The Dendritic Cell Algorithm (DCA) is an immune-inspired algorithm, developed for the purpose of anomaly detection. The algorithm performs multi-sensor data fusion and correlation which results in a 'context aware' detection system. Previous applications of the DCA have included the detection of potentially malicious port scanning activity, where it has produced high rates of true positives and low rates of false positives. In this work we aim to compare the performance of the DCA and of a Self-Organizing Map (SOM) when applied to the detection of SYN port scans, through experimental analysis. A SOM is an ideal candidate for comparison as it shares similarities with the DCA in terms of the data fusion method employed. It is shown that the results of the two systems are comparable, and both produce false positives for the same processes. This shows that the DCA can produce anomaly detection results to the same standard as an established technique.

We present in this paper some examples of how to compute by hand the PCR5 fusion rule for three sources, so the reader will better understand its mechanism. We also take into consideration the importance of sources, which is different from the classical discounting of sources.

Functional or end user requirements are the tasks that the system - Protection and control of consolidated data under development is expected to perform. However, nonfunctional - Data retrieval requirements are the qualities that the system is - Equitable treatment of users to adhere to. Functional requirements are not as difficult - Data retention and disposal to tackle, as it is easier to test their implementation in the - User monitoring and protection against unauthorized system under development. Security and privacy requirements monitoring are considered nonfunctional requirements, although in many instances they do have functionality. To identify Several laws and regulations provide a set of guidelines privacy risks early in the design process, privacy requirements that can be used to assess privacy risks. For example, engineering is used (Chiasera et al. 2008). However, the Health Insurance Portability and Accountability Act unlike security requirements engineering, little attention is (HIPAA) addresses privacy concerns of health information paid to privacy requirements engineering, thus it is less mature systems by enforcing data exchange standards.

Data integration is a critical problem in our increasingly interconnected but inevitably heterogeneous world. There are numerous data sources available in organizational databases and on public information systems like the World Wide Web. Not surprisingly, the sources often use different vocabularies and different data structures, being created, as they are, by different people, at different times, for different purposes. The goal of data integration is to provide programmatic and human users with integrated access to multiple, heterogeneous data sources, giving each user the illusion of a single, homogeneous database designed for his or her specific need. The good news is that, in many cases, the data integration process can be automated.

The field of artificial immune systems (AISs) is an emerging biologically-inspired method which builds systems based on algorithms inspired by the biological immune system. AIS research has provided a number of general purpose techniques and algorithms which have successfully been applied to a range of optimisation, classification and data mining problems. As with evolutionary algorithms and neural networks, AISs could also provide useful solutions to optimisation and classification problems in multi-sensor data fusion. More interestingly though perhaps, recent research in AISs [14,15,35,36] shows the importance of multilevel information in the construction of AISs. New models for AISs are emerging that are inspired by research in immunology into the role of the innate immune system in overall immune system dynamics. These AISs, which incorporate mechanisms inspired by both the innate and adaptive immune systems, are called second generation AISs. They stand in contrast to first generation AISs, which are inspired by adaptive immune system mechanisms only. One of the consequences of incorporating innate and adaptive mechanisms, as well as one of the defining characteristics of second generation AISs, is the need for a multilevel problem representation, and a multi-le- vel interaction of the components of the AIS with the problem [36]. As systems that integrate multilevel information sources, second generation AISs share much in common with multi-sensor data fusion systems.

In this paper we present a Dendritic Cell Algorithm (DCA) approach to information fusion, combining key elements of immunological theory with the engineering principles of data fusion. In the human immune system, DCs have the power to suppress or activate the immune system by correlation of signals representing their environment, combined with locality markers in the form of antigens. Antigens are proteins in structure and are any protein to which the immune system can potentially respond. These cells are responsible for the detection of pathogens in the human body through the correlation of information (in the form of molecular signals) within the environment. By using an abstraction of DC behaviour, similar detection properties are shown, resulting in an algorithm capable of performing anomaly detection.

Much recent work in bioinformatics has focused on the inference of various types of biological networks, representing gene regulation, metabolic processes, protein-protein interactions, etc. A common setting involves inferring network edges in a supervised fashion from a set of high-confidence edges, possibly characterized by multiple, heterogeneous data sets (protein sequence, gene expression, etc.). Here, we distinguish between two modes of inference in this setting: direct inference based upon similarities between nodes joined by an edge, and indirect inference based upon similarities between one pair of nodes and another pair of nodes. We propose a supervised approach for the direct case by translating it into a distance metric learning problem. A relaxation of the resulting convex optimization problem leads to the support vector machine (SVM) algorithm with a particular kernel for pairs, which we call the metric learning pairwise kernel (MLPK). We demonstrate, using several real biological networks, that this direct approach often improves upon the state-of-the-art SVM for indirect inference with the tensor product pairwise kernel.

The management and combination of uncertain, imprecise, fuzzy and even paradoxical or high conflicting sources of information has always been and still remains of primal importance for the development of reliable information fusion systems. In this short survey paper, we present the theory of plausible and paradoxical reasoning, known as DSmT (Dezert-Smarandache Theory) in literature, developed for dealing with imprecise, uncertain and potentially highly conflicting sources of information. DSmT is a new paradigm shift for information fusion and recent publications have shown the interest and the potential ability of DSmT to solve fusion problems where Dempster's rule used in Dempster-Shafer Theory (DST) provides counter-intuitive results or fails to provide useful result at all. This paper is focused on the foundations of DSmT and on its main rules of combination (classic, hybrid and Proportional Conflict Redistribution rules). Shafer's model on which is based DST appears as a particular and specific case of DSm hybrid model which can be easily handled by DSmT as well. Several simple but illustrative examples are given throughout this paper to show the interest and the generality of this new theory.

In this paper we consider and analyze the behavior of two combinational rules for temporal (sequential) attribute data fusion for target type estimation. Our comparative analysis is based on Dempster's fusion rule proposed in Dempster-Shafer Theory (DST) and on the Proportional Conflict Redistribution rule no. 5 (PCR5) recently proposed in Dezert-Smarandache Theory (DSmT). We show through very simple scenario and Monte-Carlo simulation, how PCR5 allows a very efficient Target Type Tracking and reduces drastically the latency delay for correct Target Type decision with respect to Demspter's rule. For cases presenting some short Target Type switches, Demspter's rule is proved to be unable to detect the switches and thus to track correctly the Target Type changes. The approach proposed here is totally new, efficient and promising to be incorporated in real-time Generalized Data Association - Multi Target Tracking systems (GDA-MTT) and provides an important result on the behavior of PCR5 with respect to Dempster's rule. The MatLab source code is provided in

Being able to analyze and interpret signal coming from electroencephalogram (EEG) recording can be of high interest for many applications including medical diagnosis and Brain-Computer Interfaces. Indeed, human experts are today able to extract from this signal many hints related to physiological as well as cognitive states of the recorded subject and it would be very interesting to perform such task automatically but today no completely automatic system exists. In previous studies, we have compared human expertise and automatic processing tools, including artificial neural networks (ANN), to better understand the competences of each and determine which are the difficult aspects to integrate in a fully automatic system. In this paper, we bring more elements to that study in reporting the main results of a practical experiment which was carried out in an hospital for sleep pathology study. An EEG recording was studied and labeled by a human expert and an ANN. We describe here the characteristics of the experiment, both human and neuronal procedure of analysis, compare their performances and point out the main limitations which arise from this study.