Models, code, and papers for "Alexis B":

Deep Multi-task Prediction of Lung Cancer and Cancer-free Progression from Censored Heterogenous Clinical Imaging

Nov 12, 2019
Riqiang Gao, Lingfeng Li, Yucheng Tang, Sanja L. Antic, Alexis B. Paulson, Yuankai Huo, Kim L. Sandler, Pierre P. Massion, Bennett A. Landman

Annual low dose computed tomography (CT) lung screening is currently advised for individuals at high risk of lung cancer (e.g., heavy smokers between 55 and 80 years old). The recommended screening practice significantly reduces all-cause mortality, but the vast majority of screening results are negative for cancer. If patients at very low risk could be identified based on individualized, image-based biomarkers, the health care resources could be more efficiently allocated to higher risk patients and reduce overall exposure to ionizing radiation. In this work, we propose a multi-task (diagnosis and prognosis) deep convolutional neural network to improve the diagnostic accuracy over a baseline model while simultaneously estimating a personalized cancer-free progression time (CFPT). A novel Censored Regression Loss (CRL) is proposed to perform weakly supervised regression so that even single negative screening scans can provide small incremental value. Herein, we study 2287 scans from 1433 de-identified patients from the Vanderbilt Lung Screening Program (VLSP) and Molecular Characterization Laboratories (MCL) cohorts. Using five-fold cross-validation, we train a 3D attention-based network under two scenarios: (1) single-task learning with only classification, and (2) multi-task learning with both classification and regression. The single-task learning leads to a higher AUC compared with the Kaggle challenge winner pre-trained model (0.878 v. 0.856), and multi-task learning significantly improves the single-task one (AUC 0.895, p<0.01, McNemar test). In summary, the image-based predicted CFPT can be used in follow-up year lung cancer prediction and data assessment.

* 8 pages, 5 figures, SPIE 2020 Medical Imaging, oral presentation 

  Click for Model/Code and Paper
Distanced LSTM: Time-Distanced Gates in Long Short-Term Memory Models for Lung Cancer Detection

Sep 11, 2019
Riqiang Gao, Yuankai Huo, Shunxing Bao, Yucheng Tang, Sanja L. Antic, Emily S. Epstein, Aneri B. Balar, Steve Deppen, Alexis B. Paulson, Kim L. Sandler, Pierre P. Massion, Bennett A. Landman

The field of lung nodule detection and cancer prediction has been rapidly developing with the support of large public data archives. Previous studies have largely focused on cross-sectional (single) CT data. Herein, we consider longitudinal data. The Long Short-Term Memory (LSTM) model addresses learning with regularly spaced time points (i.e., equal temporal intervals). However, clinical imaging follows patient needs with often heterogeneous, irregular acquisitions. To model both regular and irregular longitudinal samples, we generalize the LSTM model with the Distanced LSTM (DLSTM) for temporally varied acquisitions. The DLSTM includes a Temporal Emphasis Model (TEM) that enables learning across regularly and irregularly sampled intervals. Briefly, (1) the time intervals between longitudinal scans are modeled explicitly, (2) temporally adjustable forget and input gates are introduced for irregular temporal sampling; and (3) the latest longitudinal scan has an additional emphasis term. We evaluate the DLSTM framework in three datasets including simulated data, 1794 National Lung Screening Trial (NLST) scans, and 1420 clinically acquired data with heterogeneous and irregular temporal accession. The experiments on the first two datasets demonstrate that our method achieves competitive performance on both simulated and regularly sampled datasets (e.g. improve LSTM from 0.6785 to 0.7085 on F1 score in NLST). In external validation of clinically and irregularly acquired data, the benchmarks achieved 0.8350 (CNN feature) and 0.8380 (LSTM) on the area under the ROC curve (AUC) score, while the proposed DLSTM achieves 0.8905.

* This paper is accepted by MLMI (oral), MICCAI workshop 

  Click for Model/Code and Paper
Application of Grover's Algorithm on the ibmqx4 Quantum Computer to Rule-based Algorithmic Music Composition

Feb 02, 2019
Alexis Kirke

Previous research on quantum computing/mechanics and the arts has usually been in simulation. The small amount of work done in hardware or with actual physical systems has not utilized any of the advantages of quantum computation: the main advantage being the potential speed increase of quantum algorithms. This paper introduces a way of utilizing Grover's algorithm - which has been shown to provide a quadratic speed-up over its classical equivalent - in algorithmic rule-based music composition. The system introduced - qgMuse - is simple but scalable. It lays some groundwork for new ways of addressing a significant problem in computer music research: unstructured random search for desired music features. Example melodies are composed using qgMuse using the ibmqx4 quantum hardware, and the paper concludes with discussion on how such an approach can grow with the improvement of quantum computer hardware and software.

  Click for Model/Code and Paper
Aerial Drop of Robots and Sensors for Optimal Area Coverage

Nov 28, 2017
Kostas Alexis

The problem of rapid optimal coverage through the distribution a team of robots or static sensors via means of aerial drop is the topic of this work. Considering a nonholonomic (fixed-wing) aerial robot that corresponds to the carrier of a set of small holonomic (rotorcraft) aerial robots as well as static modules that are all equipped with a camera sensor, we address the problem of selecting optimal aerial drop times and configurations while the motion capabilities of the small aerial robots are also exploited to further survey their area of responsibility until they hit the ground. The overall solution framework consists of lightweight path-planning algorithms that can run on virtually any processing unit that might be available on-board. Evaluation studies in simulation as well as a set of elementary experiments that prove the validity of important assumptions illustrate the potential of the approach.

* 6 pages, 9 figures, technical report 

  Click for Model/Code and Paper
Realizing the Aerial Robotic Worker for Inspection Operations

Mar 08, 2017
Kostas Alexis

This report overviews a set of recent contributions in the field of path planning that were developed to enable the realization of the autonomous aerial robotic worker for inspection operations. The specific algorithmic contributions address several fundamental challenges of robotic inspection and exploration, and specifically those of optimal coverage planning given an a priori known model of the structure to be inspected, full coverage, optimized and fast inspection path planning, as well as efficient exploration of completely unknown environments and structures. All of the developed path planners support both holonomic and nonholonomic systems, and respect the on-board sensor model and constraints. An overview of the achieved results, followed by an integrating architecture in order to enable fully autonomous and highly-efficient infrastructure inspection in both known and unknown environments.

  Click for Model/Code and Paper
Technical Report: Optimal Surveillance of Dynamic Parades using Teams of Aerial Robots

Dec 30, 2016
Kostas Alexis

This technical report addresses the problem of optimal surveillance of the route followed by a dynamic parade using a team of aerial robots. The dynamic parade is considered to take place within an urban environment, it is discretized and at every iteration, the algorithm computes the best possible placing of the aerial robotic team members, subject to their camera model and the occlusions arising from the environment. As the parade route is only as well covered as its least-covered point, the optimization objective is to place the aerial robots such that they maximize the minimum coverage over the points in the route at every time instant of it. A set of simulation studies is used to demonstrate the operation and performance characteristics of the approach, while computational analysis is also provided and verifies the good scalability properties of the contributed algorithm regarding the size of the aerial robotics team.

  Click for Model/Code and Paper
On numerical approximation schemes for expectation propagation

Nov 14, 2016
Alexis Roche

Several numerical approximation strategies for the expectation-propagation algorithm are studied in the context of large-scale learning: the Laplace method, a faster variant of it, Gaussian quadrature, and a deterministic version of variational sampling (i.e., combining quadrature with variational approximation). Experiments in training linear binary classifiers show that the expectation-propagation algorithm converges best using variational sampling, while it also converges well using Laplace-style methods with smooth factors but tends to be unstable with non-differentiable ones. Gaussian quadrature yields unstable behavior or convergence to a sub-optimal solution in most experiments.

  Click for Model/Code and Paper
Performing Hybrid Recommendation in Intermodal Transportation-the FTMarket System's Recommendation Module

Sep 12, 2009
Alexis Lazanas

Diverse recommendation techniques have been already proposed and encapsulated into several e-business applications, aiming to perform a more accurate evaluation of the existing information and accordingly augment the assistance provided to the users involved. This paper reports on the development and integration of a recommendation module in an agent-based transportation transactions management system. The module is built according to a novel hybrid recommendation technique, which combines the advantages of collaborative filtering and knowledge-based approaches. The proposed technique and supporting module assist customers in considering in detail alternative transportation transactions that satisfy their requests, as well as in evaluating completed transactions. The related services are invoked through a software agent that constructs the appropriate knowledge rules and performs a synthesis of the recommendation policy.

* A. Lazanas"Performing Hybrid Recommendation in Intermodal Transportation-the FTMarket System's Recommendation Module ",International Journal of Computer Science Issues (IJCSI), Volume 3, pp24-34, August 2009 
* International Journal of Computer Science Issues (IJCSI), Volume 3, pp24-34, August 2009 

  Click for Model/Code and Paper
Combination of multiple Deep Learning architectures for Offensive Language Detection in Tweets

Mar 25, 2019
Nicolò Frisiani, Alexis Laignelet, Batuhan Güler

This report contains the details regarding our submission to the OffensEval 2019 (SemEval 2019 - Task 6). The competition was based on the Offensive Language Identification Dataset. We first discuss the details of the classifier implemented and the type of input data used and pre-processing performed. We then move onto critically evaluating our performance. We have achieved a macro-average F1-score of 0.76, 0.68, 0.54, respectively for Task a, Task b, and Task c, which we believe reflects on the level of sophistication of the models implemented. Finally, we will be discussing the difficulties encountered and possible improvements for the future.

  Click for Model/Code and Paper
Visual-Thermal Landmarks and Inertial Fusion for Navigation in Degraded Visual Environments

Mar 05, 2019
Shehryar Khattak, Christos Papachristos, Kostas Alexis

With an ever-widening domain of aerial robotic applications, including many mission critical tasks such as disaster response operations, search and rescue missions and infrastructure inspections taking place in GPS-denied environments, the need for reliable autonomous operation of aerial robots has become crucial. Operating in GPS-denied areas aerial robots rely on a multitude of sensors to localize and navigate. Visible spectrum cameras are the most commonly used sensors due to their low cost and weight. However, in environments that are visually-degraded such as in conditions of poor illumination, low texture, or presence of obscurants including fog, smoke and dust, the reliability of visible light cameras deteriorates significantly. Nevertheless, maintaining reliable robot navigation in such conditions is essential. In contrast to visible light cameras, thermal cameras offer visibility in the infrared spectrum and can be used in a complementary manner with visible spectrum cameras for robot localization and navigation tasks, without paying the significant weight and power penalty typically associated with carrying other sensors. Exploiting this fact, in this work we present a multi-sensor fusion algorithm for reliable odometry estimation in GPS-denied and degraded visual environments. The proposed method utilizes information from both the visible and thermal spectra for landmark selection and prioritizes feature extraction from informative image regions based on a metric over spatial entropy. Furthermore, inertial sensing cues are integrated to improve the robustness of the odometry estimation process. To verify our solution, a set of challenging experiments were conducted inside a) an obscurant filed machine shop-like industrial environment, as well as b) a dark subterranean mine in the presence of heavy airborne dust.

* 9 pages, 11 figures, Accepted at IEEE Aerospace Conference (AeroConf) 2019 

  Click for Model/Code and Paper
Are State-of-the-art Visual Place Recognition Techniques any Good for Aerial Robotics?

May 22, 2019
Mubariz Zaffar, Ahmad Khaliq, Shoaib Ehsan, Michael Milford, Kostas Alexis, Klaus McDonald-Maier

Visual Place Recognition (VPR) has seen significant advances at the frontiers of matching performance and computational superiority over the past few years. However, these evaluations are performed for ground-based mobile platforms and cannot be generalized to aerial platforms. The degree of viewpoint variation experienced by aerial robots is complex, with their processing power and on-board memory limited by payload size and battery ratings. Therefore, in this paper, we collect $8$ state-of-the-art VPR techniques that have been previously evaluated for ground-based platforms and compare them on $2$ recently proposed aerial place recognition datasets with three prime focuses: a) Matching performance b) Processing power consumption c) Projected memory requirements. This gives a birds-eye view of the applicability of contemporary VPR research to aerial robotics and lays down the the nature of challenges for aerial-VPR.

* IEEE ICRA 2019 Workshop on Aerial Robotics 8 pages, 7 figures 

  Click for Model/Code and Paper
Types for Parallel Complexity in the Pi-calculus

Oct 03, 2019
Patrick Baillot, Alexis Ghyselen

Type systems as a way to control or analyze programs have been largely studied in the context of functional programming languages. Some of those work allow to extract from a typing derivation for a program a complexity bound on this program. We present how to adapt this result for parallel complexity in the pi-calculus, as a model of concurrency and parallel communication. We study two notions of time complexity: the total computation time without parallelism (the work) and the computation time under maximal parallelism (the span). We define reduction relations in the pi-calculus to capture those two notions, and we present two type systems from which one can extract a complexity bound on a process. The type systems are inspired by input/output types and size types, with temporal information about communications.

  Click for Model/Code and Paper
Cross-lingual Language Model Pretraining

Jan 22, 2019
Guillaume Lample, Alexis Conneau

Recent studies have demonstrated the efficiency of generative pretraining for English natural language understanding. In this work, we extend this approach to multiple languages and show the effectiveness of cross-lingual pretraining. We propose two methods to learn cross-lingual language models (XLMs): one unsupervised that only relies on monolingual data, and one supervised that leverages parallel data with a new cross-lingual language model objective. We obtain state-of-the-art results on cross-lingual classification, unsupervised and supervised machine translation. On XNLI, our approach pushes the state of the art by an absolute gain of 4.9% accuracy. On unsupervised machine translation, we obtain 34.3 BLEU on WMT'16 German-English, improving the previous state of the art by more than 9 BLEU. On supervised machine translation, we obtain a new state of the art of 38.5 BLEU on WMT'16 Romanian-English, outperforming the previous best approach by more than 4 BLEU. Our code and pretrained models will be made publicly available.

  Click for Model/Code and Paper
Lévy Flight Foraging Hypothesis-based Autonomous Memoryless Search Under Sparse Rewards

Dec 12, 2018
Christos Papachristos, Kostas Alexis

Autonomous robots are commonly tasked with the problem of area exploration and search for certain targets or artifacts of interest to be tracked. Traditionally, the problem formulation considered is that of complete search and thus - ideally - identification of all targets of interest. An important problem however which is not often addressed is that of time-efficient memoryless search under sparse rewards that may be worth visited any number of items. In this paper we specifically address the largely understudied problem of optimizing the "time-of-arrival" or "time-of-detection" to robotically search for sparsely distributed rewards (detect targets of interest) within large-scale environments and subject to memoryless exploration. At the core of the proposed solution is the fact that a search-based L\'evy walk consisting of a constant velocity search following a L\'evy flight path is optimal for searching sparse and randomly distributed target regions in the lack of map memory. A set of results accompany the presentation of the method, demonstrate its properties and justify the purpose of its use towards large-scale area exploration autonomy.

* 5 pages, 9 figures, pre-submission 

  Click for Model/Code and Paper
Optical Flow Based Background Subtraction with a Moving Camera: Application to Autonomous Driving

Nov 16, 2018
Sotirios Diamantas, Kostas Alexis

In this research we present a novel algorithm for background subtraction using a moving camera. Our algorithm is based purely on visual information obtained from a camera mounted on an electric bus, operating in downtown Reno which automatically detects moving objects of interest with the view to provide a fully autonomous vehicle. In our approach we exploit the optical flow vectors generated by the motion of the camera while keeping parameter assumptions a minimum. At first, we estimate the Focus of Expansion, which is used to model and simulate 3D points given the intrinsic parameters of the camera, and perform multiple linear regression to estimate the regression equation parameters and implement on the real data set of every frame to identify moving objects. We validated our algorithm using data taken from a common bus route.

* 5 pages, 4 figures, presubmission 

  Click for Model/Code and Paper
Decision Variance in Online Learning

Jul 24, 2018
Sattar Vakili, Alexis Boukouvalas

Online learning has classically focused on the expected behaviour of learning policies. Recently, risk-averse online learning has gained much attention. In this paper, a risk-averse multi-armed bandit problem where the performance of policies is measured based on the mean-variance of the rewards is studied. The variance of the rewards depends on the variance of the underlying processes as well as the variance of the player's decisions. The performance of two existing policies is analyzed and new fundamental limitations on risk-averse learning is established. In particular, it is shown that although an $\mathcal{O}(\log T)$ distribution-dependent regret in time $T$ is achievable (similar to the risk-neutral setting), the worst-case (i.e. minimax) regret is lower bounded by $\Omega(T)$ (in contrast to the $\Omega(\sqrt{T})$ lower bound in the risk-neutral setting). The lower bound results are even stronger in the sense that they are proven for the case of online learning with full feedback.

  Click for Model/Code and Paper
SentEval: An Evaluation Toolkit for Universal Sentence Representations

Mar 14, 2018
Alexis Conneau, Douwe Kiela

We introduce SentEval, a toolkit for evaluating the quality of universal sentence representations. SentEval encompasses a variety of tasks, including binary and multi-class classification, natural language inference and sentence similarity. The set of tasks was selected based on what appears to be the community consensus regarding the appropriate evaluations for universal sentence representations. The toolkit comes with scripts to download and preprocess datasets, and an easy interface to evaluate sentence encoders. The aim is to provide a fairer, less cumbersome and more centralized way for evaluating sentence representations.

* LREC 2018 

  Click for Model/Code and Paper
Supervised feature evaluation by consistency analysis: application to measure sets used to characterise geographic objects

Apr 19, 2012
Patrick Taillandier, Alexis Drogoul

Nowadays, supervised learning is commonly used in many domains. Indeed, many works propose to learn new knowledge from examples that translate the expected behaviour of the considered system. A key issue of supervised learning concerns the description language used to represent the examples. In this paper, we propose a method to evaluate the feature set used to describe them. Our method is based on the computation of the consistency of the example base. We carried out a case study in the domain of geomatic in order to evaluate the sets of measures used to characterise geographic objects. The case study shows that our method allows to give relevant evaluations of measure sets.

* International Conference on Knowledge and Systems Engineering, Hanoi : Viet Nam (2010) 

  Click for Model/Code and Paper
Emerge-Sort: Converging to Ordered Sequences by Simple Local Operators

Mar 10, 2009
Dimitris Kalles, Alexis Kaporis

In this paper we examine sorting on the assumption that we do not know in advance which way to sort a sequence of numbers and we set at work simple local comparison and swap operators whose repeating application ends up in sorted sequences. These are the basic elements of Emerge-Sort, our approach to self-organizing sorting, which we then validate experimentally across a range of samples. Observing an O(n2) run-time behaviour, we note that the n/logn delay coefficient that differentiates Emerge-Sort from the classical comparison based algorithms is an instantiation of the price of anarchy we pay for not imposing a sorting order and for letting that order emerge through the local interactions.

* Contains 16 pages, 17 figures, 1 table. Text updated as of March 10, 2009. Submitted to a journal 

  Click for Model/Code and Paper