http://hdl.handle.net/123456789/10343 Sat, 04 Apr 2026 12:26:35 GMT 2026-04-04T12:26:35Z http://hdl.handle.net/123456789/14465 Classification of EEG Signals for Neuromarketing applications Syed Mohsin Ali Shah, 01-242192-008 Every year, more than 400 billion dollars is spent on marketing campaigns. It is a common practice to promote diverse customer goods through advertising campaigns in order to boost revenues and consumer awareness. The effectiveness of business investments in marketing campaigns is entirely dependent on consumers’ willingness and ability to describe how they feel after watching an advertisement. Conventional marketing techniques (e.g., television commercials and newspaper ads) are unaware of human emotions/response while watching the advertisements. Traditional advertising techniques seek to govern the consumer’s opinion toward a product, which may not reflect their actual behavior at the time of purchase. It is probable that advertisers misjudge consumer behavior because predicted opinions do not always correspond to consumers’ actual purchase behaviors. Neuromarketing is the new paradigm of understanding customer buyer behaviour, decision making as well as the prediction of their gestures for product utilization through an unconscious process. The field of neuromarketing has gained traction as means of bridging the gap between traditional advertising methods that focus on explicit consumer responses, and neuromarketing methodologies that focus on implicit consumer responses. Choice prediction allows it to figure out what buyers really desire about the product. Neuroscience information can be used in neuromarketing to know the behavior of a consumer with the help of brain activity using EEG signals. EEG-based preference recognition systems focus on three key phases. In previous studies, researchers did not focus on effective preprocessing and classification techniques of EEG signals, so in this study, an effective method for preprocessing and classification of EEG signals is proposed, using deep learning to determine the choices of consumers for various products by measuring their “liking” and “disliking” as neuromarketing applications. The proposed method involves effective preprocessing of EEG signals by removing noise and a synthetic minority oversampling technique (SMOTE) to deal with the class imbalance problem. The dataset employed in this study is a publicly available neuromarketing dataset. The dataset consists of EEG data recordings taken from 25 participants, shown different sorts of products. The responses of customers were recorded in terms of likes and dislikes. Automated features were extracted using a long-short term memory network (LSTM) and then concatenated with handcrafted features like power spectral density (PSD) and discrete wavelet transform (DWT) to create a complete feature set. The classification was done using the proposed hybrid classifier that optimizes the weights of two machine learning classifiers and one deep learning classifier and classifies the data between like and dislike. The machine learning classifiers include the Support Vector Machine (SVM), Random Forest (RF), and Deep Learning Classifier (DNN). The proposed hybrid model outperforms and achieves an accuracy of 96.89% among other different classifiers like RF, SVM, and DNN. In the proposed method, accuracy, sensitivity, and specificity were computed to evaluate and compare the proposed method with recent state-of-the-art methods. Supervised by Dr. Shehzad Khalid Sat, 01 Jan 2022 00:00:00 GMT http://hdl.handle.net/123456789/14465 2022-01-01T00:00:00Z http://hdl.handle.net/123456789/14467 Aerial Imagery Pile Burn Detection using Deep Learning Hoor Ul Ain Tahir, 01-242202-003 Wildfires are one of the costliest and deadliest natural disasters around the globe, affecting millions of acres of forest resources and threatening the lives of human and animals. Thousands of forest fires across the globe results in serious damage to the environment. Further, industrial explosions, domestic fires, farm fires, and wildfires are huge problem that causes negative effects on the environment contributing significantly towards the issue of climate change. Damage caused by such incidents are time-sensitive and can be fatal resulting in a huge loss to life and property if not timely dealt with. Recent advances in aerial images show that they can be beneficial in wildfire studies. Among different technologies and methods for collecting aerial images, drones have been used recently for manual/automatic monitoring of potential risk areas. Images received from the drones can be processed using vision and machine learning techniques for automated and timely detection of fires thus shortening the response time and reducing the damage caused by the fire whilst minimizing the cost of firefighting. Automated vision-based fire detection has therefore become an important research topic in recent years. Desired properties of good vision-based fire detection are low false alarm rate, fast response time, and high accuracy. This thesis presents a comprehensive literature review of recent vision-based approaches for the automated detection of fire from images and videos. It also includes computing the area under the fire and planning to mitigate the fire. The literature has broadly been categorized into classic vision/machine learning-based approaches and deep learning-based approaches. Based on the comparison of these approaches using a variety of datasets and performance metrics, it has been observed that deep learning-based approaches generally yield better performance as compared to classic vision/machine learning-based techniques. In this research, we further explored various deep learning alternatives for accurate fire detection. A Yolov5-based deep learning model has been proposed in this research for efficient region-based detection and segmentation of fire. Pixel level segmentation is also performed using Mask RCNN to estimate the area under the fire so that planning can be done to mitigate with the fire. The problem of availability of limited labeled training data as compared to the training samples required for deep learning-based model training is mitigated through variety of preprocessing and augmentation techniques. Comparison with existing vision-based fire segmentation approaches on publicly available datasets show the improved performance of proposed approach as compared to the competitors. Supervised by Dr. Shehzad Khalid Sat, 01 Jan 2022 00:00:00 GMT http://hdl.handle.net/123456789/14467 2022-01-01T00:00:00Z http://hdl.handle.net/123456789/14466 Weapon Detection System for Surveillance and Security Abdullah Waqar, 01-242202-001 Weapons are a critical and serious topic and has become a severe threat to current security needs. People who bring firearms into airlines, schools, and other secure locations pose a threat to public safety. In certain regions of the globe, mass shootings and gun violence are on the increase. These kinds of situations are time sensitive and may result in significant loss of life and property. Although CCTVs have been employed in many establishments but these require operators to continuously examines the video streams for weapons. The ability to identify suspicious activity is proportionate to their attention to each video stream shown on the screen, thus leading to a high rate of false positives which can become a liability to the daily operational needs of institutions. Therefore, the requirement for the deployment of video surveillance systems capable of recognizing firearms automatically has increased and plays an important role in intelligent monitoring. Several object detection models are available, which struggle to recognize firearms due to their unique size and form, as well as the varied colours of the background. This thesis presents a comprehensive literature review of recent visionbased approaches for automated detection of firearms from images and videos. The literature has broadly been categorized into classic vision/machine learning based approaches and deep learning based approaches. In this research, we further explored various deep learning alternatives for accurate fire detection. For region based detection, a deep learning based weapon detection system employing YOLO v5 for weapon detection that will be sufficiently resilient in terms of affine, rotation, occlusion, and size. The performance of our system was evaluated on a publicly available dataset and achieved the F1-score of 95.43%. Instance segmentation or pixel level segmentation was also performed which employs Mask-RCNN for the detection and segmentation of firearms. We achieved the detection accuracy (DC) of 90.66% and 88.74% Mean intersection over union (mIoU). The purposed methodology combined both techniques with different preprocessing methods along with various data augmentation techniques to improve the efficiency and accuracy of the system. Supervised by Dr. Shehzad Khalid Sat, 01 Jan 2022 00:00:00 GMT http://hdl.handle.net/123456789/14466 2022-01-01T00:00:00Z http://hdl.handle.net/123456789/17368 Predication of Judgments According to the Given Cases Using a Hybrid Approach Ayesha Shah, 01-242192-002 The advancement of technology has led to an increase in the number ofitems becoming digital. Nowadays, courts generate a large amount of data (unstructured data) each day, including legal data. The digitization of this kind of content can be advantageous to court petitioners, attorneys, and law students in a variety of ways. Legal judgment prediction resolves the issue because it is now simple to search for relevant data from a big body of information. Researchers will make their predictions about court judgments based on the outcomes, similarities to criminal cases, income texts, copywriting, etc. However legal data differs from regular data in terms of vocabulary, language use, and other factors. When making predictions about legal judgments, keep in mind that legal facts contain a significant semantic connection among the text. So, for the sake of achieving semantic dependency, we have chosen some special NLP algorithms. To keep the following problems in mind in the proposed work we designed a legal dataset with two comnponents or just two files. One contains testing data, which consists of 70 files, while the other contains training data, which consists of 2878 files. For training, we used data from Aila2019 (Indian Supreme Court data), and for testing, we used data from the Supreme Court of Pakistan. Since this data was unstructured, we first labeled it and divided it into multiple categories (columns). The data set is appropriately labeled categorized and segmented based on the given information. At this stage, data was in a structured format. The sections or columns that come after are the court's name, petition number, title, date, facts, issue, the decision and holdings, separate opinions, analysis, and the results. We made use of Power Bi, Tableau, and Jupyter notebook (Python). We employed machine leaming and natural language processing (NLP) methods for prediction. We used a hybrid approach by combining the machine learning methods XGBoost classifier, SVM, Random Forest, and Decision tree classifier, linear regression, Multi- Naive base with TF-IDF and Word2vec as word embedding techniques. Gradient boosting classifier gives good accuracy among all. We used TF-IDF on the data initially, followed by TF IDF with N-grams, which provided accuracy between 0.689 and 0.77. We employ the word2vect model for word embedding, which provides accuracy between "0.80 to 0.86" for all applied classifiers, to increase accuracy and obtain higher semantic meaning. We used accuracy, Fl-score precision, and recall to prescnt the results. The limitation of the proposed study is we did not categorize the judgments in our work according to their categories (criminal or test cases etc.). Therefore, it can be done as follows in the future. Supervised by Dr. Muahmmad Asfand-e-Yar Sat, 01 Jan 2022 00:00:00 GMT http://hdl.handle.net/123456789/17368 2022-01-01T00:00:00Z