Cloud based Social and Sensor Data Fusion

As mobile cloud computing facilitates a wide spectrum of smart applications, the need for fusing various types of data available in the cloud grows rapidly. In particular, social and sensor data lie at the core in such applications, but typically processed separately. This paper explores the potential of fusing social and sensor data in the cloud, presenting a practice---a travel recommendation system that offers the predicted mood information of people on where and when users wish to travel. The system is built upon a conceptual framework that allows to blend the heterogeneous social and sensor data for integrated analysis, extracting weather-dependant people's mood information from Tweeter and meteorological sensor data streams. In order to handle massively streaming data, the system employs various cloud-serving systems, such as Hadoop, HBase, and GSN. Using this scalable system, we performed heavy ETL as well as filtering jobs, resulting in 12 million tweets over four months. We then derived a rich set of interesting findings through the data fusion, proving that our approach is effective and scalable, which can serve as an important basis in fusing social and sensor data in the cloud.

Social and Sensor Data Fusion in the Cloud

Karl Aberer, Ho Young Jeung, Jonnahtan Eduardo Saltarin De Arco, Surender Reddy Yerva

As mobile cloud computing facilitates a wide spectrum of smart applications, the need for fusing various types of data available in the cloud grows rapidly. In particular, social and sensor data lie at the core in such applications, but typically processed separately. This paper explores the potential of fusing social and sensor data in the cloud, presenting a practice—a travel recommendation system that offers the predicted mood information of people on where and when users wish to travel. The system is built upon a conceptual framework that allows to blend the heterogeneous social and sensor data for integrated analysis, extracting weather-dependant people’s mood information from Twitter and meteorological sensor data streams. In order to handle massively streaming data, the system employs various cloud-serving systems, such as Hadoop, HBase, and GSN.

2012

Mobility-centric design of collaborative transportation systems

Embedded sensors and actuators are revolutionizing the way we perceive and interact with the physical world. Current research on such Cyber-Physical Systems (CPSs) has focused mostly on distributed sensing and data gathering. The next step is to move from passive information extraction from the physical world towards an active framework where information is retrieved, processed, and acted upon in situ. As an example of such sensor-actuator systems that provide large-scale, distributed coordination, we consider Intelligent Transportation Systems (ITSs), with the goal of increasing travel safety and efficiency. The proliferation of wireless technologies enables different actors (e.g., pedestrians, motorists, traffic operators) to communicate with each other cheaply, efficiently, and securely. By embedding computational intelligence, communication and control into such ITSs, it will be possible to build collaborative transportation applications that help solve, for example, congestion and parking problems. This thesis explores the following question: To what extent is it possible to build distributed ITS systems that rely exclusively on local communication between nodes? The potential benefits of building such systems without infrastructure are numerous, including lower fixed and variable costs, avoiding regulatory hurdles, lower entry barriers for new players, and more control over privacy. On the other hand, self-organized ITSs without infrastructure have to operate under challenging conditions: large scale, high mobility, lack of end-to-end connectivity, ephemeral contacts between wireless nodes, and heterogeneous node capabilities. Although the networking research community has invested a significant effort in designing service abstractions that mimic traditional IP connectivity on top of wireless ad hoc networks, the ITS scenarios considered in this work are too challenging to implement such a service model. The main goal of this thesis is to design communication service models and their underlying protocols that can operate in collaborative transportation applications, and to demonstrate their effectiveness through analysis of traffic data and through realistic simulations. A key point is that the ITS applications we consider can rely on more limited service primitives, because they do not require a general any-to-any delivery service with strict performance guarantees. We first define the collaborative transportation applications of interest. Then we quantify their potential benefits and discuss their functional requirements. Next, we focus on the problem of the collection of large-scale mobility data. We propose a new method for collecting such data and introduce a novel mobility data mining framework, which is necessary to study collective mobility patterns in the context of wireless ad hoc networking. Relying on the analysis of real-life mobility traces, we find that despite the high node mobility, clusters of time-stable connectivity emerge and last at specific locations. Outside such clusters the connectivity between nodes remains sparse. This leads us to the proposal of a new mobility model that captures in an elegant way two phenomena observed in reality, i.e., emergence of stable clusters and network partitioning. This mobility model, called Heterogeneous Random Walk (HRW), appears to be the worst-case mobility model for many mobility-assisted protocols. Moreover, we show that the HRW mobility model predicts the performance of an epidemic dissemination protocol more accurately than other, similarly parsimonious models. Based on the lessons learned from the mobility data analysis, we propose a new abstraction that allows us to capture collective mobility patterns. This abstraction, called a Mobility Map, can be shared globally among mobile nodes and it can be used to improve communication in mobile partitioned networks (MPNs). Notably, we present a new geocasting protocol called GeoMobCast, which uses Mobility Maps to minimize message delay. This protocol is designed to provide the users of the collective transportation applications with the required communication service. Finally, we turn our attention on the real-life implementation of the distributed ITS that leverage short-range wireless communication. To this extent, we present the results of our experimental work with wireless sensor network technologies. We also present the necessary simulation toolbox designed to implement and evaluate collaborative transportation applications.

EPFL2009

Textual Explanations and Critiques in Recommendation Systems

Diego Matteo Antognini

Artificial intelligence and machine learning algorithms have become ubiquitous. Although they offer a wide range of benefits, their adoption in decision-critical fields is limited by their lack of interpretability, particularly with textual data. Moreover, with more data available than ever before, it has become increasingly important to explain automated predictions.Generally, users find it difficult to understand the underlying computational processes and interact with the models, especially when the models fail to generate the outcomes or explanations, or both, correctly. This problem highlights the growing need for users to better understand the models' inner workings and gain control over their actions. This dissertation focuses on two fundamental challenges of addressing this need. The first involves explanation generation: inferring high-quality explanations from text documents in a scalable and data-driven manner. The second challenge consists in making explanations actionable, and we refer to it as critiquing. This dissertation examines two important applications in natural language processing and recommendation tasks.First, we present two models for extracting high-quality and personalized justifications from text documents under the paradigm of selective rationalization - a binary selection of input features from which the model computes the outcome. We propose the concept of multi-dimensional rationales and emphasize that a single overall selection does not accurately capture the multi-faceted nature of useful rationales. The first method relies on multi-task learning and learns the rationales in an unsupervised manner, with no prior in the data. Inspired by the role of concept-based thinking in human reasoning, our second model is a generalization: it assumes that only one label is observed. We empirically demonstrate the efficiency of the models in terms of explanation and predictive performance as well as their scalability. It opens new doors for applications, such as recommendation or summarization.Second, we use the high-level idea of multi-dimensional rationalization to mine massive corpora and construct large personalized justification datasets. We show that human users significantly prefer our explanations over those produced by state-of-the-art methods.Last, we propose two conversational explainable recommendation systems. The first explains a user rating by inferring a set of keyphrases. Conditioned on them, it generates an abstractive personal justification. We allow users to interact iteratively with the explanations and refine the recommendation through an unsupervised critiquing method. Our second model is based on multimodal modeling and self-supervision. It enables fast and efficient multi-step critiquing. Using real-world datasets, we show that our models exhibit better performance than state-of-the-art models in terms of recommendation, explanation, and critiquing.Overall, we demonstrate that interpretability does not come at the cost of reduced performance in two consequential applications. Our framework is applicable to other fields as well. This dissertation presents an effective means of closing the gap between promise and practice in artificial intelligence.

EPFL2022

Mobility-centric design of collaborative transportation systems

EPFL2009

Textual Explanations and Critiques in Recommendation Systems

Diego Matteo Antognini

EPFL2022