Models, code, and papers for "Allison W":

Robust Navigation of a Soft Growing Robot by Exploiting Contact with the Environment

Aug 23, 2019
Joseph D. Greer, Laura H. Blumenschein, Ron Alterovitz, Elliot W. Hawkes, Allison M. Okamura

Navigation and motion control of a robot to a destination are tasks that have historically been performed with the assumption that contact with the environment is harmful. This makes sense for rigid-bodied robots where obstacle collisions are fundamentally dangerous. However, because many soft robots have bodies that are low-inertia and compliant, obstacle contact is inherently safe. As a result, constraining paths of the robot to not interact with the environment is not necessary and may be limiting. In this paper, we mathematically formalize interactions of a soft growing robot with a planar environment in an empirical kinematic model. Using this interaction model, we develop a method to plan paths for the robot to a destination. Rather than avoiding contact with the environment, the planner exploits obstacle contact when beneficial for navigation. We find that a planner that takes into account and capitalizes on environmental contact produces paths that are more robust to uncertainty than a planner that avoids all obstacle contact.


  Click for Model/Code and Paper
Retraction of Soft Growing Robots without Buckling

Oct 25, 2019
Margaret M. Coad, Rachel P. Thomasson, Laura H. Blumenschein, Nathan S. Usevitch, Elliot W. Hawkes, Allison M. Okamura

Tip-extending soft robots that "grow" via pneumatic eversion of their body material have demonstrated applications in exploration of cluttered environments. During growth, the motion and force of the robot tip can be controlled in three degrees of freedom using actuators that direct the tip in combination with extension. However, when reversal of the growth process is attempted by retracting the internal body material from the base, the robot body often responds by buckling rather than inversion of its body material, which makes control of tip motion and force impossible. We present and validate a model to predict when buckling occurs instead of inversion during retraction, and we present and evaluate an electromechanical device that can be added to a tip-extending soft robot to prevent buckling during retraction and enable control of all three degrees of freedom of tip actuation during inversion. Using our retraction device, we demonstrate completion of three previously impossible tasks: exploring different branches of a forking path, reversing growth while applying minimal force on the environment, and bringing back environment samples to the base.

* Video available at https://www.youtube.com/watch?v=Vw8cArH0vxk 

  Click for Model/Code and Paper
A Semi-Supervised Machine Learning Approach to Detecting Recurrent Metastatic Breast Cancer Cases Using Linked Cancer Registry and Electronic Medical Record Data

Jan 17, 2019
Albee Y. Ling, Allison W. Kurian, Jennifer L. Caswell-Jin, George W. Sledge Jr., Nigam H. Shah, Suzanne R. Tamang

Objectives: Most cancer data sources lack information on metastatic recurrence. Electronic medical records (EMRs) and population-based cancer registries contain complementary information on cancer treatment and outcomes, yet are rarely used synergistically. To enable detection of metastatic breast cancer (MBC), we applied a semi-supervised machine learning framework to linked EMR-California Cancer Registry (CCR) data. Materials and Methods: We studied 11,459 female patients treated at Stanford Health Care who received an incident breast cancer diagnosis from 2000-2014. The dataset consisted of structured data and unstructured free-text clinical notes from EMR, linked to CCR, a component of the Surveillance, Epidemiology and End Results (SEER) database. We extracted information on metastatic disease from patient notes to infer a class label and then trained a regularized logistic regression model for MBC classification. We evaluated model performance on a gold standard set of set of 146 patients. Results: There are 495 patients with de novo stage IV MBC, 1,374 patients initially diagnosed with Stage 0-III disease had recurrent MBC, and 9,590 had no evidence of metastatis. The median follow-up time is 96.3 months (mean 97.8, standard deviation 46.7). The best-performing model incorporated both EMR and CCR features. The area under the receiver-operating characteristic curve=0.925 [95% confidence interval: 0.880-0.969], sensitivity=0.861, specificity=0.878 and overall accuracy=0.870. Discussion and Conclusion: A framework for MBC case detection combining EMR and CCR data achieved good sensitivity, specificity and discrimination without requiring expert-labeled examples. This approach enables population-based research on how patients die from cancer and may identify novel predictors of cancer recurrence.


  Click for Model/Code and Paper
Vine Robots: Design, Teleoperation, and Deployment for Navigation and Exploration

Feb 28, 2019
Margaret M. Coad, Laura H. Blumenschein, Sadie Cutler, Javier A. Reyna Zepeda, Nicholas D. Naclerio, Haitham El-Hussieny, Usman Mehmood, Jee-Hwan Ryu, Elliot W. Hawkes, Allison M. Okamura

A new class of robots has recently been explored, characterized by tip extension, significant length change, and directional control. Here, we call this class of robots "vine robots," due to their similar behavior to plants with the growth habit of trailing. Due to their growth-based movement, vine robots are well suited for navigation and exploration in cluttered environments, but until now, they have not been deployed outside the lab. Portability of these robots and steerability at length scales relevant for navigation are key to field applications. In addition, intuitive human-in-the-loop teleoperation enables movement in unknown and dynamic environments. We present a vine robot system that is teleoperated using a custom designed flexible joystick and camera system, long enough for use in navigation tasks, and portable for use in the field. We report on deployment of this system in two scenarios: a soft robot navigation competition and exploration of an archaeological site. The competition course required movement over uneven terrain, past unstable obstacles, and through a small aperture. The archaeological site required movement over rocks and through horizontal and vertical turns. The robot tip successfully moved past the obstacles and through the tunnels, demonstrating the capability of vine robots to achieve real-world navigation and exploration tasks.


  Click for Model/Code and Paper
Deep Learning Captures More Accurate Diffusion Fiber Orientations Distributions than Constrained Spherical Deconvolution

Nov 13, 2019
Vishwesh Nath, Kurt G. Schilling, Colin B. Hansen, Prasanna Parvathaneni, Allison E. Hainline, Camilo Bermudez, Andrew J. Plassard, Vaibhav Janve, Yurui Gao, Justin A. Blaber, Iwona Stępniewska, Adam W. Anderson, Bennett A. Landman

Confocal histology provides an opportunity to establish intra-voxel fiber orientation distributions that can be used to quantitatively assess the biological relevance of diffusion weighted MRI models, e.g., constrained spherical deconvolution (CSD). Here, we apply deep learning to investigate the potential of single shell diffusion weighted MRI to explain histologically observed fiber orientation distributions (FOD) and compare the derived deep learning model with a leading CSD approach. This study (1) demonstrates that there exists additional information in the diffusion signal that is not currently exploited by CSD, and (2) provides an illustrative data-driven model that makes use of this information.

* 2 pages, 4 figures. This work was accepted and published as an abstract at ISMRM 2018 held in Paris, France 

  Click for Model/Code and Paper
Inter-Scanner Harmonization of High Angular Resolution DW-MRI using Null Space Deep Learning

Oct 09, 2018
Vishwesh Nath, Prasanna Parvathaneni, Colin B. Hansen, Allison E. Hainline, Camilo Bermudez, Samuel Remedios, Justin A. Blaber, Kurt G. Schilling, Ilwoo Lyu, Vaibhav Janve, Yurui Gao, Iwona Stepniewska, Baxter P. Rogers, Allen T. Newton, L. Taylor Davis, Jeff Luci, Adam W. Anderson, Bennett A. Landman

Diffusion-weighted magnetic resonance imaging (DW-MRI) allows for non-invasive imaging of the local fiber architecture of the human brain at a millimetric scale. Multiple classical approaches have been proposed to detect both single (e.g., tensors) and multiple (e.g., constrained spherical deconvolution, CSD) fiber population orientations per voxel. However, existing techniques generally exhibit low reproducibility across MRI scanners. Herein, we propose a data-driven tech-nique using a neural network design which exploits two categories of data. First, training data were acquired on three squirrel monkey brains using ex-vivo DW-MRI and histology of the brain. Second, repeated scans of human subjects were acquired on two different scanners to augment the learning of the network pro-posed. To use these data, we propose a new network architecture, the null space deep network (NSDN), to simultaneously learn on traditional observed/truth pairs (e.g., MRI-histology voxels) along with repeated observations without a known truth (e.g., scan-rescan MRI). The NSDN was tested on twenty percent of the histology voxels that were kept completely blind to the network. NSDN significantly improved absolute performance relative to histology by 3.87% over CSD and 1.42% over a recently proposed deep neural network approach. More-over, it improved reproducibility on the paired data by 21.19% over CSD and 10.09% over a recently proposed deep approach. Finally, NSDN improved gen-eralizability of the model to a third in vivo human scanner (which was not used in training) by 16.08% over CSD and 10.41% over a recently proposed deep learn-ing approach. This work suggests that data-driven approaches for local fiber re-construction are more reproducible, informative and precise and offers a novel, practical method for determining these models.

* 10 pages, 5 figures 

  Click for Model/Code and Paper
Curriculum Learning in Deep Neural Networks for Financial Forecasting

Apr 29, 2019
Allison Koenecke, Amita Gajewar

For any financial organization, computing accurate quarterly forecasts for various products is one of the most critical operations. As the granularity at which forecasts are needed increases, traditional statistical time series models may not scale well. We apply deep neural networks in the forecasting domain by experimenting with techniques from Natural Language Processing (Encoder-Decoder LSTMs) and Computer Vision (Dilated CNNs), as well as incorporating transfer learning. A novel contribution of this paper is the application of curriculum learning to neural network models built for time series forecasting. We illustrate the performance of our models using Microsoft's revenue data corresponding to Enterprise, and Small, Medium & Corporate products, spanning approximately 60 regions across the globe for 8 different business segments, and totaling in the order of tens of billions of USD. We compare our models' performance to the ensemble model of traditional statistics and machine learning techniques currently used by Microsoft Finance. With this in-production model as a baseline, our experiments yield an approximately 30% improvement in overall accuracy on test data. We find that our curriculum learning LSTM-based model performs best, showing that it is reasonable to implement our proposed methods without overfitting on medium-sized data.


  Click for Model/Code and Paper
Minimum message length estimation of mixtures of multivariate Gaussian and von Mises-Fisher distributions

Feb 27, 2015
Parthan Kasarapu, Lloyd Allison

Mixture modelling involves explaining some observed evidence using a combination of probability distributions. The crux of the problem is the inference of an optimal number of mixture components and their corresponding parameters. This paper discusses unsupervised learning of mixture models using the Bayesian Minimum Message Length (MML) criterion. To demonstrate the effectiveness of search and inference of mixture parameters using the proposed approach, we select two key probability distributions, each handling fundamentally different types of data: the multivariate Gaussian distribution to address mixture modelling of data distributed in Euclidean space, and the multivariate von Mises-Fisher (vMF) distribution to address mixture modelling of directional data distributed on a unit hypersphere. The key contributions of this paper, in addition to the general search and inference methodology, include the derivation of MML expressions for encoding the data using multivariate Gaussian and von Mises-Fisher distributions, and the analytical derivation of the MML estimates of the parameters of the two distributions. Our approach is tested on simulated and real world data sets. For instance, we infer vMF mixtures that concisely explain experimentally determined three-dimensional protein conformations, providing an effective null model description of protein structures that is central to many inference problems in structural bioinformatics. The experimental results demonstrate that the performance of our proposed search and inference method along with the encoding schemes improve on the state of the art mixture modelling techniques.

* 46 pages 

  Click for Model/Code and Paper
Wind Estimation Using Quadcopter Motion: A Machine Learning Approach

Jul 11, 2019
Sam Allison, He Bai, Balaji Jayaraman

In this article, we study the well known problem of wind estimation in atmospheric turbulence using small unmanned aerial systems (sUAS). We present a machine learning approach to wind velocity estimation based on quadcopter state measurements without a wind sensor. We accomplish this by training a long short-term memory (LSTM) neural network (NN) on roll and pitch angles and quadcopter position inputs with forcing wind velocities as the targets. The datasets are generated using a simulated quadcopter in turbulent wind fields. The trained neural network is deployed to estimate the turbulent winds as generated by the Dryden gust model as well as a realistic large eddy simulation (LES) of a near-neutral atmospheric boundary layer (ABL) over flat terrain. The resulting NN predictions are compared to a wind triangle approach that uses tilt angle as an approximation of airspeed. Results from this study indicate that the LSTM-NN based approach predicts lower errors in both the mean and variance of the local wind field as compared to the wind triangle approach. The work reported in this article demonstrates the potential of machine learning for sensor-less wind estimation and has strong implications to large-scale low-altitude atmospheric sensing using sUAS for environmental and autonomous navigation applications.


  Click for Model/Code and Paper
Learning Twitter User Sentiments on Climate Change with Limited Labeled Data

Apr 15, 2019
Allison Koenecke, Jordi Feliu-Fabà

While it is well-documented that climate change accepters and deniers have become increasingly polarized in the United States over time, there has been no large-scale examination of whether these individuals are prone to changing their opinions as a result of natural external occurrences. On the sub-population of Twitter users, we examine whether climate change sentiment changes in response to five separate natural disasters occurring in the U.S. in 2018. We begin by showing that relevant tweets can be classified with over 75% accuracy as either accepting or denying climate change when using our methodology to compensate for limited labeled data; results are robust across several machine learning models and yield geographic-level results in line with prior research. We then apply RNNs to conduct a cohort-level analysis showing that the 2018 hurricanes yielded a statistically significant increase in average tweet sentiment affirming climate change. However, this effect does not hold for the 2018 blizzard and wildfires studied, implying that Twitter users' opinions on climate change are fairly ingrained on this subset of natural disasters.


  Click for Model/Code and Paper
A cryptographic approach to black box adversarial machine learning

Jun 07, 2019
Kevin Shi, Daniel Hsu, Allison Bishop

We propose an ensemble technique for converting any classifier into a computationally secure classifier. We define a simpler security problem for random binary classifiers and prove a reduction from this model to the security of the overall ensemble classifier. We provide experimental evidence of the security of our random binary classifiers, as well as empirical results of the adversarial accuracy of the overall ensemble to black-box attacks. Our construction crucially leverages hidden randomness in the multiclass-to-binary reduction.


  Click for Model/Code and Paper
Proving the NP-completeness of optimal moral graph triangulation

Mar 06, 2019
Yang Li, Lloyd Allison, Kevin Korb

Moral graphs were introduced in the 1980s as an intermediate step when transforming a Bayesian network to a junction tree, on which exact belief propagation can be efficiently done. The moral graph of a Bayesian network can be trivially obtained by connecting non-adjacent parents for each node in the Bayesian network and dropping the direction of each edge. Perhaps because the moralization process looks simple, there has been little attention on the properties of moral graphs and their impact in belief propagation on Bayesian networks. This paper addresses the mistaken claim that it has been previously proved that optimal moral graph triangulation with the constraints of minimum fill-in, treewidth or total states is NP-complete. The problems are in fact NP-complete, but they have not previously been proved. We now prove these.


  Click for Model/Code and Paper
The Complexity of Morality: Checking Markov Blanket Consistency with DAGs via Morality

Mar 05, 2019
Yang Li, Kevin Korb, Lloyd Allison

A family of Markov blankets in a faithful Bayesian network satisfies the symmetry and consistency properties. In this paper, we draw a bijection between families of consistent Markov blankets and moral graphs. We define the new concepts of weak recursive simpliciality and perfect elimination kits. We prove that they are equivalent to graph morality. In addition, we prove that morality can be decided in polynomial time for graphs with maximum degree less than $5$, but the problem is NP-complete for graphs with higher maximum degrees.


  Click for Model/Code and Paper
Efficient and Trustworthy Social Navigation Via Explicit and Implicit Robot-Human Communication

Oct 26, 2018
Yuhang Che, Allison M. Okamura, Dorsa Sadigh

In this paper, we present a planning framework that uses a combination of implicit (robot motion) and explicit (visual/audio/haptic feedback) communication during mobile robot navigation in a manner that humans find understandable and trustworthy. First, we developed a model that approximates both continuous movements and discrete decisions in human navigation, considering the effects of implicit and explicit communication on human decision making. The model approximates the human as an optimal agent, with a reward function obtained through inverse reinforcement learning. Second, a planner uses this model to generate communicative actions that maximize the robot's transparency and efficiency. We implemented the planner on a mobile robot, using a wearable haptic device for explicit communication. In a user study of navigation in an indoor environment, the robot was able to actively communicate its intent to users in order to avoid collisions and facilitate efficient trajectories. Results showed that the planner generated plans that were easier to understand, reduced users' effort, and increased users' trust of the robot, compared to simply performing collision avoidance.


  Click for Model/Code and Paper
Detecting User Engagement in Everyday Conversations

Oct 13, 2004
Chen Yu, Paul M. Aoki, Allison Woodruff

This paper presents a novel application of speech emotion recognition: estimation of the level of conversational engagement between users of a voice communication system. We begin by using machine learning techniques, such as the support vector machine (SVM), to classify users' emotions as expressed in individual utterances. However, this alone fails to model the temporal and interactive aspects of conversational engagement. We therefore propose the use of a multilevel structure based on coupled hidden Markov models (HMM) to estimate engagement levels in continuous natural speech. The first level is comprised of SVM-based classifiers that recognize emotional states, which could be (e.g.) discrete emotion types or arousal/valence levels. A high-level HMM then uses these emotional states as input, estimating users' engagement in conversation by decoding the internal states of the HMM. We report experimental results obtained by applying our algorithms to the LDC Emotional Prosody and CallFriend speech corpora.

* Proc. 8th Int'l Conf. on Spoken Language Processing (ICSLP) (Vol. 2), Jeju Island, Republic of Korea, Oct. 2004, 1329-1332. ISCA. 
* 4 pages (A4), 1 figure (EPS) 

  Click for Model/Code and Paper
Optimizing genetic algorithm strategies for evolving networks

Apr 07, 2004
Matthew J. Berryman, Andrew Allison, Derek Abbott

This paper explores the use of genetic algorithms for the design of networks, where the demands on the network fluctuate in time. For varying network constraints, we find the best network using the standard genetic algorithm operators such as inversion, mutation and crossover. We also examine how the choice of genetic algorithm operators affects the quality of the best network found. Such networks typically contain redundancy in servers, where several servers perform the same task and pleiotropy, where servers perform multiple tasks. We explore this trade-off between pleiotropy versus redundancy on the cost versus reliability as a measure of the quality of the network.

* 9 pages, 5 figures 

  Click for Model/Code and Paper
Effects of Haptic Feedback on the Wrist during Virtual Manipulation

Nov 14, 2019
Mine Sarac, Allison M. Okamura, Massimiliano Di Luca

As an alternative to thimble devices for the fingertips, we investigate haptic systems that apply stimulus to the user's forearm. Our aim is to provide effective interaction with virtual objects, despite the lack of co-location of virtual and real-world contacts, while taking advantage of relatively large skin area and ease of mounting on the forearm. We developed prototype wearable haptic devices that provide skin deformation in the normal and shear directions, and performed a user study to determine the effects of haptic feedback in different directions and at different locations near the wrist during virtual manipulation. Participants performed significantly better while discriminating stiffness values of virtual objects with normal forces compared to shear forces. We found no differences in performance or participant preferences with regard to stimulus on the dorsal, ventral, or both sides of the forearm.

* 7 pages, submitted conference paper for IEEE Haptics Symposium 2020 

  Click for Model/Code and Paper
Haptic Sketches on the Arm for Manipulation in Virtual Reality

Nov 14, 2019
Mine Sarac, Allison M. Okamura, Massimiliano Di Luca

We propose a haptic system that applies forces or skin deformation to the user's arm, rather than at the fingertips, for believable interaction with virtual objects as an alternative to complex thimble devices. Such a haptic system would be able to convey information to the arm instead of the fingertips, even though the user manipulates virtual objects using their hands. We developed a set of haptic sketches to determine which directions of skin deformation are deemed more believable during a grasp and lift task. Subjective reports indicate that normal forces were the most believable feedback to represent this interaction.

* IEEE World Haptics Conference 2019, Work In Progress 
* 2 pages, work in progress 

  Click for Model/Code and Paper
Effects of Haptic Feedback on the Wristduring Virtual Manipulation

Nov 05, 2019
Mine Sarac, Allison M. Okamura, Massimiliano Di Luca

As an alternative to thimble devices for the fingertips, we investigate haptic systems that apply stimulus to the user's forearm. Our aim is to provide effective interaction with virtual objects, despite the lack of co-location of virtual and real-world contacts, while taking advantage of relatively large skin area and ease of mounting on the forearm. We developed prototype wearable haptic devices that provide skin deformation in the normal and shear directions, and performed a user study to determine the effects of haptic feedback in different directions and at different locations near the wrist during virtual manipulation. Participants performed significantly better while discriminating stiffness values of virtual objects with normal forces compared to shear forces. We found no differences in performance or participant preferences with regard to stimulus on the dorsal, ventral, or both sides of the forearm.

* 7 pages, submitted conference paper for IEEE Haptics Symposium 2020 

  Click for Model/Code and Paper
Ignoring Distractors in the Absence of Labels: Optimal Linear Projection to Remove False Positives During Anomaly Detection

Sep 13, 2017
Allison Del Giorno, J. Andrew Bagnell, Martial Hebert

In the anomaly detection setting, the native feature embedding can be a crucial source of bias. We present a technique, Feature Omission using Context in Unsupervised Settings (FOCUS) to learn a feature mapping that is invariant to changes exemplified in training sets while retaining as much descriptive power as possible. While this method could apply to many unsupervised settings, we focus on applications in anomaly detection, where little task-labeled data is available. Our algorithm requires only non-anomalous sets of data, and does not require that the contexts in the training sets match the context of the test set. By maximizing within-set variance and minimizing between-set variance, we are able to identify and remove distracting features while retaining fidelity to the descriptiveness needed at test time. In the linear case, our formulation reduces to a generalized eigenvalue problem that can be solved quickly and applied to test sets outside the context of the training sets. This technique allows us to align technical definitions of anomaly detection with human definitions through appropriate mappings of the feature space. We demonstrate that this method is able to remove uninformative parts of the feature space for the anomaly detection setting.

* 13 pages, 6 figures 

  Click for Model/Code and Paper