Conference Papers

The entropy penalized minimum energy estimator

Pequito S., Aguiar A.P., Gomes D.A.

Proceedings of the IEEE Conference on Decision and Control

2009

Abstract:

This paper addresses the state estimation problem of nonlinear systems. We formulate the problem using a minimum energy estimator (MEE) approach and propose an entropy penalized scheme to approximate the viscosity solution of the Hamilton-Jacobi equation that follows from the MEE formulation. We derive an explicit observer algorithm that is iterative and filtering-like, which continuously improves the state estimation as more measurements arise. In addition, we propose a computationally efficient procedure to estimate the state by performing an approximation of the nonlinear system along the trajectory of the estimate. In this case, for the first and second order approximations of the state equation, we derive a closed-form (iterative) solution for the Hessian of the entropy-like version of the optimal cost function of the MEE. We illustrate and contrast the performance of our algorithms with the extended Kalman filter (EKF) using specific nonlinear examples with the feature that the EKF do not converge to the correct value.

The Explanation Game: Towards Prediction Explainability through Sparse Communication

Treviso M., Martins A.

Proc. Blackbox NLP workshop

2020

Abstract:

Explainability is a topic of growing importance in NLP. In this work, we provide a unified perspective of explainability as a communication problem between an explainer and a layperson about a classifier’s decision. We use this framework to compare several prior approaches for extracting explanations, including gradient methods, representation erasure, and attention mechanisms, in terms of their communication success. In addition, we reinterpret these methods at the light of classical feature selection, and we use this as inspiration to propose new embedded methods for explainability, through the use of selective, sparse attention. Experiments in text classification, natural language entailment, and machine translation, using different configurations of explainers and laypeople (including both machines and humans), reveal an advantage of attention-based explainers over gradient and erasure methods. Furthermore, human evaluation experiments show promising results with post-hoc explainers trained to optimize communication success and faithfulness.

The impact of ECDSA in a VANET routing service: Insights from real data traces

Cirne P., Zúquete A., Sargento s., Luísa M.

Ad Hoc Networks - Available online 28 August 2018

2018

Abstract:

Both the WAVE IEEE 1609.2 standard in USA and the ETSI ITS security standards in Europe rely on the Elliptic Curve Digital Signature Algorithm (ECDSA) to authenticate messages exchanged among vehicles. Although being faster than other equivalent algorithms, the ECDSA computational cost nevertheless affects the message validation throughput. Even worse, the number of messages that a device has to authenticate may easily exhaust its computational limits. In this article, we evaluated the impact caused by ECDSA authentication of messages of the multi-hop routing control plane used in a real Vehicular Ad Hoc Network (VANET). Such control plane uses periodic vicinity updates to keep accurate, distributed routing paths, and ECDSA-based validation delays may force to discard many of such updates. To perform the evaluation of the impact imposed by ECDSA we considered the multiple curve parameters associated to WAVE and ETSI ITS, their implementation by different cryptographic libraries and their performance in distinct hardware. We took as reference for traffic to be authenticated with ECDSA a day-long set of messages of a VANET routing control plane. These messages were inferred from connectivity status samples from all mobile nodes of a real VANET. Emulation results with those messages show that, without high-end computing devices, ECDSA authentication would have a substantial negative impact in the routing service of the tested VANET. Keywords VANETBroadcast authenticationECDSAPerformance evaluation

The impact of social media on business performance

Martin S., Serban M.

ECIS 2013 - Proceedings of the 21st European Conference on Information Systems

2013

Abstract:

Social media are gaining popularity and are increasingly used in regular operations of many companies, including start-ups, small, medium-sized, and large organizations. The purpose of this research is to explore the impact of social media and to analyze to what extent social media have impact on organizational capabilities and business performance. We develop a research model and two simple propositions based on the resource based view of the firm. We analyze the impact of six social media applications on six business capabilities and on business performance in SponsorPay, a start-up company since 2009 in the on-line game advertising industry. We use a mixed research method including qualitative analysis based on interviews and quantitative analysis based on a survey among 60 employees. We find that the use of social media enhances business capabilities and business performance. The impact is not due to one (out of six) social media tools only, but due to successfully combining the six social media tools into one effective social media ecosystem that enables coordination between internal and external business processes.

The Partial View Heat Kernel descriptor for 3D object representation

Brandao S., Costeira J.P., Veloso M.

Proceedings - IEEE International Conference on Robotics and Automation

2014

Abstract:

We introduce the Partial View Heat Kernel (PVHK) descriptor, for the purpose of 3D object representation and recognition from partial views, assumed to be partial object surfaces under self occlusion. PVHK describes partial views in a geometrically meaningful way, i.e., by establishing a unique relation between the shape of the view and the descriptor. PVHK is also stable with respect to sensor noise and therefore adequate for sensors, such as the current active 3D cameras. Furthermore, PVHK takes full advantage of the dual 3D/RGB nature of current sensors and seamlessly incorporates appearance information onto the 3D information. We formally define the PVHK descriptor, discuss related work, provide evidence of the PVHK properties and validate them in three purposefully diverse datasets, and demonstrate its potential for recognition tasks.

The Power of a Hand-shake in Human-Robot Interactions

Avelino J., Correia F., Catarino J., Ribeiro P., Moreno P., Bernardino A., Paiva A.

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

2018

Abstract:

In this paper, we study the influence of a handshake in the human emotional bond to a robot. In particular, we evaluate the human willingness to help a robot whether the robot first introduces itself to the human with or without a handshake. In the tested paradigm the robot and the human have to perform a joint task, but at a certain stage, the robot needs help to navigate through an obstacle. Without requesting explicit help from the human, the robot performs some attempts to navigate through the obstacle, suggesting to the human that it requires help. In a study with 45 participants, we measure the human’s perceptions of the social robot Vizzy, comparing the handshake vs non-handshake conditions. In addition, we evaluate the influence of a handshake in the pro-social behaviour of helping it and the willingness to help it in the future. The results show that a handshake increases the perception of Warmth, Animacy, Likeability, and the tendency to help the robot more, by removing the obstacle.

The role of peer influence in churn in wireless networks

Han Q., Ferreira P.

ACM International Conference Proceeding Series

2014

Abstract:

Subscriber churn remains a top challenge for wireless carriers. These carriers need to understand the determinants of churn to confidently apply effective retention strategies to ensure their profitability and growth. In this paper, we look at the effect of peer influence on churn and we try to disentangle it from other effects that drive simultaneous churn across friends but that do not relate to peer influence. We analyze a random sample of roughly 10 thousand subscribers from large dataset from a major wireless carrier over a period of 10 months. We apply survival models and generalized propensity score to identify the role of peer influence. We show that the propensity to churn increases when friends do and that it increases more when many strong friends churn. Therefore, our results suggest that churn managers should consider strategies aimed at preventing group churn. We also show that survival models fail to disentangle homophily from peer influence over-estimating the effect of peer influence.

The Usability Argument for Refinement Typed Genetic Programming

Fonseca A., Santos P., Silva S.

International Conference on Parallel Problem Solving from Nature

2020

Abstract:

The performance of Evolutionary Algorithms is frequently hindered by arbitrarily large search spaces. In order to overcome this challenge, domain-specific knowledge is often used to restrict the representation or evaluation of candidate solutions to the problem at hand. Due to the diversity of problems and the unpredictable performance impact, the encoding of domain-specific knowledge is a frequent problem in the implementation of evolutionary algorithms. We propose the use of Refinement Typed Genetic Programming, an enhanced hybrid of Strongly Typed Genetic Programming (STGP) and Grammar-Guided Genetic Programming (GGGP) that features an advanced type system with polymorphism and dependent and refined types. We argue that this approach is more usable for describing common problems in machine learning, optimisation and program synthesis, due to the familiarity of the language (when compared to GGGP) and the use of a unifying language to express the representation, the phenotype translation, the evaluation function and the context in which programs are executed.

TherML: Occupancy prediction for thermostat control

Koehler C., Ziebart B.D., Mankoff J., Dey A.K.

UbiComp 2013 - Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing

2013

Abstract:

Reducing the large energy consumption of temperature regulation systems is a challenge for researchers and practitioners alike. In this paper, we explore and compare two common types of solutions: A manual systems that encourages reduced energy use, and an intelligent automatic control system. We deployed an eco-feedback system with the ability to remotely control one’s thermostat to ten participants for three months. Participants appreciated the ability to remotely control the thermostat, and controlled their heating system with 78.8% accuracy, a 6.3% improvement over not having this system. However, despite having feedback and remote control, they still wasted a lot of energy heating when away from home for the day. Using data from our deployment, we developed TherML, an occupancy prediction algorithm that uses GPS data from a user’s smartphone to automatically control the indoor temperature of a home with 92.1% accuracy. We compare TherML to other state-of-the-art techniques, and show that the higher accuracy of our approach optimizes both energy usage and user comfort. We end with recommendations for a mixed initiative system that leverages aspects of both the manual and automated approaches that can better match heating control to users’ routines and preferences.