Cyberbullying has emerged as a serious concern on social media platforms, negatively affecting individuals through abusive and offensive online interactions. The rapid growth of user-generated content makes manual monitoring ineffective, creating the need for intelligent automated detection systems. This paper presents a machine learning-based framework for detecting cyberbullying in textbased social media posts. The proposed system performs text preprocessing and TF-IDF feature extraction to convert raw textual data into meaningful features. Three machine learning algorithms, namely AdaBoost, Stochastic Gradient Descent (SGD), and Multinomial Naïve Bayes, are trained and evaluated to classify posts as offensive or non-offensive. Sentiment analysis is integrated to enhance the classification process by providing additional contextual information. Furthermore, the system monitors repeated offensive behavior and supports automated user moderation through an administrative interface. Experimental results demonstrate that the proposed framework provides reliable classification performance and contributes to creating a safer and more secure online communication environment.
Afreen Begum, Sk.Mahammadunnisa· American Journal of AI Cyber...· 0 citations
Accurate prediction of stock market prices plays a vital role in financial analysis and investment planning due to the highly dynamic and nonlinear nature of market behavior. This paper presents a comparative framework for stock price prediction using Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) models. Historical stock price datasets of multiple companies, including TATA, Tesla, Facebook, and Apple, are utilized to evaluate the predictive capability of both approaches. Prior to model training, the dataset undergoes preprocessing steps such as missing value removal, chronological sorting, Min–Max normalization, and division into training and testing subsets using an 80:20 ratio. The ANN and LSTM models are independently trained on the processed data and evaluated using Mean Squared Error (MSE) and prediction accuracy. Experimental analysis demonstrates that both models successfully capture stock price trends and generate predictions closely matching actual market values. However, the ANN model consistently produces lower MSE and higher prediction accuracy than the LSTM model across the evaluated datasets. Comparative graphical analysis further confirms the effectiveness of ANN in reducing prediction error while maintaining reliable forecasting performance. The proposed framework provides a practical and efficient solution for stock price prediction and can assist investors and financial analysts in making informed investment decisions through data-driven forecasting techniques.
Prabhavathi Macherla, Sk.Mahammadunnisa· American Journal of AI Cyber...· 0 citations
The rapid growth of social media has made it easier for information to spread quickly, but it has also increased the circulation of machine-generated and misleading content. Advanced language models can now produce tweets that closely resemble human writing, making it difficult to identify fake content through manual inspection. This project presents a deep learning approach for detecting machinegenerated tweets using FastText word embeddings and a Convolutional Neural Network (CNN). The collected tweet dataset is first preprocessed by removing unwanted characters, stop words, and noise to improve text quality. FastText is then used to convert the cleaned text into meaningful vector representations that preserve semantic information. These embeddings are provided as input to the CNN model for classification. The proposed approach effectively distinguishes human-written tweets from machine-generated ones and demonstrates better performance than conventional machine learning methods. The developed system can support social media platforms in reducing the spread of automated misinformation and improving the reliability of online communication.
Sidhartha.K, Sk.Mahammadunnisa· International Journal of Dat...· 0 citations
Floods are among the most destructive natural disasters, causing severe damage to human lives, infrastructure, agriculture, and the economy. Accurate and timely flood forecasting is essential for effective disaster preparedness and mitigation. This paper presents a PrivacyAware Federated Deep Learning Framework for Intelligent Flood Forecasting and Water Level Prediction, which combines Federated Learning (FL) with a Feedforward Neural Network (FFNN) to deliver secure and accurate predictions without sharing raw data among participating stations. The proposed framework enables multiple regional nodes to train local models independently while transmitting only model parameters to a central server for global aggregation, thereby preserving data privacy and reducing communication overhead. The aggregated model identifies flood-prone regions and predicts future water levels using hydrological and meteorological parameters. Experimental evaluation demonstrates that the proposed framework achieves high prediction accuracy with low prediction error while ensuring secure, decentralized learning. The proposed system provides a reliable and scalable solution for intelligent flood forecasting and early warning applications.
S. Shivani, Sk.Mahammadunnisa· American Journal of AI Cyber...· 0 citations
Phishing websites continue to pose a serious cybersecurity threat by deceiving users into revealing sensitive information such as login credentials, banking details, and personal data. Traditional blacklist-based detection techniques are ineffective against newly created phishing websites, necessitating intelligent machine learning solutions. This paper presents PhishShield, a hybrid phishing website detection framework that integrates Support Vector Machine (SVM) and Light Gradient Boosting Machine (LightGBM) to accurately classify legitimate and phishing websites. The proposed approach utilizes URL-based feature extraction and text preprocessing to generate meaningful representations for classification. SVM provides robust decision boundaries, while LightGBM enhances predictive performance through efficient gradient boosting. Experimental evaluation demonstrates that the hybrid framework achieves higher accuracy, precision, recall, and F1-score compared to conventional machine learning models. The system is implemented as a web-based application capable of real-time URL analysis, enabling users to identify malicious websites before accessing them. The proposed framework offers an efficient, scalable, and reliable solution for strengthening web security against evolving phishing attacks.
Srija Pasupunuti, Sk.Mahammadunnisa· American Journal of AI Cyber...· 0 citations
DeepGuard is presented, an intelligent deep learning framework for automated weapon detection in images and surveillance videos using Faster Region-Based Convolutional Neural Network (Faster R-CNN) and Single Shot Detector (SSD).
Chengoli prashanth, Sk.Mahammadunnisa· American Journal of AI Cyber...· 0 citations
A semantic-aware framework for text-to-face image synthesis using a joint Bidirectional Long Short-Term Memory (BiLSTM) network and Generative Adversarial Network (GAN) that improves semantic consistency and visual realism.
Heena Anjum, Sk.Mahammadunnisa· American Journal of AI Cyber...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
