Changes between Version 97 and Version 98 of Other/Summer/2023/Inference


Ignore:
Timestamp:
Aug 8, 2023, 3:56:02 PM (11 months ago)
Author:
tm897
Comment:

—

Legend:

Unmodified
Added
Removed
Modified

  • Other/Summer/2023/Inference

    v97 v98  
    115115  * After analyzing latency, move on to accuracy tradeoffs using different thresholds
    116116
    117 == Week 8
    118 **Summary**
    119   * Explored different research questions with the data collected
    120   * Limited CPU power in terminal to imitate mobile devices
    121   * Implemented different threshold values based on confidence for sending the data to the edge and server for inference
    122   * Generated graphs for threshold vs latency
    123 **Next Steps**
    124   * Use PTP timing to get more precise time measurements
    125   * After analyzing latency, move on to accuracy tradeoffs using different thresholds
     117== Results
     118[[Image(cam1-2 better.png)]]
    126119
    127120
    … …  
    139132<a href="https://docs.google.com/presentation/d/1_iHN8Ii--qXU5rljfGRi2lQuaFMVv3BE5edFPcXJi2Q/edit?usp=sharing">Week 7</a> &nbsp
    140133
     134<a href="https://docs.google.com/presentation/d/13Lkpe6GTxxFsbYqxPZ0sVprFMsdpvdkVQ7GSKM9dSU4/edit?usp=sharing">Final Presentation</a> &nbsp
     135
     136
    141137</p>
    142138}}}
    143139   
     140
     141== References
     142
     143N. Abbas, Y. Zhang, A. Taherkordi and T. Skeie, "[Mobile Edge Computing: A Survey](," in IEEE Internet of Things Journal
     144Teerapittayanon, S., McDanel, B., & Kung, H. T. (2017, June). Distributed deep neural networks over the cloud, the edge and end devices.