Department of Computer Science

Permanent URI for this communityhttps://repository.cuilahore.edu.pk/handle/123456789/16

Browse

Author: search.filters.author.Dr. Zeeshan GillaniSubject: search.filters.subject.Computer Science

Search Results

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Deep Learning-Based Prediction of Urban Area Expansion
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Hamza Ali; FA20-RCS-003; LHR TP 8360; Dr. Zeeshan Gillani
    Multi-temporal data can be useful in many research areas. Multi-temporal data provides us with high-resolution satellite imagery. This high-resolution data can be used to understand change detection in a specific area or the layout of that complete area. To use multi-temporal data, especially custom datasets for deep learning models is real headache. Moreover, Multi temporal data can be very useful with Artificial Intelligence to develop models to tackle different problems like wildfire detection, traffic flow detection, etc. This thesis focuses on two problems 1st one is how can custom multi-temporal dataset which consists of a small sample be used to develop a deep learning model for semantic segmentation purpose of given custom dataset and 2nd problem is related to Urban expansion. The problem of urban expansion is a major issue all over the world, especially in the countries of Africa. Urban expansion has a direct impact on both economic growth and climate change. In this era Machine learning and Computer Vision techniques will provide a vital role to create a model which will help to tackle this problem using multi-temporal data. This thesis methodology is to use custom satellite images data set of a specific area and create a deep learning segmentation model to do segmentation and prediction of different areas in satellite images especially, the urban part. This research focuses on the RGB multi-temporal data set of Dakar, Senegal which is one of the Seaports on the Western Coast of Africa. This thesis methodology is divided into two separate parts. 1st part is about segmentation, an experiment was conducted using with simple Multi U-Net architecture and it achieved more than 85% accuracy on the validation dataset. After these predictions were made using random images from the test dataset. 2nd part focused on the urban expansion problem and trained a Regression model using an Artificial Neural Network which only got a 12% MSE value with 97.25% accuracy and predicts urban expansion on basis of pixel values from remote sensing data using population data from the year 2022 to 2031
  • No Thumbnail Available
    Item
    Identification of Best Sowing Patterns of Crop using Satellite Imagery and Deep Learning
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Zil E Huma Shahzadi; FA19-RCS-020; LHR TP 8337; Dr. Zeeshan Gillani
    Rapid growths in population and climate change are resulting in food insecurity. Food security is more challenged in developing countries like Pakistan where conventional practices of crop monitoring are in place. The two aspects of crop monitoring which are crop identification and yield prediction are manual which are time-consuming and resource extensive thus resulting in delayed decision making. However, the Precision Agriculture applications for crops monitoring based on Remote Sensing data can help us to effectively monitor crops and increase production and aid decision making. This study acquires remotely sensed multispectral and multitemporal satellite imagery from Sentinel-2 mission satellites to extract spectral bands over different timestamps of the rice, wheat, and sugarcane crop season. These spectral bands along with the computed vegetation indices over the growing season of wheat and rice are used with the Long Short Term Memory network for the early identification of the crops. The study also attempted to identify the best sowing dates of wheat crops with multispectral and multitemporal data. Further, the significance of the temporal data and different combinations of the spectral bands were analyzed for crop identification of the small-sized fields and a comparison was made with the existing state of the art. The best combination of the spectral bands resulted in 99.76 % accuracy for crop identification. Further, the crops are also identified with 93.77 % accuracy within the first four weeks of their seeding. Our study also identified the sowing week of wheat crop with RMSE of 0.8. The crop identification accuracy with the proposed approach is suggestive of the applicability of the study for the automatic identification of crops on large scale
  • No Thumbnail Available
    Item
    Metropolis Violation Detector Using Deep Neural Network
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Iqra Khalid; FA19-RCS-014; LHR TP 7298; Dr. Zeeshan Gillani
    Anomaly discovery on road traffic is a significant assignment because of its extraordinary potential in metropolitan traffic the board and street wellbeing. It's anything but an extremely difficult assignment since the strange occasion happens seldom and shows various practices. In this work, we present a model to recognize abnormality in street traffic by gaining from the vehicle movement designs in two particular yet connected modes, i.e., the static mode and the powerful mode, of the vehicles. The static mode investigation of the vehicles is gained from the foundation demonstrating followed by vehicle identification technique to find the unusual vehicles that keep still out and about. The unique mode investigation of the vehicles is gained from identified and followed vehicle directions to find the strange direction which is atypical from the predominant movement designs. The outcomes from the double mode investigations are finally melded by driven a re identification model to acquire the final abnormality. This study was based on three classes of anomalies (car crash, car stall and lane change). It was divided into a two class problem with 63 anomaly folders and 86 no anomaly folders. Dataset was provided by NVIDIA AI city challenge track 4 containing 100 train and 100 test videos. Firstly videos were annotated according to anomaly event time. The anomaly time was converted into seconds and then specific frames were cropped. Then 30 frames per video were selected to fed into ResNet18 for high feature extraction. Then LSTM architecture and 3D-CNN was trained and results were evaluated on accuracy evaluation measure. Satisfying results was obtained from both architectures i-e; 80 % accuracy of 3D-CNN and 83 % accuracy of ResNet with LSTM. As it is an on-growing field many work can be done in future by using advanced models for the improvements
  • No Thumbnail Available
    Item
    Pipeline for Identification of Terrorist Organization and Classification of Their Members Using Social Media
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Sana kousar; FA17-RCS-023; LHR TP 5978; Dr. Zeeshan Gillani
    Social media has a tendency to change perception or opinion of people. The surge in use of social media has made people venerable to exploitation by different banned outfits. The aim of this research is to analyze social media content and to identify potential individual or group of individual and their target. We generated a dataset using Twint API and use natural language processing techniques to preprocess the data and later use network analysis and different machine learning ensemble techniques to identify potential individuals that are targeting and recruiting people in the name of NGO’s.
  • No Thumbnail Available
    Item
    Stock Market Prediction Using Deep Learning
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Hamza Javaid; CIIT/SP22-RCS-014/LHR; Dr. Zeeshan Gillani; LHR TP 9696
    Accurate stock market prediction remains a complex research challenge due to the market’s irregular, non-linear, and highly dynamic multivariate nature. Traditional statistical methods often struggle to capture the volatile patterns, and deep dependencies present in stock time-series data. This thesis addresses the problem by proposing a hybrid deep learning-based fusion model designed to improve the accuracy of stock price trend forecasting. The proposed solution adopts a late fusion approach, integrating the complementary strengths of four models: Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) to capture sequential dependencies, the Temporal Fusion Transformer (TFT) for modeling complex temporal relationships through attention mechanisms, and the Multi-Layer Perceptron (MLP) for nonlinear feature interactions in time-series data. This architecture forms a robust forecasting system, trained on multivariate time-series data from the NASDAQ-100, which includes both raw stock metrics and derived technical indicators. The fusion model achieved an R² score of 0.99196 and an MSE of 0.00033, clearly outperforming standalone LSTM, GRU, and stacked LSTM-GRU baselines. The predictions closely follow actual market movements with minimal lag, capturing both bullish and bearish trends effectively. This research presents a high-accuracy predictive framework that offers meaningful contributions to the field of stock forecasting, helping investors make informed buy/sell/hold decisions, thereby reducing risk and improving investment strategies.