Francis Nweke
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Francis Nweke has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Abdullah Al Hafiz Khan
Kennesaw State University, Marietta, Georgia, USA
2 shared publications - Yong Pei
Kennesaw State University, Marietta, Georgia, USA
2 shared publications - Abm Adnan Azmee
Kennesaw State University, Marietta, Georgia, USA
1 shared publication - Christopher Dargan
Kennesaw State University, Marietta, Georgia, USA
1 shared publication - Dinesh Chowdary Attota
Kennesaw State University, Marietta, Georgia, USA
1 shared publication - William Stigall
Kennesaw State University, Marietta, Georgia, USA
1 shared publication
Latest Publications
- Open Access
- 18 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 247-252
Automated Alphabet Detection from Brain Waves
Brain-computer interfaces (BCIs) offer a novel method of converting brain activity into valuable data. This study investigates the use of electroencephalogram (EEG) signals for recognizing brainwave signals to record human thoughts. Our research focuses on using EEG signals to facilitate communication for people who have traditionally lost their ability to communicate. We concentrated on utilizing machine learning algorithms to decode these EEG data, especially using Support Vector Machines, which produced useful results in classification attempts. Our findings reveal that it is possible to detect individual letters from EEG signals using noninvasive approaches, demonstrating the potential of thought-to-text technology to help a wide range of people and applications.
- 18 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 247-252
Open AccessAutomated Alphabet Detection from Brain Waves
Brain-computer interfaces (BCIs) offer a novel method of converting brain activity into valuable data. This study investigates the use of electroencephalogram (EEG) signals for recognizing brainwave signals to record human thoughts. Our research focuses on using EEG signals to facilitate communication for people who have traditionally lost their ability to communicate. We concentrated on utilizing machine learning algorithms to decode these EEG data, especially using Support Vector Machines, which produced useful results in classification attempts. Our findings reveal that it is possible to detect individual letters from EEG signals using noninvasive approaches, demonstrating the potential of thought-to-text technology to help a wide range of people and applications.
- Open Access
- 18 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 60-68
Large Language Models Performance Comparison of Emotion and Sentiment Classification
The increasing application of artificial intelligence in daily life necessitates precise emotion classification for improved user interactions in areas like healthcare, marketing, and customer service. This work explores the development of emotion classification algorithms, focusing on text classification and providing low latency inferencing for seamless application into persistent-state systems. We use a parallel multi-task learning approach, to learn multiple tasks with a single loss function, allowing it to learn representations in both Emotion Classification and Sentiment Analysis simultaneously. We present a detailed analysis of a fine-tuned BERTTiny model EmoBERTTiny for emotion and sentiment classification tasks, comparing its performance against baseline models and state-of-the-art 7B parameter models. EmoBERTTiny is bench-marked against Llama-2-7B-chat and Mistral-7B-Instruct across Accuracy, F1-score, precision-recall curves and inference speed. EmoBERTTiny outperforms pre-trained and state-of-the-art models across all metrics and computational efficiency, achieving 93.14% accuracy in sentiment analysis and 85.48% accuracy on emotion classification. EmoBERTTiny processes a 256 token context window in 8.04ms on average post-tokenization, and 154.23ms on average in total processing speed.
- 18 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 60-68
Open AccessLarge Language Models Performance Comparison of Emotion and Sentiment Classification
The increasing application of artificial intelligence in daily life necessitates precise emotion classification for improved user interactions in areas like healthcare, marketing, and customer service. This work explores the development of emotion classification algorithms, focusing on text classification and providing low latency inferencing for seamless application into persistent-state systems. We use a parallel multi-task learning approach, to learn multiple tasks with a single loss function, allowing it to learn representations in both Emotion Classification and Sentiment Analysis simultaneously. We present a detailed analysis of a fine-tuned BERTTiny model EmoBERTTiny for emotion and sentiment classification tasks, comparing its performance against baseline models and state-of-the-art 7B parameter models. EmoBERTTiny is bench-marked against Llama-2-7B-chat and Mistral-7B-Instruct across Accuracy, F1-score, precision-recall curves and inference speed. EmoBERTTiny outperforms pre-trained and state-of-the-art models across all metrics and computational efficiency, achieving 93.14% accuracy in sentiment analysis and 85.48% accuracy on emotion classification. EmoBERTTiny processes a 256 token context window in 8.04ms on average post-tokenization, and 154.23ms on average in total processing speed.