Assessing Perceived Fairness from Machine Learning Developer's Perspective

Fairness in machine learning (ML) applications is an important practice for developers in research and industry. In ML applications, unfairness is triggered due to bias in the data, curation process, erroneous assumptions, and implicit bias rendered within the algorithmic development process. As ML applications come into broader use developing fair ML applications is critical. Literature suggests multiple views on how fairness in ML is described from the users perspective and students as future developers. In particular, ML developers have not been the focus of research relating to perceived fairness. This paper reports on a pilot investigation of ML developers perception of fairness. In describing the perception of fairness, the paper performs an exploratory pilot study to assess the attributes of this construct using a systematic focus group of developers. In the focus group, we asked participants to discuss three questions- 1) What are the characteristics of fairness in ML? 2) What factors influence developers belief about the fairness of ML? and 3) What practices and tools are utilized for fairness in ML development? The findings of this exploratory work from the focus group show that to assess fairness developers generally focus on the overall ML application design and development, i.e., business-specific requirements, data collection, pre-processing, in-processing, and post-processing. Thus, we conclude that the procedural aspects of organizational justice theory can explain developers perception of fairness. The findings of this study can be utilized further to assist development teams in integrating fairness in the ML application development lifecycle. It will also motivate ML developers and organizations to develop best practices for assessing the fairness of ML-based applications.

Integrating Edge-AI in Structural Health Monitoring domain

Structural health monitoring (SHM) tasks like damage detection are crucial for decision-making regarding maintenance and deterioration. For example, crack detection in SHM is crucial for bridge maintenance as crack progression can lead to structural instability. However, most AI/ML models in the literature have low latency and late inference time issues while performing in real-time environments. This study aims to explore the integration of edge-AI in the SHM domain for real-time bridge inspections. Based on edge-AI literature, its capabilities will be valuable integration for a real-time decision support system in SHM tasks such that real-time inferences can be performed on physical sites. This study will utilize commercial edge-AI platforms, such as Google Coral Dev Board or Kneron KL520, to develop and analyze the effectiveness of edge-AI devices. Thus, this study proposes an edge AI framework for the structural health monitoring domain. An edge-AI-compatible deep learning model is developed to validate the framework to perform real-time crack classification. The effectiveness of this model will be evaluated based on its accuracy, the confusion matrix generated, and the inference time observed in a real-time setting.