Search

Background The diagnosis of Parkinson disease (PD) is mainly based on clinical symptoms, and there is a lack of objective methods for correct diagnosis. At present, there have been studies on retinal structural changes as a biomark for early diagnosis of PD, but machine learning based on retinal structural changes for predicting early PD has not yet been studied. Objective To construct a machine learning model based on the characteristics of retinal structural changes, explore its value in early PD diagnosis, and the accuracy of different machine learning algorithms for early PD diagnosis. Methods From October 2021 to September 2022, 49 PD patients aged 40 to 70 years old (PD group) who attended outpatient clinics and were hospitalized in the department of neurology of Henan Provincial People's Hospital (PD group) and 39 healthy people with matching age and sex (healthy control group) who came to the hospital for physical examination were collected. All study subjects underwent swept-source optical coherence tomography and swept-source optical coherence tomography angiography, the thickness and vessel density of the macular retina were also quantitatively analyzed. The 88 subjects were randomly divided into the 62 training sets and 26 validation set according to the ratio of 7∶3. Variables with significant differences between the PD group and healthy control group were selected as the characteristic variables for inclusion in the machine learning model, and Logistic regression (LR) , K-nearest neighbor algorithm (KNN) , decision tree (DT) , random forest (RF) and extreme gradient boosting (XGboost) models were constructed in the training set. The area under the curve (AUC) , accuracy, sensitivity and specificity of the receiver operating characteristic (ROC) curve were used to evaluate the predictive value of the machine learning model based on retinal structural changes for early PD. Results Compared with the healthy control group, the density of the upper outer ring (A6) , the outer temporal outer ring (A7) , the lower outer ring (A8) and the outer nasal ring (A9) of the superficial capillaries in the PD group were reduced, the thickness of the upper inner ring (A2) , the inner temporal inner ring (A3) , the inferior inner ring (A4) , the inner ring of the nasal side (A5) of the retinal layer, A6, A7, A8 and A9, the thickness of A6 of the ganglion cell complex layer, the thickness of A7 of the nerve fiber layer, A2 and A4, A5, A6, A7, A8, A9 became thinner (P

This paper presents a multi-algorithm fusion model (StackingGroup) based on the Stacking ensemble learning framework to address the variable selection problem in high-dimensional group structure data. The proposed algorithm takes into account the differences in data observation and training principles of different algorithms. It leverages the strengths of each model and incorporates Stacking ensemble learning with multiple group structure regularization methods. The main approach involves dividing the data set into K parts on average, using more than 10 algorithms as basic learning models, and selecting the base learner based on low correlation, strong prediction ability, and small model error. Finally, we selected the grSubset + grLasso, grLasso, and grSCAD algorithms as the base learners for the Stacking algorithm. The Lasso algorithm was used as the meta-learner to create a comprehensive algorithm called StackingGroup. This algorithm is designed to handle high-dimensional group structure data. Simulation experiments showed that the proposed method outperformed other R2, RMSE, and MAE prediction methods. Lastly, we applied the proposed algorithm to investigate the risk factors of low birth weight in infants and young children. The final results demonstrate that the proposed method achieves a mean absolute error (MAE) of 0.508 and a root mean square error (RMSE) of 0.668. The obtained values are smaller compared to those obtained from a single model, indicating that the proposed method surpasses other algorithms in terms of prediction accuracy. [ABSTRACT FROM AUTHOR]

Accurate rainfall prediction remains a challenging problem because of the high volatility and complicated essence of atmospheric data. This study proposed a hybrid model (DSP) that combines the advantages of discrete wavelet transform (DWT), support vector regression (SVR), and Prophet to forecast rainfall data. First, the rainfall time series is decomposed into high-frequency and low-frequency subseries using discrete wavelet transform (DWT). The SVR and Prophet models are then used to predict high-frequency and low-frequency subsequences, respectively. Finally, the predicted rainfall is determined by summing the predicted values of each subsequence. A case study in China is conducted from 1 January 2014 to 30 June 2016. The results show that the DSP model provides excellent prediction, with RMSE, MAE, and R2 values of 6.17, 3.3, and 0.75, respectively. The DSP model yields higher prediction accuracy than the three baseline models considered, with the prediction accuracy ranking as follows: DSP > SSP > Prophet > SVR. In addition, the DSP model is quite stable and can achieve good results when applied to rainfall data from various climate types, with RMSEs ranging from 1.24 to 7.31, MAEs ranging from 0.52 to 6.14, and R2 values ranging from 0.62 to 0.75. The proposed model may provide a novel approach for rainfall forecasting and is readily adaptable to other time series predictions. [ABSTRACT FROM AUTHOR]

This paper revisits the temporal difference (TD) learning algorithm for the policy evaluation tasks in reinforcement learning. Typically, the performance of TD(0) and TD($\lambda$ λ ) is very sensitive to the choice of stepsizes. Oftentimes, TD(0) suffers from slow convergence. Motivated by the tight link between the TD(0) learning algorithm and the stochastic gradient methods, we develop a provably convergent adaptive projected variant of the TD(0) learning algorithm with linear function approximation that we term AdaTD(0). In contrast to the TD(0), AdaTD(0) is robust or less sensitive to the choice of stepsizes. Analytically, we establish that to reach an $\epsilon$ ε accuracy, the number of iterations needed is $\tilde{O}(\epsilon ^{-2}\ln ^4\frac{1}{\epsilon }/\ln ^4\frac{1}{\rho })$ O ˜ (ε - 2 ln 4 1 ε / ln 4 1 ρ) in the general case, where $\rho$ ρ represents the speed of the underlying Markov chain converges to the stationary distribution. This implies that the iteration complexity of AdaTD(0) is no worse than that of TD(0) in the worst case. When the stochastic semi-gradients are sparse, we provide theoretical acceleration of AdaTD(0). Going beyond TD(0), we develop an adaptive variant of TD($\lambda$ λ ), which is referred to as AdaTD($\lambda$ λ ). Empirically, we evaluate the performance of AdaTD(0) and AdaTD($\lambda$ λ ) on several standard reinforcement learning tasks, which demonstrate the effectiveness of our new approaches. [ABSTRACT FROM AUTHOR]

Capturing the dynamics in user preference is crucial to better predict user future behaviors because user preferences often drift over time. Many existing recommendation algorithms – including both shallow and deep ones – often model such dynamics independently, i.e., user static and dynamic preferences are not modeled under the same latent space, which makes it difficult to fuse them for recommendation. This paper considers the problem of embedding a user's sequential behavior into the latent space of user preferences, namely translating sequence to preference. To this end, we formulate the sequential recommendation task as a dictionary learning problem, which learns: 1) a shared dictionary matrix, each row of which represents a partial signal of user dynamic preferences shared across users; and 2) a posterior distribution estimator using a deep autoregressive model integrated with Gated Recurrent Unit (GRU), which can select related rows of the dictionary to represent a user's dynamic preferences conditioned on his/her past behaviors. Qualitative studies on the Netflix dataset demonstrate that the proposed method can capture the user preference drifts over time and quantitative studies on multiple real-world datasets demonstrate that the proposed method can achieve higher accuracy compared with state-of-the-art factorization and neural sequential recommendation methods. [ABSTRACT FROM AUTHOR]

We consider a class of nonconvex regularized optimization problems, which appear frequently in machine learning and data processing. Due to the structure of the problems, the iteratively reweighted algorithm was developed and applied to the consensus optimization. In this paper, we propose the acceleration of this scheme by adding an inertial term in each iteration. The proposed algorithms inherit the advantages of classical decentralized algorithms: they can be implemented over a connected network, in which the agents communicate with their neighbors and perform local computations. We also employ the diminishing stepsizes technique for the iteratively reweighted algorithm and consider its acceleration. In specific cases, our algorithms reduce to existing decentralized schemes and also indicate novel ones. Mathematically, we prove the convergence for both algorithms with several assumptions on the objective functions. With Kurdyka-Łojasiewicz property, convergence rates can be derived for constant stepsize case. Numerical results demonstrate the efficiency of the algorithms. [ABSTRACT FROM AUTHOR]

Detecting volatile organic compounds (VOCs) in human breath is critical for the early diagnosis of diseases. Good selectivity of VOC sensors is crucial for the accurate analysis of VOC biomarkers in human breath, which consists of more than 200 types of VOCs. In this paper, a flexible virtual sensor array (FVSA) was proposed based on a sensing layer of MXene and laser-induced graphene interdigital electrodes (LIG-IDEs) for detecting VOCs in exhaled human breath. The fabrication of LIG-IDEs avoids the costly and complicated procedures required for the preparation of traditional IDEs. The FVSA's responses of multiple parameters help build a unique fingerprint for each VOC, without a need for changing the temperature of the sensing element, which is commonly used in the VSA of semiconductor VOC sensors. Based on machine learning algorithms, we have achieved highly precise recognition of different VOCs and mixtures and accurate prediction (accuracy of 89.1%) of the objective VOC's concentration in variable backgrounds using this proposed FVSA. Moreover, a blind analysis validates the capacity of the FVSA to identify alcohol content in human breath with an accuracy of 88.9% using breath samples from volunteers before and after alcohol consumption. These results show that the proposed FVSA is promising for the detection of VOC biomarkers in human exhaled breath and early diagnosis of diseases. [ABSTRACT FROM AUTHOR]

Predicting material's microstructure under new processing conditions is essential in advanced manufacturing and materials science. This is because the material's microstructure hugely influences the material's properties. We demonstrate an elegant machine learning algorithm that faithfully predicts the microstructure under new conditions, without the need of knowing the governing laws. We name this algorithm, RCWGAN-GP, which is regression-based conditional generative adversarial networks with Wasserstein loss function and gradient penalty. This algorithm was trained with experimental SEM micrographs from laser-sintered alumina under various laser powers. The RCWGAN-GP realistically regenerates the SEM micrographs under the trained laser powers. Impressively, it also faithfully predicts the alumina's microstructure under unexplored laser powers. The predicted microstructure features, including the morphology of the sintered particles and the pores, match the experimental SEM micrographs very well. We further quantitatively examined the prediction accuracy of the RCWGAN-GP. We trained the algorithm with computer-created micrograph datasets of secondary-phase growth governed by the well-known Johnson–Mehl–Avrami (JMA) equation. The RCWGAN-GP accurately regenerates the micrographs at the trained time series, in terms of the grains' shapes, sizes, and spatial distributions. More importantly, the predicted secondary phase fraction accurately follows the JMA curve. [ABSTRACT FROM AUTHOR]

As a common defect, the water–cement ratio of grout can currently be monitored only during the maintenance phase, which limits the repair methods and misses the optimal opportunity for repairs. To overcome this limitation, this study integrated ultrasonic parameters previously used to characterise cement-based materials and developed a new Initial Setting Time and Water–Cement Ratio (IST_WCR) risk model to predict the setting time and water–cement ratio grout using machine learning (ML) algorithms. Experiments on grout involved four different water–cement ratios, ranging from 0.11 to 0.18. A data-driven method based on ML was used to extract predictive factors from eight ultrasonic parameters, including the speed, energy, main frequency, and main frequency amplitude of P-waves and S-waves, and to evaluate multiple ML classifiers to establish the IST_WCR risk prediction model. This model underwent internal and external cross-validations and demonstrated very strong performance with a Brier score of under 0.01. The dataset for ML classifiers contained a total of 956 signals and 7648 features. Compared with traditional methods, this method can automatically characterise the setting process of grout and identify defective water–cement ratios at a very early stage of curing. [ABSTRACT FROM AUTHOR]

Operation anomalies are common phenomena in large-scale solar farms. Effective anomaly detection and classification is essential for improving operation reliability and electricity generation. However, this is a challenging task due to the high complexity and wide variety of frequently occurring anomalies. Furthermore, existing preinstalled supervisory control and data acquisition systems (SCADA) can only provide a limited amount of information regarding the healthy condition of solar farms, making accurate anomaly detection and classification difficult. This paper presents a data-driven anomaly detection and classification solution, which can accurately detect and classify diverse photovoltaic system anomalies. The proposed solution does not require additional equipment or non-SCADA data collection. More specifically, the proposed work consists of two methods: 1) a hierarchical context-aware anomaly detection method using unsupervised learning; and 2) a multimodal anomaly classification method. The proposed solution has been deployed in two large-scale solar farms (39.36 and 21.62 MWp). Multimonth operation demonstrates the effectiveness, robustness, and cost and computation efficiency of the proposed solution. [ABSTRACT FROM AUTHOR]

• The dividing line of crack modes in the conventional RA-AF analysis method is difficult to determine. • The clustering algorithms successfully classified the crack modes of AE signals. • The dimensionality reduction results confirmed that AF has the greatest effect on crack classification. • The Gaussian mixture model is applicable to the crack classification of acoustic emission signals from different components. In actual projects, the damage of many critical components cannot be directly observed. Therefore, it is necessary to monitor their damage with structural health monitoring (SHM) technology to get the crack modes of the damage. Acoustic emission (AE) is a non-destructive testing (NDT) technique in structural health monitoring, and crack modes can be classified by analyzing the rise angle (RA) and average frequency (AF) of acoustic emission signals. However, the dividing line for classifying different crack patterns in this method is difficult to determine, and for the same member, different parameters can lead to a huge difference in the dividing line. This problem limits the application of the method. In this study, multiple machine learning algorithms were applied to cluster AE signals with known crack modes, and the clustering results were consistent with the real crack modes, solving the problem of difficult to determine the dividing line in the traditional RA-AF method. Furthermore, dimensionality reduction was performed on this set of AE signals, and the semi-empirical RA-AF analysis method was confirmed to be accurate. [ABSTRACT FROM AUTHOR]

Taxi demand prediction is one of the key factors in making online taxi hailing services more successful and more popular. Accurate taxi demand prediction can bring various advantages including, but not limited to, enhancing user experience, increasing taxi utilization, and optimizing traffic efficiency. However, the task is challenging because of complex spatial and temporal dependencies of taxi demand. In addition, relationships between non-adjacent regions are also critical for accurate taxi demand prediction, whereas they are largely ignored by existing approaches. To this end, we propose a novel graph and time-series learning model for city-wide taxi demand prediction in this paper. It has two main building blocks, the first one utilize a graph network with attention mechanism to effectively learn spatial dependencies of taxi demand in a broader perspective of the entire city, and the output at each time interval is then transferred to the second block. In the graph network, the edge is defined by an Origin–Destination relation to capture non-adjacent impacts. The second one uses a neural network which is adept with processing sequence data to capture the temporal correlations of city-wide taxi demand. Using a large, real-world dataset and three metrics, we conduct an extensive experimental study and find that our model outperforms state-of-the-art baselines by 9.3% in terms of the root-mean-square error. [ABSTRACT FROM AUTHOR]

Semi-supervised learning has attracted significant attention in pattern recognition and machine learning. Among these methods, a very popular type is semi-supervised support vector machines. However, parameter selection in heat kernel function during the learning process is troublesome and harms the performance improvement of the hypothesis. To solve this problem, a novel local behavioral searching strategy is proposed for semi-supervised learning in this paper. In detail, based on human behavioral learning theory, the support vector machine is regularized with the un-normalized graph Laplacian. After building local distribution of feature space, local behavioral paradigm considers the form of the underlying probability distribution in the neighborhood of a point. Validation of the proposed method is performed with toy and real-life data sets. Results demonstrate that compared with traditional method, our method can more effectively and stably enhance the learning performance. [ABSTRACT FROM AUTHOR]

In recent years, distributed stochastic algorithms have become increasingly useful in the field of machine learning. However, similar to traditional stochastic algorithms, they face a challenge where achieving high fitness on the training set does not necessarily result in good performance on the test set. To address this issue, we propose to use of a distributed network topology to improve the generalization ability of the algorithms. We specifically focus on the Sharpness-Aware Minimization (SAM) algorithm, which relies on perturbation weights to find the maximum point with better generalization ability. In this paper, we present the decentralized stochastic sharpness-aware minimization (D-SSAM) algorithm, which incorporates the distributed network topology. We also provide sublinear convergence results for non-convex targets, which is comparable to consequence of Decentralized Stochastic Gradient Descent (DSGD). Finally, we empirically demonstrate the effectiveness of these results in deep networks and discuss their relationship to the generalization behavior of SAM. [ABSTRACT FROM AUTHOR]

The insufficiency of labeled training data for representing the distribution of entire dataset is a major obstacle in various practical data mining applications. Semi-supervised learning algorithms, which attempt to learn from both labeled and unlabeled data, provide possibilities to solve this problem. Graph-based semi-supervised learning has recently become one of the most active research areas. In this paper, a novel graph-based semi-supervised learning approach entitled Class Dissimilarity based Linear Neighborhood Propagation (CD-LNP) is proposed, which assumes that each data point can be linearly reconstructed from its neighborhood. The neighborhood graph of the input data is constructed according to a certain kind of dissimilarity between data points, which is specially designed to integrate the class information. Our algorithm can propagate the labels from the labeled points to entire data set using these linear neighborhoods with sufficient smoothness. Experiment results demonstrate that our approach outperforms other popular graph-based semi-supervised learning methods. [ABSTRACT FROM AUTHOR]

Review-based recommendation algorithms can alleviate the data sparsity issue in collaborative filtering by combining user ratings and reviews in model learning. However, most existing methods simplify the feature extraction process from reviews by assuming that different granularities of information (e.g., word, review, and feature) are equally important, which cannot optimally leverage the most important information and thus achieves suboptimal recommendation accuracy. Besides, many existing works directly regard text features as users or items representations, which may not be enough to make precise representations due to the large amount of redundant information in reviews. To tackle the two problems mentioned above, we propose a deep learning-based method named H ierarchical A ttention N etwork Oriented Towards C rowd I ntelligence (HANCI). First, HANCI replaces the commonly-used topic models or CNN text processor with an RNN text processor in review feature extraction, which can fully exploit the advantages of the sequential dependencies of reviews by using the whole hidden layers of the bidirectional LSTM as outputs. Second, HANCI weighs the importance of features guided by crowd intelligence to more accurately represent each user on each item, and vice versa. Third, HANCI utilizes a hierarchical attention network based on multi-level review text analysis to extract more precise user preferences and item latent features, so that HANCI can explore the importance of words, the usefulness of reviews and the importance of features to achieve more accurate recommendation. Extensive experiments on three public datasets show that HANCI outperforms the state-of-the-art review-based recommendation algorithms in accuracy and meanwhile provides insightful explanations. [ABSTRACT FROM AUTHOR]