Final Year Projects (FYPs) - Undergraduates

Permanent URI for this collectionhttps://repository.cuilahore.edu.pk/handle/123456789/64

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

Browse

Now showing 1 - 20 of 30

A study of ordered random variables for Reflected Power Function Distribution
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2024) Maydah Azhar; CIIT/FA20-BST-008/LHR; Dr. Riffat Jabeen; LHR TP 9953
This thesis presents a comprehensive study of ordered random variables for the Reflected Power Function Distribution (RPFD). The primary focus is on the statistical properties, parameter estimation methods, and applications of the RPFD. The RPFD is a transformation of the traditional Power Function Distribution, which is frequently used to model phenomena in various fields such as hydrology, economics, and engineering. By reflecting the distribution around its midpoint, the RPFD provides a mirrored perspective that is particularly useful for scenarios where probabilities are skewed in the opposite direction. The study begins with an introduction to the Power Function Distribution and its reflection to form the RPFD. The properties of the RPFD, including its probability density function, survival function, hazard rate function, and moments, are thoroughly explored. Various parameter estimation techniques such as Maximum Likelihood Method (MLM), Modified Maximum Likelihood Method (MMLM), and percentile-based estimators are discussed in detail. Furthermore, the thesis delves into generalized order statistics (GOS) and their specific application to the RPFD. This includes the derivation of the probability density function (PDF) and joint PDF for GOS, as well as the calculation of mean, variance, and covariance for different scenarios. The literature review highlights key studies and methodologies that have contributed to the development and understanding of order statistics and RPFD. Empirical analysis using real-life data sets demonstrates the practical utility and superior performance of the RPFD compared to other models. Overall, this research contributes to the statistical theory by providing new insights and tools for the application of the RPFD in various scientific and engineering disciplines.
ANALYSIS OF RISK FACTORS CAUSING OBESITY IN YOUTH
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2020-04-01) Muhammad Noman Sabir; CIIT/FA19-BST-013/LHR; Nasir Inayat; LHR TP 9947
This cross-sectional study examined the problem of overweight and obesity among students at COMSATS University, Lahore Campus. A random sample of 120 youths was surveyed using a well-constructed questionnaire to identify significant risk factors associated with weight issues. The students' BMI was used to assess their weight status. Cross-tabulation and multiple linear regressions were performed to analyze the data. The results showed that waist circumference, birth weight, meals during TV viewing, time spent on sedentary activities, celebration with food, parents' BMI, and breakfast skipping were positively linked to obesity. Conversely, vegetable consumption, fruit consumption, and feeling sluggish due to overweight were negatively associated with obesity. These findings emphasize the importance of addressing multiple factors in tackling overweight and obesity among youth. Implementing interventions targeting these risk factors could lead to effective prevention and management of weight problems.
BUREAU OF STATISTICS, PUNJAB
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) FIZA SALEEM; CIIT/FA21-BST-010/LHR; LHR TP 9931
The Bureau of Statistics, Punjab, operates as the principal agency for statistical data management within the province. Functioning under the Planning and Development Department, BOS Punjab is tasked with the comprehensive collection, processing, and dissemination of statistical information. This data is disseminated through periodic publications and digital platforms, ensuring accessibility and transparency. BOS Punjab’s mandate, as defined by the National Statistical Council, encompasses the collection of provincial-level data, coordination, and support of statistical activities across Punjab, and liaison with the Federal Statistical system. The organization is also responsible for preparing and diffusing provincial indicators by collecting data from various institutional sources and conducting new censuses and surveys. The Bureau’s Head Office is situated in Lahore, supported by a network of 9 divisional and 7 district field offices across the province, ensuring extensive reach and data coverage.
Calibration estimators for estimating population mean using different distance measures
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2025-04-01) Muhammad Bilal; CIIT/FA20-BST-007/LHR; N/A; LHR TP 9952
Abstract: In order to increase the accuracy of population parameter estimations based on auxiliary data, calibration is frequently utilized. To estimate the population variance, we suggested three estimators: a calibration variance estimator, a calibration exponential ratio estimator, and a calibration coefficient estimator. The suggested assessment was contrasted with those of Bhal and Tuteja (1991), Koyuncu and Kahilar (2012), and Isaki (1981). Compared to current estimators, the calibration variance estimators that are proposed perform better.
Classification of heart disease using MLP with SeLU activation function and Binary Cross Entropy as Loss function
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2024) Nouman Ali; CIIT/FA20-BST-009/LHR; Dr. Mian Muhammad Farooq; LHR TP 9954
Multilayer perceptron are the basic components of deep learning and neural net- work characterized by their architecture of feedforwading consisting of fully con- nected neurons with the non linear activation functions.This thesis provides a comprehensive overview of MLPs,by giving detailed about their structure and com- ponents,including the input layer,hidden layers, and output layer. This explains the role of weights and bias neurons in the process of learning and adjustment of the complex pattern in data. Different activation functions which are Sigmoid, ReLU, tanh, were used, illustrating their important in non-linearity and using the model to find its relationship.The training of MLPs by using the back propagation method is thoroughly studied. This includes the forward pass,where the input data is stored and processed though the network,and the backward pass, where gradients of loss function are calculated to update the network parameters. The importance of the loss estimation and parameter updates are used in minimiz- ing the error and improving the model’s performance.Additionally, we will discuss about the important steps in data preparation, which involves the handling missing values,feature scaling, and ensuring the proper data formatting. The importance of splitting the data into training and testing is highlighted, Technique for preventing the over fitting, such as regularization,dropout, and early stopping. The guidelines for using the MLP is provided, starting with the simple one and then increasing the complexity based on different tasks.This thesis focuses on the usage of exper- imentation with various architecture,hyper parameters and optimizing the model to get the optimal results. Different techniques used for monitoring the training and the adjustment of hyper parameters are discussed, along with the methods to calculate the model accuracy and loss checking and test datasets.This thesis aims to adopt practitioners with the understanding of tools to develop robust and efficiency of model on different applications such as image recognition,NLP, and speech recognition. By following the detailed guidelines and using the best tech- niques in data preparation, training and evaluation can increase the performance of model.
Construction of Calibration Log Ratio Estimator to Estimate Population Variance
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2020-04-01) Khafiza Afzal; CIIT/FA19-BST-003/LHR; Dr. Riffat Jabeen; LHR TP 9938
Calibration is frequently used to improve the population parameter estimation’s accuracy using auxiliary data. In our study, we have introduced the calibration and the calibration log variance estimator for estimating the population variance. The study proposes the calibration variance log estimators using chi square distance measure and different calibration constraints respectively. Our findings indicate that the suggested calibration variance estimator performed better than the existing estimator.
CRESCENT BAHUMAN LIMITED
(Library Information Services COMSATS University Islamabad Lahore Campus, 2024-04-02) Maydah Azhar; FA20-BST-008; Dr. Riffat Jabeen
Bahaman Limited. The purpose of this report is to demonstrate the practical application of my academic knowledge and skills in a real-world business setting. With more than 60 years of experience in industries as diverse as textiles, sugar, banking, insurance, food, agriculture and steel, Crescent Group has built a solid reputation in Pakistan's business community. Crescent Bahaman was initially formed as a joint venture between Crescent Group and Greenwood Mills. It has been wholly owned by the Crescent Group since 2001. In FY21, the Pakistan's commodities expanded by 14% insufferable from a low-base impact, coming about because of the pandemic prompted lockdown in 2020. By and large, the figures of commodities stay inside the scope of USD 22-25b, which is in accordance with the pattern of past ten years. The portion of materials in complete products has generally been 54-59%; coming in at 57% during FY21. The low-base impact was articulated in material area also, with the post-lockdown increase of around 13% in the products. Pakistan's material commodities have CAGR of 4.4% during long term period from FY19 to FY21. Inside the materials, high worth added fragment held the most extreme offer, which has been moving vertically or most recent three years, expanding from 73.9% in FY19 to 80.7% in FY21. Knitwear, readymade pieces of clothing, and bed wear comprise the significant part of this portion.
Determinants of Child Mortality in Punjab, Pakistan
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2020-04-01) Kashaf Zahra; CIIT/FA20-BST-006/LHR; Dr. Muhammad Noor-ul-Amin; LHR TP 9951
This research project examines the key determinants of child mortality in Punjab, Pakistan, focusing on factors such as birth order, mother’s age at birth, birth interval, premature birth, and multiple births. These findings indicate that firstborn and higher-order children exhibit higher mortality rates, which are attributed to inexperienced parenting in the case of firstborns and the dispersion of resources among siblings for higher-order children. The study showed that children born to mothers aged between 20-34 years had the highest survival rates than children born to mothers who are teenagers or mothers above 34 years. This means that the families mothers give birth within the age interval 20-34 are more likely to have low mortality rates hence the need to encourage family planning. It was also observed that both premature and multiple births are associated with high mortality rates hence there is a need to enhance quality perinatal and neonatal services. It is recommended that the Ministry of Health focuses on streamlined health policies, enhanced awareness of parents, and improved supply of resources to decrease infant mortality and promote general child health in the area. Integrated approaches, awareness campaigns, and the improvement of education and health care as well as the establishment of favorable policies are indispensable to tackle the multifaceted problem of child mortality.
Development Of Calibration Log Estimator to Estimate Population Mean Using Randomized Response Technique
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2020-04-01) Rehmina; CIIT/FA19-BST-011/LHR; Dr. Riffat Jabeen; LHR TP 9944
Calibration method is a useful method in daily life meanwhile it allows us to gather a single sample without repeating the process. In the presence of sensitive information, we calculate the variation of population with the help of calibration method. We proposed calibration log ratio estimator by using the method of (Jabeen, et al. 2022) in the presence of sensitive data.
Drought Analysis using Transmuted Weibull Distribution
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2020-04-01) Ali Hassan; CIIT/FA19-BST-005/LHR; Dr. Mian Muhammad Farooq; LHR TP 9940
The study aims to predict the drought analysis using monthly rainfall and temperature data. Over the past years drought is becoming important factor that is affected by climate changes in Pakistan. In this study we analyze the impact of drought in Punjab Districts. For this purpose, firstly data collected by Pakistan Metrological Department of Punjab Districts for the years 1993 to 2022 and then further competitive strategy analysis that fits our analysis or predictions are sought and critically reviewed. Then the chosen parts from strategy analysis are applied for the graphical presentation. Firstly, Applying Standardized Precipitation Index based on precipitation data by fitting transmuted Weibull distribution from the year 1993 to 2022 of each District (Bahawalnagar, Bahawalpur, Jehlum, Jhang, Lahore, Sialkot, Sargodha, Faisalabad, and Multan) to get know about classification of drought against each observed precipitation values and understand the impact of precipitation on drought. Transmuted Weibull Distribution is fitted on precipitation data to normalize it as SPI is calculated after fitting distribution on it. Further to identify trends of drought SPI calculated at different time scales by moving average of Three months, six months, and Twelve months to find SPI values and then these values are classified according to their drought conditions as moderate, severe, extreme near to normal, slightly wet, and extreme wet. Secondly applying Standardized Anomaly Index is another index that is widely used for drought analysis based on temperature data. SAI is calculated against each District (Bahawalnagar, Bahawalpur, Jehlum, Jhang, Lahore, Sialkot, Sargodha, Faisalabad, and Multan) from 1993 to 2023. By SAI values we can analyze the impact of temperature on drought. SAI values are shown in graphical form below in Chapter Results, that shows the trend and the SAI values against each year of a particular District.
EBiz Lounge (Private) Limited
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2024) Ansa Bibi; CIIT/FA21-BST-008/LHR; Dr. Tajammul Hussain; LHR TP 9929
This internship report reflects the expert encounters and bits of knowledge acquired at EBiz Lounge Private Limited. As a Statistics student at COMSATS University, Islamabad, Lahore campus this internship offered an important chance to apply hypothetical information in a certifiable setting. The active openness in the online business, especially through association with the eBay stage, extended the comprehension of computerized commercial centers and upgraded specialized and scientific skills. The essential goal of the internship was to obtain useful involvement in overseeing item postings on eBay, advancing search engine optimization(SEO) techniques, and adding to deal development. Errands included item posting improvement, leading statistical surveying, and breaking down deals execution. Every obligation added to the proficient turn of events and gave further experiences in e-commerce dynamics. Challenges, such as adapting to changing algorithms and managing multiple priorities, offered meaningful learning opportunities. This report sums up the encounters, information acquired, and skills created during the internship. It involves the tasks which are completed in the internship, challenges I faced, and the possible solutions to get successful outcomes. Ideally, this report will act as a helpful asset for understudies and experts looking to comprehend the powerful web-based business scene and the worth of viable involvement in cultivating proficient development.
Estimation of Population Mean Using Estimator Based on Auxiliary Variable in Simple Random Sampling
(2020-04-01) Umme Habiba; CIIT/FA19-BST-007/LHR; Dr. Aamir Sanaullah; LHR TP 9951
Survey sampling is a well-established methodology employed to choose a sample of individuals from a larger population. The primary objective of this study is to estimate the population mean efficiently, by employing a comprehensive approach. To achieve this, we proposed a generalized estimator up to first degree of approximation by use of one auxiliary variable under simple random sampling framework. By deriving expressions for both bias and mean square error (MSE) of the proposed generalized estimator, we are able to ascertain its effectiveness. Remarkably, our analysis reveals that the proposed generalized estimator outperforms. Furthermore, we obtained the minimum MSE of the proposed estimator, and empirical studies demonstrated that our estimator outperform than the existing estimator found in the literature in terms of efficiency. Finally it is shown that the proposed generalized estimator efficiently work.
Generalized Transmuted Exponential Distribution
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2020-04-01) BILAL MAJEED; CIIT/FA19-BST-008/LHR; Mr. Salman Abbas; LHR TP 9942
In this study, we use the Transmuted Family of distributions to develop a novel generalized exponential model. Transmuted Exponential distribution is the name of the suggested distribution. For the proposed distribution, moments, generating functions, reliability functions, among other mathematical aspects, are explored. The maximum likelihood approach is considered to estimate the distribution parameters. The use of the under study distribution in real-world scenarios is then explained. The proposed family can be used for the generalization of the classical models.
Generalized Transmuted Weibull Distribution
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2020-04-01) MOHSIN QUDDUS; CIIT/FA19-BST-012/LHR; Salman Abbas; LHR TP 9946
In this research, we introduce a new generalized Weibull distribution using a new Transmuted family. An account of statistical characteristics of the generalized model is discussed in detail. Estimation of the model parameter is followed by method of maximum likelihood. A real-life application is presented to illustrate the applicability of the derived model. This new family of distribution can be utilized by researchers for developing generalized distributions in the future.
INTERNSHIP AT AUR-LAB
(Library Information Services COMSATS University Islamabad Lahore Campus, 2024-04-02) FAZEEL UMAR; FA20-BST-002; Dr. Mian Muhammad Farooq
AUR Lab is a cooperative venture between Predominant College, as of now positioned No. 1 private for influence among private colleges in Pakistan (QS Positioning), and We-Plan, an Australian plan firm working in Pakistan. In the span of 10 months of foundation, it has accomplished the achievement of one of its startup projects being shortlisted among top two out of roughly 100+ entries from Pakistan in the Endeavor Cup Global contest. Current undertakings are managing in various business ventures, including archeological the travel industry; Metaverse; NFT Commercial center; administration and casting a ballot; Style plan; healthcare; Shrewd Agrarian; environmental the travel industry; structural plan; AR-based promoting; energy effectiveness; street wellbeing; orientation equity; also, land income. Our group of specialists incorporates specialized staff as well as business improvement staff: Dr. Muhammad Ashraf Khan; Prof. Saleem Zubair; Ms. Qurratulain Sonia Kashmiri; Mr. Muhmmad Ahmad; Mr. Jawad Ahmad; also, Mr. Javaid Iqbal
INTERNSHIP ON AUR-LAB
(Library Information Services COMSATS University Islamabad Lahore Campus, 2024-04-02) Muhammad Samran; FA20-BST-003; Dr. Muhammad Noor-ul-Amin
AUR-LAB is a collaboration between Superior University, which is presently ranked first in Pakistan for effect among private universities (QS Ranking), and we Plan, an Australian design business based in Pakistan. Within 10 months of its inception, one of its startup initiatives was selected as one of the top two out of about 100+ proposals from Pakistan in the Venture Cup International competition. Current projects include archaeological tourism, Metaverse, NFT Marketplace, governance and voting, fashion design, healthcare, Smart Agriculture, ecological tourism, architectural design, AR-based advertising, energy efficiency, road safety, gender equality, and land revenue. Dr. Muhammad Ashraf Khan, Prof. Saleem Zubair, Ms. Qurratulain Sonia Kashmiri, Mr. Muhmmad Ahmad, Mr. Jawad Ahmad, and Mr. Javaid Iqbal are among our technical and business development professionals.
INTERNSHIP REPORT AUR LAB
(Library Information Services COMSATS University Islamabad Lahore Campus, 2024-04-02) Nouman Ali; Dr. Mian Muhammad Farooq
LAB is a collaboration between Superior University, which is presently ranked first in Pakistan for effect among private universities (QS Ranking), and we Plan, an Australian design business based in Pakistan. Within 10 months of its inception, one of its startup initiatives was selected as one of the top two out of about 100+ proposals from Pakistan in the Venture Cup International competition. Current projects include archaeological tourism, Metaverse, NFT Marketplace, governance and voting, fashion design, healthcare, Smart Agriculture, ecological tourism, architectural design, AR-based advertising, energy efficiency, road safety, gender equality, and land revenue. Dr. Muhammad Ashraf Khan, Prof. Saleem Zubair, Ms. Qurratulain Sonia Kashmiri, Mr. Muhmmad Ahmad, Mr. Jawad Ahmad, and Mr. Javaid Iqbal are among our technical and business development professionals.
INTERNSHIP REPORT OF BUREAU OF STATISTICS, GOVERNMENT OF PUNJAB, LAHORE
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2024) Shafaq Ikram; CIIT/FA21-BST-021/LHR; LHR TP 9933
The Bureau of Statistics (BOS) of the Government of Punjab plays a pivotal role in the collection, processing, and dissemination of statistical data within the province. Operating under the Department of Planning and Development, BOS is responsible for ensuring that statistical activities are conducted in accordance with the standards set by the National Statistical Council. Its primary functions include the collection of provisional data in standardized formats, coordination of statistical activities both within the province and in relation to the federal statistical system, and the provision of comprehensive statistics through collaboration with various cognate institutions. Additionally, BOS is tasked with conducting new censuses and surveys to enhance the availability of reliable data. This extensive infrastructure enables BOS to effectively gather and disseminate statistical information that is crucial for informed decision-making and policy formulation. Pakistan's statistical system has its roots in a decentralized framework established at the time of independence in 1947. Initially, statistical activities were primarily viewed as a utility for administrative functions. The Central Statistical Office (CSO) was established in 1950 as an Attached Department within the Economic Affairs Division, taske
INTERNSHIP REPORT ON BAIG ELECTRICAL COMPANY (PVT.) LIMITED
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Fakhra Manzoor; CIIT/FA21-BST-009/LHR; Dr. Riffat Jabeen; LHR TP 9957
When I was working as an intern in Baig Electrical Company (Pvt.) Ltd., I was blessed to work with an organization that was electrical based and I was able to develop on several of these skills. The type of tasks included data entry and auditing; in this way, I gained knowledge of the finance department. The management practices that were explained to me were useful in realizing that people have various responsibilities within a firm. I have appreciated various aspects of how a business runs and the many roles I can take on depending on the sector. In the course of my internment, I engaged myself with multiple exercises that were entirely a new and unique experience to me. They allowed me to participate in testing processes, which provided me with practical experience that I needed. I also came to appreciate quality assurance and got to deal with transformers and switch gears, which I found out are among the company’s biggest brands in the market. This exposure has given me this information on the competition in the electrical sector. I understood the importance of product quality and safety standards in situation to the electrical field which are the critical factor of electrical products and systems’ reliability and safety. It equipped me with technical know-how in and out, soft skills as a team player, good communicator and critical thinker.
INTERNSHIP REPORT ON BUREAU OF STATISTICS, GOVERNMENT OF PUNJAB, LAHORE
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2024) Muhammad Shehroz; CIIT/FA21-BST-025/LHR; Dr. Tajamul Hussain; LHR TP 9934
The Bureau of Statistics, Government of Punjab, serves as the primary repository and hub for statistical data activities in the province, tasked with collecting, analyzing, and disseminating statistical information through various publications and media. As it is attached to the Planning and Development Department, BOS operates in accordance with standards set by the National Statistical Council. Its key functions are to collect provincial- level data, coordinate and support statistical activities across the province, liaise with the Federal Statistical System, and prepare and disseminate provincial indicators through institutional sources and new censuses/surveys. With its Head Office in Lahore and an extensive network of 9 divisional and 15 district field offices, BOS, Punjab ensures comprehensive coverage across the province. Upon gaining independence in 1947, Pakistan faced the challenge of a decentralized statistical system, where data production was closely tied to government administration rather than a centralized statistical authority. Before establishing the Bureau of Statistics, statistical functions were dispersed across various government departments, with each department's statistical cell possessing differing levels of strength, technical expertise, and skills. However, there was no centralized agency to coordinate and harmonize their activities, resulting in a lack of cohesion and consistency in statistical data collection and analysis. Recognizing the system's limitations, the Pakistan Government established the Central Statistical Office (CSO) in 1950 as an attached department of the Economic Affairs Division, based on the recommendations of the Statistical Reorganization Committee. The CSO aimed to coordinate the country's statistical activities and meet its growing data needs. As development planning gained emphasis and demand for statistical data increased, the Planning Commission recommended expanding CSO's activities, leading to the establishment of Provincial Bureaus of Statistics in West Pakistan and East Pakistan, as advised by the IBRD Mission. The Bureau of Statistics was subsequently established in October 1957 within the Power, Irrigation & Development Department of the Government of West Pakistan, tasked with providing a continuous source of statistical data, enhancing provincial statistics, and disseminating information through publications. The Bureau was later integrated into the Planning and Development Department on January 31, 1959, and declared an attached department on July 1, 1973.