Conference Papers

TRUST: Transportation and Road Monitoring System for Ubiquitous Real-Time Information Services

Almeida J.; Rufino J.; Cardoso F.; Gomes M.; Ferreira J.

2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring)

2020

Abstract:

This paper presents the main design decisions and the architecture layout of TRUST project. The main goal of the project is to develop a weather monitoring system for road infrastructures, in order to identify potential hazards for driving and the consequent generation of alerts and recommendations for vehicle users and traffic management centers. Hybrid vehicular communications (3G/4G + ETSI ITS-G5) among vehicles, roadside infrastructure and cloud servers are employed with the aim of collecting sensor information and disseminating warning messages to the drivers in risky locations (e.g. aquaplaning, fog, floods), thus reducing the number of accidents and associated fatalities. The three layers of the system (sensor, communications and information) are described in detail, together with the applications and services that the project will deploy.

Tsallis kernels on measures

Martins A.F.T., Aguiar P.M.Q., Figueiredo M.A.T.

2008 IEEE Information Theory Workshop, ITW

2008

Abstract:

Recent approaches to classification of text, images, and other types of structured data, launched the quest for positive definite (p.d.) kernels on probability measures. In particular, kernels based on the Jensen-Shannon (JS) divergence and other information-theoretic quantities have been proposed. We introduce new JS-type divergences, by extending its two building blocks: convexity and Shannonpsilas entropy. These divergences are then used to define new information-theoretic kernels on measures. In particular, we introduce a new concept of q-convexity, for which a Jensen q-inequality is proved. Based on this inequality, we introduce the Jensen-Tsallis q-difference, a nonextensive generalization of the Jensen-Shannon divergence. Furthermore, we provide denormalization formulae for entropies and divergences, which we use to define a family of nonextensive information-theoretic kernels on measures. This family, grounded in nonextensive entropies, extends Jensen-Shannon divergence kernels, and allows assigning weights to its arguments.

Turbo parsers: Dependency parsing by approximate variational inference

Martins A.F.T., Smith N.A., Xing E.P., Aguiar P.M.Q., Figueiredo M.A.T.

EMNLP 2010 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

2010

Abstract:

We present a unified view of two state-of-theart non-projective dependency parsers, both approximate: the loopy belief propagation parser of Smith and Eisner (2008) and the relaxed linear program of Martins et al. (2009). By representing the model assumptions with a factor graph, we shed light on the optimization problems tackled in each method. We also propose a new aggressive online algorithm to learn the model parameters, which makes use of the underlying variational representation. The algorithm does not require a learning rate parameter and provides a single framework for a wide family of convex loss functions, including CRFs and structured SVMs. Experiments show state-of-the-art performance for 14 languages.

Turning on the turbo: Fast third-order non-projective turbo parsers

Martins A.F.T., Almeida M.B., Smith N.A.

ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

2013

Abstract:

We present fast, accurate, direct non-projective dependency parsers with third-order features. Our approach uses AD3, an accelerated dual decomposition algorithm which we extend to handle specialized head automata and sequential head bigram models. Experiments in fourteen languages yield parsing speeds competitive to projective parsers, with state-of-The-art accuracies for the largest datasets (English, Czech, and German).

TVR – Tall vehicle relayingin vehicular networks

Boban M., Meireles R., Barros J., Steenkiste P., Tonguz O.K.

IEEE Transactions on Mobile Computing

2014

Abstract:

Vehicle-to-Vehicle (V2V) communication is a core technology for enabling safety and non-safety applications in next generation intelligent transportation systems. Due to relatively low heights of the antennas, V2V communication is often influenced by topographic features, man-made structures, and other vehicles located between the communicating vehicles. On highways, it was shown experimentally that vehicles can obstruct the line of sight (LOS) communication up to 50 percent of the time; furthermore, a single obstructing vehicle can reduce the power at the receiver by more than 20 dB. Based on both experimental measurements and simulations performed using a validated channel model, we show that the elevated position of antennas on tall vehicles improves communication performance. Tall vehicles can significantly increase the effective communication range, with an improvement of up to 50 percent in certain scenarios. Using these findings, we propose a new V2V relaying scheme called tall vehicle relaying (TVR) that takes advantage of better channel characteristics provided by tall vehicles. TVR distinguishes between tall and short vehicles and, where appropriate, chooses tall vehicles as next hop relays. We investigate TVR’s system-level performance through a combination of link-level experiments and system-level simulations and show that it outperforms existing techniques.

Two/too simple adaptations of Word2Vec for syntax problems

Ling W., Dyer C., Black A., Trancoso I.

NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

2015

Abstract:

We present two simple modifications to the models in the popular Word2Vec tool, in order to generate embeddings more suited to tasks involving syntax. The main issue with the original models is the fact that they are insensitive to word order. While order independence is useful for inducing semantic representations, this leads to suboptimal results when they are used to solve syntax-based problems. We show improvements in part-ofspeech tagging and dependency parsing using our proposed models.

Ubiquitous mobile instrumentation

Ferreira D., Koehler C., Karapanos E., Kostakos V.

UbiComp 2013 Adjunct - Adjunct Publication of the 2013 ACM Conference on Ubiquitous Computing

2013

Abstract:

Mobile phones allow us to reach people anywhere, at anytime. In addition to the benefits for end users, researchers and developers can also benefit from the powerful devices that participants carry on a daily basis. Collectively, mobile phones form a ubiquitous computer. Ubiquitous Mobile Instrumentation (UbiMI) workshop focuses on using mobile devices as instruments to collect data and conduct mobile user studies, to understand human behavior, routines and gathering users’ context.

Ultra-dense Low Data Rate (UDLD) Communication in the THz

Singh R., Sicker D.

ACM International Conference on Nanoscale Computing and Communication,

2020

Abstract:

In the future, with the advent of the Internet of Œings (IoT), wireless sensors, and multiple 5G applications yet to be developed, an indoor room might be €lled with 1000s of devices. Œese devices will have di‚erent ‹ality of Service (QoS) demands and resource constraints, such as mobility, hardware, and eciency requirements. Œe THz band has a massive green€eld spectrum and is envisioned to cater to these dense-indoor deployments. However, THz has multiple caveats, such as high absorption rate, limited coverage range, low transmit power, sensitivity to mobility, and frequent outages, making it challenging to deploy. THz might compel networks to be dependent on additional infrastructure, which might not be pro€table for network operators and can even result in inecient resource utilization for devices demanding low to moderate data rates. Using distributed Device-to-Device (D2D) communication in the THz, we can cater to these ultra-dense low data rate type applications in a constrained resource situation. We propose a 2-Layered distributed D2D model, where devices use coordinated multi-agent reinforcement learning (MARL) to maximize eciency and user coverage for dense-indoor deployment. We explore the choice of features required to train the algorithms and how it impacts the system eciency. We show that densi€cation and mobility in a network can be used to further the limited coverage range of THz devices, without the need for extra infrastructure or resources.

UnchartIt: An Interactive Framework for Program Recovery from Charts

Ramos D., Pereira J., Lynce I., Manquinho V., Martins R.

ASE 2020

2020

Abstract:

Charts are commonly used for data visualization. Generating a chart usually involves performing data transformations, including data pre-processing and aggregation. These tasks can be cumbersome and time-consuming, even for experienced data scientists. Reproducing existing charts can also be a challenging task when information about data transformations is no longer available. In this paper, we tackle the problem of recovering data transformations from existing charts. Given an input table and a chart, our goal is to automatically recover the data transformation program underlying the chart. We divide our approach into four steps: (1) data extraction, (2) candidate generation, (3) candidate ranking, and (4) candidate disambiguation. We implemented our approach in a tool called UnchartIt and evaluated it on a set of $50$ benchmarks from Kaggle. Experimental results show that UnchartIt successfully ranks the correct data transformation program in the top-10 in $92%$ of the instances. To disambiguate those programs, we use our new interactive disambiguation procedure, which successfully returns the correct program on 98% of the ambiguous instances by asking on average fewer than 2 questions to the user.