用细胞神经网络提取二值与灰度图象边缘

边缘是图象的重要特征,采用细胞神经网络提取图象边缘时,网络参数的选择是一个重要问题。为了能够有效地提取图象边缘,基于高通滤波模板,选择了细胞神经网络的一组简单易行的参数,首先将其用于检测二值图象边缘,再在此基础上,通过综合灰度值各位面边缘检测的结果提取出灰度图象的边缘。与传统边缘提取方法Sobel和Log方法的比较可见,该方法是有效的,并且由于细胞神经网络具有高速并行运算、便于硬件实现等特点,因此使其在图象实时处理中具有更大的潜力。     

Temporary short circuit detection in induction motor winding using combination of wavelet transform and neural network

Monitoring system for induction motor is widely developed to detect the incipient fault. Such system is desirable to detect the fault at the running condition to avoid the motor stop running suddenly. In this paper, a new method for detection system is proposed that emphasizes the fault occurrences as temporary short circuit in induction motor winding. The investigation of fault detection is focused on the transient phenomena during starting and ending points of temporary short circuit. The proposed system utilizes the wavelet transform for processing the motor current signal. Energy level of high frequency signal from wavelet transform is used as the input variable of neural network which works as detection system. Three types of neural networks are developed and evaluated including feed forward neural network (FFNN), Elman neural network (ELMNN) and radial basis functions neural network (RBFNN). The results show that ELMNN is the most simply and accurate system that can recognize all of unseen data test. Laboratory based experimental setup is performed to provide real-time measurement data for this research.     

Orthogonality of decision boundaries in complex-valued neural networks

This letter presents some results of an analysis on the decision boundaries of complex-valued neural networks whose weights, threshold values, input and output signals are all complex numbers. The main results may be summarized as follows. (1) A decision boundary of a single complex-valued neuron consists of two hypersurfaces that intersect orthogonally, and divides a decision region into four equal sections. The XOR problem and the detection of symmetry problem that cannot be solved with two-layered real-valued neural networks, can be solved by two-layered complex-valued neural networks with the orthogonal decision boundaries, which reveals a potent computational power of complex-valued neural nets. Furthermore, the fading equalization problem can be successfully solved by the two-layered complex-valued neural network with the highest generalization ability. (2) A decision boundary of a three-layered complex-valued neural network has the orthogonal property as a basic structure, and its two hypersurfaces approach orthogonality as all the net inputs to each hidden neuron grow. In particular, most of the decision boundaries in the three-layered complex-valued neural network inetersect orthogonally when the network is trained using Complex-BP algorithm. As a result, the orthogonality of the decision boundaries improves its generalization ability. (3) The average of the learning speed of the Complex-BP is several times faster than that of the Real-BP. The standard deviation of the learning speed of the Complex-BP is smaller than that of the Real-BP.It seems that the complex-valued neural network and the related algorithm are natural for learning complex-valued patterns for the above reasons.     

An orthogonal neural network for function approximation

This paper presents a new single-layer neural network which is based on orthogonal functions. This neural network is developed to avoid the problems of traditional feedforward neural networks such as the determination of initial weights and the numbers of layers and processing elements. The desired output accuracy determines the required number of processing elements. Because weights are unique, the training of the neural network converges rapidly. An experiment in approximating typical continuous and discrete functions is given. The results show that the neural network has excellent performance in convergence time and approximation error.     

融合神经网络的布料碰撞检测算法

目的 针对当前在虚拟环境中布料柔体碰撞检测效率慢和准确性低的问题,提出一种根节点双层包围盒树结构和融合OpenNN （open neural networks library）神经网络加速预测碰撞检测的算法。方法 首先改进了碰撞检测常用的包围盒技术,提出根节点双层包围盒算法,减少包围盒的构造时间。其次使用神经网络优化碰撞检测技术,利用神经网络可以处理大量数据的优势,每次可以检测大量基本图元是否发生碰撞,解决了碰撞检测计算复杂性高的问题。最后准确地找到碰撞粒子并做出碰撞响应。结果 在相同的复杂布料模型情况下,根节点双层包围盒算法在运行速度上比传统混合包围盒算法快,耗时缩减了5.51%~11.32%。基于OpenNN算法的总耗时比根节点双层包围盒缩减了11.70%,比融合DNN （deep neural network）的自碰撞检测算法减少了6.62%。随着碰撞检测难度的增大,当布料模型的精度增加84%时,传统物理碰撞检测方法用时增加96%,融合DNN的自碰撞检测算法用时增加90.11%,而本文基于神经网络的算法用时仅增加了68.37%,同时表现出更高的稳定性,满足使用者对实时性的要求。结论 对于模拟场景中简单模型的碰撞,本文提出的根节点双层包围盒算法比传统的包围盒方法耗时短。对于复杂模型,基于OpenNN神经网络的碰撞检测算法在效率上优于传统的包围盒算法和融合DNN的自碰撞检查算法,而且模拟效果的准确性也得以保证,是一种高效的碰撞检测方法。     

Performance comparison between the training method and the numerical method of the orthogonal neural network in function approximation

The orthogonal neural network is a recently developed neural network based on the properties of orthogonal functions. It can avoid the drawbacks of traditional feedforward neural networks such as initial values of weights, number of processing elements, and slow convergence speed. Nevertheless, it needs many processing elements if a small training error is desired. Therefore, numerous data sets are required to train the orthogonal neural network. In the article, a least‐squares method is proposed to determine the exact weights by applying limited data sets. By using the Lagrange interpolation method, the desired data sets required to solve for the exact weights can be calculated. An experiment in approximating typical continuous and discrete functions is given. The Chebyshev polynomial is chosen to generate the processing elements of the orthogonal neural network. The experimental results show that the numerical method in determining the weights gives as good performance in approximation error as the known training method and the former has less convergence time. © 2004 Wiley Periodicals, Inc. Int J Int Syst 19: 1257–1275, 2004.     

A collisions evaluation method in virtual environment for collaborativeassembly

Collision detection is critical for collaborative assembly simulation to assist design processing. However, collisions between polygonal models may not reflect collisions between real objects in reality because of polygonal approximation and designed tolerance. This problem reduces the reliability of simulation in collaborative assembly and sometimes even results in wrong conclusions. To solve the problem, we propose a novel collision evaluation algorithm based on generalized penetration depth, approximation information, and tolerance information. Given two interfered polygonal models, generalized penetration depth is calculated using relative motion information. Then two thresholds, which are based on approximation information and tolerance information, are integrated to evaluate collisions between polygonal models. In order to distinguish the status of collisions for further analysis, the collisions between polygonal models are categorized into three types by evaluation algorithm, namely real collision, potential collision, and fake collision. Computational efficiency and accuracy of the evaluation algorithm are verified in a virtual collaborative assembly environment.     

Collision Detection Algorithm to Distinguish Between Intended Contact and Unexpected Collision

Industrial and service robots often physically interact with humans, and thus, human safety during these interactions becomes significantly important. Several solutions have been proposed to guarantee human safety, and one of the most practical, efficient solutions is the collision detection using generalized momentum and joint torque sensors. This method allows a robot to detect a collision and react to it as soon as possible to minimize the impact. However, the conventional collision detection methods cannot distinguish between intended contacts and unexpected collisions, and thus they cannot be used during certain tasks such as teaching and playback or force control. In this paper, we propose a novel collision detection algorithm which can distinguish intended contacts and unexpected collisions. In most cases, the external force during a collision shows a noticeably faster rate of change than that during an intended contact, and using this difference, the proposed observer can distinguish one from the other. Several experiments were conducted to show that the proposed algorithm can effectively distinguish intended contacts and unexpected collisions.     

基于线性规划的碰撞检测算法研究

介绍了虚拟环境中一种基于凸多面体面信息对偶线性规划模型(DualModel)的快速旋转和移动物体之间干涉碰撞实时检测方法。该文详细介绍了建模过程和求解步骤,物体由构成凸多面体的三角形面信息表示,而物体的运动由一组虚拟现实环境中的全局移动和旋转矩阵表示。这种数学编程方法具有数据结构简单、算法可靠和速度快等优点,同时能够很好地解决高速(运动帧)碰撞的问题。这一方法通过使用主-对偶(primal-dual)内点方法来解线性规划方程,具有很好的效果,能够检测多物体对之间的碰撞。实验结果表明,基于数学编程的方法相对两种著名的工具包I-COLLIDE和SOLID,具有速度快和稳定可靠的优点,而I-COLLIDE和SOLID工具包基于两种著名的算法:LinCanny(LC)最近特征算法和GJK算法(EnhancedGilbertJohnsonandKeethialgorithm)。     

Robust Detection of MAC Layer Denial-of-Service Attacks in CSMA/CA Wireless Networks

Carrier-sensing multiple-access with collision avoidance (CSMA/CA)-based networks, such as those using the IEEE 802.11 distributed coordination function protocol, have experienced widespread deployment due to their ease of implementation. The terminals accessing these networks are not owned or controlled by the network operators (such as in the case of cellular networks) and, thus, terminals may not abide by the protocol rules in order to gain unfair access to the network (selfish misbehavior), or simply to disturb the network operations (denial-of-service attack). This paper presents a robust nonparametric detection mechanism for the CSMA/CA media-access control layer denial-of-service attacks that does not require any modification to the existing protocols. This technique, based on the $M$ -truncated sequential Kolmogorov–Smirnov statistics, monitors the successful transmissions and the collisions of the terminals in the network, and determines how “explainable” the collisions are given for such observations. We show that the distribution of the explainability of the collisions is very sensitive to changes in the network, even with a changing number of competing terminals, making it an excellent candidate to serve as a jamming attack indicator. Ns-2 simulation results show that the proposed method has a very short detection latency and high detection accuracy.      

基于网络效用最大化与冲突避免的无线传感器网络MAC协议

针对周期汇报型无线传感器网络(WSN)中的无线信号冲突和能量利用效率问题,提出了一种基于网络效用最大化与冲突避免的媒体访问控制(UM-MAC)协议。该协议基于时分多路复用(TDMA)调度机制,将效用模型引入无冲突的节点工作时隙分配过程中,把链路可靠性、网络能耗归纳到一个统一的效用优化框架中;进而提出了一个启发式算法,使网络能够快速找到一个基于网络效用最大化与冲突避免的节点工作时隙调度方案。将UM-MAC协议与S-MAC协议和冲突避免MAC(CA-MAC)协议进行比较,在不同节点数量的网络环境中,UM-MAC获得的网络效用较大,平均数据包成功发送率较高,生命周期介于S-MAC与CA-MAC之间,在不同的网络负载下所有节点发数据包到汇聚节点的平均时延有所增加。仿真实验结果表明:UM-MAC协议较好地解决了冲突干扰问题,提高了网络的数据包成功发送率和能量利用效率等性能;在低网络负载时,TDMA类协议的性能并不比竞争类协议好。     

On avoiding RTS collisions for IEEE 802.11-based wireless ad hoc networks

The paper proposes an RCA (RTS collision avoidance) MAC protocol to reduce RTS collisions for IEEE 802.11-based mobile ad hoc networks (MANETs). RTS/CTS exchanging is used for the resolution of the hidden terminal problem. However, the paper shows that, even the backoff counters of two stations are different, RTS frames are also collided to each other due to the hidden terminal problem. The situation would be getting worse in high traffic load or in a dense network. RTS collisions not only result in the following CTS or ACK collisions, but also induce false blocking problem, even dead locks of transmissions. To address the above problems, an RCA MAC protocol is proposed to reduce RTS collisions. The RCA protocol utilizes a narrow band, called the tone channel, to announce the RTS transmission in advance in order to preclude the RTS transmissions of two-hop neighbors. To reduce the channel and hardware overhead, an improvement to the RCA protocol is also devised, which only uses a single channel and one transceiver to reduce RTS collisions. The RCA protocol provides a type of fast collision detection and decreases the probability of RTS collisions, which is benefit for RTS/CTS exchange scheme. Meanwhile, the RCA protocol can reduce the retransmission cost and have lower control overhead than that of IEEE 802.11 DCF. In addition, simulation results verify the advantages of the RCA protocol in comparison with IEEE 802.11 DCF.     

Two-frame structure from motion using optical flow probability distributions for unmanned air vehicle obstacle avoidance

See-and-avoid behaviors are an essential part of autonomous navigation for Unmanned Air Vehicles (UAVs). To be fully autonomous, a UAV must be able to navigate complex urban and near-earth environments and detect and avoid imminent collisions. While there have been significant research efforts in robotic navigation and obstacle avoidance during the past few years, this previous work has not focused on applications that use small autonomous UAVs. Specific UAV requirements such as non-invasive sensing, light payload, low image quality, high processing speed, long range detection, and low power consumption, etc., must be met in order to fully use this new technology. This paper presents single camera collision detection and avoidance algorithm. Whereas most algorithms attempt to extract the 3D information from a single optical flow value at each feature point, we propose to calculate a set of likely optical flow values and their associated probabilities—an optical flow probability distribution. Using this probability distribution, a more robust method for calculating object distance is developed. This method is developed for use on a UAV to detect obstacles, but it can be used on any vehicle where obstacle detection is needed.     

基于复合正交神经网络的自适应逆控制系统

目前，在自适应逆控制系统中常采用BP神经网络，而BP网络存在算法复杂、易陷入局部极小解等不足。而正交神经网络能克服BP网络的不足，但由于正交神经网络学习算法存在某些局限性，提出了一种复合正交神经网络，该正交网络结构与三层前向正交网络相同，不同的是正交网络的隐单元处理函数采用带参数的Sigmoid函数的复合正交函数，该神经网络算法简单，学习收敛速度快，并能对网络的函数参数进行优化，为非线性系统的动态建模提供了一种方法。仿真实验表明，网络在用于过程的自适应逆控制中具有很高的控制精度和自适应学习能力。该动态神经网络比其它神经网络具有更强的建模能力与学习适应性，有线性、非线性逼近精度高等优异特性，非常适合于实时控制系统。     

Flow-based anomaly detection in high-speed links using modified GSA-optimized neural network

Ever growing Internet causes the availability of information. However, it also provides a suitable space for malicious activities, so security is crucial in this virtual environment. The network intrusion detection system (NIDS) is a popular tool to counter attacks against computer networks. This valuable tool can be realized using machine learning methods and intrusion datasets. Traditional datasets are usually packet-based in which all network packets are analyzed for intrusion detection in a time-consuming process. On the other hand, the recent spread of 1–10-Gbps-technologies have clearly pointed out that scalability is a growing problem. In this way, flow-based solutions can help to solve the problem by reduction of data and processing time, opening the way to high-speed detection on large infrastructures. Besides, NIDS should be capable of detecting new malicious activities. Artificial neural network-based NIDSs can detect unseen attacks, so a multi-layer perceptron (MLP) neural classifier is used in this study to distinguish benign and malicious traffic in a flow-based NIDS. In this way, a modified gravitational search algorithm (MGSA), as a modern heuristic technique, is employed to optimize the interconnection weights of the neural anomaly detector. The proposed scheme is trained using an enhanced version of the first labeled flow-based dataset for intrusion detection introduced in 2009. In addition, the particle swarm optimization (PSO) algorithm and traditional error back-propagation (EBP) algorithm are employed to train MLP, so performance comparison becomes possible. The experimental results based on the actual network data show that the MGSA-optimized neural anomaly detector is effective for monitoring abnormal traffic flows in the gigabytes traffic environment, and the accuracy is about 97.8 %.     

Tracking a maneuvering target using neural fuzzy network

A fast target maneuver detecting and highly accurate tracking technique using a neural fuzzy network based on Kalman filter is proposed in this paper. In the automatic target tracking system, there exists an important and difficult problem: how to detect the target maneuvers and fast response to avoid miss-tracking? The traditional maneuver detection algorithms, such as variable dimension filter (VDF) and input estimation (IE) etc., are computation intensive and difficult to implement in real time. To solve this problem, neural network algorithms have been issued recently. However, the normal neural networks such as backpropagation networks usually produce the extra problems of low convergence speed and/or large network size. Furthermore, the way to decide the network structure is heuristic. To overcome these defects and to make use of neural learning ability, a developed standard Kalman filter with a self-constructing neural fuzzy inference network (KF-SONFIN) algorithm for target tracking is presented in this paper. By generating possible target trajectories including maneuver information to train the SONFIN, the trained SONFIN can detect when the maneuver occurred, the magnitude of maneuver values and when the maneuver disappeared. Without having to change the structure of Kalman filter nor modeling the maneuvering target, this new algorithm, SONFIN, can always find itself an economic network size with a fast learning process. Simulation results show that the KF-SONFIN is superior to the traditional IE and VDF methods in estimation accuracy.     

基于神经网络的高效智能入侵检测系统

描述了一种采用人工神经网络技术的高效实时入侵检测模型，对网络数据处理、神经网络的训练及其算法、神经网络的检测及其算法进行了详细的论述，目的是用神经网络的优势来改进现存入侵检测系统中的一些不足之处，使入侵检测系统效率更高，更具智能化。     

利用改进灰狼算法优化BP神经网络的入侵检测

神经网络技术被广泛应用于网络安全领域,在入侵检测中能够实现网络攻击的主动检测和攻击分类.然而随着恶意攻击的不断演化,神经网络技术存在的弊端日益显现.针对BP神经网络在入侵检测过程中存在的初始值随机性较大以及易陷入局部最优的问题,本文提出一种改进灰狼算法优化BP神经网络的入侵检测模型(IGWO-BP).首先,使用混沌映射初始化种群、设计非线性收敛因子以及动态权重策略对传统灰狼算法进行改进,并以此优化BP神经网络的初始权值和阈值,并运用改进BP神经网络对网络安全数据集进行实际检测.实验结果表明,IGWO-BP模型在NSL-KDD和UNSW-NB15数据集上取得了较优的检测结果,与其它现有模型相比性能也有较大提升.     

Minimum-Time Aggregation Scheduling in Duty-Cycled Wireless Sensor Networks

Aggregation is an important and commonplace operation in wireless sensor networks. Due to wireless interferences, aggregation in wireless sensor networks often suffers from packet collisions. In order to solve the collision problem, aggregation scheduling is extensively researched in recent years. In many sensor network applications such as real-time monitoring, aggregation time is the most concerned performance. This paper considers the minimum-time aggregation scheduling problem in duty-cycled wireless sensor networks for the first time. We show that this problem is NP-hard and present an approximation algorithm based on connected dominating set. The theoretical analysis shows that the proposed algorithm is a nearly-constant approximation. Simulation shows that the scheduling algorithm has a good performance.     

Collision identification between convex polyhedra using neuralnetworks

Collision identification between convex polyhedra is a major research focus in computer-aided manufacturing and path planning for robots. This paper presents a collision-identification neural network (CINN) to identify possible collisions between two convex polyhedra. It consists of a modified Hamming net and a constraint subnet. The modified Hamming net is designed for point-to-polyhedron collision identification, and the constraint subnet is designed to move a point within a polyhedron and detect possible collisions with another polyhedron. A CINN has a simple canonical structure. It is very easy to program and can be implemented by a modest number of nonlinear amplifiers and three analog integrators. The working principle of the CINN is very similar to the well-known Hopfield net model. Its simple collective computing power accomplishes the relatively complicated task of collision identification between convex polyhedra, rendering a suitable device for online path planning of robots. An example is presented to demonstrate the application of CINN's to collision-free motion planning.