Search

A new multi feature fusion fiber classification algorithm suitable for multi type fiber image recognition and classification were proposed to address the problem that commonly used manual identification methods in the market cannot recognize and classify multiple types of fibers. Firstly, the grayscale histograms, local binary patterns (LBP), directional gradient histograms (HOG), Hu invariant moments, and gray level co-occurrence matrix (GLCM) features of 10 types of fiber images were extracted. Then, the above features were weighted and fused to obtain a new feature, which is trained (8 000 pices fiber) and tested (2 000 pices fiber) using an support vector machine (SVM) model to obtain the final recognition accuracy. The experimental results show that the average accuracy of the algorithm is 85.8%, among which the characteristics of acrylic fiber, acetate fiber, and nylon fiber are very obvious, and the accuracy reaches over 90%. At the same time, the accuracy of difficult to distinguish wool and cashmere fibers also reaches about 88%. This algorithm has achieved good recognition results, providing a technical foundation for fast and accurate identification of fibers. [ABSTRACT FROM AUTHOR]

Partial discharge (PD) is a crucial and intricate electrical occurrence observed in various types of electrical equipment. Identifying and characterizing PDs is essential for upholding the integrity and reliability of electrical assets. This paper proposes an ensemble methodology aiming to strike a balance between the model complexity and the predictive performance in PD pattern recognition. A simple convolutional neural network (SCNN) was constructed to efficiently decrease the model parameters (quantities). A quadratic support vector machine (QSVM) was established and ensembled with the SCNN model to effectively improve the PD recognition accuracy. The input for QSVM consisted of the circular local binary pattern (CLBP) extracted from the enhanced image. A testing prototype with three types of PD was constructed and 3D phase-resolved pulse sequence (PRPS) spectrograms were measured and recorded by ultra-high frequency (UHF) sensors. The proposed methodology was compared with three existing lightweight CNNs. The experiment results from the collected dataset emphasize the benefits of the proposed method, showcasing its advantages in high recognition accuracy and relatively few mode parameters, thereby rendering it more suitable for PD pattern recognition on resource-constrained devices. [ABSTRACT FROM AUTHOR]

In this study, surface roughness is analyzed within a supervised pattern recognition framework using machine learning methods to present a robust technique for the quantitative determination of surface roughness of rocks. To reach this goal, rock surfaces are classified based on statistical, fractal, geostatistical, directional, and spectral features obtained from the surface profiles as well as the results of direct shear tests. In this way, after the calculation of the features in more than 9000 profiles collected from 84 natural rock samples, a representative vector containing representative features of the surface profiles was introduced for each surface, and joint roughness coefficient (JRC) was back-calculated from 84 direct shear tests on the rock samples. Then, principal component analysis and linear discriminant analysis of the representative vectors were performed in order to prepare the inputs for the classification. Multilayer perceptron (MLP) and radial basis function (RBF) artificial neural networks and support vector machine (SVM) were trained for the classification of rock surfaces. On the other hand, convolutional neural network (CNN) in which features are automatically extracted from the image data of representative surface profiles was the other method for the classification of rock surfaces. The comparison of the results shows RBF is a robust and reliable classifier yielding the least classification error among the investigated methods. Furthermore, comparing the results of machine learning methods with those of traditional equations proves that the SVM, MLP, and RBF yield superior performance. [ABSTRACT FROM AUTHOR]

In order to improve the recognition rate and accuracy rate of projectiles in six sky-screens intersection test system, this work proposes a new recognition method of projectiles by combining particle swarm optimization support vector and spatial-temporal constrain of six sky-screens detection sensor. Based on the measurement principle of the six sky-screens intersection test system and the characteristics of the output signal of the sky-screen, we analyze the existing problems regarding the recognition of projectiles. In order to optimize the projectile recognition effect, we use the support vector machine and basic particle swarm algorithm to form a new recognition algorithm. We set up the particle swarm algorithm optimization support vector projectile information recognition model that conforms to the six sky-screens intersection test system. We also construct a spatial-temporal constrain matching model based on the spatial geometric relationship of six sky-screen intersection, and form a new projectile signal recognition algorithm with six sky-screens spatial-temporal information constraints under the signal classification mechanism of particle swarm optimization algorithm support vector machine. Based on experiments, we obtain the optimal penalty and kernel function radius parameters in the PSO-SVM algorithm; we adjust the parameters of the support vector machine model, train the test signal data of every sky-screen, and gain the projectile signal classification results. Afterwards, according to the signal classification results, we calculate the coordinate parameters of the real projectile by using the spatial-temporal constrain of six sky-screens detection sensor, which verifies the feasibility of the proposed algorithm.

In this paper, a novel feature generator framework is proposed for handwritten digit classification. The proposed framework includes a two-stage cascaded feature generator. The first stage is based on principal component analysis (PCA), which generates projected data on principal components as features. The second one is constructed by a partially trained neural network (PTNN), which uses projected data as inputs and generates hidden layer outputs as features. The features obtained from the PCA and PTNN-based feature generator are tested on the MNIST and USPS datasets designed for handwritten digit sets. Minimum distance classifier (MDC) and support vector machine (SVM) methods are exploited as classifiers for the obtained features in association with this framework. The performance evaluation results show that the proposed framework outperforms the state-of-the-art techniques and achieves accuracies of 99.9815% and 99.9863% on the MNIST and USPS datasets, respectively. The results also show that the proposed framework achieves almost perfect accuracies, even with significantly small training data sizes. [ABSTRACT FROM AUTHOR]

In order to make full use of the characteristic information contained in the partial discharge (PD) signal and improve the recognition rate of the partial discharge type in the transformer, a partial discharge type recognition method based on wavelet transform (WT) and gray-gradient co-occurrence matrix (GGCM) algorithm was proposed. According to the internal structure characteristics of the transformer, four types of partial discharge defects were designed, and the transformer partial discharge experimental detection platform was built in the laboratory, and the high-frequency partial discharge current signal was collected by pulse current method. The flexibility of wavelet transform in non-stationary signal processing was used to construct time-frequency spectrum of partial discharge signal pulse. Then, combined with the GGCM algorithm, the 15-dimensional texture features of the time-frequency spectrum were extracted to form the feature vector. Input the feature vector into the support vector machine (SVM) classifier for pattern recognition. The results show that the recognition method combining wavelet transform and GGCM algorithm can effectively identify different types of partial discharge defects. [ABSTRACT FROM AUTHOR]

Partial discharge (PD) is a crucial and intricate electrical occurrence observed in various types of electrical equipment. Identifying and characterizing PDs is essential for upholding the integrity and reliability of electrical assets. This paper proposes an ensemble methodology aiming to strike a balance between the model complexity and the predictive performance in PD pattern recognition. A simple convolutional neural network (SCNN) was constructed to efficiently decrease the model parameters (quantities). A quadratic support vector machine (QSVM) was established and ensembled with the SCNN model to effectively improve the PD recognition accuracy. The input for QSVM consisted of the circular local binary pattern (CLBP) extracted from the enhanced image. A testing prototype with three types of PD was constructed and 3D phase-resolved pulse sequence (PRPS) spectrograms were measured and recorded by ultra-high frequency (UHF) sensors. The proposed methodology was compared with three existing lightweight CNNs. The experiment results from the collected dataset emphasize the benefits of the proposed method, showcasing its advantages in high recognition accuracy and relatively few mode parameters, thereby rendering it more suitable for PD pattern recognition on resource-constrained devices.

BACKGROUND: Advances in ablation for atrial fibrillation (AF) continue to be hindered by ambiguities in mapping, even between experts. We hypothesized that convolutional neural networks (CNN) may enable objective analysis of intracardiac activation in AF, which could be applied clinically if CNN classifications could also be explained. METHODS: We performed panoramic recording of bi-atrial electrical signals in AF. We used the Hilbert-transform to produce 175 000 image grids in 35 patients, labeled for rotational activation by experts who showed consistency but with variability (kappa [κ]=0.79). In each patient, ablation terminated AF. A CNN was developed and trained on 100 000 AF image grids, validated on 25 000 grids, then tested on a separate 50 000 grids. RESULTS: In the separate test cohort (50 000 grids), CNN reproducibly classified AF image grids into those with/without rotational sites with 95.0% accuracy (CI, 94.8%-95.2%). This accuracy exceeded that of support vector machines, traditional linear discriminant, and k-nearest neighbor statistical analyses. To probe the CNN, we applied gradient-weighted class activation mapping which revealed that the decision logic closely mimicked rules used by experts (C statistic 0.96). CONCLUSIONS: CNNs improved the classification of intracardiac AF maps compared with other analyses and agreed with expert evaluation. Novel explainability analyses revealed that the CNN operated using a decision logic similar to rules used by experts, even though these rules were not provided in training. We thus describe a scaleable platform for robust comparisons of complex AF data from multiple systems, which may provide immediate clinical utility to guide ablation. Registration: URL: https://www.clinicaltrials.gov; Unique identifier: NCT02997254. Graphic Abstract: A graphic abstract is available for this article.

Introduction: Over the years, several studies have been published reporting the use of distinct sources of information used for pattern recognition that can be translated into commands to control human-machine interface system, for example, electromyography (EMG), pressure sensors, and accelerometers. Studies using muscle motion patterns and its combination with EMG in the context of pattern recognition for evaluation of the muscles and human-machine interface system in able-bodied individuals and limb-absent subjects are scarce. Material and Methods: In this context, this research presents the assessment of the classification of patterns formed by features extracted from both muscle motion and electromyographic signals. Data sets were collected from both arms of five unilateral transradial limb-absent subjects and seven able-bodied subjects in the control group. The features from the EMG and the muscle motion such as amplitude, frequency, predictability, and variability of the signals were estimated. Results: The results were presented in terms of the sensitivity, specificity, precision, and accuracy of the classifier. The combination of both measurements, EMG and muscle motion, defined the six basic movements for limb-absent subjects within an accuracy of 98% ± 1% for the sound forearm against 96% ± 4% for the amputated forearm. Conclusions: For future work, it is expected that the strategy of classification and the combination of inertial and electromyographic activity will be used in actual scenarios for the controlling of artificial limbs and other applications related to human-machine interaction. Clinical Relevance: The use of inertial sensors may increase the usability and accuracy of systems used for diagnosing, training, therapy, or controlling devices such as orthoses and prostheses. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) is one of the most common causes of visual impairment. Automatic detection of hard exudates (HE) from retinal photographs is an important step for detection of DR. However, most of existing algorithms for HE detection are complex and inefficient. We have developed and evaluated an automatic retinal image processing algorithm for HE detection using dynamic threshold and fuzzy C-means clustering (FCM) followed by support vector machine (SVM) for classification. The proposed algorithm consisted of four main stages: (i) imaging preprocessing; (ii) localization of optic disc (OD); (iii) determination of candidate HE using dynamic threshold in combination with global threshold based on FCM; and (iv) extraction of eight texture features from the candidate HE region, which were then fed into an SVM classifier for automatic HE classification. The proposed algorithm was trained and cross-validated (10 fold) on a publicly available e-ophtha EX database (47 images) on pixel-level, achieving the overall average sensitivity, PPV, and F-score of 76.5%, 82.7%, and 76.7%. It was tested on another independent DIARETDB1 database (89 images) with the overall average sensitivity, specificity, and accuracy of 97.5%, 97.8%, and 97.7%, respectively. In summary, the satisfactory evaluation results on both retinal imaging databases demonstrated the effectiveness of our proposed algorithm for automatic HE detection, by using dynamic threshold and FCM followed by an SVM for classification.

Corn is an essential agricultural commodity since it is used in animal feed, biofuel, industrial processing, and the manufacture of non-food industrial commodities such as starch, acid, and alcohol. Early detection of diseases and pests of corn aims to reduce the possibility of crop failure and maintain the quality and quantity of crop yields. A decision tree is a nonparametric classification model in statistical machine learning that predicts target variables using tree-structured decisions. The performance of this model can increase significantly if the continuous predictor variables are discretized into valid categories. However, in some cases, the result does not provide satisfactory performance. The possible cause is the ambiguity in discretizing predictor variables. The incorporation of fuzzy membership functions into the model to resolve discretization ambiguity issues. This work aims to classify diseases and pests of corn plants using the decision tree model and improve the model’s performance by implementing fuzzy membership functions. The main contribution of this work is that we have shown a significant improvement in the decision tree model performance by implementing fuzzy membership functions; S-growth, triangle, and S-shrinkage curves. The proposed fuzzy model is better than the decision tree model, with an average performance increase from the largest to the smallest; kappa (12.16%), recall (11.8%), F-score (9.71%), precision (5.08%), accuracy (3.23%), specificity (1.94%), and AUC (0.49%). The combination of bias and variance generated by the proposed model is quite small, indicating that the model is able to capture data trends well.

A support vector machine (SVM) aims to achieve an optimal hyperplane with a maximum interclass margin and has been widely utilized in pattern recognition. Traditionally, a SVM mainly considers the separability of boundary points (i.e., support vectors), while the underlying data structure information is commonly ignored. In this paper, an improved support vector machine with earth mover's distance (EMD-SVM) is proposed. It can be regarded as an improved generalization of the standard SVM, and can automatically learn the distribution between the classes. To validate its performance, we discuss the necessity of the structural information of EMD-SVM in the linear and nonlinear cases, respectively. Experimental validation was designed and conducted in different application fields, which have shown its superior and robust performance. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Railway Science & Engineering is the property of Journal of Railway Science & Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Individual responses to fatigue have been observed in lifting kinematics, suggesting a subject-specific approach is necessary for fatigue identification. One-class support vector machines (OCSVM) may provide an objective method to classify fatigue-related kinematic changes during repetitive lifting. Participants completed a repetitive lifting protocol while motion capture recorded lifting motions. Subject-specific kinematics from participants' first 35% of lifts trained OCSVM decision boundaries. The remaining lifts were separated into test sets and classified against the decision boundary to identify the percentage of outlier lifts within each test set. Spearman's correlation assessed if the test sets' percentage of outlier lifts increased concurrently with participants' rating of perceived exertion (RPE). Significant positive associations were found for participants who demonstrated evidence of fatigue, while no significant associations were found for participants who did not demonstrate evidence of fatigue. These results demonstrate the prospective efficacy of an outlier detection tool for fatigue detection during repetitive lifting. Practitioner Summary: An objective subject-specific fatigue detection method is desired for workplace tasks, such as lifting. An outlier detection machine learning approach was identified when lifting movement patterns changed from baseline throughout a repetitive lifting protocol. Participants who demonstrated an increase in outlier movement patterns had a concurrent increase in self-reported fatigue. [ABSTRACT FROM AUTHOR]

Electromyography (EMG) processing is a fundamental part of medical research. It offers the possibility of developing new devices and techniques for the diagnosis, treatment, care, and rehabilitation of patients, in most cases non-invasively. However, EMG signals are random, non-stationary, and non-linear, making their classification difficult. Due to this, it is of vital importance to define which factors are helpful for the classification process. In order to improve this process, it is possible to apply algorithms capable of identifying which features are most important in the categorization process. Algorithms based on metaheuristic methods have demonstrated an ability to search for suitable subsets of features for optimization problems. Therefore, this work proposes a methodology based on genetic algorithms for feature selection to find the parameter space that offers the slightest classification error in 250 ms signal segments. For classification, a support vector machine is used. For this work, two databases were used, the first corresponding to the right upper extremity and the second formed by movements of the right lower extremity. For both databases, a feature space reduction of over 65% was obtained, with a higher average classification efficiency of 91% for the best subset of parameters. In addition, particle swarm optimization (PSO) was applied based on right upper extremity data, obtaining an 88% average error and a 46% reduction for the best subset of parameters. Finally, a sensitivity analysis was applied to the characteristics selected by PSO and genetic algorithms for the database of the right upper extremity, obtaining that the parameters determined by the genetic algorithms show greater sensitivity for the classification process. [ABSTRACT FROM AUTHOR]

In this study, a system is proposed that uses the Support Vector Machine (SVM) technique with Bag-of-Words (BoW) and recognizes static Pakistani Sign Language (PSL) alphabets. The application of the BoW technique with SVM, on a PSL images' dataset, has not been performed previously. Similarly, no publicly available dataset for PSL is available and previous studies have achieved a maximum classification accuracy of 91.98 %. For this study, a total of 511 images are collected for 36 static PSL alphabet signs from a native signer. The Sign Language (SL) recognition system uses the collected images as input and converts them to grayscale. To segment the images, the system uses the thresholding technique and Speeded Up Robust Feature (SURF) to extract the features. The system uses K-means clustering to cluster the extracted features. To form the BoW, the system computes the Euclidean distance among SURF descriptors and clustered data. The system then uses 5-fold cross-validation to divide the codebooks obtained from the BoW into training and testing. The developed system yields an overall accuracy of 97.87 % for the classification of static PSL signs at 1,500×1,500 image dimensions and 500 Bags. [ABSTRACT FROM AUTHOR]

In this research, support vector machine (SVM) as a supervised classification method has been used to explore the relationship between the geochemical anomaly and the surface alterations quantitatively in the Tanurcheh mineralization area. The Tanurcheh area has been located in the Khorasan Razavi province, Iran. This area has been considered as a high potential region for Cu and Au mineralization. The different mineralization processes of Au and Cu have unclearly been intertwined in this area and have created extreme surface alterations.Determination of the major origin of mineralization that has created strong alterations in this area is an important issue that can be addressed using a new proposed scenario. The relationship between the geochemical distribution map and the alteration zone was mathematically calculated using the proposed approach and then the geochemical anomaly map was predicted based on the alteration zones as an innovative achievement.In this paper, the Au and Cu geochemical data were divided into three classes, namely background, regional anomaly and local anomaly using the probability plot method. Two threshold values for Cu (70 and 300 PPM) and Au (0.13 and 0.4 PPM) were obtained by the probability plot method. Then the SVM was utilized to classify the geochemical samples using the ASTER images based on these obtained thresholds. The ASTER 14-band images were used as features in this classification. Using this novel scenario, the relationships between the Au and Cu mineralization processes with the intensity of alterations were determined and therefore the origin of these alteration zones was clarified. The SVM classification indices of correct classification rate (CCR) and confusion matrix demonstrate the main origin of alterations is related to the Cu mineralization process in this area. The CCR indices obtained based on the Au and Cu thresholds are 0.66 and 0.85 respectively. It demonstrates the intensity of alterations has more been affected by the Cu mineralization process and there is a relatively good relationship between the alteration zone and the Cu geochemical distribution map. Finally, the geochemical anomaly and background maps were properly predicted using the SVM and the ASTER bands. This paper shows the new application of SVM as a powerful tool for the interpretation of geochemical anomaly and the intensity of alteration.

In this paper, a novel feature generator framework is proposed for handwritten digit classification. The proposed framework includes a two-stage cascaded feature generator. The first stage is based on principal component analysis (PCA), which generates projected data on principal components as features. The second one is constructed by a partially trained neural network (PTNN), which uses projected data as inputs and generates hidden layer outputs as features. The features obtained from the PCA and PTNN-based feature generator are tested on the MNIST and USPS datasets designed for handwritten digit sets. Minimum distance classifier (MDC) and support vector machine (SVM) methods are exploited as classifiers for the obtained features in association with this framework. The performance evaluation results show that the proposed framework outperforms the state-of-the-art techniques and achieves accuracies of 99.9815% and 99.9863% on the MNIST and USPS datasets, respectively. The results also show that the proposed framework achieves almost perfect accuracies, even with significantly small training data sizes.

In real industrial scenarios, if the quality characteristics of a continuous or batch production process are monitored using Shewhart control charts, there could be a large number of false alarms about the process going out of control. This is because these control charts assume that the inherent noise of the monitored process is normally, independently and identically distributed, although the assumption of independence is not always correct for continuous and batch production processes. This paper presents three control chart pattern recognition systems where the inherent disturbance is assumed to be stationary. The systems use the first-order autoregressive (AR(1)), moving-average (MA(1)) and autoregressive moving-average (ARMA(1,1)) models. A special pattern generation scheme is adopted to ensure generality, randomness and comparability, as well as allowing the further categorisation of the studied patterns. Two different input representation techniques for the recognition systems were studied. These gave nearly the same performance for the MA(1) and ARMA(1,1) models, while the raw data yielded the highest accuracies when AR(1) was used. The effect of autocorrelation on the pattern recognition capabilities of the developed models was studied. It was observed that Normal and Upward Shift patterns were the most affected. [ABSTRACT FROM AUTHOR]

Background: Gait recognition has been applied in the prediction of the probability of elderly flat ground fall, functional evaluation during rehabilitation, and the training of patients with lower extremity motor dysfunction. Gait distinguishing between seemingly similar kinematic patterns associated with different pathological entities is a challenge for the clinician. How to realize automatic identification and judgment of abnormal gait is a significant challenge in clinical practice. The long-term goal of our study is to develop a gait recognition computer vision system using artificial intelligence (AI) and machine learning (ML) computing. This study aims to find an optimal ML algorithm using computer vision techniques and measure variables from lower limbs to classify gait patterns in healthy people. The purpose of this study is to determine the feasibility of computer vision and machine learning (ML) computing in discriminating different gait patterns associated with flat-ground falls. Methods: We used the Kinect® Motion system to capture the spatiotemporal gait data from seven healthy subjects in three walking trials, including normal gait, pelvic-obliquity-gait, and knee-hyperextension-gait walking. Four different classification methods including convolutional neural network (CNN), support vector machine (SVM), K-nearest neighbors (KNN), and long short-term memory (LSTM) neural networks were used to automatically classify three gait patterns. Overall, 750 sets of data were collected, and the dataset was divided into 80% for algorithm training and 20% for evaluation. Results: The SVM and KNN had a higher accuracy than CNN and LSTM. The SVM (94.9 ± 3.36%) had the highest accuracy in the classification of gait patterns, followed by KNN (94.0 ± 4.22%). The accuracy of CNN was 87.6 ± 7.50% and that of LSTM 83.6 ± 5.35%. Conclusions: This study revealed that the proposed AI machine learning (ML) techniques can be used to design gait biometric systems and machine vision for gait pattern recognition. Potentially, this method can be used to remotely evaluate elderly patients and help clinicians make decisions regarding disposition, follow-up, and treatment. [ABSTRACT FROM AUTHOR]

Extraction of built-up area (BUA) is essential for proper city planning and management. It enables the concerned authorities to formulate better city development policies and manage emergent disasters. However, the traditionally used optical data present spectral confusion where BUAs are mixed with other features adding to management complexities. Therefore, an advanced automated method is required to extract the spectral and textural features from satellite data for the pattern recognition of BUA. Landsat-8 Operational Land Imager (OLI) has been used in the current study to identify the pattern and extract BUA of Gujranwala, Pakistan. First, eight textural features based on the gray-level co-occurrence matrix (GLCM) are selected and combined with multispectral data. Then, feature selection methods are applied to select optimal features used to train the proposed support vector machine (SVM) classifier. Finally, the results from SVM classifiers are compared with k-nearest neighbor (k-NN) and backpropagation neural network (BP-NN) to highlight any improvements in results. The comparisons show that the proposed approach increases the overall accuracy of linear-SVM by 8.41%, radial basis function SVM by 8.3%, BP-NN by 7.63%, and k-NN by 6.6%. This can help city managers and planners to extract critical BUA information in otherwise unplanned and rapidly expanding cities to move toward smart and sustainable cities. [ABSTRACT FROM AUTHOR]

Aiming at facial expression recognition, the recognition rate is not high due to noise and occlusion. A hybrid approach of facial expression has been presented by combining local and global features. First, feature extraction is performed to fuse the histogram of oriented gradients (HOG) descriptor with the compounded local ternary pattern (C-LTP) descriptor. Second, features extracted by HOG and C-LTP are fused into a single feature vector. Third, the feature vector is sent to a multi-class support vector machine classifier for facial classification. Finally, the proposed method is compared with the existing facial expression recognition methods in three public facial expression image databases, and the results show that the recognition rates of the proposed method in MMI, JAFFE and CK[KG-*2]+ databases are 98.28%, 95.75% and 99.64%, respectively. The average recognition rate is 10% higher than other methods, which is better than other existing methods. The results of this study provide a reference for the research of facial expression recognition in many situations. The method of facial expression recognition proposed can effectively promote the development of human-computer interaction system and the study of computer image understanding. It is of great significance to realize the fusion of human language and natural language, as well as the establishment and implementation of the connection model between language and expression.

Label-free cell analysis is essential to personalized genomics, cancer diagnostics, and drug development as it avoids adverse effects of staining reagents on cellular viability and cell signaling. However, currently available label-free cell assays mostly rely only on a single feature and lack sufficient differentiation. Also, the sample size analyzed by these assays is limited due to their low throughput. Here, we integrate feature extraction and deep learning with high-throughput quantitative imaging enabled by photonic time stretch, achieving record high accuracy in label-free cell classification. Our system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individual cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. We compare various learning algorithms including artificial neural network, support vector machine, logistic regression, and a novel deep learning pipeline, which adopts global optimization of receiver operating characteristics. As a validation of the enhanced sensitivity and specificity of our system, we show classification of white blood T-cells against colon cancer cells, as well as lipid accumulating algal strains for biofuel production. This system opens up a new path to data-driven phenotypic diagnosis and better understanding of the heterogeneous gene expressions in cells.

In this research, a support vector machine (SVM) as a supervised classification method has been used to explore the relationship between the geochemical anomaly and the surface alterations quantitatively in the Tanurcheh mineralization area. The Tanurcheh area has been located in the Khorasan Razavi province, Iran. This area has been considered as a high potential region for Cu and Au mineralization. The different mineralization processes of Au and Cu have unclearly been intertwined in this area and have created extreme surface alterations. Determination of the major origin of mineralization that has created strong alterations in this area is an important issue that can be addressed using a new proposed scenario. The relationship between the geochemical distribution map and the alteration zone was mathematically calculated using the proposed approach and then the geochemical anomaly map was predicted based on the alteration zones as an innovative achievement. In this paper, the Au and Cu geochemical data were divided into three classes, namely background, regional anomaly, and local anomaly using the probability plot method. Two threshold values for Cu (70 and 300 PPM) and Au (0.13 and 0.4 PPM) were obtained by the probability plot method. Then the SVM was utilized to classify the geochemical samples using the ASTER images based on these obtained thresholds. The ASTER 14-band images were used as features in this classification. Using this novel scenario, the relationships between the Au and Cu mineralization processes with the intensity of alterations were determined and therefore the origin of these alteration zones was clarified. The SVM classification indices of correct classification rate (CCR) and confusion matrix demonstrate the main origin of alterations is related to the Cu mineralization process in this area. The CCR indices obtained based on the Au and Cu thresholds are 0.66 and 0.85 respectively. It demonstrates the intensity of alterations has more been affected by the Cu mineralization process and there is a relatively good relationship between the alteration zone and the Cu geochemical distribution map. Finally, the geochemical anomaly and background maps were properly predicted using the SVM and the ASTER bands. This paper shows the new application of SVM as a powerful tool for the interpretation of geochemical anomalies and the intensity of alteration. [ABSTRACT FROM AUTHOR]

Voice signal classification in three types according to their degree of periodicity, a task known as signal typing, is a relevant preprocessing step before computing any perturbation measures. However, it is a time consuming and subjective activity. This has given rise to interest in automatic systems that use objective measures to distinguish among the different signal types. The purpose of this paper is twofold. First, to propose a pattern recognition approach for automatic voice signal typing based on a multi-class linear Support Vector Machine, and using rather well-known parameters like Jitter, Shimmer, Harmonic-to-Noise Ratio, and Cepstral Prominence Peak in combination with nonlinear dynamics measures. Two novel features are also proposed as objective parameters. Second, to validate this approach using a large amount of signals coming from two well-known corpora using cross-dataset experiments to assess the generalizability of the system. A total amount of 1262 signals labeled by professional voice pathologists were used with this purpose. Statistically significant differences between all types were found for all features. Accuracies over 82.71% were estimated in all intra-datasets and inter-datasets using cross-validation. Finally, the use of posterior probabilities is proposed as a measure of the reliability of the assigned type. This could help clinicians to make a more informed decision about the type assigned to a voice. These outcomes suggest that the proposed approach can successfully discriminate among the three voice types, paving the way to a fully automatic tool for voice signal typing in the future. [ABSTRACT FROM AUTHOR]

Due to limitations imposed by cored wells, lithological data are often incomplete, and correct identification of lithofacies is problematic. Identification is actually an issue of pattern recognition, and based on newly proved findings, LightGBM (light gradient boosting machine) is considered to be an excellent pattern recognizer and, therefore, well suited for recognizing lithofacies. To remove remaining disadvantageous features and to further enhance the prediction performance of LightGBM, CRBM (continuous restricted Boltzmann machine) and AFSA (artificial fish swarm algorithm) are adopted as assistants to provide, respectively, high-quality learning data and to create optimal hyper-parameter settings during data processing. Subsequently, a predictor characterized by new ensemble learning is proposed, named CRBM-AFSA-LightGBM. To establish comprehensive verification, several validations are designed based on logging data derived from pre-salt carbonate reservoirs of the Santos Basin. Validations demonstrate the effectiveness and significance of integrating CRBM and AFSA; a further two validations are aimed at revealing whether a change in the learning data has an impact on prediction. To highlight the validation effect, PNN (probabilistic neural network) and SVM (support vector machine) are introduced as contrasting predictors. The test results demonstrate three important points: (1) CRBM and AFSA are preferred to assist in the capability of LightGBM; (2) the LightGBM-cored predictor performs better when compared with PNN-cored and SVM-cored predictors, especially when dealing with larger-scale learning data; (3) better robustness of the new predictor because reliable identification still can be achieved even when learning samples are sparse. Because all the validation evidences are optimistic, CRBM-AFSA-LightGBM is verified as a highly efficient and robust prediction tool for lithofacies identification in carbonate reservoirs. [ABSTRACT FROM AUTHOR]

At present, regions of the same class determined by Support Vector Machines (SVM) classifier, Support Vector Domain Description (SVDD) classifier and Deep Learning (DL) classifier may occupy regions of other classes or unknown classes in feature space. There exists a risk that samples of other classes or unknown classes are wrongly classified as a known class. In this paper, the Support Vector Domain Tightly Wrapping Description Design (SVDTWDD) method with appropriate rejection regions and the corresponding incremental learning algorithm are proposed to overcome the above problem. The main work includes: (1) We develop a construction algorithm of the tightly wrapping set for the homogeneous feature set; (2) Based on the homogeneous feature set and tightly wrapping set, a novel algorithm is presented for obtaining the tightly wrapping surface of the homogeneous feature region; (3) The method for constructing all the public regions outside of the tightly wrapping surface and the intersections of wrapping regions in two different tightly wrapping surfaces, as the rejection region of the classifier; (4) An incremental algorithm is also presented based on the SVD-TWDD method. The experimental results with UCI data sets show that the correct recognition rate of our proposed method is nearly100% even if with a low rejection rate.

Electromyography (EMG) processing is a fundamental part of medical research. It offers the possibility of developing new devices and techniques for the diagnosis, treatment, care, and rehabilitation of patients, in most cases non-invasively. However, EMG signals are random, non-stationary, and non-linear, making their classification difficult. Due to this, it is of vital importance to define which factors are helpful for the classification process. In order to improve this process, it is possible to apply algorithms capable of identifying which features are most important in the categorization process. Algorithms based on metaheuristic methods have demonstrated an ability to search for suitable subsets of features for optimization problems. Therefore, this work proposes a methodology based on genetic algorithms for feature selection to find the parameter space that offers the slightest classification error in 250 ms signal segments. For classification, a support vector machine is used. For this work, two databases were used, the first corresponding to the right upper extremity and the second formed by movements of the right lower extremity. For both databases, a feature space reduction of over 65% was obtained, with a higher average classification efficiency of 91% for the best subset of parameters. In addition, particle swarm optimization (PSO) was applied based on right upper extremity data, obtaining an 88% average error and a 46% reduction for the best subset of parameters. Finally, a sensitivity analysis was applied to the characteristics selected by PSO and genetic algorithms for the database of the right upper extremity, obtaining that the parameters determined by the genetic algorithms show greater sensitivity for the classification process.

Background: Gait recognition has been applied in the prediction of the probability of elderly flat ground fall, functional evaluation during rehabilitation, and the training of patients with lower extremity motor dysfunction. Gait distinguishing between seemingly similar kinematic patterns associated with different pathological entities is a challenge for the clinician. How to realize automatic identification and judgment of abnormal gait is a significant challenge in clinical practice. The long-term goal of our study is to develop a gait recognition computer vision system using artificial intelligence (AI) and machine learning (ML) computing. This study aims to find an optimal ML algorithm using computer vision techniques and measure variables from lower limbs to classify gait patterns in healthy people. The purpose of this study is to determine the feasibility of computer vision and machine learning (ML) computing in discriminating different gait patterns associated with flat-ground falls. Methods: We used the Kinect® Motion system to capture the spatiotemporal gait data from seven healthy subjects in three walking trials, including normal gait, pelvic-obliquity-gait, and knee-hyperextension-gait walking. Four different classification methods including convolutional neural network (CNN), support vector machine (SVM), K-nearest neighbors (KNN), and long short-term memory (LSTM) neural networks were used to automatically classify three gait patterns. Overall, 750 sets of data were collected, and the dataset was divided into 80% for algorithm training and 20% for evaluation. Results: The SVM and KNN had a higher accuracy than CNN and LSTM. The SVM (94.9 ± 3.36%) had the highest accuracy in the classification of gait patterns, followed by KNN (94.0 ± 4.22%). The accuracy of CNN was 87.6 ± 7.50% and that of LSTM 83.6 ± 5.35%. Conclusions: This study revealed that the proposed AI machine learning (ML) techniques can be used to design gait biometric systems and machine vision for gait pattern recognition. Potentially, this method can be used to remotely evaluate elderly patients and help clinicians make decisions regarding disposition, follow-up, and treatment.

Structural information is very important for improving the classification performance of classifiers. In order to increase the generalization performance of support vector machine (SVM) directly, several kinds of structured SVMs have been proposed. These algorithms with structural information only simply embed the global structural information or the local within-class information into SVM model. Thus, they sometimes are not suitable for real-world problems. To overcome the drawbacks, we firstly propose a novel SVM with local structural information (LSI-SVM) in this paper. In the LSI-SVM, the K-nearest neighbor (KNN) method is adopted. Applying the KNN method, the farthest neighbors set intra-class and the nearest neighbors set inter-class of the overall samples are obtained. It is more reasonable to maximize the margin between the nearest neighbors and the farthest neighbors. Both the global and local data structures are added into the optimization problem, making the LSI-SVM can fully utilize the underlying structural information and yield better performance. Furthermore, for nonlinear classification, the reproducing kernel Hilbert space theory is introduced and the kernel-based LSI-SVM is generated. What's more, in order to accelerate the training speed of LSI-SVM, a stochastic gradient LSI-SVM (LSI-SVM +) is constructed using the stochastic gradient descent (SGD) solver. Lastly, experimental results on regular-scale datasets, steel surface defects datasets, ORL face dataset and large-scale datasets demonstrate that both LSI-SVM and LSI-SVM + outperform other state-of-the-art algorithms on accuracy. In the meanwhile, our LSI-SVM + has high efficiency. [ABSTRACT FROM AUTHOR]

The identification and separation of sound sources has always been a difficult problem for acoustic technicians to tackle. This is due to the considerable complexity of a sound that is made up of many contributions at different frequencies. Each sound has a specific frequency spectrum, but when many sounds overlap it becomes difficult to discriminate between the different contributions. In this case, it can be extremely useful to have a tool that is capable of identifying the operating conditions of an acoustic source. In this study, measurements were made of the noise emitted by a wind turbine in the vicinity of a sensitive receptor. To identify the operating conditions of the wind turbine, average spectral levels in one-third octave bands were used. A model based on a support vector machine (SVM) was developed for the detection of the operating conditions of the wind turbine; then a model based on an artificial neural network was used to compare the performance of both models. The high precision returned by the simulation models supports the adoption of these tools as a support for the acoustic characterization of noise in environments close to wind turbines. [ABSTRACT FROM AUTHOR]

Image retrieval techniques in combination with support vector machine (SVM) on smartphones were studied to make pattern recognition of planar chromatograms. A micellar TLC method employed less toxic and flammable solvents was studied to discriminate four herbal medicines (HMs) from citrus fruits. And the chromatograms were used to test the pattern recognition method. The TLC method employed O/W microemulsion–formic acid (98:2) as the mobile phase, polyamide as the solid phase, and 1% aluminum trichloride aqueous solution as the visualization reagent. TLC of samples of dried lemon peel, dried sweet-orange peel, pummelo peel, and mandarin orange peel of varying origins were performed in three separate runs. Image retrieval techniques combined with SVM directly classified the chromatograms based on migration path images. A mobile application running on an Android smartphone was developed to perform the pattern recognition. The micellar TLC method satisfactorily characterized the chemical profile of the four HMs from citrus fruits. The pattern recognition method combining color layout descriptor with SVM correctly classified all the chromatograms. A smartphone with an application combining color layout descriptor with SVM would be a convenient tool for pattern recognition of planar chromatograms. [ABSTRACT FROM AUTHOR]

A method based on image processing, principal component analysis (PCA) and machine learning was proposed to identify pumpkin powdery mildew and improve the identification accuracy of pumpkin powdery mildew. The leaf-disease image was processed by the color feature compositing and detection method,in order to segment the lesion more accurately. Then 20 feature values are extracted, including the texture features, color features and morphological features of the segmented lesions, and the 20-dimensional original feature parameters were simplified to 3-dimensional feature parameters via the PCA method. Finally, three different SVM kernel functions are used to construct the classification model to compare the original feature parameters and principal component feature parameters separately. Experiment results show that the effect of illumination angle and intensity can be effectively eliminated after the super red feature calculation, and that the SVM model based on PCA and polynomial kernel function has a better recognition effect on pumpkin powdery mildew. The recognition rate is 97.3%, which is 3.15% higher than that of the traditional original characteristic parameters. Based on this finding, it can be concluded that this machine learning model can achieve accurate lesions identification. [ABSTRACT FROM AUTHOR]

In the electroencephalogram recorded data are often confounded with artifacts, especially in the case of eye blinks. Different methods for artifact detection and removal are discussed in the literature, including automatic detection and removal. Here, an automatic method of eye blink detection and correction is proposed where sparse coding is used for an electroencephalogram dataset. In this method, a hybrid dictionary based on a ridgelet transformation is used to capture prominent features by analyzing independent components extracted from a different number of electroencephalogram channels. In this study, the proposed method has been tested and validated with five different datasets for artifact detection and correction. Results show that the proposed technique is promising as it successfully extracted the exact locations of eye blinking artifacts. The accuracy of the method (automatic detection) is 89.6% which represents a better estimate than that obtained by an extreme machine learning classifier.

The segmentation of broccoli seedlings in the crops and weeds co-exist field environment is of great significance for weeding and herbicide spraying. This paper constructed a crop segmentation algorithm with a small training set for discriminating broccoli seedlings from weeds and soil. This algorithm was based on a support vector machine (SVM) combined with color-texture features. Correlation analysis and chi-square tests were used to select 6 features from the 21 color features. Gray-level co-occurrence matrix (GLCM) was used to extract 5 texture features. And each parameter of GLCM had been assessed and optimized by the chi-square test. Linear Discriminant Analysis (LDA) was used to decompose the original dataset in a set of 3 successive orthogonal components. This method selected features more reasonable and gained higher plant segmentation accuracy. When the training sample is greater than 50, the accuracy of the test set could reach 90%. The coefficient of determination (R2) between the ground truth broccoli seedling area and the segmentation broccoli area was 0.91, and the root-mean-square error (σ) was 0.10. Results demonstrated that the color-texture features were able to effectively segment broccoli seedlings even when there was a significant amount of weeds.

In recent years, pattern recognition technologies for distributed optical fiber vibration sensing have attracted more and more attention, aiming to intelligently recognize vibration events along with the optical fiber. Firstly, distributed optical fiber sensors for vibration detection are introduced. Secondly, this paper presents the state of the art of pattern recognition models used in distributed optical fiber vibration sensing systems. The feature extraction method, the model structure, and the processing performance are reported. As the results of the comparison, the support vector machine is a small sample learning method with a solid theoretical foundation and it has excellent generalization ability. The artificial neural network is suitable for massive data learning and multi-classification problems. Also, deep learning can learn more features information by a deep nonlinear network structure in an automated way, and thus has better accuracy and robustness. Furthermore, different applications of pattern recognition for distributed optical fiber vibration sensing are provided, including perimeter security, pipeline monitoring, and railway safety monitoring. Finally, the prospects of pattern recognition for distributed optical fiber vibration sensing are discussed. [ABSTRACT FROM AUTHOR]

Our previous studies demonstrated that it is possible to perform the classification of both simulated pressed and actual vocally fatigued voice productions versus vocally healthy productions through the pattern recognition of sEMG signals obtained from subjects' anterior neck. In these studies, the commonly accepted Vocal Fatigue Index factor 1 (VFI-1) was used for the ground-truth labeling of normal versus vocally fatigued voice productions. Through recent experiments, other factors with potential effects on classification were also studied, such as sEMG signal normalization, and data imbalance—i.e., the large difference between the number of vocally healthy subjects and of those with vocal fatigue. Therefore, in this paper, we present a much improved classification method derived from an extensive study of the effects of such extrinsic factors on the classification of vocal fatigue. The study was performed on a large number of sEMG signals from 88 vocally healthy and fatigued subjects including student teachers and teachers and it led to important conclusions on how to optimize a machine learning approach for the early detection of vocal fatigue. [ABSTRACT FROM AUTHOR]

B-cell epitope will be recognized and attached to the surface of receptors in B-lymphocytes to trigger immune response, thus are the vital elements in the field of epitope-based vaccine design, antibody production and therapeutic development. However, the experimental approaches in mapping epitopes are time consuming and costly. Computational prediction could offer an unbiased preliminary selection to reduce the number of epitopes for experimental validation. The deposited B-cell epitopes in the databases are those with experimentally determined positive/negative peptides and some are ambiguous resulted from different experimental methods. Prior to the development of B-cell epitope prediction module, the available dataset need to be handled with care. In this work, we first pre-processed the B-cell epitope dataset prior to B-cell epitopes prediction based on pattern recognition using support vector machine (SVM). By using only the absolute epitopes and non-epitopes, the datasets were classified into five categories of pathogen and worked on the 6-mers peptide sequences. The pre-processing of the datasets have improved the B-cell epitope prediction performance up to 99.1 % accuracy and showed significant improvement in cross validation results. It could be useful when incorporated with physicochemical propensity ranking in the future for the development of B-cell epitope prediction module. [ABSTRACT FROM AUTHOR]