July 27, 2019

3165 words 15 mins read

Paper Group ANR 523

Pre-Processing-Free Gear Fault Diagnosis Using Small Datasets with Deep Convolutional Neural Network-Based Transfer Learning. Diffusion-based nonlinear filtering for multimodal data fusion with application to sleep stage assessment. Image Compression with SVD : A New Quality Metric Based On Energy Ratio. Spatial Projection of Multiple Climate Varia …

Pre-Processing-Free Gear Fault Diagnosis Using Small Datasets with Deep Convolutional Neural Network-Based Transfer Learning


Title	Pre-Processing-Free Gear Fault Diagnosis Using Small Datasets with Deep Convolutional Neural Network-Based Transfer Learning
Authors	Pei Cao, Shengli Zhang, Jiong Tang
Abstract	Early fault diagnosis in complex mechanical systems such as gearbox has always been a great challenge, even with the recent development in deep neural networks. The performance of a classic fault diagnosis system predominantly depends on the features extracted and the classifier subsequently applied. Although a large number of attempts have been made regarding feature extraction techniques, the methods require great human involvements are heavily depend on domain expertise and may thus be non-representative and biased from application to application. On the other hand, while the deep neural networks based approaches feature adaptive feature extractions and inherent classifications, they usually require a substantial set of training data and thus hinder their usage for engineering applications with limited training data such as gearbox fault diagnosis. This paper develops a deep convolutional neural network-based transfer learning approach that not only entertains pre-processing free adaptive feature extractions, but also requires only a small set of training data. The proposed approach performs gear fault diagnosis using pre-processing free raw accelerometer data and experiments with various sizes of training data were conducted. The superiority of the proposed approach is revealed by comparing the performance with other methods such as locally trained convolution neural network and angle-frequency analysis based support vector machine. The achieved accuracy indicates that the proposed approach is not only viable and robust, but also has the potential to be readily applicable to other fault diagnosis practices.
Tasks	Transfer Learning
Published	2017-10-24
URL	http://arxiv.org/abs/1710.08904v1
PDF	http://arxiv.org/pdf/1710.08904v1.pdf
PWC	https://paperswithcode.com/paper/pre-processing-free-gear-fault-diagnosis
Repo
Framework

Diffusion-based nonlinear filtering for multimodal data fusion with application to sleep stage assessment


Title	Diffusion-based nonlinear filtering for multimodal data fusion with application to sleep stage assessment
Authors	Ori Katz, Ronen Talmon, Yu-Lun Lo, Hau-Tieng Wu
Abstract	The problem of information fusion from multiple data-sets acquired by multimodal sensors has drawn significant research attention over the years. In this paper, we focus on a particular problem setting consisting of a physical phenomenon or a system of interest observed by multiple sensors. We assume that all sensors measure some aspects of the system of interest with additional sensor-specific and irrelevant components. Our goal is to recover the variables relevant to the observed system and to filter out the nuisance effects of the sensor-specific variables. We propose an approach based on manifold learning, which is particularly suitable for problems with multiple modalities, since it aims to capture the intrinsic structure of the data and relies on minimal prior model knowledge. Specifically, we propose a nonlinear filtering scheme, which extracts the hidden sources of variability captured by two or more sensors, that are independent of the sensor-specific components. In addition to presenting a theoretical analysis, we demonstrate our technique on real measured data for the purpose of sleep stage assessment based on multiple, multimodal sensor measurements. We show that without prior knowledge on the different modalities and on the measured system, our method gives rise to a data-driven representation that is well correlated with the underlying sleep process and is robust to noise and sensor-specific effects.
Tasks
Published	2017-01-13
URL	http://arxiv.org/abs/1701.03619v2
PDF	http://arxiv.org/pdf/1701.03619v2.pdf
PWC	https://paperswithcode.com/paper/diffusion-based-nonlinear-filtering-for
Repo
Framework

Image Compression with SVD : A New Quality Metric Based On Energy Ratio


Title	Image Compression with SVD : A New Quality Metric Based On Energy Ratio
Authors	Henri Bruno Razafindradina, Paul Auguste Randriamitantsoa, Nicolas Raft Razafindrakoto
Abstract	Digital image compression is a technique that allows to reduce the size of an image in order to increase the capacity storage devices and to optimize the use of network bandwidth. The quality of compressed images with the techniques based on the discrete cosine transform or the wavelet transform is generally measured with PSNR or SSIM. Theses metrics are not suitable to images compressed with the singular values decomposition. This paper presents a new metric based on the energy ratio to measure the quality of the images coded with the SVD. A series of tests on 512 * 512 pixels images show that, for a rank k = 40 corresponding to a SSIM = 0,94 or PSNR = 35 dB, 99,9% of the energy are restored. Three areas of image quality assessments were identified. This new metric is also very accurate and could overcome the weaknesses of PSNR and SSIM.
Tasks	Image Compression
Published	2017-01-22
URL	http://arxiv.org/abs/1701.06183v1
PDF	http://arxiv.org/pdf/1701.06183v1.pdf
PWC	https://paperswithcode.com/paper/image-compression-with-svd-a-new-quality
Repo
Framework

Spatial Projection of Multiple Climate Variables using Hierarchical Multitask Learning


Title	Spatial Projection of Multiple Climate Variables using Hierarchical Multitask Learning
Authors	André R. Gonçalves, Arindam Banerjee, Fernando J. Von Zuben
Abstract	Future projection of climate is typically obtained by combining outputs from multiple Earth System Models (ESMs) for several climate variables such as temperature and precipitation. While IPCC has traditionally used a simple model output average, recent work has illustrated potential advantages of using a multitask learning (MTL) framework for projections of individual climate variables. In this paper we introduce a framework for hierarchical multitask learning (HMTL) with two levels of tasks such that each super-task, i.e., task at the top level, is itself a multitask learning problem over sub-tasks. For climate projections, each super-task focuses on projections of specific climate variables spatially using an MTL formulation. For the proposed HMTL approach, a group lasso regularization is added to couple parameters across the super-tasks, which in the climate context helps exploit relationships among the behavior of different climate variables at a given spatial location. We show that some recent works on MTL based on learning task dependency structures can be viewed as special cases of HMTL. Experiments on synthetic and real climate data show that HMTL produces better results than decoupled MTL methods applied separately on the super-tasks and HMTL significantly outperforms baselines for climate projection.
Tasks
Published	2017-01-30
URL	http://arxiv.org/abs/1701.08840v1
PDF	http://arxiv.org/pdf/1701.08840v1.pdf
PWC	https://paperswithcode.com/paper/spatial-projection-of-multiple-climate
Repo
Framework

Accelerating Kernel Classifiers Through Borders Mapping


Title	Accelerating Kernel Classifiers Through Borders Mapping
Authors	Peter Mills
Abstract	Support vector machines (SVM) and other kernel techniques represent a family of powerful statistical classification methods with high accuracy and broad applicability. Because they use all or a significant portion of the training data, however, they can be slow, especially for large problems. Piecewise linear classifiers are similarly versatile, yet have the additional advantages of simplicity, ease of interpretation and, if the number of component linear classifiers is not too large, speed. Here we show how a simple, piecewise linear classifier can be trained from a kernel-based classifier in order to improve the classification speed. The method works by finding the root of the difference in conditional probabilities between pairs of opposite classes to build up a representation of the decision boundary. When tested on 17 different datasets, it succeeded in improving the classification speed of a SVM for 12 of them by up to two orders-of-magnitude. Of these, two were less accurate than a simple, linear classifier. The method is best suited to problems with continuum features data and smooth probability functions. Because the component linear classifiers are built up individually from an existing classifier, rather than through a simultaneous optimization procedure, the classifier is also fast to train.
Tasks
Published	2017-08-20
URL	https://arxiv.org/abs/1708.05917v4
PDF	https://arxiv.org/pdf/1708.05917v4.pdf
PWC	https://paperswithcode.com/paper/accelerating-kernel-classifiers-through
Repo
Framework

On the Origin of Deep Learning


Title	On the Origin of Deep Learning
Authors	Haohan Wang, Bhiksha Raj
Abstract	This paper is a review of the evolutionary history of deep learning models. It covers from the genesis of neural networks when associationism modeling of the brain is studied, to the models that dominate the last decade of research in deep learning like convolutional neural networks, deep belief networks, and recurrent neural networks. In addition to a review of these models, this paper primarily focuses on the precedents of the models above, examining how the initial ideas are assembled to construct the early models and how these preliminary models are developed into their current forms. Many of these evolutionary paths last more than half a century and have a diversity of directions. For example, CNN is built on prior knowledge of biological vision system; DBN is evolved from a trade-off of modeling power and computation complexity of graphical models and many nowadays models are neural counterparts of ancient linear models. This paper reviews these evolutionary paths and offers a concise thought flow of how these models are developed, and aims to provide a thorough background for deep learning. More importantly, along with the path, this paper summarizes the gist behind these milestones and proposes many directions to guide the future research of deep learning.
Tasks
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07800v4
PDF	http://arxiv.org/pdf/1702.07800v4.pdf
PWC	https://paperswithcode.com/paper/on-the-origin-of-deep-learning
Repo
Framework

Beyond the technical challenges for deploying Machine Learning solutions in a software company


Title	Beyond the technical challenges for deploying Machine Learning solutions in a software company
Authors	Ilias Flaounas
Abstract	Recently software development companies started to embrace Machine Learning (ML) techniques for introducing a series of advanced functionality in their products such as personalisation of the user experience, improved search, content recommendation and automation. The technical challenges for tackling these problems are heavily researched in literature. A less studied area is a pragmatic approach to the role of humans in a complex modern industrial environment where ML based systems are developed. Key stakeholders affect the system from inception and up to operation and maintenance. Product managers want to embed “smart” experiences for their users and drive the decisions on what should be built next; software engineers are challenged to build or utilise ML software tools that require skills that are well outside of their comfort zone; legal and risk departments may influence design choices and data access; operations teams are requested to maintain ML systems which are non-stationary in their nature and change behaviour over time; and finally ML practitioners should communicate with all these stakeholders to successfully build a reliable system. This paper discusses some of the challenges we faced in Atlassian as we started investing more in the ML space.
Tasks
Published	2017-08-08
URL	http://arxiv.org/abs/1708.02363v1
PDF	http://arxiv.org/pdf/1708.02363v1.pdf
PWC	https://paperswithcode.com/paper/beyond-the-technical-challenges-for-deploying
Repo
Framework

A Separation Principle for Control in the Age of Deep Learning


Title	A Separation Principle for Control in the Age of Deep Learning
Authors	Alessandro Achille, Stefano Soatto
Abstract	We review the problem of defining and inferring a “state” for a control system based on complex, high-dimensional, highly uncertain measurement streams such as videos. Such a state, or representation, should contain all and only the information needed for control, and discount nuisance variability in the data. It should also have finite complexity, ideally modulated depending on available resources. This representation is what we want to store in memory in lieu of the data, as it “separates” the control task from the measurement process. For the trivial case with no dynamics, a representation can be inferred by minimizing the Information Bottleneck Lagrangian in a function class realized by deep neural networks. The resulting representation has much higher dimension than the data, already in the millions, but it is smaller in the sense of information content, retaining only what is needed for the task. This process also yields representations that are invariant to nuisance factors and having maximally independent components. We extend these ideas to the dynamic case, where the representation is the posterior density of the task variable given the measurements up to the current time, which is in general much simpler than the prediction density maintained by the classical Bayesian filter. Again this can be finitely-parametrized using a deep neural network, and already some applications are beginning to emerge. No explicit assumption of Markovianity is needed; instead, complexity trades off approximation of an optimal representation, including the degree of Markovianity.
Tasks
Published	2017-11-09
URL	http://arxiv.org/abs/1711.03321v1
PDF	http://arxiv.org/pdf/1711.03321v1.pdf
PWC	https://paperswithcode.com/paper/a-separation-principle-for-control-in-the-age
Repo
Framework

Re-ranking Person Re-identification with k-reciprocal Encoding


Title	Re-ranking Person Re-identification with k-reciprocal Encoding
Authors	Zhun Zhong, Liang Zheng, Donglin Cao, Shaozi Li
Abstract	When considering person re-identification (re-ID) as a retrieval process, re-ranking is a critical step to improve its accuracy. Yet in the re-ID community, limited effort has been devoted to re-ranking, especially those fully automatic, unsupervised solutions. In this paper, we propose a k-reciprocal encoding method to re-rank the re-ID results. Our hypothesis is that if a gallery image is similar to the probe in the k-reciprocal nearest neighbors, it is more likely to be a true match. Specifically, given an image, a k-reciprocal feature is calculated by encoding its k-reciprocal nearest neighbors into a single vector, which is used for re-ranking under the Jaccard distance. The final distance is computed as the combination of the original distance and the Jaccard distance. Our re-ranking method does not require any human interaction or any labeled data, so it is applicable to large-scale datasets. Experiments on the large-scale Market-1501, CUHK03, MARS, and PRW datasets confirm the effectiveness of our method.
Tasks	Person Re-Identification
Published	2017-01-29
URL	http://arxiv.org/abs/1701.08398v4
PDF	http://arxiv.org/pdf/1701.08398v4.pdf
PWC	https://paperswithcode.com/paper/re-ranking-person-re-identification-with-k
Repo
Framework

Automated Lane Detection in Crowds using Proximity Graphs


Title	Automated Lane Detection in Crowds using Proximity Graphs
Authors	Stijn Heldens, Claudio Martella, Nelly Litvak, Maarten van Steen
Abstract	Studying the behavior of crowds is vital for understanding and predicting human interactions in public areas. Research has shown that, under certain conditions, large groups of people can form collective behavior patterns: local interactions between individuals results in global movements patterns. To detect these patterns in a crowd, we assume each person is carrying an on-body device that acts a local proximity sensor, e.g., smartphone or bluetooth badge, and represent the texture of the crowd as a proximity graph. Our goal is extract information about crowds from these proximity graphs. In this work, we focus on one particular type of pattern: lane formation. We present a formal definition of a lane, proposed a simple probabilistic model that simulates lanes moving through a stationary crowd, and present an automated lane-detection method. Our preliminary results show that our method is able to detect lanes of different shapes and sizes. We see our work as an initial step towards rich pattern recognition using proximity graphs.
Tasks	Lane Detection
Published	2017-07-06
URL	http://arxiv.org/abs/1707.01698v1
PDF	http://arxiv.org/pdf/1707.01698v1.pdf
PWC	https://paperswithcode.com/paper/automated-lane-detection-in-crowds-using
Repo
Framework

Neural Networks Compression for Language Modeling


Title	Neural Networks Compression for Language Modeling
Authors	Artem M. Grachev, Dmitry I. Ignatov, Andrey V. Savchenko
Abstract	In this paper, we consider several compression techniques for the language modeling problem based on recurrent neural networks (RNNs). It is known that conventional RNNs, e.g, LSTM-based networks in language modeling, are characterized with either high space complexity or substantial inference time. This problem is especially crucial for mobile applications, in which the constant interaction with the remote server is inappropriate. By using the Penn Treebank (PTB) dataset we compare pruning, quantization, low-rank factorization, tensor train decomposition for LSTM networks in terms of model size and suitability for fast inference.
Tasks	Language Modelling, Quantization
Published	2017-08-20
URL	http://arxiv.org/abs/1708.05963v1
PDF	http://arxiv.org/pdf/1708.05963v1.pdf
PWC	https://paperswithcode.com/paper/neural-networks-compression-for-language
Repo
Framework

The in-town monitoring system for ambulance dispatch centre


Title	The in-town monitoring system for ambulance dispatch centre
Authors	Bartlomiej Placzek, Jolnta Golosz
Abstract	The paper presents the vehicles integrated monitoring system giving priorities for emergency vehicles. The described system exploits the data gathered by: geographical positioning systems and geographical information systems. The digital maps and roadside cameras provide the dispatchers with aims for in town ambulances traffic management. The method of vehicles positioning in the city network and algorithms for ambulances recognition by image processing techniques have been discussed in the paper. These priorities are needed for an efficient life-saving actions that require the real-time controlling strategies.
Tasks
Published	2017-05-31
URL	http://arxiv.org/abs/1706.03699v1
PDF	http://arxiv.org/pdf/1706.03699v1.pdf
PWC	https://paperswithcode.com/paper/the-in-town-monitoring-system-for-ambulance
Repo
Framework

Extracting an English-Persian Parallel Corpus from Comparable Corpora


Title	Extracting an English-Persian Parallel Corpus from Comparable Corpora
Authors	Akbar Karimi, Ebrahim Ansari, Bahram Sadeghi Bigham
Abstract	Parallel data are an important part of a reliable Statistical Machine Translation (SMT) system. The more of these data are available, the better the quality of the SMT system. However, for some language pairs such as Persian-English, parallel sources of this kind are scarce. In this paper, a bidirectional method is proposed to extract parallel sentences from English and Persian document aligned Wikipedia. Two machine translation systems are employed to translate from Persian to English and the reverse after which an IR system is used to measure the similarity of the translated sentences. Adding the extracted sentences to the training data of the existing SMT systems is shown to improve the quality of the translation. Furthermore, the proposed method slightly outperforms the one-directional approach. The extracted corpus consists of about 200,000 sentences which have been sorted by their degree of similarity calculated by the IR system and is freely available for public access on the Web.
Tasks	Machine Translation
Published	2017-11-02
URL	http://arxiv.org/abs/1711.00681v3
PDF	http://arxiv.org/pdf/1711.00681v3.pdf
PWC	https://paperswithcode.com/paper/extracting-an-english-persian-parallel-corpus
Repo
Framework


Title	Social Media Writing Style Fingerprint
Authors	Himank Yadav, Juliang Li
Abstract	We present our approach for computer-aided social media text authorship attribution based on recent advances in short text authorship verification. We use various natural language techniques to create word-level and character-level models that act as hidden layers to simulate a simple neural network. The choice of word-level and character-level models in each layer was informed through validation performance. The output layer of our system uses an unweighted majority vote vector to arrive at a conclusion. We also considered writing bias in social media posts while collecting our training dataset to increase system robustness. Our system achieved a precision, recall, and F-measure of 0.82, 0.926 and 0.869 respectively.
Tasks
Published	2017-12-11
URL	http://arxiv.org/abs/1712.04762v3
PDF	http://arxiv.org/pdf/1712.04762v3.pdf
PWC	https://paperswithcode.com/paper/social-media-writing-style-fingerprint
Repo
Framework

Signature Verification Approach using Fusion of Hybrid Texture Features


Title	Signature Verification Approach using Fusion of Hybrid Texture Features
Authors	Ankan Kumar Bhunia, Alireza Alaei, Partha Pratim Roy
Abstract	In this paper, a writer-dependent signature verification method is proposed. Two different types of texture features, namely Wavelet and Local Quantized Patterns (LQP) features, are employed to extract two kinds of transform and statistical based information from signature images. For each writer two separate one-class support vector machines (SVMs) corresponding to each set of LQP and Wavelet features are trained to obtain two different authenticity scores for a given signature. Finally, a score level classifier fusion method is used to integrate the scores obtained from the two one-class SVMs to achieve the verification score. In the proposed method only genuine signatures are used to train the one-class SVMs. The proposed signature verification method has been tested using four different publicly available datasets and the results demonstrate the generality of the proposed method. The proposed system outperforms other existing systems in the literature.
Tasks
Published	2017-09-27
URL	https://arxiv.org/abs/1709.09348v2
PDF	https://arxiv.org/pdf/1709.09348v2.pdf
PWC	https://paperswithcode.com/paper/signature-verification-approach-using-fusion
Repo
Framework