Pavan K. Turaga

• Ph.D. University of Maryland
• Professor (Associate) at Arizona State University

Human mobility analysis at urban-scale requires models to represent the complex nature of human movements, which in turn are affected by accessibility to nearby points of interest, underlying socioeconomic factors of a place, and local transport choices for people living in a geographic region. In this work, we represent human mobility and the asso...

Text-to-3D generation saw dramatic advances in recent years by leveraging Text-to-Image models. However, most existing techniques struggle with compositional prompts, which describe multiple objects and their spatial relationships. They often fail to capture fine-grained inter-object interactions. We introduce DecompDreamer, a Gaussian splatting-ba...

Rehabilitation is essential and critical for post-stroke patients, addressing both physical and cognitive aspects. Stroke predominantly affects older adults, with 75% of cases occurring in individuals aged 65 and older, underscoring the urgent need for tailored rehabilitation strategies in aging populations. Despite the critical role therapists pla...

The analysis of wearable sensor data has enabled many successes in several applications. To represent the high-sampling rate time-series with sufficient detail, the use of topological data analysis (TDA) has been considered, and it is found that TDA can complement other time-series features. Nonetheless, due to the large time consumption and high c...

Understanding high energy density physics (HEDP) is critical for advancements in fusion energy and astrophysics. The computational demands of the computer models used for HEDP studies have led researchers to explore deep learning methods to enhance simulation efficiency. This paper introduces HEDP-Gen, a framework for training and evaluating genera...

Knowledge distillation (KD) is a valuable technique for compressing large deep learning models into smaller, edge-suitable networks. However, conventional KD frameworks rely on pre-trained high-capacity teacher networks, which introduce significant challenges such as increased memory/storage requirements, additional training costs, and ambiguity in...

Polynomial functions have been employed to represent shape-related information in 2D and 3D computer vision, even from the very early days of the field. In this paper, we present a framework using polynomial-type basis functions to promote shape awareness in contemporary generative architectures. The benefits of using a learnable form of polynomial...

In applications involving analysis of wearable sensor data, machine learning techniques that use features from topological data analysis (TDA) have demonstrated remarkable performance. Persistence images (PIs) generated through TDA prove effective in capturing robust features, especially to signal perturbations, thus complementing classical time-se...

To address the data scarcity associated with 3D assets, 2D-lifting techniques such as Score Distillation Sampling (SDS) have become a widely adopted practice in text-to-3D generation pipelines. However, the diffusion models used in these techniques are prone to viewpoint bias and thus lead to geometric inconsistencies such as the Janus problem. To...

Deep learning methods have achieved a lot of success in various applications involving converting wearable sensor data to actionable health insights. A common application areas is activity recognition, where deep-learning methods still suffer from limitations such as sensitivity to signal quality, sensor characteristic variations, and variability b...

Deep learning has shown its efficacy in extracting useful features to solve various computer vision tasks. However, when the structure of the data is complex and noisy, capturing effective information to improve performance is very difficult. To this end, topological data analysis (TDA) has been utilized to derive useful representations that can co...

Deep Neural Networks are often vulnerable to adversarial attacks. Neural Architecture Search (NAS), one of the tools for developing novel deep neural architectures, demonstrates superior performance in prediction accuracy in various machine learning applications. However, the performance of a neural architecture discovered by NAS against adversaria...

The analysis of wearable sensor data has enabled many successes in several applications. To represent the high-sampling rate time-series with sufficient detail, the use of topological data analysis (TDA) has been considered, and it is found that TDA can complement other time-series features. Nonetheless, due to the large time consumption and high c...

Wearable sensor data analysis with persistence features generated by topological data analysis (TDA) has achieved great successes in various applications, however, it suffers from large computational and time resources for extracting topological features. In this paper, our approach utilizes knowledge distillation (KD) that involves the use of mult...

In this paper, we address the problem of adapting models from a source domain to a target domain, a task that has become increasingly important due to the brittle generalization of deep neural networks. While several test-time adaptation techniques have emerged, they typically rely on synthetic toolbox data augmentations in cases of limited target...

Time-series are commonly susceptible to various types of corruption due to sensor-level changes and defects which can result in missing samples, sensor and quantization noise, unknown calibration, unknown phase shifts etc. These corruptions cannot be easily corrected as the noise model may be unknown at the time of deployment. This also results in...

Implicit neural representations (INR) have gained significant popularity for signal and image representation for many end-tasks, such as superresolution, 3D modeling, and more. Most INR architectures rely on sinusoidal positional encoding, which accounts for high-frequency information in data. However, the finite encoding size restricts the model's...

Knowledge distillation as a broad class of methods has led to the development of lightweight and memory efficient models, using a pre-trained model with a large capacity (teacher network) to train a smaller model (student network). Recently, additional variations for knowledge distillation, utilizing activation maps of intermediate layers as the so...

Monitoring change is an important aspect of understanding variations in spatial–temporal processes. Recently, 'big data' on mobility, which are detailed across space and time, have become increasingly available from crowdsourced platforms. New methods are needed to best utilize the high spatial and temporal resolution of such data for monitoring pu...

Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, geometry-based alignment methods, e.g., Orthogonal Procrustes Alignment (OPA), formed an important class of solutions to this problem. Despite their mathematical tractability, they rarely produce effec...

Mixup is a popular data augmentation technique based on creating new samples by linear interpolation between two given data samples, to improve both the generalization and robustness of the trained model. Knowledge distillation (KD), on the other hand, is widely used for model compression and transfer learning, which involves using a larger network...

Knowledge distillation as a broad class of methods has led to the development of lightweight and memory efficient models, using a pre-trained model with a large capacity (teacher network) to train a smaller model (student network). Recently, additional variations for knowledge distillation, utilizing activation maps of intermediate layers as the so...

Converting wearable sensor data to actionable health insights has witnessed large interest in recent years. Deep learning methods have been utilized in and have achieved a lot of successes in various applications involving wearables fields. However, wearable sensor data has unique issues related to sensitivity and variability between subjects, and...

The problem of adapting models from a source domain using data from any target domain of interest has gained prominence, thanks to the brittle generalization in deep neural networks. While several test-time adaptation techniques have emerged, they typically rely on synthetic data augmentations in cases of limited target data availability. In this p...

In this paper, we develop a formulation to utilize reinforcement learning and sampling-based robotics planning to derive low free energy transition pathways between two known states. Our formulation uses Jarzynski's equality and the stiff-spring approximation to obtain point estimates of energy, and construct an informed path search with atomistic...

A foundational requirement of a deployed ML model is to generalize to data drawn from a testing distribution that is different from training. A popular solution to this problem is to adapt a pre-trained model to novel domains using only unlabeled data. In this paper, we focus on a challenging variant of this problem, where access to the original so...

Background The evidence-based quantification of the relation between changes in movement quality and functionality can assist clinicians in achieving more effective structuring or adaptations of therapy. Facilitating this quantification through computational tools can also result in the generation of large-scale data sets that can inform automated...

Deep networks for image classification often rely more on texture information than object shape. While efforts have been made to make deep-models shape-aware, it is often difficult to make such models simple, interpretable, or rooted in known mathematical definitions of shape. This paper presents a deep-learning model inspired by geometric moments,...

The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical need for techniques to rigorously introspect models and thereby ensure that they behave reliably. This has led to the design of explainable AI techniques that uncover the relationships between discernible data signatures and model predictions. In this c...

Deep neural networks are parametrized by several thousands or millions of parameters, and have shown tremendous success in many classification problems. However, the large number of parameters makes it difficult to integrate these models into edge devices such as smartphones and wearable devices. To address this problem, knowledge distillation (KD)...

Deep neural networks are parametrized by several thousands or millions of parameters, and have shown tremendous success in many classification problems. However, the large number of parameters makes it difficult to integrate these models into edge devices such as smartphones and wearable devices. To address this problem, knowledge distillation (KD)...

Domain generalization (DG) methods aim to develop models that generalize to settings where the test distribution is different from the training data. In this paper, we focus on the challenging problem of multi-source zero-shot DG, where labeled training data from multiple source domains is available but with no access to data from the target domain...

Digital health data are multimodal and high-dimensional. A patient’s health state can be characterized by a multitude of signals including medical imaging, clinical variables, genome sequencing, conversations between clinicians and patients, and continuous signals from wearables, among others. This high volume, personalized data stream aggregated o...

In this paper, we develop a Wasserstein autoencoder (WAE) with a hyperspherical prior for multimodal data in the application of inertial confinement fusion. Unlike a typical hyperspherical generative model that requires computationally inefficient sampling from distributions like the von Mis Fisher, we sample from a normal distribution followed by...

Multi-baseline stereo is any number of techniques for computing depth maps from several, typically many, photographs of a scene with known camera parameters.

Artificial intelligence methods such as deep neural networks promise unprecedented capabilities in healthcare, from diagnosing diseases to prescribing treatments. While this can eventually produce a valuable suite of tools for automating clinical workflows, a critical step forward is to ensure that the predictive models are reliable and to enable a...

We are developing a system for long term Semi-Automated Rehabilitation At the Home (SARAH) that relies on low-cost and unobtrusive video-based sensing. We present a cyber-human methodology used by the SARAH system for automated assessment of upper extremity stroke rehabilitation at the home. We propose a hierarchical model for automatically segment...

We are developing a system for long-term Semi-Automated Rehabilitation At the Home (SARAH) that relies on low-cost and unobtrusive video-based sensing. We present a cyber-human methodology used by the SARAH system for automated assessment of upper extremity stroke rehabilitation at the home. We propose a hierarchical model for automatically segment...

Four state-of-the-art Deep Learning-based Convolutional Neural Networks (DCNN) were applied to automate the semantic segmentation of a 3D Transmission x-ray Microscopy (TXM) nanotomography image data. The standard U-Net architecture as baseline along with UNet++, PSPNet, and DeepLab v3+ networks were trained to segment the microstructural features...

Deep neural networks have increasingly been used as an auxiliary tool in healthcare applications, due to their ability to improve performance of several diagnosis tasks. However, these methods are not widely adopted in clinical settings due to the practical limitations in the reliability, generalizability, and interpretability of deep learning base...

Sedentary behavior (i.e., waking behaviors in the seated/lying position at low energy expenditure), or sitting, has emerged as a potential risk factor for numerous chronic diseases and all-cause mortality during the last decade. Working adults accumulate large number of sitting hours at work and interventions have been developed to reduce sitting i...

This collaborative transdisciplinary research across the university was initiated with a seed grant from two different colleges to solve one of the major public health problems specifically focusing on humans’ sedentary behavior at the workplace. Sedentary behavior has emerged as a potential risk factor for numerous chronic diseases and all-cause m...

Motion capture (mocap) and time-of-flight based sensing of human actions are becoming increasingly popular modalities to perform robust activity analysis. Applications range from action recognition to quantifying movement quality for health applications. While marker-less motion capture has made great progress, in critical applications such as heal...

Standard deep learning models that employ the categorical cross-entropy loss are known to perform well at image classification tasks. However, many standard models thus obtained often exhibit issues like feature redundancy, low interpretability, and poor calibration. A body of recent work has emerged that has tried addressing some of these challeng...

The efficiency of solar energy farms requires detailed analytics and information on each panel regarding voltage, current, temperature, and irradiance. Monitoring utility-scale solar arrays was shown to minimize the cost of maintenance and help optimize the performance of the photo-voltaic arrays under various conditions. We describe a project that...

Resilience to serious societal challenges requires systems level thinking about complex interactions and cascading impacts of shocks and stressors to our economy, environment, and social fabric. Solutions increasingly depend on building knowledge that is rigorously empirical, transdisciplinary, and human-centered. Rooted in space and time, individu...

Application and use of deep learning algorithms for different healthcare applications is gaining interest at a steady pace. However, use of such algorithms can prove to be challenging as they require large amounts of training data that capture different possible variations. This makes it difficult to use them in a clinical setting since in most hea...

Compressive sensing cameras hold the promise of cost-effective hardware, lower data rates, and improved video quality, particularly outside the visible spectrum. However, these improvements involve significant computational cost, as sensor output must be reconstructed in order to form an image viewable by a human. This paper describes a prototype a...

Application and use of deep learning algorithms for different healthcare applications is gaining interest at a steady pace. However, use of such algorithms can prove to be challenging as they require large amounts of training data that capture different possible variations. This makes it difficult to use them in a clinical setting since in most hea...

At present, the vast majority of human subjects with neurological disease are still diagnosed through in-person assessments and qualitative analysis of patient data. In this paper, we propose to use Topological Data Analysis (TDA) together with machine learning tools to automate the process of Parkinson's disease classification and severity assessm...

In this paper, we propose the generative patch prior (GPP) that defines a generative prior for compressive image recovery, based on patch-manifold models. Unlike learned, image-level priors that are restricted to the range space of a pre-trained generator, GPP can recover a wide variety of natural images using a pre-trained patch generator. Additio...

Topological features such as persistence diagrams and their functional approximations like persistence images (PIs) have been showing substantial promise for machine learning and computer vision applications. This is greatly attributed to the robustness topological representations provide against different types of physical nuisance variables seen...

Application and use of deep learning algorithms for different healthcare applications is gaining interest at a steady pace. However, use of such algorithms can prove to be challenging as they require large amounts of training data that capture different possible variations. This makes it difficult to use them in a clinical setting since in most hea...

Input transformation based defense strategies fall short in defending against strong adversarial attacks. Some successful defenses adopt approaches that either increase the randomness within the applied transformations, or make the defense computationally intensive, making it substantially more challenging for the attacker. However, it limits the a...

Deep-learning architectures for classification problems involve the cross-entropy loss sometimes assisted with auxiliary loss functions like center loss, contrastive loss and triplet loss. These auxiliary loss functions facilitate better discrimination between the different classes of interest. However, recent studies hint at the fact that these lo...

We address the new problem of complex scene completion from sparse label maps. We use a two-stage deep network based method, called `Halluci-Net', that uses object co-occurrence relationships to produce a dense and complete label map. The generated dense label map is fed into a state-of-the-art image synthesis method to obtain the final image. The...

At present, the vast majority of human subjects with neurological disease are still diagnosed through in-person assessments and qualitative analysis of patient data. In this paper, we propose to use Topological Data Analysis (TDA) together with machine learning tools to automate the process of Parkinson's disease classification and severity assessm...

A cyber physical system approach for a utility-scale photovoltaic (PV) array monitoring and control is presented in this article. This system consists of sensors that capture voltage, current, temperature, and irradiance parameters for each solar panel which are then used to detect, predict and control the performance of the array. More specificall...

A cyber physical system approach for a utility-scale photovoltaic (PV) array monitoring and control is presented in this article. This system consists of sensors that capture voltage, current, temperature, and irradiance parameters for each solar panel which are then used to detect, predict and control the performance of the array. More specificall...

In Chapter 2, we elaborate on several faults (soiling, module degradation, shading) that cause variation in the power output of a PV array. However, since the power output is based on sun’s irradiance there is high uncertainty and intermittency due to variable weather conditions which makes it difficult to incorporate PV arrays into existing power...

Detecting faults in PV is important for the overall efficiency and reliability of a solar power plant. Ground faults, series and parallel arc faults, high resistance connections, soiling, and partial shadowing need to be detected. The I–V data in a PV array can be measured at the panellevel. This data is useful in predicting possible ground faults...

The production of PV energy is affected by external conditions such as partial shading, varying temperatures, and soiling of PV panels. Among these, partial shading causes a significant reduction in power. On the other hand, the energy production can also be affected if a PV array system has faulty modules [13] as discussed in Chapter 3. Partial sh...

The efficiency of solar energy farms requires detailed analytics and information on each panel regarding voltage, current, temperature, and irradiance. Monitoring utility-scale solar arrays was shown to minimize cost of maintenance and help optimize the performance of the array under various conditions. We describe the design of an 18 kW experiment...

Exploiting known semantic relationships between fine-grained tasks is critical to the success of recent model agnostic approaches. These approaches often rely on meta-optimization to make a model robust to systematic task or domain shifts. However, in practice, the performance of these methods can suffer, when there are no coherent semantic relatio...

Several recent studies have employed real-time feedback (RTF) of gait parameters to improve walking patterns in Parkinson’s disease (PD). In earlier work, we investigated the effects of RTF of step length and back angle during treadmill walking and observed that people with PD could follow the feedback and utilize it to modulate movements favorably...

Rapid advances in cost-effective and non-invasive depth sensors, and the development of reliable and real-time 3D skeletal data estimation algorithms, have opened up a new application area in computer vision - statistical analysis of human kinematic data for fast, automated assessment of body movements. These assessments can play important roles in...

Natural images suffer from defocus blur due to the presence of objects at different depths from the camera. Automatic estimation of spatially-varying sharpness has several applications including depth estimation, image quality assessment, information retrieval, image restoration among others. In this paper, we propose a sharpness metric based on th...

Learning representations that can disentangle explanatory attributes underlying the data improves interpretabilty as well as provides control on data generation. Various learning frameworks such as VAEs, GANs and auto-encoders have been used in the literature to learn such representations. Most often, the latent space is constrained to a partitione...

Ground-based sky imaging has won popularity due to its higher temporal and spatial resolution when compared with satellite or air-borne sky imaging systems. Cloud identification and segmentation is the first step in several areas, such as climate research and lately photovoltaic power generation forecast. Cloud-sky segmentation involves several var...