Algorithms for processing the group K nearest-neighbor query on distributed frameworks

Distributed and Parallel Databases - Given two datasets of points (called Query and Training), the Group (K) Nearest-Neighbor (GKNN) query retrieves (K) points of the Training with the smallest sum...     

Deep-MEG: spatiotemporal CNN features and multiband ensemble classification for predicting the early signs of Alzheimer’s disease with magnetoencephalography

Neural Computing and Applications - In this paper, we present the novel Deep-MEG approach in which image-based representations of magnetoencephalography (MEG) data are combined with ensemble...     

Does maintainability relate to the energy consumption of software? A case study

Software Quality Journal - Energy consumption of software has been becoming increasingly significant, since it can vary according to how the software has been developed. In recent years, developers...     

CFAR processing with switching exponential smoothers for nonhomogeneous environments

Conventional constant false alarm rate (CFAR) methods use a fixed number of cells to estimate the background variance. For homogeneous environments, it is desirable to increase the number of cells, at the cost of increased computation and memory requirements, in order to improve the estimation performance. For nonhomogeneous environments, it is desirable to use less number of cells in order to reduce the number of false alarms around the clutter edges. In this work, we present a solution with two exponential smoothers (first order IIR filters) having different time-constants to leverage the conflicting requirements of homogeneous and nonhomogeneous environments. The system is designed to use the filter having the large time-constant in homogeneous environments and to promptly switch to the filter having the small time constant once a clutter edge is encountered. The main advantages of proposed Switching IIR CFAR method are computational simplicity, small memory requirement (in comparison to windowing based methods) and its good performance in homogeneous environments (due to the large time-constant smoother) and rapid adaptation to clutter edges (due to the small time-constant smoother).     

Extracting trust information from security system of a service

The issue of trust is a research problem in emerging open environments, such as ubiquitous networks. Such environments are highly dynamic and they contain diverse number of services and autonomous entities. Entities in open environments have different security needs from services. Trust computations related to the security systems of services necessitate information that meets needs of each entity. Obtaining such information is a challenging issue for entities. In this paper, we propose a model for extracting trust information from the security system of a service based on the needs of an entity. We formally represent security policies and security systems to extract trust information according to needs of an entity. The formal representation ensures an entity to extract trust information about a security property of a service and trust information about whole security system of the service. The proposed model is applied to Dental Clinic Patient Service as a case study with two scenarios. The scenarios are analyzed experimentally with simulations. The experimental evaluation shows that the proposed model provides trust information related to the security system of a service based on the needs of an entity and it is applicable in emerging open environments.     

Exploring brain connectivity with two-dimensional neural maps

We introduce two-dimensional neural maps for exploring connectivity in the brain. For this, we create standard streamtube models from diffusion-weighted brain imaging data sets along with neural paths hierarchically projected into the plane. These planar neural maps combine desirable properties of low-dimensional representations, such as visual clarity and ease of tract-of-interest selection, with the anatomical familiarity of 3D brain models and planar sectional views. We distribute this type of visualization both in a traditional stand-alone interactive application and as a novel, lightweight web-accessible system. The web interface integrates precomputed neural-path representations into a geographical digital-maps framework with associated labels, metrics, statistics, and linkouts. Anecdotal and quantitative comparisons of the present method with a recently proposed 2D point representation suggest that our representation is more intuitive and easier to use and learn. Similarly, users are faster and more accurate in selecting bundles using the 2D path representation than the 2D point representation. Finally, expert feedback on the web interface suggests that it can be useful for collaboration as well as quick exploration of data.     

Face recognition with lattice independent component analysis and extreme learning machines

We focus on two aspects of the face recognition, feature extraction and classification. We propose a two component system, introducing Lattice Independent Component Analysis (LICA) for feature extraction and Extreme Learning Machines (ELM) for classification. In previous works we have proposed LICA for a variety of image processing tasks. The first step of LICA is to identify strong lattice independent components from the data. In the second step, the set of strong lattice independent vector are used for linear unmixing of the data, obtaining a vector of abundance coefficients. The resulting abundance values are used as features for classification, specifically for face recognition. Extreme Learning Machines are accurate and fast-learning innovative classification methods based on the random generation of the input-to-hidden-units weights followed by the resolution of the linear equations to obtain the hidden-to-output weights. The LICA-ELM system has been tested against state-of-the-art feature extraction methods and classifiers, outperforming them when performing cross-validation on four large unbalanced face databases.     

The GPU on the simulation of cellular computing models

Membrane Computing is a discipline aiming to abstract formal computing models, called membrane systems or P systems, from the structure and functioning of the living cells as well as from the cooperation of cells in tissues, organs, and other higher order structures. This framework provides polynomial time solutions to NP-complete problems by trading space for time, and whose efficient simulation poses challenges in three different aspects: an intrinsic massively parallelism of P systems, an exponential computational workspace, and a non-intensive floating point nature. In this paper, we analyze the simulation of a family of recognizer P systems with active membranes that solves the Satisfiability problem in linear time on different instances of Graphics Processing Units (GPUs). For an efficient handling of the exponential workspace created by the P systems computation, we enable different data policies to increase memory bandwidth and exploit data locality through tiling and dynamic queues. Parallelism inherent to the target P system is also managed to demonstrate that GPUs offer a valid alternative for high-performance computing at a considerably lower cost. Furthermore, scalability is demonstrated on the way to the largest problem size we were able to run, and considering the new hardware generation from Nvidia, Fermi, for a total speed-up exceeding four orders of magnitude when running our simulations on the Tesla S2050 server.     

Optimal configuration of Energy-Efficient Ethernet

The IEEE 802.3az standard provides a new low power mode that Ethernet network interfaces can use to save energy when there is no traffic to transmit. Simultaneously with the final standard approval, several algorithms were proposed to govern the physical interface state transition between the normal active mode and the new low power mode. In fact, the standard leaves this sleeping algorithm unspecified to spur competition among different vendors and achieve the greatest energy savings. In this paper, we try to bring some light to the most well known sleeping algorithms, providing mathematical models for the expected energy savings and the average packet delay inflicted on outgoing traffic. We will then use the models to derive optimum configuration parameters for them under given efficiency constraints.     

A multi-objective approach for the motion planning of redundant manipulators

Kinematic redundancy occurs when a manipulator possesses more degrees of freedom than those required to execute a given task. Several kinematic techniques for redundant manipulators control the gripper through the pseudo-inverse of the Jacobian, but lead to a kind of chaotic inner motion with unpredictable arm configurations. Such algorithms are not easy to adapt to optimization schemes and, moreover, often there are multiple optimization objectives that can conflict between them. Unlike single optimization, where one attempts to find the best solution, in multi-objective optimization there is no single solution that is optimum with respect to all indices. Therefore, trajectory planning of redundant robots remains an important area of research and more efficient optimization algorithms are needed. This paper presents a new technique to solve the inverse kinematics of redundant manipulators, using a multi-objective genetic algorithm. This scheme combines the closed-loop pseudo-inverse method with a multi-objective genetic algorithm to control the joint positions. Simulations for manipulators with three or four rotational joints, considering the optimization of two objectives in a workspace without and with obstacles are developed. The results reveal that it is possible to choose several solutions from the Pareto optimal front according to the importance of each individual objective.