An Analysis of the Power Consumption of Various Computer Vision Machine Learning Techniques on a Microcontroller Utilizing the ClusterDuck Protocol

Aug 3, 2026

Upload by Ophelia

This senior project analyzes power consumption when running multiple computer-vision machine learning techniques on a microcontroller using the ClusterDuck protocol. The work covers engineering requirements, system design choices, and test plans, then documents development, integration, and measured outcomes across models and datasets. Results are presented through training metrics, model comparison tables, and power measurements over time for logistic regression, SVM, and CNN, enabling informed trade-offs for embedded deployment under constrained energy budgets.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages76

Reading Time3 h 12 min

AccessFree to download

Introduction

Background

Requirements

Design

Test Plans

Development and Construction

Integration and Test Results

Conclusion

Bibliography

AN ANALYSIS OF THE POWER CONSUMPTION OF VARIOUS COMPUTER VISION MACHINE LEARNING TECHNIQUES ON A MICROCONTROLLER UTILIZING THE CLUSTERDUCK PROTOCOL by Kaveh Shafiei [kshafiei@calpoly.edu](kshafiei@calpoly.edu) Senior Project ELECTRICAL ENGINEERING DEPARTMENT California Polytechnic State University San Luis Obispo 13 June 2025 Statement of Disclaimer Since this project is a result of a class assignment, it has been graded and accepted as fulfillment of the course requirements. Acceptance does not imply technical accuracy or reliability. Any use of information in this report is at the risk of the user. These risks may include catastrophic failure of the device or infringement of patent or copyright laws. California Polytechnic State University at San Luis Obispo and its staff cannot be held liable for any use or misuse of the project. TABLE OF CONTENTS Section Page Acknowledgements ............................................................................................................. 4 I. Introduction............................................................................................................. 7 II. Background............................................................................................................. 9 III. Requirements .......................................................................................................... 17 IV. Design ..................................................................................................................... 20 V. Test Plans ................................................................................................................ 24 VI. Development and Construction ............................................................................. 26 VII. Integration and Test Results .................................................................................. 32 VIII. Conclusion .............................................................................................................. 42 IX. Bibliography ........................................................................................................... 44 Appendices A. Analysis of Senior Project Appendix............................................................................ 48 B. Specifications.................................................................................................................. 54 C. Parts List and Costs ........................................................................................................ 55 D. Schedule and Time Estimates........................................................................................ 56 E. Code................................................................................................................................. 59 LIST OF TABLES AND FIGURES Tables Page 1. Table I: Engineering Specifications and Customer Requirements .............................. 17 2. Table II: Model Loss Functions ..................................................................................... 28 3. Table III: Uncompressed Model Training Parameters & Test Accuracy....................28 4. Table IV: Compressed Model Metrics........................................................................... 29 5. Table V: Logistic Regression Power Measurements.................................................... 30 6. Table VI: SVM Power Measurements........................................................................... 31 7. Table VII: CNN Power Measurements.......................................................................... 32 8. Table VIII: Model Power Consumption by Dataset ..................................................... 34 9. Table IX: Logistic Regression Power Consumption .................................................... 36 10. Table X: SVM Power Consumption.........................................................................

FAQs

What is the main objective of the project?

To measure and compare the power consumption of different computer-vision machine learning techniques when deployed on a microcontroller using the ClusterDuck protocol.

Which machine learning models are evaluated for power consumption?

The project reports power measurements for logistic regression, SVM (support vector machine), and CNN (convolutional neural network).

How are the results organized and presented?

Findings are presented using tables and figures that include model loss and metrics, power measurements over time, and comparisons by dataset and model type.

Aug 3, 2026

Upload by Ophelia