July 28, 2019

2788 words 14 mins read

Paper Group ANR 213

A Finite State and Rule-based Akshara to Prosodeme (A2P) Converter in Hindi. A Study of AI Population Dynamics with Million-agent Reinforcement Learning. Reasoning by Cases in Structured Argumentation. The Multiscale Bowler-Hat Transform for Blood Vessel Enhancement in Retinal Images. On Matching Skulls to Digital Face Images: A Preliminary Approac …

A Finite State and Rule-based Akshara to Prosodeme (A2P) Converter in Hindi


Title	A Finite State and Rule-based Akshara to Prosodeme (A2P) Converter in Hindi
Authors	Somnath Roy
Abstract	This article describes a software module called Akshara to Prosodeme (A2P) converter in Hindi. It converts an input grapheme into prosedeme (sequence of phonemes with the specification of syllable boundaries and prosodic labels). The software is based on two proposed finite state machines\textemdash one for the syllabification and another for the syllable labeling. In addition to that, it also uses a set of nonlinear phonological rules proposed for foot formation in Hindi, which encompass solutions to schwa-deletion in simple, compound, derived and inflected words. The nonlinear phonological rules are based on metrical phonology with the provision of recursive foot structure. A software module is implemented in Python. The testing of the software for syllabification, syllable labeling, schwa deletion and prosodic labeling yield an accuracy of more than 99% on a lexicon of size 28664 words.
Tasks
Published	2017-05-04
URL	http://arxiv.org/abs/1705.01833v1
PDF	http://arxiv.org/pdf/1705.01833v1.pdf
PWC	https://paperswithcode.com/paper/a-finite-state-and-rule-based-akshara-to
Repo
Framework

A Study of AI Population Dynamics with Million-agent Reinforcement Learning


Title	A Study of AI Population Dynamics with Million-agent Reinforcement Learning
Authors	Yaodong Yang, Lantao Yu, Yiwei Bai, Jun Wang, Weinan Zhang, Ying Wen, Yong Yu
Abstract	We conduct an empirical study on discovering the ordered collective dynamics obtained by a population of intelligence agents, driven by million-agent reinforcement learning. Our intention is to put intelligent agents into a simulated natural context and verify if the principles developed in the real world could also be used in understanding an artificially-created intelligent population. To achieve this, we simulate a large-scale predator-prey world, where the laws of the world are designed by only the findings or logical equivalence that have been discovered in nature. We endow the agents with the intelligence based on deep reinforcement learning (DRL). In order to scale the population size up to millions agents, a large-scale DRL training platform with redesigned experience buffer is proposed. Our results show that the population dynamics of AI agents, driven only by each agent’s individual self-interest, reveals an ordered pattern that is similar to the Lotka-Volterra model studied in population biology. We further discover the emergent behaviors of collective adaptations in studying how the agents’ grouping behaviors will change with the environmental resources. Both of the two findings could be explained by the self-organization theory in nature.
Tasks
Published	2017-09-13
URL	http://arxiv.org/abs/1709.04511v4
PDF	http://arxiv.org/pdf/1709.04511v4.pdf
PWC	https://paperswithcode.com/paper/a-study-of-ai-population-dynamics-with
Repo
Framework

Reasoning by Cases in Structured Argumentation


Title	Reasoning by Cases in Structured Argumentation
Authors	Mathieu Beirlaen, Jesse Heyninck, Christian Straßer
Abstract	We extend the $ASPIC^+$ framework for structured argumentation so as to allow applications of the reasoning by cases inference scheme for defeasible arguments. Given an argument with conclusion `$A$ or $B$', an argument based on $A$ with conclusion $C$, and an argument based on $B$ with conclusion $C$, we allow the construction of an argument with conclusion $C$. We show how our framework leads to different results than other approaches in non-monotonic logic for dealing with disjunctive information, such as disjunctive default theory or approaches based on the OR-rule (which allows to derive a defeasible rule` If ($A$ or $B$) then $C$’, given two defeasible rules `If $A$ then $C$' and` If $B$ then $C$’). We raise new questions regarding the subtleties of reasoning defeasibly with disjunctive information, and show that its formalization is more intricate than one would presume.
Tasks
Published	2017-03-24
URL	http://arxiv.org/abs/1703.08397v1
PDF	http://arxiv.org/pdf/1703.08397v1.pdf
PWC	https://paperswithcode.com/paper/reasoning-by-cases-in-structured
Repo
Framework

The Multiscale Bowler-Hat Transform for Blood Vessel Enhancement in Retinal Images


Title	The Multiscale Bowler-Hat Transform for Blood Vessel Enhancement in Retinal Images
Authors	Çiğdem Sazak, Carl J. Nelson, Boguslaw Obara
Abstract	Enhancement, followed by segmentation, quantification and modelling, of blood vessels in retinal images plays an essential role in computer-aid retinopathy diagnosis. In this paper, we introduce a new vessel enhancement method which is the bowler-hat transform based on mathematical morphology. The proposed method combines different structuring elements to detect innate features of vessel-like structures. We evaluate the proposed method qualitatively and quantitatively, and compare it with the existing, state-of-the-art methods using both synthetic and real datasets. Our results show that the proposed method achieves high-quality vessel-like structure enhancement in both synthetic examples and in clinically relevant retinal images, and is shown to be able to detect fine vessels while remaining robust at junctions.
Tasks
Published	2017-09-16
URL	http://arxiv.org/abs/1709.05495v3
PDF	http://arxiv.org/pdf/1709.05495v3.pdf
PWC	https://paperswithcode.com/paper/the-multiscale-bowler-hat-transform-for-blood
Repo
Framework

On Matching Skulls to Digital Face Images: A Preliminary Approach


Title	On Matching Skulls to Digital Face Images: A Preliminary Approach
Authors	Shruti Nagpal, Maneet Singh, Arushi Jain, Richa Singh, Mayank Vatsa, Afzel Noore
Abstract	Forensic application of automatically matching skull with face images is an important research area linking biometrics with practical applications in forensics. It is an opportunity for biometrics and face recognition researchers to help the law enforcement and forensic experts in giving an identity to unidentified human skulls. It is an extremely challenging problem which is further exacerbated due to lack of any publicly available database related to this problem. This is the first research in this direction with a two-fold contribution: (i) introducing the first of its kind skull-face image pair database, IdentifyMe, and (ii) presenting a preliminary approach using the proposed semi-supervised formulation of transform learning. The experimental results and comparison with existing algorithms showcase the challenging nature of the problem. We assert that the availability of the database will inspire researchers to build sophisticated skull-to-face matching algorithms.
Tasks	Face Recognition
Published	2017-10-08
URL	http://arxiv.org/abs/1710.02866v1
PDF	http://arxiv.org/pdf/1710.02866v1.pdf
PWC	https://paperswithcode.com/paper/on-matching-skulls-to-digital-face-images-a
Repo
Framework

Fuzzy Recommendations in Marketing Campaigns


Title	Fuzzy Recommendations in Marketing Campaigns
Authors	S. Podapati, L. Lundberg, L. Skold, O. Rosander, J. Sidorova
Abstract	The population in Sweden is growing rapidly due to immigration. In this light, the issue of infrastructure upgrades to provide telecommunication services is of importance. New antennas can be installed at hot spots of user demand, which will require an investment, and/or the clientele expansion can be carried out in a planned manner to promote the exploitation of the infrastructure in the less loaded geographical zones. In this paper, we explore the second alternative. Informally speaking, the term Infrastructure-Stressing describes a user who stays in the zones of high demand, which are prone to produce service failures, if further loaded. We have studied the Infrastructure-Stressing population in the light of their correlation with geo-demographic segments. This is motivated by the fact that specific geo-demographic segments can be targeted via marketing campaigns. Fuzzy logic is applied to create an interface between big data, numeric methods for processing big data and a manager.
Tasks
Published	2017-06-13
URL	http://arxiv.org/abs/1706.03940v1
PDF	http://arxiv.org/pdf/1706.03940v1.pdf
PWC	https://paperswithcode.com/paper/fuzzy-recommendations-in-marketing-campaigns
Repo
Framework

The Geometric Block Model


Title	The Geometric Block Model
Authors	Sainyam Galhotra, Arya Mazumdar, Soumyabrata Pal, Barna Saha
Abstract	To capture the inherent geometric features of many community detection problems, we propose to use a new random graph model of communities that we call a Geometric Block Model. The geometric block model generalizes the random geometric graphs in the same way that the well-studied stochastic block model generalizes the Erdos-Renyi random graphs. It is also a natural extension of random community models inspired by the recent theoretical and practical advancement in community detection. While being a topic of fundamental theoretical interest, our main contribution is to show that many practical community structures are better explained by the geometric block model. We also show that a simple triangle-counting algorithm to detect communities in the geometric block model is near-optimal. Indeed, even in the regime where the average degree of the graph grows only logarithmically with the number of vertices (sparse-graph), we show that this algorithm performs extremely well, both theoretically and practically. In contrast, the triangle-counting algorithm is far from being optimum for the stochastic block model. We simulate our results on both real and synthetic datasets to show superior performance of both the new model as well as our algorithm.
Tasks	Community Detection
Published	2017-09-16
URL	http://arxiv.org/abs/1709.05510v2
PDF	http://arxiv.org/pdf/1709.05510v2.pdf
PWC	https://paperswithcode.com/paper/the-geometric-block-model
Repo
Framework

Neural Machine Translation between Herbal Prescriptions and Diseases


Title	Neural Machine Translation between Herbal Prescriptions and Diseases
Authors	Sun-Chong Wang
Abstract	The current study applies deep learning to herbalism. Toward the goal, we acquired the de-identified health insurance reimbursements that were claimed in a 10-year period from 2004 to 2013 in the National Health Insurance Database of Taiwan, the total number of reimbursement records equaling 340 millions. Two artificial intelligence techniques were applied to the dataset: residual convolutional neural network multitask classifier and attention-based recurrent neural network. The former works to translate from herbal prescriptions to diseases; and the latter from diseases to herbal prescriptions. Analysis of the classification results indicates that herbal prescriptions are specific to: anatomy, pathophysiology, sex and age of the patient, and season and year of the prescription. Further analysis identifies temperature and gross domestic product as the meteorological and socioeconomic factors that are associated with herbal prescriptions. Analysis of the neural machine transitional result indicates that the recurrent neural network learnt not only syntax but also semantics of diseases and herbal prescriptions.
Tasks	Machine Translation
Published	2017-07-09
URL	http://arxiv.org/abs/1707.02575v1
PDF	http://arxiv.org/pdf/1707.02575v1.pdf
PWC	https://paperswithcode.com/paper/neural-machine-translation-between-herbal
Repo
Framework

Real-Time Capable Micro-Doppler Signature Decomposition of Walking Human Limbs


Title	Real-Time Capable Micro-Doppler Signature Decomposition of Walking Human Limbs
Authors	Sherif Abdulatif, Fady Aziz, Bernhard Kleiner, Urs Schneider
Abstract	Unique micro-Doppler signature ($\boldsymbol{\mu}$-D) of a human body motion can be analyzed as the superposition of different body parts $\boldsymbol{\mu}$-D signatures. Extraction of human limbs $\boldsymbol{\mu}$-D signatures in real-time can be used to detect, classify and track human motion especially for safety application. In this paper, two methods are combined to simulate $\boldsymbol{\mu}$-D signatures of a walking human. Furthermore, a novel limbs $\mu$-D signature time independent decomposition feasibility study is presented based on features as $\mu$-D signatures and range profiles also known as micro-Range ($\mu$-R). Walking human body parts can be divided into four classes (base, arms, legs, feet) and a decision tree classifier is used. Validation is done and the classifier is able to decompose $\mu$-D signatures of limbs from a walking human signature on real-time basis.
Tasks
Published	2017-11-25
URL	http://arxiv.org/abs/1711.09175v1
PDF	http://arxiv.org/pdf/1711.09175v1.pdf
PWC	https://paperswithcode.com/paper/real-time-capable-micro-doppler-signature
Repo
Framework

Identifying Phrasemes via Interlingual Association Measures – A Data-driven Approach on Dependency-parsed and Word-aligned Parallel Corpora


Title	Identifying Phrasemes via Interlingual Association Measures – A Data-driven Approach on Dependency-parsed and Word-aligned Parallel Corpora
Authors	Johannes Graën
Abstract	This is a preprint of the article “Identifying Phrasemes via Interlingual Association Measures” that was presented in February 2016 at the LeKo (Lexical combinations and typified speech in a multilingual context) conference in Innsbruck.
Tasks
Published	2017-09-24
URL	http://arxiv.org/abs/1709.08196v1
PDF	http://arxiv.org/pdf/1709.08196v1.pdf
PWC	https://paperswithcode.com/paper/identifying-phrasemes-via-interlingual
Repo
Framework

Modelling prosodic structure using Artificial Neural Networks


Title	Modelling prosodic structure using Artificial Neural Networks
Authors	Jean-Philippe Bernardy, Charalambos Themistocleous
Abstract	The ability to accurately perceive whether a speaker is asking a question or is making a statement is crucial for any successful interaction. However, learning and classifying tonal patterns has been a challenging task for automatic speech recognition and for models of tonal representation, as tonal contours are characterized by significant variation. This paper provides a classification model of Cypriot Greek questions and statements. We evaluate two state-of-the-art network architectures: a Long Short-Term Memory (LSTM) network and a convolutional network (ConvNet). The ConvNet outperforms the LSTM in the classification task and exhibited an excellent performance with 95% classification accuracy.
Tasks	Speech Recognition
Published	2017-06-13
URL	http://arxiv.org/abs/1706.03952v2
PDF	http://arxiv.org/pdf/1706.03952v2.pdf
PWC	https://paperswithcode.com/paper/modelling-prosodic-structure-using-artificial
Repo
Framework

A Versatile Approach to Evaluating and Testing Automated Vehicles based on Kernel Methods


Title	A Versatile Approach to Evaluating and Testing Automated Vehicles based on Kernel Methods
Authors	Zhiyuan Huang, Yaohui Guo, Henry Lam, Ding Zhao
Abstract	Evaluation and validation of complicated control systems are crucial to guarantee usability and safety. Usually, failure happens in some very rarely encountered situations, but once triggered, the consequence is disastrous. Accelerated Evaluation is a methodology that efficiently tests those rarely-occurring yet critical failures via smartly-sampled test cases. The distribution used in sampling is pivotal to the performance of the method, but building a suitable distribution requires case-by-case analysis. This paper proposes a versatile approach for constructing sampling distribution using kernel method. The approach uses statistical learning tools to approximate the critical event sets and constructs distributions based on the unique properties of Gaussian distributions. We applied the method to evaluate the automated vehicles. Numerical experiments show proposed approach can robustly identify the rare failures and significantly reduce the evaluation time.
Tasks
Published	2017-10-01
URL	http://arxiv.org/abs/1710.00283v1
PDF	http://arxiv.org/pdf/1710.00283v1.pdf
PWC	https://paperswithcode.com/paper/a-versatile-approach-to-evaluating-and
Repo
Framework

Random active path model of deep neural networks with diluted binary synapses


Title	Random active path model of deep neural networks with diluted binary synapses
Authors	Haiping Huang, Alireza Goudarzi
Abstract	Deep learning has become a powerful and popular tool for a variety of machine learning tasks. However, it is challenging to understand the mechanism of deep learning from a theoretical perspective. In this work, we propose a random active path model to study collective properties of deep neural networks with binary synapses, under the removal perturbation of connections between layers. In the model, the path from input to output is randomly activated, and the corresponding input unit constrains the weights along the path into the form of a $p$-weight interaction glass model. A critical value of the perturbation is observed to separate a spin glass regime from a paramagnetic regime, with the transition being of the first order. The paramagnetic phase is conjectured to have a poor generalization performance.
Tasks
Published	2017-05-02
URL	http://arxiv.org/abs/1705.00850v3
PDF	http://arxiv.org/pdf/1705.00850v3.pdf
PWC	https://paperswithcode.com/paper/random-active-path-model-of-deep-neural
Repo
Framework

Semantically-Guided Video Object Segmentation


Title	Semantically-Guided Video Object Segmentation
Authors	Sergi Caelles, Yuhua Chen, Jordi Pont-Tuset, Luc Van Gool
Abstract	This paper tackles the problem of semi-supervised video object segmentation, that is, segmenting an object in a sequence given its mask in the first frame. One of the main challenges in this scenario is the change of appearance of the objects of interest. Their semantics, on the other hand, do not vary. This paper investigates how to take advantage of such invariance via the introduction of a semantic prior that guides the appearance model. Specifically, given the segmentation mask of the first frame of a sequence, we estimate the semantics of the object of interest, and propagate that knowledge throughout the sequence to improve the results based on an appearance model. We present Semantically-Guided Video Object Segmentation (SGV), which improves results over previous state of the art on two different datasets using a variety of evaluation metrics, while running in half a second per frame.
Tasks	Semantic Segmentation, Semi-supervised Video Object Segmentation, Video Object Segmentation, Video Semantic Segmentation
Published	2017-04-06
URL	http://arxiv.org/abs/1704.01926v2
PDF	http://arxiv.org/pdf/1704.01926v2.pdf
PWC	https://paperswithcode.com/paper/semantically-guided-video-object-segmentation
Repo
Framework

Speech Dereverberation Using Nonnegative Convolutive Transfer Function and Spectro temporal Modeling


Title	Speech Dereverberation Using Nonnegative Convolutive Transfer Function and Spectro temporal Modeling
Authors	Nasser Mohammadiha, Simon Doclo
Abstract	This paper presents two single channel speech dereverberation methods to enhance the quality of speech signals that have been recorded in an enclosed space. For both methods, the room acoustics are modeled using a nonnegative approximation of the convolutive transfer function (NCTF), and to additionally exploit the spectral properties of the speech signal, such as the low rank nature of the speech spectrogram, the speech spectrogram is modeled using nonnegative matrix factorization (NMF). Two methods are described to combine the NCTF and NMF models. In the first method, referred to as the integrated method, a cost function is constructed by directly integrating the speech NMF model into the NCTF model, while in the second method, referred to as the weighted method, the NCTF and NMF based cost functions are weighted and summed. Efficient update rules are derived to solve both optimization problems. In addition, an extension of the integrated method is presented, which exploits the temporal dependencies of the speech signal. Several experiments are performed on reverberant speech signals with and without background noise, where the integrated method yields a considerably higher speech quality than the baseline NCTF method and a state of the art spectral enhancement method. Moreover, the experimental results indicate that the weighted method can even lead to a better performance in terms of instrumental quality measures, but that the optimal weighting parameter depends on the room acoustics and the utilized NMF model. Modeling the temporal dependencies in the integrated method was found to be useful only for highly reverberant conditions.
Tasks
Published	2017-09-16
URL	http://arxiv.org/abs/1709.05557v1
PDF	http://arxiv.org/pdf/1709.05557v1.pdf
PWC	https://paperswithcode.com/paper/speech-dereverberation-using-nonnegative
Repo
Framework