Nonflat surface level pyramid: a high connectivity multidimensional interconnection network

Parallel machines are extensively used to increase computational speed in solving different scientific problems. Various topologies with different properties have been proposed so far and each one is suitable for specific applications. Pyramid interconnection networks have potentially powerful architecture for many applications such as image processing, visualization, and data mining. The major advantage of pyramids which is important for image processing systems is hierarchical abstracting and transferring the data toward the apex node, just like the human being vision system, which reach to an object from an image. There are rapidly growing applications in which the multidimensional datasets should be processed simultaneously. For such a system, we need a symmetric and expandable interconnection network to process data from different directions and forward them toward the apex. In this paper, a new type of pyramid interconnection network called Non-Flat Surface Level (NFSL) pyramid is proposed. NFSL pyramid interconnection networks constructed by L-level A-lateral-base pyramids that are named basic-pyramids. So, the apex node is surrounded by the level-one surfaces of NFSL that are the first nearest level of nodes to apex in the basic pyramids. Two topologies which are called NFSL-T and NFSL-Q originated from Trilateral-base and Quadrilateral-base basic-pyramids are studied to exemplify the proposed structure. To evaluate the proposed architecture, the most important properties of the networks are determined and compared with those of the standard pyramid networks and its variants.     

Formation control of underactuated bio-inspired snake robots

This paper considers formation control of snake robots. In particular, based on a simplified locomotion model, and using the method of virtual holonomic constraints, we control the body shape of the robot to a desired gait pattern defined by some pre-specified constraint functions. These functions are dynamic in that they depend on the state variables of two compensators which are used to control the orientation and planar position of the robot, making this a dynamic maneuvering control strategy. Furthermore, using a formation control strategy we make the multi-agent system converge to and keep a desired geometric formation, and enforce the formation follow a desired straight line path with a given speed profile. Specifically, we use the proposed maneuvering controller to solve the formation control problem for a group of snake robots by synchronizing the commanded velocities of the robots. Simulation results are presented which illustrate the successful performance of the theoretical approach.     

Stream fusion for multi-stream automatic speech recognition

Multi-stream automatic speech recognition (MS-ASR) has been confirmed to boost the recognition performance in noisy conditions. In this system, the generation and the fusion of the streams are the essential parts and need to be designed in such a way to reduce the effect of noise on the final decision. This paper shows how to improve the performance of the MS-ASR by targeting two questions; (1) How many streams are to be combined, and (2) how to combine them. First, we propose a novel approach based on stream reliability to select the number of streams to be fused. Second, a fusion method based on Parallel Hidden Markov Models is introduced. Applying the method on two datasets (TIMIT and RATS) with different noises, we show an improvement of MS-ASR.     

Estimating botnet virulence within mathematical models of botnet propagation dynamics

Mathematical models of botnet propagation dynamics are increasingly deemed to have potential for significant contribution to botnet mitigation. Botnet virulence, which comprises network vulnerability rate and network infection rate, is a key factor in those models. In this paper we discuss a practical approach that draws on epidemiological models in biology to estimate the botnet virulence in a network. Our research provides mathematical models of botnet propagation dynamics with concrete measures of botnet virulence, which make those models practical and hence employable in mitigation of real world botnets in a timely fashion. The approach is based on random sampling and follows a novel application of statistical learning and inference in a botnet-versus-network setting. We have implemented this research in the Matlab programming language. In this paper, we discuss an experimental evaluation of the effectiveness of this research with respect to botnet propagation dynamics realistically simulated in a GTNetS network simulation platform.     

PiSHi: click the images and I tell if you are a human

This paper introduces pictorial intelligent system for human identification (PiSHi), an image-based captcha which uses three human cognitive abilities to distinguish humans from machines. The first is the human ability to easily recognise the image’s upright orientation. The second is the human brain’s ability in recognising a picture’s content when it is only partially visible. And the third is the human ability in unconscious decision making when encountering pictorial challenges. This work models such complicated human patterns in problem solving for the first time. In order to extract these behavioural patterns and save them in a pattern database, we have implemented our own captcha and performed a series of experiments. PiSHi’s interface presents the user with a set of distorted pictures and asks her to click on the upright orientation of all the pictures in any preferred order. Next, it captures the user’s interaction patterns, compares them with the ones saved in the pattern database, and grants her a corresponding credit. Based on this credit, the user either passes or fails the test, and participates in updating the picture database. Our experiments indicate that human users can solve our proposed captcha effectively—with an accuracy of 99.44 %. Besides, our proposed system is secure against several types of attacks including random guessing and reverse image search engines. The results offer the possibility of utilising the identified human behavioural models in practical captchas.     

Hierarchical Classifiers for Robust Topological Robot Localization

This paper presents a novel appearance-based technique for topological robot localization and place recognition. A vocabulary of visual words is formed automatically, representing local features that frequently occur in the set of training images. Using the vocabulary, a spatial pyramid representation is built for each image by repeatedly subdividing it and computing histograms of visual words at increasingly fine resolutions. An information maximization technique is then applied to build a hierarchical classifier for each class by learning informative features. While top-level features in the hierarchy are selected from the coarsest resolution of the representation, capturing the holistic statistical properties of the images, child features are selected from finer resolutions, encoding more local characteristics, redundant with the information coded by their parents. Exploiting the redundancy in the data enables the localization system to achieve greater reliability against dynamic variations in the environment. Achieving an average classification accuracy of 88.9% on a challenging topological localization database, consisting of twenty seven outdoor places, demonstrates the advantages of our hierarchical framework for dealing with dynamic variations that cannot be learned during training.     

Classification of primitive shapes using brain–computer interfaces

Brain–computer interfaces (BCIs) are recent developments in alternative technologies of user interaction. The purpose of this paper is to explore the potential of BCIs as user interfaces for CAD systems. The paper describes experiments and algorithms that use the BCI to distinguish between primitive shapes that are imagined by a user. Users wear an electroencephalogram (EEG) headset and imagine the shape of a cube, sphere, cylinder, pyramid or a cone. The EEG headset collects brain activity from 14 locations on the scalp. The data is analyzed with independent component analysis (ICA) and the Hilbert–Huang Transform (HHT). The features of interest are the marginal spectra of different frequency bands (theta, alpha, beta and gamma bands) calculated from the Hilbert spectrum of each independent component. The Mann–Whitney U-test is then applied to rank the EEG electrode channels by relevance in five pair-wise classifications. The features from the highest ranking independent components form the final feature vector which is then used to train a linear discriminant classifier. Results show that this classifier can discriminate between the five basic primitive objects with an average accuracy of about 44.6% (compared to naïve classification rate of 20%) over ten subjects (accuracy range of 36%–54%). The accuracy classification changes to 39.9% when both visual and verbal cues are used. The repeatability of the feature extraction and classification was checked by conducting the experiment on 10 different days with the same participants. This shows that the BCI holds promise in creating geometric shapes in CAD systems and could be used as a novel means of user interaction.     

Multi-objective mixture design and optimisation of steel fiber reinforced UHPC using machine learning algorithms and metaheuristics

Ultra-high-performance concrete (UHPC) is a recent class of concrete with improved durability, rheological and mechanical and durability properties compared to traditional concrete. The production cost of UHPC is considerably high due to a large amount of cement used, and also the high price of other required constituents such as quartz powder, silica fume, fibres and superplasticisers. To achieve specific requirements such as desired production cost, strength and flowability, the proportions of UHPC’s constituents must be well adjusted. The traditional mixture design of concrete requires cumbersome, costly and extensive experimental program. Therefore, mathematical optimisation, design of experiments (DOE) and statistical mixture design (SMD) methods have been used in recent years, particularly for meeting multiple objectives. In traditional methods, simple regression models such as multiple linear regression models are used as objective functions according to the requirements. Once the model is constructed, mathematical programming and simplex algorithms are usually used to find optimal solutions. However, a more flexible procedure enabling the use of high accuracy nonlinear models and defining different scenarios for multi-objective mixture design is required, particularly when it comes to data which are not well structured to fit simple regression models such as multiple linear regression. This paper aims to demonstrate a procedure integrating machine learning (ML) algorithms such as Artificial Neural Networks (ANNs) and Gaussian Process Regression (GPR) to develop high-accuracy models, and a metaheuristic optimisation algorithm called Particle Swarm Optimisation (PSO) algorithm for multi-objective mixture design and optimisation of UHPC reinforced with steel fibers. A reliable experimental dataset is used to develop the models and to justify the final results. The comparison of the obtained results with the experimental results validates the capability of the proposed procedure for multi-objective mixture design and optimisation of steel fiber reinforced UHPC. The proposed procedure not only reduces the efforts in the experimental design of UHPC but also leads to the optimal mixtures when the designer faces strength-flowability-cost paradoxes.

     

Graph attention-based collaborative filtering for user-specific recommender system using knowledge graph and deep neural networks

Knowledge and Information Systems - Collaborative filtering suffers from the issues of data sparsity and cold start. Due to which recommendation models that only rely on the user–item...     

Multiple robust H∞ controller design using the nonsmooth optimization method

This paper proposes a systematic technique to design multiple robust H_∞ controllers. The proposed technique achieves a desired robust performance objective, which is impossible to achieve with a single robust controller, by dividing the uncertainty set into several subsets and by designing a robust controller to each subset. To achieve this goal with a small number of divisions of the uncertainty set, an optimization problem is formulated. Since the cost function of this optimization problem is not a smooth function, a numerical nonsmooth optimization algorithm is proposed to solve this problem. This method avoids the use of Lyapunov variables, and therefore it leads to a moderate size optimization problem. A numerical example shows that the proposed multiple robust control method can improve the closed‐loop performance when a single robust controller cannot achieve satisfactory performance. Copyright © 2009 John Wiley & Sons, Ltd.