January 25, 2020

3171 words 15 mins read

Paper Group ANR 1626

Weightless Neural Network with Transfer Learning to Detect Distress in Asphalt. A Distributed Approach to LARS Stream Reasoning (System paper). Recommending research articles to consumers of online vaccination information. Discovery of Important Subsequences in Electrocardiogram Beats Using the Nearest Neighbour Algorithm. Multi-Vehicle Mixed-Reali …

Weightless Neural Network with Transfer Learning to Detect Distress in Asphalt


Title	Weightless Neural Network with Transfer Learning to Detect Distress in Asphalt
Authors	Suayder Milhomem, Tiago da Silva Almeida, Warley Gramacho da Silva, Edeilson Milhomem da Silva, Rafael Lima de Carvalho
Abstract	The present paper shows a solution to the problem of automatic distress detection, more precisely the detection of holes in paved roads. To do so, the proposed solution uses a weightless neural network known as Wisard to decide whether an image of a road has any kind of cracks. In addition, the proposed architecture also shows how the use of transfer learning was able to improve the overall accuracy of the decision system. As a verification step of the research, an experiment was carried out using images from the streets at the Federal University of Tocantins, Brazil. The architecture of the developed solution presents a result of 85.71% accuracy in the dataset, proving to be superior to approaches of the state-of-the-art.
Tasks	Transfer Learning
Published	2019-01-03
URL	http://arxiv.org/abs/1901.03660v1
PDF	http://arxiv.org/pdf/1901.03660v1.pdf
PWC	https://paperswithcode.com/paper/weightless-neural-network-with-transfer
Repo
Framework

A Distributed Approach to LARS Stream Reasoning (System paper)


Title	A Distributed Approach to LARS Stream Reasoning (System paper)
Authors	Thomas Eiter, Paul Ogris, Konstantin Schekotihin
Abstract	Stream reasoning systems are designed for complex decision-making from possibly infinite, dynamic streams of data. Modern approaches to stream reasoning are usually performing their computations using stand-alone solvers, which incrementally update their internal state and return results as the new portions of data streams are pushed. However, the performance of such approaches degrades quickly as the rates of the input data and the complexity of decision problems are growing. This problem was already recognized in the area of stream processing, where systems became distributed in order to allocate vast computing resources provided by clouds. In this paper we propose a distributed approach to stream reasoning that can efficiently split computations among different solvers communicating their results over data streams. Moreover, in order to increase the throughput of the distributed system, we suggest an interval-based semantics for the LARS language, which enables significant reductions of network traffic. Performed evaluations indicate that the distributed stream reasoning significantly outperforms existing stand-alone LARS solvers when the complexity of decision problems and the rate of incoming data are increasing. Under consideration for acceptance in Theory and Practice of Logic Programming.
Tasks	Decision Making
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12344v1
PDF	https://arxiv.org/pdf/1907.12344v1.pdf
PWC	https://paperswithcode.com/paper/a-distributed-approach-to-lars-stream
Repo
Framework

Recommending research articles to consumers of online vaccination information


Title	Recommending research articles to consumers of online vaccination information
Authors	Eliza Harrison, Paige Martin, Didi Surian, Adam G. Dunn
Abstract	Research communications often introduce biases or misrepresentations without providing reliable links to the research they use so readers can check the veracity of the claims being made. We tested the feasibility of a tool that can be used to automatically recommend research articles to research communications. From 207,538 vaccination-related PubMed articles, we selected 3,573 unique links to webpages using Altmetric. We tested a method for ranking research articles relative to each webpage using a canonical correlation analysis (CCA) approach. Outcome measures were the median rank of the correct source article; the percentage of webpages for which the source article was correctly ranked first; and the percentage ranked within the top 50 candidate articles. The best of the baseline approaches ranked the matching source article first for more a quarter of webpages; and within the top 50 for more than half. Augmenting baseline methods with CCA improved results but failed when added to some of the baseline approaches. The best CCA-based approach ranked the matching source articles first for 14%; and in the top 50 for 38%. Tools to help people identify source articles for vaccination-related research communications are potentially feasible and may support the prevention of bias and misrepresentation of research in news and social media.
Tasks
Published	2019-04-26
URL	http://arxiv.org/abs/1904.11886v1
PDF	http://arxiv.org/pdf/1904.11886v1.pdf
PWC	https://paperswithcode.com/paper/recommending-research-articles-to-consumers
Repo
Framework

Discovery of Important Subsequences in Electrocardiogram Beats Using the Nearest Neighbour Algorithm


Title	Discovery of Important Subsequences in Electrocardiogram Beats Using the Nearest Neighbour Algorithm
Authors	Ricards Marcinkevics, Steven Kelk, Carlo Galuzzi, Berthold Stegemann
Abstract	The classification of time series data is a well-studied problem with numerous practical applications, such as medical diagnosis and speech recognition. A popular and effective approach is to classify new time series in the same way as their nearest neighbours, whereby proximity is defined using Dynamic Time Warping (DTW) distance, a measure analogous to sequence alignment in bioinformatics. However, practitioners are not only interested in accurate classification, they are also interested in why a time series is classified a certain way. To this end, we introduce here the problem of finding a minimum length subsequence of a time series, the removal of which changes the outcome of the classification under the nearest neighbour algorithm with DTW distance. Informally, such a subsequence is expected to be relevant for the classification and can be helpful for practitioners in interpreting the outcome. We describe a simple but optimized implementation for detecting these subsequences and define an accompanying measure to quantify the relevance of every time point in the time series for the classification. In tests on electrocardiogram data we show that the algorithm allows discovery of important subsequences and can be helpful in detecting abnormalities in cardiac rhythms distinguishing sick from healthy patients.
Tasks	Medical Diagnosis, Speech Recognition, Time Series
Published	2019-01-26
URL	http://arxiv.org/abs/1901.09187v1
PDF	http://arxiv.org/pdf/1901.09187v1.pdf
PWC	https://paperswithcode.com/paper/discovery-of-important-subsequences-in
Repo
Framework

Multi-Vehicle Mixed-Reality Reinforcement Learning for Autonomous Multi-Lane Driving


Title	Multi-Vehicle Mixed-Reality Reinforcement Learning for Autonomous Multi-Lane Driving
Authors	Rupert Mitchell, Jenny Fletcher, Jacopo Panerati, Amanda Prorok
Abstract	Autonomous driving promises to transform road transport. Multi-vehicle and multi-lane scenarios, however, present unique challenges due to constrained navigation and unpredictable vehicle interactions. Learning-based methods—such as deep reinforcement learning—are emerging as a promising approach to automatically design intelligent driving policies that can cope with these challenges. Yet, the process of safely learning multi-vehicle driving behaviours is hard: while collisions—and their near-avoidance—are essential to the learning process, directly executing immature policies on autonomous vehicles raises considerable safety concerns. In this article, we present a safe and efficient framework that enables the learning of driving policies for autonomous vehicles operating in a shared workspace, where the absence of collisions cannot be guaranteed. Key to our learning procedure is a sim2real approach that uses real-world online policy adaptation in a mixed-reality setup, where other vehicles and static obstacles exist in the virtual domain. This allows us to perform safe learning by simulating (and learning from) collisions between the learning agent(s) and other objects in virtual reality. Our results demonstrate that, after only a few runs in mixed-reality, collisions are significantly reduced.
Tasks	Autonomous Driving, Autonomous Vehicles
Published	2019-11-26
URL	https://arxiv.org/abs/1911.11699v2
PDF	https://arxiv.org/pdf/1911.11699v2.pdf
PWC	https://paperswithcode.com/paper/multi-vehicle-mixed-reality-reinforcement
Repo
Framework

Unsupervised Boosting-based Autoencoder Ensembles for Outlier Detection


Title	Unsupervised Boosting-based Autoencoder Ensembles for Outlier Detection
Authors	Hamed Sarvari, Carlotta Domeniconi, Bardh Prenkaj, Giovanni Stilo
Abstract	Autoencoders, as a dimensionality reduction technique, have been recently applied to outlier detection. However, neural networks are known to be vulnerable to overfitting, and therefore have limited potential in the unsupervised outlier detection setting. Current approaches to ensemble-based autoencoders do not generate a sufficient level of diversity to avoid the overfitting issue. To overcome the aforementioned limitations we develop a Boosting-based Autoencoder Ensemble approach (in short, BAE). BAE is an unsupervised ensemble method that, similarly to the boosting approach, builds an adaptive cascade of autoencoders to achieve improved and robust results. BAE trains the autoencoder components sequentially by performing a weighted sampling of the data, aimed at reducing the amount of outliers used during training, and at injecting diversity in the ensemble. We perform extensive experiments and show that the proposed methodology outperforms state-of-the-art approaches under a variety of conditions.
Tasks	Dimensionality Reduction, Outlier Detection
Published	2019-10-22
URL	https://arxiv.org/abs/1910.09754v1
PDF	https://arxiv.org/pdf/1910.09754v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-boosting-based-autoencoder
Repo
Framework

A Domain-agnostic, Noise-resistant, Hardware-efficient Evolutionary Variational Quantum Eigensolver


Title	A Domain-agnostic, Noise-resistant, Hardware-efficient Evolutionary Variational Quantum Eigensolver
Authors	Arthur G. Rattew, Shaohan Hu, Marco Pistoia, Richard Chen, Steve Wood
Abstract	Variational quantum algorithms have shown promise in numerous fields due to their versatility in solving problems of scientific and commercial interest. However, leading algorithms for Hamiltonian simulation, such as the Variational Quantum Eigensolver (VQE), use fixed preconstructed ansatzes, limiting their general applicability and accuracy. Thus, variational forms—the quantum circuits that implement ansatzes —are either crafted heuristically or by encoding domain-specific knowledge. In this paper, we present an Evolutionary Variational Quantum Eigensolver (EVQE), a novel variational algorithm that uses evolutionary programming techniques to minimize the expectation value of a given Hamiltonian by dynamically generating and optimizing an ansatz. The algorithm is equally applicable to optimization problems in all domains, obtaining accurate energy evaluations with hardware-efficient ansatzes. In molecular simulations, the variational forms generated by EVQE are up to $18.6\times$ shallower and use up to $12\times$ fewer CX gates than those obtained by VQE with a unitary coupled cluster ansatz. EVQE demonstrates significant noise-resistance properties, obtaining results in noisy simulation with at least $3.6\times$ less error than VQE using any tested ansatz configuration. We successfully evaluated EVQE on a real 5-qubit IBMQ quantum computer. The experimental results, which we obtained both via simulation and on real quantum hardware, demonstrate the effectiveness of EVQE for general-purpose optimization on the quantum computers of the present and near future.
Tasks
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09694v4
PDF	https://arxiv.org/pdf/1910.09694v4.pdf
PWC	https://paperswithcode.com/paper/a-domain-agnostic-noise-resistant
Repo
Framework

End-to-End Optimized Transmission over Dispersive Intensity-Modulated Channels Using Bidirectional Recurrent Neural Networks


Title	End-to-End Optimized Transmission over Dispersive Intensity-Modulated Channels Using Bidirectional Recurrent Neural Networks
Authors	Boris Karanov, Domaniç Lavery, Polina Bayvel, Laurent Schmalen
Abstract	We propose an autoencoding sequence-based transceiver for communication over dispersive channels with intensity modulation and direct detection (IM/DD), designed as a bidirectional deep recurrent neural network (BRNN). The receiver uses a sliding window technique to allow for efficient data stream estimation. We find that this sliding window BRNN (SBRNN), based on end-to-end deep learning of the communication system, achieves a significant bit-error-rate reduction at all examined distances in comparison to previous block-based autoencoders implemented as feed-forward neural networks (FFNNs), leading to an increase of the transmission distance. We also compare the end-to-end SBRNN with a state-of-the-art IM/DD solution based on two level pulse amplitude modulation with an FFNN receiver, simultaneously processing multiple received symbols and approximating nonlinear Volterra equalization. Our results show that the SBRNN outperforms such systems at both 42 and 84,Gb/s, while training fewer parameters. Our novel SBRNN design aims at tailoring the end-to-end deep learning-based systems for communication over nonlinear channels with memory, such as the optical IM/DD fiber channel.
Tasks
Published	2019-01-24
URL	http://arxiv.org/abs/1901.08570v2
PDF	http://arxiv.org/pdf/1901.08570v2.pdf
PWC	https://paperswithcode.com/paper/end-to-end-optimized-transmission-over
Repo
Framework

An Introduction to Person Re-identification with Generative Adversarial Networks


Title	An Introduction to Person Re-identification with Generative Adversarial Networks
Authors	Hamed Alqahtani, Manolya Kavakli-Thorne, Charles Z. Liu
Abstract	Person re-identification is a basic subject in the field of computer vision. The traditional methods have several limitations in solving the problems of person illumination like occlusion, pose variation and feature variation under complex background. Fortunately, deep learning paradigm opens new ways of the person re-identification research and becomes a hot spot in this field. Generative Adversarial Nets (GANs) in the past few years attracted lots of attention in solving these problems. This paper reviews the GAN based methods for person re-identification focuses on the related papers about different GAN based frameworks and discusses their advantages and disadvantages. Finally, it proposes the direction of future research, especially the prospect of person re-identification methods based on GANs.
Tasks	Person Re-Identification
Published	2019-04-12
URL	http://arxiv.org/abs/1904.05992v2
PDF	http://arxiv.org/pdf/1904.05992v2.pdf
PWC	https://paperswithcode.com/paper/an-introduction-to-person-re-identification
Repo
Framework

Visual Place Recognition for Aerial Robotics: Exploring Accuracy-Computation Trade-off for Local Image Descriptors


Title	Visual Place Recognition for Aerial Robotics: Exploring Accuracy-Computation Trade-off for Local Image Descriptors
Authors	Bruno Ferrarini, Maria Waheed, Sania Waheed, Shoaib Ehsan, Michael Milford, Klaus D. McDonald-Maier
Abstract	Visual Place Recognition (VPR) is a fundamental yet challenging task for small Unmanned Aerial Vehicle (UAV). The core reasons are the extreme viewpoint changes, and limited computational power onboard a UAV which restricts the applicability of robust but computation intensive state-of-the-art VPR methods. In this context, a viable approach is to use local image descriptors for performing VPR as these can be computed relatively efficiently without the need of any special hardware, such as a GPU. However, the choice of a local feature descriptor is not trivial and calls for a detailed investigation as there is a trade-off between VPR accuracy and the required computational effort. To fill this research gap, this paper examines the performance of several state-of-the-art local feature descriptors, both from accuracy and computational perspectives, specifically for VPR application utilizing standard aerial datasets. The presented results confirm that a trade-off between accuracy and computational effort is inevitable while executing VPR on resource-constrained hardware.
Tasks	Visual Place Recognition
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00258v1
PDF	https://arxiv.org/pdf/1908.00258v1.pdf
PWC	https://paperswithcode.com/paper/visual-place-recognition-for-aerial-robotics
Repo
Framework

A Comparison of Semantic Similarity Methods for Maximum Human Interpretability


Title	A Comparison of Semantic Similarity Methods for Maximum Human Interpretability
Authors	Pinky Sitikhu, Kritish Pahi, Pujan Thapa, Subarna Shakya
Abstract	The inclusion of semantic information in any similarity measures improves the efficiency of the similarity measure and provides human interpretable results for further analysis. The similarity calculation method that focuses on features related to the text’s words only, will give less accurate results. This paper presents three different methods that not only focus on the text’s words but also incorporates semantic information of texts in their feature vector and computes semantic similarities. These methods are based on corpus-based and knowledge-based methods, which are: cosine similarity using tf-idf vectors, cosine similarity using word embedding and soft cosine similarity using word embedding. Among these three, cosine similarity using tf-idf vectors performed best in finding similarities between short news texts. The similar texts given by the method are easy to interpret and can be used directly in other information retrieval applications.
Tasks	Information Retrieval, Semantic Similarity, Semantic Textual Similarity
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09129v2
PDF	https://arxiv.org/pdf/1910.09129v2.pdf
PWC	https://paperswithcode.com/paper/a-comparison-of-semantic-similarity-methods
Repo
Framework

A Relational Tucker Decomposition for Multi-Relational Link Prediction


Title	A Relational Tucker Decomposition for Multi-Relational Link Prediction
Authors	Yanjie Wang, Samuel Broscheit, Rainer Gemulla
Abstract	We propose the Relational Tucker3 (RT) decomposition for multi-relational link prediction in knowledge graphs. We show that many existing knowledge graph embedding models are special cases of the RT decomposition with certain predefined sparsity patterns in its components. In contrast to these prior models, RT decouples the sizes of entity and relation embeddings, allows parameter sharing across relations, and does not make use of a predefined sparsity pattern. We use the RT decomposition as a tool to explore whether it is possible and beneficial to automatically learn sparsity patterns, and whether dense models can outperform sparse models (using the same number of parameters). Our experiments indicate that—depending on the dataset–both questions can be answered affirmatively.
Tasks	Graph Embedding, Knowledge Graph Embedding, Knowledge Graphs, Link Prediction
Published	2019-02-03
URL	http://arxiv.org/abs/1902.00898v1
PDF	http://arxiv.org/pdf/1902.00898v1.pdf
PWC	https://paperswithcode.com/paper/a-relational-tucker-decomposition-for-multi
Repo
Framework

Learning Analogy-Preserving Sentence Embeddings for Answer Selection


Title	Learning Analogy-Preserving Sentence Embeddings for Answer Selection
Authors	Aissatou Diallo, Markus Zopf, Johannes Fuernkranz
Abstract	Answer selection aims at identifying the correct answer for a given question from a set of potentially correct answers. Contrary to previous works, which typically focus on the semantic similarity between a question and its answer, our hypothesis is that question-answer pairs are often in analogical relation to each other. Using analogical inference as our use case, we propose a framework and a neural network architecture for learning dedicated sentence embeddings that preserve analogical properties in the semantic space. We evaluate the proposed method on benchmark datasets for answer selection and demonstrate that our sentence embeddings indeed capture analogical properties better than conventional embeddings, and that analogy-based question answering outperforms a comparable similarity-based technique.
Tasks	Answer Selection, Question Answering, Semantic Similarity, Semantic Textual Similarity, Sentence Embeddings
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05315v1
PDF	https://arxiv.org/pdf/1910.05315v1.pdf
PWC	https://paperswithcode.com/paper/learning-analogy-preserving-sentence
Repo
Framework

Neural IR Meets Graph Embedding: A Ranking Model for Product Search


Title	Neural IR Meets Graph Embedding: A Ranking Model for Product Search
Authors	Yuan Zhang, Dong Wang, Yan Zhang
Abstract	Recently, neural models for information retrieval are becoming increasingly popular. They provide effective approaches for product search due to their competitive advantages in semantic matching. However, it is challenging to use graph-based features, though proved very useful in IR literature, in these neural approaches. In this paper, we leverage the recent advances in graph embedding techniques to enable neural retrieval models to exploit graph-structured data for automatic feature extraction. The proposed approach can not only help to overcome the long-tail problem of click-through data, but also incorporate external heterogeneous information to improve search results. Extensive experiments on a real-world e-commerce dataset demonstrate significant improvement achieved by our proposed approach over multiple strong baselines both as an individual retrieval model and as a feature used in learning-to-rank frameworks.
Tasks	Graph Embedding, Information Retrieval, Learning-To-Rank
Published	2019-01-24
URL	http://arxiv.org/abs/1901.08286v1
PDF	http://arxiv.org/pdf/1901.08286v1.pdf
PWC	https://paperswithcode.com/paper/190108286
Repo
Framework

Deep Video Precoding


Title	Deep Video Precoding
Authors	Eirina Bourtsoulatze, Aaron Chadha, Ilya Fadeev, Vasileios Giotsas, Yiannis Andreopoulos
Abstract	Several groups are currently investigating how deep learning may advance the state-of-the-art in image and video coding. An open question is how to make deep neural networks work in conjunction with existing (and upcoming) video codecs, such as MPEG AVC, HEVC, VVC, Google VP9 and AOM AV1, as well as existing container and transport formats, without imposing any changes at the client side. Such compatibility is a crucial aspect when it comes to practical deployment, especially due to the fact that the video content industry and hardware manufacturers are expected to remain committed to these standards for the foreseeable future. We propose to use deep neural networks as precoders for current and future video codecs and adaptive video streaming systems. In our current design, the core precoding component comprises a cascaded structure of downscaling neural networks that operates during video encoding, prior to transmission. This is coupled with a precoding mode selection algorithm for each independently-decodable stream segment, which adjusts the downscaling factor according to scene characteristics, the utilized encoder, and the desired bitrate and encoding configuration. Our framework is compatible with all current and future codec and transport standards, as our deep precoding network structure is trained in conjunction with linear upscaling filters (e.g., the bilinear filter), which are supported by all web video players. Results with FHD and UHD content and widely-used AVC, HEVC and VP9 encoders show that coupling such standards with the proposed deep video precoding allows for 15% to 45% rate reduction under encoding configurations and bitrates suitable for video-on-demand adaptive streaming systems. The use of precoding can also lead to encoding complexity reduction, which is essential for cost-effective cloud deployment of complex encoders like H.265/HEVC and VP9.
Tasks
Published	2019-08-02
URL	https://arxiv.org/abs/1908.00812v2
PDF	https://arxiv.org/pdf/1908.00812v2.pdf
PWC	https://paperswithcode.com/paper/deep-video-precoding
Repo
Framework