Search

Photocatalysts have made great contributions to the degradation of pollutants to achieve environmental purification. The traditional method of developing new photocatalysts is to design and perform a large number of experiments to continuously try to obtain efficient photocatalysts that can degrade pollutants, which is time-consuming, costly, and does not necessarily achieve the best performance of the photocatalyst. The rapid development of photocatalysis has been accelerated by the rapid development of artificial intelligence. Intelligent algorithms can be utilized to design photocatalysts and predict photocatalytic performance, resulting in a reduction in development time and the cost of new catalysts. In this paper, the intelligent algorithms for photocatalyst design and photocatalytic performance prediction are reviewed, especially the artificial neural network model and the model optimized by an intelligent algorithm. A detailed discussion is given on the advantages and disadvantages of the neural network model, as well as its application in photocatalysis optimized by intelligent algorithms. The use of intelligent algorithms in photocatalysis is challenging and long term due to the lack of suitable neural network models for predicting the photocatalytic performance of photocatalysts. The prediction of photocatalytic performance of photocatalysts can be aided by the combination of various intelligent optimization algorithms and neural network models, but it is only useful in the early stages. Intelligent algorithms can be used to design photocatalysts and predict their photocatalytic performance, which is a promising technology. [ABSTRACT FROM AUTHOR]

Simple Summary: Melanoma is the most dangerous type of skin cancer worldwide. Early detection of melanoma is crucial for better outcomes, but this often can be challenging. This research explores the use of artificial intelligence (AI) techniques combined with non-invasive imaging methods to improve melanoma detection. The authors aim to evaluate the current state of AI-based techniques using tools including dermoscopy, optical coherence tomography (OCT), and reflectance confocal microscopy (RCM). The findings demonstrate that several AI algorithms perform as well as or better than dermatologists in detecting melanoma, particularly in the analysis of dermoscopy images. This research highlights the potential of AI to enhance diagnostic accuracy, leading to improved patient outcomes. Further studies are needed to address limitations and ensure the reliability and effectiveness of AI-based techniques. Background: Melanoma, the deadliest form of skin cancer, poses a significant public health challenge worldwide. Early detection is crucial for improved patient outcomes. Non-invasive skin imaging techniques allow for improved diagnostic accuracy; however, their use is often limited due to the need for skilled practitioners trained to interpret images in a standardized fashion. Recent innovations in artificial intelligence (AI)-based techniques for skin lesion image interpretation show potential for the use of AI in the early detection of melanoma. Objective: The aim of this study was to evaluate the current state of AI-based techniques used in combination with non-invasive diagnostic imaging modalities including reflectance confocal microscopy (RCM), optical coherence tomography (OCT), and dermoscopy. We also aimed to determine whether the application of AI-based techniques can lead to improved diagnostic accuracy of melanoma. Methods: A systematic search was conducted via the Medline/PubMed, Cochrane, and Embase databases for eligible publications between 2018 and 2022. Screening methods adhered to the 2020 version of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Included studies utilized AI-based algorithms for melanoma detection and directly addressed the review objectives. Results: We retrieved 40 papers amongst the three databases. All studies directly comparing the performance of AI-based techniques with dermatologists reported the superior or equivalent performance of AI-based techniques in improving the detection of melanoma. In studies directly comparing algorithm performance on dermoscopy images to dermatologists, AI-based algorithms achieved a higher ROC (>80%) in the detection of melanoma. In these comparative studies using dermoscopic images, the mean algorithm sensitivity was 83.01% and the mean algorithm specificity was 85.58%. Studies evaluating machine learning in conjunction with OCT boasted accuracy of 95%, while studies evaluating RCM reported a mean accuracy rate of 82.72%. Conclusions: Our results demonstrate the robust potential of AI-based techniques to improve diagnostic accuracy and patient outcomes through the early identification of melanoma. Further studies are needed to assess the generalizability of these AI-based techniques across different populations and skin types, improve standardization in image processing, and further compare the performance of AI-based techniques with board-certified dermatologists to evaluate clinical applicability. [ABSTRACT FROM AUTHOR]

Curriculum is the basis of vocational training, its development level and teaching efficiency determine the realization of vocational training objectives, as well as the quality and level of major vocational academic training. Therefore, the development of curriculum is an important issue. And affect the school's teaching capacity building. The analysis of the latest developments in the main courses shows that there are some deviations or irrationalities in the curriculum in some colleges and universities, and the general problems of understanding the latest courses, such as lack of solid foundation in curriculum setting, unclear direction of objectives, unclear reform ideas, inadequate and systematic construction measures, lack of attention to the quality of education. This paper explains the rules for the establishment of first-level courses, clarifies the ideas and priorities of architecture, and explores strategies for building university-level courses using knowledge of artificial intelligence and neural network algorithms in order to gain experience from them. [ABSTRACT FROM AUTHOR]

As a consequence of increasing wind power penetration level, it will be a big challenge to control and operate the power system because of the inherent uncertainty of the wind energy. One of the ways to deal with the wind power variability is to predict it accurately and reliably. The traditional point forecasting-based technique cannot notably solve the uncertainty in power system operation. In order to compute the probabilistic forecasting, which yields information on the uncertainty of wind power, a novel hybrid intelligent method that incorporates the wavelet transform, neural network (NN), and improved krill herd optimization algorithm (IKHOA), is used in this paper. Also, the extreme learning machine is exerted to train NN and calculates point forecasts, and IKHOA is applied to forecast the noise variance. The robust method called bootstrap is regarded to create prediction intervals and calculate the model uncertainty. The efficiency of proposed forecasting engine is evaluated by usage of wind power data from the Alberta, Canada. [ABSTRACT FROM AUTHOR]

This paper presents a neural network-based method to generate multiple images with different exposures from a single input low dynamic range (LDR) image for improved high dynamic range (HDR) imaging. The proposed algorithm consists of three steps: 1) 2-D histogram estimation; 2) neural network-based LDR images estimation; and 3) generation of an optimal set of differently exposed images. The proposed method first generates image features by estimating a patched-based 2-D histogram. The extracted features are used in an input layer of the neural network, which plays a role to select an optimal set of LDR images. A set of LDR images is generated using a curvature-based contrast enhancement method. Experimental results show that the proposed method can generate an optimal set of LDR images using neural network and provide improved HDR images. In addition, the proposed method can be implemented as a preprocessing step in most existing HDR frameworks. The proposed HDR approach is considered as a single-input method that gives almost the same performance to multiple image-based HDR method. [ABSTRACT FROM PUBLISHER]

This paper describes a novel method of facial representation and recognition based upon adaptive processing of tree structures. Instead of the conventional flat vector representation for a face, a neural network approach-based technique is proposed to transform the Localised Gabor Feature (LGF) vectors extracted from human facial components into Human Face Tree Structure (HFTS) to represent a human face. A structural training algorithm is assigned to train and recognize the face identity in this HFTS representation with the corresponding LGF vectors. By benchmarking using the tested public face databases presented in this paper, our approach is able to achieve accuracy up to 90% under different scenarios of lighting conditions and posture orientations. [ABSTRACT FROM AUTHOR]

This paper proposes a new passive robust fault detection scheme using non-linear models that include parameter uncertainty. The non-linear model considered here is described by a group method of data handling (GMDH) neural network. The problem of passive robust fault detection using models including parameter uncertainty has been mainly addressed by checking if the measured behaviour is inside the region of possible behaviours based on the so-called forward test since it bounds the direct image of an interval function. The main contribution of this paper is to propose a new backward test, based on the inverse image of an interval function, that allows checking if there exists a parameter in the uncertain parameter set that is consistent with the measured system behaviour. This test is implemented using interval constraint satisfaction algorithms which can perform efficiently in deciding if the measured system state is consistent with the GMDH model and its associated uncertainty. Finally, this approach is tested on the servoactuator being a FDI benchmark in the European Project DAMADICS. [Copyright &y& Elsevier]

Original Hebbian encoding scheme of bidirectional associative memory (BAM) provides a poor pattern capacity and recall performance. Based on Rosenblatt's perceptron learning algorithm, the pattern capacity of BAM is enlarged, and perfect recall of all training pattern pairs is guaranteed. However, these methods put their emphases on pattern capacity, rather than error correction capability which is another critical point of BAM. This paper analyzes the sensitivity to noise in RAM and obtains an interesting idea to improve noise immunity of BAM. Some researchers have found that the noise sensitivity of BAM relates to the minimum absolute value of net inputs (MAV). However, in this paper, the analysis on failure association shows that it is related not only to MAV but also to the variance of weights associated with synapse connections. In fact, it is a positive monotone increasing function of the quotient of MAV divided by the variance of weights. This idea provides an useful principle of improving error correction capability of RAM. Some revised encoding schemes, such as small variance learning for RAM (SVBAM), evolutionary pseudorelaxation learning for BAM (EPRLAB) and evolutionary bidirectional learning (EBL), have been introduced to illustrate the performance of this principle. All these methods perform better than their original versions in noise immunity. Moreover, these methods have no negative effect on the pattern capacity of BAM. The convergence of these methods is also discussed in this paper. If there exist solutions, EPRLAB and EBL always converge to a global optimal solution in the senses of both, pattern capacity and noise immunity. However, the convergence of SVBAM may be affected by a preset function. [ABSTRACT FROM AUTHOR]

Designing intelligent and robust autonomous navigation systems remains a great challenge in mobile robotics. Inverse reinforcement learning (IRL) offers an efficient learning technique from expert demonstrations to teach robots how to perform specific tasks without manually specifying the reward function. Most of existing IRL algorithms assume the expert policy to be optimal and deterministic, and are applied to experiments with relatively small-size state spaces. However, in autonomous navigation tasks, the state spaces are frequently large and demonstrations can hardly visit all the states. Meanwhile the expert policy may be non-optimal and stochastic. In this paper, we focus on IRL with large-scale and high-dimensional state spaces by introducing the neural network to generalize the expert’s behaviors to unvisited regions of the state space and an explicit policy representation is easily expressed by neural network, even for the stochastic expert policy. An efficient and convenient algorithm, Neural Inverse Reinforcement Learning (NIRL), is proposed. Experimental results on simulated autonomous navigation tasks show that a mobile robot using our approach can successfully navigate to the target position without colliding with unpredicted obstacles, largely reduce the learning time, and has a good generalization performance on undemonstrated states. Hence prove the robot intelligence of autonomous navigation transplanted from limited demonstrations to completely unknown tasks. [ABSTRACT FROM AUTHOR]

The objective of this paper is to review some important progress with H infinity control methods and to derive an artificial algorithm for dealing with stability problems of multiple time-delay structural systems. Neural network modeling and linear deferential inclusion are utilized to represent a multiple time-delay structural system. We can derive a novel stability criterion using linear matrix inequality methods. Moreover, the H∞ control performance is ensured for multiple time-delay structural systems based on traditional Lyapunov theory. [ABSTRACT FROM PUBLISHER]

Active queue control aims to improve the overall communication network throughput, while providing lower delay and small packet loss rate. The basic idea is to actively trigger packet dropping (or marking provided by explicit congestion notification (ECN)) before buffer overflow. In this paper, two artificial neural networks (ANN)-based control schemes are proposed for adaptive queue control in TCP communication networks. The structure of these controllers is optimized using genetic algorithm (GA) and the output weights of ANNs are optimized using particle swarm optimization (PSO) algorithm. The controllers are radial bias function (RBF)-based, but to improve the robustness of RBF controller, an error-integral term is added to RBF equation in the second scheme. Experimental results show that GA- PSO-optimized improved RBF (I-RBF) model controls network congestion effectively in terms of link utilization with a low packet loss rate and outperforms Drop Tail, proportional-integral (PI), random exponential marking (REM), and adaptive random early detection (ARED) controllers. [ABSTRACT FROM AUTHOR]

This paper presents a new approach, known as symmetry axis based feature extraction and recognition (SAFER), for recognizing objects under translation, rotation and scaling. Unlike most previous invariant object recognition (IOR) systems, SAFER puts emphasis on both simplicity and accuracy of the recognition system. To achieve simplicity, it uses simple formulae for extracting invariant features from an object. The scheme used in feature extraction is based on the axis of symmetry and angles of concentric circles drawn around the object. SAFER divides the extracted features into a number of groups based on their similarity. To improve the recognition performance, SAFER uses a number of neural networks (NNs) instead of single NN are used for training and recognition of extracted features. The new approach, SAFER, has been tested on two of real world problems i.e., English characters with two different fonts and images of different shapes. The experimental results show that SAFER can produce good recognition performance in comparison with other algorithms. [ABSTRACT FROM AUTHOR]

This paper describes a new algorithm with neuron-by-neuron computation methods for the gradient vector and the Jacobian matrix. The algorithm can handle networks with arbitrarily connected neurons. The training speed is comparable with the Levenberg-Marquardt algorithm, which is currently considered by many as the fastest algorithm for neural network training. More importantly, it is shown that the computation of the Jacobian, which is required for second-order algorithms, has a similar computation complexity as the computation of the gradient for first-order learning methods. This new algorithm is implemented in the newly developed software, Neural Network Trainer, which has unique capabilities of handling arbitrarily connected networks. These networks with connections across layers can be more efficient than commonly used multilayer perceptron networks. [ABSTRACT FROM AUTHOR]

In this paper, a new algorithm is proposed for resolution enhancement in hyperspectral images (HSIs). The key techniques are included: spectral unmixing and superresolution mapping, by which spatial and spectral information of HSIs is substantially fused. The proposed algorithm first represents each pixel in scene as a linear combination of landcover spectra and noise. Then, a fully constrained least squares algorithm is used to obtain the proportion of each landcover in each pixel, i.e., abundance, subjecting to two constraints: nonnegativity and sum-to-one. After that, superresolution mapping is performed on high-resolution grids according to spectral unmixing abundances of each landcover and following spatial correlation of clutters. Thus, by reasonably integrating spatial and spectral information of landcovers in HSIs, the proposed algorithm realizes resolution enhancement of the HSIs based on a back-propagation neural network. The proposed algorithm is independent from the a priori information associated with original HSIs, i.e., a main merit of the algorithm. In order to evaluate the performance of the new algorithm, numerical experiments are conducted on both simulated images and real HSIs collected by the Airborne Visible/Infrared Imaging Spectrometer. The proposed algorithm is compared with the traditional method in the experiments. The experimental results prove that the proposed algorithm effectively enhances the resolution of HSIs and indicate its applicability. [ABSTRACT FROM AUTHOR]

The neural networks are successfully applied to many applications in different domains. However, due to the results made by the neural networks are difficult to explain the decision process of neural networks is supposed as a black box. The explanation of reasoning is important to some applications such like credit approval application and medical diagnosing software. Therefore, the rule extraction algorithm is becoming more and more important in explaining the extracted rules from the neural networks. In this paper, a decompositional algorithm is analyzed and designed to extract rules from neural networks. The algorithm is simple but efficient; can reduce the extracted rules but improve the efficiency of the algorithm at the same time. Moreover, the algorithm is compared to the other two algorithms, M-of-N and Garcez, by solving the MONK’s problem. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, a procedure of testing and evaluation on the sound quality of cars are proposed and sound quality is analysed through the cars’ road running test on the providing ground, which was carried out with varying running speed. In addition to this experimental analysis, a neural network predictor is also designed to model the system for possible experimental applications. The proposed neural network is a recurrent type network, which consists of two types of neuron function in the hidden layer. As basic factors for sound quality, only objective factors are considered such as loudness, sharpness, speech intelligibility, and sound pressure level. The correlation between sound pressure level and another factor are discussed from a point of view of running speed dependency. Results of both computer simulations and experiments show that the neural predictor algorithm gives good results at accommodating different cases and provides superior prediction on two cars’ sound analysis. [Copyright &y& Elsevier]

Abstract: This paper presents the design of a hybrid learning model, termed as neural network tree (NNTree). It incorporates the advantages of both decision tree and neural network. An NNTree is a decision tree, where each non-terminal node contains a neural network. The idea of the proposed method is to use the framework of multilayer perceptron to design tree-structured pattern classifier. At each non-terminal node, the multilayer perceptron partitions the dataset into subsets, being the number of classes in the dataset present at that node. The NNTree is designed by splitting the non-terminal nodes of the tree by maximizing classification accuracy of the multilayer perceptron. In effect, it produces a reduced height -ary tree. The versatility of the proposed scheme is illustrated through its application in diverse fields. The effectiveness of the hybrid algorithm, along with a comparison with other related algorithms, has been demonstrated on a set of benchmark datasets. Simulation results show that the NNTree achieves excellent performance in terms of classification accuracy, size of the tree, and classification time. [Copyright &y& Elsevier]

It is difficult to determine the recognition mechanism in the neurons of a neural network trained for pattern recognition due to the non-linear nature of neural networks. This paper describes a recognition mechanism of a four-layer back propagation neural network using Alopex algorithm. We have developed a small-scale, four-layered neural network model for simple character recognition, which can recognize the patterns transformed by affined conversion. Alopex algorithm is an iterative and stochastic processing method, which was proposed for optimization of a given cost function. In this case the receptive fields of the neurons in the output layers are obtained using the Alopex algorithm. [ABSTRACT FROM AUTHOR]

Continuum or hyper-redundant robot manipulators can exhibit behavior similar to biological trunks, tentacles, or snakes. Unlike traditional rigid-link robot manipulators, continuum robot manipulators do not have rigid joints, hence these manipulators are extremely dexterous, compliant, and are capable of dynamic adaptive manipulation in unstructured environments. However, the development of high-performance control algorithms for these manipulators is quite a challenge, due to their unique design and the high degree of uncertainty in their dynamic models. In this paper, a controller for continuum robots, which utilizes a neural network feedforward component to compensate for dynamic uncertainties is presented. Experimental results using the OCTARM, which is a soft extensible continuum manipulator, are provided to illustrate that the addition of the neural network feedforward component to the controller provides improved performance. [ABSTRACT FROM AUTHOR]

This paper presents an analysis of a random access memory (RAM)-based associative memory which uses a weighted voting scheme for information retrieval. This weighted voting memory can operate in heteroassociative or autoassociative mode, can store both real-valued and binary-valued patterns and, unlike memory models, is equipped with a rejection mechanism. A theoretical analysis of the performance of the weighted voting memory is given for the case of binary and random memory sets. Performance measures are derived as a function of the model parameters: pattern size, window size, and number of patterns in the memory set. It is shown that the weighted voting model has large capacity and error correction. The results show that the weighted voting model can successfully achieve high-detection and -identification rates and, simultaneously, low-false-acceptance rates. [ABSTRACT FROM AUTHOR]

Abstract: The biggest problem that networked control systems face is the random time-varying delay, which often causes system instability and even collapse. Aiming at this problem, a new modeling scheme for the networked control systems, motivated from a variable-period sampling approach, is presented in this paper. Here, the time delay to occur at current sampling step is taken as the sampling period between current sampling step and next sampling step. To predict online the time delay induced in the networked control systems, a BP feedforward neural network is adopted and the training algorithm of the BP neural network is given. To make the BP neural network adapt to the changing environment of the networked control systems and improve its prediction accuracy, the BP neural network is designed to further update according to its prediction error after each prediction. At each sampling step, good approximation to actual time delay becomes available and different sampling period is obtained. Control simulations using the variable sampling period and fixed sampling period are compared. Simulation results show that this new approach can alleviate the influence of time delay to the greatest extent and improve the performance of the networked control systems. [Copyright &y& Elsevier]

Abstract: In this paper, we present an improved version of the online phase-space learning algorithm of Tsung and Cottrell (1995), called ARTISTE (Autonomous Real-TIme Selection of Training Examples). The new version''s advantages derive from an online adaptive learning rate that depends on the error. We demonstrate the algorithm''s efficacy on two problems: learning a pair of sine waves offset by 90° and the van der Pol oscillator. The online version of the algorithm allows the system to learn as it behaves. We show that the adaptive learning rate technique gives us excellent results in the learning of the above two tasks. [Copyright &y& Elsevier]

Abstract: In this paper we equate the problem of predicting the loop 3D structure in the comparative modeling to a problem of finding the maximal clique with the best weight. Each possible conformation of a residue in a loop sequence is represented as a node in a graph. Edges are then drawn between pairs of nodes that are consistent with each other. Edge and nodes are weighted according to some fixed criteria. Once the entire graph is constructed, all the maximal sets of cliques are found using an algorithm of artificial neural network models. The cliques with the best weights represent the optimal conformation of the region of loop sequence. [Copyright &y& Elsevier]

Abstract: A common video indexing technique is to segment a video sequence into shots and then select representative key-frames. This paper proposes a new method using an improved ART2 neural network for scene change detection. The proposed algorithm extracts DC-sequence from a video and then makes a gray variance sequence for detecting smooth intervals. During that procedure, a local minimum sequence occurring at typical gradual changes is extracted and eliminated from the smooth intervals by our local minimum detection algorithm. Then, a new sequence is constructed by concatenating obtained smooth intervals. Feature elements such as pixel-wise difference, histogram difference, and correlation coefficients are extracted from the new sequence. These three elements, plus one extra element reducing the distortion of the ART2 neural network, are presented as an input vector to the ART2 neural network that has two output units in the F2 layer. Frames at the ends of each smooth interval are assigned to the second cluster that represents key-frames. Experimental results showed that the proposed algorithm using the extra element was better than the method without it in terms of precision and recall rates. Also, it produced better results than Patel''s method (Patel and Sethi, 1996) and the twin comparison method (Zhang et al., 1993). [Copyright &y& Elsevier]

This paper presents a methodology on land use mapping using CMODIS (Chinese Moderate Resolution Imaging Spectroradiometer) data on-board SZ-3 (Shenzhou 3) spacecraft. The integrated method is composed of genetic algorithm (GA) for feature ex- traction and neural network classifier for land use classification. In the data preprocessing, a moment matching method was adopted to remove the stripes in the images. Then by using the reproduction, crossover and mutation operators of GA based on the mechanism of "natural selection", and with Jeffries-Matusita distance as its discriminate rule and the training samples, the optimal band combination for land use classification was obtained. To generate a land use map, the three layers back propagation neural network classifier is used for training the samples and classification. Compared with the Maximum Likelihood classification algorithm, the results show that the accuracy of land use classification is obviously improved by using our proposed method, the selected band number in the classification process is reduced, and the computational performance for training and classification is improved. The result also shows that the CMODIS data can be effectively used for land use/land cover classification and change monitoring at regional and global scale. [ABSTRACT FROM AUTHOR]

Abstract: Globally linearizing control (GLC) is a control algorithm capable of using nonlinear process model directly. In GLC, mostly, first-principle models derived from dynamic mass, energy and momentum balances are used. When the process is not perfectly known, the unknown parts of the first principles model should be represented by black-box models, e.g. by neural networks. This paper is devoted to the identification and application of such hybrid models for GLC. It is shown that the first principles part of the model determines the dominant structure of the controller, while the black-box elements of the hybrid model are used as state and/or disturbance estimators. For the identification of the neural network elements of the hybrid model a sensitivity approach based algorithm has been developed. The underlying framework is illustrated by the temperature control of a continuous stirred tank reactor where a neural network is used to model the heat released by an exothermic chemical reaction. [Copyright &y& Elsevier]

This paper proposes an information system that classifies Web pages according a taxonomy, which is mainly used from seven search engines/directories. The proposed classifier is a four-layer generalised regression neural network (GRNN) that aims to perform the information segmentation according to information filtering techniques using content descriptor vectors. Eight categories of Web pages were used in order to evaluate the robustness of the method, while no restrictions were imposed except for the language of the content, which is English. The system can be used as an assistant and consultative tool for classification purposes as well as for estimating the population of Web pages at any given point in time. [ABSTRACT FROM AUTHOR]

Mathematical essence and structures of the feedforward neural networks are investigated in this paper. The interpolation mechanisms of the feedforward neural networks are explored. For example, the well-known result, namely, that a neural network is an universal approximator, can be concluded naturally from the interpolative representations. Finally, the learning algorithms of the feedforward neural networks are discussed. [Copyright &y& Elsevier]

The authors previously reported on a variable logic circuit using a neural network (NN), in which logic operation was controlled by an analog voltage. In that design, the synaptic weights were determined by the error back-propagation (BP) algorithm. Then, logic outputs outside the specification were produced between logic outputs with Hamming distances of two or more. This paper proposes a design of NN in which no logic outside the specification is output, together with a method of calculating the synaptic weights. Based on the correspondence between the change of the output logic and the control voltage, the necessary number of hidden-layer neurons can be defined. The computation time for the synaptic weights is reduced. By constructing an NN circuit by the proposed method, it is verified that the desired operation is realized. © 1999 Scripta Technica, Electron Comm Jpn Pt 3, 83(1): 14–20, 2000 [ABSTRACT FROM AUTHOR]

A near-optimum parallel algorithm for solving the one-dimensional gate assignment problem is presented in this paper, where the problem is NP-hard and one of the most fundamental layout problems in VLSI design. The proposed system is composed of n × n processing elements based on the artificial two-dimensional maximum neural network for (n + 2)-gate assignment problems. Our algorithm has discovered improved solutions in the benchmark problems compared with the best existing algorithms. The proposed approach is applicable to other VLSI layout problems such as the PLA (Programmable Logic Array) folding problem. © 1999 Scripta Technica, Electr Eng Jpn, 129(2): 71–77, 1999 [ABSTRACT FROM AUTHOR]

In a multihop radio network, packets are transmitted from course nodes to destination nodes by activating several links between nodes. Each node can either send a packet to, or receive a packet from, at most one of its adjacent nodes simultaneously. To minimize the transmission time for given requests, the problems must be solved by selecting a transmission route for each request (the routing problem) and by finding a link activation schedule (the link activation problem). The routing problem is decomposed into two subproblems: the candidate extraction problem and the route selection problem. In this paper, we propose a neural network algorithm using the maximum neuron model for the route selection problem. We verify through simulations that our algorithm finds better solutions in a shorter time than the existing algorithms. We also probe the NP-hardness of this problem. © 1999 Scripta Technica, Electr Eng Jpn, 129(2): 78–86, 1999 [ABSTRACT FROM AUTHOR]

Various studies on learning rules for neural networks have been done. However, most of those do not consider the hardware implementation, which is a great drawback in the LSI implementation of neural networks with learning capability. From such a viewpoint, this paper proposes a self-organizing learning rule by modifying the Hebbian learning rule. This rule can be implemented easily on an analog VLSI chip as an on-chip learning rule. The self-organizing ability of the system is verified by simulation experiments. It is shown from the experiment that the learning speed is improved by a factor of 2 to 3, and it is possible to avoid the sudden termination of the learning and the divergence of the synaptic weights. [ABSTRACT FROM AUTHOR]

In cellular mobile communication, the same channel is shared by a number of cells. Up to now, the model has been considered where the same channel is used with a sufficient separation, so that the radiowave interference is sufficiently small for any call generated in the cell. Recently, on the other hand, a model has been proposed where the same channel is assigned independently of the specified cell separation, as long as the carrier-interference ratio is above a certain value. Although the assignment algorithm has been discussed for the traditional model, no report has been made on the detailed assignment procedure for the new model. With such a situation as the background, this paper proposes an application of Hopfield's neural net as an approach to the channel assignment in the new model and derives the energy function. Several results of computer simulation are shown where the proposed neural net is applied to the mobile communication model. It is not always true that the neural net produces the optimal solution, but it is interesting that an unexpected improvement of the channel utilization is observed in the communication traffic as far as the result of computer simulation is concerned. [ABSTRACT FROM AUTHOR]

Many existing scene-adaptive nonuniformity correction (NUC) methods suffer from slow convergence rate together with ghosting effects. In this paper, an improved NUC algorithm based on total variation penalized neural network regression is presented. Our work mainly focuses on solving the overfitting problem in least mean square (LMS) regression of traditional neural network NUC methods, which is realized by employing a total variation penalty in the cost function and redesigning the processing architecture. Moreover, an adaptive gated learning rate is presented to further reduce the ghosting artifacts and guarantee fast convergence. The performance of the proposed algorithm is comprehensively investigated with artificially corrupted test sequences and real infrared image sequences, respectively. Experimental results show that the proposed algorithm can effectively accelerate the convergence speed, suppress ghosting artifacts, and promote correction precision. [ABSTRACT FROM AUTHOR]