Search for: All records

In recent years, neural networks (NNs) have been embraced by several scientific and engineering disciplines for diverse modeling and inferencing applications. The importance of quantifying the confidence in NN predictions has escalated due to the increasing adoption of these decision models. Nevertheless, conventional NN do not furnish uncertainty estimates associated with their predictions and are therefore ill-calibrated. Uncertainty quantification techniques offer probability distributions or CIs to represent the uncertainty associated with NN predictions, instead of solely presenting the point predictions/estimates. Once the uncertainty in NN is quantified, it is crucial to leverage this information to modify training objectives and improve the accuracy and reliability of the corresponding decision models. This work presents a novel framework to utilize the knowledge of input and output uncertainties in NN to guide querying process in the context of Active Learning. We also derive the lower and upper bounds for label complexity. The efficacy of the proposed framework is established by conducting experiments across classification and regression tasks. 

Ovarian cancer survival depends strongly on the time of diagnosis. Detection at stage 1 must be the goal of liquid biopsies for ovarian cancer detection. We report the development and validation of graphene-based optical nanobiosensors (G-NBSs) that quantify the activities of a panel of proteases, which were selected to provide a crowd response that is specific for ovarian cancer. These G-NBSs consist of few-layer explosion graphene featuring a hydrophilic coating, which is linked to fluorescently labeled highly selective consensus sequences for the proteases of interest, as well as a fluorescent dye. The panel of G-NBSs showed statistically significant differences in protease activities when comparing localized (early-stage) ovarian cancer with both metastatic (late-stage) and healthy control groups. A hierarchical framework integrated with active learning (AL) as a prediction and analysis tool for early-stage detection of ovarian cancer was implemented, which obtained an overall accuracy score of 94.5%, with both a sensitivity and specificity of 0.94. 

Cyber-Physical-Human Systems (CPHS) interconnect humans, physical plants and cyber infrastructure across space and time. Industrial processes, electromechanical systems operations and medical diagnosis are some examples where one can see the intersection of humans, physical and cyber components. Emergence of Artificial Intelligence (AI) based computational models, controllers and decision support engines have improved the efficiency and cost effectiveness of such systems and processes. These CPHS typically involve a collaborative decision environment, comprising of AI-based models and human experts. Active Learning (AL) is a category of AI algorithms which aims to learn an efficient decision model by combining domain expertise of the human expert and computational capabilities of the AI model. Given the indispensable role of humans and lack of understanding about human behavior in collaborative decision environments, modeling and prediction of behavioral biases is a critical need. This paper, for the first time, introduces different behavioral biases within an AL context and investigates their impacts on the performance of AL strategies. The modelling of behavioral biases is demonstrated using experiments conducted on a real-world pancreatic cancer dataset. It is observed that classification accuracy of the decision model reduces by at least 20% in case of all the behavioral biases.