Pattern Recognition Framework Research Articles

DLPR: Deep Learning-Based Enhanced Pattern Recognition Frame-Work for Improved Myoelectric Prosthesis Control

In EMG based pattern recognition (EMG-PR), deep learning-based techniques have become more prominent for their self-regulating capability to extract discriminant features from large data-sets. Moreover, the performance of traditional machine learning-based methods show limitation to categorize over a certain number of classes and degrades over a period of time. In this paper, an accurate, robust, and fast convolutional neural network-based framework for EMG pattern identification is presented. To assess the performance of the proposed system, five publicly available and benchmark data-sets of upper limb activities were used. This data-set contains 49 to 52 upper limb motions (NinaPro DB1, NinaPro DB2, and NinaPro DB3), Data with force variation, and data with arm position variation for intact and amputated subjects. The classification accuracies of 92.18% (53 classes), 91.56% (49 classes), 84.98% (49 classes of amputees), 95.67% (6 classes with force variation), and 99.12% (8 classes with arm position variation) have been observed during the testing. The performance of the proposed system is compared with the state of art techniques in the literature. The findings demonstrate that classification accuracy and time complexity have been improved significantly. For signal pre-processing and deep learning techniques, Keras which is a high-level API for TensorFlow is utilised to build profound learning models. The proposed method has been tested on the Intel Core i7 3.5GHz, 7th Gen CPU with 8GB DDR4 RAM.

A novel pattern recognition framework based on ensemble of handcrafted features on images

A novel pattern recognition framework based on ensemble of handcrafted features on images

Emotion Recognition and EEG Analysis Using ADMM-Based Sparse Group Lasso

This study presents an efficient sparse learning-based pattern recognition framework to recognize the discrete states of three emotions—happy, angry, and neutral emotion—using electroencephalogram (EEG) signals. In affective computing with massive spatiotemporal brainwave signals, a large number of features can be extracted to capture various information from multivariate brain data. However, it is often a challenge to model high-dimensional features efficiently in consideration of the intrinsic structure, such as channel location, feature group, time epoch, etc. In this study, features were extensively extracted from EEG signals and were applied on a structured sparse learning model to perform feature selection and classification simultaneously. An efficient ADMM-based algorithm with a closed-form solution was developed to solve the sparse group model. Experimental results show that the proposed method is capable of selecting a small number of important neural features to discriminate the three emotion states with high classification accuracy. With greatly enhanced interpretability and efficiency to learn neural signatures of brain activity from high-dimensional-feature, low-sample-size brain imaging data, the presented computational framework is promising for handling emotion recognition problems with high-dimensional brain imaging data.

Mixed-Type Wafer Defect Pattern Recognition Framework Based on Multifaceted Dynamic Convolution

Wafer Defect pattern recognition is an essential process in semiconductor manufacturing. This helps the manufacturers improve their fabrication process, reduce initial costs, and avoid further defects. However, mixed-type defects can be varied and complicated, which is difficult for traditional deep learning model to learn their features. To address this problem, we utilize dynamicity to allow the adaptive integration of information. Therefore, this paper proposed a mixed-type wafer defect pattern recognition framework based on multi-faceted dynamic convolution (MFD). This framework can effectively detect decisive features and integrate helpful information from defect patterns. Specifically, the proposed MFD firstly designs a 1-D auto-encoder to process the input, and extends it to a 3-D to obtain trans-pixel dynamic perception. In addition, we apply a channel-amalgamating mechanism to obtain the trans-channel dynamic perception and further synthesize the information across the channel. We appraised our model based on a dataset with 38 defect patterns generated from real industrial manufacturing. The results showed that the proposed framework excelled the vanilla CNN and state-of-the-art deep learning models. Further interpretable analysis based on visualization also indicated that this framework can adaptively procure the significant features from different defects.

Intelligent framework for social robots based on artificial intelligence-driven mobile edge computing

In recent years, artificial intelligence technology has gradually expanded its application scenarios in the field of education. Nevertheless, at present, most AI application scenarios are still difficult to really penetrate into the core links. Educational robot based on artificial intelligence technology can provide humanized interaction and personalized intelligent teaching in different links, thus it has attracted more attention and development than ever. For mobile robots, vision based target recognition technology is a very basic but challenging topic. The result of robot target recognition is directly related to the positioning, navigation and other work of the robot. Therefore, this paper studies the intelligent education information framework of social robot based on artificial intelligence-driven mobile edge computing. The pattern recognition framework is applied to the system and the proposed model is tested on the public database. Compared to the other state-of-the-art methodologies, the proposed idea performs better.

Computational optimal transport for molecular spectra: The fully discrete case.

The use of computational optimal transport is investigated as a tool for comparing two molecular spectra. Unlike other techniques for comparing molecular spectra in a pattern-recognition framework, transport distances simultaneously encode information about line positions and intensities. In addition, it is shown that transport distances are a useful alternative to Euclidean distances as Euclidean distances are based on line-by-line comparisons, while transport distances reflect broader features of molecular spectra and adequately compare spectra with different resolutions. This paper includes a tutorial on the use of optimal transport and investigates several well-chosen examples to illustrate the utility of computational optimal transport for comparing molecular spectra.

Recent changes in the atmospheric circulation patterns during the dry-to-wet transition season in south tropical South America (1979-2020): Impacts on precipitation and fire season

AbstractWe analyze the characteristics of atmospheric variations over tropical South America using the pattern recognition framework of weather typing or atmospheric circulation patterns (CPs). During 1979-2020, nine CPs are defined in the region, using a k-means algorithm based on daily unfiltered 850 hPa winds over 0035°N-30°S, 90°W-30°W. CPs are primarily interpreted as stages of the annual cycle of the low-level circulation. We identified three “winter” CPs (CP7, CP8 and CP9), three “summer” CPs (CP3, CP4 and CP5) and three “transitional” CPs (CP1, CP2 and CP6). Significant long-term changes are detected during the dry-to-wet transition season (July-October) over south tropical South America (STSA). One of the wintertime patterns (CP9) increases from 20% in the 1980s to 35% in the last decade while the “transitional” CP2 decreases from 13% to 7%. CP9 is characterized by enhancement of the South American Low-Level Jet and increasing atmospheric subsidence over STSA. CP2 is characterized by southerly cold-air incursions and anomalous convective activity over STSA. The years characterized by high (low) frequency of CP9 (CP2) during the dry-to-wet transition season are associated with a delayed South American Monsoon onset and anomalous dry conditions over STSA. Consistently, a higher frequency of CP9 intensifies the fire season over STSA (1999-2020). Over the Brazilian states of Maranhão, Tocantins, Goiás and São Paulo, the seasonal frequency of CP9 explains around 35%-44% of the interannual variations of fire counts.

Improving stock trading decisions based on pattern recognition using machine learning technology.

PRML, a novel candlestick pattern recognition model using machine learning methods, is proposed to improve stock trading decisions. Four popular machine learning methods and 11 different features types are applied to all possible combinations of daily patterns to start the pattern recognition schedule. Different time windows from one to ten days are used to detect the prediction effect at different periods. An investment strategy is constructed according to the identified candlestick patterns and suitable time window. We deploy PRML for the forecast of all Chinese market stocks from Jan 1, 2000 until Oct 30, 2020. Among them, the data from Jan 1, 2000 to Dec 31, 2014 is used as the training data set, and the data set from Jan 1, 2015 to Oct 30, 2020 is used to verify the forecasting effect. Empirical results show that the two-day candlestick patterns after filtering have the best prediction effect when forecasting one day ahead; these patterns obtain an average annual return, an annual Sharpe ratio, and an information ratio as high as 36.73%, 0.81, and 2.37, respectively. After screening, three-day candlestick patterns also present a beneficial effect when forecasting one day ahead in that these patterns show stable characteristics. Two other popular machine learning methods, multilayer perceptron network and long short-term memory neural networks, are applied to the pattern recognition framework to evaluate the dependency of the prediction model. A transaction cost of 0.2% is considered on the two-day patterns predicting one day ahead, thus confirming the profitability. Empirical results show that applying different machine learning methods to two-day and three-day patterns for one-day-ahead forecasts can be profitable.

A novel framework for regional pattern recognition of drought intensities

A novel framework for regional pattern recognition of drought intensities

Facial Image Analysis for Identification of Gender: A Machine Learning based Approach

Facial biometrics for gender classification is known to significantly improve the efficiency of person identification in biometric access control models. It not only increases the speed but also improves the accuracy. It reduces the effort of finding a match for a face in the databases to almost a half. The process like any pattern recognition framework needs to extract the useful features. A novel gender identification algorithm is proposed which is based on the facial features of a person. Viola Jones object detection technique is used for face detection from an image, and the relevant facial features are extracted using Topographic Independent Component Analysis. An SVM based classifier is trained using the calculated feature vector to determine whether the person in the image is a male or a female.

Semi-supervised style transfer mapping-based framework for sEMG-based pattern recognition with 1- or 2-DoF forearm motions

BackgroundThe development of body-worn sensors has made it easier to measure surface electromyograms (sEMGs) from individuals and to employ sEMG-based interfaces for user-centric health monitoring, rehabilitation, human augmentation, and amusement. However, it remains difficult to measure large amounts of sEMG data from a user (target). Thus, the development of a subject-to-subject transfer framework that uses the information that is available from other people (source) is challenging work. ObjectivesIn this study, we propose a subject-to-subject transfer framework, which includes the following four steps: (i) the construction of individual support vector machines (SVMs) from the source subjects; (ii) the selection of effective classifiers for the target based on the individual SVM classification results; (iii) the linear projection of the target data into the source subject data using the semi-supervised style transfer mapping algorithm; and (iv) an ensemble strategy of class probabilities for the selected classifiers. MethodsTo evaluate the performance of proposed framework, we collected 8-class, 1-DoF and 14-class, 2-DoF sEMG datasets that were acquired from the same 25 subjects using an eight-channel wearable device. The classifiers were trained with time-domain and autoregressive features. ResultsOur proposed method exhibited superior performance on both datasets compared to a conventional transfer framework using covariate shift adaptation. The sEMG datasets and sample codes used in this study are publicly available at https://github.com/Suguru55/SS-STM_for_MyoDatasets.

Gap-free global annual soil moisture: 15 km grids for 1991–2018

Abstract. Soil moisture is key for understanding soil–plant–atmosphere interactions. We provide a soil moisture pattern recognition framework to increase the spatial resolution and fill gaps of the ESA-CCI (European Space Agency Climate Change Initiative v4.5) soil moisture dataset, which contains > 40 years of satellite soil moisture global grids with a spatial resolution of ∼ 27 km. We use terrain parameters coupled with bioclimatic and soil type information to predict finer-grained (i.e., downscaled) satellite soil moisture. We assess the impact of terrain parameters on the prediction accuracy by cross-validating downscaled soil moisture with and without the support of bioclimatic and soil type information. The outcome is a dataset of gap-free global mean annual soil moisture predictions and associated prediction variances for 28 years (1991–2018) across 15 km grids. We use independent in situ records from the International Soil Moisture Network (ISMN, 987 stations) and in situ precipitation records (171 additional stations) only for evaluating the new dataset. Cross-validated correlation between observed and predicted soil moisture values varies from r= 0.69 to r= 0.87 with root mean squared errors (RMSEs, m3 m−3) around 0.03 and 0.04. Our soil moisture predictions improve (a) the correlation with the ISMN (when compared with the original ESA-CCI dataset) from r= 0.30 (RMSE = 0.09, unbiased RMSE (ubRMSE) = 0.37) to r= 0.66 (RMSE = 0.05, ubRMSE = 0.18) and (b) the correlation with local precipitation records across boreal (from r= < 0.3 up to r= 0.49) or tropical areas (from r= < 0.3 to r= 0.46) which are currently poorly represented in the ISMN. Temporal trends show a decline of global annual soil moisture using (a) data from the ISMN (-1.5[-1.8,-1.24] %), (b) associated locations from the original ESA-CCI dataset (-0.87[-1.54,-0.17] %), (c) associated locations from predictions based on terrain parameters (-0.85[-1.01,-0.49] %), and (d) associated locations from predictions including bioclimatic and soil type information (-0.68[-0.91,-0.45] %). We provide a new soil moisture dataset that has no gaps and higher granularity together with validation methods and a modeling approach that can be applied worldwide (Guevara et al., 2020, https://doi.org/10.4211/hs.9f981ae4e68b4f529cdd7a5c9013e27e).

Modeling train timetables as images: A cost-sensitive deep learning framework for delay propagation pattern recognition

As a vital component of train operational control, train delay propagation pattern discovery is critically important for both railway controllers and passengers. In this study, we present a carefully designed deep learning model, called FCF-Net, that comprises fully connected neural networks (FCNN) and convolutional neural networks (CNN) for train delay propagation pattern recognition in railway systems. FCF-Net first uses a CNN component that handles train timetables as images to capture interactions of train events and an FCNN component to capture the influence of non-operational features separately; then it uses another FCNN component to combinedly learn the dependencies between operational and non-operational features. In addition, considering the imbalance of train delay data, a cost-sensitive technique that assigns different misclassification costs for different class was used to better deal with the imbalanced data. The main goal of the FCF-Net is to realize efficient and accurate train delay propagation pattern recognition by mining potential knowledge from train operation data. The predictive and computational performance of the model was tested and evaluated on data from two high-speed railway lines with different operational features in China. The results show that FCF-Net, once trained with sufficient data, outperforms conventional deep learning with common loss and other state-of-the-art deep learning models for train delay propagation pattern recognition, indicating its capability in knowledge discovery from train operation data. In addition, the computational results show that FCF-Net exhibits more efficient training process than existing state-of-the-art deep learning models.

Learning regularized representations of categorically labelled surface EMG enables simultaneous and proportional myoelectric control

BackgroundProcessing the surface electromyogram (sEMG) to decode movement intent is a promising approach for natural control of upper extremity prostheses. To this end, this paper introduces and evaluates a new framework which allows for simultaneous and proportional myoelectric control over multiple degrees of freedom (DoFs) in real-time. The framework uses multitask neural networks and domain-informed regularization in order to automatically find nonlinear mappings from the forearm sEMG envelope to multivariate and continuous encodings of concurrent hand- and wrist kinematics, despite only requiring categorical movement instruction stimuli signals for calibration.MethodsForearm sEMG with 8 channels was collected from healthy human subjects (N = 20) and used to calibrate two myoelectric control interfaces, each with two output DoFs. The interfaces were built from (I) the proposed framework, termed Myoelectric Representation Learning (MRL), and, to allow for comparisons, from (II) a standard pattern recognition framework based on Linear Discriminant Analysis (LDA). The online performances of both interfaces were assessed with a Fitts’s law type test generating 5 quantitative performance metrics. The temporal stabilities of the interfaces were evaluated by conducting identical tests without recalibration 7 days after the initial experiment session.ResultsMetric-wise two-way repeated measures ANOVA with factors method (MRL vs LDA) and session (day 1 vs day 7) revealed a significant (p<0.05) advantage for MRL over LDA in 5 out of 5 performance metrics, with metric-wise effect sizes (Cohen’s d) separating MRL from LDA ranging from left|dright|=0.62 to left|dright|=1.13. No significant effect on any metric was detected for neither session nor interaction between method and session, indicating that none of the methods deteriorated significantly in control efficacy during one week of intermission.ConclusionsThe results suggest that MRL is able to successfully generate stable mappings from EMG to kinematics, thereby enabling myoelectric control with real-time performance superior to that of the current commercial standard for pattern recognition (as represented by LDA). It is thus postulated that the presented MRL approach can be of practical utility for muscle-computer interfaces.

Research on Underground Pipeline Fault Monitoring Method Based on Big Data

Distributed optical fiber sensors can sensitively sense local temperature changes caused by leakage at any position of the pipeline, but massive monitoring data has significant spatio-temporal non-stationary characteristics, and it is difficult to directly diagnose leakage based on the monitoring data. Under the framework of statistical pattern recognition, a spatio-temporal big data analysis method based on sliding window outlier analysis is proposed. Only the internal characteristics of distributed temperature monitoring data can be used to realize the intelligent identification of pipeline leakage, and the sliding is determined. The value method of window length and abnormal state diagnosis window length, and the physical simulation of prototype insulation steel pipe leakage monitoring was carried out. The results show that when the pipeline is intact, this method will not cause false alarms. Once the pipeline leaks, the method can quickly identify the pipeline leakage event and accurately locate the leak location.

Influence of music liking on EEG based emotion recognition

In studies of emotions, music is usually used to induce the emotions that are measured on the arousal-valence/arousal-valence-dominance scales. However, the influence of music liking (that depends on individual preference and appraisal) on the induced emotions is often ignored. This work presents a novel study on the influence of liking on arousal, valence, and dominance using a signal processing and pattern recognition framework. Emotion recognition was performed using a feature-level fusion of three features together with feature selection method and a classifier. The features were derived from wavelet decomposition of EEG, pairwise functional connectivity, and graph-theoretic measures that reflect characteristics of an individual electrode, pair of electrodes, and topological properties of the brain networks, respectively. Here, classification is done between the high/low categories of each of the arousal, valence, and dominance scales under three different cases of music liking. The study shows that the classification performances of arousal, valence, and dominance were 22.50%, 14.87%, and 19.44% above the empirical chance-level, respectively. The fusion framework gave up to 5% relative improvement over individual features. The study indicates that liking influences classification performance and also the temporal dynamics of emotional experience across these scales. We observe an inverted U relationship between the level of liking and arousal and dominance classification performance. We also analyzed the feature and electrode usage and specific aspects of brain activity at different levels of liking. This reveals the importance of high-frequency bands and hemispheric features in emotion recognition.

A Pattern Recognition Framework for Detecting Changes in Chinese Internet Management System

Past studies on the Chinese Internet management system have revealed a smart Internet management system that takes advantage of time to filter content with collective action potential. How and why such a system was institutionalized? We offer a historical institutional analysis to explain the way in which the system evolved. We implement social network analysis to examine the Weibo posts of recurrent events, the elections in Area A in 2016 and 2018, to identify pattern changes in the system. There are two aspects of the changes: the centralization of the command line to a single authority and the implementation of a discriminatory strategy to deal with the various online expressions together forming this intelligent system. The improved Chinese information surveillance system demonstrates both a top-down information management and a bottom-up opinion formation.

Contextual Approach to Industrial Situation Recognition

The article describes the development of multifaceted and efficient approaches to the context information analysis for synthesis of industrial situations context recognition algorithm in automated management systems within the enterprises. The probability theory method and method of statistical analysis, decision theory method, methods of algorithm and combination theory were used while researching. The research resulted in the development of new approaches to the context information analysis framework for pattern recognition which enables us to identify the procedure of contextual recognition for synthesis of working industrial situation recognition algorithm. A correspondence between the recognition error rate and the guaranteed recognition threshold, which can be used for setting up the automated context-based recognition systems, was analytically obtained during the research.

A fully-automated computer-aided breast lesion detection and classification system

This study presents an automatic computer-aided detection and diagnosis system which consists of two parts. The first part is for breast lesion characterization developed in pattern recognition framework (K-means clustering method) which is important to provide useful information for breast lesion characterization. Characterization of the detected lesion areas is done based on 6 parameters that are: (1) histogram, (2) shape, (3) gray level co-occurrence matrix, (4) gray level run length matrix, (5) neighboring gray tone difference matrix, and (6) gray level dependence matrix features. The second part of the system is developed based on machine learning algorithms and serves for the classification of localized breast lesions as benign and malignant. For classification, 4 different machine learning algorithms were investigated: (1) support vector, (2) k-nearest neighbors, (3) random forest, and (4) naïve Bayes classifiers. 84 histopathologically proven breast lesions were analyzed in the study. The proposed system compensates the motion artifacts, segments breast lesions, and classifies the lesions as benign and malignant. The results prove that the developed comprehensive system can detect and classifies breast lesions without any intervention. The best accuracy, sensitivity, specificity, and precision values to decide the tumor aggressiveness are 90.36%, 96.25%, 83.33%, and 92%, respectively.

Robustness of Muscle Synergies under Variant Muscle Contraction Force during Forearm Movements.

The Electromyography-based Pattern-Recognition (EMG-PR) framework has been investigated for almost three decades towards developing an intuitive myoelectric prosthesis. To utilize the knowledge of the underlying neurophysiological processes of natural movements, the concept of muscle synergy has been applied in prosthesis control and proved to be of great potential recently. For a muscle-synergy-based myoelectric system, the variation of muscle contraction force is also a confounding factor. This study evaluates the robustness of muscle synergies under a variant force level for forearm movements. Six channels of forearm surface EMG were recorded from six healthy subjects when they performed 4 movements (hand open, hand close, wrist flexion, and wrist extension) using low, moderate, and high force, respectively. Muscle synergies were extracted from the EMG using the alternating nonnegativity constrained least squares and active set (NNLS) algorithm. Three analytic strategies were adopted to examine whether muscle synergies were conserved under different force levels. Our results consistently showed that there exists fixed, robust muscle synergies across force levels. This outcome would provide valuable insights to the implementation of muscle- synergy-based assistive technology for the upper extremity.