Search

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.sysarc.2006.09.008 Byline: Nadia Nedjah (a), Luiza de Macedo Mourelle (b) Keywords: Cryptography; Modular exponentiation; m-ary method Abstract: Modular exponentiation is an important operation in several public-key cryptosystems. It is performed using successive modular multiplications. For the sake of efficiency, one needs to reduce the total number of required modular multiplications. In this paper, we propose two efficient hardware implementations for computing modular exponentiations, which are based on the m-ary method. The m-ary method includes a power pre-computation step. The first design ignores the exponent and pre-computes all possible powers while the second takes advantage of the formation of the exponent to compute only those powers that are really necessary for the rest of the computation. As it can be expected, the implementation of the first architecture, compared with that of the second one, requires more time to complete an exponentiation. In compensation, however, the first should require less hardware area than the second. We provide a comparison of these two implementations using the performance factor, which takes into account both space and time requirements. Author Affiliation: (a) Department of Electronics Engineering and Telecommunication, Faculty of Engineering, State University of Rio de Janeiro, Brazil (b) Department of Systems Engineering and Computation, Faculty of Engineering, State University of Rio de Janeiro, Brazil Article History: Received 2 May 2006; Revised 29 August 2006; Accepted 15 September 2006

Several neural network models have been proposed in the literature to predict the future behavior of financial time series. However, an intrinsic limitation arises from this particular prediction task with modeling via neural networks, since the prediction, when sampled in daily frequency, have 1-step-ahead delay with respect to real time series observations. In order to overcome such drawback, we present a deep increasing–decreasing-linear neural network (wherein each layer is composed of a set of increasing–decreasing-linear processing units) to predict the behavior of financial time series. In addition, we present a learning process to train the proposed model using a descending gradient-based approach. In order to assess the model's prediction performance, we use twelve financial time series from relevant stock markets around the world. The obtained results show that the proposed model have competitiveness, in terms of predictive performance, and have better effectiveness when compared to recent models presented in the literature of time series prediction. [ABSTRACT FROM AUTHOR]

The automatic speech recognition based on detection of phonemes provides advantages for online recognition of a speech represented by a sound signal. The development of a system for automatic speech recognition is multidisciplinary. It covers several areas of research, such as linguistics, signal processing and computational intelligence. In this work, the process starts with a speech signal pre-processing to extract the main features of the speech signal at a given instant of time. Inspired by the "divide and conquer" principle, we bridge the complexity gap of automatic speech recognition by devising models based on an ensemble of neural network experts, allowing to divide the huge decision space regarding speech recognition so that each expert takes care only of a delimited area of this decision space. This novel application of this strategy improves the precision, sensitivity and accuracy of the recognition process. Each included expert decides regarding each one of the pre-processed input samples. The decision set thus obtained is weighted. So, the expert with the highest weight for the output will determine the sample final classification. After that, a dynamic post-processing step, implemented as a recurrent neural network, is executed. It aims at mitigating the oscillatory effect that occurs during the recognition of classes with similar characteristics. In this work, two ensembles are investigated. The first is based on the clustering of similar phonetics classes while the second takes care of the imbalanced distribution of samples in the training set. The proposed model achieves 7.63% improvement in terms of accuracy with respect to the best so far related model for automatic speech recognition. • It provides an online tool for Automatic Speech Recognition for Portuguese language. • An ensemble of expert neural networks is explored, dividing the decision. • Expert only takes care of a well-delimited area of this decision space. • Two models are proposed: (1) grouping similar phonetics; (2) unbalanced dataset. • A dynamic post-processing using an RNN is performed, mitigating of output oscillatory effects. [ABSTRACT FROM AUTHOR]

Off-line pattern recognition in speech signals is a complex task. Yet, this task becomes harder when the recognition result is required online or in real-time. The present work proposes an online identification of the Portuguese language phonemes using a non-linear autoregressive model with exogenous inputs, commonly called NARX. The process first conditions the input speech signal, and extracts its frequency characteristics. Then it pre-classifies the extracted features into one of the ten possible groups of phonemes, as available in the Portuguese language. This pre-classification is done using a multilayer perceptron network (MLP) with a supervised learning. Subsequently, the MLP output vector, together with the vector that carries the input frequencies, feeds a NARX neural network by means of a temporal delay of four times and feed-backward recurrent links that encompass the results of all hidden layers of the network. As a result of this process, the proposed phoneme recognition process improves the accuracy of an online identification of the Portuguese spoken phonemes during a natural conversation. When the phoneme input signal is well conditioned and continuous over time, the proposed recognition process can provide the correct classification in real-time, with an acceptable accuracy rate. [ABSTRACT FROM AUTHOR]

In a wireless sensors network in general, and a swarm of robots in particular, solving the localization problem consists of discovering the sensor’s or robot’s positions without the use of external references, such as the Global Positioning System – GPS. In this problem, the solution is performed based on distance measurements to existing reference nodes also known as anchors. These nodes have knowledge about their respective positions in the environment. Aiming at efficient yet accurate method to approach the localization problem, some bio-inspired algorithms have been explored. In this sense, targeting the accuracy of the final result rather than the efficiency of the computational process, we propose a new localization method based on Min–Max and Particle Swarm Optimization. Generally, the performance results prove the effectiveness of the proposed method for any swarm configuration. Furthermore, its efficiency is demonstrated for high connectivity swarms. Specifically, the proposed method was able to reduce the localization average error by 84%, in the worst case, considering a configuration of 10 anchors and 100 unknown nodes and by almost 100%, in the best case, considering 30 anchors and 200 unknown nodes. This proves that for high connectivity networks or swarms, the proposed method provides almost exact solution to the localization problem, which is a big shift forward in the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Weightless Neural Networks (WNNs) are a powerful mechanism for pattern recognition. Aiming at enhancing their learning capabilities, Multi-valued Probabilistic Logic Nodes (M-PLN) are used, instead of crisp neurons with a 0/1 based RAM-nodes. An M-PLN stores a mapping of, or possibly, the triggering probability, for each input pattern that needs to be recognized. The M-PLN model attempts to strengthen the discrepancies between distinct patterns used during the training process and those that have not yet been processed. In this paper, an efficient yet customizable hardware architecture for M-PLN based neural network is proposed. It implements the learning and operation processes of a pyramidal network structure, augmented by a probabilistic rewarding/punishing search algorithm. The training algorithm can adapt itself to the overall hit ratio so far achieved by the network. Using class-dedicated layers, the hardware is able to handle image classification in parallel and thus, very efficiently. Furthermore, the classification process is performed in a pipelined manner so its stages never stop working until all input images are classified. Nonetheless, during network training, only one of these layers is activated. Last but not least, the architecture is customizable as its structure can be tailored in accordance to the application characteristics in terms of class number, pattern tuple size and image resolution. In order to evaluate the time and cost requirements of the proposed design, its underlying architecture was specified in VHDL and functionally tested. The presented results are two-fold: first, based on many functional simulations, estimated time and cost requirements are analyzed; second, to further assess the performance of the proposed the design, the VHDL model was synthesized to produce a semi-custom implementation on FPGAs. We also give an assessment of the quality of the entailed classification process. The architecture exhibits performance and reconfiguration capabilities that are very promising and encouraging towards the fabrication of a prototype on ASIC. [ABSTRACT FROM AUTHOR]

In swarm robotics, it is necessary to develop methods and strategies that guide the collective execution of tasks by the robots. The design of such tasks can be done considering it as a collection of simpler behaviors, called subtasks. In this paper, the Wave Swarm is presented as a general strategy to manage the sequence of subtasks that compose the collective navigation, which is an important task in swarm robotics. The proposed strategy is based mainly on the execution of wave algorithms. The swarm is viewed as a distributed system, wherein the communication is achieved by message passing among robot’s neighborhood. Message propagation delimits the start and end of each subtask. Simulations are performed to demonstrate that controlled navigation of robot swarms/clusters is achieved with three subtasks, which are recruitment, alignment and movement. [ABSTRACT FROM AUTHOR]

Dynamic task allocation in a robotic swarm is a necessary process for proper management of the swarm. It allows the distribution of the identified tasks to be performed, among the swarm of robots, in such a way that a pre-defined proportion of execution of those tasks is achieved. In this context, there is no central unit to take care of the task allocation. So any algorithm proposal must be distributed, allowing every, and each robot in the swarm to identify the task it must perform. This paper proposes a distributed control algorithm to implement dynamic task allocation in a swarm robotics environment. The algorithm is inspired by the particle swarm optimization. In this context, each robot that integrates the swarm must run the algorithm periodically in order to control the underlying actions and decisions. The algorithm was implemented on ELISA III real swarm robots and extensively tested. The algorithm is effective and the corresponding performance is promising. [ABSTRACT FROM AUTHOR]

Nowadays, final products often encompass a certain intelligence therein to deal with variation or lack of precision in the sensing input data. This intelligence is usually acquired via the utilization of existing soft techniques, such as artificial neural networks, genetic algorithms and fuzzy control, among others. Thus, it is profitable to have on-the-shelf shell scalable and adaptive hardware designs that implement these soft techniques. This availability allows for an immediate embedding of any of those designs onto final products. This usually entails a reduced time-to-market of the product. Process control is one of the many applications that took advantage of the fuzzy paradigm. In general, controllers are embedded into the controlled device. This paper presents a novel design of a reconfigurable efficient parallel architecture to implement fuzzy controllers on hardware with almost no design effort for final users. The proposed architecture is herein proven suitable for embedding. It is customizable, so it allows the setup and configuration of the controller parameters, and hence its use for any problem application. Two fuzzy controllers that model autonomous car driving are implemented and their cost and performance evaluated. [ABSTRACT FROM AUTHOR]

Highlights: [•] Two novel congestion-aware algorithms based on ACO adapted to the routing problem. [•] An adaptive and static routing. [•] The proposed algorithms overcome the congested routes. [•] The found solutions improve the execution time of applications mapped onto Network-on-Chip. [ABSTRACT FROM AUTHOR]

Abstract: There are several neural network implementations using either software, hardware-based or a hardware/software co-design. This work proposes a hardware architecture to implement an artificial neural network (ANN), whose topology is the multilayer perceptron (MLP). In this paper, we explore the parallelism of neural networks and allow on-the-fly changes of the number of inputs, number of layers and number of neurons per layer of the net. This reconfigurability characteristic permits that any application of ANNs may be implemented using the proposed hardware. In order to reduce the processing time that is spent in arithmetic computation, a real number is represented using a fraction of integers. In this way, the arithmetic is limited to integer operations, performed by fast combinational circuits. A simple state machine is required to control sums and products of fractions. Sigmoid is used as the activation function in the proposed implementation. It is approximated by polynomials, whose underlying computation requires only sums and products. A theorem is introduced and proven so as to cover the arithmetic strategy of the computation of the activation function. Thus, the arithmetic circuitry used to implement the neuron weighted sum is reused for computing the sigmoid. This resource sharing decreased drastically the total area of the system. After modeling and simulation for functionality validation, the proposed architecture synthesized using reconfigurable hardware. The results are promising. [Copyright &y& Elsevier]

Abstract: Network-on-chip (NoC) are considered the next generation of communication infrastructure in embedded systems. In the platform-based design methodology, an application is implemented by a set of collaborative intellectual property (IP) blocks. The selection of the most suited set of IPs as well as their physical mapping onto the NoC infrastructure to implement efficiently the application at hand are two hard combinatorial problems that occur during the synthesis process of Noc-based embedded system implementation. In this paper, we propose an innovative preference-based multi-objective evolutionary methodology to perform the assignment and mapping stages. We use one of the well-known and efficient multi-objective evolutionary algorithms NSGA-II and microGA as a kernel. The optimization processes of assignment and mapping are both driven by the minimization of the required silicon area and imposed execution time of the application, considering that the decision maker’s preference is a pre-specified value of the overall power consumption of the implementation. [Copyright &y& Elsevier]

Abstract: Pattern matching is a fundamental feature in many applications such as functional programming, logic programming, theorem proving, term rewriting and rule-based expert systems. Usually, patterns are pre-processed into a deterministic finite automaton. Using such an automaton allows one to determine the matched pattern(s) by a single scan of the input term. The matching automaton is typically based on left-to-right traversal of patterns. In this paper, we propose a method to build such an automaton. Then, we propose an incremental method to build a deterministic concise automaton for non-necessarily sequential rewriting systems. With ambiguous patterns a subject term may be an instance of more than one pattern. To select the pattern to use, a priority rule is usually engaged. The pre-processing of the patterns adds new patterns, which are instances of the original ones. When the original patterns are ambiguous, some of the instances supplied may be irrelevant for the matching process. They may cause an unnecessary increase in the space requirements of the automaton and may also reduce the time efficiency of the matching process. Here, we devise a new pre-processing operation that recognises and avoids such irrelevant instances. Hence improves space and time requirements for the matching automaton. [Copyright &y& Elsevier]

• IoT is a revolutionary technology with innumerable applications in industrial sectors. • Potential benefits of big data to small and medium size enterprises are discussed. • Effects of integrating IoT and Big data on the SMEs are presented. • An approach to detect XSS attack for protecting user's privacy is proposed. • Implementation details and outcomes that prove the efficiency of proposed approach are provided. Advancement in embedded Nano-technologies empowers IoT technology which serves as the backbone technology for many small and medium enterprises. Evolution of smart devices proved as a supreme source of data, denoted as Big data, that is analyzed to instantly extricate constructive and valuable information that helps the organization in many ways. As it may embrace sensitive information, hence, it turned out to be the fascinating target of multitude of attacks that aims at stealing the information, resulting into privacy breaches. XSS attack is one such security attack that supports the attacker to intrude into user's personal space. Therefore, this paper is focused on designing an approach that detects XSS attack in IoT network to protect the data privacy. It employs Convolution Neural Network (CNN) to detect the XSS attack payload after applying certain data preparation methods. This approach helps in preventing privacy breaches which eventually helps the enterprises in strengthening their bond with their users. The experimental results unveiled that the approach achieves a detection accuracy of 99% after the successful execution of data preparation methods. [ABSTRACT FROM AUTHOR]