Roberto Yus

University of Maryland, Baltimore County | UMBC · Department of Computer Science and Electrical Engineering

Location-Based Services (LBSs) are attracting great interest nowadays, mainly due to the economic value they can provide. So, different applications are being developed for tracking, navigation, advertising, etc., but most of those applications are designed for specific scenarios and goals with implicit knowledge about the application context. Howe...

FaceBlock takes regular pictures taken by your smartphone or Google Glass as input and converts them into Privacy-Aware Pictures. These pictures are generated by using a combination of Face Detection and Face Recognition algorithms. By using FaceBlock, a user can take a picture of herself and specify her policy/rule regarding pictures taken by othe...

The massive spread of mobile computing in our daily lives has attracted a huge community of mobile application (apps) developers. These developers can take advantage of the benefits of semantic technologies (such as knowledge sharing and reusing, and knowledge decoupling) to enhance their applications. Moreover, the use of semantic reasoners would...

This paper describes a middleware framework for IoT smart spaces, SemIoTic, that provides application developers and end-users with the semantic domain-relevant view of the smart space, hiding the complexity of having to deal with/understand lower-level information generated by sensors and actuators. SemIoTic uses a meta-model, based on the popular...

This paper considers the challenge of scalable implementation of fine-grained access control over large corpus of policies in database systems. Current approach to enforcing fine-grained policies based on rewriting queries does not scale when number of policies may be in the order of thousands. Our work identifies one such use case in the context o...

Privacy policies inform users about the data management practices of organizations. Yet, their complexity often renders them largely incomprehensible to the average user, necessitating the development of privacy assistants. With the advent of generative AI (genAI) technologies, there is an untapped potential to enhance privacy assistants in answeri...

As the adoption of smart devices continues to permeate all aspects of our lives, concerns surrounding user privacy have become more pertinent than ever before. While privacy policies define the data management practices of their manufacturers, previous work has shown that they are rarely read and understood by users. Hence, automatic analysis of pr...

Non-negative matrix factorization (NMF) with missing-value completion is a well-known effective Collaborative Filtering (CF) method used to provide personalized user recommendations. However, traditional CF relies on a privacy-invasive collection of user data to build a central recommender model. One-shot federated learning has recently emerged as...

This paper presents Sentaur, a middleware designed, built, and deployed to support sensor-based smart space analytical applications. Sentaur supports a powerful data model that decouples semantic data (about the application domain) from sensor data (using which the semantic data is derived). By supporting mechanisms to map/translate data, concepts,...

Emerging domains, such as sensor-driven smart spaces and social media analytics, require incoming data to be enriched prior to its use. Enrichment often consists of machine learning (ML) functions that are too expensive/infeasible to execute at ingestion. We develop a strategy entitled Just-in-time ENrichmeNt in quERy Processing (JENNER) to support...

Non-negative matrix factorization (NMF) with missing-value completion is a well-known effective Collaborative Filtering (CF) method used to provide personalized user recommendations. However, traditional CF relies on the privacy-invasive collection of users' explicit and implicit feedback to build a central recommender model. One-shot federated lea...

Smart space administration and application development is challenging in part due to the semantic gap that exists between the high-level requirements of users and the low-level capabilities of IoT devices. The stakeholders in a smart space are required to deal with communicating with specific IoT devices, capturing data, processing it, and abstract...

This artifact abstract is a guideline for SmartSPEC, a simulator for generating customizable smart space datasets using semantic models of spaces, people, events and sensors. SmartSPEC is based on two main components: (i) Scenario Learning which produces metamodels of events and people using input seed data; and (ii) Scenario Generation which uses...

This paper presents SmartSPEC, an approach to generate customizable smart space datasets using sensorized spaces in which people and events are embedded. Smart space datasets are critical to design, deploy and evaluate robust systems and applications to ensure cost-effective operation and safety/comfort/convenience of the space occupants. Often, re...

This paper explores the data cleaning challenges that arise in using WiFi connectivity data to locate users to semantic indoor locations such as buildings, regions, rooms. WiFi connectivity data consists of sporadic connections between devices and nearby WiFi access points (APs), each of which may cover a relatively large area within a building. Ou...

This paper describes the collaborative effort between privacy and security researchers at nine different institutions along with researchers at the Naval Information Warfare Center to deploy, test, and demonstrate privacy-preserving technologies in creating sensor-based awareness using the Internet of Things (IoT) aboard naval vessels in the contex...

Current approaches for enforcing Fine Grained Access Control (FGAC) in DBMS do not scale to scenarios when the number of access control policies are in the order of thousands. This paper identifies such a use case in the context of emerging smart spaces wherein systems may be required by legislation, such as Europe’s GDPR and California’s CCPA, to...

This paper proposes SmartBench, a benchmark focusing on queries resulting from (near) real-time applications and longer-term analysis of IoT data. SmartBench, derived from a deployed smart building monitoring system, is comprised of: 1) An extensible schema that captures the fundamentals of an IoT smart space; 2) A set of representative queries foc...

Location-Based Services (LBS) are attracting a great interest with the fast expansion of mobile computing nowadays. These services use the user location to customize the offered information. However, most of those services are designed for specific scenarios and goals with implicit knowledge about the application context. As a consequence, hundreds...

This paper explores the data cleaning challenges that arise in using WiFi connectivity data to locate users to semantic indoor locations such as floors, regions, rooms, etc. WiFi connectivity data consists of sporadic connections between devices and nearby WiFi access points (APs), each of which may cover a relatively large area within a building....

This demonstration showcases the SemIoTic middleware [2] which provides inhabitants of an IoT space, as well as developers of applications , with a semantic view of the space. Participants will have an opportunity to see how useful IoT applications can be easily developed focusing on describing what information is needed without having to deal with...

Modern information systems often collect raw data in the form of text, images, video, and sensor readings. Such data needs to be further interpreted/enriched prior to being analyzed. Enrichment is often a result of automated machine learning and or signal processing techniques that associate appropriate but uncertain tags with the data. Traditional...

Emerging IoT technologies promise to bring revolutionary changes to many domains including health, transportation, and building management. However, continuous monitoring of individuals threatens privacy. The success of IoT thus depends on integrating privacy protections into IoT infrastructures. This demonstration adapts a recently-proposed system...

Current buildings rely on predefined rules to control the temperature in rooms disregarding their residents' thermal comfort. Multiple approaches have been presented in the literature to tackle this issue (e.g., by enabling occupants to express their feedback using their mobile devices). In general setting, to reach consensus among group members, w...

The Internet of Things (IoT) is changing the way we interact with our environment in domains as diverse as health, transportation, office buildings and our homes. In smart building environments, information captured about the building and its inhabitants will aid in development of services that improve productivity, comfort, social interactions, sa...

The Internet of Things (IoT) is changing the way we interact with our environment in domains as diverse as health, transportation, office buildings and our homes. In smart building environments, information captured about the building and its inhabitants will aid in development of services that improve productivity, comfort, social interactions, sa...

In the last decade, we have witnessed the birth and spread of the Semantic Web and its associated semantic technologies. In this successful scenario, ontologies have played a crucial role. However, being knowledge representation frameworks as they are, the benefits of their use are beyond the WWW, but to many other different kind of systems, making...

Semantic textual similarity is a measure of the degree of semantic equivalence between two pieces of text. We describe the SemSim system and its performance in the *SEM 2013 and SemEval-2014 tasks on semantic textual similarity. At the core of our system lies a robust distributional word similarity component that combines Latent Semantic Analysis a...

Mobile devices have penetrated our daily lives and currently smartphones and tablets are everywhere. These devices are equipped with different sensors which enable them to capture multimedia information (e.g., several cameras and microphone). Therefore, today is easier than ever to count with a device which could capture information of interest in...

Structured data extracted from the Web is highly heterogeneous due to its disparate origins and nature. There exist some techniques to integrate this information based on the extraction of synonymy relationships among the different entities involved. However, synonymy is a very strict and therefore uncommon relationship. We present a novel approach...

In this paper we introduce a network of static and mobile agents which collaborate to process information requests by mobile users. The agents help users to define their information needs, process their requests by deploying themselves on devices near the information requested, and obtain results from users and their mobile devices, in a continuous...

With the widespread availability of cheap but powerful mobile devices and high-speed mobile Internet, we are witnessing an unprecedented growth in the number of mobile applications (apps). In this paper, we present a systematic review of mobile apps which use Semantic Web technologies. We analyzed more than 400 papers from proceedings of important...

The number of mobile applications (apps) in major app stores exceeded one million in 2013. While app stores provide a central point for storing app metadata, they often impose restrictions on the access to this information thus limiting the potential to develop tools to search, recommend, and analyze app information. A few projects have circumvente...

We present Mobipedia, an integrated knowledge base with information about 1 million mobile applications (apps) such as their category , meta-data (author, reviews, rating, release date), permissions and libraries used, and similar apps. The goal of Mobipedia is to integrate unstructured and semi-structured data about mobile apps from publicly avail...

Mobile devices are ubiquitous and, due to their increasing number of sensors and their powerful features, enable users to consume and produce huge amounts of highly-dynamic data (such as location data, other devices in range, and another local context information recollected by sensors). Semantic techniques can be applied to offer smart data to the...

The advantage of using semantic reasoners based on Description Logics (DL) for the development of intelligent systems is doubtless: They make easy the optimal management of knowledge (expressed as ontologies). Reasoning is a complex and computationally expensive task traditionally performed on powerful server and desktop computers. However, we shou...

For a Technical Director (TD) in charge of a live broadcasting, selecting the best camera shots among the available video sources is a challenging task, even more now that the number of cameras (some of them mobile, or attached to moving objects) in the broadcasting of sport events is increasing. So, the TD needs to manage a great amount of continu...

Emergency management has attracted the focus of mobile computing research in the last years due to the flexibility that it provides in critical scenarios. The lack of a pre-existing infrastructure or even a communication breakdown are important issues that mobile computing can deal with. In addition, Semantic Web techniques to handle the data in th...

The emergence of low-cost cameras with nearly professional features in the consumer market represents a new important source of video information. For example, using an increasing number of these cameras in live TV broadcastings enables obtaining varied contents without affecting the production costs. However, searching for interesting shots (e.g.,...

Community Health Workers (CHWs) act as liaisons between health-care providers and patients in underserved or un-served areas. However, the lack of information sharing and training support impedes the effectiveness of CHWs and their ability to correctly diagnose patients. In this paper, we propose and describe a system for mobile and wearable comput...

Infoboxer uses statistical and semantic knowledge from linked data sources to ease the process of creating Wikipedia infoboxes. It creates dynamic and semantic templates by suggesting attributes common for similar articles and controlling the expected values semantically.

Wearable computing devices like Google Glass are at the forefront of technological evolution in smart devices. The ubiquitous and oblivious nature of photography using these devices has made people concerned about their privacy in private and public settings. The Face-Block (http://face-block.me/) project protects the privacy of people around Glass...

Capturing, maintaining, and using context information helps mobile applications provide better services and generates data useful in specifying information sharing policies. Obtaining the full benefit of con-text information requires a rich and expressive representation that is grounded in shared semantic models. We summarize some of our past work...

We describe UMBC's systems developed for the SemEval 2014 tasks on Multi-lingual Semantic Textual Similarity (Task 10) and Cross-Level Semantic Similarity (Task 3). Our best submission in the Multilingual task ranked second in both English and Spanish subtasks using an unsupervised approach. Our best sys-tems for Cross-Level task ranked second in P...

Applications for mobile devices could often show a more intelligent behavior by using a semantic reasoner to discover new knowledge. Unfortunately, using Description Logic reasoners on Android devices is not trivial. In this paper we continue our previous work on investigating the use of semantic reasoners on mobile devices. In particular, we port...

The massive spread of mobile computing in our daily lives has attracted a huge community of mobile apps developers. These developers can take advantage of the benefits of semantic technologies (such as knowledge sharing and reusing, knowledge decoupling, etc.) to enhance their applications. Moreover, the use of semantic reasoners would enable them...

Nowadays people are exposed to huge amounts of information that are generated continuously. However, current mobile applications, Web pages, and Location-Based Services (LBSs) are designed for specific scenarios and goals. In this demo we show the system SHERLOCK, which searches and shares up-to-date knowledge from nearby devices to relieve the use...

The production costs of broadcasting sport events that require tracking moving objects are continuously increasing. Although those events are very demanded by the audience, broadcasting organizations have economical difficulties to afford them. For that reason, they are demanding the development of new professional software and hardware equipments...

In this demo paper we present MultiCAMBA (Multi-CAMera Broadcasting Assistant), a contex and location aware system that, using a 3D model updated continuously with real-time data retrieved from the scenario, helps technical directors (TDs) in the live broadcasting task. They can indicate in run-time their interest in certain moving objects or geogr...

Broadcasting sport events in live is a challenging task because obtaining the best views requires taking into account many dynamic factors, such as: the location and movement of interesting objects, all the views provided by cameras in the scenario (some of them wireless, mobile, or attached to moving objects), possible occlusions, etc. Therefore,...