Lung cancer classification using neural networks for CT images

Early detection of cancer is the most promising way to enhance a patient's chance for survival. This paper presents a computer aided classification method in computed tomography (CT) images of lungs developed using artificial neural network. The entire lung is segmented from the CT images and the parameters are calculated from the segmented image. The statistical parameters like mean, standard deviation, skewness, kurtosis, fifth central moment and sixth central moment are used for classification. The classification process is done by feed forward and feed forward back propagation neural networks. Compared to feed forward networks the feed forward back propagation network gives better classification. The parameter skewness gives the maximum classification accuracy. Among the already available thirteen training functions of back propagation neural network, the Traingdx function gives the maximum classification accuracy of 91.1%. Two new training functions are proposed in this paper. The results show that the proposed training function 1 gives an accuracy of 93.3%, specificity of 100% and sensitivity of 91.4% and a mean square error of 0.998. The proposed training function 2 gives a classification accuracy of 93.3% and minimum mean square error of 0.0942.     

Enhanced avatar control using neural networks

This paper presents realistic avatar movements using a limited number of sensors. An inverse kinematics algorithm, SHAKF, is used to configure an articulated skeletal model, and a neural network is employed to predict the movement of joints not bearing sensors. The results show that the neural network is able to give a very close approximation to the actual rotation of the joints. This allows a substantial reduction in the number of sensors to configure an articulated human skeletal model.     

Portfolio selection using neural networks

In this paper we apply a heuristic method based on artificial neural networks (NN) in order to trace out the efficient frontier associated to the portfolio selection problem. We consider a generalization of the standard Markowitz mean-variance model which includes cardinality and bounding constraints. These constraints ensure the investment in a given number of different assets and limit the amount of capital to be invested in each asset. We present some experimental results obtained with the NN heuristic and we compare them to those obtained with three previous heuristic methods. The portfolio selection problem is an instance from the family of quadratic programming problems when the standard Markowitz mean-variance model is considered. But if this model is generalized to include cardinality and bounding constraints, then the portfolio selection problem becomes a mixed quadratic and integer programming problem. When considering the latter model, there is not any exact algorithm able to solve the portfolio selection problem in an efficient way. The use of heuristic algorithms in this case is imperative. In the past some heuristic methods based mainly on evolutionary algorithms, tabu search and simulated annealing have been developed. The purpose of this paper is to consider a particular neural network (NN) model, the Hopfield network, which has been used to solve some other optimisation problems and apply it here to the portfolio selection problem, comparing the new results to those obtained with previous heuristic algorithms.     

Learning images using compositional pattern-producing neural networks for source camera identification and digital demographic diagnosis

In this work, we propose a neural network based framework to explore the statistical correlation intrinsically embedded due to interpolations in a relatively small neighborhood, in which the interpolation process is cognized from the interpolation results and the spatially invariant stylized computational rules in interpolation algorithms are simulated and learned by adjusting weights and bias values of neural networks. Experiments show that, our approach is competitive among the state of the art of source camera identification methods. It is also effective for digital forgery detection and other interesting experiments such as the digital demographic diagnosis and prediction. The framework can also be applied to other types of image interpolations such as super-resolution.     

Stochastic neural networks

The first purpose of this paper is to present a class of algorithms for finding the global minimum of a continuous-variable function defined on a hypercube. These algorithms, based on both diffusion processes and simulated annealing, are implementable as analog integrated circuits. Such circuits can be viewed as generalizations of neural networks of the Hopfield type, and are called diffusion machines.Our second objective is to show that learning in these networks can be achieved by a set of three interconnected diffusion machines: one that learns, one to model the desired behavior, and one to compute the weight changes.This research was supported in part by U.S. Army Research Office Grant DAAL03-89-K-0128.     

SR-30 turbojet engine real-time sensor health monitoring using neural networks,and Bayesian belief networks

This paper describes the use of artificial intelligence-based techniques for detecting and isolating sensor failures in a turbojet engine. Specifically, three artificial intelligence (AI) techniques are employed: artificial neural networks (NNs), statistical expectations, and Bayesian belief networks (BBNs). These techniques are combined into an overall system that is capable of distinguishing between sensor failure and engine failure—a critical capability in the operation of turbojet engines. The turbojet engine used in this study is an SR-30 developed by Turbine Technologies. Initially, NNs were designed and trained to recognize sensor failure in the engine. The increased random noise output from failing sensors was used as the key indicator. Next, a Bayesian statistical method was used to recognize sensor failure based on the bias error occurring in the sensors. Finally, a BBN was developed to interpret the results of the NN and statistical evaluations. The BBN determines whether single or multiple sensor failures signify engine failure, or whether sensor failures represent separate, unrelated incidences. The BBN algorithm is also used to distinguish between bias and noise errors on sensors used to monitor turbojet performance. The overall system is demonstrated to work equally well during start-up and main-stage operation of the engine. Results show that the method can efficiently detect and isolate single or multiple sensor failures within this dynamic environment.     

Noise analysis of robot manipulator using neural networks

Due to a lot of robot manipulators application in industry, low noise degree is very important criteria for robot manipulator's joints. In this paper, joint noise problem of a robot manipulator with five joints is investigated both theoretically and experimentally. The investigation is consisted of two steps. First step is to analyze the noise of joints using a hardware and software. The hardware is a part of noise sensors. The second step; according to experimental results, some neural networks are employed for finding robust neural noise analyzer. Five types of neural networks are used to compare each other. From the results, it is noted that the proposed RBFNN gives the best results for analyzing joint noise of the robot manipulator.     

遥感图像飞机目标分类的卷积神经网络方法

目的 遥感图像飞机目标分类,利用可见光遥感图像对飞机类型进行有效区分,对提供军事作战信息有重要意义。针对该问题,目前存在一些传统机器学习方法,但这些方法需人工提取特征,且难以适应真实遥感图像的复杂背景。近年来,深度卷积神经网络方法兴起,网络能自动学习图像特征且泛化能力强,在计算机视觉各领域应用广泛。但深度卷积神经网络在遥感图像飞机分类问题上应用少见。本文旨在将深度卷积神经网络应用于遥感图像飞机目标分类问题。方法 在缺乏公开数据集的情况下,收集了真实可见光遥感图像中的8种飞机数据,按大致4∶1的比例分为训练集和测试集,并对训练集进行合理扩充。然后针对遥感图像与飞机分类的特殊性,结合深度学习卷积神经网络相关理论,有的放矢地设计了一个5层卷积神经网络。结果 首先,在逐步扩充的训练集上分别训练该卷积神经网络,并分别用同一测试集进行测试,实验表明训练集扩充有利于网络训练,测试准确率从72.4%提升至97.2%。在扩充后训练集上,分别对经典传统机器学习方法、经典卷积神经网络LeNet-5和本文设计的卷积神经网络进行训练,并在同一测试集上测试,实验表明该卷积神经网络的分类准确率高于其他两种方法,最终能在测试集上达到97.2%的准确率,其余两者准确率分别为82.3%、88.7%。结论 在少见使用深度卷积神经网络的遥感图像飞机目标分类问题上,本文设计了一个5层卷积神经网络加以应用。实验结果表明,该网络能适应图像场景,自动学习特征,分类效果良好。     

Fault detection on robot manipulators using artificial neural networks

Nowadays, gas welding applications on vehicle’s parts with robot manipulators have increased in automobile industry. Therefore, the speed of end-effectors of robot manipulator is affected on each joint during the welding process with complex trajectory. For that reason, it is necessary to analyze the noise and vibration of robot’s joints for predicting faults. This paper presents an experimental investigation on a robot manipulator, using neural network for analyzing the vibration condition on joints. Firstly, robot manipulator’s joints are tested with prescribed of trajectory end-effectors for the different joints speeds. Furthermore, noise and vibration of each joint are measured. And then, the related parameters are tested with neural network predictor to predict servicing period. In order to find robust and adaptive neural network structure, two types of neural predictors are employed in this investigation. The results of two approaches improved that an RBNN type can be employed to predict the vibrations on industrial robots.     

Pruning backpropagation neural networks using modern stochastic optimisation techniques

Approaches combining genetic algorithms and neural networks have received a great deal of attention in recent years. As a result, much work has been reported in two major areas of neural network design: training and topology optimisation. This paper focuses on the key issues associated with the problem of pruning a multilayer perceptron using genetic algorithms and simulated annealing. The study presented considers a number of aspects associated with network training that may alter the behaviour of a stochastic topology optimiser. Enhancements are discussed that can improve topology searches. Simulation results for the two mentioned stochastic optimisation methods applied to non-linear system identification are presented and compared with a simple random search.     

Downstream performance prediction for a manufacturing system using neural networks and six-sigma improvement techniques

Intelligent techniques have been applied in a range of industrial environments [Meziane F, Vadera S, Kobbacy K, Proudlove N. Intelligent systems in manufacturing: current developments and future prospects. Integrated Manuf Syst 2000;11(4):218–38; Stephanopoulos G, Han C. Intelligent systems in process engineering: a review. Comput Chem Eng, 1996;20 (6–7):743–91; Johnston AB, Maguire LP, McGinnity TM. Using business improvement techniques to inform the optimisation of production cycle time: an industrial case study. Proceedings of the IEEE SMC UK-RI Chapter conference 2004 on intelligent cybernetic systems. September 7–8, 2004 ISSN:1744–9189; Proudlove NC, Vadera S, Kobbacy KAH. Intelligent management systems in operations: A review. J Oper Res Soc, 1998;49(7):682–99] although their implementation is not the first choice of many process engineers. In contrast process engineers in a diverse range of manufacturing environments regularly deploy business improvement techniques, such as the six-sigma methodology. Such techniques aim to control and subsequently identify the relationship between the process inputs and outputs so that a process engineer can more accurately predict how the process output shall perform based on the system inputs. Factors such as cost reduction, automatic process control or simply process prediction may be the defining factors in establishing prediction models.     

Feature extraction method for a robot map using neural networks

Many map-building algorithms using ultrasonic sensors have been developed for mobile robot applications. In indoor environments, the ultrasonic sensor system gives some uncertain data. To compensate for this effect, a new feature extraction method using neural networks is proposed. A new, effective representation of the target is defined, and the reflection wave data patterns are learnt using neural networks. As a consequence, the targets are classified as planes, corners, or edges, which all frequently occur in indoor environments. We constructed our own robot system for the experiments which were carried out to show the performance. This work was presented in part at the 7th International Symposium on Artificial Life and Robotics, Oita, Japan, January 16–18, 2002     

Aeromagnetic compensation using neural networks

Airborne magnetic surveys in geophysical exploration can be subject to interference effects from the aircraft. Principal sources are the permanent magnetism of various parts of the aircraft, induction effects created by the earth's magnetic field and eddy-current fields produced by the aircraft's manoeuvres. Neural networks can model these effects as functions of roll, pitch, heading and their time derivatives, together with vertical acceleration, charging currents to the generator, etc., without assuming an explicit physical model. Separation of interference effects from background regional and diurnal fields can also be achieved in a satisfactory way.     

Segmentation of ultrasound images by using a hybrid neural network

A hybrid neural network is presented for the segmentation of ultrasound images.

Feature vectors are formed by the discrete cosine transform of pixel intensities in region of interest (ROI). The elements and the dimension of the feature vectors are determined by considering only two parameters: The amount of ignored coefficients, and the dimension of the ROI.

First-layer-nodes of the proposed hybrid network represent hyperspheres (HSs) in the feature space. Feature space is partitioned by intersecting these HSs to represent the distribution of classes. The locations and radii of the HSs are found by the genetic algorithms.

Restricted Coulomb energy (RCE) network, modified RCE network, multi-layer perceptron and the proposed hybrid neural network are examined comparatively for the segmentation of ultrasound images.     

Analysis of radar images for rainfall forecasting using neural networks

This paper describes a new approach to the analysis of weather radar data for short-range rainfall forecasting based on a neural network model. This approach consists in extracting synthetic information from radar images using the approximation capabilities of multilayer neural networks. Each image in a sequence is approximated using a modified radial basis function network trained by a competitive mechanism. Prediction of the rain field evolution is performed by analysing and extrapolating the time series of weight values. This method has been compared to the conventional cross-correlation technique and the persistence method for three different rainfall events, showing significant improvement in 30 and 60 min ahead forecast accuracy.     

自组织多模型逼近性能分析与改进

针对基于自组织映射神经网络的非线性函数逼近,研究其方法和原理,指出它与一般前向神经网络在逼近原理上的不同．在此基础上,进一步研究该方法的逼近性能,分析其两个不足之处,进而提出一种提高逼近性能的改进神经网络训练策略．最后通过仿真实例验证了所得结论,表明了改进方法的有效性．     

Nonlinear systems identification using dynamic multi-time scale neural networks

In this paper, two Neural Network (NN) identifiers are proposed for nonlinear systems identification via dynamic neural networks with different time scales including both fast and slow phenomena. The first NN identifier uses the output signals from the actual system for the system identification. The on-line update laws for dynamic neural networks have been developed using the Lyapunov function and singularly perturbed techniques. In the second NN identifier, all the output signals from nonlinear system are replaced with the state variables of the neuron networks. The on-line identification algorithm with dead-zone function is proposed to improve nonlinear system identification performance. Compared with other dynamic neural network identification methods, the proposed identification methods exhibit improved identification performance. Three examples are given to demonstrate the effectiveness of the theoretical results.     

Servo controller design using neural networks

The dynamics of a physical plant may be difficult to express as concise mathematical equations. In practice there exist uncertainties that cannot be modeled with the system equations. Hence, robustness against system uncertainties is essential in a control system design. In this article, multilayered neural networks (MNNs) are used to compensate for model uncertainties of a dynamical system. Neural network models are used along with a classical linear servo controller derived from the linear state space equations. These models are trained so that system uncertainties are compensated. The design of a servo system indicates the enhanced performance of the neural-network-based servo controller as compared to the classical servo controller.     

Scenery image recognition and interpretation using fuzzy inference neural networks

In this paper, we propose a new image recognition and interpretation system. The proposed system is composed of three processes: (1) regional segmentation process; (2) image recognition process; and (3) image interpretation process. As a pre-processing in the regional segmentation process, an input image is divided into some proper regions using techniques based on K-means algorithm. In both the image recognition and the interpretation processes, fuzzy inference neural networks (FINNs) working in parallel are employed to achieve a high level of recognition and interpretation. Scenery images are used and it is confirmed that the system has an average of 71.9% accuracy rate in the recognition process and good results in the interpretation process without heuristic knowledge. In addition, it is also confirmed that the proposed system has an ability to extract proper rules for the image recognition and interpretation.     

A new learning method using prior information of neural networks

In this paper, we present a new learning method using prior information for three-layer neural networks. Usually when neural networks are used for identification of systems, all of their weights are trained independently, without considering interrelated weights values. Thus, the training results are usually not good. The reason for this in that each parameter has its influence on others during learning. To overcome this problem, we first give an exact mathematical equation that describes the relation between weight values given a set of data conveying prior information. The we present a new learning method that trains part of the weights and calculates the others using these exact mathematical equations. This method often a priori keeps the given mathematical structure exactly the same during learning; in other words, training is done so that the network follows a predetermined trajectory. Numerical computer simulation results are provided to support this approach. This work was presented, in part, at the Fourth International Symposium on Artificial Life and Robotics, Oita, Japan, January 19–22, 1999.