Department of Computer Science

Permanent URI for this communityhttps://repository.cuilahore.edu.pk/handle/123456789/16

Browse

Filters

2020 - 202214

Settings

Subject: search.filters.subject.sp18

Search Results

Now showing 1 - 10 of 14
  • No Thumbnail Available
    Item
    Machine Learning Approach Towards Motion Planning for Manipulation
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Imran Zahoor Sajid; SP18-RCS-007; LHR TP 8353; Dr. Wajahat M Qazi
    Motion planning is an essential part of robotics. This is important for robots to perform navigational and manipulative tasks. This aims at finding a path from a start position to a goal position while avoiding collisions with obstacles. These days robots are being deployed in public places where they need to deal with uncertainty and a dynamic environment. A motion planning problem generally requires a robot to deal with a dynamic environment, uncertainty, and kinodynamic (velocity, acceleration, and force/torque) constraints. A significant amount of work has been done to solve the problem of motion planning in a dynamic environment. Numerous ways to deal with movement arranging and obstacle avoidance algorithms have been proposed. Those methods can be categorized into sampling-based, imitation learning, and biological inspired, and deep learning. Those approaches have been improved techniques and algorithms for solving motion planning problems. Even though several new efficient techniques have been proposed and many existing ones have been improved, the multitude of motion planning issues has been steadily growing. These problems involve the determination of collision-free paths, modeling of changing environment, real-time recognition of obstacles, and dynamic constraints, etc. These limitations create movement arranging issues really testing and require solid and effective calculations, procedures, and approaches. This study attempts to introduce a deep learning-based planner to Kautham which is a motion planning simulation tool for study and research purposes. Kautham uses OMPL which offers sampling-based planners. Kautham relies on these planners, so it also inherits the problems of sampling-based algorithms. We hope that a deep learning-based planner can reduce the computation time for various environmental settings and can improve Kautham performance and provide a chance to researchers and students to learn and understand deep learning planners. This work results shows that machine learning based planner computation time is less than the sampling based planner.
  • No Thumbnail Available
    Item
    Detecting Fraud Apps Using Sentimental Analysis
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) SAMEE ULLAH ( SP18-BCS-033), FATIMA FAREED (SP18-BCS-009); LHR TP 8030; MUHAMMAD SHAHID BHATTI
    Play store offers many applications, but unfortunately, its programs are fraudulent. Such applications damage the phone and can be data theft. Therefore, such programs must be found to identify fraud and theft for users. So, we will make an application that processes the comments, information, and application review. The widespread use of mobile phones and applications throughout the community has helped establish counterfeit applications among today's most prominent online threats. In addition, there are many applications with intentions of fraud available on the internet. Fake behavior is most prevalent in application stores such as the Google play store and the Apple application store. Nowadays, there are so many programs available on the internet because the user cannot always get accurate or genuine reviews about the product on the internet. In this project, we propose the system by developing a program that helps to detect fraudulent programs with comments and data learning analysis. The development of apps was expanded to millions at the play store, making the clients in a fluffy state while downloading the applications. Unfortunately, there are many apps from which any application can misrepresent, so recognition of simple applications is required. Extortion applications essentially manage counterfeit applications. Along these lines, our framework assists the client with recognizing which application is valid. We will propose a method to detect the fraud app based on user reviews and ratings of the application. The reviews will be collected from the play store and categorized into positive or negative result. The user reviews are much important in this system as they may change anytime when a user see suspicious in the application or a there may be any bug in the latest version or update of the application.
  • No Thumbnail Available
    Item
    SecurityWire
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Usama Arshad (SP18-BCS-132), Neha Imran (SP18-BCS-172), Muhammad Abuzar (SP18-BCS-131); LHR TP 8029; Tahir Muhammad
    Our project is based upon Cyber Security and Development. We will provide a platform for issues related to application and website security, either it be a software developer or a product owner, they will have a handy platform where they will have several choices to get their worthy credentials protected from any threats. Our application will be based upon an automated tool that will test any website for common vulnerabilities like OWASP top 10 bugs. We will also provide a Bug Bounty Platform that will allow website owners to connect with Security Researchers to find more logical bugs that were not found by our automated tool. The modules included in the development of this project are briefly descripted below: Automatic vulnerability scanner: As a free user, our automated scanner will look for all the vulnerabilities and only display the number of vulnerabilities it found. Paid version will display all the vulnerabilities with details it found and the suggestions to remove them. Bug Bounty platform: An automated tool can only test a limited number of vulnerabilities. Therefore, manual testing is in huge demand. We’ll have security researchers and ethical hackers registered on our App who will test websites posted by website owners or developers to get super secure websites. Upon finding a bug or vulnerability, a detailed report will be submitted on our platform. Our team will look for the validity of the vulnerability. If valid, these vulnerabilities will then be shared with the respective program owner and open complete validation with critical impact, the respective security researcher will be awarded, named, Bug bounty.
  • No Thumbnail Available
    Item
    Recommendation System
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Ibad Ahmad (SP18- BCS-159). Haseeb Yaseen (SP18- BCS-0470, Wahaj Hafeez(SP18- BCS-007); LHR TP 8023; Kanza Hamid
    Our project is a generic recommendation system, which will be varying and adopting in the environment with the passage of time. In this project, our aim is to provide an online recommendation system service, which people can use to make their experience a lot better on contrary to their experience with some other service. To find a correct, low budget orientated and location friendly service is very important and required for users but it’s not a cake walk today as there are plenty of sources which are not among those which can be reliable. As of now, lot of recommendation systems are not able to suggest users an appropriate place that map their needs. Information mismatch have a great negative impact on such recommendation system predictions. To make a customised recommended application for imparting beneficial and powerful on line services, we want mass reviews and updated data from online databases
  • No Thumbnail Available
    Item
    Automated Multiclass Liver Disease Diagnosis
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Abubakkar Siddique (SP18-BCS-121), Muhammad Ali (SP18-BCS-077 ), Umer Sajjad (SP18-BCS-081); LHR TP 8024; Kanza Hamid
    Our project Automated Multiclass liver disease diagnosis is used to diagnose normal, fatty and Cirrhosis liver diseases. The methodology that we are intending to implement, for detecting liver abnormalities in an automated manner is based on the ultrasound images. We deal with cases that are on boundaries and train such Machine learning algorithm to predict correct labels. To achieve this, created a website to predict liver disease in which we only need a liver ultrasound image and our website predict liver disease. Our trained model is Support Vector Classifier that helps us predicting Liver diseases. Our model trained on features that are extracted from relevant liver ultrasound images dataset. We extract features from each ultrasound image using Wavelet Packet Transformation techniques this feature extraction techniques help us to get high end results. Fatty and Cirrhosis liver diseases are among the most serious disorder which can’t be diagnosed at initial stages. Moreover, if these disorders are not captured initially, they may eventually lead to serious and critical circumstances. As of now, the most accurate method for the detection of most disorders of liver is Biopsy. A biopsy is a very expensive and painful method [1]. Therefore, considering all these problems, we have decided to jump into this problem and automate this complete process with the use of Machine Learning Classifier. Our proposed methodology for Automated Liver Disease Diagnosis will be a great help for poor people as it will be less expensive and ultimately providing relief from pain to the patients because they only need ultrasound images for predicting disease
  • No Thumbnail Available
    Item
    Uni-Explorer
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Rohan Mumta (Sp18-bcs 040), Maha Irfan (SP18- BCS-168); LHR TP 8028; Tahir Muhammad
    The main idea of this project is to make an application that will help students find the right university for their chosen discipline. We will be making a broad platform where students and consultants can make accounts and students can get in touch with consultants after paying a small fee for their time. Students can also search for specific universities depending upon the rating of the university, their budget or the location. Students can also calculate their merit using the merit calculator built separately for each university. Students can also take sample or mock quizzes that can help them prepare better for a specific university. The domain of the website will be limited to national universities as our key propose is to facilitate the students of Pakistan to target a better institute according to their interest.
  • No Thumbnail Available
    Item
    E-Book Application
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Amena Amer (SP18-BCS-087), Ayesha Aslam (SP18-BCS-123), Zerwah Zafar (SP18-BCS-185); LHR TP 8031; Sabeen Amjad
    As of 2011, a survey was conducted by Li within the academic domain which further proposed a study that among all survey respondents over half of the respondents preferred and used electronic books in their work. According to the research, 2 billion books are produced in the US alone annually which requires the consumption of 32 million trees. One A4 sheet takes 10 litres of water to be produced. No harm can overshadow the alarming environmental harm our planet goes through to produce paper for the books each year. It is depleting our water and destructing our planet by adding to the global warming crisis. No matter how successful a business is, there comes a time when you need to find a new sales channel. Printed books have reigned the world for thousands of years, but now it is time for it to evolve too. In this digital era where everyone is shifting towards online business, e-books have also gained immense importance amongst people. The rapid increase of e-Books has modified the interface of library catalogues by providing the members with access to more information. Rosso identified the main purpose in preferring e-books to include mobility, saving physical space, saving time and money, and ease-of-use while enhancing the learning process. A person can carry the utmost 2 to 3 books with himself anywhere to read, instead of packing a ton of books to read; he can download an e-book application so he could carry thousands of books without weighing less with him throughout the world wherever he goes. Every time a person requires reading a book, he has to go to a book shop and buy the book on his own but the e-book application enables the user to download books that save the user time of going somewhere to buy the hardcopy as well as the printing cost. Digital books let the user read his favourite books on the go with enabling him to get all the information he requires under a single screen. Hence, our final year project proposes a solution to all these problems by creating an E-book Application that has all the required features which the other applications lack and in a low pricing model. We will make a complete web application for online reading.
  • No Thumbnail Available
    Item
    Pragmatic Evidence on Android Malware Analysis Techniques: A Systematic Literature Review
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Mr Mian Muhammad Bilal; SP18-RCS-021; LHR TP 7584; Sajid Ibrahim Hashmi
    A large number of state-of-the-art studies on android malware detection and analysis techniques have been published during the last decade. A few comprehensive surveys also exist on the subject. The authors proposed different techniques, tools and frameworks to identify the malware. However, no study attempted to address a systematic review of literature on detection and analysis of android malware methods, systems, and frameworks. In this thesis, we have attempted to present a systematic review of literature on android malware detection and analysis techniques and tools. In this review study, we have identified different android malware detection and analysis methods and tools presented from 2010 to 2021 by following the guidelines of Kitchenham Systematic Literature Review methodology. This thesis presents the 75 most relevant studies out of 3343 published studies. We have determined the android malware datasets used by the android malware detection and analysis techniques. This thesis work has identified that the most used malicious datasets are Genome (39%) and Drebin (36%). We have identified the source code analysis methods in terms of static, dynamic, and hybrid used by android malware detection techniques. We have also identified the limitations and future directions of existing techniques as research gaps for the community. Based on the pragmatic evidence of this research, we have proposed a hybrid analysis based multiple feature analysis framework. This framework will not only address the limitations of static and dynamic based approaches, but it will also analyse evolving android malware datasets using deep neural network and machine learning techniques and improve the accuracy for evolving malware samples
  • No Thumbnail Available
    Item
    Task-Oriented Grasping for Manipulation
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Muhammad Usman Sarwar; SP18-RCS-027; LHR TP 7285; DR. Wajahat M Qazi
    Robot grasping is an important component to perform manipulation tasks. It is considered one of the ways for robots to interact with the environment [1]. Grasp planner plans a valid grasp for the underlying object. A valid grasp is a grasp, which prevents an object to fall [2]. The problem arises when the robot needs to grasp an object for a specific task. In this case, a valid grasp may not be a valid grasp. For instance, a robot needs to pour a liquid from one container to the other. Technically, in this case, a top grasp is a valid grasp but consider the pouring action, the top grasp is not valid. Existing methods to generate a grasp are mostly based on analytical and geometrical solutions. These approaches have performed well in generating a valid grasp, which is not a task/action specific. To generate an action-specific grasp, a robot needs to understand the task and its prerequisites. These prerequisites can be grounded on social norms or technical aspects. These norms and values act as constraints, which robots need to consider while planning a task-specific valid grasp. Induction of task-specific constraints in grasp planning requires the robot to have cognitive skillsets along with geometrical ones. The cognitive skillset requirement includes but is not limited to perception, short- & long-term memories, contextual awareness, situation awareness, semantics, and cultural understanding along with social norms. A cognitive architecture is required to put all these features into an executable framework. The challenge is to design and implement such cognitive architecture in such a way that the robot may be able to learn and perform task-specific grasp considering the given constraints. The research intends to develop such an artifact that allows the robot to perform task-specific grasp. Indeed, at this stage of research, the intention is not to develop a domain-independent task-specific grasp planner. Therefore, the application and validation of the contribution will be validated using kitchen domain objects
  • No Thumbnail Available
    Item
    Detection of Fire and Smoke from Video Sequences
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Ali Hussain; SP18-RCS-003; LHR TP 7280; Dr. Usama Ijaz Bajwa
    Since the introduction of deep neural networks in object detection, fire and smoke has been in the focus of many researchers. The recent state of the art Convolution Neural Network (CNN) based architectures provide more than 95% fire-smoke detection accuracy but in controlled environments, e.g., a fire in server rooms or production lines. Fire burns differently in certain environments; wildfires and domestic fire have distinctive characteristics and burning patterns. A fire detection system should be strong enough to better generalize different fire burning patterns. Training such a system needs a massive amount of annotated data describing unique fire patterns. In this research, a deep neural network-based fire and smoke detection system will be proposed. This network's primary focus will be consuming less training data for better generalization to achieve high accuracy with a low false-positive rate. The results have been reported using the ROC, accuracy, false positive rates