Theses and Dissertations

Permanent URI for this collectionhttp://ir.daiict.ac.in/handle/123456789/1

Browse

Has files: YesSubject: search.filters.subject.Microcontroller

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Comparative Study: Neural Networks on MCUs at the Edge
    (2021) Anand, Harshita; Bhatt, Amit
    Computer vision has evolved excessively over the years, the sizes of the processor and camera shrinking, rising the computational complexity and power and also becoming affordable, making it achievable to be integrated onto embedded systems. It has several critical applications that require a Huge accuracy and vast real-time response in order to achieve a good user experience. The Neural network (NN) poses as an attractive choice for embedded vision architectures due to their superior performance and better accuracy in comparison to the traditional processing algorithms. Due to the security and latency issues which make larger systems unattractive for certain time-dependent applications, we require an always-on system; this application has a highly constrained power budget and needs to be typically run on tiny microcontroller systems having limited memory and compute capability. The NN design model must consider these above constraints. We have performed NN model explorations and evaluated the embedded vision applications including person detection, object detection, image classifications, and facial recognition on resource-constrained microcontrollers. We trained a variety of neural network architectures present in the literature, comparing their accuracies and memory/compute requirements. We present the possibility of optimizing the NN architectures in a way for them to be able to fit among the computational and memory criteria for the microcontroller systems without salvaging the accuracy. We also delve into the concepts of the depth-wise separable convolutional neural network (DS-CNN) and convolutional neural network (CNN) both of which are utilized in MobileNet Architecture. This thesis aims to present a comparative analysis based on the performance of edge devices in the field of embedded computer vision. The three parameters under major focus are latency, accuracy, and million operations, in this study.
  • Thumbnail Image
    ItemOpen Access
    Real-time PID controller for UAV stability
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2016) Rathod, Hari; Parekh, Rutu; Dubey, Rahul
    Recently there has been a significant rise in the popularity of multi-rotor UAVsdue to its ability to hover and ability to execute vertical take-off and landing. Advancesin the field of compact and powerful microcontrollers, efficient brushlessmotors, MEMS sensors has allowed us to build small autonomous quadcopterswith on-board controller for stabilization and control of it.This thesis is dedicated to implementation and testing of a 6-Degrees of Freedom(DOF) feedback control system for an Unmanned Aerial Vehicle (UAV) equippedwith inertial sensors with focus on Vertical Take-off and Landing (VTOL). Thebasic six maneuvers are move up-down, left-right and forth and back. The quadcopteris inherently unstable and under-actuated system because we have fourmotors to control 6-DOF of UAV. The quadcopter has independently actuated motorswhose rotation speed is controlled by flight controller. The flight controllerboard has a feedback PID (Proportional-Integral-Derivative) algorithm code burnedonto it. The PID controller has a initial set point and the readings from the gyroscopeand accelerometer are continuously fed back to the PID. The readings thatindicate the inclination along any arm of quadcopter will generate an error aftercomparing with the initial point and then PID will generate a correspondingoutput to eliminate the error and balance the quadcopter.
  • Thumbnail Image
    ItemOpen Access
    Enabling technologies for remote health monitoring
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2016) Thakkar, Nileshkumar; Mishra, Biswajit
    Blood Pressure (BP) is one of the vital signs to measure health care of the personand it is useful to find out the cardiovascular diseases. Recent research showsthat measurement of BP using physiological parameters is gaining more interests.Current methods of measuring the BP are based on cuff based systems that areoften cumbersome and uncomfortable. The state of the art demands continuousmonitoring of BP using cuff-less devices employing non-invasive methods. Theaim of this work is to implement a wearable system that measures the BP basedupon physiological parameters: Pulse Transit Time (PTT) and Pulse Wave Velocity(PWV). By doing so, this enables a cuff-less and non-invasive method to measurethe BP. To obtain physiological parameters, we have used two physiologicalsignals that are Electrocardiogram (ECG) and Photoplethysmography (PPG). Wehave obtained ECG signal through single lead three electrodes along with an ECGfilter that is processed further in the microcontroller. In addition to this, a photodetecting sensor has been used to capture the Photoplethysmography (PPG) signalfrom the subject. These physiological signals have been further processedin a dedicated processor to measure Heart Rate (HR), PTT, and PWV. We havecalculated BP from different methods and the error analysis for all methods arepresented. Based upon the comparison of error for all methods, we have usedPulse Wave Velocity Peak (PWVp) parameter to derive BP. The error for SystolicBlood Pressure (SBP) is +11 mmHg to -12 mmHg and Diastolic Blood Pressure(DBP) measurement with PWVp based method is +10 mmHg to -14 mmHg incomparison to standard cuff based method. Further, ECG and PPG signals havebeen transferred to the smart phone over bluetooth to enable continuous remotemonitoring.