Mahesh K. Banavar

Sai Zhang, Cihan Tepedelenlioglu, Mahesh K. Banavar et al.

A distributed consensus algorithm for estimating the maximum value of the initial measurements in a sensor network with communication noise is proposed. In the absence of communication noise, max estimation can be done by updating the state value with the largest received measurements in every iteration at each sensor. In the presence of communication noise, however, the maximum estimate will incorrectly drift and the estimate at each sensor will diverge. As a result, a soft-max approximation together with a non-linear consensus algorithm is introduced herein. A design parameter controls the trade-off between the soft-max error and convergence speed. An analysis of this trade-off gives a guideline towards how to choose the design parameter for the max estimate. We also show that if some prior knowledge of the initial measurements is available, the consensus process can converge faster by using an optimal step size in the iterative algorithm. A shifted non-linear bounded transmit function is also introduced for faster convergence when sensor nodes have some prior knowledge of the initial measurements. Simulation results corroborating the theory are also provided.

Chinmay Sahu, Mahesh Banavar, Stephanie Schuckers

In this paper, we propose a new technique to uniquely classify and identify multiple users accessing a single application using keystroke dynamics. This problem is usually encountered when multiple users have legitimate access to shared computers and accounts, where, at times, one user can inadvertently be logged in on another user's account. Since the login processes are usually bypassed at this stage, we rely on keystroke dynamics in order to tell users apart. Our algorithm uses the quantile transform and techniques from localization to classify and identify users. Specifically, we use an algorithm known as ordinal Unfolding based Localization (UNLOC), which uses only ordinal data obtained from comparing distance proxies, by "locating" users in a reduced PCA/Kernel-PCA/t-SNE space based on their typing patterns. Our results are validated with the help of benchmark keystroke datasets and show that our algorithm outperforms other methods.

Chinmay Sahu, Blaine Ayotte, Mahesh K. Banavar

In this innovative practice work-in-progress paper, we compare two different methods to teach machine learning concepts to undergraduate students in Electrical Engineering. While machine learning is now being offered as a senior-level elective in several curricula, this does not mean all students are exposed to it. Exposure to the concepts and practical applications of machine learning will assist in the creation of a workforce ready to tackle problems related to machine learning, currently a hot topic in industry. Preliminary assessments indicate that this approach promotes student learning. While students prefer the proposed side-by-side teaching approach, numerical comparisons show that the workshop approach may be more effective for student learning, indicating that further work in this area is required.

Swati Kar, Soumyabrata Dey, Mahesh K Banavar et al.

This paper presents the development of an Artificial Intelligence (AI) based fighter jet agent within a customized Pygame simulation environment, designed to solve multi-objective tasks via deep reinforcement learning (DRL). The jet's primary objectives include efficiently navigating the environment, reaching a target, and selectively engaging or evading an enemy. A reward function balances these goals while optimized hyperparameters enhance learning efficiency. Results show more than 80\% task completion rate, demonstrating effective decision-making. To enhance transparency, the jet's action choices are analyzed by comparing the rewards of the actual chosen action (factual action) with those of alternate actions (counterfactual actions), providing insights into the decision-making rationale. This study illustrates DRL's potential for multi-objective problem-solving with explainable AI. Project page is available at: \href{https://github.com/swatikar95/Autonomous-Fighter-Jet-Navigation-and-Combat}{Project GitHub Link}.

Joseph Drahos, Richard Plesh, Keivan Bahmani et al.

Face recognition (FR) systems have become widely used and readily available in recent history. However, differential performance between certain demographics has been identified within popular FR models. Skin tone differences between demographics can be one of the factors contributing to the differential performance observed in face recognition models. Skin tone metrics provide an alternative to self-reported race labels when such labels are lacking or completely not available e.g. large-scale face recognition datasets. In this work, we provide a further analysis of the generalizability of the Skin Reflectance Estimate based on Dichromatic Separation (SREDS) against other skin tone metrics and provide a use case for substituting race labels for SREDS scores in a privacy-preserving learning solution. Our findings suggest that SREDS consistently creates a skin tone metric with lower variability within each subject and SREDS values can be utilized as an alternative to the self-reported race labels at minimal drop in performance. Finally, we provide a publicly available and open-source implementation of SREDS to help the research community. Available at https://github.com/JosephDrahos/SREDS

Arfina Rahman, Mahesh Banavar

Photoplethysmography (PPG) signals, which measure changes in blood volume in the skin using light, have recently gained attention in biometric authentication because of their non-invasive acquisition, inherent liveness detection, and suitability for low-cost wearable devices. However, PPG signal quality is challenged by motion artifacts, illumination changes, and inter-subject physiological variability, making robust feature extraction and classification crucial. This study proposes a lightweight and cost-effective biometric authentication framework based on PPG signals extracted from low-frame-rate fingertip videos. The CFIHSR dataset, comprising PPG recordings from 46 subjects at a sampling rate of 14 Hz, is employed for evaluation. The raw PPG signals undergo a standard preprocessing pipeline involving baseline drift removal, motion artifact suppression using Principal Component Analysis (PCA), bandpass filtering, Fourier-based resampling, and amplitude normalization. To generate robust representations, each one-dimensional PPG segment is converted into a two-dimensional time-frequency scalogram via the Continuous Wavelet Transform (CWT), effectively capturing transient cardiovascular dynamics. We developed a hybrid deep learning model, termed CVT-ConvMixer-LSTM, by combining spatial features from the Convolutional Vision Transformer (CVT) and ConvMixer branches with temporal features from a Long Short-Term Memory network (LSTM). The experimental results on 46 subjects demonstrate an authentication accuracy of 98%, validating the robustness of the model to noise and variability between subjects. Due to its efficiency, scalability, and inherent liveness detection capability, the proposed system is well-suited for real-world mobile and embedded biometric security applications.

Olaoluwayimika Olugbenle, Logan Drake, Naveenkumar G. Venkataswamy et al.

We present our work on leveraging low-frame-rate monochrome (blue light) videos of fingertips, captured with an off-the-shelf fingerprint capture device, to extract vital signs and identify users. These videos utilize photoplethysmography (PPG), commonly used to measure vital signs like heart rate. While prior research predominantly utilizes high-frame-rate, multi-wavelength PPG sensors (e.g., infrared, red, or RGB), our preliminary findings demonstrate that both user identification and vital sign extraction are achievable with the low-frame-rate data we collected. Preliminary results are promising, with low error rates for both heart rate estimation and user authentication. These results indicate promise for effective biometric systems. We anticipate further optimization will enhance accuracy and advance healthcare and security.

Dharambir Mahto, Prashant Yadav, Mahesh Banavar et al.

Sepsis is a life-threatening condition affecting over 48.9 million people globally and causing 11 million deaths annually. Despite medical advancements, predicting sepsis remains a challenge due to non-specific symptoms and complex pathophysiology. The SXI++ LNM is a machine learning scoring system that refines sepsis prediction by leveraging multiple algorithms and deep neural networks. This study aims to improve robustness in clinical applications and evaluates the predictive performance of the SXI++ LNM for sepsis prediction. The model, utilizing a deep neural network, was trained and tested using multiple scenarios with different dataset distributions. The model's performance was assessed against unseen test data, and accuracy, precision, and area under the curve (AUC) were calculated. THE SXI++ LNM outperformed the state of the art in three use cases, achieving an AUC of 0.99 (95% CI: 0.98-1.00). The model demonstrated a precision of 99.9% (95% CI: 99.8-100.0) and an accuracy of 99.99% (95% CI: 99.98-100.0), maintaining high reliability.

Mahesh K. Banavar, Shandeepa Wickramasinghe, Monalisa Achalla et al.

A main challenge in target localization arises from the lack of reliable distance measures. This issue is especially pronounced in indoor settings due to the presence of walls, floors, furniture, and other dynamically changing conditions such as the movement of people and goods, varying temperature, and airflows. Here, we develop a new computational framework to estimate the location of a target without the need for reliable distance measures. The method, which we term Ordinal UNLOC, uses only ordinal data obtained from comparing the signal strength from anchor pairs at known locations to the target. Our estimation technique utilizes rank aggregation, function learning as well as proximity-based unfolding optimization. As a result, it yields accurate target localization for common transmission models with unknown parameters and noisy observations that are reminiscent of practical settings. Our results are validated by both numerical simulations and hardware experiments.

Blaine Ayotte, Mahesh K. Banavar, Daqing Hou et al.

Keystroke dynamics study the way in which users input text via their keyboards. Having the ability to differentiate users, typing behaviors can unobtrusively form a component of a behavioral biometric recognition system to improve existing account security. Keystroke dynamics systems on free-text data have previously required 500 or more characters to achieve reasonable performance. In this paper, we propose a novel instance-based graph comparison algorithm called the instance-based tail area density (ITAD) metric to reduce the number of keystrokes required to authenticate users. Additionally, commonly used features in the keystroke dynamics literature, such as monographs and digraphs, are all found to be useful in informing who is typing. The usefulness of these features for authentication is determined using a random forest classifier and validated across two publicly available datasets. Scores from the individual features are fused to form a single matching score. With the fused matching score and our ITAD metric, we achieve equal error rates (EERs) for 100 and 200 testing digraphs of 9.7% and 7.8% for the Clarkson II dataset, improving upon state-of-the-art of 35.3% and 15.3%.