|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Exponential stability and periodic solutions of delayed cellular neural networks显示文摘A set of criteria are presented for the global exponential stability and the existence of periodic solutions of delayed cellular neural networks (DCNNs) by constructing suitable Lyapunov function-als, introducing many parameters qij* , rij* , qij, rij∈ R and wi>0 (i, j = 1, 2, …, n) and combining them with the elementary inequality 2ab≤a2 + b2 technique. These criteria have important significance in the design and applications of globally stable DCNNs and periodic oscillatory DCNNs. In addition, the results in literature are extended and improved. Two examples are given to illustrate the theory. | 曹进德 | 2000 | Science China(Technological Sciences)2000，43，3： | 17 |
| 2 | Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks显示文摘X-ray diffraction(XRD)data acquisition and analysis is among the most time-consuming steps in the development cycle of novel thin-film materials.We propose a machine learning-enabled approach to predict crystallographic dimensionality and space group from a limited number of thin-film XRD patterns.We overcome the scarce data problem intrinsic to novel materials development by coupling a supervised machine learning approach with a model-agnostic,physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database(ICSD)and experimental data.As a test case,115 thin-film metalhalides spanning three dimensionalities and seven space groups are synthesized and classified.After testing various algorithms,we develop and implement an all convolutional neural network,with cross-validated accuracies for dimensionality and space group classification of 93 and 89%,respectively.We propose average class activation maps,computed from a global average pooling layer,to allow high model interpretability by human experimentalists,elucidating the root causes of misclassification.Finally,we systematically evaluate the maximum XRD pattern step size(data acquisition rate)before loss of predictive accuracy occurs,and determine it to be 0.16°2θ,which enables an XRD pattern to be obtained and classified in 5.5 min or less. | Felipe Oviedo Zekun Ren Shijing Sun Charles Settens Zhe Liu Noor Titan Putri Hartono Savitha Ramasamy Brian L.DeCost Siyu I.P.Tian Giuseppe Romano Aaron Gilad Kusne Tonio Buonassisi | 2019 | npj Computational Materials2019，，1： | 15 |
| 3 | Parameter Optimization of Interval Type-2 Fuzzy Neural Networks Based on PSO and BBBC Methods显示文摘Interval type-2 fuzzy neural networks(IT2FNNs)can be seen as the hybridization of interval type-2 fuzzy systems(IT2FSs) and neural networks(NNs). Thus, they naturally inherit the merits of both IT2 FSs and NNs. Although IT2 FNNs have more advantages in processing uncertain, incomplete, or imprecise information compared to their type-1 counterparts, a large number of parameters need to be tuned in the IT2 FNNs,which increases the difficulties of their design. In this paper,big bang-big crunch(BBBC) optimization and particle swarm optimization(PSO) are applied in the parameter optimization for Takagi-Sugeno-Kang(TSK) type IT2 FNNs. The employment of the BBBC and PSO strategies can eliminate the need of backpropagation computation. The computing problem is converted to a simple feed-forward IT2 FNNs learning. The adoption of the BBBC or the PSO will not only simplify the design of the IT2 FNNs, but will also increase identification accuracy when compared with present methods. The proposed optimization based strategies are tested with three types of interval type-2 fuzzy membership functions(IT2FMFs) and deployed on three typical identification models. Simulation results certify the effectiveness of the proposed parameter optimization methods for the IT2 FNNs. | Jiajun Wang Tufan Kumbasar | 2019 | IEEE/CAA Journal of Automatica Sinica2019，6，1： | 14 |
| 4 | Efficient spectrum prediction and inverse design for plasmonic waveguide systems based on artificial neural networks显示文摘In this paper, we propose a novel approach to achieve spectrum prediction, parameter fitting, inverse design, and performance optimization for the plasmonic waveguide-coupled with cavities structure(PWCCS) based on artificial neural networks(ANNs). The Fano resonance and plasmon-induced transparency effect originated from the PWCCS have been selected as illustrations to verify the effectiveness of ANNs. We use the genetic algorithm to design the network architecture and select the hyperparameters for ANNs. Once ANNs are trained by using a small sampling of the data generated by the Monte Carlo method, the transmission spectra predicted by the ANNs are quite approximate to the simulated results. The physical mechanisms behind the phenomena are discussed theoretically, and the uncertain parameters in the theoretical models are fitted by utilizing the trained ANNs.More importantly, our results demonstrate that this model-driven method not only realizes the inverse design of the PWCCS with high precision but also optimizes some critical performance metrics for the transmission spectrum. Compared with previous works, we construct a novel model-driven analysis method for the PWCCS that is expected to have significant applications in the device design, performance optimization, variability analysis,defect detection, theoretical modeling, optical interconnects, and so on. | TIAN ZHANG JIA WANG QI LIU JINZAN ZHOU JIAN DAI XU HAN YUE ZHOU KUN XU | 2019 | Photonics Research2019，7，3： | 13 |
| 5 | Feature-Based Aggregation and Deep Reinforcement Learning:A Survey and Some New Implementations显示文摘In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning schemes. We introduce features of the states of the original problem, and we formulate a smaller 'aggregate' Markov decision problem, whose states relate to the features. We discuss properties and possible implementations of this type of aggregation, including a new approach to approximate policy iteration. In this approach the policy improvement operation combines feature-based aggregation with feature construction using deep neural networks or other calculations. We argue that the cost function of a policy may be approximated much more accurately by the nonlinear function of the features provided by aggregation, than by the linear function of the features provided by neural networkbased reinforcement learning, thereby potentially leading to more effective policy improvement. | Dimitri P.Bertsekas | 2019 | IEEE/CAA Journal of Automatica Sinica2019，6，1： | 12 |
| 6 | Fault diagnosis for distillation process based on CNN–DAE显示文摘Distillation is the most widely used operation for liquid mixture separation in the chemical industry. It is of great importance to detect and diagnose faults in distillation process. Due to the strong feedback and coupling of processes in a distillation column, it is difficult to use deep auto-encoders(DAEs) alone to achieve good results in detecting and diagnosing faults, in terms of accuracy and efficiency. This paper proposes a hybrid fault-diagnosis model based on convolutional neural networks(CNNs) and DAEs, by integrating the powerful capability of CNN in feature extraction and of DAE in classification. A case study was carried out with the distillation process of depropanization. It is shown that the proposed hybrid model is of good performance compared to other models, in terms of the accuracy of fault detection in such a process. Also, with the increase of structural layers of the CNN–DAE model, the diagnostic accuracy will be improved, with an optimal accuracy of 92.2%. | Chuankun Li Dongfeng Zhao Shanjun Mu Weihua Zhang Ning Shi Lening Li | 2019 | Chinese Journal of Chemical Engineering2019，27，3： | 12 |
| 7 | STABILITY OF BIDIRECTIONAL ASSOCIATIVE MEMORY NEURAL NETWORKS WITH DELAYS显示文摘In this paper the globally asymptotic stability of more general two-layer nonlinear feedback associative memory neural networks with time delays is examined. The sufficient conditions of existence, uniqueness and globally asymptotic stability of the equilibrum position are given. Finally, two interesting examples to illustrate the theory are given. | Liao Xiaoxin(Dept. of Auto. Control. Huazhong Univ. of Science & Technology, Wuhan 430074)Liao Yang(Dept. of Computer Science, Nanjing University, Nanjing 210093)Liao Yu (Wuhan Soundy Science & Commerce Company, Wuhan 430070) | 1998 | Journal of Electronics(China)1998，15，4： | 11 |
| 8 | Signal-Based Intelligent Hydraulic Fault Diagnosis Methods: Review and Prospects显示文摘Hydraulic systems have the characteristics of strong fault concealment,powerful nonlinear time-varying signals,and a complex vibration transmission mechanism;hence,diagnosis of these systems is a challenge.To provide accurate diagnosis results automatically,numerous studies have been carried out.Among them,signal-based methods are commonly used,which employ signal processing techniques based on the state signal used for extracting features,and further input the features into the classifier for fault recognition.However,their main deficiencies include the following:(1)The features are manually designed and thus may have a lack of objectivity.(2)For signal processing,feature extraction and pattern recognition are conducted using independent models,which cannot be jointly optimized globally.(3)The machine learning algorithms adopted by these methods have a shallow architecture,which limits their capacity to deeply mine the essential features of a fault.As a breakthrough in artificial intelligence,deep learning holds the potential to overcome such deficiencies.Based on deep learning,deep neural networks(DNNs)can automatically learn the complex nonlinear relations implied in a signal,can be globally optimized,and can obtain the high-level features of multi-dimensional data.In this paper,the main technology used in an intelligent fault diagnosis and the current research status of hydraulic system fault diagnosis are summarized and analyzed.The significant prospect of applying deep learning in the field of intelligent fault diagnosis is presented,and the main ideas,methods,and principles of several typical DNNs are described and summarized.The commonality between a fault diagnosis and other issues regarding typical pattern recognition are analyzed,and research ideas for applying DNNs for hydraulic fault diagnosis are proposed.Meanwhile,the research advantages and development trend of DNNs(both domestically and overseas)as applied to an intelligent fault diagnosis are reviewed.Furthermore,the fault characteristics of a complex hydraulic system are summarized and discussed,and the key problems and possible research ideas of applying DNNs to an intelligent hydraulic fault diagnosis are presented and comprehensively analyzed. | Juying Dai Jian Tang Shuzhan Huang Yangyang Wang | 2019 | Chinese Journal of Mechanical Engineering2019，32，5： | 11 |
| 9 | Unsupervised Electric Motor Fault Detection by Using Deep Autoencoders显示文摘Fault diagnosis of electric motors is a fundamental task for production line testing, and it is usually performed by experienced human operators. In the recent years, several methods have been proposed in the literature for detecting faults automatically. Deep neural networks have been successfully employed for this task, but, up to the authors' knowledge, they have never been used in an unsupervised scenario. This paper proposes an unsupervised method for diagnosing faults of electric motors by using a novelty detection approach based on deep autoencoders. In the proposed method, vibration signals are acquired by using accelerometers and processed to extract LogMel coefficients as features. Autoencoders are trained by using normal data only, i.e., data that do not contain faults. Three different autoencoders architectures have been evaluated: the multilayer perceptron(MLP) autoencoder, the convolutional neural network autoencoder, and the recurrent autoencoder composed of long short-term memory(LSTM) units. The experiments have been conducted by using a dataset created by the authors, and the proposed approaches have been compared to the one-class support vector machine(OC-SVM) algorithm. The performance has been evaluated in terms area under curve(AUC) of the receiver operating characteristic curve, and the results showed that all the autoencoder-based approaches outperform the OCSVM algorithm. Moreover, the MLP autoencoder is the most performing architecture, achieving an AUC equal to 99.11 %. | Emanuele Principi Damiano Rossetti Stefano Squartini Francesco Piazza | 2019 | IEEE/CAA Journal of Automatica Sinica2019，6，2： | 10 |
| 10 | Study on correlations of modal frequencies and environmental factors for a suspension bridge based on improved neural networks显示文摘By using of long-term monitoring data of Runyang Suspension Bridge,the improved back-propagation neural networks (BPNNs) are formulated for modeling the correlations between modal frequencies and environmental conditions including wind,temperature and vehicle load.Then,with the correlation models the environmental effects on modal frequencies are quantified and the abnormal changes of measured frequencies are detected by means of the hypothesis tests.Analysis results reveal that BPNN-based correlation models improved by both early stopping and Bayesian regularization techniques exhibit excellent generalization capability.And the developed correlation models can effectively reduce the environmental variability in modal frequencies.The t-test method provides a good capability to detect the damage-induced 0.16% and 0.12% abnormal changes of the 5th and 6th modal frequencies,respectively.Hence,the proposed method is suitable for real-time monitoring of suspension bridge conditions. | DING YouLiang,DENG Yang & LI AiQun Key Laboratory of Concrete and Prestressed Concrete Structure of Ministry of Education,Southeast University,Nanjing 210096,China | 2010 | Science China(Technological Sciences)2010，53，9： | 9 |
| 11 | ON GLOBAL ROBUST STABILITY FOR INTERVAL HOPFIELD NEURAL NETWORKS WITH TIME DELAY显示文摘The theorem obtained by Liao was not true (see [2]). So, this paper presents some criteria of global robust stability for interval Hopfield neural networks with time delay. The methods to judge the robust stability are practical and easily verifiable. | 王林山 高玉英 | 2003 | Annals of Differential Equations2003，19，3： | 9 |
| 12 | Design of task-specific optical systems using broadband diffractive neural networks显示文摘Deep learning has been transformative in many fields,motivating the emergence of various optical computing architectures.Diffractive optical network is a recently introduced optical computing framework that merges wave optics with deep-learning methods to design optical neural networks.Diffraction-based all-optical object recognition systems,designed through this framework and fabricated by 3D printing,have been reported to recognize handwritten digits and fashion products,demonstrating all-optical inference and generalization to sub-classes of data.These previous diffractive approaches employed monochromatic coherent light as the illumination source.Here,we report a broadband diffractive optical neural network design that simultaneously processes a continuum of wavelengths generated by a temporally incoherent broadband source to all-optically perform a specific task learned using deep learning.We experimentally validated the success of this broadband diffractive neural network architecture by designing,fabricating and testing seven different multi-layer,diffractive optical systems that transform the optical wavefront generated by a broadband THz pulse to realize(1)a series of tuneable,single-passband and dual-passband spectral filters and(2)spatially controlled wavelength de-multiplexing.Merging the native or engineered dispersion of various material systems with a deep-learning-based design strategy,broadband diffractive neural networks help us engineer the light–matter interaction in 3D,diverging from intuitive and analytical design methods to create taskspecific optical components that can all-optically perform deterministic tasks or statistical inference for optical machine learning. | Yi Luo Deniz Mengu Nezih T.Yardimci Yair Rivenson Muhammed Veli Mona Jarrahi Aydogan Ozcan | 2019 | Light(Science & Applications)2019，8，1： | 9 |
| 13 | Adaptive Control Based on Neural Networks for an Uncertain 2-DOF Helicopter System With Input Deadzone and Output Constraints显示文摘In this paper, a study of control for an uncertain2-degree of freedom(DOF) helicopter system is given. The2-DOF helicopter is subject to input deadzone and output constraints. In order to cope with system uncertainties and input deadzone, the neural network technique is introduced because of its capability in approximation. In order to update the weights of the neural network, an adaptive control method is utilized to improve the system adaptability. Furthermore, the integral barrier Lyapunov function(IBLF) is adopt in control design to guarantee the condition of output constraints and boundedness of the corresponding tracking errors. The Lyapunov direct method is applied in the control design to analyze system stability and convergence. Finally, numerical simulations are conducted to prove the feasibility and effectiveness of the proposed control based on the model of Quanser's 2-DOF helicopter. | Yuncheng Ouyang Lu Dong Lei Xue Changyin Sun | 2019 | IEEE/CAA Journal of Automatica Sinica2019，6，3： | 9 |
| 14 | An Energy-Efficient Data Collection Scheme Using Denoising Autoencoder in Wireless Sensor Networks显示文摘As one of the key operations in Wireless Sensor Networks(WSNs), the energy-efficient data collection schemes have been actively explored in the literature. However, the transform basis for sparsifing the sensed data is usually chosen empirically, and the transformed results are not always the sparsest. In this paper, we propose a Data Collection scheme based on Denoising Autoencoder(DCDA) to solve the above problem. In the data training phase, a Denoising AutoEncoder(DAE) is trained to compute the data measurement matrix and the data reconstruction matrix using the historical sensed data. Then, in the data collection phase, the sensed data of whole network are collected along a data collection tree. The data measurement matrix is utilized to compress the sensed data in each sensor node, and the data reconstruction matrix is utilized to reconstruct the original data in the sink.Finally, the data communication performance and data reconstruction performance of the proposed scheme are evaluated and compared with those of existing schemes using real-world sensed data. The experimental results show that compared to its counterparts, the proposed scheme results in a higher data compression rate, lower energy consumption, more accurate data reconstruction, and faster data reconstruction speed. | Guorui Li Sancheng Peng Cong Wang Jianwei Niu Ying Yuan | 2019 | Tsinghua Science and Technology2019，24，1： | 9 |
| 15 | Relation Classification via Recurrent Neural Network with Attention and Tensor Layers显示文摘Relation classification is a crucial component in many Natural Language Processing(NLP) systems. In this paper, we propose a novel bidirectional recurrent neural network architecture(using Long Short-Term Memory,LSTM, cells) for relation classification, with an attention layer for organizing the context information on the word level and a tensor layer for detecting complex connections between two entities. The above two feature extraction operations are based on the LSTM networks and use their outputs. Our model allows end-to-end learning from the raw sentences in the dataset, without trimming or reconstructing them. Experiments on the SemEval-2010 Task 8dataset show that our model outperforms most state-of-the-art methods. | Runyan Zhang Fanrong Meng Yong Zhou Bing Liu | 2018 | Big Data Mining and Analytics2018，1，3： | 9 |
| 16 | A review of neural networks in plant disease detection using hyperspectral data显示文摘This paper reviews advanced Neural Network(NN)techniques available to process hyperspectral data,with a special emphasis on plant disease detection.Firstly,we provide a review on NN mechanism,types,models,and classifiers that use different algorithms to process hyperspectral data.Then we highlight the current state of imaging and nonimaging hyperspectral data for early disease detection.The hybridization of NNhyperspectral approach has emerged as a powerful tool for disease detection and diagnosis.Spectral Disease Index(SDI)is the ratio of different spectral bands of pure disease spectra.Subsequently,we introduce NN techniques for rapid development of SDI.We also highlight current challenges and future trends of hyperspectral data. | Kamlesh Golhani Siva K.Balasundram Ganesan Vadamalai Biswajeet Pradhan | 2018 | Information Processing in Agriculture2018，5，3： | 9 |
| 17 | Finding the optical properties of plasmonic structures by image processing using a combination of convolutional neural networks and recurrent neural networks显示文摘Image processing can be used to extract meaningful optical results from images.Here,from images of plasmonic structures,we combined convolutional neural networks with recurrent neural networks to extract the absorption spectra of structures.To provide the data required for the model,we performed 100,000 simulations with similar setups and random structures.In designing this deep network,we created a model that can predict the absorption response of any structure with a similar setup.We used convolutional neural networks to collect spatial information from the images,and then,we used that data and recurrent neural networks to teach the model to predict the relationship between the spatial information and the absorption spectrum.Our results show that this image processing method is accurate and can be used to replace time-and computationally-intensive numerical simulations.The trained model can predict the optical results in less than a second without the need for a strong computing system.This technique can be easily extended to cover different structures and extract any other optical properties. | Iman Sajedian Jeonghyun Kim Junsuk Rho | 2019 | Microsystems & Nanoengineering2019，5，1： | 9 |
| 18 | Approximation Problems in System Identification With Neural Networks显示文摘In this paper, the capability of neural networks and some approximation problens in system identification with neural networks are investigated. Some results are given: (i) For any function g ∈Llocp (R1) ∩S’ (R1) to be an Lp-Tauber-Wiener function, it is necessary and sufficient that g is not apolynomial; (ii) If g∈(Lp TW), then the set of is dense in Lp(K)’ (iii) It is proved that bycompositions of some functions of one variable, one can approximate continuous functional defined on compact Lp(K) and continuous operators from compact Lp1(K1) to LP2(K2). These results confirm the capability of neural networks in identifying dynamic systems. | 陈天平 | 1994 | Science China Mathematics1994，37，4： | 8 |
| 19 | Genetic Algorithm Based on New Evaluation Function and Mutation Model for Training of BPNN显示文摘A local minimum is frequently encountered in the training of back propagation neural networks (BPNN), which sharply slows the training process. In this paper, an analysis of the formation of local minima is presented, and an improved genetic algorithm (GA) is introduced to overcome local minima. The Sigmoid function is generally used as the activation function of BPNN nodes. It is the flat characteristic of the Sigmoid function that results in the formation of local minima. In the improved GA, pertinent modifications are made to the evaluation function and the mutation model. The evaluation of the solution is associated with both the training error and gradient. The sensitivity of the error function to network parameters is used to form a self adapting mutation model. An example of industrial application shows the advantage of the improved GA to overcome local minima. | 周祥 何小荣 陈丙珍 | 2002 | Tsinghua Science and Technology2002，7，1： | 8 |
| 20 | Multi-AUV SOM task allocation algorithm considering initial orientation and ocean current environment显示文摘There is an ocean current in the actual underwater working environment. An improved self-organizing neural network task allocation model of multiple autonomous underwater vehicles(AUVs) is proposed for a three-dimensional underwater workspace in the ocean current. Each AUV in the model will be competed, and the shortest path under an ocean current and different azimuths will be selected for task assignment and path planning while guaranteeing the least total consumption. First, the initial position and orientation of each AUV are determined. The velocity and azimuths of the constant ocean current are determined. Then the AUV task assignment problem in the constant ocean current environment is considered. The AUV that has the shortest path is selected for task assignment and path planning. Finally, to prove the effectiveness of the proposed method, simulation results are given. | Da-qi ZHU Yun QU Simon X.YANG | 2019 | Frontiers of Information Technology & Electronic Engineering2019，20，3： | 8 |
您所在的机构暂未开通此部分的功能，请联系管理员