M.Phil / MS

Permanent URI for this collectionhttps://repository.cuilahore.edu.pk/handle/123456789/36

This collection archives the complete set of theses produced by students of the COMSATS University Islamabad, Lahore Campus.

Browse

Subject: search.filters.subject.sp19

Search Results

Now showing 1 - 9 of 9
  • No Thumbnail Available
    Item
    Towards Automatically Resolving Biasness and Conflicts in Stakeholders Input for Requirement Prioritization
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Nabiha Yaseen; SP19-RCS-026; Dr. Farooq Ahmad; LHR TP 8043
    Requirements are needed before developing any project, so these requirements are elicited from the stakeholders. Software Engineers elicit these requirements to meet the demands of the stakeholders. Software engineers find it challenging to satisfy the demands of multi stakeholders if these elicited requirements are vague or misinterpreted. To meet the accuracy, satisfaction, and expectations of multi stakeholders, prioritization of the elicited requirements is needed. Prioritizing the elicited requirements can completely prevent contract breaches or violations like budget overruns, project deadline mismatches, overshooting of delivery dates, and omitting crucial requirements during development. There are various techniques have been introduced in this area, but the problems related to RE are still under research in terms of lack of collaboration among multi stakeholders, Developer’s effort in eliciting conflicted requirements and to make changes after, and resource and time waste. To address these problems, we designed an approach called the Collaborative Requirements Elicitation Tool (CRET), which is intended to facilitate and improve efficient collaboration between multiple users to get the best from requirements elicitation. To enable multiple stakeholders to cooperatively elicit the same goals and requirements toward project that are conflict-free and unbiased, our tool has been designed and developed in a way to support the real-time communication and collaboration among them and to get the requirements on which they are collaboratively satisfied. Our proposed tool was evaluated for its ability to get best accuracy measures to eliciting the requirements in an unbiased, conflict-free, collaborative, timely efficient and lowering the developer’s effort manner. In our proposed tool CRET, requirement elicitation was done collaboratively, by using the Point P rating technique to set the requirement prioritizing values and employed the k-mean clustering algorithm prioritize the elicited requirements. Introduced two new features in this research is the report requirement feature and other is authority approval to remove the conflicts before forwarding the requirements for prioritization. We utilized the PHP LARAVEL framework to develop this web-based tool. With groups 2 of requirement engineers and client stakeholders, we conducted a user study to evaluate the tool, focusing on requirement elicitation and prioritization using CRET. The study's findings indicate that our proposed automated tool support can assist multiple stakeholders in collaborative communicating with other stakeholders more effectively to produce better and improved requirement elicitation, and our tool eliminates conflicts and biases of multiple stakeholders during elicitation through their collaboration. Our tool works in the four operational steps collaboratively RE (requirement elicitation), RRR (Req rating and reviewing), AA (authority approval) and RP (requirement prioritizing). In the RE phase of the software development life cycle; RP is a task that relates to multi phase decision making. It is mostly used for software release planning and influences the creation of the best software product by eliciting stakeholders' preferred needs.
  • No Thumbnail Available
    Item
    Hashtag Recommendation for Micro Videos Using 3D Convolutional Neural Network
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Bilal Ahmed; SP19-RCS-009; LHR TP 8351; Dr. Ashfaq Ahmad
    In recent years, due to common usage of camera equipment like mobile phones and variations of various short videos platform, a lot of videos published each second are either creative or non-creative. Compared to short videos creation, traditional video creation process is very long process like time consuming, producing & casting. Creating shot video is easy where you can use any smart device’s camera, a video is creative if it creates a meaningful interest in your mind after watching else non creative. In this paper we focused on a deep learning algorithm for understanding consistent features and complementary features of micro videos in vine dataset using 3-dimensional convolutional network. The algorithm works on equal-sized frames of video to extract & learn features such as spatial features where we train the model on three different modules of vine dataset d60, d80 & d 100 of vine. We also perform batch normalization on convolutional outputs to avoid overfit & got best results for given vine test data. Through experimental practice we found that 3D CNN performs better than previous methods of understanding video method. In addition to given algorithm we found that how different training dataset affect the feature extraction and affect the results
  • No Thumbnail Available
    Item
    Deep Neural Network Based Model for Context-Aware Human Activity Recognition
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Amiq Inayat; SP19-RCS-024; LHR TP 8342
    currently, with the growth of smart sensing technologies in ubiquitous computing. Human activity recognition (HAR) is becoming a fundamental research problem. HAR aims to recognize the person’s body position, motion, and function with camera and sensors-based systems. Even though camera based HAR gain much progress but due to certain privacy concerns researchers focus with cost-effective sensor-based miniatures for HAR. Because it can play a vital role in aging care, smart homes, and daily life assistant Apps. As the human activities bring a lot of information about context that can help models to accomplish context-awareness. The precise acknowledgement of in¬the¬wild human activities and the contexts related with these activities remains an open research challenge that needs to be addressed. In this work, the aim is to present a context aware human activity recognition (CAHAR) scheme to learn the variability of human behavior context in the wild with physical activity recognition. Deep neural networks and Machine Learning (ML) algorithms opted to get behavioral context of a person in the designed scheme of CAHAR and use different machine learning classifier for comparison with the presented scheme
  • No Thumbnail Available
    Item
    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
  • No Thumbnail Available
    Item
    Enhancing Crime Classification in Surveillance Videos for Real Time Monitoring
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Muhammad Salman Ghauri; SP19-RCS-027; LHR TP 7590; Dr. Usama Ijaz Bajwa
    Anomalies can be detected with the help of patterns and events that differ from the normal flow of events. The paradigms of surveillance may relate to abuse, fights, road accidents and snatchings, etc. In real-world surveillance, finding unusual events in these massive video streams is a difficult endeavor, since they often occur inconsistently. However, deep learning-based anomaly detection helps reduce human labor and its decision-making ability can be compared to that of humans, thus ensuring the safety of the public. In the majority of reported studies, anomalies are detected from surveillance videos based on binary classification. The reported approaches did not cover other anomalous events from surveillance videos, including abuse, fights, vehicle accidents, shootings, stealing, vandalism, and robberies. This paper proposes an intelligent anomaly detection framework based on deep features that can operate more efficiently in surveillance networks. In the proposed framework, spatial-temporal features are first extracted from a series of frames by passing them through a CNN model that has been pretrained. Analyzing the frames in a sequence can be beneficial in detecting anomalous events. Once the deep features have been extracted, the data is then passed to the Long Short-Term Memory (LSTM) model. The model can accurately classify ongoing anomalies/normal events in complex surveillance scenes of smart cities. A dataset from the University of Central Florida (UCF) Crime video dataset is used to perform extensive experiments on anomaly detection. We report an increase in data accuracy of 47.83% over state-of-the-art methods for UCF-Crime datasets.
  • No Thumbnail Available
    Item
    Multi-Aspect Hate Speech Analysis for Roman Urdu Text
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Aniqa Khalid; SP19-RCS-004; LHR TP 7597; Dr. Waqas Anwar
    We live in the age of technology where a large amount of information is produced daily on social media sites as it becomes a source for expressing their opinions and sharing ideas with other people, it also becomes a place for abusive language, personal attacks, and hateful comments. Determining the nature of the suspension is difficult and time-consuming. Automating the process of hate speech analysis in online conversations is the best way to ensure user security and improve online conversations. In this study, we have produced our dataset for Roman Urdu containing more than 3k comments which were annotated by NLP experts with the following aspects: Hostility, directness, target and group. The dataset is trained using various deep learning & machine learning algorithms for figuring out which model is the best at classifying multi-aspect hate speech. The results showed that logistic regression and bi-LSTM are the best algorithm in determining the toxicity of Roman Urdu text.
  • No Thumbnail Available
    Item
    Petri Net Based Formal Semantic Extraction from Code
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Shafaq Naz; SP19-RCS-017; LHR TP 7293; Dr. Farooq Ahmad
    Due to the rise of reverse engineering practices from the last two decades, worth of design engineers become highlighted. Therefore, the point of concern is the verifiability of the reverse engineered architecture, because these practices are more likely to use in safety critical systems. Hence, a prototype is needed to verify or to validate the reverse engineered design or module of the legacy system to use in further applications to evade future loss. Therefore, dynamic analysis of the system is main concern which is not possible through direct reversing from the source code. It may include multiple execution trace analysis of the system. Generating a diagram, representing the design of the application, from the code helps to study the runtime behavior of the application. However, diagrams are an informal representation of the behavior which do not support verification and validation of the application. Therefore, there is a need to generate the formal representation of the application. This research focus on the automatic generation of Petri net models from code which describe the behavior of the application as well as its verification. Moreover, generating Petri net formal model from code is a challenging task which is the focus of this research. Firstly, a systematic literature review and comparison of different reverse engineering tools will be performed to critically find out the research gap. Further, this research will proceed to provide a framework to reverse engineer the formal representation of code to understand the behavior the system
  • No Thumbnail Available
    Item
    Multi-Label Author Profiling on Multi-Lingual Text
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Samra Kanwal; SP19-RCS-011; LHR TP 6418; Dr. Rao Muhammad Adeel Nawab
    Author profiling is the task of author attributes classification where the main aim is to predict the profile and demographic features of an author which includes age group, gender, region, personality, etc., by examining the written content of the author. There are different promising applications of author profiling including security, forensic analysis, and identification of harassing text messages, marketing intelligence, and fake profile identification. In literature, the majority of the studies have been carried for single-label author profiling i.e., predicting only one single label at a time. There are very few studies available on multi-label author profiling on mono-lingual text, i.e., predicting more than one label at a time. However, the problem of multi-label author profiling has not been completely explored for multi-lingual text. The main objective of this research work is to explore the problem of multi-label author profiling on multi lingual text (English and Roman Urdu). For this purpose, the aim is to predict four author traits including gender, age, education, and language as a multi-label task using three state-of-the-art methods: (1) Content based Methods (N-gram models for both word and character), (2) Deep Learning Approaches (CNN, LSTM, BI-LSTM, GRU, and BI-GRU) and (3) Transfer Learning Approaches (BERT, and XLNET). The evaluations were carried out on three benchmark multi-lingual datasets, RUEN-AP-17, SMS–AP–18, and BT-AP-19. After extensive experimentation and comparison, the results show that the content-based method outperforms the deep learning and transfer learning methods for multi-label author profiling tasks on all multi-lingual corpora used in this study. On the RUEN AP-17 corpus the best results (Accuracy = 0.71, F1-measure = 0.65) were obtained using the word tri-gram model with the Naïve Bayes classifier. On SMS–AP–18 corpus the best results (Accuracy = 0.74, F1-measure = 0.69) were obtained using word uni gram model using support vector machine with one-vs-rest and one-vs-one classifiers, and on BT-AP-19 corpus the best results (Accuracy = 0.74, F1-measure = 0.69) were obtained using word bi-gram model using support vector machine with one-vs-rest and one-vs-one classifiers
  • No Thumbnail Available
    Item
    Detecting Real, Simulated and Artificial Cases of Paraphrasing
    (Library Information Services COMSATS University Islamaabad Lahore Campus, 2021) Ayesha Shahzadi; SP19-RCS-016; Dr. Jawad Shafi,
    Paraphrase detection is the process of identifying the use of existing text(s) as a new text in the same context with different alterations/modifications. In recent years, paraphrase detection has gained the attention of the research community due to its potential applications in different domains of NLP and Machine Learning. Paraphrasing may carry out on three use case levels 1) Real Cases, 2) Simulated Cases, and 3) Artificial Cases. Real Cases are examples from the real-world data available on different platforms, websites, e books, and over the internet on multiple topics and domains. When human manipulates the data content by using different grammatical rules and editions for paraphrasing and then claims to be original data that is Simulated Cases paraphrasing. Now the world is shifting from manual tasking to the availability of tools to modify data freely on the internet. Modifications in available data by using online tools is an example of Artificial Cases paraphrasing. To identify the use case of paraphrasing is a crucial task because, without any computational and experimental environment, no tool can identify the paraphrasing type. More importantly, Artificial Cases paraphrase detection is the most difficult task to identify. The world is lacking the standard set of examples for Simulated Cases and Artificial Cases. To fulfill this gap, we purposed one Simulated Cases corpus and three Artificial Cases corpora for paraphrasing in the English language on Sentence Level with binary classification as paraphrased or non-paraphrased. To address this problem, this study has three main goals: (1) develop benchmark corpora for simulated and Artificial Cases of paraphrasing and (2) apply WordNet-based approaches, Kull-back Libeler, and approach on Real, Simulated, and Artificial Cases of paraphrasing and (3) identify which automatic paraphrasing tools are more difficult to detect paraphrasing. We tried to contribute on the initial level, we developed a corpus for Simulated Cases and Artificial Cases from previous studies. We developed benchmark corpora as Quora Simulated Corpus on Simulated Cases, Artificial Article Rewriter Corpus, Artificial ix Rewriter Tool Corpus, and Artificial Paraphrasing Tool Corpus on Artificial Cases. Each corpus contains 5801 sentence pairs for the English language from different domains. We applied different approaches like N-gram Overlap. Kull-back Liebler and Wordnet based approaches to extract features from data on Real, Simulated, and Artificial Cases corpora. Five different machine learning classifiers like Random Forest, Decision Tree, Multilayer Perceptron, Adaboost, and Gradient Boosting classifiers were evaluated by using Precision, Recall, and F1 measure. We only reported the highest F1 scores, as AARC, ARTC, and QSC scored 85%, APTC scored 89%, and MSRPPC scored 71% results for all combined approaches.a
2025 @ COMSATS University Islamabad, Lahore Campus. All rights reserved.