies fundamental change in understanding transactions. The tenets decentralisation, security, limited supply seek revolutionise conventional environment, providing fresh opportunities for inclusion, transparency, innovation. Nevertheless, path cryptocurrencies being influenced by ongoing challenges, such as regulatory uncertainties market volatility, they progressively establish themselves vital component global economy. It can be deduced Dogecoin lacks ability supplant Bitcoin. Ethereum Bitcoin exhibit notably higher level security compared Bit connect. That rationale behind their withstand decline 2018 also endure current decrease price. depreciation dogecoin inevitable. valid authentic currency. Nonetheless, cultural structure ultimately undermines its own triumph.

Language: Английский

---

Evaluating the MobileNet50 CNN Model for Deep Learning-Based Maize Visualisation and Classification

Published: April 18, 2024

Plant diseases present a substantial threat to global food security, and the timely detection of such remains challenging time-consuming task. The accurate determination plant's health status identification specific infections typically require expertise professionals. advent Deep Learning has significantly transformed field computer vision, offering highly efficient techniques for image analysis categorization. This study specifically focuses on utilizing MobileNet50 Convolutional Neural Network (CNN) model visually represent categorize images maize. maize, widely cultivated crop, is intricate due its diverse array varieties growth stages. research aims leverage capabilities advanced CNN architecture enhance precision effectiveness maize classification. achieved an impressive accuracy 97%, demonstrating robust performance in distinguishing various types states plants. By employing MobileNet50, this contributes advancement vision applications agriculture, facilitating prompt diseases. utilization deep learning approach reduces dependency human expertise, making it more accessible large-scale agricultural monitoring. Ultimately, integration classification holds promise revolutionizing plant disease contributing efforts securing resources.

Language: Английский

---

Classification of Student Mental Health Analysis using Logistic Regression and other classification techniques through Machine Learning Methods

Published: March 1, 2024

The examination of student mental health is a significant area scholarly investigation that seeks to comprehend and address the psychological emotional well-being students within educational settings. process involves evaluation, anticipation, provision assistance for students' using various approaches, including as surveys, machine learning algorithms, clinical assessments. use algorithms analysis complex consequential endeavour. This may provide insight on identification who be at risk appropriate timing providing support. In this context, methods, such logistic regression other classification might potentially advantageous. research aims identify some noteworthy concerns pertaining overall students. paper explores philosophical difficulties underlying these challenges examines answers provided by modern statistics visualisation techniques. study offers variety robust models, Random Forest, Decision Tree, SVM, Logistic Regression, possess several advantages are well-suited categorical data. psycholinguistic data set conduct comprehensive comparison different statistical methodologies. Upon conducting an evaluation Linear Support Vector Machine (SVM), it was seen Regression Classification Technique exhibited highest level accuracy. Specifically, model achieved 65 percent accuracy rate across diverse optimisation parameters.

Language: Английский

---

Incorporating the CatBoost Classification Method in Machine Learning Applications for Smote Analysis and Bankruptcy Data Equalisation

Published: April 18, 2024

In the context of financial risk assessment, ability to predict bankruptcy has considerable significance in ensuring stability economic systems. One enduring challenges this specific domain is imbalanced datasets, where frequency cases reflecting much lower compared instances representing non-bankrupt scenarios. The objective research investigate use Synthetic Minority Over-sampling Technique (SMOTE) combination with CatBoost classification algorithm. focus on achieving data equalisation and enhancing prediction. algorithm efficiently leverages distinct qualities benefits provided by each methodology. a technique designed address problem class imbalance creating synthetic samples for minority class. This social strategy improves model's capacity gather acquire patterns from that not well represented. algorithm, which accesses categorical feature handling skills an efficient boosting methodology, used analyse enlarged dataset develop robust prediction model task detection. main aim study employ Catboost classifier order classify Bankruptcy precision will be achieved SMOTE Analysis, particularly issue unbalanced data. report confusion matrix as evaluation metrics assess anticipated accuracy level 97 percent. proposed would visual tools show results.

Language: Английский

---

ResNet50 Utilization for Bag Classification: A CNN Model Visualization Approach in Deep Learning

Published: June 28, 2024

Language: Английский

---

Visualisation and Classification of Coffee Leaves via the Use of a Sequential CNN Model Based on Deep Learning

Published: Feb. 21, 2024

The coffee industry plays a crucial role in global agriculture and economy. Monitoring the health classification of plants is vital for optimizing yield ensuring sustainable production. Coffee are very vulnerable to several diseases pests. long-term effects excessive pesticide usage may enhance disease resistance, severely limiting plants' ability fend off infections. goal this project create sophisticated system that employs deep learning-based Sequential Convolutional Neural Network (CNN) model visualise categorise leaves. This study provides unique method visualising categorising leaves using CNN model. plant growers be able spot infections more promptly with aforementioned approach, enhancing India's crop output. suggested proposing an accuracy 97% was created aid farmers industry. Hence, shows promising interpretability outcomes, leading growth precision business.

Language: Английский

---

Utilizing Machine Learning and employing the XGBoost Classification Technique for evaluating the likelihood of Autism Spectrum Disorder (ASD)

Published: May 24, 2024

Language: Английский

---

Classification of Tweets using a Machine Learning and Natural Language Processing Algorithm for Disaster Prediction

Published: March 1, 2024

This research investigates the use of machine learning (ML) and natural language processing (NLP) algorithms for categorization tweets to anticipate disasters. study aims extensive up-to-date social media data, namely from Twitter, construct a reliable model distinguishing that pertain disasters those do not. The technique being offered encompasses many key steps, including gathering pre-processing collected extraction relevant features, subsequent deployment several models. primary objective is develop highly effective precise system can classify in real-time, hence enhancing early warning systems catastrophe management. efficacy will be assessed using evaluation criteria such as precision, recall, accuracy. position helpful tool boosting prediction skills. this forecast if particular tweet pertains an actual or If case, make 1. condition not met, anticipated outcome would value zero. outcomes are also represented form Learning Rate Confusion Matrices proposed research.

Language: Английский

---

Impact of a Novel Convolution Neural Network on Chest X-Ray Images for Pneumonia Detection

2022 IEEE 7th International conference for Convergence in Technology (I2CT), Journal Year: 2024, Volume and Issue: unknown

Published: April 5, 2024

Pneumonia is still considered as a major worldwide healthcare hazard which needs immediate treatment and timely precise identification. The research paper shows the method for identification of disease with use Convolutional Neural Network (CNN) on Chest X-ray(CXR) images help Batch normalisation, padding data augmentation. uses comprehensive dataset 3450 CXR images. experiments were conducted over 200 epochs to ensure accuracy. normalization contributed stability better interpretability CNN. Data Augmentation including Colour jitter made training set more diverse generalization. classification parameters like precision, recall ,F1 score accuracy used estimation model's efficacy. model showed 96.02% reflecting its reliability in classification. This study gives medical professionals dependable effective tool that improves state-of-the-art pneumonia diagnosis.

Language: Английский

---

Analysing the Electrical Fault Detection and Classification Capabilities of a Decision Tree Classifier

Published: April 18, 2024

The identification of faults in traditional approaches often depends on intricate algorithms and considerable preparation data. On the other hand, decision tree classifiers provide a more simple but effective method for automated fault classification. aim this study is to evaluate how well Decision Tree Classifier performs field detecting categorizing electrical faults. Electrical systems are vulnerable multitude errors that have potential compromise dependability security whole infrastructure. utilises dataset consists signals obtained from various failure situations, such as short circuits, overloads, ground information used train Classifier, which aims construct prediction model purpose recognising categorising forms failures. research assesses performance by analysing important metrics like accuracy, precision, recall, F1 score. results indicate capable efficiently recognizing classifying defects, showcasing its adaptability different scenarios. significant contributions understanding may be context problem detection systems. These findings emphasise efficacy means improving robustness power distribution networks. implications enhancing maintenance techniques advancing development intelligent real-time monitoring

Language: Английский

---