Paper Group ANR 451
Benchmarking time series classification – Functional data vs machine learning approaches. Open Problem: The Oracle Complexity of Convex Optimization with Limited Memory. Scale-dependent Relationships in Natural Language. Anthropometric clothing measurements from 3D body scans. A flexible integer linear programming formulation for scheduling clinic …
Benchmarking time series classification – Functional data vs machine learning approaches
| Title | Benchmarking time series classification – Functional data vs machine learning approaches |
| Authors | Florian Pfisterer, Laura Beggel, Xudong Sun, Fabian Scheipl, Bernd Bischl |
| Abstract | Time series classification problems have drawn increasing attention in the machine learning and statistical community. Closely related is the field of functional data analysis (FDA): it refers to the range of problems that deal with the analysis of data that is continuously indexed over some domain. While often employing different methods, both fields strive to answer similar questions, a common example being classification or regression problems with functional covariates. We study methods from functional data analysis, such as functional generalized additive models, as well as functionality to concatenate (functional-) feature extraction or basis representations with traditional machine learning algorithms like support vector machines or classification trees. In order to assess the methods and implementations, we run a benchmark on a wide variety of representative (time series) data sets, with in-depth analysis of empirical results, and strive to provide a reference ranking for which method(s) to use for non-expert practitioners. Additionally, we provide a software framework in R for functional data analysis for supervised learning, including machine learning and more linear approaches from statistics. This allows convenient access, and in connection with the machine-learning toolbox mlr, those methods can now also be tuned and benchmarked. |
| Tasks | Time Series, Time Series Classification |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07511v1 |
| https://arxiv.org/pdf/1911.07511v1.pdf | |
| PWC | https://paperswithcode.com/paper/benchmarking-time-series-classification |
| Repo | |
| Framework | |
Open Problem: The Oracle Complexity of Convex Optimization with Limited Memory
| Title | Open Problem: The Oracle Complexity of Convex Optimization with Limited Memory |
| Authors | Blake Woodworth, Nathan Srebro |
| Abstract | We note that known methods achieving the optimal oracle complexity for first order convex optimization require quadratic memory, and ask whether this is necessary, and more broadly seek to characterize the minimax number of first order queries required to optimize a convex Lipschitz function subject to a memory constraint. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.00762v1 |
| https://arxiv.org/pdf/1907.00762v1.pdf | |
| PWC | https://paperswithcode.com/paper/open-problem-the-oracle-complexity-of-convex |
| Repo | |
| Framework | |
Scale-dependent Relationships in Natural Language
| Title | Scale-dependent Relationships in Natural Language |
| Authors | Aakash Sarkar, Marc Howard |
| Abstract | Natural language exhibits statistical dependencies at a wide range of scales. For instance, the mutual information between words in natural language decays like a power law with the temporal lag between them. However, many statistical learning models applied to language impose a sampling scale while extracting statistical structure. For instance, Word2Vec constructs a vector embedding that maximizes the prediction between a target word and the context words that appear nearby in the corpus. The size of the context is chosen by the user and defines a strong scale; relationships over much larger temporal scales would be invisible to the algorithm. This paper examines the family of Word2Vec embeddings generated while systematically manipulating the sampling scale used to define the context around each word. The primary result is that different linguistic relationships are preferentially encoded at different scales. Different scales emphasize different syntactic and semantic relations between words.Moreover, the neighborhoods of a given word in the embeddings change significantly depending on the scale. These results suggest that any individual scale can only identify a subset of the meaningful relationships a word might have, and point toward the importance of developing scale-free models of semantic meaning. |
| Tasks | |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07506v1 |
| https://arxiv.org/pdf/1912.07506v1.pdf | |
| PWC | https://paperswithcode.com/paper/scale-dependent-relationships-in-natural |
| Repo | |
| Framework | |
Anthropometric clothing measurements from 3D body scans
| Title | Anthropometric clothing measurements from 3D body scans |
| Authors | Song Yan, Johan Wirta, Joni-Kristian Kämäräinen |
| Abstract | We propose a full processing pipeline to acquire anthropometric measurements from 3D measurements. The first stage of our pipeline is a commercial point cloud scanner. In the second stage, a pre-defined body model is fitted to the captured point cloud. We have generated one male and one female model from the SMPL library. The fitting process is based on non-rigid Iterative Closest Point (ICP) algorithm that minimizes overall energy of point distance and local stiffness energy terms. In the third stage, we measure multiple circumference paths on the fitted model surface and use a non-linear regressor to provide the final estimates of anthropometric measurements. We scanned 194 male and 181 female subjects and the proposed pipeline provides mean absolute errors from 2.5 mm to 16.0 mm depending on the anthropometric measurement. |
| Tasks | |
| Published | 2019-11-02 |
| URL | https://arxiv.org/abs/1911.00694v1 |
| https://arxiv.org/pdf/1911.00694v1.pdf | |
| PWC | https://paperswithcode.com/paper/anthropometric-clothing-measurements-from-3d |
| Repo | |
| Framework | |
A flexible integer linear programming formulation for scheduling clinician on-call service in hospitals
| Title | A flexible integer linear programming formulation for scheduling clinician on-call service in hospitals |
| Authors | David Landsman, Huiting Ma, Jesse Knight, Kevin Gough, Sharmistha Mishra |
| Abstract | Scheduling of personnel in a hospital environment is vital to improving the service provided to patients and balancing the workload assigned to clinicians. Many approaches have been tried and successfully applied to generate efficient schedules in such settings. However, due to the computational complexity of the scheduling problem in general, most approaches resort to heuristics to find a non-optimal solution in a reasonable amount of time. We designed an integer linear programming formulation to find an optimal schedule in a clinical division of a hospital. Our formulation mitigates issues related to computational complexity by minimizing the set of constraints, yet retains sufficient flexibility so that it can be adapted to a variety of clinical divisions. We then conducted a case study for our approach using data from the Infectious Diseases division at St. Michael’s Hospital in Toronto, Canada. We analyzed and compared the results of our approach to manually-created schedules at the hospital, and found improved adherence to departmental constraints and clinician preferences. We used simulated data to examine the sensitivity of the runtime of our linear program for various parameters and observed reassuring results, signifying the practicality and generalizability of our approach in different real-world scenarios. |
| Tasks | |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08526v1 |
| https://arxiv.org/pdf/1910.08526v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-flexible-integer-linear-programming |
| Repo | |
| Framework | |
Generalized Feedback Loop for Joint Hand-Object Pose Estimation
| Title | Generalized Feedback Loop for Joint Hand-Object Pose Estimation |
| Authors | Markus Oberweger, Paul Wohlhart, Vincent Lepetit |
| Abstract | We propose an approach to estimating the 3D pose of a hand, possibly handling an object, given a depth image. We show that we can correct the mistakes made by a Convolutional Neural Network trained to predict an estimate of the 3D pose by using a feedback loop. The components of this feedback loop are also Deep Networks, optimized using training data. This approach can be generalized to a hand interacting with an object. Therefore, we jointly estimate the 3D pose of the hand and the 3D pose of the object. Our approach performs en-par with state-of-the-art methods for 3D hand pose estimation, and outperforms state-of-the-art methods for joint hand-object pose estimation when using depth images only. Also, our approach is efficient as our implementation runs in real-time on a single GPU. |
| Tasks | Hand Pose Estimation, Pose Estimation |
| Published | 2019-03-25 |
| URL | http://arxiv.org/abs/1903.10883v1 |
| http://arxiv.org/pdf/1903.10883v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-feedback-loop-for-joint-hand |
| Repo | |
| Framework | |
Information-Theoretic Registration with Explicit Reorientation of Diffusion-Weighted Images
| Title | Information-Theoretic Registration with Explicit Reorientation of Diffusion-Weighted Images |
| Authors | Henrik Grønholt Jensen, François Lauze, Sune Darkner |
| Abstract | We present an information-theoretic approach to registration of DWI with explicit optimization over the orientational scale, with an additional focus on normalized mutual information as a robust information-theoretic similarity measure for DWI. The framework is an extension of the LOR-DWI density-based hierarchical scale-space model, that varies and optimizes over the integration, spatial, directional, and intensity scales. We extend the model to non-rigid deformations and show that the formulation provides intrinsic regularization through the orientational information. Our experiments illustrate that the proposed model deforms ODFs correctly and is capable of handling the classic complex challenges in DWI-registrations, such as the registration of fiber-crossings along with kissing, fanning and interleaving fibers. Our results clearly illustrate a novel promising regularizing effect, that comes from the nonlinear orientation-based cost function. We illustrate the properties of the different image scales, and show that including orientational information in our model make the model better at retrieving deformations compared to standard scalar-based registration. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.12056v2 |
| https://arxiv.org/pdf/1905.12056v2.pdf | |
| PWC | https://paperswithcode.com/paper/information-theoretic-registration-with |
| Repo | |
| Framework | |
Content-based image retrieval using Mix histogram
| Title | Content-based image retrieval using Mix histogram |
| Authors | Mohammad Rezaei, Ali Ahmadi, Navid Naderi |
| Abstract | This paper presents a new method to extract image low-level features, namely mix histogram (MH), for content-based image retrieval. Since color and edge orientation features are important visual information which help the human visual system percept and discriminate different images, this method extracts and integrates color and edge orientation information in order to measure similarity between different images. Traditional color histograms merely focus on the global distribution of color in the image and therefore fail to extract other visual features. The MH is attempting to overcome this problem by extracting edge orientations as well as color feature. The unique characteristic of the MH is that it takes into consideration both color and edge orientation information in an effective manner. Experimental results show that it outperforms many existing methods which were originally developed for image retrieval purposes. |
| Tasks | Content-Based Image Retrieval, Image Retrieval |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09722v1 |
| https://arxiv.org/pdf/1909.09722v1.pdf | |
| PWC | https://paperswithcode.com/paper/190909722 |
| Repo | |
| Framework | |
Natural-Logarithm-Rectified Activation Function in Convolutional Neural Networks
| Title | Natural-Logarithm-Rectified Activation Function in Convolutional Neural Networks |
| Authors | Yang Liu, Jianpeng Zhang, Chao Gao, Jinghua Qu, Lixin Ji |
| Abstract | Activation functions play a key role in providing remarkable performance in deep neural networks, and the rectified linear unit (ReLU) is one of the most widely used activation functions. Various new activation functions and improvements on ReLU have been proposed, but each carry performance drawbacks. In this paper, we propose an improved activation function, which we name the natural-logarithm-rectified linear unit (NLReLU). This activation function uses the parametric natural logarithmic transform to improve ReLU and is simply defined as. NLReLU not only retains the sparse activation characteristic of ReLU, but it also alleviates the “dying ReLU” and vanishing gradient problems to some extent. It also reduces the bias shift effect and heteroscedasticity of neuron data distributions among network layers in order to accelerate the learning process. The proposed method was verified across ten convolutional neural networks with different depths for two essential datasets. Experiments illustrate that convolutional neural networks with NLReLU exhibit higher accuracy than those with ReLU, and that NLReLU is comparable to other well-known activation functions. NLReLU provides 0.16% and 2.04% higher classification accuracy on average compared to ReLU when used in shallow convolutional neural networks with the MNIST and CIFAR-10 datasets, respectively. The average accuracy of deep convolutional neural networks with NLReLU is 1.35% higher on average with the CIFAR-10 dataset. |
| Tasks | |
| Published | 2019-08-10 |
| URL | https://arxiv.org/abs/1908.03682v2 |
| https://arxiv.org/pdf/1908.03682v2.pdf | |
| PWC | https://paperswithcode.com/paper/natural-logarithm-rectified-activation |
| Repo | |
| Framework | |
Comparison of UNet, ENet, and BoxENet for Segmentation of Mast Cells in Scans of Histological Slices
| Title | Comparison of UNet, ENet, and BoxENet for Segmentation of Mast Cells in Scans of Histological Slices |
| Authors | Alexander Karimov, Artem Razumov, Ruslana Manbatchurina, Ksenia Simonova, Irina Donets, Anastasia Vlasova, Yulia Khramtsova, Konstantin Ushenin |
| Abstract | Deep neural networks show high accuracy in theproblem of semantic and instance segmentation of biomedicaldata. However, this approach is computationally expensive. Thecomputational cost may be reduced with network simplificationafter training or choosing the proper architecture, which providessegmentation with less accuracy but does it much faster. In thepresent study, we analyzed the accuracy and performance ofUNet and ENet architectures for the problem of semantic imagesegmentation. In addition, we investigated the ENet architecture by replacing of some convolution layers with box-convolutionlayers. The analysis performed on the original dataset consisted of histology slices with mast cells. These cells provide a region forsegmentation with different types of borders, which vary fromclearly visible to ragged. ENet was less accurate than UNet byonly about 1-2%, but ENet performance was 8-15 times faster than UNet one. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2019-09-15 |
| URL | https://arxiv.org/abs/1909.06840v3 |
| https://arxiv.org/pdf/1909.06840v3.pdf | |
| PWC | https://paperswithcode.com/paper/comparison-of-unet-enet-and-boxenet-for |
| Repo | |
| Framework | |
Confidence Intervals for Selected Parameters
| Title | Confidence Intervals for Selected Parameters |
| Authors | Yoav Benjamini, Yotam Hechtlinger, Philip B. Stark |
| Abstract | Practical or scientific considerations often lead to selecting a subset of parameters as important.'' Inferences about those parameters often are based on the same data used to select them in the first place. That can make the reported uncertainties deceptively optimistic: confidence intervals that ignore selection generally have less than their nominal coverage probability. Controlling the probability that one or more intervals for selected parameters do not cover---the simultaneous over the selected’’ (SoS) error rate—is crucial in many scientific problems. Intervals that control the SoS error rate can be constructed in ways that take advantage of knowledge of the selection rule. We construct SoS-controlling confidence intervals for parameters deemed the most ``important’’ $k$ of $m$ shift parameters because they are estimated (by independent estimators) to be the largest. The new intervals improve substantially over \v{S}id'{a}k intervals when $k$ is small compared to $m$, and approach the standard Bonferroni-corrected intervals when $k \approx m$. Standard, unadjusted confidence intervals for location parameters have the correct coverage probability for $k=1$, $m=2$ if, when the true parameters are zero, the estimators are exchangeable and symmetric. | |
| Tasks | |
| Published | 2019-06-02 |
| URL | https://arxiv.org/abs/1906.00505v1 |
| https://arxiv.org/pdf/1906.00505v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600505 |
| Repo | |
| Framework | |
Online Event Recognition from Moving Vehicles: Application Paper
| Title | Online Event Recognition from Moving Vehicles: Application Paper |
| Authors | Efthimis Tsilionis, Nikolaos Koutroumanis, Panagiotis Nikitopoulos, Christos Doulkeridis, Alexander Artikis |
| Abstract | We present a system for online composite event recognition over streaming positions of commercial vehicles. Our system employs a data enrichment module, augmenting the mobility data with external information, such as weather data and proximity to points of interest. In addition, the composite event recognition module, based on a highly optimised logic programming implementation of the Event Calculus, consumes the enriched data and identifies activities that are beneficial in fleet management applications. We evaluate our system on large, real-world data from commercial vehicles, and illustrate its efficiency. Under consideration for acceptance in TPLP. |
| Tasks | |
| Published | 2019-07-25 |
| URL | https://arxiv.org/abs/1907.11007v1 |
| https://arxiv.org/pdf/1907.11007v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-event-recognition-from-moving-vehicles |
| Repo | |
| Framework | |
Deep-Sentiment: Sentiment Analysis Using Ensemble of CNN and Bi-LSTM Models
| Title | Deep-Sentiment: Sentiment Analysis Using Ensemble of CNN and Bi-LSTM Models |
| Authors | Shervin Minaee, Elham Azimi, AmirAli Abdolrashidi |
| Abstract | With the popularity of social networks, and e-commerce websites, sentiment analysis has become a more active area of research in the past few years. On a high level, sentiment analysis tries to understand the public opinion about a specific product or topic, or trends from reviews or tweets. Sentiment analysis plays an important role in better understanding customer/user opinion, and also extracting social/political trends. There has been a lot of previous works for sentiment analysis, some based on hand-engineering relevant textual features, and others based on different neural network architectures. In this work, we present a model based on an ensemble of long-short-term-memory (LSTM), and convolutional neural network (CNN), one to capture the temporal information of the data, and the other one to extract the local structure thereof. Through experimental results, we show that using this ensemble model we can outperform both individual models. We are also able to achieve a very high accuracy rate compared to the previous works. |
| Tasks | Sentiment Analysis |
| Published | 2019-04-08 |
| URL | http://arxiv.org/abs/1904.04206v1 |
| http://arxiv.org/pdf/1904.04206v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-sentiment-sentiment-analysis-using |
| Repo | |
| Framework | |
Model-Free Reinforcement Learning for Financial Portfolios: A Brief Survey
| Title | Model-Free Reinforcement Learning for Financial Portfolios: A Brief Survey |
| Authors | Yoshiharu Sato |
| Abstract | Financial portfolio management is one of the problems that are most frequently encountered in the investment industry. Nevertheless, it is not widely recognized that both Kelly Criterion and Risk Parity collapse into Mean Variance under some conditions, which implies that a universal solution to the portfolio optimization problem could potentially exist. In fact, the process of sequential computation of optimal component weights that maximize the portfolio’s expected return subject to a certain risk budget can be reformulated as a discrete-time Markov Decision Process (MDP) and hence as a stochastic optimal control, where the system being controlled is a portfolio consisting of multiple investment components, and the control is its component weights. Consequently, the problem could be solved using model-free Reinforcement Learning (RL) without knowing specific component dynamics. By examining existing methods of both value-based and policy-based model-free RL for the portfolio optimization problem, we identify some of the key unresolved questions and difficulties facing today’s portfolio managers of applying model-free RL to their investment portfolios. |
| Tasks | Portfolio Optimization |
| Published | 2019-04-10 |
| URL | https://arxiv.org/abs/1904.04973v2 |
| https://arxiv.org/pdf/1904.04973v2.pdf | |
| PWC | https://paperswithcode.com/paper/model-free-reinforcement-learning-for |
| Repo | |
| Framework | |
Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation
| Title | Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation |
| Authors | Ziheng Zhang, Anpei Chen, Ling Xie, Jingyi Yu, Shenghua Gao |
| Abstract | In this work, we demonstrate yet another approach to tackle the amodal segmentation problem. Specifically, we first introduce a new representation, namely a semantics-aware distance map (sem-dist map), to serve as our target for amodal segmentation instead of the commonly used masks and heatmaps. The sem-dist map is a kind of level-set representation, of which the different regions of an object are placed into different levels on the map according to their visibility. It is a natural extension of masks and heatmaps, where modal, amodal segmentation, as well as depth order information, are all well-described. Then we also introduce a novel convolutional neural network (CNN) architecture, which we refer to as semantic layering network, to estimate sem-dist maps layer by layer, from the global-level to the instance-level, for all objects in an image. Extensive experiments on the COCOA and D2SA datasets have demonstrated that our framework can predict amodal segmentation, occlusion and depth order with state-of-the-art performance. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.12898v2 |
| https://arxiv.org/pdf/1905.12898v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-semantics-aware-distance-map-with |
| Repo | |
| Framework | |
