DIMENSIONAL ANALYZER
Presented By: Under the Guidance:
Aayushi Verma (2200680110003) Mr. Rahul Singh
Aditya Choudary (2200680110011) (IT Department , Miet)
Akshat Agarwal (2200680110016)
Anmol Dhiman (2200680110021)
Department of Information Technology
Meerut Institute of Engineering & Technology, Meerut (U.P)
Email :
[email protected] Presentation Outlines
• Introduction
• Abstract
• Survey
• Research
• Library Used
• Problem Statement
• Objective of the study
• Experimental Details
• System and Hardware analysis
• Result
• References
Introduction
•Purpose and Relevance:
•Explain the significance of dimensional analysis for society and industries, including
fields like healthcare, manufacturing, and environmental studies. Highlight the potential to
improve human decision- making and problem-solving through more accurate and
efficient analysis.
•Machine Learning's Role in Enhancing Human Insights: Describe how ML can
deepen human understanding of complex data, making it easier for specialists to analyze
and interpret.
Abstarct
Summary of Objectives and Outcomes: This study developed a dimensional analyzer
powered by ML to provide accurate, interpretable insights in real time. The analyzer
addresses limitations in traditional approaches by improving data processing efficiency
and interpretability. By making data analysis more accessible, this project has potential
applications across multiple fields, from medical diagnostics to industrial quality
control.
Survey
•Background on Existing Studies: A review of existing dimensional analysis tools
reveals a gap in methods that balance speed and accuracy with user-friendly output.
Current tools often focus on technical precision at the expense of intuitive interfaces.
•Challenges for Human-Centered Design: While ML enhances data accuracy, the
complexity of implementing it effectively for non-specialist users remains a significant
challenge. This project
investigates how ML can overcome these limitations to meet human needs.
Research
•Methodologies Considered: Various ML algorithms and techniques,
such as neural networks and decision trees, were evaluated to optimize for
both accuracy and interpretability. Ensuring data quality and developing
preprocessing methods that retain critical details were key research focus
areas.
•Data Collection and Human Usability: The data sources were chosen to
reflect realistic use cases where accuracy and clarity of analysis are essential
for human users. This included datasets that are commonly used in fields
like healthcare imaging and industrial design.
Library Used
• OpenCV
• NumPy
Problem Statement
•Human Limitations in Interpreting Complex Data:
Specialists need tools that allow them to interpret and analyze data
without extensive technical training. Traditional approaches often
fail to support non-expert users effectively due to complex data
formats or slow processing times.
Objective of the Study
•Enhancing Human-Centric Use Cases: The primary objective
is to develop a dimensional analyzer that not only increases data
processing speed and accuracy but is also accessible and
interpretable for users across industries.
Experimental Details
•Tools and Frameworks Used: The project utilized Python,
TensorFlow, and OpenCV libraries, focusing on models that
prioritize both accuracy and ease of interpretation for human
users.
•Human-Centered Design in Experimentation: The analyzer
was designed with use cases like medical scans or manufacturing
inspections in mind, ensuring the output data could be quickly and
easily interpreted.
System and Hardware analysis
1. System Overview
1. Brief description of the system’s purpose.
2.Hardware Components
1. Processor: Type and cores.
2. RAM: Total memory and usage.
3. Storage: Type and capacity.
4. Graphics Card: Model.
5. Network Interfaces: Connection types.
3.Performance Metrics
1. CPU Utilization: Current usage stats.
2. Memory Usage: Current and historical data.
3. Disk Speed: Average read/write speeds.
4. Network Performance: Bandwidth and latency.
Result
•The dimensional analyzer successfully measures
object dimensions in images as intended.
•Sensitive to lighting and image quality; struggles with
complex shapes.
References
• https://pypi.org/project/opencv-python/
• https://numpy.org/doc/stable/
