A Fast Algorithm for Sparse Support Vector Machines for Mobile Computing Applications

This research presents a fast algorithm for projected support vector machines (PSVM) by selecting a basis vector set (BVS) for the kernel-induced feature space, the training points are projected onto the subspace spanned by the selected BVS. A standard linear support vector machine (SVM) is then produced in the subspace with the projected training points. As the dimension of the subspace is determined by the size of the selected basis vector set, the size of the produced SVM expansion can be specified. A two-stage algorithm is derived which selects and refines the basis vector set achieving a locally optimal model. The model expansion coefficients and bias are updated recursively for increase and decrease in the basis set and support vector set. The condition for a point to be classed as outside the current basis vector and selected as a new basis vector is derived and embedded in the recursive procedure. This guarantees the linear independence of the produced basis set. The proposed algorithm is tested and compared with an existing sparse primal SVM (SpSVM) and a standard SVM (LibSVM) on seven public benchmark classification problems. Our new algorithm is designed for use in the application area of human activity recognition using smart devices and embedded sensors where their sometimes limited memory and processing resources must be exploited to the full and the more robust and accurate the classification the more satisfied the user. Experimental results demonstrate the effectiveness and efficiency of the proposed algorithm. This work builds upon a previously published algorithm specifically created for activity recognition within mobile applications for the EU Haptimap project [1]. The algorithms detailed in this paper are more memory and resource efficient making them suitable for use with bigger data sets and more easily trained SVMs.

An evaluation of the effectiveness of an algorithm intervention in reducing inappropriate faecal samples sent for Clostridium difficile testing.

Background: Clostridium difficile (C. difficile) is a leading cause of infectious diarrhoea in hospitals. Sending faecal samples for testing expedites diagnosis and appropriate treatment. Clinical suspicion of C. difficile based on patient history, signs and symptoms is the basis for sampling. Sending faecal samples from patients with diarrhoea ‘just in case’ the patient has C. difficile may be an indication of poor clinical management.

Aim: To evaluate the effectiveness of an intervention by an Infection Prevention and Control Team (IPCT) in reducing inappropriate faecal samples sent for C. difficile testing.

Method: An audit of numbers of faecal samples sent before and after a decision-making algorithm was introduced. The number of samples received in the laboratory was retrospectively counted for 12-week periods before and after an algorithm was introduced.
Findings: There was a statistically significant reduction in the mean number of faecal samples sent post the algorithm. Results were compared to a similar intervention carried out in 2009 in which the same message was delivered by a memorandum. In 2009 the memorandum had no effect on the overall number of weekly samples being sent.

Conclusion: An algorithm intervention had an effect on the number of faecal samples being sent for C. difficile testing and thus contributed to the effective use of the laboratory service.

Targeting FPGA DSP Slices for a Large Integer Multiplier for Integer Based FHE

Homomorphic encryption offers potential for secure cloud computing. However due to the complexity of homomorphic encryption schemes, performance of implemented schemes to date have been unpractical. This work investigates the use of hardware, specifically Field Programmable Gate Array (FPGA) technology, for implementing the building blocks involved in somewhat and fully homomorphic encryption schemes in order to assess the practicality of such schemes. We concentrate on the selection of a suitable multiplication algorithm and hardware architecture for large integer multiplication, one of the main bottlenecks in many homomorphic encryption schemes. We focus on the encryption step of an integer-based fully homomorphic encryption (FHE) scheme. We target the DSP48E1 slices available on Xilinx Virtex 7 FPGAs to ascertain whether the large integer multiplier within the encryption step of a FHE scheme could fit on a single FPGA device. We find that, for toy size parameters for the FHE encryption step, the large integer multiplier fits comfortably within the DSP48E1 slices, greatly improving the practicality of the encryption step compared to a software implementation. As multiplication is an important operation in other FHE schemes, a hardware implementation using this multiplier could also be used to improve performance of these schemes.

Scaled Heavy-Ball Acceleration of the Richardson-Lucy Algorithm for 3D Microscopy Image Restoration

The Richardson–Lucy algorithm is one of the most important in image deconvolution. However, a drawback is its slow convergence. A significant acceleration was obtained using the technique proposed by Biggs and Andrews (BA), which is implemented in the deconvlucy function of the image processing MATLAB toolbox. The BA method was developed heuristically with no proof of convergence. In this paper, we introduce the heavy-ball (H-B) method for Poisson data optimization and extend it to a scaled H-B method, which includes the BA method as a special case. The method has a proof of the convergence rateof O(K^2), where k is the number of iterations. We demonstrate the superior convergence performance, by a speedup factor off ive, of the scaled H-B method on both synthetic and real 3D images.

Co-operative tensegrity-based formation control algorithm for a multi-aircraft system

This paper presents a tensegrity-based co-operative control algorithm for an aircraft formation. The 6 degrees-of-freedom model of the well-known Aerosonde unmanned aerial vehicle (UAV), is integrated with the model of the tensegrity structure and a decentralised control scheme is proposed. The strategy is shown to be scalable for 2n number of UAVs and is able to maintain a firm geometry whilst allowing flexible shape transformations. Simulation results demonstrate the effectiveness and stability of the proposed tensegrity-based formation control algorithm in 3D.

A hybrid mixed cost-function TEQ initialization algorithm for ADSL modems

In this paper, we present a hybrid mixed cost-function adaptive initialization algorithm for the time domain equalizer in a discrete multitone (DMT)-based asymmetric digital subscriber loop. Using our approach, a higher convergence rate than that of the commonly used least-mean square algorithm is obtained, whilst attaining bit rates close to the optimum maximum shortening SNR and the upper bound SNR. Moreover, our proposed method outperforms the minimum mean-squared error design for a range of TEQ filter lengths.

Lattice-based Encryption Over Standard Lattices in Hardware

Lattice-based cryptography has gained credence recently as a replacement for current public-key cryptosystems, due to its quantum-resilience, versatility, and relatively low key sizes. To date, encryption based on the learning with errors (LWE) problem has only been investigated from an ideal lattice standpoint, due to its computation and size efficiencies. However, a thorough investigation of standard lattices in practice has yet to be considered. Standard lattices may be preferred to ideal lattices due to their stronger security assumptions and less restrictive parameter selection process. In this paper, an area-optimised hardware architecture of a standard lattice-based cryptographic scheme is proposed. The design is implemented on a FPGA and it is found that both encryption and decryption fit comfortably on a Spartan-6 FPGA. This is the first hardware architecture for standard lattice-based cryptography reported in the literature to date, and thus is a benchmark for future implementations.
Additionally, a revised discrete Gaussian sampler is proposed which is the fastest of its type to date, and also is the first to investigate the cost savings of implementing with lamda_2-bits of precision. Performance results are promising in comparison to the hardware designs of the equivalent ring-LWE scheme, which in addition to providing a stronger security proof; generate 1272 encryptions per second and 4395 decryptions per second.

Design of an OFDM Physical Layer Encryption Scheme

This paper presents a new encryption scheme implemented at the physical layer of wireless networks employing orthogonal frequency-division multiplexing (OFDM). The new scheme obfuscates the subcarriers by randomly reserving several subcarriers for dummy data and resequences the training symbol by a new secure sequence. Subcarrier obfuscation renders the OFDM transmission more secure and random, while training symbol resequencing protects the entire physical layer packet, but does not affect the normal functions of synchronization and channel estimation of legitimate users while preventing eavesdroppers from performing these functions. The security analysis shows the system is robust to various attacks by analyzing the search space using an exhaustive key search. Our scheme is shown to have a better performance in terms of search space, key rate and complexity in comparison with other OFDM physical layer encryption schemes. The scheme offers options for users to customize the security level and key rate according to the hardware resource. Its low complexity nature also makes the scheme suitable for resource limited devices. Details of practical design considerations are highlighted by applying the approach to an IEEE 802.11 OFDM system case study.

The alternating least-squares algorithm for CDPCA

Clustering and Disjoint Principal Component Analysis (CDP CA) is a constrained principal component analysis recently proposed for clustering of objects and partitioning of variables, simultaneously, which we have implemented in R language. In this paper, we deal in detail with the alternating least-squares algorithm for CDPCA and highlight its algebraic features for constructing both interpretable principal components and clusters of objects. Two applications are given to illustrate the capabilities of this new methodology.

Estimating fuzzy membership functions parameters by the levenberg-marquardt algorithm

In previous papers from the authors fuzzy model identification methods were discussed. The bacterial algorithm for extracting fuzzy rule base from a training set was presented. The Levenberg-Marquardt algorithm was also proposed for determining membership functions in fuzzy systems. In this paper the Levenberg-Marquardt technique is improved to optimise the membership functions in the fuzzy rules without Ruspini-partition. The class of membership functions investigated is the trapezoidal one as it is general enough and widely used. The method can be easily extended to arbitrary piecewise linear functions as well.

Genetic programming and bacterial algorithm for neural networks and fuzzy systems design

In the field of control systems it is common to use techniques based on model adaptation to carry out control for plants for which mathematical analysis may be intricate. Increasing interest in biologically inspired learning algorithms for control techniques such as Artificial Neural Networks and Fuzzy Systems is in progress. In this line, this paper gives a perspective on the quality of results given by two different biologically connected learning algorithms for the design of B-spline neural networks (BNN) and fuzzy systems (FS). One approach used is the Genetic Programming (GP) for BNN design and the other is the Bacterial Evolutionary Algorithm (BEA) applied for fuzzy rule extraction. Also, the facility to incorporate a multi-objective approach to the GP algorithm is outlined, enabling the designer to obtain models more adequate for their intended use.

Optimal dynamic control of laminated adaptive structures using a higher order model and a genetic algorithm

This paper deals with a finite element formulation based on the classical laminated plate theory, for active control of thin plate laminated structures with integrated piezoelectric layers, acting as sensors and actuators. The control is initialized through a previous optimization of the core of the laminated structure, in order to minimize the vibration amplitude. Also the optimization of the patches position is performed to maximize the piezoelectric actuator efficiency. The genetic algorithm is used for these purposes. The finite element model is a single layer triangular plate/shell element with 24 degrees of freedom for the generalized displacements, and one electrical potential degree of freedom for each piezoelectric element layer, which can be surface bonded or embedded on the laminate. To achieve a mechanism of active control of the structure dynamic response, a feedback control algorithm is used, coupling the sensor and active piezoelectric layers. To calculate the dynamic response of the laminated structures the Newmark method is considered. The model is applied in the solution of an illustrative case and the results are presented and discussed.

Bacterial algorithm applied for fuzzy rule extraction

This paper presents a method of using the so-colled "bacterial algorithm" (4,5) for extracting a fuzzy rule base from a training set. The bewly proposed bacterial evolutionary algorithm (BEA) is shown. In our application one bacterium corresponds to a fuzzy rule system.

Adaptive generalized predictive control algorithm implemented over an heterogeneous parallel architecture

In this paper a parallel implementation of an Adaprtive Generalized Predictive Control (AGPC) algorithm is presented. Since the AGPC algorithm needs to be fed with knowledge of the plant transfer function, the parallelization of a standard Recursive Least Squares (RLS) estimator and a GPC predictor is discussed here.

Adaptive generalized predictive control algorithm implemented over a DSP network

In this paper a parallel implementation of an Adaprtive Generalized Predictive Control (AGPC) algorithm is presented. Since the AGPC algorithm needs to be fed with knowledge of the plant transfer function, the parallelization of a standard Recursive Least Squares (RLS) estimator and a GPC predictor is discussed here.