M.Phil / MS

Permanent URI for this collectionhttps://repository.cuilahore.edu.pk/handle/123456789/42

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

Browse

Filter results by year or month

Now showing 1 - 20 of 75

Module level power electronics in distrubted power system for solar PV application
(COMSATS University Islamabad Lahore Campus, 0022) Muhammad Talha Naveed; , SP20-REE-015; Dr. Muhammad Yaqoob Javed; LHR TP 7895
hotovoltaic (PV) solar energy is as promising as other renewable energies. Different researchers and engineers are attempting to increase the efficiency of solar PV system. As a result, for PV modules, this enhancement may be accomplished at almost the same level. As is well known, solar PV systems are less efficiency as a result of changing climatic conditions. Module-level power electronics (MLPE) do this by providing the performance improvements of a distributed transmission system in both partial and full shading conditions. As a result, MLPE successfully harvests the distributed maximum power point (DMPP) from solar to accept DC from PV or the grid. Each PV module is connected to the power system via a separate dc/dc converter with Maximum Power Point Tracking (MPPT) capabilities in the DMPP scheme. Each PV panel has a built in power optimization or micro-inverter that helps it work better in partial shade. In order to design the MLPE the efficiency of contemporary string inverters are comparing. The efficiency may be measured in a variety of situations, including uniform irradiation and partial shade. As a result, a DC-DC converter that is attached to each PV module is required to offset shading losses. The optimizer identifies the Local peak using a DC-DC converter from the unit, shuts down the modules during fire situations, troubleshoots, and monitoring a module in a highly efficient manner in this work. On the Matlab software tool, the effectiveness of the proposed power optimizer is displayed. To calculate efficiency, several firms such as SMA, Solar Edge, Huawei, Tigo, and Enphase can use helioscope to compare production and loses data. The results suggest that MLPE produces superior outcomes.
Nowcasting of RSSL in wireless communication channel over the sea using machine learning algorithms
(COMSATS University Islamabad Lahore Campus, 0023) Farwa Jafar,; FA20-REE-005; Dr. Khurram Zaidi; LHR TP 7896
The presence of naturally occurring evaporation duct (ED) phenomenon is very high in the tropical/equatorial regions of the world. Although, refractivity estimation of EM and Radio waves in ED is well studied in the literature, still, the signal propagation through ED over-the-horizon needs to be thoroughly researched to help determine the received-signal-strength-level (RSSL) for a reliable wireless communication link. In order to accurately predict RSSL in ED, we have acquired RSSL (avg.) per-minute data for three months over-the-horizon distance of 50 km (Tx-Rx) from onshore-to-offshore Oil & Gas Platform. This data was collected using fixed antenna heights in ED. Applying deep learning algorithms on real-time RSSL data, we have nowcasted the future RSSL values for next 5 seconds timescale in this thesis. A thorough comparison is made between the CNN and LSTM deep learning methods for real-time series prediction analysis. These deep learning networks are linked with numerous convolution layers to grasp the nonlinear mapping between measured and future RSSL values. Coding and Simulation work is performed in Python 3.9 environment and results are generated in Kaggle Notebook. CNN and LSTM networks have never been used earlier for predicting “signal strength” over-the-horizon and over-the-sea under ED environment. The contribution of this research is to bridge this gap and examine the accuracy of LSTM and CNN for nowcasting RSSL data. According to what we've discovered, both of these neural network models are capable of achieving adequate to high prediction power given that the "datasets" are suitably big. Both methods, when taken as a whole, are reliable with regard to their hyperparameters. However, with increasing number of training courses, LSTM didn’t improve its performance, whereas CNNs performed correspondingly more accurate each time. For 3rd training, CNN has given the most optimal fitting of training data as compare to test data. The RMSE achieved for CNN after third training was 4.47 which is the least of all simulations. Hence, CNNs proved to be superior, since they operate one order of magnitude quicker than LSTM. We proposed that the early predictive capability, speed, and resilience of CNN open its door to nowcasting’s future.
A Research On Clock-Synchronous Sleep And Wake
(Publisher COMSATS University Islambad Lahore Campus, 2016) Usama Masood; FA12-MSEE-018; Dr. Ali Nawaz Khan, Assistant Profesor [Supervisor]; LHR TP 6980
A Research on Clock-Synchronous Sleep and Wake Scheduling Scheme in Wireless Sensor Networks Network Wireless Sensor Network (WSN) consist of a unique set of resources like on-board battery and wireless communication devices with limited bandwidth. WSN offers a wide range of applications for monitoring space or targets. WSN is capable of performing simple processing tasks like tracking, detection of an event, or classification and may consist of multiple nodes that can process the information and communicate with nearby nodes in real-time for environmental monitoring, event detection, surveillance, object tracking, battlefield situation monitoring, and data collection etc. However, there are certain limitations in deploying WSN efficiently such as in terms of limited power resource for a single node in WSN, limited processing capability and varying network life time. It had been shown that wireless communication to and from sensor nodes consumes significantly more battery power in comparison to power expended in sensing, computation and memory access procedures. One of the possible solutions to this problem is to communicate as sparingly as possible through efficient sleep/wake scheduling for WSN nodes to extend node and network lifetime. A major research issue in WSN is to develop an energy efficient MAC protocol that not only provides increase in network lifetime but also addresses latency. In this research, a new MAC protocol is designed using sleep/wake scheduling for WSN. Though energy consumption in WSN is unavoidable due to communication necessity and for different stages like idle listening, retransmission, channel sensing and overhearing; this proposed protocol will help in decreasing this energy consumption. Energy efficiency and latency of the proposed sleep/wake scheduling scheme is evaluated and compared with the state of the art research. An AEL (Accounting for Energy and Latency) factor is introduced which is the deciding element for active and sleep cycles of the node. This said AEL factor defines the minimum duty cycle among the network nodes and is specified prior to nodes deployment depending upon application requirements. In the proposed protocol, the nodes adjust their duty cycles according to this AEL factor depending upon traffic load, their position and their connectivity in the network. The effect of this AEL factor on energy efficiency and delay is evaluated for different network densities in this research thesis. While incorporating sleep/wake scheduling for energy efficiency, delays are added in the network to route packet from node towards sink. Therefore, it is necessary to address latency for MAC protocol especially for delay constrained applications. This research thesis focuses on sleep/wake scheduling scheme ensuring energy efficiency, decreased latency and increased network lifetime by selecting an appropriate AEL value. The research includes the comparison of the proposed protocol with state of the art research and has shown significant percentage improvements in energy efficiency and delay from S-MAC and Anycast protocol
Output Feedback FTC Scheme For Linear Parameter
(Publisher COMSATS University Islambad Lahore Campus, 2016) Izhar Ul Haq; , FA13-MSEE-006; Dr. Mirza Tariq Hamayun, Assistant Profesor [Supervisor]; LHR TP 6820
The proposed research has been carried out for an Active Fault Tolerant Control (FTC) of Linear Parameter Varying (LPV) systems using output feedback mechanism. Output feedback is a practical approach due to the fact that all the plant states are not accessible or measurable, therefore estimating the unknown states and maintaining the closed loop stability in an LPV framework is closer to the control of nonlinear systems. At the same time, it utilizes the mature nature of linear control theory. In this research, LPV observers in LMI framework have been designed for affine LPV plant, using two different LPV approaches namely affine and polytopic, in order to estimate the unknown states. These estimated states are used as a feedback to LPV controller. Integral sliding mode controller in LPV framework has been designed along with control allocation scheme to control the controlled states as well as to counter for actuators faults and failures. It has been assumed that Fault Detection and Isolation unit, also called FDI, is providing updated actuator faults or failures information to the control allocation (CA) scheme. Detailed performance and stability of the proposed control scheme has been checked in fault-free case, i.e. nominal condition, as well as in the situation when actuator fault occurs. To validate the proposed output feedback FTC mechanism, an LPV model of longitudinal plant of aircraft, taken from the literature, has been considered as a benchmark in the simulation. The simulation results show that the system is quadratically stable and give good tracking capability by the LPV controller-observer pair in nominal as well as in actuator’s fault or failure situation.
Design Of Hemispherical Antenna For Breast Cancer
(Publisher COMSATS University Islambad Lahore Campus, 2017) Iqra Asghar,; SP15-REE-005; Dr. Asim Ali Khan, Assistant Profesor [Supervisor]; LHR TP 6824
Microwave imaging has proven to be successful for medical imaging applications including breast cancer, lungs cancer, brain stroke detection, cardiac imaging etc. Microwave imaging has the ability to detect malignancy present at depth of tissue, providing non-invasive imaging, measuring dielectric contrast between tissues. This imaging procedure provides an effective substitute of mammography, ultrasound or MRI as all these screenings provide unreliable and uncomfortable detection. In this thesis, microwave imaging system has been simulated for breast tumor detection. The designed microwave imaging system includes the use of holographic imaging. For the design of holographic imaging array, two-dimensional (2D) and three-dimensional (3D) breast models have been designed in MATLAB. Holographic array simulations have been carried out in MATLAB. To efficiently reconstruct an image, inverse scattering algorithm has been applied in holography imaging array. The building block of microwave imaging is to design a suitable antenna that must efficiently transmit and receive electromagnetic signals. An efficient compact double layer antenna has been designed in HFSS for the breast malignancy detection system. The antenna provides good impedance matching, wide bandwidth, stable and symmetric radiation pattern for near field imaging. To improve the performance of imaging system, the antenna was simulated in an array configuration. To overcome the drawbacks of array system, a novel array topology has been simulated in HFSS. The designed array system consists of separate transmitters and receivers for imaging, to provide low cost, reliable and effective detecti
Mechine And Learning Based IoT Instruion Detection
(Publisher COMSATS University Islambad Lahore Campus, 2018) Muhammad Saad Sarfraz Khan; , SP16-REE-006; Dr. Abbas Javed, Assistant Profesor [Supervisor]; LHR TP 6439
In today’s world, technological advancements are gradually increasing, so small scale to large scale companies use the internet for business purposes. Other than that Internet of Things (IoT) is a current trend in the world. Most companies try to improve their companies by making them smart premises since this will give a lot of advantages; some are increasing customer satisfaction, saving time, control expenses, monitoring, and many more. So, with the rise of these technological advancements, diverse types of security issues like DDoS, malware, virus, worms, and many other issues occurs as well because of the software or device vulnerabilities. These are harmful to organizations’ sensitive data due to the violation of integrity, confidentiality, and availability. IoT devices have been extensively implemented in many different applications in recent years, such as smart homes, medical, heavy industry, agriculture, networks, security, transportation, etc. An adversary can capture the network traffic of IoT devices and analyze it to reveal user activities even if the traffic is encrypted. Due to the increasing number of cyber-attacks, we need IoT security solutions. The majority of the attacks are extended versions of previously known attacks and bypass the conventional firewall system. An Intrusion Detection System (IDS) performed an incredibly significant part to figure out the novel types of attacks by analyzing the network traffic. Machine Learning (ML) and Deep Learning (DL) based techniques such as Random Forest (RF), Support Vector Machine (SVM), J48, Naïve Bayes (NB), Logistic Regression (LR), etc. are used as a classifier to categorize the network traffic as normal and attack class. The objective of this research is to compare the impact of different Feature Selection (FS) techniques such as Information Gain (IG), Chi-Square, Correlation-based Feature Selection (CFS) subsets evaluator, Classifier based attributes, and other techniques on the accuracy, computational time and confusion matrix of ML & DL based techniques and identify the attack categories. FS methods and classifiers have been implemented on four different data sets NSL KDD, UNSW-15, CIC IDS2017, and TON_IoT and a comparative assessment of the outcome is presented. By applying our proposed comparative model, we will be able to trace out the malicious attacks i.e., DoS, DDoS, routing attacks, Man-in-The-Middle (MITM), etc. in the realm of IoT networks. This model detects the attacks with high accuracy and consumes less time as compared to the other methods.
A Research On Feasibility Of Intra Vehicle
(Publisher COMSATS University Islambad Lahore Campus, 2018) Naeem Mirza,; FA13-MSEE-016; Dr. Ali Nawaz Khan, Assistant Profesor [Supervisor]
In Intra Vehicular Wireless Sensor Network (IVWSN), Engine Control Units (ECUs) gathers information about the vehicle from the sensors over wireless channels. This information is then transferred to On-Board Unit (OBU) through Controller Area Network (CAN) in order to monitor and maintain vehicular operations. CAN bus is widely used wired media for communication between ECU and sensors by several car manufacturers but it requires very careful sensor deployment and wiring. In this research thesis, we have achieved low cost and energy efficient communication between (1) sensor nodes and ECU using CAN bus and (2) OBU and ECU within Vehicular Ad Hoc Network (VANET) using Bluetooth low energy (BLE) CC2540/CC2541 modules that can be readily employed in densely urban environment for wireless inter vehicular (up to 50m range) as well as wireless intra vehicular (up to 10m range) communication. The BLE system was invented for the purpose of transmitting small packets of data at once, while consuming less power than Basic Rate & Enhanced Data Rate (BR & EDR) and IEEE 802.15.4 standard based ZigBee devices. A typical communication scenario involves either a Peripheral/ Central or Broadcaster/ Observer device pair. For our tests, we have chosen the Peripheral/ Central modes as they provide greater flexibility to configure application parameters and allow bidirectional communication. We have included comparison between BLE and CAN bus for communication between (1) ECUs and sensors and (2) ECU and OBU, in terms of energy efficiency, throughput, latency and coverage area. Furthermore, wireless communication between ECUs and sensors had been a
Model Identification And Control Of A Lab Based
(Publisher COMSATS University Islambad Lahore Campus, 2018) Anila Barkat,; FA14-REE-011; Dr. Mirza Tariq Hamayun, Assistant Profesor [Supervisor]; LHR TP 6847
Inverted pendulum control system has vast applications in the field of control system. Every system which is inherently unstable can be controlled like inverted pendulum is controlled. To design a Robust Control system for Inverted pendulum to investigate the behaviour of rapid change in scheduled parameters is aim of this thesis. The designed mechanism has a monitoring and calibrating VI (Virtual Instrument) which is constructed in LabVIEW. This VI send a step input to the inverted pendulum and obtain the transient response of the system from that response system’s model is identified. This model helped in control designing part because model of every system represents its characteristic. Then LPV controller is designed to cater for the parameters variations to enhance the performance and robustness. Moreover, the designed robust controller is implemented on the hardware platform to show its effectiveness. The identified mathematical model is validated by comparing the simulation and real time simulation results with LQR and PID controller.
A 3D Accelerometer Based Human Activity Classification
(COMSATS University Islamabad Lahore Campus, 2018) Aftab Paul,; FA16-REE-009; Contributor(s): Dr. Ali Nawaz Khan, Assistant Profesor [Supervisor]; LHR TP 7475
Recently, Automated Human Activity Recognition has been extensively used for long term health monitoring of healthy individuals and to provide assisted living for the elderly. Long-term health monitoring systems have been successfully implemented for the prevention of chronic diseases like heart disease, obesity, workers syndrome, and other diseases related to sedentary lifestyle. Activities of Daily Living such as sitting, standing, walking, working in office, jogging, and running etc. can be efficiently classified using sensors such as 3D accelerometers, gyroscopes, and magnetometers. Such systems have demonstrated very high classification accuracies for activities performed for longer durations of time. However, these systems are unable to detect and classify transitory activities where the subject switches from one basic activity to another. For example, if a subject stands up from the chair to walk out of the room and then goes downstairs to reach ground floor of the office building has transitions from stationary sitting to standing and then walking, walking to going downstairs and then walking again and these transitions may not be classified correctly by existing automated human activity recognition systems since the models are trained using nonrealtime segmented data for each individual activity class. This research aims to develop a system for the detection of transitory activities. A Mobile phone-based accelerometer is used to record these activities from the chest of subject through MyNeuroHealth application. Data is collected, pre-processed, and classified into different activity classes. This data is used to train Artificial Neural Network to classify transitory activities. The proposed system achieved an accuracy of more than 50% with real-time data. Furthermore, it is also observed that using two accelerometers for collecting the movement data can enhance classification accuracy to 65%. Given that little or no work has been done in this dimension of HAR, this research may be extended to improve the accuracy of HAR for real-time automated long term health monitoring systems. X
A HYBRID MAC LAYER PROTOCOL FOR HETEROGENEOUS WIRELESS BODY AREA NETWORKS
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2019) Hina Bushra; CIIT/FA14-REE-007/LHR; Dr. Ali Nawaz Khan; LHR TP 5627
The rapid advancements in wireless communication technologies and micro-electronics systems have fostered the development of small and intelligent micro-components that incorporate sensing devices and wireless communications into a single miniature circuit which is wearable or implantable inside the human body for medical and healthcare applications. These components when deployed over or across the body of subject communicate wirelessly to constitute Wireless Body Area Networks (WBANs). Since several WBAN nodes are sharing the wireless channel to report their collected data back to a base-station or sink node, the medium access mechanism must be robust, scalable, and energy efficient. Furthermore, it may also adapt to different data-rate requirements for different sensors in a heterogeneous WBAN. In this research, Adaptive Sleep and Dynamic GTS allocation algorithms in WBAN have been implemented and compared with the proposed protocol entitled Adaptive Dynamic MAC that takes into consideration number and type of sensors, variable data-rates and energy requirements through managing sleep/wakeup intervals for WBAN nodes and implementing adaptive schedules for communication within the network. Network performance is compared on the basis of network lifetime, throughput and channel utilization through analytical model that is also verified in a customized simulator. Simulation results are gathered by observing network performance under variable network energy conditions, change in the position of gateway node, and effect of heterogeneous sensor nodes on mentioned performance parameters. It has been shown that Adaptive Dynamic MAC performs better than Dynamic GTS Allocation framework in all mentioned parameters. Furthermore, proposed algorithm has better network lifetime and throughput characteristics in comparison to baseline Adaptive Sleep algorithm.
Dynamic Adjustments Of Threshold Temperatures
(Publisher COMSATS University Islambad Lahore Campus, 2019) Muhammad Ibtesam; , FA15-REE-004 Contributor(s); : Dr. Naeem Shahzad, Assistant Profesor [Supervisor]; LHR TP 5432
This research work addresses the issues of thermal emergencies in real-time embedded system using scheduling based algorithms. The algorithms considers execution of periodic task sets including both independent and dependent tasks over homogeneous multi-core processors without violating deadlines. We propose two algorithms in this work. The first one adjusts the thermal threshold values based on the processor utilization to reduce thermal peaks and thermal spatial gradients for independent periodic task sets. The second algorithm is a DVFS enabled load-balancing algorithm for execution of dependent periodic task sets to reduce the temperature peaks and spatial gradients. The proposed algorithms are evaluated in a simulation environment using a scheduling and thermal model for synthetic and bench marks techniques. The used hardware platform comprises four and eight cores. The results show that GTAI with 74ºC threshold reduces average temperature up to 6ºC and maximum temperature spatial gradient was reduced by 33% as compared to benchmarks techniques. The DVFS enabled DFS was able to decrease peak temperature by 31% and temperature spatial gradients by almost 50% in a 4-Core system.
Short Term And Medium Term Electrial Load Forecast
(Publisher COMSATS University Islambad Lahore Campus, 2020) Umar Javed,; FA18-REE-026; Dr. Muhammad Javad, Assistant Profesor
,The electrical load forecasting finds its application in several federal policy related matters, network expansion, and suitable allocation of energy resources within masses. The planning institutions of power utilities in Pakistan are making use of traditional statistical methodologies for electrical load forecasting purpose, which are not capable of incorporating system non-linearities effectively. The modern day deep neural network based non-linear parametric modeling techniques are more suitable to handle the system dynamics and non-linearities effectively, rather than traditionally employed statistical methodologies. In this research work, Long Short-Term Memory based Recurrent Neural Network model (RNN-LSTM) is developed and implement for the load forecasting of Pakistan. The temporal and climatic factors are also embedded as input parameters in these forecasting models after thorough exploratory data analysis. The results of RNN-LSTM are compared with different linear and non linear parametric modeling techniques. The qualitative and quantitative comparison among all linear and non-linear parametric methodologies reveals that the proposed RNN - LSTM outperforms among all other forecasting models.
Controller Synthesis For One Sided Lipschitz Discr
(Publisher COMSATS University Islambad Lahore Campus, 2020) Waqas Hussain,; FA16-REE-006; Dr. Mujtaba Jaffery, Assistant Profesor; LHR TP 5630
This thesis is concerned with stochastic stability of a class of non-linear discrete-time MJSs with time-varying delay, disturbance and partially unknown transition probabilities. By using linear matrix inequality approach and constructing proper Lyapunov-Krasovskii functional, sufficient criteria have been obtained that ensures the asymptotic stability of proposed system. By using the statae feedback controller, it is guaranteed that the state trajectories starting from a given region will remain in it even in the presence of disturbance, time-varying delay, where the non-linear fuction satisfy the one-sided Lipschitz and quadratically inner bounded conditions. In addition, second part of this research deals with the designing of observer-based controller which will stabilize the system without the requirement that the system states are measureable. Finally two examples are given to demonstrate the efficiency of the proposed design.
Active Power Management Of Standalone DC Micro And
(Publisher COMSATS University Islambad Lahore Campus, 2020) Tahir Riaz Sindhu; , FA16-REE-004; Dr. Muhammad Yaqoob Javed, Assistant Profesor; LHR TP 5629
Standalone DC microgrids are emerging as an efficient solution for integrating renewable energy sources in remote and off-grid areas. Effective active power management is essential to ensure system stability, reliability, and optimal utilization of available resources. This paper presents a comprehensive approach to active power management in a standalone DC microgrid incorporating renewable energy sources such as solar photovoltaic systems, energy storage units, and varying load demands. The proposed control strategy dynamically balances power generation, storage, and consumption by prioritizing critical loads and maintaining DC bus voltage within acceptable limits. Advanced control techniques, including droop control and energy management algorithms, are implemented to enhance system performance under fluctuating conditions. Simulation results demonstrate improved power sharing, reduced energy losses, and enhanced system stability. The study highlights the importance of intelligent power management strategies in achieving sustainable and reliable standalone DC microgrid operation.
Wavelet Transform Based Sparse Code Multiple
(Publisher COMSATS University Islambad Lahore Campus, 2020) Muhammad Sajid Sarwar,; SP17-REE-010; Dr. Amjad Hussain, Assistant Profesor; LHR TP 5633
Fifth Generation (5G) of wireless communications that incorporates very high data rates, massive connectivity and very low latency can be fundamental part of 4th Industrial revolution. As far as, physical layer is concerned, Multiple Access (MA) techniques are significant in accommodating users on frequency and time resources for an efficient spectrum utilization, least Multi-Access Interference (MAI) and greater throughput. 5G is transforming user access techniques from orthogonal to non-orthogonal resource sharing methods. Non-Orthogonal Multiple Access (NOMA) technique is the transmission of superimposed signal of multi-users on shared frequency band simultaneously instead of utilizing separate frequency & time slot for each user. NOMA is categoried into Power Domain (PD) NOMA & Code Domain (CD) NOMA. Sparse Code Multiple Access (SCMA), a type of CD-NOMA that facilitates greater user connectivity for 5G. SCMA utilizes sparse resource allocation and non-orthogonal three dimensional codebooks to increase spectrum efficiency. Superimposed encoded data of all users employs a complex receiver such as Message Passing Algorithm (MPA) to extract user specific signal. In this research work, MAI for overloaded SCMA will be examined and different signal processing techniques will be employed to reduce it. Multi-Carrier (MC) communication techniques such as Fast Fourier Transformed Orthogonal Frequency Division Multiplexing (FFT-OFDM) combined with SCMA are analysed in literature and offers satisfactory performance for wireless communications. Recently proposed MC modulation schemes such as Wavelet Transformed OFDM (WT-OFDM) remained relatively unexplored with reference to SCMA. WT provides better decomposition & reconstruction as compared to FFT which is helpful for interference mitigation in a signal. Therefore, Wavelet Transform (WT) is expected to improve Signal to Interference and Noise Ratio (SINR) for SCMA users. Simulation models of SCMA and MC-SCMA schemes are presented that utilize MPA receiver to decode data of all superimposed users and show that WT-SCMA is superior to FFT-SCMA in the context of BER performance. Analytical models are derived for SINR employing Maximal Ratio Combining (MRC) to examine MAI for a particular user in the SCMA/MC-SCMA systems. SINR comparison shows that WT-SCMA outperforms FFT-SCMA.
Human Activity Recognition System For Long Term
(Publisher COMSATS University Islambad Lahore Campus, 2020) Shan E Ali,; SP18-REE-026; Dr. Ali Nawaz Khan, Assistant Profesor [Supervisor]; LHR TP 6444
The study of Human Activity Recognition (HAR) for Long Term Health Monitoring (LTHM) has gained significant importance for its wide range of applications. These applications range from sports and rehabilitation sciences to assisted living for older people. In addition to that LTHM is an efficient solution for the prevention of lifestyle diseases like stroke, heart failure, and various health problems that occur due to prolonged inactivity. With the increased availability of accelerometer sensors embedded in mobile phones, we can efficiently explore the Activities of Daily Living (ADLs) of an individual. This research aims to develop a LTHM system for evaluating ADLs of a person using a mobile phone-based accelerometer sensor and the ‘MyNeuroHealth’ application. Data collected in an unconstrained environment by various individuals throughout the day to create templates of ADLs. Collected data is prepared and preprocessed by assigning hourly labels to the ADLs, encoding categorical values and random sampling of data. This data is used for training the machine learning model and for classifying activities according to their energy expenditure or user exhaustion levels. Collected dataset further extended to daily, weekly, and monthly basis to provide long-term health profiling (LTHP). 23 types of basic, complex and transitional activities were evaluated for each day. The results show that an Artificial Neural Network (ANN) can efficiently identify and detect ADLs with more than 90% accuracy. Person independent ADLs templates for weeks 1, 2, 3 and 4 achieved an accuracy of 89, 96, 93 and 89 percent correspondingly. On the other hand, person dependent ADLs templates from various walks of life achieved on average 94% accuracy. Person independent ADLs templates for weeks 1, 2, 3 and 4 achieved an accuracy of 89%, 96%, 93% and 89% percent correspondingly.
Robust Kalman Filter For 2-D Nonlinear Systems
(Publisher COMSATS University Islambad Lahore Campus, 2020) Talha Zeb,; SP18-REE-030; Dr, Muhammad Yaqoob Javeed, Assistant Profesor [Supervisor]; LHR TP 6449
Kalman filter (KF), being an optimal estimator for linear systems and known statistics of Gaussian noise, is an optimal filter thus widely used method for state estimation. However, the central obstruction in its implementation is that the dynamics of the model must be exactly known. Many advances in robust control and estimation to reduce the effects of model uncertainties have attracted various studies on robust Kalman filtering. There are three renowned approaches for robust linear state estimation i.e. H∞ filtering, set valued filtering and guaranteed cost (GC) filtering; all of them are used with Kalman filtering framework due to its wider applicability. Since, the exact minimum of estimation error variance is not mathematically computed, the usual choice, therefore, is to enforce a constant upper bound on error variances for all acceptable uncertainties. This upper bound is then minimized instead of obtaining (global) minimum variance. Thus, the robust KFs (RKFs) are sub-optimal but adaptable to practical scenarios. Since, all of the above methods perform de-regularization, they either suffer from inherent conservativeness or existence conditions. Practically, these conditions cannot be ensured to be satisfied at all arbitrary iterations. If the conditions are not met at any iteration, the filter may perform poorly. However, a RKF based on least square (LS) approach employed unique Regularized Least Square (RLS) criterion for uncertain models. The distinctive features of this method are it performs regularization thus avoids existence conditions and vector optimization problem is reduced to scalar minimization problem. Hence, this approach, according to the best of our knowledge, is most suitable for online implementation.
Attitude Control Of Satellite Using Computationall
(Publisher COMSATS University Islambad Lahore Campus, 2020) Muhammad Shah Rukh Ahmad,; CIIT/FA12-MSEE-011/LHR; Dr. Mujtaba H. Jaffery, Assistant Profesor [Supervisor]
Attitude control System (ACS) of spacecraft performs the attitude control to counter the effects of disturbances present in the space environment. MPC (Model Predictive Control), controller is a control algorithm which uses the mathematical model of the plant and also considers input and output constraints for the calculation of optimal control law in real-time. The issues with the conventional MPC are its computational time and feasibility at each sampling instant. The larger computational time and infeasible optimization solution in real-time applications is a cause of concern. Previous work has only considered the implementation of MPC by considering the inputs constraints. The use of MPC to consider output constraints and effect of feasibility and computation time has not been explored. Therefore computationally efficient two variant algorithms of MPC i.e., Optimal MPC (OMPC) and Laguerre OMPC (LOMPC), have been selected as control algorithms to study feasibility and computational time by linking dual mode, closed-loop paradigm and Laguerre function techniques for linear and non-linear model. Linear model approximates non-linear model because of small angle approximations. Also changes in satellites attitude angles because of disturbances fall in the domain of small angles approximation regions. The effect of changing the position of Laguerre Poles on the closed loop performance and computation time was explored. The input constraints were considered on the control torque, whereas output constraints were considered for roll, pitch and yaw angles. The conclusion is that the in the case of linear approximated model, use of OMPC algorithms with Laguerre functions improves computational time. Both OMPC and LOMPC do not affect the closed loop performance even if infeasible solutions are produced. When OMPC and LOMPC algorithms were applied to the non-linear model, diverging non-zero steady-state errors were introduced and plant became unstable. It was evident from the results that OMPC and LOMPC were not able to control the non-linear model.
Real Time Implimentation Of High Power Three Phase
(Publisher COMSATS University Islambad Lahore Campus, 2020) Ayesha Khan,; FA18-REE-005; Dr, Mujtaba Hussain Jaffery, Assistant Profesor
Electric power quality is a business issue and requires a lot of attention. If a failure exists due to internal integration of the power system in any one of the internal networks, it would cause uncomplimentary consequences to the entire power system. Current harmonics and their mitigation is the topic of interest in industries due to the excessive use of non-linear load that causes to reduce the life of the equipment and degrades the electric power quality. So, harmonic pollution in the system rises and in order to reduce it, a Hybrid shunt active harmonic power filter (HSAHPF) is designed and simulated in MATLAB SIMULINK. For power quality improvement, Digital Real-time and efficient hardware in the loop (HIL) controller is implemented for testing the efficacy using instantaneous active and reactive power theory (Pq0) and instantaneous active and reactive current theory (Id-Iq) as control algorithms for reference current generation in HSAHPF. The control algorithms are employed in a cost-effective microcontroller i.e Arduino MEGA. The real-time simulations from SIMULINK are interacting with the controller for generating reference currents in the HIL technique based on Pq0 and Id-Iq control algorithms. For the inner control loop, switching signals are generated by Hysteresis Current Controller or PWM and charging/ discharging of the capacitor is conserved with the use of the PI controller. The real-time testing of HSAHPF using controller HIL simulations have demonstrated the ability of control algorithms to run in a portable embedded device. The system response for both of the implemented control algorithms in Arduino provides minimum THD with improved stability time. Through this HIL approach, mitigation of harmonics and better-quality power attained with power factor near to unity is also verified experimentally.
Real-Time Air Pollution Monitoring Using Machine
(COMSATS University Islamabad Lahore Campus, 2020) Rana Ahtisham Ali,; SP18-REE-015; Dr. Abbas Javed, Assistant Profesor [Supervisor]; LHR TP 7466
According to World Health Organization (WHO), the air in Lahore, Pakistan, has an annual average of 68 µg/m3 of PM 2.5 particles which are 6.8 times more than safe levels recommended by WHO. In December 2016, the amount of PM2.5 went above 100 µg/m3 which was more than 10 times safe levels set by WHO. Currently, there is no network for real time air pollution prediction available in Lahore, nor Pakistan. In this research, an Internet of Things (IoT) based low cost/low power outdoor air quality monitoring system has been developed. We developed the wireless sensor nodes for the monitoring and prediction of the PM2.5 particles in the air. The nodes comprised of different sensors for measuring PM2.5, SO2, O3, CO, NH3, NO2, humidity, and temperature values and Long Range (LoRa) transceiver for uploading the data on the cloud. The coverage range of LoRa gateway has been tested in Lahore, Pakistan and it is found that coverage range of the sensor node is around 2.7 KM in densely populated areas. Five different artificial neural network models are used for the prediction ahead of 1hr, 2hr, 3hr, 4hr, 5hr and 6hr. We obtained the accuracy of 99% for tested model of LSTM. The accuracy of LSTM model for 1hr ahead is 13% more than FFNN, 2% than Elman NN, 0.41% than NARX and 0.45% than layer recurrent. The accuracy of LSTM model to predict 6hr ahead is above 95%. For 6hr ahead prediction, accuracy of LSTM is 15% better than FFN, 12% than Elam NN, 7% than layer recurrent and 9% than NARX NN. Results show that the LSTM model outclass all other models. The computational time of LSTM model to predict 6hr ahead is 150.22565msec. While FFN takes 30 msec, Elman NN takes 60msec, NARX takes 80msec and layer recurrent take 90 msec. The 1hr ahead predicted model of feed-forward NN embedded in all nodes and placed at different places for real-time testing. The dataset collected at the server side analyzed and it is found that our air pollution monitoring system is capable of accurately predicting the future (1 hour ahead) concentration of PM 2.5 in outdoor air. Its accuracy for 1hr ahead prediction is up-to 90% and its algorithm takes 0.642 micro seconds computational time for the prediction level of PM2.5.