585 citations · 841 across the 29 of their papers we have counts for
35 papers
GraphBEAT: Graph-based Bucketized Event Aggregation Over Time for Early Risk Stratification of Gastrointestinal Cancers
Leo Y. Li-Han, Chris Varghese, Elizabeth B. Habermann +4
Longitudinal electronic health records (EHRs) contain complementary diagnostic and laboratory information about patient health. However, irregularity, sparsity, heterogeneity, and…
Automated Prediction of Postoperative Pancreatic Fistula Using Preoperative Computed Tomography
Ashok Choudhary, Chris Varghese, Leo Y. Li-Han +5
Postoperative pancreatic fistula (POPF) is a serious complication after pancreatic resection, increasing morbidity, hospital stay, and healthcare costs. We present an automatic, en…
Digitally enriching a high-risk population for pancreatic cancer using routine blood-based measures and clinical histories
Chris Varghese, Leo Y. Li-Han, Richa Bisht +10
Earlier detection of pancreatic cancer is key to enabling wider access to curative treatment and reducing cancer deaths; however, screening is presently not viable. Latent digital…
GraD-IBD: Graph Representation Learning from Diagnosis Trajectories for Early Detection of Inflammatory Bowel Disease
Leo Y. Li-Han, Ellen L. Larson, Elizabeth B. Habermann +2
International Classification of Diseases (ICD) is a globally recognized coding system that records diagnostic events during each patient encounter, providing a standardized data fo…
Beyond Amplitude: Channel State Information Phase-Aware Deep Fusion for Robotic Activity Recognition
Rojin Zandi, Hojjat Salehinejad, Milad Siami
Wi-Fi Channel State Information (CSI) has emerged as a promising non-line-of-sight sensing modality for human and robotic activity recognition. However, prior work has predominantl…
Synthetic Feature Augmentation Improves Generalization Performance of Language Models
Ashok Choudhary, Cornelius Thiels, Hojjat Salehinejad
Training and fine-tuning deep learning models, especially large language models (LLMs), on limited and imbalanced datasets poses substantial challenges. These issues often result i…
Deep Learning on Hester Davis Scores for Inpatient Fall Prediction
Hojjat Salehinejad, Ricky Rojas, Kingsley Iheasirim +2
Fall risk prediction among hospitalized patients is a critical aspect of patient safety in clinical settings, and accurate models can help prevent adverse events. The Hester Davis…
RoboMNIST: A Multimodal Dataset for Multi-Robot Activity Recognition Using WiFi Sensing, Video, and Audio
Kian Behzad, Rojin Zandi, Elaheh Motamedi +2
We introduce a novel dataset for multi-robot activity recognition (MRAR) using two robotic arms integrating WiFi channel state information (CSI), video, and audio data. This multim…
Enhancing Robotic Arm Activity Recognition with Vision Transformers and Wavelet-Transformed Channel State Information
Rojin Zandi, Kian Behzad, Elaheh Motamedi +2
Vision-based methods are commonly used in robotic arm activity recognition. These approaches typically rely on line-of-sight (LoS) and raise privacy concerns, particularly in smart…
Robustness Evaluation of Machine Learning Models for Robot Arm Action Recognition in Noisy Environments
Elaheh Motamedi, Kian Behzad, Rojin Zandi +2
In the realm of robot action recognition, identifying distinct but spatially proximate arm movements using vision systems in noisy environments poses a significant challenge. This…
RoboFiSense: Attention-Based Robotic Arm Activity Recognition with WiFi Sensing
Rojin Zandi, Kian Behzad, Elaheh Motamedi +2
Despite the current surge of interest in autonomous robotic systems, robot activity recognition within restricted indoor environments remains a formidable challenge. Conventional m…
Hypertension Detection From High-Dimensional Representation of Photoplethysmogram Signals
Navid Hasanzadeh, Shahrokh Valaee, Hojjat Salehinejad
Hypertension is commonly referred to as the "silent killer", since it can lead to severe health complications without any visible symptoms. Early detection of hypertension is cruci…
Robot Motion Prediction by Channel State Information
Rojin Zandi, Hojjat Salehinejad, Kian Behzad +2
Autonomous robotic systems have gained a lot of attention, in recent years. However, accurate prediction of robot motion in indoor environments with limited visibility is challengi…
Joint Human Orientation-Activity Recognition Using WiFi Signals for Human-Machine Interaction
Hojjat Salehinejad, Navid Hasanzadeh, Radomir Djogo +1
WiFi sensing is an important part of the new WiFi 802.11bf standard, which can detect motion and measure distances. In recent years, some machine learning methods have been propose…
S-Rocket: Selective Random Convolution Kernels for Time Series Classification
Hojjat Salehinejad, Yang Wang, Yuanhao Yu +2
Random convolution kernel transform (Rocket) is a fast, efficient, and novel approach for time series feature extraction using a large number of independent randomly initialized 1-…
LiteHAR: Lightweight Human Activity Recognition from WiFi Signals with Random Convolution Kernels
Hojjat Salehinejad, Shahrokh Valaee
Anatomical movements of the human body can change the channel state information (CSI) of wireless signals in an indoor environment. These changes in the CSI signals can be used for…
A Framework For Pruning Deep Neural Networks Using Energy-Based Models
Hojjat Salehinejad, Shahrokh Valaee
A typical deep neural network (DNN) has a large number of trainable parameters. Choosing a network with proper capacity is challenging and generally a larger network with excessive…
Pruning of Convolutional Neural Networks Using Ising Energy Model
Hojjat Salehinejad, Shahrokh Valaee
Pruning is one of the major methods to compress deep neural networks. In this paper, we propose an Ising energy model within an optimization framework for pruning convolutional ker…
A Real-World Demonstration of Machine Learning Generalizability: Intracranial Hemorrhage Detection on Head CT
Hojjat Salehinejad, Jumpei Kitamura, Noah Ditkofsky +7
Machine learning (ML) holds great promise in transforming healthcare. While published studies have shown the utility of ML models in interpreting medical imaging examinations, thes…
Deep Sequential Learning for Cervical Spine Fracture Detection on Computed Tomography Imaging
Hojjat Salehinejad, Edward Ho, Hui-Ming Lin +10
Fractures of the cervical spine are a medical emergency and may lead to permanent paralysis and even death. Accurate diagnosis in patients with suspected fractures by computed tomo…
EDropout: Energy-Based Dropout and Pruning of Deep Neural Networks
Hojjat Salehinejad, Shahrokh Valaee
Dropout is a well-known regularization method by sampling a sub-network from a larger deep neural network and training different sub-networks on different subsets of the data. Insp…
Survey of Dropout Methods for Deep Neural Networks
Alex Labach, Hojjat Salehinejad, Shahrokh Valaee
Dropout methods are a family of stochastic techniques used in neural network training or inference that have generated significant research interest and are widely used in practice…
Ising-Dropout: A Regularization Method for Training and Compression of Deep Neural Networks
Hojjat Salehinejad, Shahrokh Valaee
Overfitting is a major problem in training machine learning models, specifically deep neural networks. This problem may be caused by imbalanced datasets and initialization of the m…
Cylindrical Transform: 3D Semantic Segmentation of Kidneys With Limited Annotated Images
Hojjat Salehinejad, Sumeya Naqvi, Errol Colak +2
In this paper, we propose a novel technique for sampling sequential images using a cylindrical transform in a cylindrical coordinate system for kidney semantic segmentation in abdo…