{"id":30,"date":"2018-12-13T19:48:55","date_gmt":"2018-12-13T19:48:55","guid":{"rendered":"http:\/\/groups.cs.umass.edu\/infofusion\/?page_id=30"},"modified":"2023-10-02T15:04:11","modified_gmt":"2023-10-02T15:04:11","slug":"publications","status":"publish","type":"page","link":"https:\/\/groups.cs.umass.edu\/infofusion\/publications\/","title":{"rendered":"Publications"},"content":{"rendered":"
<\/a><\/form>\r\n \r\n \r\n \r\n \r\n \r\n \r\n
\r\n

2025<\/h3>\r\n <\/td>\r\n <\/tr>

Shiv Shankar; Ritwik Sinha; Madalina Fiterau<\/p>

Experimentation under Treatment Dependent Network Interference<\/a> Conference<\/span> <\/p>

41st Conference on Uncertainty in Artificial Intelligence, <\/span>vol. 286, <\/span>PMLR, <\/span>2025<\/span>.<\/p>

Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

\r\n

2024<\/h3>\r\n <\/td>\r\n <\/tr>

Iman Deznabi, Yunfei Lou, Abhinav Shaw, Natcha Simsiri, Tauhidur Rahman, Madalina Fiterau<\/p>

Dynamic Clustering via Branched Deep Learning Enhances Personalization of Stress Prediction from Mobile Sensor Data<\/a> Journal Article<\/span> <\/p>

In: <\/span>Nature Scientific Reports, <\/span>vol. 14, <\/span>no. 6631, <\/span>2024<\/span>.<\/p>

Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

Iman Deznabi, Peeyush Kumar, Madalina Fiterau<\/p>

Zero-shot micro-climate prediction with deep learning<\/a> Workshop<\/span> <\/p>

2024<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@workshop{Deznabi2024,
\r\ntitle = {Zero-shot micro-climate prediction with deep learning},
\r\nauthor = {Iman Deznabi, Peeyush Kumar, Madalina Fiterau},
\r\nurl = {https:\/\/arxiv.org\/abs\/2401.02665},
\r\nyear  = {2024},
\r\ndate = {2024-01-05},
\r\nurldate = {2024-01-05},
\r\njournal = {Tackling Climate Change with Machine Learning workshop NeurIPS (2023)},
\r\nabstract = {Weather station data is a valuable resource for climate prediction, however, its reliability can be limited in remote locations. To compound the issue, making local predictions often relies on sensor data that may not be accessible for a new, previously unmonitored location. In response to these challenges, we propose a novel zero-shot learning approach designed to forecast various climate measurements at new and unmonitored locations. Our method surpasses conventional weather forecasting techniques in predicting microclimate variables by leveraging knowledge extracted from other geographic locations.},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {workshop}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>
\r\n

2023<\/h3>\r\n <\/td>\r\n <\/tr>

Shiv Shankar <\/p>

AI assisted Search for Atmospheric CO2 Capture<\/a> Workshop<\/span> <\/p>

2023<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@workshop{nokey,
\r\ntitle = {AI assisted Search for Atmospheric CO2 Capture},
\r\nauthor = {Shiv Shankar },
\r\nurl = {https:\/\/s3.us-east-1.amazonaws.com\/climate-change-ai\/papers\/neurips2023\/111\/paper.pdf},
\r\nyear  = {2023},
\r\ndate = {2023-12-01},
\r\nurldate = {2023-12-01},
\r\nabstract = {Carbon capture technologies is an important tool for mitigating climate change. In recent years, polymer membrane separation methods have emerged as a
\r\npromising technology for separating CO2 and other green house gases from the
\r\natmosphere. Designing new polymers for such tasks is quite difficult. In this work
\r\nwe look at machine learning based methods to search for new polymer designs
\r\noptimized for CO2 separation. An ensemble ML models is trained on a large
\r\ndatabase of molecules to predict permeabilities of CO2\/N2 and CO2\/O2 pairs. We
\r\nthen use search based optimization to discover new polymers that surpass existing
\r\npolymer designs. Simulations are then done to verify the predicted performance
\r\nof the new designs. Overall result suggests that ML based search can be used to
\r\ndiscover new polymers optimized for carbon capture},
\r\nhowpublished = {AI for Climate Change, Neurips 2023},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {workshop}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>

Iman Deznabi, Madalina Fiterau<\/p>

MultiWave: Multiresolution Deep Architectures through Wavelet Decomposition for Multivariate Timeseries Forecasting and Prediction.<\/a> Conference<\/span> <\/p>

Conference on Health, Inference, and Learning (CHIL 2023), <\/span>vol. 209, <\/span>2023<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@conference{Deznabi2023,
\r\ntitle = {MultiWave: Multiresolution Deep Architectures through Wavelet Decomposition for Multivariate Timeseries Forecasting and Prediction.},
\r\nauthor = {Iman Deznabi, Madalina Fiterau},
\r\nurl = {https:\/\/proceedings.mlr.press\/v209\/deznabi23a\/deznabi23a.pdf},
\r\nyear  = {2023},
\r\ndate = {2023-06-25},
\r\nurldate = {2023-06-25},
\r\nbooktitle = {Conference on Health, Inference, and Learning (CHIL 2023)},
\r\nvolume = {209},
\r\nabstract = {The analysis of multivariate time series data is challenging due to the various frequencies of signal changes that can occur over both short and long terms. Furthermore, standard deep learning models are often unsuitable for such datasets, as signals are typically sampled at different rates. To address these issues, we introduce MultiWave, a novel framework that enhances deep learning time series models by incorporating components that operate at the intrinsic frequencies of signals. MultiWave uses wavelets to decompose each signal into subsignals of varying frequencies and groups them into frequency bands. Each frequency band is handled by a different component of our model. A gating mechanism combines the output of the components to produce sparse models that use only specific signals at specific frequencies. Our experiments demonstrate that MultiWave accurately identifies informative frequency bands and improves the performance of various deep learning models, including LSTM, Transformer, and CNN-based models, for a wide range of applications. It attains top performance in stress and affect detection from wearables. It also increases the AUC of the best-performing model by 5% for in-hospital COVID-19 mortality prediction from patient blood samples and for human activity recognition from accelerometer and gyroscope data. We show that MultiWave consistently identifies critical features and their frequency components, thus providing valuable insights into the applications studied.},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {conference}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>
The analysis of multivariate time series data is challenging due to the various frequencies of signal changes that can occur over both short and long terms. Furthermore, standard deep learning models are often unsuitable for such datasets, as signals are typically sampled at different rates. To address these issues, we introduce MultiWave, a novel framework that enhances deep learning time series models by incorporating components that operate at the intrinsic frequencies of signals. MultiWave uses wavelets to decompose each signal into subsignals of varying frequencies and groups them into frequency bands. Each frequency band is handled by a different component of our model. A gating mechanism combines the output of the components to produce sparse models that use only specific signals at specific frequencies. Our experiments demonstrate that MultiWave accurately identifies informative frequency bands and improves the performance of various deep learning models, including LSTM, Transformer, and CNN-based models, for a wide range of applications. It attains top performance in stress and affect detection from wearables. It also increases the AUC of the best-performing model by 5% for in-hospital COVID-19 mortality prediction from patient blood samples and for human activity recognition from accelerometer and gyroscope data. We show that MultiWave consistently identifies critical features and their frequency components, thus providing valuable insights into the applications studied.<\/div>
Close<\/a><\/p><\/div>

Shiv Shankar; Sidong Zhang; Trang Nguyen; Madalina Fiterau<\/p>

HyperFuse: Multimodal Fusion via Hypernetworks<\/a> Working paper<\/span> <\/p>

2023<\/span>.<\/p>

Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

\r\n

2022<\/h3>\r\n <\/td>\r\n <\/tr>

Edmond Cunningham, Adam D Cobb, Susmit Jha<\/p>

Principal Component Flows<\/a> Conference<\/span> <\/p>

2022<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@conference{nokey,
\r\ntitle = {Principal Component Flows},
\r\nauthor = {Edmond Cunningham, Adam D Cobb, Susmit Jha},
\r\nurl = {https:\/\/proceedings.mlr.press\/v162\/cunningham22a.html},
\r\nyear  = {2022},
\r\ndate = {2022-07-17},
\r\nurldate = {2022-07-17},
\r\nabstract = {Normalizing flows map an independent set of latent variables to their samples using a bijective transformation. Despite the exact correspondence between samples and latent variables, their high level relationship is not well understood. In this paper we characterize the geometric structure of flows using principal manifolds and understand the relationship between latent variables and samples using contours. We introduce a novel class of normalizing flows, called principal component flows (PCF), whose contours are its principal manifolds, and a variant for injective flows (iPCF) that is more efficient to train than regular injective flows. PCFs can be constructed using any flow architecture, are trained with a regularized maximum likelihood objective and can perform density estimation on all of their principal manifolds. In our experiments we show that PCFs and iPCFs are able to learn the principal manifolds over a variety of datasets. Additionally, we show that PCFs can perform density estimation on data that lie on a manifold with variable dimensionality, which is not possible with existing normalizing flows. },
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {conference}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>

Christen H Fleming, Iman Deznabi, Shauhin Alavi, Margaret C Crofoot, Ben T Hirsch, E Patricia Medici, Michael J Noonan, Roland Kays, William F Fagan, Daniel Sheldon, Justin M Calabrese<\/p>

Population-level inference for home-range areas<\/a> Journal Article<\/span> <\/p>

In: <\/span>Methods in Ecology and Evolution journal (2022), <\/span>vol. 13, <\/span>iss. 5, <\/span>pp. 1027-1041, <\/span>2022<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@article{nokey,
\r\ntitle = {Population-level inference for home-range areas},
\r\nauthor = {Christen H Fleming, Iman Deznabi, Shauhin Alavi, Margaret C Crofoot, Ben T Hirsch, E Patricia Medici, Michael J Noonan, Roland Kays, William F Fagan, Daniel Sheldon, Justin M Calabrese},
\r\nurl = {https:\/\/besjournals.onlinelibrary.wiley.com\/doi\/full\/10.1111\/2041-210X.13815},
\r\ndoi = {13815},
\r\nyear  = {2022},
\r\ndate = {2022-02-03},
\r\nurldate = {2022-02-03},
\r\njournal = {Methods in Ecology and Evolution journal (2022)},
\r\nvolume = {13},
\r\nissue = {5},
\r\npages = {1027-1041},
\r\nabstract = {1. Home-range estimates are a common product of animal tracking data, as each range represents the area needed by a given individual. Population-level inference of home-range areas\u2014where multiple individual home ranges are considered to be sampled from a population\u2014is also important to evaluate changes over time, space or covariates such as habitat quality or fragmentation, and for comparative analyses of species averages. Population-level home-range parameters have traditionally been estimated by first assuming that the input tracking data were sampled independently when calculating home ranges via conventional kernel density estimation (KDE) or minimal convex polygon (MCP) methods, and then assuming that those individual home ranges were measured exactly when calculating the population-level estimates. This conventional approach does not account for the temporal autocorrelation that is inherent in modern tracking data, nor for the uncertainties of each individual home-range estimate, which are often large and heterogeneous.
\r\n2. Here, we introduce a statistically and computationally efficient framework for the population-level analysis of home-range areas, based on autocorrelated kernel density estimation (AKDE), that can account for variable temporal autocorrelation and estimation uncertainty.
\r\n3. We apply our method to empirical examples on lowland tapir Tapirus terrestris, kinkajou Potos flavus, white-nosed coati Nasua narica, white-faced capuchin monkey Cebus capucinus and spider monkey Ateles geoffroyi, and quantify differences between species, environments and sexes.
\r\n4. Our approach allows researchers to more accurately compare different populations with different movement behaviours or sampling schedules while retaining statistical precision and power when individual home-range uncertainties vary. Finally, we emphasize the estimation of effect sizes when comparing populations, rather than mere significance tests.},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {article}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>
1. Home-range estimates are a common product of animal tracking data, as each range represents the area needed by a given individual. Population-level inference of home-range areas\u2014where multiple individual home ranges are considered to be sampled from a population\u2014is also important to evaluate changes over time, space or covariates such as habitat quality or fragmentation, and for comparative analyses of species averages. Population-level home-range parameters have traditionally been estimated by first assuming that the input tracking data were sampled independently when calculating home ranges via conventional kernel density estimation (KDE) or minimal convex polygon (MCP) methods, and then assuming that those individual home ranges were measured exactly when calculating the population-level estimates. This conventional approach does not account for the temporal autocorrelation that is inherent in modern tracking data, nor for the uncertainties of each individual home-range estimate, which are often large and heterogeneous.
\r\n2. Here, we introduce a statistically and computationally efficient framework for the population-level analysis of home-range areas, based on autocorrelated kernel density estimation (AKDE), that can account for variable temporal autocorrelation and estimation uncertainty.
\r\n3. We apply our method to empirical examples on lowland tapir Tapirus terrestris, kinkajou Potos flavus, white-nosed coati Nasua narica, white-faced capuchin monkey Cebus capucinus and spider monkey Ateles geoffroyi, and quantify differences between species, environments and sexes.
\r\n4. Our approach allows researchers to more accurately compare different populations with different movement behaviours or sampling schedules while retaining statistical precision and power when individual home-range uncertainties vary. Finally, we emphasize the estimation of effect sizes when comparing populations, rather than mere significance tests.<\/div>
Close<\/a><\/p><\/div>
\r\n

2021<\/h3>\r\n <\/td>\r\n <\/tr>

Iman Deznabi, Mohit Iyyer, Madalina Fiterau<\/p>

Predicting in-hospital mortality by combining clinical notes with time-series data<\/a> Conference<\/span> <\/p>

Association for Computational Linguistics (ACL-IJCNLP 2021) Findings, <\/span>2021<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@conference{Deznabi2021b,
\r\ntitle = {Predicting in-hospital mortality by combining clinical notes with time-series data},
\r\nauthor = {Iman Deznabi, Mohit Iyyer, Madalina Fiterau},
\r\nurl = {https:\/\/aclanthology.org\/2021.findings-acl.352.pdf},
\r\nyear  = {2021},
\r\ndate = {2021-08-06},
\r\nurldate = {2021-08-06},
\r\nbooktitle = {Association for Computational Linguistics (ACL-IJCNLP 2021) Findings},
\r\nabstract = {In intensive care units (ICUs), patient health is monitored through (1) continuous vital signals from various medical devices, and (2) clinical notes consisting of opinions and summaries from doctors which are recorded in electronic health records (EHR). It is difficult to jointly model these two sources of information because clinical notes, unlike vital signals, are collected at irregular intervals and their contents are relatively unstructured. In this paper, we present a model that combines both sources of information about ICU patients to make accurate in-hospital mortality predictions. We apply a fine-tuned BERT model to each of the patient's clinical notes. The resulting embeddings are then combined to obtain the overall embedding for the entire text part of the data. This is then combined with the output of an LSTM model that encodes patients' vital signals. Our model improves upon the state of the art for mortality prediction, attaining an AUC score of 0.9, compared to the previous 0.87, setting a new standard for mortality prediction on the MIMIC III benchmark.},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {conference}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>

Edmond Cunningham, Madalina Fiterau<\/p>

A Change of Variables Method For Rectangular Matrix-Vector Products<\/a> Conference<\/span> <\/p>

2021<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@conference{nokey,
\r\ntitle = {A Change of Variables Method For Rectangular Matrix-Vector Products},
\r\nauthor = {Edmond Cunningham, Madalina Fiterau},
\r\nurl = {https:\/\/proceedings.mlr.press\/v130\/cunningham21a.html},
\r\nyear  = {2021},
\r\ndate = {2021-04-13},
\r\nabstract = {Rectangular matrix-vector products (MVPs) are used extensively throughout machine learning and are fundamental to neural networks such as multi-layer perceptrons. However, the use of rectangular MVPs in successive normalizing flow transformations is notably missing. This paper identifies this methodological gap and plugs it with a tall and wide MVP change of variables formula. Our theory builds up to a practical algorithm that envelops existing dimensionality increasing flow methods such as augmented flows. We show that tall MVPs are closely related to the stochastic inverse of wide MVPs and empirically demonstrate that they improve density estimation over existing dimension changing methods. },
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {conference}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>

Iman Deznabi, Tamanna Motahar, Ali Sarvghad, Madalina Fiterau, Narges Mahyar<\/p>

Impact of the COVID-19 Pandemic on the Academic Community Results from a survey conducted at University of Massachusetts Amherst<\/a> Journal Article<\/span> <\/p>

In: <\/span>ACM, Digital Government: Research and Practive, COVID-19 Commentary, <\/span>vol. 2, <\/span>iss. 2, <\/span>no. 22, <\/span>pp. 1-12, <\/span>2021<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@article{Deznabi2021,
\r\ntitle = {Impact of the COVID-19 Pandemic on the Academic Community Results from a survey conducted at University of Massachusetts Amherst},
\r\nauthor = {Iman Deznabi, Tamanna Motahar, Ali Sarvghad, Madalina Fiterau, Narges Mahyar},
\r\nurl = {https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3436731},
\r\ndoi = {3436731},
\r\nyear  = {2021},
\r\ndate = {2021-01-02},
\r\nurldate = {2021-01-02},
\r\njournal = {ACM, Digital Government: Research and Practive, COVID-19 Commentary},
\r\nvolume = {2},
\r\nnumber = {22},
\r\nissue = {2},
\r\npages = {1-12},
\r\nabstract = {The COVID-19 pandemic has significantly impacted academic life in the United States and beyond. To gain a better understanding of its impact on the academic community, we conducted a large-scale survey at the University of Massachusetts Amherst. We collected multifaceted data from students, staff, and faculty on several aspects of their lives, such as mental and physical health, productivity, and finances. All our respondents expressed mental and physical issues and concerns, such as increased stress and depression levels. Financial difficulties seem to have the most considerable toll on staff and undergraduate students, while productivity challenges were mostly expressed by faculty and graduate students. As universities face many important decisions with respect to mitigating the effects of this pandemic, we present our findings with the intent of shedding light on the challenges faced by various academic groups in the face of the pandemic, calling attention to the differences between groups. We also contribute a discussion highlighting how the results translate to policies for the effective and timely support of the categories of respondents who need them most. Finally, the survey itself, which includes conditional logic allowing for personalized questions, serves as a template for further data collection, facilitating a comparison of the impact on campuses across the United States.},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {article}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>
The COVID-19 pandemic has significantly impacted academic life in the United States and beyond. To gain a better understanding of its impact on the academic community, we conducted a large-scale survey at the University of Massachusetts Amherst. We collected multifaceted data from students, staff, and faculty on several aspects of their lives, such as mental and physical health, productivity, and finances. All our respondents expressed mental and physical issues and concerns, such as increased stress and depression levels. Financial difficulties seem to have the most considerable toll on staff and undergraduate students, while productivity challenges were mostly expressed by faculty and graduate students. As universities face many important decisions with respect to mitigating the effects of this pandemic, we present our findings with the intent of shedding light on the challenges faced by various academic groups in the face of the pandemic, calling attention to the differences between groups. We also contribute a discussion highlighting how the results translate to policies for the effective and timely support of the categories of respondents who need them most. Finally, the survey itself, which includes conditional logic allowing for personalized questions, serves as a template for further data collection, facilitating a comparison of the impact on campuses across the United States.<\/div>
Close<\/a><\/p><\/div>
\r\n

2020<\/h3>\r\n <\/td>\r\n <\/tr>

Edmond Cunningham; Renos Zabounidis; Abhinav Agrawal; Madalina Fiterau; Daniel Sheldon<\/p>

Normalizing Flows Across Dimensions<\/a> Workshop<\/span> <\/p>

International Conference on Machine Learning (ICML) Workshops 2020, <\/span>ICML 2020 Inductive biases, invariances and generalization in RL (BIG) workshop, <\/span>2020<\/span>.<\/p>

Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

Purva Pruthi; Javier Gonz\u00e1lez; Xiaoyu Lu; Madalina Fiterau<\/p>

Structure Mapping for Transferability of Causal Models<\/a> Workshop<\/span> <\/p>

International Conference on Machine Learning (ICML) Workshops 2020, <\/span>ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, <\/span>2020<\/span>.<\/p>

Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

\r\n

2019<\/h3>\r\n <\/td>\r\n <\/tr>

Brett Beaulieu-Jones; Samuel G Finlayson; Corey Chivers; Irene Chen; Matthew McDermott; Jaz Kandola; Adrian V Dalca; Andrew Beam; Madalina Fiterau; Tristan Naumann<\/p>

Trends and Focus of Machine Learning Applications for Health Research<\/a> Journal Article<\/span> <\/p>

In: <\/span>JAMA network open, <\/span>vol. 2, <\/span>no. 10, <\/span>pp. e1914051\u2013e1914051, <\/span>2019<\/span>.<\/p>

Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

Yi Ren Fung; Ziqiang Guan; Ritesh Kumar; Yeahuay Joie Wu; Madalina Fiterau<\/p>

Alzheimer's Disease Brain MRI Classification: Challenges and Insights<\/a> Workshop<\/span> <\/p>

IJCAI ARIAL Workshop, <\/span>2019<\/span>.<\/p>

Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

Surya Teja Devarakonda; Yeahuay Joie Wu; Yi Ren Fung; Madalina Fiterau<\/p>

FLARe: Forecasting by Learning Anticipated Representations<\/a> Proceedings Article<\/span> <\/p>

In: <\/span>Proceedings of the Machine Learning for Healthcare Conference, MLHC 2019, 9-10 August 2019, Ann Arbor, Michigan, USA, <\/span>pp. 53\u201365, <\/span>Proceedings of Machine Learning Research, <\/span>2019<\/span>.<\/p>

Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

Jason A Fries; Paroma Varma; Vincent S Chen; Ke Xiao; Heliodoro Tejeda; Priyanka Saha; Jared Dunnmon; Henry Chubb; Shiraz Maskatia; Madalina Fiterau; Scott Delp; Euan Ashley; Christopher R\u00e9; James R Priest<\/p>

Weakly Supervised Classification of Aortic Valve Malformations using Unlabeled Cardiac MRI Sequences<\/a> Journal Article<\/span> <\/p>

In: <\/span>Nature communications, <\/span>vol. 10, <\/span>no. 1, <\/span>pp. 1\u201310, <\/span>2019<\/span>.<\/p>

Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

Debasmita Ghose; Shasvat Mukeshkumar Desai; Sneha Bhattacharya; Deep Chakraborty; Madalina Fiterau; Tauhidur Rahman<\/p>

Pedestrian Detection in Thermal Images Using Saliency Maps<\/a> Workshop<\/span> <\/p>

Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2019, <\/span>Computer Vision Foundation, <\/span>2019<\/span>.<\/p>

Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

Abhishek Sharma; Aritra Ghosh; Madalina Fiterau<\/p>

Generative Sequential Stochastic Model for Marked Point Processes<\/a> Workshop<\/span> <\/p>

International Conference on Machine Learning (ICML) Workshops 2019, <\/span>ICML Time Series Workshop, <\/span>2019<\/span>.<\/p>

Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

Rheeya Uppaal; Bryon Kucharski; Bhanu Pratap; Iman Deznabi; Madalina Fiterau<\/p>

Multi-resolution Attention with Signal Splitting for Multivariate Time Series Classification<\/a> Workshop<\/span> <\/p>

International Conference on Machine Learning (ICML) Workshops 2019, <\/span>ICML Time Series Workshop, <\/span>2019<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@workshop{ICMLTS19:mass,
\r\ntitle = {Multi-resolution Attention with Signal Splitting for Multivariate Time Series Classification},
\r\nauthor = {Rheeya Uppaal and Bryon Kucharski and Bhanu Pratap and Iman Deznabi and Madalina Fiterau},
\r\nurl = {http:\/\/roseyu.com\/time-series-workshop\/submissions\/2019\/timeseries-ICML19_paper_55.pdf},
\r\nyear  = {2019},
\r\ndate = {2019-06-15},
\r\nurldate = {2019-06-15},
\r\nbooktitle = {International Conference on Machine Learning (ICML) Workshops 2019},
\r\npublisher = {ICML Time Series Workshop},
\r\nabstract = {Real world multivariate time series pose three significant challenges: irregularity in sampling, missing values, and varying sampling frequencies among signals. Recent work for inference on such data aims at solving one of these issues, however a unified model is still lacking. We present a unified method which handles all three: Multi-resolution Attention with Signal Splitting (MASS). Our method is model-agnostic and can be applied to any existing model, significantly boosting predictive performance. MASS uses parallel multi-resolution blocks to model different resolution data streams, in addition to splitting signals into components of specific resolutions, to provide approximately a 3% improvement on the Physionet Challenge 2012 Dataset. We also compare to the state of the art TBM and GRU-D models, showcasing promising results against them.},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {workshop}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>

Abhinav Shaw; Natcha Simsiri; Iman Deznaby; Madalina Fiterau; Tauhidur Rahman<\/p>

Personalized Student Stress Prediction with Deep Multitask Network<\/a> Workshop<\/span> <\/p>

International Conference on Machine Learning (ICML) Workshops 2019, <\/span>ICML Adaptive and Multitask Learning Workshop, <\/span>2019<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@workshop{DBLP:journals\/corr\/abs-1906-11356,
\r\ntitle = {Personalized Student Stress Prediction with Deep Multitask Network},
\r\nauthor = {Abhinav Shaw and Natcha Simsiri and Iman Deznaby and Madalina Fiterau and Tauhidur Rahman},
\r\nurl = {http:\/\/arxiv.org\/abs\/1906.11356},
\r\nyear  = {2019},
\r\ndate = {2019-06-15},
\r\nurldate = {2019-06-15},
\r\nbooktitle = {International Conference on Machine Learning (ICML) Workshops 2019},
\r\njournal = {International Conference on Machine Learning (ICML) Workshops 2019},
\r\npublisher = {ICML Adaptive and Multitask Learning Workshop},
\r\nabstract = {With the growing popularity of wearable devices, the ability to utilize physiological data collected from these devices to predict the wearer's mental state such as mood and stress suggests great clinical applications, yet such a task is extremely challenging. In this paper, we present a general platform for personalized predictive modeling of behavioural states like students' level of stress. Through the use of Auto-encoders and Multitask learning we extend the prediction of stress to both sequences of passive sensor data and high-level covariates. Our model outperforms the state-of-the-art in the prediction of stress level from mobile sensor data, obtaining a 45.6 % improvement in F1 score on the StudentLife dataset.},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {workshop}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>

Bhanu Pratap Singh; Iman Deznabi; Bharath Narasimhan; Bryon Kucharski; Rheeya Uppaal; Akhila Josyula; Madalina Fiterau<\/p>

Multi-resolution Networks For Flexible Irregular Time Series Modeling (Multi-FIT)<\/a> Technical Report<\/span> <\/p>

2019<\/span>.<\/p>

Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

Ziqiang Guan; Ritesh Kumar; Yi Ren Fung; Yeahuay Wu; Madalina Fiterau<\/p>

A Comprehensive Study of Alzheimer's Disease Classification Using Convolutional Neural Networks<\/a> Technical Report<\/span> <\/p>

2019<\/span>.<\/p>

Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@techreport{DBLP:journals\/corr\/abs-1904-07950,
\r\ntitle = {A Comprehensive Study of Alzheimer's Disease Classification Using Convolutional Neural Networks},
\r\nauthor = {Ziqiang Guan and Ritesh Kumar and Yi Ren Fung and Yeahuay Wu and Madalina Fiterau},
\r\nurl = {http:\/\/arxiv.org\/abs\/1904.07950},
\r\nyear  = {2019},
\r\ndate = {2019-04-26},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {techreport}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>