Multitask TSK fuzzy system modeling by mining intertask common hidden structure

Transfer Learning Algorithm With Knowledge Division Level

One of the major challenges of transfer learning algorithms is the domain drifting problem where the knowledge of source scene is inappropriate for the task of target scene. To solve this problem, a transfer learning algorithm with knowledge division level (KDTL) is proposed to subdivide knowledge of source scene and leverage them with different drifting degrees. The main properties of KDTL are three folds. First, a comparative evaluation mechanism is developed to detect and subdivide the knowledge into three kinds-the ineffective knowledge, the usable knowledge, and the efficient knowledge. Then, the ineffective and usable knowledge can be found to avoid the negative transfer problem. Second, an integrated framework is designed to prune the ineffective knowledge in the elastic layer, reconstruct the usable knowledge in the refined layer, and learn the efficient knowledge in the leveraged layer. Then, the efficient knowledge can be acquired to improve the learning performance. Third, the theoretical analysis of the proposed KDTL is analyzed in different phases. Then, the convergence property, error bound, and computational complexity of KDTL are provided for the successful applications. Finally, the proposed KDTL is tested by several benchmark problems and some real problems. The experimental results demonstrate that this proposed KDTL can achieve significant improvement over some state-of-the-art algorithms.

Multi-source online transfer algorithm based on source domain selection for EEG classification

The non-stationary nature of electroencephalography (EEG) signals and individual variability makes it challenging to obtain EEG signals from users by utilizing brain-computer interface techniques. Most of the existing transfer learning methods are based on batch learning in offline mode, which cannot adapt well to the changes generated by EEG signals in the online situation. To address this problem, a multi-source online migrating EEG classification algorithm based on source domain selection is proposed in this paper. By utilizing a small number of labeled samples from the target domain, the source domain selection method selects the source domain data similar to the target data from multiple source domains. After training a classifier for each source domain, the proposed method adjusts the weight coefficients of each classifier according to the prediction results to avoid the negative transfer problem. This algorithm was applied to two publicly available motor imagery EEG datasets, namely, BCI Competition Ⅳ Dataset Ⅱa and BNCI Horizon 2020 Dataset 2, and it achieved average accuracies of 79.29 and 70.86%, respectively, which are superior to those of several multi-source online transfer algorithms, confirming the effectiveness of the proposed algorithm.

Mutual Supervised Fusion & Transfer Learning with Interpretable Linguistic Meaning for Social Data Analytics

Social data analytics is often taken as the most commonly used method for community discovery, product recommendations, knowledge graph, etc. In this study, social data are firstly represented in different feature spaces by using various feature extraction algorithms. Then we build a transfer learning model to leverage knowledge from multiple feature spaces. During modeling, since the assumption that the training and the testing data have the same distribution is always true, we give a theorem and its proof which asserts the necessary and sufficient condition for achieving a minimum testing error. We also theoretically demonstrate that maximizing the classification error consistency across different feature spaces can improve the classification performance. Additionally, the cluster assumption derived from semi-supervised learning is introduced to enhance knowledge transfer. Finally, a Tagaki-Sugeno-Kang (TSK) fuzzy system-based learning algorithm is proposed, which can generate interpretable fuzzy rules. Experimental results not only demonstrate the promising social data classification performance of our proposed approach but also show its interpretability which is missing in many other models.

A Deep-Ensemble-Level-Based Interpretable Takagi-Sugeno-Kang Fuzzy Classifier for Imbalanced Data

Existing research reveals that the misclassification rate for imbalanced data depends heavily on the problematic areas due to the existence of small disjoints, class overlap, borderline, and rare data samples. In this study, by stacking zero-order Takagi-Sugeno-Kang (TSK) fuzzy subclassifiers on the minority class and its problematic areas in the deep ensemble, a novel deep-ensemble-level-based TSK fuzzy classifier (IDE-TSK-FC) for imbalanced data classification tasks is presented to achieve both promising classification performance and high interpretability of zero-order TSK fuzzy classifiers. Simultaneously, according to the stacked generalization principle, the proposed classifier lifts up oversampling from the data level to the deep ensemble level with a guarantee of enhanced generalization capability for class imbalance learning. In the structure of IDE-TSK-FC, the first interpretable zero-order TSK fuzzy subclassifier is built on the original training dataset. After that, several successive zero-order TSK fuzzy subclassifiers are stacked layer by layer on the newly identified problematic areas from the original training dataset plus the corresponding interpretable predictions obtained by the averaging strategy on all previous layers. IDE-TSK-FC simply takes the classical K -nearest neighboring algorithm at each layer to identify its problematic area that consists of the minority samples and its surrounding K majority neighbors. After randomly neglecting certain input features and randomly selecting the five Gaussian membership functions for all the chosen input features and the augmented feature in the premise of each fuzzy rule, each subclassifier can be quickly obtained by using the least learning machine to determine the consequent part of each fuzzy rule. The experimental results on both the public datasets and a real-world healthcare dataset demonstrate IDE-TSK-FC's superiority in class imbalanced learning.

Multi-task Fuzzy Clustering–Based Multi-task TSK Fuzzy System for Text Sentiment Classification

Text sentiment classification is an important technology for natural language processing. A fuzzy system is a strong tool for processing imprecise or ambiguous data, and it can be used for text sentiment analysis. This article proposes a new formulation of a multi-task Takagi-Sugeno-Kang fuzzy system (TSK FS) modeling, which can be used for text sentiment image classification. Using a novel multi-task fuzzy c-means clustering algorithm, the common (public) information among all tasks and the individual (private) information for each task are extracted. The information about clustering, for example, cluster centers, can be used to learn the antecedent parameters of multi-task TSK fuzzy systems. With the common and individual antecedent parameters obtained, a corresponding multi-task learning mechanism for learning consequent parameters is devised. Accordingly, a multi-task fuzzy clustering–based multi-task TSK fuzzy system (MTFCM-MT-TSK-FS) is proposed. When the proposed model is built, the information conveyed by the fuzzy rules formed is two-fold, including (1) common fuzzy rules representing the inter-task correlation information and (2) individual fuzzy rules depicting the independent information of each task. The experimental results on several text sentiment datasets demonstrate the validity of the proposed model.

Epilepsy Signal Recognition Using Online Transfer TSK Fuzzy Classifier Underlying Classification Error and Joint Distribution Consensus Regularization

In this study, an online transfer TSK fuzzy classifier O-T-TSK-FC is proposed for recognizing epilepsy signals. Compared with most of the existing transfer learning models, O-T-TSK-FC enjoys its merits from the following three aspects: 1) Since different patients often response to the same neuronal firing stimulation in different neural manners, the labeled data in the source domain cannot accurately represent the primary EEG data in the target domain. Therefore, we design an objective function which can integrate with subject-specific data in the target domain to induce the target predictive function. 2) A new regularization used for knowledge transfer is proposed from the perspective of error consensus, and its rationality is explained from the perspective of probability density estimation. 3) Clustering is used to partition source domains so as to reduce the computation of O-T-TSK-FC without affecting its performance. Based on the EEG signals collected from Bonn University, six different online scenarios for transfer learning are constructed. Experimental results on them show that O-T-TSK-FC performs better than benchmarking algorithms and robustly.

Assessing the Adequacy of Hemodialysis Patients via the Graph-Based Takagi-Sugeno-Kang Fuzzy System

Maintenance hemodialysis is the main method for the treatment of end-stage renal disease in China. The Kt/V value is the gold standard of hemodialysis adequacy. However, Kt/V requires repeated blood drawing and evaluation; it is hard to monitor dialysis adequacy frequently. In order to meet the need for repeated clinical assessments of dialysis adequacy, we want to find a noninvasive way to assess dialysis adequacy. Therefore, we collect some clinically relevant data and develop a machine learning- (ML-) based model to predict dialysis adequacy for clinical hemodialysis patients. We collect 250 patients, including gender, age, ultrafiltration (UF), predialysis body weight (preBW), postdialysis body weights (postBW), blood pressure (BP), heart rate (HR), and blood flow (BF). An efficient graph-based Takagi-Sugeno-Kang Fuzzy System (G-TSK-FS) model is proposed to predict the dialysis adequacy of hemodialysis patients. The root mean square error (RMSE) of our model is 0.1578. The proposed model can be used as a feasible method to predict dialysis adequacy, providing a new way for clinical practice. Our G-TSK-FS model could be used as a feasible method to predict dialysis adequacy, providing a new way for clinical practice.

A Self-Representation-Based Fuzzy SVM Model for Predicting Vascular Calcification of Hemodialysis Patients

In end-stage renal disease (ESRD), vascular calcification risk factors are essential for the survival of hemodialysis patients. To effectively assess the level of vascular calcification, the machine learning algorithm can be used to predict the vascular calcification risk in ESRD patients. As the amount of collected data is unbalanced under different risk levels, it has an influence on the classification task. So, an effective fuzzy support vector machine based on self-representation (FSVM-SR) is proposed to predict vascular calcification risk in this work. In addition, our method is also compared with other conventional machine learning methods, and the results show that our method can better complete the classification task of the vascular calcification risk.

Analysis and Management of Flu Disease Public Opinion Based on Machine Learning

In the new media era, there are more ways of information dissemination, and the speed of information dissemination becomes faster. Along with it, various public opinions and rumors flood the cyberspace. As a mainstream social media information publishing platform, microblog has become the main way for netizens to obtain, disseminate and publish information. Because microblog can freely make speeches, and has a fast transmission speed and a wide range, it is easy for public opinion information to be widely disseminated in a short time. In particular, information such as rumors in public opinion can affect the network environment and social stability. Therefore, it is necessary to analyze and predict public opinion changes and to provide early warning. The literature uses the classic BP-NN (BP-NN) as the base prediction model, and uses the information published on the Sina microblog platform as a sample to analyze and predict the public opinion of influenza diseases. Due to the BP-NN’ slow convergence speed, this paper introduces an improved genetic algorithm to select the optimal parameters in the BP-NN (IGA-BP-NN), shorten the calculation time, and improve the analysis and prediction efficiency. The experiments verify that the work in this paper can provide more accurate early-warning information for the public opinion management of related departments.

Classification of EEG signals in epilepsy using a novel integrated TSK fuzzy system

The use of machine learning technology to recognize electrical signals of the brain is becoming increasingly popular. Compared with doctors’ manual judgment, machine learning methods are faster. However, only when its recognition accuracy reaches a high level can it be used in practice. Due to the difference in the data distributions of the training dataset and the test dataset and the lack of training samples, the classification accuracies of general machine learning algorithms are not satisfactory. In fact, among the many machine learning methods used to process epilepsy electroencephalogram (EEG) signals, most are black box methods; however, in medicine, methods with explanatory power are needed. In response to these three challenges, this paper proposes a novel technique based on domain adaptation learning, semi-supervised learning and a fuzzy system. In detail, we use domain adaptation learning to reduce deviation from the data distribution, semi-supervised learning to compensate for the lack of training samples, and the Takagi-Sugen-Kang (TSK) fuzzy system model to improve interpretability. Our experimental results show that the performance of the new method is better than those of most advanced epilepsy classification methods.

Brain MRI Intelligent Diagnostic Using an Improved Deep Convolutional Neural Network

The diagnosis of brain diseases based on magnetic resonance imaging (MRI) is a mainstream practice. In the course of practical treatment, medical personnel observe and analyze the changes in the size, position, and shape of various brain tissues in the brain MRI image, thereby judging whether the brain tissue has been diseased, and formulating the corresponding medical plan. The conclusion drawn after observing the image will be influenced by the subjective experience of the experts and is not objective. Therefore, it has become necessary to try to avoid subjective factors interfering with the diagnosis. This paper proposes an intelligent diagnosis model based on improved deep convolutional neural network (IDCNN). This model introduces integrated support vector machine (SVM) into IDCNN. During image segmentation, if IDCNN has problems such as irrational layer settings, too many parameters, etc., it will make its segmentation accuracy low. This study made a slight adjustment to the structure of IDCNN. First, adjust the number of convolution layers and down-sampling layers in the DCNN network structure, adjust the network’s activation function, and optimize the parameters to improve IDCNN’s non-linear expression ability. Then, use the integrated SVM classifier to replace the original Softmax classifier in IDCNN to improve its classification ability. The simulation experiment results tell that compared with the model before improvement and other classic classifiers, IDCNN improves segmentation results and promote the intelligent diagnosis of brain tissue.

Mining Maximal Dynamic Spatial Colocation Patterns

A spatial colocation pattern represents a subset of spatial features with instances that are prevalently located together in a geographic space. Although many algorithms for mining spatial colocation patterns have been proposed, the following problems still remain. these methods miss certain meaningful patterns (e.g., {Ganoderma_lucidum_new, maple_tree_dead} and {water_hyacinth_new(increase), algae_dead(decrease)}) and obtain a wrong conclusion if the instances of two or more features increase/decrease (i.e., new/dead) in the same/approximate proportion, which has no effect on the prevalent patterns; and the efficiency of existing methods is low in mining prevalent spatial colocation patterns, because the number of prevalent spatial colocation patterns is quite large. Therefore, we first propose the concept of a dynamic spatial colocation pattern that can reflect the dynamic relationships among spatial features. Second, we mine a small number of prevalent maximal dynamic spatial colocation patterns that can derive all prevalent dynamic spatial colocation patterns, which can improve the efficiency of obtaining all prevalent dynamic spatial colocation patterns. Third, we propose an algorithm for mining prevalent maximal dynamic spatial colocation patterns and two pruning strategies. Finally, the effectiveness and efficiency of the proposed method and the pruning strategies are verified by extensive experiments over real/synthetic data sets.

Design and Implementation of Human-Computer Interaction Systems Based on Transfer Support Vector Machine and EEG Signal for Depression Patients’ Emotion Recognition

At present, the demand for intelligentization of human-computer interaction systems (HCIS) has become increasingly prominent. Being able to recognize the emotions of users of interactive systems is a distinguishing feature of intelligent interactive systems. The intelligent HCIS can analyze the emotional changes of patients with depression, complete the interaction with the patients in a more appropriate manner, and the recognition results can assist family members or medical personnel to make response measures based on the patient’s emotional changes. Based on this background, this paper proposes a sentiment recognition method based on transfer support vector machines (TSVM) and EEG signals. The ER (ER) results based on this method are applied to HCIS. Such a HCIS is mainly used for the interaction of patients with depression. When a new field related to a certain field appears, if the new field data is relabeled, the sample is expensive, and it is very wasteful to discard all the old field data. The main innovation of this research is that the introduced classification model is TSVM. TSVM is a transfer learning strategy based on SVM. Transfer learning aims to solve related but different target domain problems by using a large amount of labeled source domain data. Therefore, the transfer support vector machine based on the transfer mechanism can use the small labeled data of the target domain and a large amount of old data in the related domain to build a high-quality classification model for the target domain, which can effectively improve the accuracy of classification. Comparing the classification results with other classification models, it can be concluded that TSVM can effectively improve the accuracy of ER in patients with depression. The HCIS based on the classification model has higher accuracy and better stability.

An Intelligence EEG Signal Recognition Method via Noise Insensitive TSK Fuzzy System Based on Interclass Competitive Learning

Epilepsy is an abnormal function disease of movement, consciousness, and nerve caused by abnormal discharge of brain neurons in the brain. EEG is currently a very important tool in the process of epilepsy research. In this paper, a novel noise-insensitive Takagi-Sugeno-Kang (TSK) fuzzy system based on interclass competitive learning is proposed for EEG signal recognition. First, a possibilistic clustering in Bayesian framework with interclass competitive learning called PCB-ICL is presented to determine antecedent parameters of fuzzy rules. Inherited by the possibilistic c-means clustering, PCB-ICL is noise insensitive. PCB-ICL learns cluster centers of different classes in a competitive relationship. The obtained clustering centers are attracted by the samples of the same class and also excluded by the samples of other classes and pushed away from the heterogeneous data. PCB-ICL uses the Metropolis-Hastings method to obtain the optimal clustering results in an alternating iterative strategy. Thus, the learned antecedent parameters have high interpretability. To further promote the noise insensitivity of rules, the asymmetric expectile term and Ho-Kashyap procedure are adopted to learn the consequent parameters of rules. Based on the above ideas, a TSK fuzzy system is proposed and is called PCB-ICL-TSK. Comprehensive experiments on real-world EEG data reveal that the proposed fuzzy system achieves the robust and effective performance for EEG signal recognition.

Fast Enhanced Exemplar-Based Clustering for Incomplete EEG Signals

The diagnosis and treatment of epilepsy is a significant direction for both machine learning and brain science. This paper newly proposes a fast enhanced exemplar-based clustering (FEEC) method for incomplete EEG signal. The algorithm first compresses the potential exemplar list and reduces the pairwise similarity matrix. By processing the most complete data in the first stage, FEEC then extends the few incomplete data into the exemplar list. A new compressed similarity matrix will be constructed and the scale of this matrix is greatly reduced. Finally, FEEC optimizes the new target function by the enhanced α-expansion move method. On the other hand, due to the pairwise relationship, FEEC also improves the generalization of this algorithm. In contrast to other exemplar-based models, the performance of the proposed clustering algorithm is comprehensively verified by the experiments on two datasets.

Downsizing and enhancing broad learning systems by feature augmentation and residuals boosting

Recently, a broad learning system (BLS) has been theoretically and experimentally confirmed to be an efficient incremental learning system. To get rid of deep architecture, BLS shares the same architecture and learning mechanism of the well-known functional link neural networks (FLNN), but works in broad learning way on both the randomly mapped features of original features of data and their randomly generated enhancement nodes. As such, BLS often requires a huge heap of hidden nodes to achieve the prescribed or satisfactory performance, which may inevitably cause both overwhelming storage requirement and overfitting phenomenon. In this study, a stacked architecture of broad learning systems called D&BLS is proposed to achieve enhanced performance and simultaneously downsize the system architecture. By boosting the residuals between previous and current layers and simultaneously augmenting the original input space with the outputs of the previous layer as the inputs of current layer, D&BLS stacks several lightweight BLS sub-systems to guarantee stronger feature representation capability and better classification/regression performance. Three fast incremental learning algorithms of D&BLS are also developed, without the need for the whole re-training. Experimental results on some popular datasets demonstrate the effectiveness of D&BLS in the sense of both enhanced performance and reduced system architecture.

Classification and Diagnosis of Thyroid Carcinoma Using Reinforcement Residual Network with Visual Attention Mechanisms in Ultrasound Images

How to differentiate thyroid cancer nodules from a large number of benign nodules is always a challenging subject for clinicians. This paper proposes a novel Sal-deel network model to achieve the classification and diagnosis of thyroid cancer, which can simulate visual attention mechanism. The Sal-deep network introduces saliency map as an additional information on the deep residual network, which selectively enhances the feature extracted from different regions according to the mask map. Sal-deep network can work effectively for the benchmark networks with different data sets and different structures, and it is a universal network model. Sal-deep network increases the complexity of the network, but improves the efficiency of the network. A large number of qualitative and quantitative experiments show that our improved network is superior to other existing deep models in terms of classification accuracy rate and Recall, which is suitable for clinical application.

Segmentation and Diagnosis of Liver Carcinoma Based on Adaptive Scale-Kernel Fuzzy Clustering Model for CT Images

Medical image analysis plays an important role in computer-aided liver-carcinoma diagnosis. Aiming at the existing image fuzzy clustering segmentation being not suitable to segment CT image with non-uniform background, a fast robust kernel space fuzzy clustering segmentation algorithm is proposed. Firstly, the sample in euclidean space is mapped into the high dimensional feature space through the kernel function. Then the linear weighted filtering image is obtained by combining the current pixel with its neighborhood pixels through the space information in CT image. Finally, the two-dimensional histogram between the clustered pixel and its neighborhood mean is introduced into the robust kernel space image fuzzy clustering, and the iterative expression of the fast robust fuzzy clustering in kernel space is obtained by using Lagrange multiplier method. The experimental results on four databases show that our proposed method can segment liver tumors from abdominal CT volumes effectively and automatically, and the comprehensive segmentation performance of the proposed method is superior to that of several existing methods.

Transfer Learning Based Fault Diagnosis with Missing Data Due to Multi-Rate Sampling

Deep learning is an effective feature extraction method widely applied in fault diagnosis fields since it can extract fault features potentially involved in multi-sensor data. But different sensors equipped in the system may sample data at different sampling rates, which will inevitably result in a problem that a very small number of samples with a complete structure can be used for deep learning since the input of a deep neural network (DNN) is required to be a structurally complete sample. On the other hand, a large number of samples are required to ensure the efficiency of deep learning based fault diagnosis methods. To solve the problem that a structurally complete sample size is too small, this paper proposes a fault diagnosis framework of missing data based on transfer learning which makes full use of a large number of structurally incomplete samples. By designing suitable transfer learning mechanisms, extra useful fault features can be extracted to improve the accuracy of fault diagnosis based simply on structural complete samples. Thus, online fault diagnosis, as well as an offline learning scheme based on deep learning of multi-rate sampling data, can be developed. The efficiency of the proposed method is demonstrated by utilizing data collected from the QPZZ- II rotating machinery vibration experimental platform system.

A Novel Distributed Multitask Fuzzy Clustering Algorithm for Automatic MR Brain Image Segmentation

Artificial intelligence algorithms have been used in a wide range of applications in clinical aided diagnosis, such as automatic MR image segmentation and seizure EEG signal analyses. In recent years, many machine learning-based automatic MR brain image segmentation methods have been proposed as auxiliary methods of medical image analysis in clinical treatment. Nevertheless, many problems regarding precise medical images, which cannot be effectively utilized to improve partition performance, remain to be solved. Due to the poor contrast in grayscale images, the ambiguity and complexity of MR images, and individual variability, the performance of classic algorithms in medical image segmentation still needs improvement. In this paper, we introduce a distributed multitask fuzzy c-means (MT-FCM) clustering algorithm for MR brain image segmentation that can extract knowledge common among different clustering tasks. The proposed distributed MT-FCM algorithm can effectively exploit information common among different but related MR brain image segmentation tasks and can avoid the negative effects caused by noisy data that exist in some MR images. Experimental results on clinical MR brain images demonstrate that the distributed MT-FCM method demonstrates more desirable performance than the classic signal task method.

Optimizing Evaluation Metrics for Multitask Learning via the Alternating Direction Method of Multipliers

Multitask learning (MTL) aims to improve the generalization performance of multiple tasks by exploiting the shared factors among them. Various metrics (e.g., -score, area under the ROC curve) are used to evaluate the performances of MTL methods. Most existing MTL methods try to minimize either the misclassified errors for classification or the mean squared errors for regression. In this paper, we propose a method to directly optimize the evaluation metrics for a large family of MTL problems. The formulation of MTL that directly optimizes evaluation metrics is the combination of two parts: 1) a regularizer defined on the weight matrix over all tasks, in order to capture the relatedness of these tasks and 2) a sum of multiple structured hinge losses, each corresponding to a surrogate of some evaluation metric on one task. This formulation is challenging in optimization because both of its parts are nonsmooth. To tackle this issue, we propose a novel optimization procedure based on the alternating direction scheme of multipliers, where we decompose the whole optimization problem into a subproblem corresponding to the regularizer and another subproblem corresponding to the structured hinge losses. For a large family of MTL problems, the first subproblem has closed-form solutions. To solve the second subproblem, we propose an efficient primal-dual algorithm via coordinate ascent. Extensive evaluation results demonstrate that, in a large family of MTL problems, the proposed MTL method of directly optimization evaluation metrics has superior performance gains against the corresponding baseline methods.

Active Multitask Learning With Trace Norm Regularization Based on Excess Risk

This paper addresses the problem of active learning on multiple tasks, where labeled data are expensive to obtain for each individual task but the learning problems share some commonalities across multiple related tasks. To leverage the benefits of jointly learning from multiple related tasks and making active queries, we propose a novel active multitask learning approach based on trace norm regularized least squares. The basic idea is to induce an optimal classifier which has the lowest risk and at the same time which is closest to the true hypothesis. Toward this aim, we devise a new active selection criterion that takes into account not only the risk but also the excess risk, which measures the distance to the true hypothesis. Based on this criterion, our proposed algorithm actively selects the instance to query for its label based on the combination of the two risks. Experiments on both synthetic and real-world datasets show that our proposed algorithm provides superior performance as compared to other state-of-the-art active learning methods.

Seizure Classification From EEG Signals Using Transfer Learning, Semi-Supervised Learning and TSK Fuzzy System

Recognition of epileptic seizures from offline EEG signals is very important in clinical diagnosis of epilepsy. Compared with manual labeling of EEG signals by doctors, machine learning approaches can be faster and more consistent. However, the classification accuracy is usually not satisfactory for two main reasons: the distributions of the data used for training and testing may be different, and the amount of training data may not be enough. In addition, most machine learning approaches generate black-box models that are difficult to interpret. In this paper, we integrate transductive transfer learning, semi-supervised learning and TSK fuzzy system to tackle these three problems. More specifically, we use transfer learning to reduce the discrepancy in data distribution between the training and testing data, employ semi-supervised learning to use the unlabeled testing data to remedy the shortage of training data, and adopt TSK fuzzy system to increase model interpretability. Two learning algorithms are proposed to train the system. Our experimental results show that the proposed approaches can achieve better performance than many state-of-the-art seizure classification algorithms.

Multi-task diagnosis for autism spectrum disorders using multi-modality features: A multi-center study

Autism spectrum disorder (ASD) is a neurodevelopment disease characterized by impairment of social interaction, language, behavior, and cognitive functions. Up to now, many imaging-based methods for ASD diagnosis have been developed. For example, one may extract abundant features from multi-modality images and then derive a discriminant function to map the selected features toward the disease label. A lot of recent works, however, are limited to single imaging centers. To this end, we propose a novel multi-modality multi-center classification (M3CC) method for ASD diagnosis. We treat the classification of each imaging center as one task. By introducing the task-task and modality-modality regularizations, we solve the classification for all imaging centers simultaneously. Meanwhile, the optimal feature selection and the modeling of the discriminant functions can be jointly conducted for highly accurate diagnosis. Besides, we also present an efficient iterative optimization solution to our formulated problem and further investigate its convergence. Our comprehensive experiments on the ABIDE database show that our proposed method can significantly improve the performance of ASD diagnosis, compared to the existing methods. Hum Brain Mapp 38:3081-3097, 2017. © 2017 Wiley Periodicals, Inc.

Integrating Soft Set Theory and Fuzzy Linguistic Model to Evaluate the Performance of Training Simulation Systems

The advancement of high technologies and the arrival of the information age have caused changes to the modern warfare. The military forces of many countries have replaced partially real training drills with training simulation systems to achieve combat readiness. However, considerable types of training simulation systems are used in military settings. In addition, differences in system set up time, functions, the environment, and the competency of system operators, as well as incomplete information have made it difficult to evaluate the performance of training simulation systems. To address the aforementioned problems, this study integrated analytic hierarchy process, soft set theory, and the fuzzy linguistic representation model to evaluate the performance of various training simulation systems. Furthermore, importance-performance analysis was adopted to examine the influence of saving costs and training safety of training simulation systems. The findings of this study are expected to facilitate applying military training simulation systems, avoiding wasting of resources (e.g., low utility and idle time), and providing data for subsequent applications and analysis. To verify the method proposed in this study, the numerical examples of the performance evaluation of training simulation systems were adopted and compared with the numerical results of an AHP and a novel AHP-based ranking technique. The results verified that not only could expert-provided questionnaire information be fully considered to lower the repetition rate of performance ranking, but a two-dimensional graph could also be used to help administrators allocate limited resources, thereby enhancing the investment benefits and training effectiveness of a training simulation system.

A Hybrid Short-Term Traffic Flow Prediction Model Based on Singular Spectrum Analysis and Kernel Extreme Learning Machine

Short-term traffic flow prediction is one of the most important issues in the field of intelligent transport system (ITS). Because of the uncertainty and nonlinearity, short-term traffic flow prediction is a challenging task. In order to improve the accuracy of short-time traffic flow prediction, a hybrid model (SSA-KELM) is proposed based on singular spectrum analysis (SSA) and kernel extreme learning machine (KELM). SSA is used to filter out the noise of traffic flow time series. Then, the filtered traffic flow data is used to train KELM model, the optimal input form of the proposed model is determined by phase space reconstruction, and parameters of the model are optimized by gravitational search algorithm (GSA). Finally, case validation is carried out using the measured data of an expressway in Xiamen, China. And the SSA-KELM model is compared with several well-known prediction models, including support vector machine, extreme learning machine, and single KLEM model. The experimental results demonstrate that performance of the proposed model is superior to that of the comparison models. Apart from accuracy improvement, the proposed model is more robust.

Robust Face Recognition via Multi-Scale Patch-Based Matrix Regression

In many real-world applications such as smart card solutions, law enforcement, surveillance and access control, the limited training sample size is the most fundamental problem. By making use of the low-rank structural information of the reconstructed error image, the so-called nuclear norm-based matrix regression has been demonstrated to be effective for robust face recognition with continuous occlusions. However, the recognition performance of nuclear norm-based matrix regression degrades greatly in the face of the small sample size problem. An alternative solution to tackle this problem is performing matrix regression on each patch and then integrating the outputs from all patches. However, it is difficult to set an optimal patch size across different databases. To fully utilize the complementary information from different patch scales for the final decision, we propose a multi-scale patch-based matrix regression scheme based on which the ensemble of multi-scale outputs can be achieved optimally. Extensive experiments on benchmark face databases validate the effectiveness and robustness of our method, which outperforms several state-of-the-art patch-based face recognition algorithms.

A Novel Cascade Classifier for Automatic Microcalcification Detection

In this paper, we present a novel cascaded classification framework for automatic detection of individual and clusters of microcalcifications (μC). Our framework comprises three classification stages: i) a random forest (RF) classifier for simple features capturing the second order local structure of individual μCs, where non-μC pixels in the target mammogram are efficiently eliminated; ii) a more complex discriminative restricted Boltzmann machine (DRBM) classifier for μC candidates determined in the RF stage, which automatically learns the detailed morphology of μC appearances for improved discriminative power; and iii) a detector to detect clusters of μCs from the individual μC detection results, using two different criteria. From the two-stage RF-DRBM classifier, we are able to distinguish μCs using explicitly computed features, as well as learn implicit features that are able to further discriminate between confusing cases. Experimental evaluation is conducted on the original Mammographic Image Analysis Society (MIAS) and mini-MIAS databases, as well as our own Seoul National University Bundang Hospital digital mammographic database. It is shown that the proposed method outperforms comparable methods in terms of receiver operating characteristic (ROC) and precision-recall curves for detection of individual μCs and free-response receiver operating characteristic (FROC) curve for detection of clustered μCs.

A Computationally Inexpensive Optimal Guidance via Radial-Basis-Function Neural Network for Autonomous Soft Landing on Asteroids

Optimal guidance is essential for the soft landing task. However, due to its high computational complexities, it is hardly applied to the autonomous guidance. In this paper, a computationally inexpensive optimal guidance algorithm based on the radial basis function neural network (RBFNN) is proposed. The optimization problem of the trajectory for soft landing on asteroids is formulated and transformed into a two-point boundary value problem (TPBVP). Combining the database of initial states with the relative initial co-states, an RBFNN is trained offline. The optimal trajectory of the soft landing is determined rapidly by applying the trained network in the online guidance. The Monte Carlo simulations of soft landing on the Eros433 are performed to demonstrate the effectiveness of the proposed guidance algorithm.

Using Dynamic Multi-Task Non-Negative Matrix Factorization to Detect the Evolution of User Preferences in Collaborative Filtering

Predicting what items will be selected by a target user in the future is an important function for recommendation systems. Matrix factorization techniques have been shown to achieve good performance on temporal rating-type data, but little is known about temporal item selection data. In this paper, we developed a unified model that combines Multi-task Non-negative Matrix Factorization and Linear Dynamical Systems to capture the evolution of user preferences. Specifically, user and item features are projected into latent factor space by factoring co-occurrence matrices into a common basis item-factor matrix and multiple factor-user matrices. Moreover, we represented both within and between relationships of multiple factor-user matrices using a state transition matrix to capture the changes in user preferences over time. The experiments show that our proposed algorithm outperforms the other algorithms on two real datasets, which were extracted from Netflix movies and Last.fm music. Furthermore, our model provides a novel dynamic topic model for tracking the evolution of the behavior of a user over time.

A Decision Support System Coupling Fuzzy Logic and Probabilistic Graphical Approaches for the Agri-Food Industry: Prediction of Grape Berry Maturity

Agri-food is one of the most important sectors of the industry and a major contributor to the global warming potential in Europe. Sustainability issues pose a huge challenge for this sector. In this context, a big issue is to be able to predict the multiscale dynamics of those systems using computing science. A robust predictive mathematical tool is implemented for this sector and applied to the wine industry being easily able to be generalized to other applications. Grape berry maturation relies on complex and coupled physicochemical and biochemical reactions which are climate dependent. Moreover one experiment represents one year and the climate variability could not be covered exclusively by the experiments. Consequently, harvest mostly relies on expert predictions. A big challenge for the wine industry is nevertheless to be able to anticipate the reactions for sustainability purposes. We propose to implement a decision support system so called FGRAPEDBN able to (1) capitalize the heterogeneous fragmented knowledge available including data and expertise and (2) predict the sugar (resp. the acidity) concentrations with a relevant RMSE of 7 g/l (resp. 0.44 g/l and 0.11 g/kg). FGRAPEDBN is based on a coupling between a probabilistic graphical approach and a fuzzy expert system.