Browse
Recent Submissions
Item A METHODOLOGY FOR GLAUCOMA DISEASE DETECTION USING DEEP LEARNING TECHNIQUES(UMT, Lahore, 2020) FATIMA GHANIThe main source of the glaucoma is irreversible impairment of vision. In literature we reviewed many methods to machine learning used on fundus pictures by different researchers. Any current machine learning solutions include C4.5, the Naïve Bayes Classifier, and Random Wood. Many methods cannot more reliably diagnose glaucoma disorder. We developed an architecture focused on the methodology of Deep Learning ( DL) which is a Convolution Neural Network (CNN) for the classification of Glaucoma diseases. We used numerous deep learning neural networks such as the Inception-V3 and the Vgg16 model for Glaucoma classification and identification purposes. We have obtained 508 fundus photos belonging to 25 groups from the JSIEC, Shantou City, Guangdong Province , China, Joint Shantou Foreign Eye Centre. Since uploading the photos, we've applied the increase to the provided dataset and rendered the 1563 training and testing data collection pictures. The downloaded dataset is not labelled, so we wanted a named picture dataset for our research in deep learning. But we have labelled both photos with the class name of the disease after the augmentation. We also used two deep neural network models Inception V-3 and Vgg16 in this paper which are supervised learning methods for classification arrangements. Such structures require operating processes that need to learn to use previous knowledge , make judgments about it and fix it if any errors arise. Taking into consideration the success findings collected, it is shown that the pre-trained Inception V-3 model has the best classification efficiency with 90.01% accuracy for two other models suggested (90.01% accuracy for InceptionV3 and 83.46% accuracy for Vgg16).Item Intelligent digital twin to make robot learn the assembly process by Deep Learning(UMT, Lahore, 2020) Bilal AhmadThe fundamental objective of this thesis is to make an intelligent digital twin through deep learning for operational support of a human-robot assembly station. Digital twin, as a virtual portrayal referring to a product or system, is used for the purpose of designing, simulating and optimizing the complexity of the system under observation. For testing purposes, convolutional neural network (CNN) are integrated with a digital twin. It is used for application of a collaborative robot for an assembly application. Collaborative robots are a new form of industrial robots that are safe for humans and can work alongside humans and have received ample attraction in the recent past years for automation of simple to complex tasks. Artificial intelligence can enable us to couple the effects of machine learning and data analytics to establish a digital twin covering the whole of the lifecycle of a manufacturing system; and probe, sense and respond to its behavior. One solution that can come out of this is an adaptive behavior of robot when interacting with humans and intelligently generating robot program to perform a task. However, in a factory environment there can be a large variety of components that robot may need to handle. For the experimentation, it is exemplified with LEGO elements. The data is collected from Kaggle, where data in the imagery structure is presented. A corresponding model is developed for the purpose of classification of LEGO construction elements and attain a recognition accuracy of at least 90 percent. Significant computing power is required in the case of LEGO elements to achieve a satisfactory proficient of distinguishing in a neural network. An optimal solution is achieved by restraining the distinguishable classes up to 16. Then in Tecnomatix Process Simulate software, which is a simulation software, a digital twin of the collaborative robot was generated and was programed for assembly tasks after classification model. The data synchronization with a digital twin and an automated generation of robot program is the core developments of this thesis. This thesis aims to: ix a. Develop a digital twin (DT) of a physical robotic assembly station b. Generate robot actions in the digital twin to assemble LEGO elements c. Develop a deep learning algorithm (DLA) to learn LEGO elements d. Synchronize DLA with the DT to automatically generate assembly sequenceItem A Methodology for Power Forecasting in Pakistan Using Different Machine Learning Techniques(UMT, Lahore, 2020) Zoya ZahidOver the last decade, the energy sector has experienced a major modernization cycle. Its network is undergoing accelerated upgrades. The instability of production, demand, and markets is far less stable than ever before. Also, the corporate concept is profoundly questioned. Many decision- making processes in this competitive and complex setting depend on probabilistic predictions to measure unpredictable futures. In recent years, the interest in probabilistic energy forecasting analysis has rapidly begun, even though many articles in the energy forecasting literature focus on points or single-valuation forecasting. In Pakistan, the bulk of early studies require various kinds of econometric modeling. However, the simulation of time series appears to deliver stronger results given the projected economic and demographic parameters usually deviate from the achievements. We used machine learning methods, such as ARIMA and Long-Short - Term Memory (LSTM), to calculate Pakistan's future primary energy demand from 2019 to 2030. In this study, we used the methods used in machine learning. We have accessed the dataset of the electricity sector for forecasting purposes from the hydrocarbon development institute of Pakistan (HDIP). The dataset of HDIP is from 1999 to 2019 with different attributes like Electricity Installed Capacity (Hydel Thermal (WAPDA), Thermal (K-Electric), Thermal (IPPs), Nuclear), Energy Consumption by Sector (Domestic, Commercial), Resource Production (Oil, Gas, Coal, Electricity), and Resource Consumption (Oil, Gas, Coal, Electricity). We have forecast the energy demand of each attribute till 2030 with ARIMA technique, and LSTM. Predicting overall primary energy demand using machine learning appears to be more accurate than summing up the individual forecasts. Tests have shown that specific energy sources exceed annual growth levelsItem Employing Deep Learning to Recognize Real from Fake Urdu Signatures(UMT, Lahore, 2020) SAMAN RIZWANUrdu is one of Pakistan's official languages. It is spoken and understood by about 100 million people around the world including Pakistan and many other countries where pakistani communities have settled down. The study of methods identifying text written in Urdu script is an active research area. An interesting study approach could be to identify signatures that are written in Urdu Language. Deep learning provides many methods that can be used to address numerous computer vision problems including image classification and object detection. The state of the art method in deep learning that provides good results in computer vision is “Convolutional Neural Networks” that were introduced in 1995. The deep convolutional neural network consists of multiple convolutional and pooling layers. These layers have the ability to learn the features of the images automatically which results in better accuracy. The research proposed here employs deep learning methods to identify urdu signature samples as real or forged. As there has not been much work in Urdu Script so there was no data available online for urdu signatures. The data set was created by collecting signature samples from high school students using an offline method. The model used is a convolutional neural network (CNN) that is trained and then evaluated using urdu signature images.Item An Implementable System for Detection and Identification of License Plates in Pakistan(UMT, Lahore, 2020) Muhammad Bilal NayyarAutomated License Plate Identification (ANPR) is a large-scale monitoring system that Photographs vehicles and recognizes their license numbers. The ANPR can help Detect stolen vehicles. Stolen vehicles can be traced effectively. This research provides a way to recognize the use of the ANPR system in highways. Using different vehicles, a rear- view image of the vehicle is captured and processed Algorithm. In this context, the license plate area is located using a new function how to detect license plates that contain multiple algorithms. Whose vehicle plate image is captured by cameras and processed to capture the image License plate information. This system is implemented not only to reduce human consumption but also to facilitate human labor because of the power and its potential use of development of automatic license plate. The identification system will result in greater efficiency in the vehicle monitoring system and number plate Identification systems are used commercially, abroad and locally. This is the system Implemented using the Python Image Processing Toolbox, which uses optical characters Image identification for reading vehicle license plates. The data is collected from safe city and collect by myself locally, where data in the imagery structure is presented. A corresponding model is developed for the purpose of identification and recognition of License Plates and attain a recognition accuracy of at least 95 percent. Significant computing power is required in the case of License Plate Recognition to achieve a satisfactory proficient of recognition in a neural network. This research is a step towards smart city plan of Pakistan. In today's world where basic electronics find their place in areas like home automation, automotive automation. Automatic water storage system and so on, it will take us a little further in the smart city plan.Item Analytical Modeling for Predicting Winning team combinations for Pakistan Super League (PSL)(UMT, Lahore, 2020) Mehak FatimaT20 cricket is the popular and most exciting form of the game. Since its creation, PSL has been very successful and has created a billion-dollar industry. This is of interest to researchers in various disciplines such as data science, economics and finance. Various statistical techniques have been used in sports that affect not only the audience but also the athletes. Using various data mining techniques, predictive models were created that players can choose from. However, no substantially accurate publication has been published until now. Furthermore, the T20 league of Pakistan (PSL) has not been targeted yet, based on individual players profiles and winning teams combination. Thus, considering this issue, the present study was conducted. Herein, research was performed to develop a model that can help franchise owners to bid for talented players and build a winning team with minimum spending. The framework comprised of three main aspects, i.e. data collection, data processing and player statistics calculation, and the probability calculations. The data was collected from ESPNcricinfo and was analyzed for various statistical analyses. Based on these analyses, the probabilistic model was developed. The model achieved 90% accuracy as it was validated through actual teams of 2019 PSL which were winner and runner-up. Thus, on the basis of these results, it is concluded that the proposed model can be a beneficial tool for PSL squad selection and bidding. This model supports the process of creating teams and selecting participants in PSL. Since this study is specifically targeted at the PSL field, which has not been previously selected as a target, it is beneficial for team managers to select and create winning team combinations. The results of this study will bring huge benefits to the cricket, T20 and PSL domains, and will open up new directions for the study of cricket prediction research.Item A comparison of Deep and Classical approaches in the outcome prediction of Business Process Monitoring(UMT, Lahore, 2020) Muhammad Usman KhanPrescient cycle checking targets determining the conduct, execution, and results of business measures at runtime. It recognizes issues before they happen and re-apportion assets before they are squandered. Albeit Direct learning (DL) has yielded discoveries, most existing methodologies expand on classical machine learning (ML) procedures, especially with regards to result arranged prescient cycle checking. This situation mirrors an absence of comprehension about which occasion log properties encourage the utilization of DL methods. To address this hole, the creators thought about the exhibition of DL (i.e., straightforward feedforward profound neural organizations and long transient memory organizations) and ML strategies (i.e., arbitrary backwoods and backing vector machines) in view of five freely accessible occasion logs. It could be seen that DL by and large beats traditional ML strategies. Besides, three explicit suggestions could be induced from further perceptions: First, the outperformance of DL procedures is especially solid for logs with a high variation to-case proportion (i.e., numerous non-standard cases).Item Changing of objects into words using image captioning(UMT, Lahore, 2020) Muhammad Umair Tariq ChohanThe models of image captioning usually follow a design which is an encoder and a decoder design which use pictures and highlight vectors as an addition to the encoder. Some calculations utilizes include vectors removed from the district proposition got from an item identifier. This study uses Object Relation Transformer, expanding this methodology by expressly joining data about the spatial connection between input distinguished articles through mathematical consideration. The results obtained by qualitative and quantitative approaches show the significance of such mathematical consideration for picture subtitling, prompting enhancements for all basic captioning measurements on the MS-COCO dataset.Item LIFE CYCLE OF WORLD DYNASTIES AND THEIR RULERS(UMT, Lahore, 2020) Waseem Ahmad ChishtiThis study describes the life cycle of world dynasties and their rulers. This is the pioneering research on the subject that enlightens the key concepts and factors associated with the life cycle of world dynasties and their rulers. In this study 358 dynasties and 3802 rulers from 52 monarchies have been selected. Monarchies are selected based on three criteria. First, monarchies that currently exist. Second, monarchies ruling on large populations and third, monarchies ruling on large areas. This study explains a number of variables including reign, reign age, age, relationships between successor and predecessor or types of relations in a dynasty. Important factors such as the average reign period, age and reign age of world dynasties and their rulers are analysed. Moreover, the most important factors that helped in the continuation of dynasties and genre of relations are found. All these factors have been used to explain the life cycle of world dynasties and their rulers. In this research, the authors experimentally demonstrate that the life cycle of any political party can also be described likewise as well as the importance of cronyism in any type of government.Item Modeling Influence of Other Countries on Pakistan(UMT, Lahore, 2020) Qumer MumtazItem Evaluating collaborative tendencies of research scholars working in Universities of Pakistan(UMT, Lahore, 2020) Umer SaeedThe quality of scientific research publications has increased as a result of increased scientific collaborations. Another area that is ripe for investigation is the effect of integrating research on collaboration with a theoretical lens. Accordingly this work, using the Network theory – degree, degree centrality, closeness centrality & betweenness centrality - focuses on existence of in-house co-authorship network in selected universities and its effect on the number of publications. It also addresses how such information can facilitate recruitment and retention policies of universities. The large number of author profiles of Scopus Scholar have been crawled and analyzed in this data driven study to find the list of publications. The number of authors working in in-house collaboration who are found to build an in- house co-authorship network in Pakistan Higher Education Institutions (HEIs) is 46513 (2015-2019). Results imply that only a few universities have strong in-house co-author networksItem Machine Generated Deep Image Captioning with Style(UMT, Lahore, 2020) Muhammad AftabA powerful tool for perceiving the physical world is sight. The study of computer vision aims to provide sight to artificial agents, enabling them to understand complex visual scenes. As a core topic in artificial intelligence and machine learning it has been the focus of extensive research, but is far from solved, with humans still outperforming artificial vision systems in most tasks. Communication between humans is primarily through language. Designing an agent that can communicate via language is an important goal for human-agent interaction and for building agents that can learn from the vast repositories of human knowledge. With these aims natural language processing is a core topic in artificial intelligence and machine learning. Like computer vision, natural language processing has been the focus of extensive research, but remains an open problem. This thesis seeks to connect two core topics in machine intelligence: vision and language. Although several topics exist at the intersection.In this research focus on automatic image captioning: generating natural language descriptions of image content. Automatic captioning involves both the image understanding problem from computer vision and the natural language generation problem from natural language processing. To improve communication the researcher endeavour to add an extra layer to automatic captioning in the form of linguistic style. Stylistic variations in language have a range of useful applications, such as: reaching a broad audience, reducing misinformation, and engaging viewers. With these applications in mind the research develop and evaluate novel methods capable of generating stylised captions for natural images. Previous research into image caption generation has focused on generating purely descriptive captions; In this research the focus is on generating visually relevant captions with a distinct linguistic style. Captions with style have the potential to ease communication and add a new layer of personalisation. First, the researcher consider naming variations in image captions, and propose a method for predicting context- dependent names that takes into account visual and linguistic information. This method makes use of a large-scale image caption dataset, which the researcher also use to explore naming conventions and report naming conventions for hundreds of 9 people. Next the researcher propose the SentiCap model, which relies on recent advances in artificial neural networks to generate visually relevant image captions with positive or negative sentiment. To balance descriptiveness and sentiment, the SentiCap model dynamically switches between two recurrent neural networks, one tuned for descriptive words and one for sentiment words. As the first published model for generating captions with sentiment, SentiCap has influenced a number of subsequent works. The researcher then investigate the sub-task of modelling styled sentences without images. The specific task chosen is sentence simplification: rewriting news article sentences to make them easier to understand. For this task the researcher design a neural sequence-to-sequence model that can work with limited training data, using novel adaptations for word copying and sharing word embeddings. Finally, the researcher present SemStyle, a system for generating visually relevant image captions in the style of an arbitrary text corpus. A shared term space allows a neural network for vision and content planning to communicate with a network for styled language generation. SemStyle achieves competitive results in human and automatic evaluations of descriptiveness and style. As a whole, this thesis presents two complete systems for styled caption generation that are first of their kind and demonstrate, for the first time, that automatic style transfer for image captions is achievable. Contributions also include novel ideas for object naming and sentence simplification. This thesis opens up inquiries into highly personalised image captions; large scale visually grounded concept naming; and more generally, styled text generation with content control.Item i DEVELOP A BAYESIAN FRAMEWORK FOR PREDICTING LIKELIHOOD OF HIT MOVIES.(UMT, Lahore, 2020) MUHAMMAD USMAN MANZOORThis study proposes a framework for predicting likelihood of producing a Hit film by implementing probabilistic inference. We propose the Bayesian networks properties are efficient for the problem in hand. We implemented a Bayesian network model to build Stars recommendations system, which is very uncertain in nature. Bayesian Network is Custom-made to the problem in hand. We examine the process through which stars affects the chances of getting an award in film fairs on individual basis and also in group. We performed the Bayesian Network model on the data sets of Lollywood movies and Lux Style Awards from 2002-2019 and the data for the analysis was consisted of all Urdu movies which were released between 2002-2019. The author prepared all the data sets from three different sources which includes IMDB, PAKDB, and PAKMAG and then verified all the data. There were total 239 movies which were part of our initial data set. Our Training Data set was consisted of total 214 movies, 619 stars, and our Test Data set was consisted of 25 movies, which were part of Lux Style award 2019. The Authors validated the model by applying the model on all the movies on the Test Data set on all 25 movies, whether they obtain an award or not. The authors also examine the process through which stars affects the chances of getting an award by Lux style award, that is, whether they influence the movie at least to be selected as a nominee or the best case to get an award. They find that star power influence the success of a film and plays its role. The chemistry between stars also plays key role on screen and is significant factor in the success or failure of the film. The authors also generated a costar network for all the stars and showed the degree of centrality and the closeness centrality as well.Item IMPACT OF WEATHER ON COVID-19 IN METROPOLITAN CITIES OF PAKISTAN: A DATA-DRIVEN APPROACH(2020) MEHAK NARMEENABSTRACT The occurrence of severe acute respiratory syndrome coronavirus 2 disease (SARS-CoV-2 or COVID-19) in China at the end of 2019 has affected a lot of lives and created a chaos in the world. No country was safe from its disastrous impact. It also started impacting metropolitan cities of Pakistan and has spread quickly nationwide in the first quarter of the year 2020. As high temperature reduces some of the viruses, for example, influenza, likewise it was believed that it would aid in restricting the spread of Coronavirus (Covid-19) as well. This study is determined to explore the influence of meteorological factors on the spread of COVID-19 in metropolitan cities (Islamabad, Karachi, Lahore, and Peshawar) of Pakistan and forecast its spread. These cities reported a significant number of cases considering data till June 3, 2020, when the weather gets hotter than normal days plus the humidity. Variables such as confirmed cases, fatalities, recoveries, and transmission type is employed for the study. Our results confirmed that temperature and humidity had not affected the transmission of the virus in these cities. A forecast was also produced using Facebook's Prophet Library to predict a trend in the coming days. The points predicted we are out with an average of 8.37% for the whole country from the actual value. Thus, considering the results obtained, policies announced by the government should be followed to prevent the rapid increase of the outbreak, the possible pressure on the health system.Item Predicting Depression Using Transfer Learning – ULMFIT(UMT, Lahore, 2020) Amna GhaffarRecently the usage of social media is increasing day by day. The use of social media sites makes it easier for people to express their interests, feelings and their daily life. According to the recent researches it is proven that using user-generated content (UGC) in a correct way can help in determining mental health levels of people. Here our focus is to collect the data from microblogging website, Twitter and Time to Change website. The aim is to apply Inductive Transfer Learning method to predict depression accurately by leveraging the data from the above mentioned sources. For this purpose, we’ve used state-of-the-art Inductive Transfer Learning model, ULMFiT and compared it with traditional machine learning model Linear SVCItem Measuring Emotional Response through Neuromarketing: Study of Advertisements and Its Influence on Customer Purchasing Choice(UMT, Lahore, 2020) Tabassum BashirThis current research is aim to study the Measuring Emotional Response through Neuromarketing Study of Advertisements and Its Influence on Customer Purchasing Choice. The objective of this thesis is to initiate development of a valid and reliable measurement process to assess a viewer's emotional response to television advertising through neuromarketing. The development of this measure is based on current psychological theories about the emotional process, and takes advantage of current methods available to measure emotional response. The goals for the measurement process are to provide information on emotional response to television advertising from two diverse sources, automatic real-time response, and cognitive after-the- fact responses. The selection of instruments to meet these goals first involved a review of the psychological literature on emotional theory to provide direction on defining what an emotional response is, and how the emotional subcomponents relate. This provides direction for evaluating the instruments available for measuring emotional response through neuromarketing, and selecting two that will satisfy the above goal. The use of these measurement instruments in a pretest is then outlined, and the thesis concludes with directions for future research. The usefulness of combining measures should be explored through a pretest. In designing the pretest, the success in capturing specific emotional responses attributable to the advertisement will depend on the setting used, the selection of advertisements and the program these advertisements are embedded in. The setting should copy a normal viewing environment to encourage normal behavior in subjects. The advertisements used should maximize the variability in emotional response, while being new to the subjects to avoid frequency biases. The program should be carefully selected to avoid content effects To structure and delineate areas for new research, emotional response to television advertising can be approached from the viewpoint of what could impact or influence the response. This leads to the definition of the following areas of influence: the advertisement; the group of advertisements the advertisement is placed in; the program; the viewing environment; and the viewer.