VMVishal Monga

Vishal Monga

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Vishal Monga has a total of 118 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers
    Open Access

    Intervention in Health Misinformation Using Large Language Models for Automated Detection, Thematic Analysis, and Inoculation: Case Study on COVID-19

    by Samira Malek, Christopher Griffin, Robert D Fraleigh, Robert Lennon, Vishal Monga, Lijiang Shen

    Background: The rapid growth of social media as an information channel has enabled the swift spread of inaccurate or false health information, significantly impacting public health. This widespread dissemination of misinformation has caused confusion, eroded trust in health authorities, led to noncompliance with health guidelines, and encouraged risky health behaviors. Understanding the dynamics of misinformation on social media is essential for devising effective public health communication strategies. Objective: This study aims to present a comprehensive and automated approach that leverages large language models (LLMs) and machine learning techniques to detect misinformation on social media, uncover the underlying causes and themes, and generate refutation arguments, facilitating control of its spread and promoting public health outcomes by inoculating people against health misinformation. Methods: We use 2 datasets to train 3 LLMs, namely, BERT, T5, and GPT-2, to classify documents into 2 categories: misinformation and nonmisinformation. In addition, we use a separate dataset to identify misinformation topics. To analyze these topics, we applied 3 topic modeling algorithms—Latent Dirichlet Allocation, Top2Vec, and BERTopic—and selected the optimal model based on performance evaluated across 3 metrics. Using a prompting approach, we extract sentence-level representations for the topics to uncover their underlying themes. Finally, we design a prompt text capable of identifying misinformation themes effectively. Results: The trained BERT model demonstrated exceptional performance, achieving 98% accuracy in classifying misinformation and nonmisinformation, with a 44% reduction in false-positive rates for artificial intelligence–generated misinformation. Among the 3 topic modeling approaches used, BERTopic outperformed the others, achieving the highest metrics with a Coherence Value of 0.41, Normalized Pointwise Mutual Information of −0.086, and Inverse Rank-Biased Overlap of 0.99. To address the issue of unclassified documents, we developed an algorithm to assign each document to its closest topic. In addition, we proposed a novel method using prompt engineering to generate sentence-level representations for each topic, achieving a 99.6% approval rate as “appropriate” or “somewhat appropriate” by 3 independent raters. We further designed a prompt text to identify themes of misinformation topics and developed another prompt capable of detecting misinformation themes with 82% accuracy. Conclusions: This study presents a comprehensive and automated approach to addressing health misinformation on social media using advanced machine learning and natural language processing techniques. By leveraging LLMs and prompt engineering, the system effectively detects misinformation, identifies underlying themes, and provides explanatory responses to combat its spread. The proposed method was tested on an English language COVID-19–related dataset and has not been evaluated on real-world online social media data; the experiments were conducted offline.


  • GLAPAL-H: Global, Local, and Parts Aware Learner for Hydrocephalus Infection Diagnosis in Low-Field MRI

    by Srijit Mukherjee, Kelsey Templeton, Starlin Tindimwebwa, Pei-Yi Lin, Jason Sutin, Mingzhao Yu, Mallory Peterson, Chip Truwit, Steven J. Schiff, Vishal Monga

    Objective: The study aims to develop a method for differentiating between healthy, post-infectious hydrocephalus (PIH), and non-post-infectious hydrocephalus (NPIH) in infants using low-field MRI, which is a safer, low-cost alternative to CT scans. The study develops a custom approach that captures hydrocephalic etiology while simultaneously addressing quality issues encountered in low-field MRI. Methods: Specifically, we propose GLAPAL-H, a Global, Local, And Parts Aware Learner, which develops a multi-task architecture with global, local, and parts segmentation branches. The architecture segments images into brain tissue and CSF while using a shallow CNN for local feature extraction and develops a parallel deep CNN branch for global feature extraction. Three regularized training loss functions are developed — one for each of global, local, and parts components. The global regularizer captures holistic features, the local focuses on fine details, and the parts regularizer learns soft segmentation masks that enable local features to capture hydrocephalic etiology. Results: The study's results show that GLAPAL-H outperforms state-of-the-art alternatives, including CT-based approaches, for both Two-Class (PIH vs. NPIH) and Three-Class (PIH vs. NPIH vs. Healthy) classification tasks in accuracy, interpretability, and generalizability. Conclusion/Significance: GLAPAL-H highlights the potential of low-field MRI as a safer, low-cost alternative to CT imaging for pediatric hydrocephalus infection diagnosis and management. Practically, GLAPAL-H demonstrates robustness against quantity and quality of training imagery, enhancing its deployability.


  • Open Access

    CLIF-Net: Intersection-guided Cross-view Fusion Network for Infection Detection from Cranial Ultrasound

    by Mingzhao Yu, Mallory R. Peterson, Kathy Burgoine, Thaddeus Harbaugh, Peter Olupot-Olupot, Melissa Gladstone, Cornelia Hagmann, Frances M. Cowan, Andrew Weeks, Sarah U. Morton, et al.

    This paper addresses the problem of detecting possible serious bacterial infection (pSBI) of infancy, i.e. a clinical presentation consistent with bacterial sepsis in newborn infants using cranial ultrasound (cUS) images. The captured image set for each patient enables multiview imagery: coronal and sagittal, with geometric overlap. To exploit this geometric relation, we develop a new learning framework, called the intersection-guided Crossview Local-and Image-level Fusion Network (CLIF-Net). Our technique employs two distinct convolutional neural network branches to extract features from coronal and sagittal images with newly developed multi-level fusion blocks. Specifically, we leverage the spatial position of these images to locate the intersecting region. We then identify and enhance the semantic features from this region across multiple levels using cross-attention modules, facilitating the acquisition of mutually beneficial and more representative features from both views. The final enhanced features from the two views are then integrated and projected through the image-level fusion layer, outputting pSBI and non-pSBI class probabilities. We contend that our method of exploiting multi-view cUS images enables a first of its kind, robust 3D representation tailored for pSBI detection. When evaluated on a dataset of 302 cUS scans from Mbale Regional Referral Hospital in Uganda, CLIF-Net demonstrates substantially enhanced performance, surpassing the prevailing state-of-the-art infection detection techniques.

  • Open Access

    A Methodology Framework for Analyzing Health Misinformation to Develop Inoculation Intervention Using Large Language Models: A case study on covid-19

    by Samira Malek, Christopher Griffin, Robert Fraleigh, Robert P. Lennon, Vishal Monga, Lijiang Shen

    Background The rapid growth of social media as an information channel has enabled the swift spread of inaccurate or false health information, significantly impacting public health. This widespread dissemination of misinformation has caused confusion, eroded trust in health authorities, led to noncompliance with health guidelines, and encouraged risky health behaviors. Understanding the dynamics of misinformation on social media is essential for devising effective public health communication strategies. Objective This study aims to present a comprehensive and automated approach that leverages Large Language Models (LLMs) and Machine Learning (ML) techniques to detect misinformation on social media, uncover the underlying causes and themes, and generate refutation arguments, facilitating control of its spread and promoting public health outcomes by inoculating people against health misinformation. Methods We use two datasets to train three LLMs, namely BERT, T5, and GPT-2, to classify documents into two categories: misinformation and non-misinformation. Additionally, we employ a separate dataset to identify misinformation topics. To analyze these topics, we apply three topic modeling algorithms—Latent Dirichlet Allocation (LDA), Top2Vec, and BERTopic—and selected the optimal model based on performance evaluated across three metrics. Using a prompting approach, we extract sentence-level representations for the topics to uncover their underlying themes. Finally, we design a prompt text capable of identifying misinformation themes effectively. Results The trained BERT model demonstrated exceptional performance, achieving 98% accuracy in classifying misinformation and non-misinformation, with a 44% reduction in false positive rates for AI-generated misinformation. Among the three topic modeling approaches employed, BERTopic outperformed the others, achieving the highest metrics with a Coherence Value (CV) of 0.41, Normalized Pointwise Mutual Information (NPMI) of -0.086, and Inverted RBO (IRBO) of 0.99. To address the issue of unclassified documents, we developed an algorithm to assign each document to its closest topic. Additionally, we proposed a novel method using prompt engineering to generate sentence-level representations for each topic, achieving a 99.6% approval rate as “appropriate” or “somewhat appropriate” by three independent raters. We further designed a prompt text to identify themes of misinformation topics and developed another prompt capable of detecting misinformation themes with 80% accuracy. Conclusions This study presents a comprehensive and automated approach to addressing health misinformation on social media using advanced machine learning and natural language processing techniques. By leveraging large language models (LLMs) and prompt engineering, the system effectively detects misinformation, identifies underlying themes, and provides explanatory responses to combat its spread. (Journal of Medical Internet Research) doi:


  • CLIF-Net: Intersection-Guided Cross-View Fusion Network for Infection Detection From Cranial Ultrasound

    by Mingzhao Yu, Mallory R. Peterson, Kathy Burgoine, Thaddeus Harbaugh, Peter Olupot-Olupot, Melissa Gladstone, Cornelia Hagmann, Frances M. Cowan, Andrew Weeks, Sarah U. Morton, et al.

    This paper addresses the problem of detecting possible serious bacterial infection (pSBI) of infancy, i.e. a clinical presentation consistent with bacterial sepsis in newborn infants using cranial ultrasound (cUS) images. The captured image set for each patient enables multiview imagery: coronal and sagittal, with geometric overlap. To exploit this geometric relation, we develop a new learning framework, called the intersection-guided Crossview Local- and Image-level Fusion Network (CLIF-Net). Our technique employs two distinct convolutional neural network branches to extract features from coronal and sagittal images with newly developed multi-level fusion blocks. Specifically, we leverage the spatial position of these images to locate the intersecting region. We then identify and enhance the semantic features from this region across multiple levels using cross-attention modules, facilitating the acquisition of mutually beneficial and more representative features from both views. The final enhanced features from the two views are then integrated and projected through the image-level fusion layer, outputting pSBI and non-pSBI class probabilities. We contend that our method of exploiting multi-view cUS images enables a first of its kind, robust 3D representation tailored for pSBI detection. When evaluated on a dataset of 302 cUS scans from Mbale Regional Referral Hospital in Uganda, CLIF-Net demonstrates substantially enhanced performance, surpassing the prevailing state-of-the-art infection detection techniques.

  • Physically Enriched Product Adaptive Deep Networks for Industrial Metal Detection

    by Suhrid Das, Ankit Tyagi, Vishal Monga

    This study addresses a longstanding metal-detection problem (classifying a product as clean or contaminated) using two-frequency electromagnetic fields by analyzing complex temporal data. Traditional contamination detection methods rely on analyzing permittivity and conductivity signals obtained when products pass through the detector’s electromagnetic field. While reliable, these methods struggle with Product Effect—a phenomenon where conductive product signals overshadow contaminant signals, leading to false negatives. Advances in deep learning have enhanced detection accuracy but often require large training datasets, which are impractical in many industrial metal detection scenarios where cost of data acquisition is high. To address these challenges, we propose physically-enriched deep learning architectures that integrate domain knowledge with state-of-the-art feature extraction models. Our contribution centers on two key innovations: adaptive models capable of countering product effect and improving contamination detection accuracy compared to both traditional signal processing and machine learning methods, and secondly, an enhanced ability to classify contaminant (metal) type, enabled by a data pre-processing module that we call learnable denoisers. Extensive experiments on challenging real-world data demonstrate that – our product adaptation modules and a newly designed training strategy that extracts pure metal signatures from contaminated products – enable scalable performance across diverse products. The proposed models successfully mitigate both false positives and negatives (missed metal detection) breaking a stiff trade-off. Further, benefits of our approach are most pronounced when training data is limited indicating superior generalizability.


  • Open Access

    A Methodology Framework for Analyzing Health Misinformation to Develop Inoculation Intervention Using Large Language Models: A case study on covid-19 (Preprint)

    by Samira Malek, Christopher Griffin, Robert D Fraleigh, Robert Lennon, Vishal Monga, Lijiang Shen

    BACKGROUND The rapid growth of social media as an information channel has enabled the swift spread of inaccurate or false health information, significantly impacting public health. This widespread dissemination of misinformation has caused confusion, eroded trust in health authorities, led to noncompliance with health guidelines, and encouraged risky health behaviors. Understanding the dynamics of misinformation on social media is essential for devising effective public health communication strategies. OBJECTIVE This study aims to present a comprehensive and automated approach that leverages Large Language Models (LLMs) and Machine Learning (ML) techniques to detect misinformation on social media, uncover the underlying causes and themes, and generate refutation arguments, facilitating control of its spread and promoting public health outcomes by inoculating people against health misinformation. METHODS We use two datasets to train three LLMs, namely BERT, T5, and GPT-2, to classify documents into two categories: misinformation and non-misinformation. Additionally, we employ a separate dataset to identify misinformation topics. To analyze these topics, we apply three topic modeling algorithms—Latent Dirichlet Allocation (LDA), Top2Vec, and BERTopic—and selected the optimal model based on performance evaluated across three metrics. Using a prompting approach, we extract sentence-level representations for the topics to uncover their underlying themes. Finally, we design a prompt text capable of identifying misinformation themes effectively. RESULTS The trained BERT model demonstrated exceptional performance, achieving 98% accuracy in classifying misinformation and non-misinformation, with a 44% reduction in false positive rates for AI-generated misinformation. Among the three topic modeling approaches employed, BERTopic outperformed the others, achieving the highest metrics with a Coherence Value (CV) of 0.41, Normalized Pointwise Mutual Information (NPMI) of -0.086, and Inverted RBO (IRBO) of 0.99. To address the issue of unclassified documents, we developed an algorithm to assign each document to its closest topic. Additionally, we proposed a novel method using prompt engineering to generate sentence-level representations for each topic, achieving a 99.6% approval rate as "appropriate" or "somewhat appropriate" by three independent raters. We further designed a prompt text to identify themes of misinformation topics and developed another prompt capable of detecting misinformation themes with 80% accuracy. CONCLUSIONS This study presents a comprehensive and automated approach to addressing health misinformation on social media using advanced machine learning and natural language processing techniques. By leveraging large language models (LLMs) and prompt engineering, the system effectively detects misinformation, identifies underlying themes, and provides explanatory responses to combat its spread.

  • Model-Based Learning for MIMO Radar Waveform Design in the Presence of Multiple Targets

    by Junho Kweon, Fulvio Gini, Maria Sabrina Greco, Muralidhar Rangaswamy, Vishal Monga

    This study addresses detecting multiple targets in the presence of signal-dependent clutter using a Multiple-Input Multiple-Output (MIMO) radar system. Our primary objective is to design transmit waveforms that maximize the worst-case Signal-to-Interference-Noise-Ratio (SINR) across multiple targets. Practical constraints enforced in our work are the waveform similarity constraint (SC) and the constant modulus constraint (CMC). We confront a complex max-min and fractional non-convex optimization problem. For tractability, we introduce a surrogate cost function based on the sum-of-reciprocals of SINRs. We show that despite the fractional form, an exact gradient can be computed for this cost function, leading to a sum-of-reciprocals exact descent (SRED) numerical optimization approach. We then propose a model-based deep learning technique that evolves the iterative SRED algorithm into a Sum-of-Reciprocals Exact Learning (SREL) approach. SREL enhances waveform optimization by learning key parameters, including descent direction and step sizes, via distinct training frameworks for intra- and inter-target parameters. We first develop intra-target training focusing on a single SINR maximization. Inter-target parameters are then trained to balance between the multiple gradients, each corresponding to a SINR reciprocal, in order to maximize the worst-case SINR. Numerical experiments conducted for benchmark scenarios demonstrate that both SRED and SREL surpass the state-of-the-art counterparts in achieving superior worst-case SINR and generating favorable range-azimuth beampattern profiles. Notably, SREL, by virtue of parameter learning, also brings computational benefits in that the SREL requires a smaller number of steps than SRED iterations.


  • MIMO Radar Beampattern Design via Algorithm Unrolling

    by Kareem Metwaly, Junho Kweon, Khaled Alhujaili, Fulvio Gini, Maria Sabrina Greco, Muralidhar Rangaswamy, Vishal Monga

    Optimizing a transmit Multiple-Input Multiple-Output (MIMO) radar waveform subject to the non-convex constant modulus constraint (CMC) remains a problem of enduring interest. The past decade has seen a variety of tailored iterative approaches with various performance-complexity trade-offs. Despite promising work, iterative algorithms have a speed handicap and require meticulous parameter tuning. Deep learning has recently been proposed for MIMO radar waveform design, where iterative optimization is replaced by a neural network that regresses from the problem specification to the desired waveform. Once trained, a deep network can quickly regress the desired waveform coefficients, but it is a black box and may excel only when generous training is available. We present a fast, learned, and explainable deep (FLED) learning approach by unrolling a state-of-the-art iterative algorithm. We particularly leverage the recently proposed Projection-Descent-Retraction (PDR) algorithm and design a neural network where each PDR iteration is mapped to a step of the network while preserving the CMC. Alongside an interpretable network architecture, we propose learning of key algorithm parameters such as the direction of descent, while introducing learning of FLED initialization and solution refinement through trainable prune-expand blocks. By enforcing appropriate regularizers in the learning of these parameters, FLED breaks the trade-off between computational speed and performance. Compared to the state-of-the-art alternatives, it is near real-time with boosted performance – fidelity to the desired beampattern. Crucially, the benefits of FLED over competing deep learning techniques are enhanced in the regime of limited training, i.e., FLED exhibits superior generalizability.