http://hdl.handle.net/123456789/13168 2026-08-31T09:44:53Z 2026-08-31T09:44:53Z Muhammad Ibrahim Lodhi, 01-249241-007 http://hdl.handle.net/123456789/21658 2026-08-31T09:33:17Z 2026-01-01T00:00:00Z

Data Driven Earthquake Prediction using Intelligent Techniques Muhammad Ibrahim Lodhi, 01-249241-007 Earthquakes represent one of the most devastating natural hazards, claiming thousands of lives and causing trillions in economic damage annually, particularly in seismically active regions like the Himalayan arc and Pacific Ring of Fire . Despite advances in seismic monitoring, accurate prediction of earthquake magnitude the key determinant of potential destruction remains elusive due to the nonlinear, chaotic dynamics of fault systems and the rarity of large events in historical catalogs. In conventional probabilistic seismic hazard analysis, long term risk predictions can be made, but reliable short term predictions are not possible, which makes society prone to abrupt ruptures. This thesis works to fill this crucial research gap by proposing and developing a new deep learning model to predict magnitude based on multi modal precursor. Although there have been some recent attempts to apply machine learning to seismicity forecasting, there have been several models still using simple regression models or simple neural networks, which are not capable of handling spatiotemporal correlations effectively. Although models such as random forest approaches have had moderate success at the regional scale, they also tend to neglect long term temporal correlations and lack generability across different tectonic settings. Although there have been some promising approaches using transformers for time series data, there have been no attempts to apply these models to seismicity forecasting, mainly due to their high complexity and the need for specific adaptations. These models, although successful, also emphasize the need to develop models that can integrate heterogeneous features of seismicity, such as b value anomaly, ionospheric TEC, and waveform magnitude, effectively, which can also provide probabilistic forecasting. In light of these challenges, this thesis develops the approach for earthquake magnitude prediction using modern deep learning and making a particular focus on: revealing temporal dynamics and predictive uncertainty. It focuses on an enhanced Temporal Fusion Transformer (TFT) architecture combining bidirectional LSTMs, GRUs, multi head attention, and gating mechanisms that combine past observations with simple future covariates and static spatial contextual information into a single unified forecasting model. To overcome the small size and imbalance in conventional seismic catalogs, this study constructs an augmented dataset with a model based synthetic data generator and relies on the assumption that the added records preserve the statistical and spatial properties of the original events. The original data and augmented are subjected to extensive feature engineering comprising lagged magnitudes, rolling statistics, interv action terms, and cluster based spatial descriptors, followed by their transformation into supervised sequences to model time series. The TFT model is trained using a quantile loss function to produce probabilistic forecasts at multiple quantiles, allowing the derivation of both point estimates and prediction intervals for earthquake magnitude. The training procedure incorporates regularization techniques such as dropout, weight decay, and gradient clipping, together with adaptive learning rate scheduling and validation based check pointing to promote stable convergence and generalization. Model performance is evaluated on a temporally held out test set using root mean squared error (RMSE), mean absolute error (MAE), and average quantile loss, alongside visual diagnostics such as prediction truth scatter plots, residual analysis, and time series overlays. In addition, Monte Carlo dropout is employed at inference time to form an ensemble of stochastic predictions, providing an estimate of epistemic uncertainty and enabling a comparison between single model and ensemble behavior. The results indicate that the proposed TFT architecture, combined with carefully designed augmentation and feature engineering, can achieve low prediction errors while generating well calibrated prediction intervals for normalized earthquake magnitudes. Spatial comparison plots show that the synthetic events closely follow the geographic distribution of the original Catalog, suggesting that the augmented dataset is suitable for training without distorting the underlying seismic patterns. Overall, the thesis demonstrates that attention based sequence models, when paired with realistic data augmentation and rigorous evaluation, offer a promising direction for probabilistic earthquake magnitude forecasting and for quantifying the uncertainty inherent in such predictions. Supervised by Dr. Saba Mahmood

2026-01-01T00:00:00Z Ali Arshad, 01-243231-002 http://hdl.handle.net/123456789/19737 2025-10-08T03:57:48Z 2025-01-01T00:00:00Z

Exploring Evolutionary Algorithms for Optimal Features Selection to Detect Anomaly Based Intrusion In IoT Ali Arshad, 01-243231-002 In light of the fast-evolving scenario of the IoT, network security constantly bears immense challenges due to the increasing number of cyber threats and vulnerabilities. Traditional intrusion detection systems use predefined signatures and rule-based approaches to detect malicious activities within a network. In contrast to the traditional signature-based intrusion detection system, which utilizes previously established attack patterns, an anomaly-based intrusion detection system typically utilizes machine learning, statistical models, and artificial intelligence to assess network traffic, system log entries, and user behavior. . This research proposes the anomaly-based intrusion detection system using Particle Swarm Optimization (PSO)-based feature selection and ensemble learning in enhancing detection accuracy for IoT networks. Performance of stacking, hard voting, soft voting, and autoencoder-based models is evaluated over the benchmark datasets NSL-KDD and KDDCup 99 in analyzing their effectiveness in detecting anomalous behaviors in IoT environments. From the results, it is clear that PSO-based feature selection is highly significant in anomaly detection. Anomaly detection gets better performance by reducing feature redundancy along with improving classification accuracy. Of all the models tested, Stacking performed the best, with an accuracy of 98.87% on NSL-KDD and 99.76% on KDDCup 99, proving to be the most effective method. Soft Voting and Hard Voting also did well on NSL-KDD, recording 98.38% and 98.13% accuracy respectively, which highlighted the strength of ensemble methods in identifying anomalies based on IoT. The Autoencoder model demonstrated unsupervised anomaly detection, with a slightly less accurate of 96.63% on NSL-KDD and 98.23% on KDDCup 99, due to its greater false positive rates. This suggests that models based on deep learning could make a significant performance improvement on anomaly classification by leveraging their explicit feature selection capabilities. Stacking is an ensemble learning algorithm that increases predictive performance by aggregating multiple base models in a superior way. It can be used optimally when there exists some labeled data in supervised learning cases. Auto-Encoders correspondingly are neural networks deployed mainly in unsupervised learning, and they serve very well in detecting anomalies without labeled data. Supervised by Dr. Saba Mahmood

2025-01-01T00:00:00Z Hafiz Muhammad Ahmad, 01-243222-003 http://hdl.handle.net/123456789/19738 2025-10-07T11:57:44Z 2025-01-01T00:00:00Z

AI-Driven for Smart Concrete Bridge Inspection and Maintenance Hafiz Muhammad Ahmad, 01-243222-003 Concrete bridges require timely and accurate defect detection in order to maintain their structural safety, time-consuming, expensive processes often suffer from human errors. Meta-learning is applied to enhance convolutional neural networks for multi-target defect classification. The CODEBRIM dataset is harnessed in this study, challenging due to overlapping defects and varying environmental conditions. MetaQNN and ENAS are two advanced neural architecture search techniques used to automatically design optimized CNN models. These models are then compared with traditional architectures like ResNet, VGG, and DenseNet. Experimental results show that meta-learned models achieve significant improvements in terms of classification accuracy and computational efficiency. The most accurate models attained 75% test accuracy, reflecting the strength of simultaneous multi-defect identification. It proposes an AI-powered way of automated bridge inspection that is expected to be faster, more reliable, and less expensive than today, enhancing security on infrastructure items and lower maintenance costs. Supervised by Dr. Usman Hashmi

2025-01-01T00:00:00Z Muhammad Idrees, 01-243222-007 http://hdl.handle.net/123456789/19739 2025-10-08T06:59:50Z 2025-01-01T00:00:00Z

Intelligent Resource Management Framework Using Context Aware Statistics for B5G Network Muhammad Idrees, 01-243222-007 With the rapid evolution of mobile communication from 1G to 6G, efficient resource management has become essential to meet increasing demands of the networks. Traditional static allocation methods struggle to handle dynamic and heterogeneous B5G networks, leading to inefficiencies in latency, bandwidth utilization, and Quality of Service (QoS). To address these challenges, we propose an Intelligent Resource Management Framework that integrates Federated Learning (FL) with Context-Aware Statistics for optimized resource allocation. Our approach enables the training of decentralized models at the network edge using the Federated Average (FedAvg) algorithm, reducing communication overhead while preserving data privacy. Each network node locally train a model on real-time context-aware data, including user mobility, traffic variations, and signal fluctuations. The local models are then aggregated to improve learning without compromising privacy. The experimental results demonstrate superior performance, achieving 99.58% precision in resource prediction, significantly outperforming traditional centralized deep learning models. Key performance matrices such as precision, recall, F1 score, and AUC confirm the model’s ability to efficiently allocate resources under varying network conditions. The framework dynamically adjusts to traffic surges, interference, and mobility changes, ensuring optimal QoS and network stability. FD averaging algorithm performs better than other techniques. So, the proposed work achieved resource management, privacy preservation, low latency, and high data rates. Supervised by Dr. Muhammad Khurram Ehsan

2025-01-01T00:00:00Z