Models, code, and papers for "Michelle X":

Confiding in and Listening to Virtual Agents: The Effect of Personality

Nov 02, 2018
Jingyi Li, Michelle X. Zhou, Huahai Yang, Gloria Mark

We present an intelligent virtual interviewer that engages with a user in a text-based conversation and automatically infers the user's psychological traits, such as personality. We investigate how the personality of a virtual interviewer influences a user's behavior from two perspectives: the user's willingness to confide in, and listen to, a virtual interviewer. We have developed two virtual interviewers with distinct personalities and deployed them in a real-world recruiting event. We present findings from completed interviews with 316 actual job applicants. Notably, users are more willing to confide in and listen to a virtual interviewer with a serious, assertive personality. Moreover, users' personality traits, inferred from their chat text, influence their perception of a virtual interviewer, and their willingness to confide in and listen to a virtual interviewer. Finally, we discuss the implications of our work on building hyper-personalized, intelligent agents based on user traits.


  Click for Model/Code and Paper
Tell Me About Yourself: Using an AI-Powered Chatbot to Conduct Conversational Surveys

May 25, 2019
Ziang Xiao, Michelle X. Zhou, Q. Vera Liao, Gloria Mark, Changyan Chi, Wenxi Chen, Huahai Yang

The rise of increasingly more powerful chatbots offers a new way to collect information through conversational surveys, where a chatbot asks open-ended questions, interprets a user's free-text responses, and probes answers when needed. To investigate the effectiveness and limitations of such a chatbot in conducting surveys, we conducted a field study involving about 600 participants. In this study, half of the participants took a typical online survey on Qualtrics and the other half interacted with an AI-powered chatbot to complete a conversational survey. Our detailed analysis of over 5200 free-text responses revealed that the chatbot drove a significantly higher level of participant engagement and elicited significantly better quality responses in terms of relevance, depth, and readability. Based on our results, we discuss design implications for creating AI-powered chatbots to conduct effective surveys and beyond.

* Currently under review 

  Click for Model/Code and Paper
Decoupling Respiratory and Angular Variation in Rotational X-ray Scans Using a Prior Bilinear Model

Nov 05, 2018
Tobias Geimer, Paul Keall, Katharina Breininger, Vincent Caillet, Michelle Dunbar, Christoph Bert, Andreas Maier

Data-driven respiratory signal extraction from rotational X-ray scans is a challenge as angular effects overlap with respiration-induced change in the scene. In this paper, we use the linearity of the X-ray transform to propose a bilinear model based on a prior 4D scan to separate angular and respiratory variation. The bilinear estimation process is supported by a B-spline interpolation using prior knowledge about the trajectory angle. Consequently, extraction of respiratory features simplifies to a linear problem. Though the need for a prior 4D CT seems steep, our proposed use-case of driving a respiratory motion model in radiation therapy usually meets this requirement. We evaluate on DRRs of 5 patient 4D CTs in a leave-one-phase-out manner and achieve a mean estimation error of 3.01 % in the gray values for unseen viewing angles. We further demonstrate suitability of the extracted weights to drive a motion model for treatments with a continuously rotating gantry.


  Click for Model/Code and Paper
DeepSource: Point Source Detection using Deep Learning

Jul 07, 2018
A. Vafaei Sadr, Etienne. E. Vos, Bruce A. Bassett, Zafiirah Hosenie, N. Oozeer, Michelle Lochner

Point source detection at low signal-to-noise is challenging for astronomical surveys, particularly in radio interferometry images where the noise is correlated. Machine learning is a promising solution, allowing the development of algorithms tailored to specific telescope arrays and science cases. We present DeepSource - a deep learning solution - that uses convolutional neural networks to achieve these goals. DeepSource enhances the Signal-to-Noise Ratio (SNR) of the original map and then uses dynamic blob detection to detect sources. Trained and tested on two sets of 500 simulated 1 deg x 1 deg MeerKAT images with a total of 300,000 sources, DeepSource is essentially perfect in both purity and completeness down to SNR = 4 and outperforms PyBDSF in all metrics. For uniformly-weighted images it achieves a Purity x Completeness (PC) score at SNR = 3 of 0.73, compared to 0.31 for the best PyBDSF model. For natural-weighting we find a smaller improvement of ~40% in the PC score at SNR = 3. If instead we ask where either of the purity or completeness first drop to 90%, we find that DeepSource reaches this value at SNR = 3.6 compared to the 4.3 of PyBDSF (natural-weighting). A key advantage of DeepSource is that it can learn to optimally trade off purity and completeness for any science case under consideration. Our results show that deep learning is a promising approach to point source detection in astronomical images.

* 15 pages, 13 figures, submitted to MNRAS 

  Click for Model/Code and Paper
Detecting Falls with X-Factor Hidden Markov Models

Jan 20, 2017
Shehroz S. Khan, Michelle E. Karg, Dana Kulic, Jesse Hoey

Identification of falls while performing normal activities of daily living (ADL) is important to ensure personal safety and well-being. However, falling is a short term activity that occurs infrequently. This poses a challenge to traditional classification algorithms, because there may be very little training data for falls (or none at all). This paper proposes an approach for the identification of falls using a wearable device in the absence of training data for falls but with plentiful data for normal ADL. We propose three `X-Factor' Hidden Markov Model (XHMMs) approaches. The XHMMs model unseen falls using "inflated" output covariances (observation models). To estimate the inflated covariances, we propose a novel cross validation method to remove "outliers" from the normal ADL that serve as proxies for the unseen falls and allow learning the XHMMs using only normal activities. We tested the proposed XHMM approaches on two activity recognition datasets and show high detection rates for falls in the absence of fall-specific training data. We show that the traditional method of choosing a threshold based on maximum of negative of log-likelihood to identify unseen falls is ill-posed for this problem. We also show that supervised classification methods perform poorly when very limited fall data are available during the training phase.

* Applied Soft Computing Volume 55, June 2017, Pages 168-177 
* 27 pages, 4 figures, 3 tables, Applied Soft Computing, 2017 

  Click for Model/Code and Paper
Medical Multimodal Classifiers Under Scarce Data Condition

Feb 24, 2019
Faik Aydin, Maggie Zhang, Michelle Ananda-Rajah, Gholamreza Haffari

Data is one of the essential ingredients to power deep learning research. Small datasets, especially specific to medical institutes, bring challenges to deep learning training stage. This work aims to develop a practical deep multimodal that can classify patients into abnormal and normal categories accurately as well as assist radiologists to detect visual and textual anomalies by locating areas of interest. The detection of the anomalies is achieved through a novel technique which extends the integrated gradients methodology with an unsupervised clustering algorithm. This technique also introduces a tuning parameter which trades off true positive signals to denoise false positive signals in the detection process. To overcome the challenges of the small training dataset which only has 3K frontal X-ray images and medical reports in pairs, we have adopted transfer learning for the multimodal which concatenates the layers of image and text submodels. The image submodel was trained on the vast ChestX-ray14 dataset, while the text submodel transferred a pertained word embedding layer from a hospital-specific corpus. Experimental results show that our multimodal improves the accuracy of the classification by 4% and 7% on average of 50 epochs, compared to the individual text and image model, respectively.


  Click for Model/Code and Paper
A Survey of the Trends in Facial and Expression Recognition Databases and Methods

Dec 05, 2015
Sohini Roychowdhury, Michelle Emmons

Automated facial identification and facial expression recognition have been topics of active research over the past few decades. Facial and expression recognition find applications in human-computer interfaces, subject tracking, real-time security surveillance systems and social networking. Several holistic and geometric methods have been developed to identify faces and expressions using public and local facial image databases. In this work we present the evolution in facial image data sets and the methodologies for facial identification and recognition of expressions such as anger, sadness, happiness, disgust, fear and surprise. We observe that most of the earlier methods for facial and expression recognition aimed at improving the recognition rates for facial feature-based methods using static images. However, the recent methodologies have shifted focus towards robust implementation of facial/expression recognition from large image databases that vary with space (gathered from the internet) and time (video recordings). The evolution trends in databases and methodologies for facial and expression recognition can be useful for assessing the next-generation topics that may have applications in security systems or personal identification systems that involve "Quantitative face" assessments.

* International Journal of Computer Science & Engineering Survey, 2015, 6, 1-19 
* 16 pages, 4 figures, 3 tables, International Journal of Computer Science and Engineering Survey, October, 2015 

  Click for Model/Code and Paper
A Flexible Mixed Integer Programming framework for Nurse Scheduling

Oct 12, 2012
Murphy Choy, Michelle Cheong

In this paper, a nurse-scheduling model is developed using mixed integer programming model. It is deployed to a general care ward to replace and automate the current manual approach for scheduling. The developed model differs from other similar studies in that it optimizes both hospitals requirement as well as nurse preferences by allowing flexibility in the transfer of nurses from different duties. The model also incorporated additional policies which are part of the hospitals requirement but not part of the legislations. Hospitals key primary mission is to ensure continuous ward care service with appropriate number of nursing staffs and the right mix of nursing skills. The planning and scheduling is done to avoid additional non essential cost for hospital. Nurses preferences are taken into considerations such as the number of night shift and consecutive rest days. We will also reformulate problems from another paper which considers the penalty objective using the model but without the flexible components. The models are built using AIMMS which solves the problem in very short amount of time.


  Click for Model/Code and Paper
Intelligent Search Heuristics for Cost Based Scheduling

Oct 04, 2012
Murphy Choy, Michelle Cheong

Nurse scheduling is a difficult optimization problem with multiple constraints. There is extensive research in the literature solving the problem using meta-heuristics approaches. In this paper, we will investigate an intelligent search heuristics that handles cost based scheduling problem. The heuristics demonstrated superior performances compared to the original algorithms used to solve the problems described in Li et. Al. (2003) and Ozkarahan (1989) in terms of time needed to establish a feasible solution. Both problems can be formulated as a cost problem. The search heuristic consists of several phrases of search and input based on the cost of each assignment and how the assignment will interact with the cost of the resources.


  Click for Model/Code and Paper
Adaptive Grasp Control through Multi-Modal Interactions for Assistive Prosthetic Devices

Oct 18, 2018
Michelle Esponda, Thomas M. Howard

The hand is one of the most complex and important parts of the human body. The dexterity provided by its multiple degrees of freedom enables us to perform many of the tasks of daily living which involve grasping and manipulating objects of interest. Contemporary prosthetic devices for people with transradial amputations or wrist disarticulation vary in complexity, from passive prosthetics to complex devices that are body or electrically driven. One of the important challenges in developing smart prosthetic hands is to create devices which are able to mimic all activities that a person might perform and address the needs of a wide variety of users. The approach explored here is to develop algorithms that permit a device to adapt its behavior to the preferences of the operator through interactions with the wearer. This device uses multiple sensing modalities including muscle activity from a myoelectric armband, visual information from an on-board camera, tactile input through a touchscreen interface, and speech input from an embedded microphone. Presented within this paper are the design, software and controls of a platform used to evaluate this architecture as well as results from experiments deigned to quantify the performance.

* Presented at AI-HRI AAAI-FSS, 2018 (arXiv:1809.06606) 

  Click for Model/Code and Paper
Pruning Bayesian Networks for Efficient Computation

Mar 27, 2013
Michelle Baker, Terrance E. Boult

This paper analyzes the circumstances under which Bayesian networks can be pruned in order to reduce computational complexity without altering the computation for variables of interest. Given a problem instance which consists of a query and evidence for a set of nodes in the network, it is possible to delete portions of the network which do not participate in the computation for the query. Savings in computational complexity can be large when the original network is not singly connected. Results analogous to those described in this paper have been derived before [Geiger, Verma, and Pearl 89, Shachter 88] but the implications for reducing complexity of the computations in Bayesian networks have not been stated explicitly. We show how a preprocessing step can be used to prune a Bayesian network prior to using standard algorithms to solve a given problem instance. We also show how our results can be used in a parallel distributed implementation in order to achieve greater savings. We define a computationally equivalent subgraph of a Bayesian network. The algorithm developed in [Geiger, Verma, and Pearl 89] is modified to construct the subgraphs described in this paper with O(e) complexity, where e is the number of edges in the Bayesian network. Finally, we define a minimal computationally equivalent subgraph and prove that the subgraphs described are minimal.

* Appears in Proceedings of the Sixth Conference on Uncertainty in Artificial Intelligence (UAI1990) 

  Click for Model/Code and Paper
Evaluating Discussion Boards on BlackBoard as a Collaborative Learning Tool A Students Survey and Reflections

Oct 03, 2012
AbdelHameed A. Badawy, Michelle M. Hugue

In this paper, we investigate how the students think of their experience in a junior level course that has a blackboard course presence where the students use the discussion boards extensively. A survey is set up through blackboard as a voluntary quiz and the student who participated were given a freebie point. The results and the participation were very interesting in terms of the feedback we got via open comments from the students as well as the statistics we gathered from the answers to the questions. The students have shown understanding and willingness to participate in pedagogy-enhancing endeavors.

* In proceedings of the IEEE International Conference on Education and Management Technology (ICEMT 2010), pages 79 - 82, Cairo, Egypt November 2010 
* 5 pages, 12 tables, appears in proceedings of the IEEE International Conference on Education and Management Technology (ICEMT 2010), Cairo, Egypt November 2010. arXiv admin note: substantial text overlap with arXiv:1210.1178 

  Click for Model/Code and Paper
Bayesian Anomaly Detection and Classification

Feb 22, 2019
Ethan Roberts, Bruce A. Bassett, Michelle Lochner

Statistical uncertainties are rarely incorporated in machine learning algorithms, especially for anomaly detection. Here we present the Bayesian Anomaly Detection And Classification (BADAC) formalism, which provides a unified statistical approach to classification and anomaly detection within a hierarchical Bayesian framework. BADAC deals with uncertainties by marginalising over the unknown, true, value of the data. Using simulated data with Gaussian noise, BADAC is shown to be superior to standard algorithms in both classification and anomaly detection performance in the presence of uncertainties, though with significantly increased computational cost. Additionally, BADAC provides well-calibrated classification probabilities, valuable for use in scientific pipelines. We show that BADAC can work in online mode and is fairly robust to model errors, which can be diagnosed through model-selection methods. In addition it can perform unsupervised new class detection and can naturally be extended to search for anomalous subsets of data. BADAC is therefore ideal where computational cost is not a limiting factor and statistical rigour is important. We discuss approximations to speed up BADAC, such as the use of Gaussian processes, and finally introduce a new metric, the Rank-Weighted Score (RWS), that is particularly suited to evaluating the ability of algorithms to detect anomalies.

* 29 pages, 13 figures, Demo available: https://github.com/ethyroberts/BADAC 

  Click for Model/Code and Paper
Instance-based Deep Transfer Learning

Sep 08, 2018
Tianyang Wang, Jun Huan, Michelle Zhu

Deep transfer learning has acquired significant research interest. It makes use of pre-trained models that are learned from a source domain, and utilizes these models for the tasks in a target domain. Model-based deep transfer learning is arguably the most frequently used method. However, very little work has been devoted to enhancing deep transfer learning by focusing on the influence of data. In this work, we propose an instance-based approach to improve deep transfer learning in target domain. Specifically, we choose a pre-trained model which is learned from a source domain, and utilize this model to estimate the influence of each training sample in a target domain. Then we optimize training data of the target domain by removing the training samples that will lower the performance of the pre-trained model. We then fine-tune the pre-trained model with the optimized training data in the target domain, or build a new model which can be initialized partially based on the pre-trained model, and fine-tune it with the optimized training data in the target domain. Using this approach, transfer learning can help deep learning models to learn more useful features. Extensive experiments demonstrate the effectiveness of our approach on further boosting deep learning models for typical high-level computer vision tasks, such as image classification.


  Click for Model/Code and Paper
An ELU Network with Total Variation for Image Denoising

Aug 14, 2017
Tianyang Wang, Zhengrui Qin, Michelle Zhu

In this paper, we propose a novel convolutional neural network (CNN) for image denoising, which uses exponential linear unit (ELU) as the activation function. We investigate the suitability by analyzing ELU's connection with trainable nonlinear reaction diffusion model (TNRD) and residual denoising. On the other hand, batch normalization (BN) is indispensable for residual denoising and convergence purpose. However, direct stacking of BN and ELU degrades the performance of CNN. To mitigate this issue, we design an innovative combination of activation layer and normalization layer to exploit and leverage the ELU network, and discuss the corresponding rationale. Moreover, inspired by the fact that minimizing total variation (TV) can be applied to image denoising, we propose a TV regularized L2 loss to evaluate the training effect during the iterations. Finally, we conduct extensive experiments, showing that our model outperforms some recent and popular approaches on Gaussian denoising with specific or randomized noise levels for both gray and color images.

* 10 pages, Accepted by the 24th International Conference on Neural Information Processing (2017) 

  Click for Model/Code and Paper
Knowledge Distillation for Small-footprint Highway Networks

Dec 20, 2016
Liang Lu, Michelle Guo, Steve Renals

Deep learning has significantly advanced state-of-the-art of speech recognition in the past few years. However, compared to conventional Gaussian mixture acoustic models, neural network models are usually much larger, and are therefore not very deployable in embedded devices. Previously, we investigated a compact highway deep neural network (HDNN) for acoustic modelling, which is a type of depth-gated feedforward neural network. We have shown that HDNN-based acoustic models can achieve comparable recognition accuracy with much smaller number of model parameters compared to plain deep neural network (DNN) acoustic models. In this paper, we push the boundary further by leveraging on the knowledge distillation technique that is also known as {\it teacher-student} training, i.e., we train the compact HDNN model with the supervision of a high accuracy cumbersome model. Furthermore, we also investigate sequence training and adaptation in the context of teacher-student training. Our experiments were performed on the AMI meeting speech recognition corpus. With this technique, we significantly improved the recognition accuracy of the HDNN acoustic model with less than 0.8 million parameters, and narrowed the gap between this model and the plain DNN with 30 million parameters.

* 5 pages, 2 figures, accepted to icassp 2017 

  Click for Model/Code and Paper
Identifying Model Weakness with Adversarial Examiner

Nov 25, 2019
Michelle Shu, Chenxi Liu, Weichao Qiu, Alan Yuille

Machine learning models are usually evaluated according to the average case performance on the test set. However, this is not always ideal, because in some sensitive domains (e.g. autonomous driving), it is the worst case performance that matters more. In this paper, we are interested in systematic exploration of the input data space to identify the weakness of the model to be evaluated. We propose to use an adversarial examiner in the testing stage. Different from the existing strategy to always give the same (distribution of) test data, the adversarial examiner will dynamically select the next test data to hand out based on the testing history so far, with the goal being to undermine the model's performance. This sequence of test data not only helps us understand the current model, but also serves as constructive feedback to help improve the model in the next iteration. We conduct experiments on ShapeNet object classification. We show that our adversarial examiner can successfully put more emphasis on the weakness of the model, preventing performance estimates from being overly optimistic.

* To appear in AAAI-20 

  Click for Model/Code and Paper
Deep Sensor Fusion for Real-Time Odometry Estimation

Jul 31, 2019
Michelle Valente, Cyril Joly, Arnaud de La Fortelle

Cameras and 2D laser scanners, in combination, are able to provide low-cost, light-weight and accurate solutions, which make their fusion well-suited for many robot navigation tasks. However, correct data fusion depends on precise calibration of the rigid body transform between the sensors. In this paper we present the first framework that makes use of Convolutional Neural Networks (CNNs) for odometry estimation fusing 2D laser scanners and mono-cameras. The use of CNNs provides the tools to not only extract the features from the two sensors, but also to fuse and match them without needing a calibration between the sensors. We transform the odometry estimation into an ordinal classification problem in order to find accurate rotation and translation values between consecutive frames. Results on a real road dataset show that the fusion network runs in real-time and is able to improve the odometry estimation of a single sensor alone by learning how to fuse two different types of data information.

* arXiv admin note: substantial text overlap with arXiv:1902.08536 

  Click for Model/Code and Paper
Fusing Laser Scanner and Stereo Camera in Evidential Grid Maps

Feb 22, 2019
Michelle Valente, Cyril Joly, Arnaud de la Fortelle

Automation driving techniques have seen tremendous progresses these last years, particularly due to a better perception of the environment. In order to provide safe yet not too conservative driving in complex urban environment, data fusion should not only consider redundant sensing to characterize the surrounding obstacles, but also be able to describe the uncertainties and errors beyond presence/absence (be it binary or probabilistic). This paper introduces an enriched representation of the world, more precisely of the potential existence of obstacles through an evidential grid map. A method to create this representation from 2 very different sensors, laser scanner and stereo camera, is presented along with algorithms for data fusion and temporal updates. This work allows a better handling of the dynamic aspects of the urban environment and a proper management of errors in order to create a more reliable map. We use the evidential framework based on the Dempster-Shafer theory to model the environment perception by the sensors. A new combination operator is proposed to merge the different sensor grids considering their distinct uncertainties. In addition, we introduce a new long-life layer with high level states that allows the maintenance of a global map of the entire vehicle's trajectory and distinguish between static and dynamic obstacles. Results on a real road dataset show that the environment mapping data can be improved by adding relevant information that could be missed without the proposed approach.


  Click for Model/Code and Paper
An LSTM Network for Real-Time Odometry Estimation

Feb 22, 2019
Michelle Valente, Cyril Joly, Arnaud de La Fortelle

The use of 2D laser scanners is attractive for the autonomous driving industry because of its accuracy, light-weight and low-cost. However, since only a 2D slice of the surrounding environment is detected at each scan, it is a challenge to execute important tasks such as the localization of the vehicle. In this paper we present a novel framework that explores the use of deep Recurrent Convolutional Neural Networks (RCNN) for odometry estimation using only 2D laser scanners. The application of RCNNs provides the tools to not only extract the features of the laser scanner data using Convolutional Neural Networks (CNNs), but in addition it models the possible connections among consecutive scans using the Long Short-Term Memory (LSTM) Recurrent Neural Network. Results on a real road dataset show that the method can run in real-time without using GPU acceleration and have competitive performance compared to other methods, being an interesting approach that could complement traditional localization systems.


  Click for Model/Code and Paper