A5009920995- Speech and Audio Processing
- Speech Recognition and Synthesis
- Online Learning and Analytics
- Music and Audio Processing
- Music Technology and Sound Studies
- Sentiment Analysis and Opinion Mining
- Stock Market Forecasting Methods
- Emotion and Mood Recognition
- Data Mining Algorithms and Applications
- Currency Recognition and Detection
- Retinal Imaging and Analysis
- Forecasting Techniques and Applications
- Anomaly Detection Techniques and Applications
- Internet of Things and AI
- Digital Imaging for Blood Diseases
- Flow Measurement and Analysis
- Rough Sets and Fuzzy Logic
- Gait Recognition and Analysis
- User Authentication and Security Systems
- Impact of AI and Big Data on Business and Society
- Systemic Lupus Erythematosus Research
- Neural Networks and Applications
- Network Security and Intrusion Detection
- Radiomics and Machine Learning in Medical Imaging
- Advanced Electrical Measurement Techniques
Bowen University
2024
Landmark University
2022-2024
Sarcasm and irony represent intricate linguistic forms in social media communication, demanding nuanced comprehension of context tone. In this study, we propose an advanced natural language processing methodology utilizing long short-term memory with attention mechanism (LSTM-AM) to achieve impressive accuracy 99.86% detecting interpreting sarcasm within text. Our approach involves innovating novel deep learning models adept at capturing subtle cues, contextual dependencies, sentiment shifts...
This paper presents a transformative explainable convolutional neural network (CNN) framework for cataract detection, utilizing hybrid deep learning model combining Siamese networks with VGG16. By leveraging rate scheduler and Grad-CAM (Gradient-weighted Class Activation Mapping) explainability, the proposed not only achieves high accuracy in identifying cataract-infected images but also provides interpretable visual explanations of its predictions. Performance evaluation metrics such as...
Financial forecasting plays a critical role in decision-making across various economic sectors, aiming to predict market dynamics and indicators through the analysis of historical data. This study addresses challenges posed by traditional methods, which often struggle capture complexities financial data, leading suboptimal predictions. To overcome these limitations, this research proposes hybrid model that integrates Bayesian optimization with Long Short-Term Memory (LSTM) networks. The...
The accuracy of any speech translation system essentially depends on the quality audio signal inputted into it. Many researchers have worked different approaches in an attempt to reduce level noise signals. Such approaches, among others, include Wavelet, Fourier Transform (FT), and deep learning. These algorithms well noisy a certain degree, but their degree is not sufficient enough for speech-to-speech (S2S) because presence just little can alter semantic representation underlying language....
In this study, we introduce an innovative approach that combines convolutional neural networks (CNN) with attention mechanism (AM) to achieve precise emotion detection from speech data within the context of e-learning. Our primary objective is leverage strengths deep learning through CNN and harness focus-enhancing abilities mechanisms. This fusion enables our model pinpoint crucial features signal, significantly enhancing classification performance. experimental results validate efficacy...
This study presents the development and evaluation of a Multi-Task Long Short-Term Memory (LSTM) model with an Attention Mechanism designed to predict students' academic performance. The concurrently addresses two tasks: predicting overall performance (total score) as regression task categorizing levels (remarks) classification task. By processing both tasks simultaneously, optimizes computational efficiency resource use. dataset includes detailed student records across various metrics such...
This study presents the development and evaluation of a Multi-Task Long Short-Term Memory (LSTM) model with an attention mechanism for predicting students’ academic performance. The research is motivated by need efficient tools to enhance student assessment support tailored educational interventions. tackles two tasks: overall performance (total score) as regression task classifying levels (remarks) classification task. By handling both tasks simultaneously, it improves computational...
Neural Network-based speech-to-speech (S2S) translators require a robust and well-refined dataset of audio signals, from which they make automatic translations. These during recording, are usually accompanied by some noises, normally alter the information conveyed original noiseless signal. This type problem affects accuracy translation system. Although many de-noising techniques have been proposed researchers for removing noises raw however, this paper presents novel approach noise removal...