Narrow Results

This paper presents a 65nm CMOS low-power, highly linear variable gain amplifier (VGA) suitable for biomedical applications. Typical biological signal amplitudes are in the 0.5–100mV range, and therefore require circuits with a wide dynamic range. Existing VGA architectures mostly exhibit a poor linearity, due to very low local feedback loop-gain. A technique to increase the loop-gain has been explored by adding additional feedback to the tail current source of the input differential pair. Stability analysis of the proposed technique was undertaken with pole-zero analysis. A prototype of Analog Front End (AFE) has been designed to provide 25–50 dB gain, and post-layout simulations showed a 15dB reduction in the harmonic distortion for 20mV pk-pk input signal compared to the conventional architecture. The circuit occupies 3,108$\mu$m² silicon area and consumes 0.43 $\mu$A from a 1.2V power supply.

Phase error of the demodulation clock in the Coriolis vibratory gyroscope system allows the quadrature errors to leak into the sense channel and causes significant bias and temperature drift at the rate output. A phase self-correction method to suppress the temperature drift of the bias in gyroscopes is proposed. Through sweeping the demodulation clock phase and simultaneously monitoring the mechanical quadrature error output in gyroscopes, the optimal demodulation clock phase with minimum relatively phase shift is determined. Thus the bias influenced by the temperature and surroundings can be calibrated on-chip at start-up or when the environment changes drastically without the requirement of the complicated instruments. The proposed approach is validated by a silicon MEMS gyroscope with the natural frequency of 2.8kHz, which shows nearly 22 times improvement in the temperature sensitivity of the system bias, from 550mdeg/s/^∘C down to 24.7mdeg/s/^∘C.

Rising acceptance of machine learning driven decision support systems underscores the need for ensuring fairness for all stakeholders. This work proposes a novel approach to increase a Neural Network model’s fairness during the training phase. We offer a frame-work to create a family of diverse fairness enhancing regularization components that can be used in tandem with the widely accepted binary-cross-entropy based accuracy loss. We use Bias Parity Score (BPS), a metric that quantifies model bias with a single value, to build loss functions pertaining to different statistical measures — even for those that may not be developed yet. We analyze behavior and impact of the newly minted regularization components on bias. We explore their impact in the realm of recidivism and census-based adult income prediction. The results illustrate that apt fairness loss functions can mitigate bias without forsaking accuracy even for imbalanced datasets.

This paper presents some novel entropy estimators of a continuous random variable using simple random sampling (SRS), ranked set sampling (RSS), and double RSS (DRSS) schemes. The theoretical results of the proposed entropy estimators are derived. The proposed entropy estimators are compared in terms of the bias and the root mean squared errors, theoretically and numerically, with the Vasicek O. [A test for normality based on sample entropy, J. R. Stat. Soc. B38:54–59, 1976.] entropy estimators using SRS, RSS, and DRSS schemes. It turns out that the new novel entropy estimators are substantially better than the existing Vasicek’s entropy estimators.

This paper examines the performance of a new probability model developed in terms of the surface area and velocity of an aero-structure, and presents some relevant statistical inferences. Several examples will compare the robustness of three kinds of point estimators developed for the lift coefficient. Four different types of confidence intervals for the lift coefficient are also developed, and it is shown that the shortest length confidence interval is an UMA confidence interval. Using the probability model, the correlation coefficient between lift and velocity, and the relevant regression slope are computed. The inferences and the results of this paper can be used particularly in the designing process of an aero-structure, especially when there is some uncertainty about its surface area; this provides some flexibilities for aerodynamicists in determining some of the unknown design characteristics.

Innovations in human-centered biomedical informatics are often developed with the eventual goal of real-world translation. While biomedical research questions are usually answered in terms of how a method performs in a particular context, we argue that it is equally important to consider and formally evaluate the ethical implications of informatics solutions. Several new research paradigms have arisen as a result of the consideration of ethical issues, including but not limited for privacy-preserving computation and fair machine learning. In the spirit of the Pacific Symposium on Biocomputing, we discuss broad and fundamental principles of ethical biomedical informatics in terms of Olelo Noeau, or Hawaiian proverbs and poetical sayings that capture Hawaiian values. While we emphasize issues related to privacy and fairness in particular, there are a multitude of facets to ethical biomedical informatics that can benefit from a critical analysis grounded in ethics.

Point estimation can be used in both predictive and descriptive data mining tasks. Three classical point estimation methods — the method of moments, maximum likelihood estimation, and the Expectation-Maximization algorithm — are discussed in this chapter, followed by a review of measurements of estimation performance. This chapter intends to introduce basic concepts and methods of point estimation. These concepts and methods are the basis for more advanced estimation techniques.

In machine learning, a bias occurs whenever training sets are not representative for the test data, which results in unreliable models. The most common biases in data are arguably class imbalance and covariate shift. In this work, we aim to shed light on this topic in order to increase the overall attention to this issue in the field of machine learning. We propose a scalable novel framework for reducing multiple biases in high-dimensional data sets in order to train more reliable predictors. We apply our methodology to the detection of irregular power usage from real, noisy industrial data. In emerging markets, irregular power usage, and electricity theft in particular, may range up to 40% of the total electricity distributed. Biased data sets are of particular issue in this domain. We show that reducing these biases increases the accuracy of the trained predictors. Our models have the potential to generate significant economic value in a real world application, as they are being deployed in a commercial software for the detection of irregular power usage.

Artificial Intelligence (AI) algorithms showcase the potential to steer a paradigm shift in clinical medicine, especially medical imaging. Concerns associated with model generalizability and biases necessitate rigorous external validation of AI algorithms prior to their adoption into clinical workflows. To address the barriers associated with patient privacy, intellectual property, and diverse model requirements, we introduce ClinValAI, a framework for establishing robust cloud-based infrastructures to clinically validate AI algorithms in medical imaging. By featuring dedicated workflows for data ingestion, algorithm scoring, and output processing, we propose an easily customizable method to assess AI models and investigate biases. Our novel orchestration mechanism facilitates utilizing the complete potential of the cloud computing environment. ClinValAI’s input auditing and standardization mechanisms ensure that inputs consistent with model prerequisites are provided to the algorithm for a streamlined validation. The scoring workflow comprises multiple steps to facilitate consistent inferencing and systematic troubleshooting. The output processing workflow helps identify and analyze samples with missing results and aggregates final outputs for downstream analysis. We demonstrate the usability of our work by evaluating a state-of-the-art breast cancer risk prediction algorithm on a large and diverse dataset of 2D screening mammograms. We perform comprehensive statistical analysis to study model calibration and evaluate performance on important factors, including breast density, age, and race, to identify latent biases. ClinValAI provides a holistic framework to validate medical imaging models and has the potential to advance the development of generalizable AI models in clinical medicine and promote health equity.