Search

Visual recognition of crowd dynamics has had a huge impact on several applications including surveillance, situation awareness, homeland security and intelligent environments. However, the state-of-the-art in crowd analysis has become diverse due to factors such as: (a) the underlying definition of a crowd, (b) the constituent elements of the crowd processing model, (c) its application, hence (d) the dataset and (e) the evaluation criteria available for benchmarking. Although such diversity is healthy, the techniques for crowd modelling thus developed have failed to establish credibility therefore becoming unreliable and of questionable validity across different research disciplines. This paper aims to give an account of such issues by deducing key statistical evidence from the existing literature and providing recommendations towards focusing on the general aspects of techniques rather than any specific algorithm. The advances and trends in crowd analysis are drawn in the context of crowd modelling studies published in leading journals and conferences over the past 7 years. Finally, this paper shall also provide a qualitative and quantitative comparison of some existing methods using various publicly available crowd datasets to substantiate some of the theoretical claims. [ABSTRACT FROM AUTHOR]

A unified associative memory model with a novel method for designing associative memories is presented in this paper. Based on continuous recurrent neural networks, bipolar patterns inputted from external can cause the output of neural networks to be memorized patterns. In the method, two conditions relevant to external inputs are derived to ensure the network states converge to a stable interval, and an exponential stable criterion is proposed for the network being a bipolar associative memory with higher recall speed. By introducing a tunable slope activation function and considering time delay, the proposed model is general and can recall the memorized patterns in auto-associative and hetero-associative way, while higher robust and more flexible memory can be obtained through the proposed method. Experimental verification demonstrates the effectiveness and generalization of the proposed method. [ABSTRACT FROM AUTHOR]

Swarm robotics is a growing field of swarm intelligence inspired by natural swarms for providing a solution for the collaboration among swarm agents to achieve a common goal. One of the challenges in designing a swarm robotic system with desired collective behaviour is to understand the effect of individual behaviour on group performance. This paper considers a system composed of autonomous swarm agents, each one executing its algorithm. We present a generic fault-tolerant pattern formation algorithm, in which different agents from different positions gather and then form a desired geometric pattern specifically a uniform circle and maintain it in the presence of faulty agents. We present an analysis based on simulations and experimental results of the proposed algorithm on swarm forming the pattern, in which failures are deliberately induced to check their fault tolerance capability and pattern formation capability. Our findings show that the formed geometric pattern can be restored and maintained depending on the different parameters in the presence of faulty agents. • We introduce a Fault-tolerance algorithm for pattern formation of swarm agents. • Elaborated the Uniform Circle formation and then fault-tolerance in uniform circle formation. • Used Sensor-based analysis as mathematical model. • Fault-tolerance algorithm is simulated and validated. [ABSTRACT FROM AUTHOR]

Abstract: Last few years have witnessed the development of various multi-objective evolutionary algorithms since they allow the generation of the overall Pareto front for multi-objective optimizations. With the problems in the real-world becoming more and more complex, however, no reported work in the literature focuses on the high-dimensional objective optimizations (HOPs). In this paper, we propose an evolutionary algorithm named HOEA (high-dimensional objective evolutionary algorithm) for HOPs. By adopting the concept of nonlinear definition for optimizing object, HOPs can be solved by HOEA, while the well-known multi-objective evolutionary algorithms work poorly on HOPs. We further analyze the nonlinear dynamic properties of HOEA on the basis of martingale theoretical framework. The theoretical results indicate that this new algorithm is indeed capable of achieving convergence. We also conduct experiments on HOEA with two representative test instances. The experimental results either confirm our theoretical results or show that the proposed algorithm is efficient and effective for HOPs. [Copyright &y& Elsevier]

Abstract: In this paper, a dynamic theorem proving (DTP) algorithm is proposed for dynamically judging whether a component set is consistency-based diagnosis in model-based diagnosis. Firstly, the model of the system to be diagnosed and all the observations are described with conjunctive normal forms (CNF), and the problem of diagnosis is translated into the satisfiability of the related clauses in the CNF files. Next, all the minimal consistency-based diagnostic sets are derived by calling DTP dynamically combining with the CSSE-tree. As the theorem about the number of components in minimal diagnosis is proposed, the majority of the non-minimal diagnosis can never be produced. Moreover, this approach can compute all the consistency-based diagnostic sets directly, without computing all the conflict sets and therefore the hitting sets of the collection of the corresponding conflict sets like the classical methods. Finally, the approach’s soundness, completeness and complexity are analyzed and proved, and results show that the program is easy to be implemented, and the diagnosis efficiency is highly improved. [Copyright &y& Elsevier]

Abstract: This paper presents a comparative study of implementation of feature extraction and classification algorithms based on wavelet neural networks (WNN) for chaos-based digital modulation (CBDM) classification. Thirteen different feature extraction methods are generated by separately using Daubechies, Biorthogonal, Coiflets, and Symlets wavelet filters. WNN model is used, which consists of two layers: wavelet entropy and multi-layer perceptron (MLP) neural networks for expert CBDM classification. The chaos-based digital modulated signals used in this experimental study are Chaos Shift Keying (CSK), Chaotic On–Off Keying (COOK), Differential Chaos Shift Keying (DCSK), Correlation Delay Shift Keying (CDSK), Symmetric Chaos Shift Keying (SCSK) and Frequency-Modulated Differential Chaos Shift Keying (FM-DCSK). The performance of this comparison system is evaluated by using total 1806 CBDM signals for each of these feature extraction methods. Mean correct classification rate is about 98.76% for the sample CBDM signals. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a novel particle swarm optimization (PSO) algorithm based on Markov chains and competitive penalized method. Such an algorithm is developed to solve global optimization problems with applications in identifying unknown parameters of a class of genetic regulatory networks (GRNs). By using an evolutionary factor, a new switching PSO (SPSO) algorithm is first proposed and analyzed, where the velocity updating equation jumps from one mode to another according to a Markov chain, and acceleration coefficients are dependent on mode switching. Furthermore, a leader competitive penalized multi-learning approach (LCPMLA) is introduced to improve the global search ability and refine the convergent solutions. The LCPMLA can automatically choose search strategy using a learning and penalizing mechanism. The presented SPSO algorithm is compared with some well-known PSO algorithms in the experiments. It is shown that the SPSO algorithm has faster local convergence speed, higher accuracy and algorithm reliability, resulting in better balance between the global and local searching of the algorithm, and thus generating good performance. Finally, we utilize the presented SPSO algorithm to identify not only the unknown parameters but also the coupling topology and time-delay of a class of GRNs. [ABSTRACT FROM AUTHOR]

Abstract: Belief revision, as one central problem in artificial intelligence, is of interest in decision-making and game theory. To deal with local belief change that is a desirable property for belief revision, a novel notion – the finest splitting was proposed by Parikh, Kourousias and Makinson, respectively. But it was not clear how to construct the finest splitting of a propositional theory (a closed set of propositional formulae). In this paper, we propose a constructive method, that is intractable generally, to compute the finest splitting of a propositional theory. We also propose a polynomial time algorithm to compute the finest splitting of a propositional theory consisting of clauses. As an application in the diagnosis theory, we show that, given a diagnosis system , it is quite easy to compute all of its diagnosis if the splitting of is pre-computed. Additionally, in terms of this approach, we can have more specific reason to interpret observation than the original one. [Copyright &y& Elsevier]