Department of Electrical Engineering
Permanent URI for this communityhttps://repository.cuilahore.edu.pk/handle/123456789/18
Browse
4 results
Search Results
Item Landslide Monitoring Using State of the Art Machine Learning Techniques with Image Processing of Space Borne Remote Sensing Imagery Data(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2024) Mohammad Mazan; FA21-REE-003; Dr. Muhammad Farooq-i-Azam; LHR TP 9366Landslides present significant worldwide difficulties, leading to profound repercussions such as property destruction and human death. As a result, the methods we currently have, including light detection and ranging (LiDAR) and on-site assessments by experts to look at things like topography, ground fractures, slope stability, and changes in vegetation, are not good enough to accurately predict and prevent these events. The rising frequency of landslides worldwide, intensified by alterations in weather patterns and human actions, underscores the necessity for sophisticated alert and surveillance tools. Landslides can result in devastating outcomes, such as fatalities, displacement of individuals, and significant economic repercussions. Technological advancements, namely in machine learning, remote sensing, and image processing, provide promising options to improve landslide prediction and mitigation efforts. This work aims to address the critical issue of evaluating and predicting landslides, with the objective of creating a dependable approach. We extract landslide causative factors from remote sensing imagery data through image processing, compile them into a single dataset, and then use this dataset to train machine learning algorithms. The landslide causative factors included in our dataset are the Topographic Wetness Index (TWI), Peak Ground Acceleration (PGA), Stream Power Index (SPI), Terrain Ruggedness Index (TRI), Normalized Difference Vegetation Index (NDVI), curvature, elevation, faults, rainfall, geology, solar radiation, aspect, landcover, slope, streams, and roads. We tested how well different machine learning algorithms could predict the risk of landslides. These included Logistic Regression (LR), Random Forest (RF), XGBoost (XGB), AdaBoost, Long Short-Term Memory (LSTM) networks, Deep Neural Networks (DNN), NGboost, and 1D Convolutional Neural Networks 1D (CNN 1D). The results demonstrate significant accuracy scores for each model, with the LSTM network emerging as the most efficient, showcasing an accuracy of 0.91 and an amazing Area Under the Curve (AUC) score of 94%. The success of the LSTM can be due to its proficiency in managing sequential and time-dependent data, which is essential for comprehending and predicting the dynamic characteristics of landslides. The LSTM’s ability to utilize temporal patterns improves the effectiveness of early warning systems, representing a notable progress in landslide prediction approaches.Item Power Potential Assessment of Wave Energy and Integration with other Renewable Energy Resources for Coastal Areas(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2024) Muhammad Shaharyar Haider; FA21-REE-005; Dr. Sobia Baig; LHR TP 9367Climate change is one of the most signicant challenges faced by the world. As the hu man population continues to grow, so too does the demand for energy. Fossil fuels being the primary source of energy produce greenhouse gases which adversely affect our climate. The United Nations Sustainable Development Goals (UNSDGs) emphasize the urgent need for reliable, sustainable, and clean energy. Wave energy is a promising form of renewable energy that harnesses the power of ocean waves to produce electricity. While it is under utilized and research on it is lacking in comparison to other renewable energy resources, it can contribute signicantly towards achieving the UNSDGs by providing a clean source of electricity for coastal areas. This research work assesses the potential of wave energy at a selected coastal location, aiming to evaluate its feasibility as a complementary energy source alongside other renew able energy sources. Historical wave parameter data spanning 15 years is obtained for the selected location and processed. Using Python, the dataset comprising of sea state param eters in each month of the year is then tted with probability density functions. The Monte Carlo simulation is used to generate synthetic wave scenarios. These simulations incorpo rate randomness in the wave parameters to assess the variability of wave energy generation. The MATLABbased tool for simulating wave energy converters, WEC-Sim, is used to as sess the capabilities of a converter in harvesting the resource based on the monthly average of wave parameters obtained from the simulations. In addition, a hybrid wave and solar energy system is developed using MATLAB Simulink to integrate the two renewable re sources. The analysis revealed signicant seasonal variations in wave power. At the selected location, the yearly average wave power was observed to be 376 kW/m, with the winter months from October to March showing a high availability of wave power. The month of January has the highest theoretical wave power potential of 675 kW/m. The sum mer months showed signicantly lower power potential with the month of July showing the lowest potential of 140 kW/m. This suggests seasonal variability in wave energy resource as sea conditions change and impact generation. The WEC-Sim simulations revealed that the wave energy converters only capture a fraction of the wave power. The commercially available and tested wave energy converters are analyzed and the most suitable converter is selected for use at the selected location. The research concludes that wave energy is a vi able energy source with negligible greenhouse emissions, and is capable of reducing yearly energy costs by up to 18250 USD per meter of energy capture from wavefronts. These ndings underscore the importance of integrating wave energy into the broader renewable energy portfolio to achieve the UNSDGs, especially in remote coastal communities where grid infrastructure is challenging to set up and maintainItem An Efficient Fault Detection Method for Grid Connected Solar Photovoltaic System(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2024) Zain Rasool; FA21-REE-001; Dr. Muhammad Yaqoob Javed; LHR TP 9369Photovoltaic (PV) module faults have harmful effects on both the efficiency of power generation and overall safety. Among these faults, current mismatch is the most common type, leading to a decrease in output current and causing distinct steps in the (current and voltage) I-V representative curves as well as multiple spikes in the P-V curves. Consequently, the power output of PV units is significantly impacted. This research delves into the scrutiny of faulty PV units in real-world PV power sites, specifically focusing on current inequality faults resulting from partial shadowing, hot spots, and cracks. There are various techniques used to detect the current faults. These techniques are ground fault detection and interruption (GFDI), over current protection (OCP), Insulation monitoring devices (IMD), and Arc fault current interruption (AFCI). Other than these devices various classification algorithms have also been developed which can be employed to classify the detected PV faults while the system is running. In this research the dataset from previous research is used to train regression tree, SVM, and logistic regression classifiers. Amongst these classifiers, regression tree classifier has presented an accuracy of up-to 99%, while the previous research presented an accuracy of 98%. This research distinguishes between different fault features within the I-V curve steps and proposes computational analytics and statistical techniques for diagnosing PV unit mismatch faults. The inclusion of PV system reduces the carbon footprint paving ways to green energy, in addition to saving fuel and generation costs on a yearly basis. As such this research aligns itself with the Sustainable Development Goals (SDGs) set by the United Nations.Item Deep Learning based Classification of Fetal Movements in Expecting Mothers using 3D Accelerometry Data(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2023) Mubah Mustafa; FA21-REE-002; Dr. Muhammad Jawad; LHR TP 8475Fetal activity is an important indicator of a healthy fetus and its normal growth in the womb as they are the reliable sign of normal functional central nervous and musculoskeletal system of the fetus. Electronic fetal monitors are commonly used worldwide to monitor fetal health. Due to the development in electronics, medical and computer technologies, fetal monitors are now improved in functionality and smaller in size, but the use of these monitors is still restricted to hospital premises. This research work focuses on the efficient classification of fetal movement from the normal human activity of the mother. Tri-axial accelerometers and acoustic sensors are commonly used in previous works to detect fetal movement and most of the techniques in different available research are restricted to their use in hospitals and clinics. Two different datasets of fetal movement are used in this research work. The datasets contain measurements from single accelerometer for fetal movement detection. After collection and pre-processing of the 3D accelerometer measurements dataset to detect fetal movement from multiple pregnant women, different state of the art machine learning algorithms are implemented to classify the fetal movement from maternal body movement with relative degree of accuracy. Among all employed algorithms, the Extreme Gradient Boost algorithm demonstrates superior performance in classifying fetal movement on Mendeley and Zenodo fetal movement dataset, achieving an accuracy of 94.58% and 96.01%, respectively. Moreover, we also developed multi-label classification algorithms for the classification of fetal movement, laugh, and other maternal body movements. Extra Trees classifier shows 93.72 % accuracy in multi-label classification. Furthermore, the accuracy of deep learning algorithms for multi-label classification of fetal movement, laugh, and other maternal body movements is presented in this research work. The convolutional neural network with 1D convolutional layer shows the high test accuracy of 88.96 % with a test loss of 18.67 %. The efficiency of different classifiers is tested on real time data collected in an unconstraint environment from MyNeuroHealth application. As expected, graph and tree based classifiers provided the highest accuracy on spatially and temporally correlated accelerometry data which was collected from 13 pregnant human subjects.