Accurate and large-scale privacy-preserving data mining using the election paradigm

With the proliferation of the Web and ICT technologies there have been concerns about the handling and use of sensitive information by data mining systems. Recent research has focused on distributed environments where the participants in the system may also be mutually mistrustful. In this paper we discuss the design and security requirements for large-scale privacy-preserving data mining (PPDM) systems in a fully distributed setting, where each client possesses its own records of private data. To this end we argue in favor of using some well-known cryptographic primitives, borrowed from the literature on Internet elections. More specifically, our framework is based on the classical homomorphic election model, and particularly on an extension for supporting multi-candidate elections. We also review a recent scheme [Z. Yang, S. Zhong, R.N. Wright, Privacy-preserving classification of customer data without loss of accuracy, in: SDM’ 2005 SIAM International Conference on Data Mining, 2005] which was the first scheme that used the homomorphic encryption primitive for PPDM in the fully distributed setting. Finally, we show how our approach can be used as a building block to obtain Random Forests classification with enhanced prediction performance.     

Design, Implementation and Validation of an Open Source IP-PBX/VoIP Gateway Multi-Core SoC

The telephony world is consistently moving to the transmission of voice through packet networks, so as to unify data and voice and to enable the provisioning of new services in a less costly manner. Service providers are offloading the task of converting analog voice to VoIP to the end-points. In this paper we present an IP-PBX/VoIP Gateway system based on a single, multi-core SoC that performs all the required processing. The system targets the low density market of home gateways and SME IP-PBXs, where cost is the main factor. We prove it is feasible to implement a 4-channel IP-PBX/VoIP gateway on a SoC based purely on both software and hardware provided by the open-source community, reducing both upfront and final product costs thus allowing new players into the market. The highly configurable design allows the integration of multiple embedded cores in the same die increasing channel density while reducing clock cycles per channel. The idea of using one or more open-source embedded cores can be extended to many different applications requiring moderate DSP performance, resulting in a “DSP-free”, low-cost system, with minimal design effort.     

KnowBaSICS-M: an ontology-based system for semantic management of medical problems and computerised algorithmic solutions

In this paper, an ontology-based system (KnowBaSICS-M) is presented for the semantic management of Medical Computational Problems (MCPs), i.e., medical problems and computerised algorithmic solutions. The system provides an open environment, which: (1) allows clinicians and researchers to retrieve potential algorithmic solutions pertinent to a medical problem and (2) enables incorporation of new MCPs into its underlying Knowledge Base (KB). KnowBaSICS-M is a modular system for MCP acquisition and discovery that relies on an innovative ontology-based model incorporating concepts from the Unified Medical Language System (UMLS). Information retrieval (IR) is based on an ontology-based Vector Space Model (VSM) that estimates the similarity among user-defined MCP search criteria and registered MCP solutions in the KB. The results of a preliminary evaluation and specific examples of use are presented to illustrate the benefits of the system. KnowBaSICS-M constitutes an approach towards the construction of an integrated and manageable MCP repository for the biomedical research community.     

Finding the K highest-ranked answers in a distributed network

In this paper, we present an algorithm for finding the k highest-ranked (or Top-k) answers in a distributed network. A Top-K query returns the subset of most relevant answers, in place of all answers, for two reasons: (i) to minimize the cost metric that is associated with the retrieval of all answers; and (ii) to improve the recall and the precision of the answer-set, such that the user is not overwhelmed with irrelevant results. Our study focuses on multi-hop distributed networks in which the data is accessible by traversing a network of nodes. Such a setting captures very well the computation framework of emerging Sensor Networks, Peer-to-Peer Networks and Vehicular Networks. We present the Threshold Join Algorithm (TJA), an efficient algorithm that utilizes a non-uniform threshold on the queried attribute in order to minimize the transfer of data when a query is executed. Additionally, TJA resolves queries in the network rather than in a centralized fashion which further minimizes the consumption of bandwidth and delay. We performed an extensive experimental evaluation of our algorithm using a real testbed of 75 workstations along with a trace-driven experimental methodology. Our results indicate that TJA requires an order of magnitude less communication than the state-of-the-art, scales well with respect to the parameter k and the network topology.     

rfid in pervasive computing: State-of-the-art and outlook

rfid has already found its way into a variety of large scale applications and arguably it is already one of the most successful technologies in the history of computing. Beyond doubt, rfid is an effective automatic identification technology for a variety of objects including natural, manufactured and handmade artifacts; humans and other species; locations; and increasingly media content and mobile services. In this survey we consider developments towards establishing rfid as the cost-effective technical solution for the development of open, shared, universal pervasive computing infrastructures and look ahead to its future. In particular, we discuss the ingredients of current large scale applications; the role of network services to provide complete systems; privacy and security implications; and how rfid is helping prototype emerging pervasive computing applications. We conclude by identifying common trends in the new applications of rfid and ask questions related to sustainable universal deployment of this technology.     

Understanding and measuring the urban pervasive infrastructure

The increasing popularity of mobile computing devices has allowed for new research and application areas. Specifically, urban areas exhibit an elevated concentration of such devices enabling potential ad-hoc co-operation and sharing of resources among citizens. Here, we argue that people, architecture and technology together provide the infrastructure for these applications and an understanding of this infrastructure is important for effective design and development. We focus on describing the metrics for describing this infrastructure and elaborate on a set of observation, analysis and simulation methods for capturing, deriving and utilising those metrics.

Can we do without GUIs? Gesture and speech interaction with a patient information system

We have developed a gesture input system that provides a common interaction technique across mobile, wearable and ubiquitous computing devices of diverse form factors. In this paper, we combine our gestural input technique with speech output and test whether or not the absence of a visual display impairs usability in this kind of multimodal interaction. This is of particular relevance to mobile, wearable and ubiquitous systems where visual displays may be restricted or unavailable. We conducted the evaluation using a prototype for a system combining gesture input and speech output to provide information to patients in a hospital Accident and Emergency Department. A group of participants was instructed to access various services using gestural inputs. The services were delivered by automated speech output. Throughout their tasks, these participants could see a visual display on which a GUI presented the available services and their corresponding gestures. Another group of participants performed the same tasks but without this visual display. It was predicted that the participants without the visual display would make more incorrect gestures and take longer to perform correct gestures than the participants with the visual display. We found no significant difference in the number of incorrect gestures made. We also found that participants with the visual display took longer than participants without it. It was suggested that for a small set of semantically distinct services with memorable and distinct gestures, the absence of a GUI visual display does not impair the usability of a system with gesture input and speech output.     

Globally Convergent Modification of the Quickprop Method

A mathematical framework for the convergence analysis of the well-known Quickprop method is described. Furthermore, we propose a modification of this method that exhibits improved convergence speed and stability, and, at the same time, alleviates the use of heuristic learning parameters. Simulations are conducted to compare and evaluate the performance of the new modified Quickprop algorithm with various popular training algorithms. The results of the experiments indicate that the increased convergence rates achieved by the proposed algorithm, affect by no means its generalization capability and stability.     

Detecting objects of variable shape structure with hidden state shape models

This paper proposes a method for detecting object classes that exhibit variable shape structure in heavily cluttered images. The term "variable shape structure" is used to characterize object classes in which some shape parts can be repeated an arbitrary number of times, some parts can be optional, and some parts can have several alternative appearances. Hidden State Shape Models (HSSMs), a generalization of Hidden Markov Models (HMMs), are introduced to model object classes of variable shape structure using a probabilistic framework. A polynomial inference algorithm automatically determines object location, orientation, scale and structure by finding the globally optimal registration of model states with the image features, even in the presence of clutter. Experiments with real images demonstrate that the proposed method can localize objects of variable shape structure with high accuracy. For the task of hand shape localization and structure identification, the proposed method is significantly more accurate than previously proposed methods based on chamfer-distance matching. Furthermore, by integrating simple temporal constraints, the proposed method gains speed-ups of more than an order of magnitude, and produces highly accurate results in experiments on non-rigid hand motion tracking.