Search

• The MBAN is proposed to learn invariant semantic representation of text image through mutual guidance mechanism. • The proposed method can deal with multiple types of irregularity, particularly blurring and arbitrary shape in this paper. • The proposed model helps alleviae the attention drift problem. • The proposed method achieves comparable or superior performance on standard benchmarks. Reading irregular text of arbitrary shape or low quality in natural scene images is a challenging task. Existing irregular scene text recognition methods mainly focus on irregular text with arbitrary shape, but rarely focus on irregular text of low quality. In this work, we propose a simple but effective method for recognizing irregular texts with arbitrary shape and low quality simultaneously. The proposed Multi-Branch guided Attention Network (MBAN) makes mutual guidance among multi-branch data in training, so as to learn invariant semantic representation between regular text images and the corresponding irregular images. Compared with the standard attention framework for text recognition, MBAN can significantly improve the performance of irregular text recognition while preserving similar performance for regular text recognition. In addition, regarding the attention drift problem encountered in standard attention network, MBAN can significantly improve the accuracy of alignment factors at each time step. We verify the effectiveness of MBAN in irregular text recognition and attention drift problem through extensive experiments. The performance of MBAN is shown to be comparable on regular datasets and superior on some irregular datasets with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The article discusses the emergence of "machine language," a new form of representation that combines deep neural networks with symbolic intelligence. The authors propose three essential properties that machine language should possess: spontaneity, flexibility, and semantics. They simulate the process of language emergence through a collaborative game between two agents, where one describes an image using machine language and the other interprets and draws the image based on the description. The article also compares machine language with discrete language and continuous features in terms of interpretability, generalization, and robustness. The authors argue that machine language, which emphasizes visual information, can lead to significant progress in AI capability. [Extracted from the article]

This paper studies the finite-time hybrid projective synchronization of the drive-response complex networks. In the model, general transmission delays and distributed delays are also considered. By designing the adaptive intermittent controllers, the response network can achieve hybrid projective synchronization with the drive system in finite time. Based on finite-time stability theory and several differential inequalities, some simple finite-time hybrid projective synchronization criteria are derived. Two numerical examples are given to illustrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Abnormal intra-QRS potentials (AIQPs) are commonly observed in patients at high risk for ventricular tachycardia. We present a method for approximating a measured QRS complex using a non-linear neural network with all radial basis functions having the same smoothness. We extracted the high frequency, but low amplitude intra-QRS potentials using the approximation error to identify possible ventricular tachycardia. With a specified number of neurons, we performed an orthogonal least squares algorithm to determine the center of each Gaussian radial basis function. We found that the AIQP estimation error arising from part of the normal QRS complex could cause clinicians to misjudge patients with ventricular tachycardia. Our results also show that it is possible to correct this misjudgment by combining multiple AIQP parameters estimated using various spread parameters and numbers of neurons. Clinical trials demonstrate that higher AIQP-to-QRS ratios in the X, Y and Z leads are visible in patients with ventricular tachycardia than in normal subjects. A linear combination of 60 AIQP-to-QRS ratios can achieve 100% specificity, 90% sensitivity, and 95.8% total prediction accuracy for diagnosing ventricular tachycardia. [ABSTRACT FROM AUTHOR]

In this paper, a semi-active suspension control system based on Magneto-Rheological (MR) damper is designed for a commercial vehicle to improve the ride comfort and driving stability. A mathematical model of MR damper based on the Bouc-Wen hysteresis model is built. The mathematical model could precisely describe the characteristics of MR damper compared with the bench test results. The neural network-PID controller is designed for the semi-active suspension systems. According to the numerical results, the proposed controller can constrain vehicle vibrations and roll angle significantly. A detailed multi-body dynamic model of the light vehicle with four semi-active suspensions are established, and an actual vehicle handling and stability tests are carried out to verify the control performances of the proposed controller. It can be concluded that MR semi-active suspension systems can play a key role in coordination between the ride comfort and handling stability for the commercial vehicle. [ABSTRACT FROM AUTHOR]

In response to the increasing threat of hypersonic weapons, it is of great importance for the defensive side to achieve fast prediction of their feasible attack domain and online inference of their most probable targets. In this study, an online footprint prediction and attack intention inference algorithm for hypersonic glide vehicles (HGVs) is proposed by leveraging the utilization of deep neural networks (DNNs). Specifically, this study focuses on the following three contributions. First, a baseline multi-constrained entry guidance algorithm is developed based on a compound bank angle corridor, and then a dataset containing enough trajectories for the following DNN learning is generated offline by traversing different initial states and control commands. Second, DNNs are developed to learn the functional relationship between the flight state/command and the corresponding ranges; on this basis, an online footprint prediction algorithm is developed by traversing the maximum/minimum ranges and different heading angles. Due to the substitution of DNNs for multiple times of trajectory integration, the computational efficiency for footprint prediction is significantly improved to the millisecond level. Third, combined with the predicted footprint and the hidden information in historical flight data, the attack intention and most probable targets can be further inferred. Simulations are conducted through comparing with the state-of-the-art algorithms, and results demonstrate that the proposed algorithm can achieve accurate prediction for flight footprint and attack intention while possessing significant real-time advantage. [ABSTRACT FROM AUTHOR]

Network based sensing has become an important field of research, and it is expected that new applications of remote sensing will be developed. A fuzzy collaborative sensor network is developed in this study to predict the cycle time of a job in a semiconductor manufacturing factory, which is an important task for the factory. In the fuzzy collaborative sensor network, each sensor detects the status of a particular job as well as various environmental conditions present in the factory and uses a fuzzy neural network to analyze the received information. Each sensor communicates its settings and forecasting results to other sensors with the aid of a central control unit. According to the experimental results, the aggregate forecasting performance was considerably improved through the sensors' collaboration. [ABSTRACT FROM AUTHOR]

In character string recognition integrating segmentation and classification, high classification accuracy and resistance to noncharacters are desired to the underlying classifier. In a previous evaluation study, the modified quadratic discriminant function (MQDF) proposed by Kimura et al. was shown to be superior in noncharacter resistance but inferior in classification accuracy to neural networks. This paper proposes a discriminative learning algorithm to optimize the parameters of MQDF with aim to improve the classification accuracy while preserving the superior noncharacter resistance. We refer to the resulting classifier as discriminative learning QDF (DLQDF). The parameters of DLQDF adhere to the structure of MQDF under the Gaussian density assumption and are optimized under the minimum classification error (MCE) criterion. The promise of DLQDF is justified in handwritten digit recognition and numeral string recognition, where the performance of DLQDF is comparable to or superior to that of neural classifiers. The results are also competitive to the best ones reported in the literature. [ABSTRACT FROM AUTHOR]

This paper deals with the speed synchronization control of integrated motor-transmission (IMT) powertrain systems in pure electric vehicles (EVs) over a controller area network (CAN) subject to both network-induced delays and network congestion. A CAN has advantages over point-to-point communication; however, it imposes network-induced delays and network congestion into the control system, which can deteriorate the shifting quality and make system integration difficult. This paper presents a co-design scheme combining active period scheduling and discrete-time slip mode control (SMC) to deal with both network-induced delays and network congestion of the CAN, which improves the speed synchronization control for high shifting quality and prevents network congestion for the system's integration. The results of simulations and hardware-in-loop experiments show the effectiveness of the proposed scheme, which can ensure satisfactory speed synchronization performance while significantly reducing the network's utilization. [ABSTRACT FROM AUTHOR]

Handwritten Chinese text recognition based on over-segmentation and path search integrating multiple contexts has been demonstrated successful, wherein the language model (LM) and character shape models play important roles. Although back-off N -gram LMs (BLMs) have been used dominantly for decades, they suffer from the data sparseness problem, especially for high-order LMs. Recently, neural network LMs (NNLMs) have been applied to handwriting recognition with superiority to BLMs. With the aim of improving Chinese handwriting recognition, this paper evaluates the effects of two types of character-level NNLMs, namely, feedforward neural network LMs (FNNLMs) and recurrent neural network LMs (RNNLMs). Both FNNLMs and RNNLMs are also combined with BLMs to construct hybrid LMs. For fair comparison with BLMs and a state-of-the-art system, we evaluate in a system with the same character over-segmentation and classification techniques as before, and compare various LMs using a small text corpus used before. Experimental results on the Chinese handwriting database CASIA-HWDB validate that NNLMs improve the recognition performance, and hybrid RNNLMs outperform the other LMs. To report a new benchmark, we also evaluate selected LMs on a large corpus, and replace the baseline character classifier, over-segmentation, and geometric context models with convolutional neural network (CNN) based models. The performance on both the CASIA-HWDB and the ICDAR-2013 competition dataset are improved significantly. On the CASIA-HWDB test set, the character-level accurate rate (AR) and correct rate (CR) achieve 95.88% and 95.95%, respectively. [ABSTRACT FROM AUTHOR]

Recent deep learning based methods have achieved the state-of-the-art performance for handwritten Chinese character recognition (HCCR) by learning discriminative representations directly from raw data. Nevertheless, we believe that the long-and-well investigated domain-specific knowledge should still help to boost the performance of HCCR. By integrating the traditional normalization-cooperated direction-decomposed feature map (directMap) with the deep convolutional neural network (convNet), we are able to obtain new highest accuracies for both online and offline HCCR on the ICDAR-2013 competition database. With this new framework, we can eliminate the needs for data augmentation and model ensemble, which are widely used in other systems to achieve their best results. This makes our framework to be efficient and effective for both training and testing. Furthermore, although directMap+convNet can achieve the best results and surpass human-level performance, we show that writer adaptation in this case is still effective. A new adaptation layer is proposed to reduce the mismatch between training and test data on a particular source layer. The adaptation process can be efficiently and effectively implemented in an unsupervised manner. By adding the adaptation layer into the pre-trained convNet, it can adapt to the new handwriting styles of particular writers, and the recognition accuracy can be further improved consistently and significantly. This paper gives an overview and comparison of recent deep learning based approaches for HCCR, and also sets new benchmarks for both online and offline HCCR. [ABSTRACT FROM AUTHOR]

• We extend the cross-modal prototype learning CMPL framework to three modalities. • CMPL achieves state-of-the-art results on online and offline zero-shot handwritten character recognition. • CMPL shows promising cross-domain generalization ability in zero-shot handwritten character recognition. Traditional methods of handwritten character recognition rely on extensive labeled data. However, humans can generalize to unseen handwritten characters by watching a few printed examples in textbooks. To simulate this ability, we propose a cross-modal prototype learning method (CMPL) to realize zero-shot recognition. For each character class, a prototype is generated by mapping the printed character into a deep neural network feature space. For unseen character class, its prototype can be directly produced from a printed character sample, therefore, not requiring any handwritten samples to realize class-incremental learning. Specifically, CMPL considers different modalities simultaneously - online handwritten trajectories, offline handwritten images, and auxiliary printed character images. The joint learning of the above modalities is achieved through sharing printed prototypes between online and offline data. In zero-shot inference, we feed CMPL the printed samples to obtain corresponding class prototypes, and then the unseen handwritten character can be recognized by the nearest prototype. Our experimental results demonstrate that CMPL outperforms the state-of-the-art methods in both online and offline zero-shot handwritten Chinese character recognition. Moreover, we also show the cross-domain generalization of CMPL from two perspectives: cross-language and modern-to-ancient handwritten character recognition, focusing on the transferability between different languages and different styles (i.e., modern and historical handwritings). [ABSTRACT FROM AUTHOR]

Despite the success of convolutional neural network (CNN) in conventional closed-set recognition (CSR), it still lacks robustness for dealing with unknowns (those out of known classes) in open environment. To improve the robustness of CNN in open-set recognition (OSR) and meanwhile maintain its high accuracy in CSR, we propose an alternative deep framework called convolutional prototype network (CPN), which keeps CNN for representation learning but replaces the closed-world assumed softmax with an open-world oriented and human-like prototype model. To equip CPN with discriminative ability for classifying known samples, we design several discriminative losses for training. Moreover, to increase the robustness of CPN for unknowns, we interpret CPN from the perspective of generative model and further propose a generative loss, which is essentially maximizing the log-likelihood of known samples and serves as a latent regularization for discriminative learning. The combination of discriminative and generative losses makes CPN a hybrid model with advantages for both CSR and OSR. Under the designed losses, the CPN is trained end-to-end for learning the convolutional network and prototypes jointly. For application of CPN in OSR, we propose two rejection rules for detecting different types of unknowns. Experiments on several datasets demonstrate the efficiency and effectiveness of CPN for both CSR and OSR tasks. [ABSTRACT FROM AUTHOR]

Text detection and localization in natural scene images is important for content-based image analysis. This problem is challenging due to the complex background, the non-uniform illumination, the variations of text font, size and line orientation. In this paper, we present a hybrid approach to robustly detect and localize texts in natural scene images. A text region detector is designed to estimate the text existing confidence and scale information in image pyramid, which help segment candidate text components by local binarization. To efficiently filter out the non-text components, a conditional random field (CRF) model considering unary component properties and binary contextual component relationships with supervised parameter learning is proposed. Finally, text components are grouped into text lines/words with a learning-based energy minimization method. Since all the three stages are learning-based, there are very few parameters requiring manual tuning. Experimental results evaluated on the ICDAR 2005 competition dataset show that our approach yields higher precision and recall performance compared with state-of-the-art methods. We also evaluated our approach on a multilingual image dataset with promising results. [ABSTRACT FROM AUTHOR]

Label noise poses a serious threat to deep neural networks (DNNs). Employing robust loss functions which reconcile fitting ability with robustness is a simple but effective strategy to handle this problem. However, the widely-used static trade-off between these two factors contradicts the dynamics of DNNs learning with label noise, leading to inferior performance. Therefore, we propose a dynamics-aware loss (DAL) to solve this problem. Considering that DNNs tend to first learn beneficial patterns, then gradually overfit harmful label noise, DAL strengthens the fitting ability initially, then gradually improves robustness. Moreover, at the later stage, to further reduce the negative impact of label noise and combat underfitting simultaneously, we let DNNs put more emphasis on easy examples than hard ones and introduce a bootstrapping term. Both the detailed theoretical analyses and extensive experimental results demonstrate the superiority of our method. • Based on the dynamic nature of DNNs learning with label noise, we propose Dynamics-Aware Loss (DAL). • We present detailed analyses to certify the superiority of DAL. • Our extensive experiments demonstrate the superior performance and practicality of DAL. [ABSTRACT FROM AUTHOR]

• A theoretical framework for domain generalization (DG) from the perspective of information bottleneck (IB) principle is established. • Based on the framework, a feasible solution by class-wise instance discrimination (CID) combined with maximizing feature entropy (MFE) is proposed to learn the desired representation for DG. • The proposed method achieves excellent performance on multiple datasets without knowing domain labels. • The proposed regularization rule (MFE) improves other invariance-based DG methods consistently. Although deep neural networks have achieved superior performance on many classical tasks, they deteriorate in real applications due to the unpredictable distribution shift. Domain generalization (DG) focuses on improving the generalization ability of the predictive model in unseen domains by training on multiple available source domains. All these domains share the same categories but commonly obey different distributions. In this paper, we establish a new theoretical framework for domain generalization from the perspective of the information bottleneck (IB) principle, which links representation learning in DG with domain-invariant representation learning and maximizing feature entropy (MFE). Based on the theoretical framework, we provide a feasible solution by class-wise instance discrimination combined with inter-dimension decorrelation and intra-dimension uniformity to learn the desired representation for domain generalization, which achieves excellent performance on multiple datasets without knowing domain labels. Extensive experiments show that the proposed regularization rule (MFE) can improve invariance-based DG methods consistently. Moreover, as an extreme case of domain generalization, we also show that MFE is promising to improve adversarial robustness. [ABSTRACT FROM AUTHOR]

Highlights • We present a new framework of deep convolutional neural network architecture distillation, namely LightweightNet, for acceleration and compression. • We exploit the prior knowledge of pre-defined network architecture to guide the efficient design of acceleration/compression strategies, while not using pre-trained model. • The proposed framework consists of network parameter compression, network structure acceleration, and non-tensor layer improvement. • The proposed framework demonstrates a higher acceleration/compression rate than previous methods in experiments, including a large category handwritten Chinese character recognition task with state-of-the-art performance. Abstract In recent years, deep neural networks have achieved remarkable successes in many pattern recognition tasks. However, the high computational cost and large memory overhead hinder them from applications on resource-limited devices. To address this problem, many deep network acceleration and compression methods have been proposed. One group of methods adopt decomposition and pruning techniques to accelerate and compress a pre-trained model. Another group designs single compact unit to stack their own networks. These methods are subject to complicated training processes, or lack of generality and extensibility. In this paper, we propose a general framework of architecture distillation, namely LightweightNet, to accelerate and compress convolutional neural networks. Rather than compressing a pre-trained model, we directly construct the lightweight network based on a baseline network architecture. The LightweightNet, designed based on a comprehensive analysis of the network architecture, consists of network parameter compression, network structure acceleration, and non-tensor layer improvement. Specifically, we propose the strategy of low-dimensional features of fully-connected layers for substantial memory saving, and design multiple efficient compact blocks to distill convolutional layers of baseline network with accuracy-sensitive distillation rule for notable time saving. Finally, it can effectively reduce the computational cost and the model size by > 4 × with negligible accuracy loss. Benchmarks on MNIST, CIFAR-10, ImageNet and HCCR (handwritten Chinese character recognition) datasets demonstrate the advantages of the proposed framework in terms of speed, performance, storage and training process. In HCCR, our method even outperforms traditional handcrafted features-based classifiers in terms of speed and storage while maintaining state-of-the-art recognition performance. [ABSTRACT FROM AUTHOR]

The performance behavior of the lithium-ion battery can be simulated by the battery model and thus applied to a variety of practical situations. Although the particle swarm optimization (PSO) algorithm has been used for the battery model development, it is usually unable to find an optimal solution during the iteration process. To resolve this problem, an adaptive random disturbance PSO algorithm is proposed. The optimal solution can be updated continuously by obtaining a new random location around the particle’s historical optimal location. There are two conditions considered to perform the model process. Initially, the test operating condition is used to validate the model effectiveness. Secondly, the verification operating condition is used to validate the model generality. The performance results show that the proposed model can achieve higher precision in the lithium-ion battery behavior, and it is feasible for wide applications in industry. [ABSTRACT FROM AUTHOR]

Recent deep learning based approaches have achieved great success on handwriting recognition. Chinese characters are among the most widely adopted writing systems in the world. Previous research has mainly focused on recognizing handwritten Chinese characters. However, recognition is only one aspect for understanding a language, another challenging and interesting task is to teach a machine to automatically write (pictographic) Chinese characters. In this paper, we propose a framework by using the recurrent neural network (RNN) as both a discriminative model for recognizing Chinese characters and a generative model for drawing (generating) Chinese characters. To recognize Chinese characters, previous methods usually adopt the convolutional neural network (CNN) models which require transforming the online handwriting trajectory into image-like representations. Instead, our RNN based approach is an end-to-end system which directly deals with the sequential structure and does not require any domain-specific knowledge. With the RNN system (combining an LSTM and GRU), state-of-the-art performance can be achieved on the ICDAR-2013 competition database. Furthermore, under the RNN framework, a conditional generative model with character embedding is proposed for automatically drawing recognizable Chinese characters. The generated characters (in vector format) are human-readable and also can be recognized by the discriminative RNN model with high accuracy. Experimental results verify the effectiveness of using RNNs as both generative and discriminative models for the tasks of drawing and recognizing Chinese characters. [ABSTRACT FROM PUBLISHER]

Fine-grained recognition is one of the most difficult topics in visual recognition, which aims at distinguishing confusing categories such as bird species within a genus. The information of part and bounding boxes in fine-grained images is very important for improving the performance. However, in real applications, the part and/or bounding box annotations may not exist. This makes fine-grained recognition a challenging problem. In this paper, we propose a jointly trained Convolutional Neural Network (CNN) architecture to solve the fine-grained recognition problem without using part and bounding box information. In this framework, we first detect part candidates by calculating the gradients of feature maps of a trained CNN model w.r.t. the input image and then filter out unnecessary ones by fusing two saliency detection methods. Meanwhile, two groups of global object locations are obtained based on the saliency detection methods and a segmentation method. With the filtered part candidates and approximate object locations as inputs, we construct the CNN architecture with local parts and global discrimination (LG-CNN) which consists of two CNN networks with shared weights. The upper stream of LG-CNN is focused on the part information of the input image, the bottom stream of LG-CNN is focused on the global input image. LG-CNN is jointly trained by two stream loss functions to guide the updating of the shared weights. Experiments on three popular fine-grained datasets well validate the effectiveness of our proposed LG-CNN architecture. Applying our LG-CNN architecture to generic object recognition datasets also yields superior performance over the directly fine-tuned CNN architecture with a large margin. [ABSTRACT FROM AUTHOR]

An artificial neural network (ANN)-based noise model of MOSFETs for breakdown operation is presented for the first time. This ANN architecture for avalanche noise model determination is developed using a feed-forward back propagation neural network program with optimisation algorithm of Levenberg Marquardt. Good agreement between measured and simulated noise parameters is achieved in the breakdown region. This simple and accurate breakdown characterisation method based on the ANN can be applicable to noise modelling for devices operating in the breakdown region. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN) has achieved the state-of-the-art performance in many different visual tasks. Learned from a large-scale training data set, CNN features are much more discriminative and accurate than the handcrafted features. Moreover, CNN features are also transferable among different domains. On the other hand, traditional dictionary-based features (such as BoW and spatial pyramid matching) contain much more local discriminative and structural information, which is implicitly embedded in the images. To further improve the performance, in this paper, we propose to combine CNN with dictionary-based models for scene recognition and visual domain adaptation (DA). Specifically, based on the well-tuned CNN models (e.g., AlexNet and VGG Net), two dictionary-based representations are further constructed, namely, mid-level local representation (MLR) and convolutional Fisher vector (CFV) representation. In MLR, an efficient two-stage clustering method, i.e., weighted spatial and feature space spectral clustering on the parts of a single image followed by clustering all representative parts of all images, is used to generate a class-mixture or a class-specific part dictionary. After that, the part dictionary is used to operate with the multiscale image inputs for generating mid-level representation. In CFV, a multiscale and scale-proportional Gaussian mixture model training strategy is utilized to generate Fisher vectors based on the last convolutional layer of CNN. By integrating the complementary information of MLR, CFV, and the CNN features of the fully connected layer, the state-of-the-art performance can be achieved on scene recognition and DA problems. An interested finding is that our proposed hybrid representation (from VGG net trained on ImageNet) is also complementary to GoogLeNet and/or VGG-11 (trained on Place205) greatly. [ABSTRACT FROM AUTHOR]

This paper investigates the problem of exponential synchronization of discrete-time neural networks with mixed time delays, actuator saturation and failures. Meanwhile, the unreliable communication links are considered between the neural networks, and such unreliable links are modeled as stochastic missing data satisfying Bernoulli distributions. In order to show the relationships between actuator constraints, unreliable communication link and mixed delay neural networks, by using Lyapunov functional approach, a missing data probability dependent exponential synchronization criterion is given. Then, based on such criterion, a reliable controller is designed to ensure that the neural networks are exponentially synchronized in the mean square. Finally, a numerical example is provided to illustrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Text classification can help users to effectively handle and exploit useful information hidden in large-scale documents. However, the sparsity of data and the semantic sensitivity to context often hinder the classification performance of short texts. In order to overcome the weakness, we propose a unified framework to expand short texts based on word embedding clustering and convolutional neural network (CNN). Empirically, the semantically related words are usually close to each other in embedding spaces. Thus, we first discover semantic cliques via fast clustering. Then, by using additive composition over word embeddings from context with variable window width, the representations of multi-scale semantic units 1 1 Semantic units are defined as n -grams which have dominant meaning of text. With n varying, multi-scale contextual information can be exploited. in short texts are computed. In embedding spaces, the restricted nearest word embeddings (NWEs) 2 2 In order to prevent outliers, a Euclidean distance threshold is preset between semantic cliques and semantic units, which is used as restricted condition. of the semantic units are chosen to constitute expanded matrices, where the semantic cliques are used as supervision information. Finally, for a short text, the projected matrix 3 3 The projected matrix is obtained by table looking up, which encodes Unigram level features. and expanded matrices are combined and fed into CNN in parallel. Experimental results on two open benchmarks validate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, we propose a feature learning method for handwritten Chinese character recognition (HCCR), called discriminative quadratic feature learning (DQFL). Based on original gradient direction feature representation, quadratic correlation between features is used to promote the feature dimensionality, then discriminative feature extraction (DFE) is used for dimensionality reduction. By combining dimensionality promotion and reduction, we can learn a much more discriminative and nonlinear feature representation, which can then boost the classification accuracy significantly. For dimensionality promotion, two types of correlation are exploited, namely, statistical correlation and spatial correlation. Statistical correlation is computed on multiple local feature vectors in different regions of the character image; while spatial correlation encodes the dependency between features of two positions. Feature correlation increases the dimensionality by over 40,000. DFE then reduces the dimensionality to less than 300 without losing discriminability. Classification is performed using nearest prototype classifier (NPC), modified quadratic discriminant function (MQDF) and discriminative learning quadratic discriminant function (DLQDF). In experiments on the CASIA-HWDB1.1 standard dataset, the proposed DQFL method improves the test accuracies of NPC, MQDF and DLQDF by 4.94%, 1.83%, and 1.82%, respectively. The test accuracy is further improved by training set expansion. On the ICDAR 2013 Chinese handwriting recognition competition dataset, the proposed DQFL+DLQDF classifier outperforms the best participating system based on deep convolutional neural network (CNN), while the test speed is much faster. [ABSTRACT FROM AUTHOR]

The collision fault detection of a XXY stage is proposed for the first time in this paper. The stage characteristic signals are extracted and imported into the master and slave chaos error systems by signal filtering from the vibratory magnitude of the stage. The trajectory diagram is made from the chaos synchronization dynamic error signals E1 and E2. The distance between characteristic positive and negative centers of gravity, as well as the maximum and minimum distances of trajectory diagram, are captured as the characteristics of fault recognition by observing the variation in various signal trajectory diagrams. The matter-element model of normal status and collision status is built by an extension neural network. The correlation grade of various fault statuses of the XXY stage was calculated for diagnosis. The dSPACE is used for real-time analysis of stage fault status with an accelerometer sensor. Three stage fault statuses are detected in this study, including normal status, Y collision fault and X collision fault. It is shown that the scheme can have at least 75% diagnosis rate for collision faults of the XXY stage. As a result, the fault diagnosis system can be implemented using just one sensor, and consequently the hardware cost is significantly reduced. [ABSTRACT FROM AUTHOR]

Background: Hospital-acquired infections (HAI) are associated with increased attributable morbidity, mortality, prolonged hospitalization, and economic costs. A simple, reliable prediction model for HAI has great clinical relevance. The objective of this study is to develop a scoring system to predict HAI that was derived from Logistic Regression (LR) and validated by Artificial Neural Networks (ANN) simultaneously. Methodology/Principal Findings: A total of 476 patients from all the 806 HAI inpatients were included for the study between 2004 and 2005. A sample of 1,376 non-HAI inpatients was randomly drawn from all the admitted patients in the same period of time as the control group. External validation of 2,500 patients was abstracted from another academic teaching center. Sixteen variables were extracted from the Electronic Health Records (EHR) and fed into ANN and LR models. With stepwise selection, the following seven variables were identified by LR models as statistically significant: Foley catheterization, central venous catheterization, arterial line, nasogastric tube, hemodialysis, stress ulcer prophylaxes and systemic glucocorticosteroids. Both ANN and LR models displayed excellent discrimination (area under the receiver operating characteristic curve [AUC]: 0.964 versus 0.969, p = 0.507) to identify infection in internal validation. During external validation, high AUC was obtained from both models (AUC: 0.850 versus 0.870, p = 0.447). The scoring system also performed extremely well in the internal (AUC: 0.965) and external (AUC: 0.871) validations. Conclusions: We developed a scoring system to predict HAI with simple parameters validated with ANN and LR models. Armed with this scoring system, infectious disease specialists can more efficiently identify patients at high risk for HAI during hospitalization. Further, using parameters either by observation of medical devices used or data obtained from EHR also provided good prediction outcome that can be utilized in different clinical settings. [ABSTRACT FROM AUTHOR]