Browsing by Author "Dr. Atif Saeed"

Now showing 1 - 6 of 6

Banquette Hall Comparison System (BHCS)
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2020-11-20) Numan Khalid; CIIT/FA16-BSE-074/LHR; Dr. Atif Saeed; LHR TP 6231
BHCS is a web-based system that provides the users the facility to choose the best banquette hall for different events provided by different halls after comparing it with multiple banquette halls from the data gathered. BHCS is an easy approach for the user basically for the Pakistani community where 95% of the banquette halls don't have a web portal and if there are they have only provided the customers with the packages and their contact information neglecting the prices they charge for these packages.
Cricket Squad Formation using Machine Learning
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Muhammad Shaukat Ali; SP19-RCS-022; Dr. Atif Saeed
Cricket is primarily played in three formats around the world: test match, one day international (ODI), and twenty-twenty (T20). T20 has made a great revolution in the world of cricket. The Pakistan Cricket Board (PCB) arranges a tournament named the Pakistan Super League (PSL) every year, which is in T20 format. PSL is liked and watched by a large number of people, and it has a greater amount of statistical data. PSL is based on the Draft system for selecting players for making teams. This draft-based method for selecting players has different categories, each with its own constraints. 16 player squad must have five foreign players, and an 18 players squad could have six or five foreign players. A larger amount of money is used in the draft system. Players’ selection is one of the most important tasks for team formation. PSL team selection is made by team management, and it is very complex for humans to analyze all the previous statistics of the players for better selection. It is also true that human-based systems are not very efficient. It is very important to analyze players' performances for ease of selection and to make the right decision for the selection of players for teams by team management, coaches, and captains. In this thesis, machine learning techniques are used for squad selection in our model, which is named SFPML (Squad Formation in Pakistan Super League using Machine Learning). Important features of a batsman and bowler are used. Our model ranks the batsmen and bowlers based on their previous performances. If a new player enters the PSL tournament, his position in the league is determined by finding similarities among PSL players. Our thesis also attempts to predict the performances of players, such as how many runs a batsman will score, and how many wickets a bowler will take
Identification of Citation in Computer Science using Deep Learning and Cyberpsychology During COVID-19
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2023) Muhammad Sohail Farooq; SP21-RCS-021; LHR TP 8673; Dr. Atif Saeed
In December 2019, a novel strain of Covid surfaced, unleashing a pervasive and inescapable illness upon the world. This inquiry aims to meticulously explore bibliometric facets, specifically scrutinizing publications in the field of computer science throughout 2020 in the aftermath of the global epidemic outbreak. The data, meticulously sourced from the Google Scholar website, involves the random selection of profiles belonging to computer science scholars, initiating an exhaustive exploration into citation rates. It anticipates unveiling that 2020 witnessed the culmination of a substantial body of scholarly work, surpassing the output of the preceding four years. Furthermore, leveraging this data, the study aspires to prognosticate future citation trends. Deep learning applications have emerged as a key revelation, acknowledged for their capacity to furnish superior data representations, consequently yielding more enlightening outcomes. The subsequent phase embarks on an odyssey to unravel the causative factors behind the surge in citation rates, adopting a psychological vantage point that encompasses elements such as home isolation and dedicated quarantine. The study goes beyond the statistical analyses, delving into the psyche of scholars, thereby presenting a more nuanced understanding of the underlying factors contributing to increased citation rates. This illuminating descriptive-analytical exploration not only establishes a correlation between scholars' isolation experiences and their learning trajectories but also encapsulates this connection in terms of recorded academic citations. The research findings not only offer a comprehensive comprehension of the scholar isolation phenomenon but also serve as a clarion call for heightened awareness among stakeholders. This heightened awareness, rooted in both qualitative and quantitative evidence, not only validates the hypotheses posited but also provides a robust foundation for future research initiatives. In summation, this groundbreaking study unveils, for the first time, the critical interplay between quarantine and addiction factors in the realm of global research, underscoring the paramount significance of these elements in shaping scholarly discourse on a worldwide scale.
Intelligent Hotel Recommendation System Using Sentiment Classification and Machine Learning
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Muhammad Ahmad Yousaf; CIIT/SP23-RCS-019/LHR; Dr. Atif Saeed; LHR TP 9704
Travellers are depending more and more on digital platforms to select appropriate lodgings as their dependence on online evaluations grows. However, current hotel recommendation systems sometimes offer general recommendations without being able to comprehend user-specific requirements or evaluate reviews according to specific service elements like location, cleanliness, food quality, and security. Additionally, these systems frequently ignore neutral thoughts, which lowers the recommendations' accuracy and personalization. This study's goal is to create an intelligent hotel recommendation system that combines cutting- edge machine learning and sentiment analysis methods to provide tailored, aspect-based recommendations. To achieve robust classification, the suggested model combines Random Forest with BERT (Bidirectional Encoder Representations from Transformers) for deep contextual sentiment interpretation. To handle a sizable dataset of hotel reviews gathered from Booking.com, the system uses natural language processing techniques including lemmatization, tokenization, stop-word removal, and feature extraction using TF-IDF. By classifying and analyzing reviews based on different hotel features, consumers may do query-based filtering. For instance, they might request hotels with high ratings for cleanliness or food quality. Common issues with current systems, such as cold- start issues, a lack of aspect-level insights, and inadequate user personalization, are addressed by this hybrid paradigm. The method improves the accuracy and applicability of hotel suggestions by precisely reading user preferences and attitudes. The study shows how deep learning and ensemble techniques may be used to create recommendation systems that are more context-aware and user- centric, which enhances decision- making in actual travel situations
personality and Career Prediction Using Textual, Image and Audio Data
(Library Information Services, CUI Lahore, 2022) Muhammad Hamza; FA18- BSE- 003; Dr. Atif Saeed
The rapid advancement in technology has been a major factor in today's world of revolution, where everything is constantly evolving and upgrading. Although this modernized environment has provided multiple facilities to save human time and provide comfort, there is still much more to be done. Events play an important role in one's life and everyone wants that to be memorable but organizing an event is a hectic and running job and requires a lot of patience and leg work. Our project "EventX" is an idea of developing a website that aims to create a platform that can be used by any individual to organize any kind of event i.e., wedding events, birthday events, family/friends gathering, formal events, etc. at the comfort of their home. In parallel, we will register all the service providers on our platform who are already offering or wants to offer event-related services i.e., venue, catering, decoration (interior/exterior), customized cakes, DJ services, event coverage, etc. By a single platform, any user can organize a completely successful event without any physical effort just by logging into our website and hiring the best suitable service provider according to their need, flavour, and interest. In this way, both the service provider and the taker will get benefits from this system.
Securing Email Communications: Advanced Approaches to Detecting Phishing Through Spam
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Amna Asif; SP23-RCS-006; Dr. Atif Saeed; LHR TP 9484
The growing complexity of email-based communication has made it difficult to correctly identify the spam emails which provide significant hazards such as phishing, malware distribution and data breaches. Conventional spam detection algorithms that use static rule-based techniques like Keyword-Based Filtering, Blacklist Filtering, or rely on individual machine learning algorithms like Naïve Bayes, Logistic Regression, K-Nearest Neighbors, usually fall behind in increasing false positive and decreasing accuracy. This study used an optimal ensemble-based approach for spam email identification using Gradient Boosting Machine and Extreme Gradient Boosting algorithms and aims to enhance spam email detection accuracy through efficient hyper parameter tuning of these machine learning algorithms. Primarily, baseline models were trained on default parameters and then performance of these models was improved through randomized search cross validation method to examine the tuning space of hyper-parameters for efficient hyper-parameter values. By using the Enron dataset, a publicly available extensive collection of actual email data containing 33639 labeled emails, models were assessed using key metrics such as accuracy, F1-score, recall, precision, and ROC-AUC. The experimental results of this study presented that the performance of both algorithms was enhanced by the hyper-parameter tuning when contrasted with the baseline models. The modified XGBoost model outperformed the baseline version and other competitive models with an accuracy of 98.65%. Furthermore, on tuned parameters GBM performed well, demonstrating the effectiveness of ensemble algorithm approach. The results highlight the superiority of ensemble algorithms for challenging classification problems and validate the significance of hyper parameters modification in improving model performance. This research offers useful insights for enhancing cybersecurity measures in email communication systems by developing strong spam detection frameworks.