January 28, 2020

3155 words 15 mins read

Paper Group ANR 908

Wearable Sensor Data Based Human Activity Recognition using Machine Learning: A new approach. Privacy-Utility Trade-off of Linear Regression under Random Projections and Additive Noise. Milli-RIO: Ego-Motion Estimation with Millimetre-Wave Radar and Inertial Measurement Unit Sensor. Oriented Boxes for Accurate Instance Segmentation. Accelerating Mi …

Wearable Sensor Data Based Human Activity Recognition using Machine Learning: A new approach


Title	Wearable Sensor Data Based Human Activity Recognition using Machine Learning: A new approach
Authors	H. D. Nguyen, K. P. Tran, X. Zeng, L. Koehl, G. Tartare
Abstract	Recent years have witnessed the rapid development of human activity recognition (HAR) based on wearable sensor data. One can find many practical applications in this area, especially in the field of health care. Many machine learning algorithms such as Decision Trees, Support Vector Machine, Naive Bayes, K-Nearest Neighbor, and Multilayer Perceptron are successfully used in HAR. Although these methods are fast and easy for implementation, they still have some limitations due to poor performance in a number of situations. In this paper, we propose a novel method based on the ensemble learning to boost the performance of these machine learning methods for HAR.
Tasks	Activity Recognition, Human Activity Recognition
Published	2019-05-09
URL	https://arxiv.org/abs/1905.03809v1
PDF	https://arxiv.org/pdf/1905.03809v1.pdf
PWC	https://paperswithcode.com/paper/wearable-sensor-data-based-human-activity
Repo
Framework

Privacy-Utility Trade-off of Linear Regression under Random Projections and Additive Noise


Title	Privacy-Utility Trade-off of Linear Regression under Random Projections and Additive Noise
Authors	Mehrdad Showkatbakhsh, Can Karakus, Suhas Diggavi
Abstract	Data privacy is an important concern in machine learning, and is fundamentally at odds with the task of training useful learning models, which typically require the acquisition of large amounts of private user data. One possible way of fulfilling the machine learning task while preserving user privacy is to train the model on a transformed, noisy version of the data, which does not reveal the data itself directly to the training procedure. In this work, we analyze the privacy-utility trade-off of two such schemes for the problem of linear regression: additive noise, and random projections. In contrast to previous work, we consider a recently proposed notion of differential privacy that is based on conditional mutual information (MI-DP), which is stronger than the conventional $(\epsilon, \delta)$-differential privacy, and use relative objective error as the utility metric. We find that projecting the data to a lower-dimensional subspace before adding noise attains a better trade-off in general. We also make a connection between privacy problem and (non-coherent) SIMO, which has been extensively studied in wireless communication, and use tools from there for the analysis. We present numerical results demonstrating the performance of the schemes.
Tasks
Published	2019-02-13
URL	http://arxiv.org/abs/1902.04688v1
PDF	http://arxiv.org/pdf/1902.04688v1.pdf
PWC	https://paperswithcode.com/paper/privacy-utility-trade-off-of-linear
Repo
Framework

Milli-RIO: Ego-Motion Estimation with Millimetre-Wave Radar and Inertial Measurement Unit Sensor


Title	Milli-RIO: Ego-Motion Estimation with Millimetre-Wave Radar and Inertial Measurement Unit Sensor
Authors	Yasin Almalioglu, Mehmet Turan, Chris Xiaoxuan Lu, Niki Trigoni, Andrew Markham
Abstract	With the fast-growing demand of location-based services in various indoor environments, robust indoor ego-motion estimation has attracted significant interest in the last decades. Single-chip millimeter-wave (MMWave) radar as an emerging technology provides an alternative and complementary solution for robust ego-motion estimation. This paper introduces Milli-RIO, a MMWave radar based solution making use of a fixed beam antenna and inertial measurement unit sensor to calculate 6 degree-of-freedom pose of a moving radar. Detailed quantitative and qualitative evaluations prove that the proposed method achieves precisions on the order of few centimetres for indoor localization tasks.
Tasks	Motion Estimation, RF-based Pose Estimation
Published	2019-09-12
URL	https://arxiv.org/abs/1909.05774v1
PDF	https://arxiv.org/pdf/1909.05774v1.pdf
PWC	https://paperswithcode.com/paper/milli-rio-ego-motion-estimation-with
Repo
Framework

Oriented Boxes for Accurate Instance Segmentation


Title	Oriented Boxes for Accurate Instance Segmentation
Authors	Patrick Follmann, Rebecca König
Abstract	State-of-the-art instance-aware semantic segmentation algorithms use axis-aligned bounding boxes as an intermediate processing step to infer the final instance mask output. This often leads to coarse and inaccurate mask proposals due to the following reasons: Axis-aligned boxes have a high background to foreground pixel-ratio, there is a strong variation of mask targets with respect to the underlying box, and neighboring instances frequently reach into the axis-aligned bounding box of the instance mask of interest. In this work, we overcome these problems by proposing to use oriented boxes as the basis to infer instance masks. We show that oriented instance segmentation improves the mask predictions, especially when objects are diagonally aligned, touching, or overlapping each other. We evaluate our model on the D2S and Screws datasets and show that we can significantly improve the mask accuracy by 10% and 12% mAP compared to instance segmentation using axis-aligned bounding boxes, respectively. On the newly introduced Pill Bags dataset we outperform the baseline using only 10% of the mask annotations.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07732v3
PDF	https://arxiv.org/pdf/1911.07732v3.pdf
PWC	https://paperswithcode.com/paper/oriented-boxes-for-accurate-instance
Repo
Framework

Accelerating Min-Max Optimization with Application to Minimal Bounding Sphere


Title	Accelerating Min-Max Optimization with Application to Minimal Bounding Sphere
Authors	Hakan Gokcesu, Kaan Gokcesu, Suleyman Serdar Kozat
Abstract	We study the min-max optimization problem where each function contributing to the max operation is strongly-convex and smooth with bounded gradient in the search domain. By smoothing the max operator, we show the ability to achieve an arbitrarily small positive optimality gap of $\delta$ in $\tilde{O}(1/\sqrt{\delta})$ computational complexity (up to logarithmic factors) as opposed to the state-of-the-art strong-convexity computational requirement of $O(1/\delta)$. We apply this important result to the well-known minimal bounding sphere problem and demonstrate that we can achieve a $(1+\varepsilon)$-approximation of the minimal bounding sphere, i.e. identify an hypersphere enclosing a total of $n$ given points in the $d$ dimensional unbounded space $\mathbb{R}^d$ with a radius at most $(1+\varepsilon)$ times the actual minimal bounding sphere radius for an arbitrarily small positive $\varepsilon$, in $\tilde{O}(n d /\sqrt{\varepsilon})$ computational time as opposed to the state-of-the-art approach of core-set methodology, which needs $O(n d /\varepsilon)$ computational time.
Tasks
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12733v1
PDF	https://arxiv.org/pdf/1905.12733v1.pdf
PWC	https://paperswithcode.com/paper/accelerating-min-max-optimization-with
Repo
Framework

Search-Based Serving Architecture of Embeddings-Based Recommendations


Title	Search-Based Serving Architecture of Embeddings-Based Recommendations
Authors	Sonya Liberman, Shaked Bar, Raphael Vannerom, Danny Rosenstein, Ronny Lempel
Abstract	Over the past 10 years, many recommendation techniques have been based on embedding users and items in latent vector spaces, where the inner product of a (user,item) pair of vectors represents the predicted affinity of the user to the item. A wealth of literature has focused on the various modeling approaches that result in embeddings, and has compared their quality metrics, learning complexity, etc. However, much less attention has been devoted to the issues surrounding productization of an embeddings-based high throughput, low latency recommender system. In particular, how the system might keep up with the changing embeddings as new models are learnt. This paper describes a reference architecture of a high-throughput, large scale recommendation service which leverages a search engine as its runtime core. We describe how the search index and the query builder adapt to changes in the embeddings, which often happen at a different cadence than index builds. We provide solutions for both id-based and feature-based embeddings, as well as for batch indexing and incremental indexing setups. The described system is at the core of a Web content discovery service that serves tens of billions recommendations per day in response to billions of user requests.
Tasks	Recommendation Systems
Published	2019-07-07
URL	https://arxiv.org/abs/1907.03336v1
PDF	https://arxiv.org/pdf/1907.03336v1.pdf
PWC	https://paperswithcode.com/paper/search-based-serving-architecture-of
Repo
Framework

Human Activity Recognition Using LSTM-RNN Deep Neural Network Architecture


Title	Human Activity Recognition Using LSTM-RNN Deep Neural Network Architecture
Authors	Schalk Wilhelm Pienaar, Reza Malekian
Abstract	Using raw sensor data to model and train networks for Human Activity Recognition can be used in many different applications, from fitness tracking to safety monitoring applications. These models can be easily extended to be trained with different data sources for increased accuracies or an extension of classifications for different prediction classes. This paper goes into the discussion on the available dataset provided by WISDM and the unique features of each class for the different axes. Furthermore, the design of a Long Short Term Memory (LSTM) architecture model is outlined for the application of human activity recognition. An accuracy of above 94% and a loss of less than 30% has been reached in the first 500 epochs of training.
Tasks	Activity Recognition, Human Activity Recognition
Published	2019-05-02
URL	http://arxiv.org/abs/1905.00599v1
PDF	http://arxiv.org/pdf/1905.00599v1.pdf
PWC	https://paperswithcode.com/paper/human-activity-recognition-using-lstm-rnn
Repo
Framework

Computational model discovery with reinforcement learning


Title	Computational model discovery with reinforcement learning
Authors	Maxime Bassenne, Adrián Lozano-Durán
Abstract	The motivation of this study is to leverage recent breakthroughs in artificial intelligence research to unlock novel solutions to important scientific problems encountered in computational science. To address the human intelligence limitations in discovering reduced-order models, we propose to supplement human thinking with artificial intelligence. Our three-pronged strategy consists of learning (i) models expressed in analytical form, (ii) which are evaluated a posteriori, and iii) using exclusively integral quantities from the reference solution as prior knowledge. In point (i), we pursue interpretable models expressed symbolically as opposed to black-box neural networks, the latter only being used during learning to efficiently parameterize the large search space of possible models. In point (ii), learned models are dynamically evaluated a posteriori in the computational solver instead of based on a priori information from preprocessed high-fidelity data, thereby accounting for the specificity of the solver at hand such as its numerics. Finally in point (iii), the exploration of new models is solely guided by predefined integral quantities, e.g., averaged quantities of engineering interest in Reynolds-averaged or large-eddy simulations (LES). We use a coupled deep reinforcement learning framework and computational solver to concurrently achieve these objectives. The combination of reinforcement learning with objectives (i), (ii) and (iii) differentiate our work from previous modeling attempts based on machine learning. In this report, we provide a high-level description of the model discovery framework with reinforcement learning. The method is detailed for the application of discovering missing terms in differential equations. An elementary instantiation of the method is described that discovers missing terms in the Burgers’ equation.
Tasks
Published	2019-12-29
URL	https://arxiv.org/abs/2001.00008v1
PDF	https://arxiv.org/pdf/2001.00008v1.pdf
PWC	https://paperswithcode.com/paper/computational-model-discovery-with
Repo
Framework


Title	Graph Neural Networks for Human-aware Social Navigation
Authors	Luis J. Manso, Ronit R. Jorvekar, Diego R. Faria, Pablo Bustos, Pilar Bachiller
Abstract	Autonomous navigation is a key skill for assistive and service robots. To be successful, robots have to navigate avoiding going through the personal spaces of the people surrounding them. Complying with social rules such as not getting in the middle of human-to-human and human-to-object interactions is also important. This paper suggests using Graph Neural Networks to model how inconvenient the presence of a robot would be in a particular scenario according to learned human conventions so that it can be used by path planning algorithms. To do so, we propose two ways of modelling social interactions using graphs and benchmark them with different Graph Neural Networks using the SocNav1 dataset. We achieve close-to-human performance in the dataset and argue that, in addition to promising results, the main advantage of the approach is its scalability in terms of the number of social factors that can be considered and easily embedded in code, in comparison with model-based approaches. The code used to train and test the resulting graph neural network is available in a public repository.
Tasks	Autonomous Navigation
Published	2019-09-19
URL	https://arxiv.org/abs/1909.09003v2
PDF	https://arxiv.org/pdf/1909.09003v2.pdf
PWC	https://paperswithcode.com/paper/graph-neural-networks-for-human-aware-social
Repo
Framework

Multi-user Resource Control with Deep Reinforcement Learning in IoT Edge Computing


Title	Multi-user Resource Control with Deep Reinforcement Learning in IoT Edge Computing
Authors	Lei Lei, Huijuan Xu, Xiong Xiong, Kan Zheng, Wei Xiang, Xianbin Wang
Abstract	By leveraging the concept of mobile edge computing (MEC), massive amount of data generated by a large number of Internet of Things (IoT) devices could be offloaded to MEC server at the edge of wireless network for further computational intensive processing. However, due to the resource constraint of IoT devices and wireless network, both the communications and computation resources need to be allocated and scheduled efficiently for better system performance. In this paper, we propose a joint computation offloading and multi-user scheduling algorithm for IoT edge computing system to minimize the long-term average weighted sum of delay and power consumption under stochastic traffic arrival. We formulate the dynamic optimization problem as an infinite-horizon average-reward continuous-time Markov decision process (CTMDP) model. One critical challenge in solving this MDP problem for the multi-user resource control is the curse-of-dimensionality problem, where the state space of the MDP model and the computation complexity increase exponentially with the growing number of users or IoT devices. In order to overcome this challenge, we use the deep reinforcement learning (RL) techniques and propose a neural network architecture to approximate the value functions for the post-decision system states. The designed algorithm to solve the CTMDP problem supports semi-distributed auction-based implementation, where the IoT devices submit bids to the BS to make the resource control decisions centrally. Simulation results show that the proposed algorithm provides significant performance improvement over the baseline algorithms, and also outperforms the RL algorithms based on other neural network architectures.
Tasks
Published	2019-06-19
URL	https://arxiv.org/abs/1906.07860v1
PDF	https://arxiv.org/pdf/1906.07860v1.pdf
PWC	https://paperswithcode.com/paper/multi-user-resource-control-with-deep
Repo
Framework

Explaining Away Results in Accurate and Tolerant Template Matching


Title	Explaining Away Results in Accurate and Tolerant Template Matching
Authors	M. W. Spratling
Abstract	Recognising and locating image patches or sets of image features is an important task underlying much work in computer vision. Traditionally this has been accomplished using template matching. However, template matching is notoriously brittle in the face of changes in appearance caused by, for example, variations in viewpoint, partial occlusion, and non-rigid deformations. This article tests a method of template matching that is more tolerant to such changes in appearance and that can, therefore, more accurately identify image patches. In traditional template matching the comparison between a template and the image is independent of the other templates. In contrast, the method advocated here takes into account the evidence provided by the image for the template at each location and the full range of alternative explanations represented by the same template at other locations and by other templates. Specifically, the proposed method of template matching is performed using a form of probabilistic inference known as “explaining away”. The algorithm used to implement explaining away has previously been used to simulate several neurobiological mechanisms, and been applied to image contour detection and pattern recognition tasks. Here it is applied for the first time to image patch matching, and is shown to produce superior results in comparison to the current state-of-the-art methods.
Tasks	Contour Detection
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04169v1
PDF	https://arxiv.org/pdf/1911.04169v1.pdf
PWC	https://paperswithcode.com/paper/explaining-away-results-in-accurate-and
Repo
Framework

SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals


Title	SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals
Authors	Iris Hendrickx, Su Nam Kim, Zornitsa Kozareva, Preslav Nakov, Diarmuid Ó Séaghdha, Sebastian Padó, Marco Pennacchiotti, Lorenza Romano, Stan Szpakowicz
Abstract	In response to the continuing research interest in computational semantic analysis, we have proposed a new task for SemEval-2010: multi-way classification of mutually exclusive semantic relations between pairs of nominals. The task is designed to compare different approaches to the problem and to provide a standard testbed for future research. In this paper, we define the task, describe the creation of the datasets, and discuss the results of the participating 28 systems submitted by 10 teams.
Tasks
Published	2019-11-23
URL	https://arxiv.org/abs/1911.10422v1
PDF	https://arxiv.org/pdf/1911.10422v1.pdf
PWC	https://paperswithcode.com/paper/semeval-2010-task-8-multi-way-classification
Repo
Framework

GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences


Title	GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences
Authors	Prune Truong, Martin Danelljan, Radu Timofte
Abstract	Establishing dense correspondences between a pair of images is an important and general problem, covering geometric matching, optical flow and semantic correspondences. While these applications share fundamental challenges, such as large displacements, pixel-accuracy, and appearance changes, they are currently addressed with specialized network architectures, designed for only one particular task. This severely limits the generalization capabilities of such networks to new scenarios, where e.g. robustness to larger displacements or higher accuracy is required. In this work, we propose a universal network architecture that is directly applicable to all the aforementioned dense correspondence problems. We achieve both high accuracy and robustness to large displacements by investigating the combined use of global and local correlation layers. We further propose an adaptive resolution strategy, allowing our network to operate on virtually any input image resolution. The proposed GLU-Net achieves state-of-the-art performance for geometric and semantic matching as well as optical flow, when using the same network and weights. Code and trained models are available at https://github.com/PruneTruong/GLU-Net.
Tasks	Optical Flow Estimation
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05524v2
PDF	https://arxiv.org/pdf/1912.05524v2.pdf
PWC	https://paperswithcode.com/paper/glu-net-global-local-universal-network-for
Repo
Framework

Distilling Pixel-Wise Feature Similarities for Semantic Segmentation


Title	Distilling Pixel-Wise Feature Similarities for Semantic Segmentation
Authors	Yuhu Shan
Abstract	Among the neural network compression techniques, knowledge distillation is an effective one which forces a simpler student network to mimic the output of a larger teacher network. However, most of such model distillation methods focus on the image-level classification task. Directly adapting these methods to the task of semantic segmentation only brings marginal improvements. In this paper, we propose a simple, yet effective knowledge representation referred to as pixel-wise feature similarities (PFS) to tackle the challenging distillation problem of semantic segmentation. The developed PFS encodes spatial structural information for each pixel location of the high-level convolutional features, which helps guide the distillation process in an easier way. Furthermore, a novel weighted pixel-level soft prediction imitation approach is proposed to enable the student network to selectively mimic the teacher network’s output, according to their pixel-wise knowledge-gaps. Extensive experiments are conducted on the challenging datasets of Pascal VOC 2012, ADE20K and Pascal Context. Our approach brings significant performance improvements compared to several strong baselines and achieves new state-of-the-art results.
Tasks	Neural Network Compression, Semantic Segmentation
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14226v1
PDF	https://arxiv.org/pdf/1910.14226v1.pdf
PWC	https://paperswithcode.com/paper/distilling-pixel-wise-feature-similarities
Repo
Framework

A Novel Privacy-Preserving Deep Learning Scheme without Using Cryptography Component


Title	A Novel Privacy-Preserving Deep Learning Scheme without Using Cryptography Component
Authors	Chin-Yu Sun, Allen C. -H. Wu, TingTing Hwang
Abstract	Recently, deep learning, which uses Deep Neural Networks (DNN), plays an important role in many fields. A secure neural network model with a secure training/inference scheme is indispensable to many applications. To accomplish such a task usually needs one of the entities (the customer or the service provider) to provide private information (customer’s data or the model) to the other. Without a secure scheme and the mutual trust between the service providers and their customers, it will be an impossible mission. In this paper, we propose a novel privacy-preserving deep learning model and a secure training/inference scheme to protect the input, the output, and the model in the application of the neural network. We utilize the innate properties of a deep neural network to design a secure mechanism without using any complicated cryptography component. The security analysis shows our proposed scheme is secure and the experimental results also demonstrate that our method is very efficient and suitable for real applications.
Tasks	Privacy Preserving Deep Learning
Published	2019-08-21
URL	https://arxiv.org/abs/1908.07701v1
PDF	https://arxiv.org/pdf/1908.07701v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-privacy-preserving-deep-learning
Repo
Framework