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
9 results
Search Results
Item Neural Abstractive Text Summarization for Urdu Language(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Adnan Sanaullah; FA18-RCS-012; LHR TP 8343; Dr. Muhammad Waqas AnwarText summarization achieved a lot of popularity in natural language processing because of the large amount of literature available on internet, especially for English language. Nowadays, most used technique is abstractive text summarization in which generated summaries are quite related to the human-written summaries. In this research, to create the summaries for the Urdu language the abstractive text summarization technique is used. In this technique, the Attention based sequence to sequence encoder decoder model are used to create the summaries. For the training of model for Urdu Language, two dataset which are BBC Urdu Dataset and Urdu News 1M are used. In order to evaluate the model, ROUGE metrics are used in which the model generated summary and human-written summary are compared and then performance of the model is measured. After training the model on both datasets, there is the quit the difference between the results of both the datasets which is due to the size of dataset. Although the model got 42.85 rouge-1 score on BBC Urdu Dataset and 66.67 on Urdu News 1M Dataset. Our model shows promising results on both the datasets but if the size of dataset increases the model performs better. We also discussed the problem faced during the completion of research and results of the model in this research workItem A Deep Learning Model for Efficient Effort Estimation in Scrum Projects(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Ahmad Amjad; FA18-RCS-028; LHR TP 8041; Dr. Farrukh ZeshanSoftware Development Effort Estimation (SDEE) is defined as the process of predicting the effort required to develop a software system. Effort estimation at the earlier stage in scrum project is specially a challenging task because the requirements are volatile in nature and it can be changeable at any phase of the whole project life cycle. A project manager needs estimation for making a decision and predicting the total budget. The success or failure of software development depends on the accurate estimation of efforts required to complete a project. In literature, the three basic ways are explored for efforts estimation in scrum projects which are purely model based method, the expert-based methods and hybrid-based methods. In the model-based method the data collected from similar previous project to make prediction about the new project, the expert-based method totally dependent on human expertise to make such kind of judgement whereas the hybrid method are the combination of both model based and expert based methods. Every method has different challenges but in the era of agile software development methodologies, traditional planning and software effort estimation methods are replaced to meet customer’s satisfaction in agile environments. However, software effort estimation remains a challenge. Although teams have achieved better accuracy in estimating story points effort required to implement user stories or issues, these estimations mostly rely on subjective assessments, leading to inaccuracy and impacting software project delivery. Some researchers are pointing good results by the adoption of deep learning to address this issue. Given the foregoing, this study proposes a deep learning model for story points estimationin t h e scrum projects. In this study proposed a model which used the combination of Bidirectional LSTM and Recurrent Highway Network two powerful deep learning techniques using the story points for efforts estimation in the scrum projects. The proposed model is trained over a large d a t a s e t s for story points estimation made by 16 open-source projects which have 23313 issue that are large story point datasets according to my knowledge. The performance of the proposed model has validated through the evaluation techniques such as Mean absolute error (MAE), Mean square error (MSE), and Median absolute error (MdAE). The results shown that the proposed model provides betters result as compared to previous approachesItem Fake News Detection for Urdu language using Machine Learning Techniques(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Ahmad Raza Khan; FA18-RCS-005; LHR TP 7587; Dr. Hasan JamalThe main target of this research is to detect fake news in Urdu language. Although many studies have already been conducted on fake news detection for different languages but not much work has been done for Urdu language and there is a research gap for fake news detection in Urdu language. To compare, evaluate and develop a fake news detection system for Urdu language, standardized and high-quality benchmark resources are needed but unfortunately corpora for Urdu language are not available, even though Urdu is a morphologically rich language and has more than 300 million speakers all over the world. To compensate for this gap, we develop a novel high quality, and a large-sized benchmark corpus for Urdu fake news detection. Only one benchmark dataset is previously available for fake news detection tasks in the Urdu language that contains a total of 900 news articles in which 500 are real news and 400 are fake news articles. Our novel corpus contains 1800 news articles out of which 1000 are real news articles and 800 are fake news articles. Our dataset contains five domain data (Business, Health, Showbiz, Sports, and Technology). These news articles are tagged manually into real and fake news tags. These news articles are collected from different authentic news sources. After corpus creation, feature extraction is performed using different combinations of word n-gram, character n-gram, and function n-gram. The range of this n-gram varies from 1 to 6 for our experiments. We use different weighting schemes such as Term Frequency-Inverse Document Frequency (TF-IDF), Log entropy, Binary weighting schemes, etc. After extracting features from the text, state-of-the-art machine learning techniques are applied to the corpus to evaluate the fake news detection system. In machine learning techniques, Multinomial Naïve Bayes (MNB), Linear Support Vector Classifier, Logistic regression, Random Forest, Decision Tree, Bernoulli Naïve Bayes (BNB) and Ada-Boost are used. Each classifier is trained and tested separately. Standard evaluation measures are used to check the working of the fake news detection system i.e., accuracy, precision, recall, F1-score. We compare our results with previous research results and Linear SVC and Logistic Regression outperforms other classifiers.Item Human Activity Recognition Based on Multimodal Sensor Data Fusion using Deep Neural Networks(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Saad Ahmed; FA18-RCS-027; LHR TP 7588; Dr. Allah Bux SarganoIn recent years, Human Activity Recognition (HAR) has been one of the core research areas due to its various applications. It has been attracting growing attention in the computer vision field. In HAR, activities are normally represented using numerous sensor modalities, like vision, inertial, skeleton, audio, etc. However, there are limitations associated with these sensors like Local barriers, image barriers, sensor unreliability, and consumer concerns. Multimodal Human Activity Recognition (MMHAR) solves these problems by using more than one modality sensor to enable the complementary information of different domains in the recognition task. Recently, various Deep learning-based approaches have been proposed for MMHAR and have achieved state-of-the-results. Though great efforts have been made in this area using various modalities, little attention has been paid to the analysis of the dominance and relevance of one modality over another. This research work highlights the importance of multimodal-based sensor fusion using deep neural networks to achieve HAR and highlights which modality has more importance in recognizing activities. This research work proposes a novel deep multimodal fusion network based on two-stream architecture. One model stream uses the Three-dimensional Convolutional Neural Network (3D-CONV) to handle the depth sensor data. At the same time, the second stream of the model uses a Two-dimensional Convolutional Neural Network and Long Short Term Memory (2D-CONVLSTM) for handling the inertial sensor data. Both streams capture features from data generated through depth and inertial sensors. Decision level fusion combines the results generated from both streams to get the final prediction. The proposed model has been evaluated on a publicly available benchmark dataset Berkley MHAD (Multimodal Human Action Detection) and has produced state-of-the-art accuracy of 99.73%, outperforming the previous methods. The depth sensor and inertial sensor data are passed to the proposed model streams separately in a Single modality-based Human Activity Recognition (SHAR) process. It is observed that the depth camera sensor achieves a higher accuracy result of 98.89 % than an inertial sensor accuracy score of 89.34%. x Hence, it is concluded that the depth camera sensor has more importance in the recognition task than inertial sensor datItem Cross Domain Sentiment Classification for Urdu Language(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Sana Hassan; FA18-RCS-010; LHR TP 6410; Dr. Muhammad Waqas AnwarAn enormous amount of information is produced daily on the internet about different prod ucts and objects. People like to express their feelings, thoughts in their native language on different social sites. This bulk data needs to be interpreted. So, Sentiment Analysis (SA) is required which extracts people’s opinions, feelings, and thoughts. However, it is a highly domain-dependent task. Due to this, the issue of domain-transfer arises. If a classifier is tested with any different domain, other than on which it is trained, its performance is affected. Many tasks and frameworks are created in mostly English and western languages. Tasks intended for the English language cannot be applied for other languages, hence there is a need to work on different dialects. In this research, we performed a cross-domain sentiment Analysis on data set of Urdu language comprising of 9000 sentences from sports tweets in which there are two domains (Hockey and Cricket). Furthermore, preparing corpus for specific domains in the Urdu language we applied ma chine learning and deep learning approach. After this, we evaluated results using standard evaluation measures and a confusion matrix, Gated Recurrent Units (GRU) gives the highest accuracy of (77%)Item Predictionof the user's future location based on past Trajectories(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Umar; SP18-RCS-018Nowadays the use of technology is very common in human life and a large number of people have cell phones, PDAs, or fitness wristbands for their personal use. These modern devices have many powerful applications based on their hardware specifications. GPS hardware module is commonly available in all the above mentioned devices and it generates the GPS log data which are the key points of movement patterns for the individual. It is believed that continuously capturing the user GPS log data and then mining the trajectories patterns can be useful to predict the future location of the user. And it is useful in Smart Advertisement Campaign, Intelligent Transportation System and Smart Reminders, etc. Several studies have been carried out on monitoring the user's location. But there are some deficiencies regarding the individual to collective and even hybrid prediction. However, these studies have not utilized the user's daily routine trajectory patterns for assistance. This work aims to extract the meaningful trajectories patterns from large GPS data of daily routines which may be useful for the prediction of the next possible movement activities of individuals. The dataset which is used in this research is Geolife Trajectories in which 182 users' data captured over three years. There are 17,621 trajectories recorded by mobile phone GPS.In this research,the Hidden Markov Model(HMM) and K Means Clustering are used for the future prediction ofan individual’s movement. The proposedwork is concentrated on the user's past day routine as well as time frame. The model uses these parameters as input and able to give results like “Where is the person physically present when it is a Friday?” or time and day bounded queries like “Where is the person physically present between 5:00 pm to 8:00 pm on Sundays?”.The experiment is conducted over the 182 user’s data and achieve the individual accuracy is upto83% as well as combined accuracy is an average of 35.64% recorded.Item Developing a Urdu Lemmatizer Using Dictionary Look-up Approach(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Saima Shaukat; FA18-RCS-009; LHR TP 5987; Dr. Rao Muhammad Adeel NawabLemmatization is the process of finding the root form of a word. Lemmatization is used as preprocessing step for most of the NLP applications. Lemmatization is im portant part of NLP applications which involve the use of root form instead of using derivational forms of words. Text mining, information retrieval systems, document clustering, search engines and text categorizations are few of the applications where lemmatization process is used. Urdu is a widely spoken language in the world, but very less work has been done on developing basic NLP tools for this language, one of them is Urdu lemmatizer. Since Urdu is a morphologically rich language and has words with many inflectional and derivational forms, development of an efficient lemmatizer is a challenging task and it will be useful for many Urdu NLP applications. These challenges help us to choose the customized and more appropriate approach for Urdu lemmatization which is dictionary-based approach. The main aim of this research work is to develop an Urdu lemmatizer. To develop the efficient Urdu lemmatizer, we used dictionary look-up approach. Majority of exist ing lemmatizers are of in English and other European languages. Most of the existing lemmatizers are rule based and also the information about parts of speech tags is ig nored. Development of large dictionaries for Urdu Language is also missing in existing work. To fulfill this gap, the main goals of the study are: (1) Develop a large bench mark corpus for the Urdu language and (2) Explore the relationship between parts of speech tag and lemmatizer (3) Developed the standard approach for Urdu lemmatizer. The first major contribution of this study is the development of a large benchmark Urdu dictionary. The proposed corpus was developed in the following steps: (1) In the first step we collected data from two different sources: urmono corpus and Wikipedia dump (2) Preprocess and tokenize the collected data (3) extract the frequency of each word using python script (4) Selection of most frequent words (5) Assign parts of speech ix tags to selected words (6) manually annotate data (assign lemma to each word) (7) De velop a benchmark corpus and save in a standard csv format. Second major contribution of this research work is exploring the relationship be tween POS tag and lemma of a word. Train the POS tagger on collected Wikipedia dump and then used in the development of Urdu lemmatizer because user can enter input with or without POS tags. If user will enter input without POS tag, tagger will assign most frequent used tag to the word before generating lemma of a word. As a third major contribution of this research work, proposed a dictionary-based approach for Urdu lemmatizer. As the Urdu is morphological rich language; it also includes many Persian, Turkish and Arabic words. So, for the efficient lemmatizer, dictionary-based approach is more suitable. The evaluation was carried out using two techniques (1) With-POS-DLA (2) Without-POS-DLA. We achieved accuracy of 66.79% and 76.44% respectively. The best result is achieved by using Without-POS DLA technique.Item Author Region Identification for Urdu Language(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Rehman Akram Chughtai; FA18-RCS-007; LHR TP 6407; Dr. Rao Muhammad Adeel NawabAuthor region identification is a subtask of author profiling which intends to identify the region of the author, based on the written text. Identification of author region may improve content recommendation, security, reduction in cyber-crimes due to its different applications in fake profile detection, content recommendation, sales and marketing, and forensic linguistics. Lot of work has been done on several author profiling tasks in English, Arabic and other European languages but no significant work found on author region identification task using Urdu language. To fill this gap, we proposed a large benchmark corpus and methods to predict author’s region using Urdu language articles. The proposed corpus consists of 12,100 Urdu articles written by authors from different regions. These articles are categorized into three different regions i.e. Pakistan, India and others. There are 5000 Urdu articles for Pakistan region, 5000 Urdu articles for India region and 2100 articles for Others category. For each article, article web links, author name and domain of each article is mentioned for future research purposes. To demonstrate how our proposed corpus can be used for the development and evaluation of author region identification for Urdu, I applied different classical machine learning and deep learning approaches. For classical machine learning, I used word n-grams technique for feature extractions and then applied classifiers i.e. Logistic Regression, SVM, Naïve Bayes, Random Forest, Adaboost and Gradient boosting for multi classification task. For deep learning algorithms, I applied CNN, RNN, LSTM, Bi-LSTM, and GRU on proposed corpus. Evaluation was carried out using accuracy, weighted precision, weighted recall and weighted F1-measure as evaluation measures. Experiments show that the best results with accuracy of 85 % is achieved by classical machine learning approach using SVM classifier on 3000 features with word n-gram [n ranges from 1 to 3], while for deep learning approach CNN with 1 layer outclass other classifiers with accuracy of 96 %. Deep learning CNN method performed best among all classical machine learning and deep learning methods for author region identification task on proposed Urdu articles corpus.Item Neural Architecture Based Urdu Named Entity Recognition(Library Information Services COMSATS University Islamaabad Lahore Campus, 2020) Muhammad Ehsan; FA18-RCS-018; LHR TP 6413; Dr. Muhammad Waqas AnwarIn natural language processing, named entity recognition (NER) is the issue of figuring out and arrange named elements referenced in unstructured content into pre-characterized classifications. To compare, evaluate and develop a NER system, we need standard and high-quality benchmark resources. But unfortunately, corpora in a huge amount are available for many other languages but not for the Urdu language. Even though Urdu is a rich language in all aspects and has more than 300 million speakers all over the world. As state-of-the-art sequence labeling systems are heavily based on large amounts of domain specific knowledge and hand-crafted feature for efficient learning from small data. When the dataset is in a large amount and high quality then the Named Entity Recognition (NER) task can be solved in a better way and provides better results on a large amount of labeled data, but the availability of labeled data in most of the languages is limited for training purpose. One way is there are scarcely any limitations on identifiable words. Hence, concluded the little amount of exampled data is troublesome. Subsequently, deliberately built orthographic features and language-explicit information assets (e.g., gazetteers) are broadly utilized for understanding this undertaking. Tragically, for new languages and new domains, the task of identifying explicit language sources and feature extraction is mainly an expensive process. As a result, it makes efficient NER system development adaptation a challenge. Another way to makes an efficient NER system is the use of deep neural network models that have achieved highest performance in the domain of natural language processing (NLP). However, this performance highly depends on the availability of huge amount of annotated data. The other way to get a better generalization from a small amount of data is to deploy semi-supervised models that performs on small set of annotated examples and a large set of unannotated data. Due to limited annotated data for many Natural Language Processing (NLP) problems like NER for the Urdu language, we will solve the NER problem using deep neural algorithms. In deep learning methods, we perform 44 experiments by using recurrent neural network (RNN), long short-term memory (LSTM), Bidirectional LSTM, gated recurrent unit (GRU), Bidirectional GRU and GRUCell in a supervised learning setting to compare with ix the previous models. Our model outperformed the previous results with F1-score of 91.43%. We also use multi-layer perceptron in a semi-supervised setting. This model gives the results with F1-score of 51.00%. We use standard evaluation measures to check the performance of the NER system. However, deep learning results with semi-supervised settings unable to beat the results of deep learning results with supervised settings.