http://hdl.handle.net/123456789/100 2026-04-04T12:04:29Z 2026-04-04T12:04:29Z Khatri, Tarwan Kumar http://hdl.handle.net/123456789/8911 2019-08-08T07:01:38Z 2018-01-01T00:00:00Z

A HYBRID APPROACH FOR EMERGENCY FEEDBACK SYSTEM USING BRAIN COMPUTING INTERFACE Khatri, Tarwan Kumar In the advancement of the technology, humans have been used as a part in brain computing interface field. BCI provides a communication pathway between wired brain and extraneous devices using electroencephalography (EEG) signals. EEG is the signal technique in BCI field which is used to track and record brain patterns from surface of the scalp using different electrode locations which sends the signal to computer to record results. In the BCI research field, Neuro-prosthetics applications are focused primarily, which purposes is to restoring discredited hearing, visual perception and apparent movement of organs. Brain Machine Interface has turned to a great research field that consists of many challenges in neurobiology. Patients in a locked in syndrome (LIS) on account of wicked neurological disorders involve unseamed emergency care by their caregivers or guardians. Nevertheless, it is a very hard job for the guardians to endlessly monitor the patients’ state, particularly when there is no possibility of direct communication. There have been existing research studies to enforce P300, Steady State Visual Evoked Potential (SSVEP) and Hybrid speller applications which have not been validated on patients with LIS diseases. Hence, their clinical value has not been validated. They worked on spelling the characters, words, cursor movement, and spelling of numerical values. In the present study, an Emergency Feedback System has been developed for such patients using Hybrid approach which consists of combination of Steady State Visual Evoked Potential (SSVEP) and P300 Event Related Potentials (ERPs). In order to affirm the usability of System interface, three Healthy participants have been invited for experimentations. Further, three LIS Patients have been invited to check the clinical feasibility of Emergency Feedback System. All the Healthy participants and LIS Patients have succeeded in providing commands to our Emergency Feedback System precisely. The average accuracy to perform a single session has been reported 88.32% for all Healthy participants while the average accuracy to perform a single session has been measured 85.66% for all LIS Patients. Beside these, the average time required to execute a command has been measured 14 bpm for all Healthy participants while for the LIS Patients, it has been reported 6 bpm per command. Supervised by Dr. Humera Farooq

2018-01-01T00:00:00Z Zeeshan, Muhammad http://hdl.handle.net/123456789/8912 2019-08-08T07:03:42Z 2018-01-01T00:00:00Z

AN ONTOLOGICAL APPROACH FOR GENERATING ADAPTIVE CONTENT IN A CONTEXT-AWARE GAME-BASED INQUIRY LEARNING ENVIRONMENT Zeeshan, Muhammad Context-aware game based inquiry learning is considered as one of the promising strategies for enhancing the learning process. Participants are encouraged to learn from their environment in the form of small tasks because they physically interact with the objects in their environment. With the advancement of ubiquitous technologies, visitors of any location or site can use their smartphones along with sensor devices to collect information from their environment and learn about the exhibits using context-aware inquiry learning strategy. Information is always available in environment for the visitors but due to lack of interest or guidance, they are unable to learn and cash the available information. Therefore, we need a system that aims to provide assistance and guidance to the end user in learning process. Moreover, the system also aims to make the learning process more interesting for end user by using game based strategy. For this purpose, we developed MUSEON, an ontology and game based context-aware mobile learning approach. Thus, the aim of this research is to develop an intelligent context-aware mobile learning approach which retains the fun factor for the visitors by enhancing their learning performances. For demonstration and evaluation of the developed system museum environment is used. For the evaluation purposes, an experiment with visitors of Pakistan Maritime Museum was conducted. The participants were divided into two groups i.e. experimental and controlled group. Experimental group learn with the guidance of MUSEON while controlled group learn by using conventional learning methods. The results proved that ontology-based context-aware game based inquiry learning has significant potential and influence on the learning performances of the visitors while comparing with the conventional learning methodologies. Supervised by Dr. Sohaib Ahmed

2018-01-01T00:00:00Z Khalid, Muhammad Noman http://hdl.handle.net/123456789/8913 2019-08-08T07:05:14Z 2018-01-01T00:00:00Z

A COMPARISON AND EFFECTIVE PENETRATION TESTING APPROACHES WITH NMPREDICTOR BASED ON MACHINE LEARNING Khalid, Muhammad Noman Vulnerabilities are known to be difficult to detect and prevent, especially in the context of web application. Although a significant research on web application security has been ongoing for a while, these applications have been a major source of problems and their security continues to be challenged. An important part of the problem derives from vulnerable source code of web applications. In order to overcome web vulnerabilities, different penetration tester used variety secure programming, static analysis, dynamic analysis, hybrid analysis of techniques such as and machine learning. Machine learning is consider an approach to prevent web vulnerabilities with a wide range of web applications because it is more preferable and does not have problems of false positive rate. There are numerous method proposed for detecting web vulnerabilities based on machine learning. It is very difficult to measure, which method is efficient to secure web application. Furthermore, there is lack of study found that targets the comparison of machine-learning method.to Find out optimal method. However, comparative study is required to understand the six differentpath that could be followed by different penetration tester. In this thesis we use machine learning. In order to fmd optimal method for existing studies, Drupal metrics file With J48 and random forest. We have implemented . methods based on decision were taken on NMPREDIGTO^. method with the feature extraction, performance parameters, classifiers with default parameters and 10k cross validation. Training data is passed through J48 and random forest to form a training model on which testing data is predicted and analyzed. Our results state that, to prevent web vulnerabilities VULPREDICTOR shows better results as compared to all others methods. We have found much higher accuracy of NMPREDICTOR method with respect to those reported by existing studies. Supervised by Dr. Humera Farooq

2018-01-01T00:00:00Z Bashir, Fatima http://hdl.handle.net/123456789/8910 2019-08-08T06:53:26Z 2017-01-01T00:00:00Z

AN EXPLORATORY STUDY OF STUDENTS’ LEARNING PERFORMANCE IN FLIPPED CLASSROOM USING DECISION TREE Bashir, Fatima With the advancement in technology, educational systems have paved the way in order to provide effectiveness in classroom learning environment. Flipped Classroom model is of the most effective and influential methods that follows student-centered approach. It enhances students’ learning outcomes and create a motivational level through conducting learning activities during in-class sessions. This study is divided into two segments, to accomplish predictive analysis of students’ performance based on overall assessments and to explore effectiveness of two models by comparing students’ learning outcome through both flipped and traditional classrooms and evaluate which model help students more to captivate during the course. To perform predicative analysis, we have implemented decision tree classifier that help instructor to evaluate and predict student’s learning outcomes based on their overall performance before final exams. The focus group during this study were student of MBA enrolled in strategic management course. The focus group was further divided into experimental and control groups representing both teaching learning environment, flipped and traditional classroom respectively. The results found in this study reflects that students learning capability increased though the flipped learning approach as compare to traditional way of teaching. To further support our experimental results a questionnaire was conducted with experimental group that reflects promising results. Predictive analysis performed during our experimental study produced satisfactory results with effective accuracy. Supervised by Dr. Sohaib Ahmed

2017-01-01T00:00:00Z