Browsing by Author "Dr. Tariq Umer"

Now showing 1 - 13 of 13

A Digital Twin Assisted Disease Detection for Leafy Green Vegetables Using Federated Learning in Smart Greenhouse
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Iqra Pervez; CIIT/SP23-RCS-016/LHR; Dr. Tariq Umer; LHR TP 9703
Agricultural production is seriously vulnerable to the rapid evolution of plant diseases in greenhouse environment. In modern agriculture, ensuring timely and accurate disease detection in leafy green vegetables is crucial for improving crop yield and sustainability. The effects of environmental temperature, humidity on plant’s health which restricts the efficacy of current disease management techniques in greenhouses. This research presents a Digital Twin-assisted model for disease detection in lettuce plants, leveraging Federated-based Learning to enable privacy-preserving and distributed model training within a smart greenhouse environment. The study integrates five pre-trained models AlexNet, MobileNet, ResNet50, EfficientNetB3, and VGG16 to evaluate their effectiveness in classifying plant diseases. This study utilise a lettuce diseases dataset from Kaggle. Among the tested models, VGG16 achieved the highest accuracy of 98%, demonstrating its superior capability for disease classification in resource-constrained settings. Additionally, a correlation analysis between humidity, temperature and disease occurrence was conducted using Unity 3D and Microsoft Azure, providing deeper insights into the environmental conditions influencing plant health. The proposed model is useful for monitoring crops in real time and shows that combining Digital Twin technology with Federated-based Learning can improve decision-making in smart farming systems.
A Digital Twin based Approach for Healthier Smart City Environment
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2023) Khazina Naveed; FA21-RCS-001; Dr. Tariq Umer
Air quality, toxic substances, climate change, pollution, and occupational hazards are the environmental factors that have a great impact on human and environmental health. The presence of pollutants and contaminants in the environment can have detrimental effects on human health, including respiratory issues, cardiovascular ailments, cancer, neurological disorders, and various other illnesses. Certain groups, such as children, older adults, and individuals with pre-existing health conditions, are more vulnerable to the health impacts of environmental hazards. Air Quality Index is used to depict the air quality of an area. This thesis delves into studying the utilization of Digital Twin models as an innovative strategy for creating a sustainable smart city environment by accurately forecasting Air Quality Index (AQI) using time series analysis. The study applies different deep learning models, namely Gated Recurrent Units (GRU), Long Short Term Memory (LSTM), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and deep Artificial neural networks (ANN) for precisely predicting the AQI levels for a healthier environment. The time-series historical data of Delhi city has been gathered from the year 2015 to 2020 and is preprocessed before proceeding to train and validate different deep learning models. The six selected machine learning algorithms have been implemented and it has been observed that CNN offers unparalleled accuracy compared to other evaluated models making it highly effective for precise forecasting. The CNN-1D-2 layer yielded the best results with root mean squared error (RMSE) reaching 3.010343, the mean absolute error (MAE) reaching 1.706329, the mean absolute percentage error (MAPE) reaching 0.013216, and the R2 reaching 0.99931. The digital twin model is developed by incorporating InfluxDB and Grafana. InfluxDB is an open-source platform that has been used to store the historical and real-time data of AQI using python. The Grafana online platform is utilized for data visualization and management and facilitates real-time monitoring. The 3D model of the city is developed in Blender and then the 3D file is exported to Microsoft Azure Digital Twin explorer to develop a digital twin using Digital Twin Definition Language (DTDL). The digital twin model displays the forecasted value of AQI and different pollutants along with their previous trends in the form of graphs. The 3D model of the city is covered with different colors based on ranges or thresholds defined for AQI. The findings contribute to the advancement of smart city development by utilizing digital twin-based approaches for creating healthier and more sustainable urban environments
A Digital Twin-Assisted Hybrid Decision-Making Model for Autonomous Vehicles Behavior Analysis
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2023) Hina Saleem; SP22-RCS-005; LHR TP 8682; Dr. Tariq Umer
This thesis aims to center its attention on the development of a prototype of a Digital Twin that can be utilized for the analysis of autonomous vehicle behavior. The objective of the project was to explore the potential connection and configuration of Digital Twin and Autonomous Vehicles in order to create a visualization-based model for analyzing vehicle behavior. Two methods were employed to establish the connection between autonomous vehicles and a Digital Twin. The first method involved simulating a instinctive model using historical data to recreate scenarios. The second method involved simulating a computational model to incorporate a texture from the physical environment into the DT. In order to initiate the configuration of the DT, Carla was employed to generate states representing the ahead going speed and acceleration of a vehicle, thereby allowing for testing of the OpenModelica models. Additionally, efforts were made to increase the statistics by utilizing Carla as a realistic tool to integrate Autonomous Vehicles with Carla. This thesis introduces a configuration that introduces the concept of the DT being one step ahead of the PT. The PT, which is based on machine learning, was introduced as a means of generating similar parameters to those of a vehicle in a physical environment, thereby allowing for testing of this setting. However, the research did not inspect methods for integrating the same 3D geography in Carla and the machine learning-based simulator, which limited the experiments conducted while the machine learning simulators served as the PT. Furthermore, the statistics between Carla and OM was unable to investigate the concept of reflecting x back action to the PT. Consequently, a second design diagram, based on the knowledge acquired in this project, is presented in the thesis, with the potential for further investigation. In conclusion, this thesis presents a Digital Twin-based methodologies utilized throughout the project establish a strong foundation for future research in the development of a Digital Twin-based model for autonomous vehicles
AI-Driven Resource Allocation in Edge Metaverse for the Internet of Medical Things (IoMT)
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Saira Shairi; CIIT/SP24-RCS-023/LHR; Dr. Tariq Umer ; LHR TP 10042
Healthcare delivery is increasingly dependent on the Internet of Medical Things (IoMT), yet the rapid growth of heterogeneous devices and dynamic network conditions make resource allocation, latency control, and privacy preservation critical challenges. In modern healthcare, ensuring timely and accurate activity recognition is essential for improving patient care and enabling real-time clinical decision-making. The variability in device capacity and communication links restricts the effectiveness of conventional resource management strategies. This research presents a predictive, privacy-preserving framework for intelligent resource optimization in IoMT environments, leveraging Federated Reinforcement Learning (FRL) with a Deep Q-Network (DQN) to support distributed decision-making without exposing sensitive health data. The study integrates a Hybrid FRL-ConvLSTM model for activity recognition, enabling accurate workload prediction to guide scheduling and offloading strategies between device and edge layers. Simulation experiments under diverse workloads and network conditions confirm that the proposed approach achieves significant improvements in reducing delay, and bandwidth efficiency. The proposed model is effective for real-time healthcare monitoring and demonstrates that combining predictive deep learning with FRL-based optimization can significantly enhance reliability, and privacy in IoMT systems, it gives accuracy of 99.5% .
An Empirical Study of SQA Topics in Tester Discussions on Stack Exchange
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Nimra Ikram; SP22-RCS-004; Dr. Tariq Umer; LHR TP 9491
Software quality assurance (SQA) is becoming more and more well-known all over the world since it is crucial to the reliable and efficient implementation of mobile and web applications. Software test engineers can obtain SQA tools and frameworks like Selenium, Automation, Selenium-web driver, and manual-testing etc. Because of the popularity of SQA, software test engineers routinely discuss SQA related application difficulties on social media platforms such as Stack Exchange (SE). This study attempts to identify challenges encountered by software test engineers during the creation of SQA based apps utilizing the SE data set. Understanding software test engineers talks on SE can provide insights into the amount of time, difficulty, and popularity of SQA based difficulties. Throughout this paper, we gathered 10,593 SE postings discussing SQA difficulties. Topics are identified and arranged into categories and subcategories based on their relationships. Each topic's difficulty and popularity have been examined. Our study showed various findings. Software test engineers highlight five SQA related questions on SE: Testing Techniques, SQA Communication and Collaboration, Software Testing, UI Automation Strategies and Best Practices and Defect Management. Secondly, the topic of Test Coverage Analysis of Test Methodology (Fused_Popularity=4.50) is the most popular in the Testing Techniques topic, followed by Cross Browser and Control Handling in Database Design Testing topic (Fused_Popularity=2.57) within the Software Testing category. Thirdly, SQA based issues across all topics are rapidly expanding on SE, with new queries submitted everyday about testing tools, testing challenges, and acceptance. Fourth, Framework support, Test Automation ,and Selenium Python Web driver Best Practices are the most common categories for 'how' questions. However, many searches in other categories start with 'What'. Fifthly, SE most popular SQA topics are Software Testing (Fused_Popularity=10.8) and UI Automation Strategies and Best Practices (Fused_Popularity=7.0). Sixth, the questions for Testing Technique (Fused_Difficulty = 11.06) and Software Testing (Fused_Difficulty = 4.4) are particularly difficult than the other classification. Our empirical findings could benefit the number of those who are involved: software test engineers, and SQA researchers. Software Test Engineers and researchers can expand their understanding of new ways and create unique techniques for making difficult SQA issues easier to understand
Balancing Fertilizer Usage with Real-Time NPK Data: A Precision Agriculture Model for Sustainable Agriculture in Pakistan
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Jawad Hassan; CIIT/SP24-RCS-005/LHR; Dr. Tariq Umer; LHR TO 10036
Pakistan is facing a lot of problems in the agriculture sector as the use of imbalanced fertilizers and inefficiency of nutrients management is going to cause the very low yield of the agricultural fields. It is a matter of fact that traditional agricultural methods often lead to the inappropriate distribution of fertilizers that affects the crop yields, hikes soil infertility, and devastates the environment even more. Either more or less fertilizers usage disrupts the nutrient balance in the soil thereby creating longer agricultural inefficiencies. Utilizing real-time soil and climate monitoring and analysis can provide the technological power to deal with these challenges as AI-driven precision agriculture gains popularity. This research is dedicated to the development of an intelligent fertilizer recommendation system by using sensor-based NPK analysis that is combined with Al decision-making. This system will use prompt and accurate data from soil nutrient sensors, weather conditions, and crop requirements to provide recommendations of a proper fertilization dosage to specific fields. The novel approach seeks to minimize fertilizer wastage, to lower the environmental impact, and to maximize crop yields. The new method aims to reduce the waste of fertilizer, to keep the environmental impact at a low level, and to make the harvest bigger. One of the approaches involves the use of IoT-based soil monitoring systems to gather real-time data, training of machine learning models on historical soil and crop data for nutrient requirements prediction, and the development of a user-friendly decision-support system for farmers. This will be achieved through the provision of actional insights for the farmers who will later take the necessary course of action in their fertilizer applications. Optimizing nutrient management through the use of the new system is the way to go to stop the degradation Environmental issues like soil acidification and
Data Driven Vehicular Heterogeneity based Intelligent Collision Avoidance System for IoV
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Iqra Adnan; SP21-RCS-004; LHR TP 8056; Dr. Tariq Umer
The Internet of Vehicles (IoV) is becoming a trending field of research for researchers. Its implementation in the real world is increasing day by day to facilitate drivers in driving and provide safe road conditions to travelers to be safe from accidents. Many research studies on IoV focused on the issue of collision avoidance between vehicles on the road. Companies like the world’s biggest car company TESLA use IoV and certain machine learning algorithms to make their cars autonomous. Keeping in view the importance of collision avoidance issues between vehicles on the road. Our proposed work is to perform an analysis of real-life vehicular data based on the characteristics of different types of vehicles moving on the roads. Due to the heterogeneousness of the types of vehicles (cars, buses), their parameters are also different. From the vehicular data based on this heterogeneousness, we intended to find out the different parameters’ roles for the collision avoidance system. Using the capabilities of machine learning techniques on the gathered data, a framework for the collision avoidance system is suggested for vehicles on the roads. Performance analysis of the framework for predicting the accident well before the time for the drivers is presented for better road conditions.
Design and Development of a Secure and Light Weight User Authentication Scheme for Smart Home
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Shiza Gul; SP21-RCS-011; LHR TP 8060; Dr. Tariq Umer
The Internet of Things (IoT) is becoming more advanced day by day, in which smart homes provide different services of home to people. Users like the comfort of the use of home service that smart devices provide. But here is privacy and security in smart homes because smart devices and users perform communication across insecure channels. As smart devices with limited resources do not have the computing and storage capacity to create and execute existing methods that often require complicated computations, Smart Home Area Network (HAN) system experiences major problems in establishing strong authentication methods. Furthermore, the diverse nature of IoT nodes makes it difficult to create end-to-end device authentication in IoT systems. IoT devices commonly use poor authentication protocols. The primary barrier against numerous security attacks on IoT networks is authentication. To strengthen IoT privacy and security against frequent attacks like impersonation and replay attacks, this thesis analyses the research gaps and provides a new security mechanism and authentication technique. By providing a lightweight mutual-authentication and key exchange protocol for IoT based identity and continuously chained hash in HAN, this research improves IoT privacy and security. Using temporary symmetric keys and identities, devices may mutually authenticate and create a connection with the gateway node in an untraceable method. To verify the sender's identity, the Continuous chained-hash approach is presented (through a response challenge). The session keys are often updated after each data transmission to maintain forward secrecy. The proposed method provides authentication while ensuring that IoT device transactions cannot be tracked. Three different techniques are used to assess and simulate the security of the protocols; formal analysis that used the Burrows-Abadi-Needham logic (BAN), informal analysis, and model-checking that used the automated validation of Internet security protocols and applications (AVISPA) tool. The cost and effectiveness of the proposed method are evaluated and compared with other relevant protocols. The outcomes demonstrated that our techniques are more effective.
Design and Development of a Trust-based secure Authentication scheme for Internet of Drones (IoD) Networks
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2023) Fatima Fayyaz; FA21-RCS-004; LHR TP 8674; Dr. Tariq Umer
Drone advancement is prevailing in the latest trends in various sectors. The concept and deployment of commercial drones can provide services in different fields of life. They can be very beneficial in terms of serving industrial, agricultural, construction, packet delivery, videography, and health care providing services in managing, securing, and broadcasting operations. Diversification of networks and dynamic conditions due to heterogeneousness in types of drones and their ownership, a trust factor between these drones is a very critical issue in their intercommunication. Attacker can easily capture the data from a un-secured public channel and can misuse it against participants. Internet of Drone network protection is very important and challenging, as it ensures message integrity, message authenticity and secure authorization access. The lack of this trust factor has just left the Internet of Drones (IoD) domain exposed to security and privacy threats. The drone nodes can only establish a connection to other drones if they are considered legitimate or corporate (friendly) nodes, the rest of them will not be able to make any connection as they are non-corporate (adversary) or unauthorized. The proposed trust factor is based on a security model that establishes trust by continuous authentication and monitoring access attempts between nodes located in the corporate cluster for data delivery. Hence, a trust-based network authenticated framework is much needed for overcoming these security issues. For achieving secure data decimation and intercommunication it is highly important to create a trust-based, threat-free, environment for IOD networks and to provide the strength to security framework in vulnerable authentication schemes against different type of attacks i.e.; replay and impersonation attack, this paper analyzes the research gaps and proposes a new framework for authentication schemes. Considering the previous proposed factors and techniques, this research focuses on establishing a new architecture for providing secure authentication among Internet of Drones (IoD) environment. This paper presents the more secure framework by mutual authentication and key exchange protocol in IoD with continuous chained Hash Function. System generates temporary symmetric keys to establish connection between two nodes, hence devices can mutually authenticate and establishes connection in an untraceable manner. For the verification of sender identity, chained-hashed way is presented. Session keys between devices are updated after every transaction to maintain secrecy. The evaluation of cost and effectiveness of the proposed method with previous protocol are computed. The outcomes demonstrated that our techniques are more secure than previous frameworks.
Design and Development of Trust-Based Secure Access Control in Metaverse for Wearable Devices
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Zonash Faysal; CIIT/SP23-RCS-030/LHR; Dr. Tariq Umer; LHR TP 9707
The sudden emergence of the metaverse has expanded options for immersive digital environments, especially through head-worn wearables that function as portals to virtual spaces. But then the integration of wearables with the metaverse has some serious security, privacy, and trust implications. In this dissertation, we propose a trust- based secure access control mechanism dedicated to wearable devices inside the metaverse. The proposed approach makes sure the trustworthiness of the network by examining four trust parameters, i.e., security, privacy, integrity, and availability. The trustworthiness measurement of the system is described, and a weighted trust score is computed to measure the reliability of the system, and a comprehensive authentication protocol is designed, combining multi-factor authentication principles, encryption, certain hashing mechanisms and a session key generation process. Using the AVISPA tool, the architecture is validated and discusses the resilience to the well known attacks impersonation, replay and theft. The results give a story to the efficacy of the lightweight framework to establish a secure environment for wearables in the metaverse. This research adds to the growing bank of knowledge in the field of improving the safety, security and reliability of virtual environments for end users.
IntelliLearn: An AI-driven learning hub
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2024) Ahmad Shahzad (SP20-BSE-023); Hasham Ahmad (SP20-BSE-007); Dr. Tariq Umer
In the modern world of evolving education, IntelliLearn emerges as the modern and groundbreaking solution specifically tailor made to end the monopoly of selling past papers and helping notes. The vision is attached to AI Based learning assistance platform seeking the betterment of students and helping them in learning process in a very user-friendly way with customizable and collaborative learning. The core of the Intellilearn is to empower the students with their self learning and optimize their learning curve in an efficient and economical manner. THe traditional ways of learning from past papers or books and highlighting keywords has been the backbone of our educational methods. IntelliLearn uses the power of OCR (Optical Character Recognition) and NLP (Natural Language Programming) model technologies used for highlighting keywords and Question Generation with the help of AI based on those keywords and keypoints. This will result in transcending the boundaries of conventional reading and demonopolize the selling of past papers. This will result in broadening the boundaries of conventional reading and demonopolize the selling of past papers. Key features of Intellilearn will be user friendly design and digitization, AI-driven content highlighting and question generation, collaborative learning environment and history tracking. A student will be able to track their learning progress and customize their study sessions with the personalized learning and history tracking feature. Intellilearn will adapt to individual learning styles and will offer personalization according to students to help with their educational needs. Traditional learning methodologies have several drawdowns, lesser and incomplete availability of information and relying too much on a single textbook and academic resources. "Intellilearn," an AI-powered learning support tool, addresses these challenges by providing solutions that help students succeed in their academic goals
Multi-Pollutant based Hybrid Framework for Green Smart Cities using Machine Learning Techniques.
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2023) Usama Masood; FA21-RCS-013; LHR TP 8676; Dr. Tariq Umer
Achieving a sustainable environment is one of the most emerging issues discussed in the smart cities concept. Due to the rapid population growth in the world, the concentration of greenhouse gases is increasing day by day. A lot of research studies have focused on different techniques and technologies to reduce environmental pollution. To achieve a sustainable environment, it is important to consider the multi-pollutant factors involve in polluting the environment. In MS thesis, we proposed a multi-pollutants-based intelligent hybrid framework using machine learning that considers the multiple sources of pollution in the city environments. The research emphasizes a comprehensive comparisons of machine learning algorithm for predicting the air quality index in smart cities. In this research. The framework considers the concentration of the pollutants in the environment and will make intelligent predictions on their combined effect on the environment as well as the individual groups based on the similar characteristics of gases concerning the guidelines of WHO. The effect of the concentration of multi-pollutants on air quality and water quality will be analyzed. Machine Learning Techniques including Linear Regression, Support Vector Regression, Random Forest Regression, Decision Tree Regression, and Long Short Term Memory (LSTM) will be applied to predict air quality index and for the classification of pollutants. The evaluation measure used in this research is Accuracy, Precision, F1 score and Recall to find the accuracy of these models.
Neural Network-Based Anomaly Detection in Cryptocurrency Transactions
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Rashida Noreen; CIIT/SP23-RCS-025/LHR; Dr. Tariq Umer; LHR TP 9705
Cryptocurrency, especially the rapid growth in adopting bitcoins has led to a significant increase in fraud and illegal transactions, which faces serious challenges for financial integrity and digital trust. Methods of detecting traditional fraud are often reduced to detecting sophisticated patterns within the blockchain network due to decentralized and dynamic nature of transaction flows. This thesis presents a graph-based deep learning approach to detect discrepancy in cryptocurrency transactions, which uses a large, label dataset of bitcoin transactions collected over time. The functioning begins with the collection and prepressing of the elliptical dataset, which includes more than 230,000 edges representing more than 200,000 transactions and money flows represented as nodes. Dataset consists of three classes: license, illegal and unknown transactions. To extract meaningful insight from this data, a broad time-based and network-based feature engineering was performed. After feature engineering, the dataset was converted into a graph structure suitable for processing by the graph neural network (GNNS). Four state -of -the -art models trained and evaluated: Graph Attention Network (GAT), GATV2, Siamese GNN, Relational Graph Convolution Network (RGCN), and graph transformers. The model was trained and validated using stratified partitions to ensure balanced class representation. In the models, the Siamese GNN achieved the highest performance with an accuracy of 95.67% GAT followed closely with 94.90% accuracy, while graph transformers 94.60% and GATV2 achieved 94.46% competitive but slightly less results. RGCN showed 93.77% the least effective performance, especially struggling with unknown transactions classification. The results strongly suggest that graphs can play an important role in increasing the accuracy and reliability of the system that detects fraud in the blockchain environment, especially in accordance with dynamic and asymmetrical graphs.