Search

A patent has been issued to Change Healthcare Holdings LLC for systems and methods of using machine learning for fee risk estimations. The patent describes how machine learning can be used to predict payback forecast data for prescription data, specifically focusing on direct and indirect remuneration (DIR) fees charged to retail pharmacies. The invention aims to provide real-time visibility into DIR fee application and the ability to implement mitigation tactics to reduce these fees. The patent outlines various embodiments of the invention, including computer-implemented methods and apparatuses. [Extracted from the article]

Non-parallel hyperplane classifiers have attracted many attention due to their wider applicability than parallel hyperplane classifiers, and it accelerates the training speed through separately training of each hyperplane. However, it does not consider the correlation relationship among the non-parallel hyperplanes. In addition, since these non-parallel hyperplanes are built on the same training data, there may exist correlation among them due to redundancy of the data. In this paper, we investigate the decorrelation problem of non-parallel hyperplane classifiers. We integrate non-parallel hyperplanes into a unified model and explore this relationship through a joint classifier learning approach. Taking the twin support vector machine as an example, a novel decorrelation regularization term is added into the joint problem. Additionally, an effective alternating optimization algorithm has been introduced to address this nonconvex problem. To evaluate the proposed method, a series of experiments are conducted on binary and multi-class classification datasets from the benchmark database repository. Experimental results compared to several parallel and non-parallel hyperplane based classifiers demonstrate the effectiveness of the proposed method. • A unified non-parallel SVM with decorrelation TWJCL for multi-class classification is proposed. • Compared to JCL, TWJCL achieves decorrelation in each binary classification. • Experiments show TWJCL has low correlation coefficient and good classification performance. [ABSTRACT FROM AUTHOR]

Researchers from the School of Computer Science and Engineering have conducted a study on the early prediction of ovarian cancer using machine learning techniques and explainable artificial intelligence (XAI) methodologies. The study aimed to evaluate the effectiveness of various prediction methodologies, including support vector machines and ensemble learning techniques. The researchers collected a dataset of 349 patients with known ovarian cancer status and applied preprocessing techniques to enhance the input data. The results showed promising accuracy rates, and the study contributes to the field of oncology and women's health by offering a new approach to the early diagnosis of ovarian cancer. [Extracted from the article]

A recent study conducted by researchers at the University of Szeged in Hungary aimed to analyze the association between endometrium development, hormone levels, embryo quality, clinical pregnancy, anamnestic parameters, and body mass index (BMI) in women undergoing in vitro fertilization (IVF) treatment. The study included 537 participants divided into four BMI-based groups. The results showed that there was no convincing correlation between endometrial thickness development and BMI. However, FSH and LH levels exhibited a surprising decreasing trend with increasing BMI, suggesting a role of nutritional status in reproductive capability. The study also used a Support Vector Machine (SVM) model to predict potential pregnancies based on medical data, achieving an average accuracy of 61.71%. Further optimization is needed to confidently predict the outcome of embryo transfer. [Extracted from the article]

A study conducted at COMSATS University Islamabad explores the use of support vector machines (SVM) and exponentially weighted moving average (EWMA) control charts to improve the quality and safety of patient care in the healthcare department. The researchers used the SVM regression model to adjust risk factors associated with patients and designed EWMA control charts based on the residuals obtained through the SVM model. The study found that the resulting SVM-EWMA chart had superior shift detection capabilities and was more effective than the risk-adjusted EWMA control chart. This research provides valuable insights into using machine learning techniques to assess patient conditions in cardiac surgery. [Extracted from the article]

A research paper from the Dr. Sivanthi Aditanar College of Engineering in Tiruchendur, India, explores the analysis of Bipolar Disorder (BD) using structural magnetic resonance imaging (MRI) and a supervised learning framework. The study aims to identify specific abnormalities in brain cells that indicate BD. The researchers employed a 3D texture analysis approach, extracting texture features from the MRI data and using a supervised learning algorithm called Support Vector Machine (SVM) to classify samples as healthy or abnormal. The results showed promising outcomes, with the SVM model achieving an accuracy of 90.42%. This research provides valuable insights into the application of supervised learning and MRI data analysis for understanding BD. [Extracted from the article]

A recent study conducted by the Indian Institute of Technology (IIT) Hyderabad addresses the need for novel drug therapies to combat colorectal cancer (CRC). The researchers utilized the pharmacological profiles of anticancer drugs from the Genomics of Drug Sensitivity in Cancer (GDSC) database and developed QSAR models using the Support Vector Machine (SVM) algorithm to predict alternative and promiscuous anticancer compounds for CRC treatment. The QSAR models demonstrated robustness and achieved high correlation values. The researchers also identified two potential anti-CRC FDA-approved drugs, viomycin and diamorphine, using the QSAR models. They have incorporated these models into a user-friendly prediction Web server named 'ColoRecPred' for easy accessibility and utility. The Web server can be used for screening chemical libraries to identify potential anti-CRC drugs. [Extracted from the article]

A study conducted at Fudan University in China has developed a machine learning model based on positron emission tomography/computed tomography (PET/CT) scans to predict epidermal growth factor receptor (EGFR) mutations in non-small cell lung cancer (NSCLC) patients. The model was created using the least absolute shrinkage and selection operator logistic regression (LLR) algorithm and support vector machine (SVM) classifier. The study found that combining radiomics features with clinical features improved the predictive efficacy of the models. The researchers concluded that models that incorporate clinical features are more clinically valuable. [Extracted from the article]

Researchers from the First Affiliated Hospital of Shandong First Medical University in China have developed a stacking ensemble prediction model for hyperuricemia (HUA), a condition characterized by high levels of uric acid in the blood. The model, which combines three individual models using machine learning techniques, outperformed the individual models in predicting HUA. The researchers also identified several risk factors for HUA, including being female, younger, and having higher levels of uric acid, body mass index, g-glutamyl transpeptidase, total protein, triglycerides, creatinine, and fasting blood glucose. The model's performance was validated in a separate cohort of subjects. [Extracted from the article]

A recent study conducted in Telangana, India, explores the use of self-organizing maps and vulnerability data analysis to verify symptoms of fetal brain tumor glioblastoma. Glioblastoma is a disease caused by abnormal cells in the brain, which can be detected using MRI brain imaging. If left untreated, glioblastoma can be fatal, so early diagnosis is crucial. The study proposes a method that achieves a high accuracy rate of 98.12% in diagnosing glioblastoma, outperforming other methods such as genetic algorithms and support vector machines. This research has the potential to improve the diagnosis and treatment of brain cancer in both children and adults. [Extracted from the article]

A recent report from Aalto University in Espoo, Finland discusses the use of pre-trained models for the detection and severity level classification of dysarthria from speech. The study found that the features derived from these models outperformed three baseline features commonly used in acoustic analysis. Specifically, the HuBERT features showed the best performance, with absolute accuracy improvements ranging from 1.33% to 2.86% in the detection problem and 6.54% to 10.46% in the severity level classification problem. This research provides valuable insights into the potential of machine learning in diagnosing and treating dysarthria. [Extracted from the article]

According to a preprint abstract, researchers have developed a new approach called the bio support vector machine (SVM) to enhance vaccine development. The immune system's primary role is to identify foreign contaminants, and this process involves the interaction of various components, including immunogens, antibodies, and sensitized lymphocytes. Immunogens have surface structures called epitopes, which allow the immune system to distinguish between self and foreign entities. The bio SVM method achieved a prediction accuracy of 90.31% in 10-fold cross-validation, outperforming previous algorithms. However, it is important to note that this research has not yet undergone peer review. [Extracted from the article]

A new study conducted by researchers from the Fifth Affiliated Hospital of Wenzhou Medical University focuses on the development and validation of a machine learning-based fusion model to predict Ki-67 expression levels in patients with head and neck squamous cell carcinoma (HNSCC) using multiparametric magnetic resonance imaging (MRI). The study involved 351 patients with HNSCC and utilized seven machine learning classifiers to train the model. The support vector machine (SVM) classifier showed the best performance, achieving an average area under the curve (AUC) of 0.851 in the validation cohorts. The fusion model incorporating SVM-based radiomics scores with clinical factors demonstrated promising predictive performance and potential for prognosis evaluation and clinical decision-making. [Extracted from the article]

A recent study conducted by researchers from Gifu University Graduate School of Medicine in Japan explored the use of polygenic scores and machine learning techniques to diagnose panic disorder. The study found that combining multiple polygenic scores for psychiatric disorders improved the accuracy of diagnosis. The support vector machine classifier exhibited the highest accuracy among the five classifiers tested. However, the overall accuracy of diagnosing panic disorder based solely on polygenic score combinations was found to be modest. [Extracted from the article]

A preprint abstract from Heart Disease Weekly discusses the use of machine learning models to predict and detect heart disease. The research evaluates the effectiveness of various machine learning models, such as Support Vector Machines, K-nearest neighbors, Random Forest, and Logistic Regression, in predicting heart disease based on patient health data. The study suggests that machine learning can improve early diagnosis and individualized treatment, potentially transforming patient care and healthcare methods. The research emphasizes the potential of machine learning to revolutionize healthcare and lower the global burden of heart disease. However, it is important to note that this preprint has not yet undergone peer review. [Extracted from the article]

A new report discusses research findings on telemedicine conducted by researchers at Universitas Multimedia Nusantara. The study focuses on the positive sentiment of telemedicine applications and uses algorithms such as Naive Bayes and Support Vector Machine for sentiment analysis. The research concludes that the Support Vector Machine algorithm performs more accurately in predicting public opinion than the Naive Bayes algorithm. This information can be useful for understanding public perception of telemedicine and its potential societal impact. [Extracted from the article]

Researchers from the Department of Respiratory and Critical Care Medicine in Wuhan, China have conducted a bioinformatics study to identify biomarkers in response to Burkholderia pseudomallei (BP) infection. The study involved mRNA extraction from BP-infected mouse macrophages and the analysis of gene expression data using machine learning algorithms. The researchers found that the FZD4 gene exhibited upregulation in both macrophages and lung tissue in response to BP infection, suggesting its potential as a biomarker for BP infection. These findings contribute to a better understanding of the pathogenesis of BP infection. [Extracted from the article]

• Solve the imbalance problem in cardiovascular disease data. • A novel method named ADWGKFO is proposed to transform the unbalanced data sets. • A more targeted sampling weight determination method is proposed. • A sample testing method based on Gaussian kernel is proposed to filter new samples. • Empirical analysis shows the proposed method performs better than similar methods. In risk assessment of cardiovascular disease (CVD), the classification error caused by unbalanced data is a significant challenge, which has sparked widespread concern and research upsurge in the field of data mining. Therefore, in view of the imbalance of CVD data sets, an oversampling method via adaptive double weights and Gaussian kernel function (ADWGKFO) is proposed, which converts the unbalanced data sets into balanced data sets. Firstly, clustering algorithm is utilized to cluster minority samples, boundary samples are identified by Borderline-Synthetic Minority Over-sampling Technique (Borderline-SMOTE), K nearest neighbor and support vector machine algorithms, and the number of samples synthesized in each group is calculated based on the double weights of boundary points and majority distribution. Secondly, in order to clearly define the classification boundary, the mutual class potential of new samples in each cluster is calculated by Gaussian kernel function, and new samples are filtered according to the mutual class potential until the data set is balanced. Finally, taking the data sets from Kaggle platform as the research samples, the proposed method is empirically analyzed. In order to validate the efficacy and universality of the proposed method, this paper selects CatBoost that is a new integrated algorithm to test the effect of the ADWGKFO method, and compares it with different sampling methods and different classifiers using performance evaluation indexes such as accuracy, F1-score and area under the curve (AUC). Compared with the combinations of other methods, the accuracy, F1-score and AUC are significantly improved. It is concluded that the ADWGKFO method described in this paper can successfully improve the data quality, and increases the reliability of CVD risk assessment. [ABSTRACT FROM AUTHOR]

Researchers at GLA University in Uttar Pradesh, India, have developed a method to classify brain tumors based on magnetic resonance imaging (MRI) images using machine learning. The study used a dataset of 599 brain MRI studies and employed various optimization techniques to extract features from the images and improve classification accuracy. The proposed method achieved high accuracy in classifying different tumor regions, such as peritumoral edema, enhancing-core, and necrotic tumor core. This approach has the potential to automate and expedite the classification of brain tumors without requiring extensive human expertise. [Extracted from the article]

A report from Jawaharlal Nehru University in Delhi, India, discusses the classification of the hallmark of cancer, which refers to the biological capabilities of tumor cells that aid in understanding their development and identification during different stages of the disease. The study focuses on creating an improved model for multi-label classification using machine learning algorithms, specifically Support Vector Machines (SVM), and domain-specific embeddings to add semantics to the vector-represented text. The research aims to enhance the efficacy of classification methods and understand label correlation through collaboration with medical domain experts. The study has been peer-reviewed and provides valuable insights into cancer research. [Extracted from the article]

A recent study conducted at Capital Medical University aimed to develop a model for predicting hemorrhage in patients with cerebral arteriovenous malformations (AVMs). The researchers used three datasets and extracted rupture-related features to construct an ensemble model using logistic regression, decision tree, and support vector machine models. The ensemble model showed favorable performance in predicting subsequent hemorrhage in patients with AVMs. This research provides valuable insights into the use of machine learning techniques in evaluating rupture risk in AVMs. [Extracted from the article]

A study conducted by researchers at the First Affiliated Hospital of Guangxi Medical University aimed to develop and validate an artificial intelligence radiopathological model using CT scans and stained slides to predict the pathological staging of gastric cancer. The study included 202 gastric cancer patients and utilized machine learning algorithms to construct radiomic and radiopathological models. The SVM_radiopathomics model demonstrated superior performance in distinguishing between stage I-II and stage III gastric cancer. This study highlights the feasibility of using pathological slides and CT images for research on pathological staging. [Extracted from the article]

A recent report from Ho Chi Minh City Open University discusses the use of artificial intelligence (AI) in addressing frequently asked questions about psychology. The researchers developed an AI-driven chatbot system that utilizes machine learning techniques, such as Support Vector Machines (SVM), to generate contextually relevant responses. Through experimentation, they found that SVM outperformed other classifiers in terms of accuracy, precision, recall, and F1-score. The study highlights the effectiveness of ensemble classifiers, particularly SVM, in providing accurate and valuable information to enhance mental health support. [Extracted from the article]

A recent study conducted by researchers at the University of Naples "Federico II" in Italy aimed to predict the occurrence of distant metastases in patients with non-small cell lung cancer (NSCLC) using machine learning methods and texture analysis of PET/CT images. The study evaluated 79 patients with advanced NSCLC who had undergone PET/CT scans before any therapy. The researchers used six machine learning methods and extracted texture features from the images. The best combination of features, including shape sphericity, gray level run length matrix_run length non-uniformity (GLRLM_RLNU), Total Lesion Glycolysis (TLG), Metabolic Tumor Volume (MTV), and shape compactness, along with the decision tree method, predicted the occurrence of distant metastases with an accuracy of 74.4% and an AUC of 0.63 in NSCLC patients. [Extracted from the article]

ChemImage Corporation has been issued a patent for a method of fusing sensor data for cardiac monitoring. The patent describes a system that combines image data from an image sensor with additional data from other sensors to generate a fused data set. This fused data set is then used to determine the cardiac condition of a patient. The invention aims to provide early and objective warning signs of potential heart failure. The patent includes various embodiments and claims related to the method and the devices used for cardiac monitoring. [Extracted from the article]

Researchers at Zhejiang University of Technology in China have developed an intelligent electrocardiogram (ECG) recognition method for the rapid diagnosis and evaluation of cardiovascular diseases. The method utilizes a convolutional neural network (CNN) and support vector machines (SVM) with an improved antlion algorithm (ALO) to classify ECG signals in real time. The algorithm achieved an average accuracy, sensitivity, and specificity of 99.97%, 99.97%, and 99.99%, respectively. This approach shows promise for improving the recognition performance of cardiovascular diseases compared to existing methods. [Extracted from the article]

A recent study conducted by researchers at Gachon University in South Korea explores the use of metaheuristic-based feature selection methods to improve machine learning algorithms for diagnosing sarcopenia, a condition characterized by muscular atrophy. The study used data from the 8th Korean Longitudinal Study on Aging and evaluated the performance of different algorithms, including decision trees, random forests, support vector machines, and naive bayes. The results showed that the harmony search-derived feature set trained with a support vector machine had higher accuracy and weighted F1 score compared to traditional methods. The study suggests that metaheuristic-based feature selection has the potential to advance sarcopenia diagnosis and calls for further research in this area. [Extracted from the article]

A recent study conducted at Shiraz University aimed to improve the accuracy of breast cancer diagnosis by using a feature selection algorithm based on particle swarm optimization (PSO) combined with machine learning methods. The researchers tested their algorithm on three common breast cancer datasets and found that it significantly improved accuracy while reducing the number of features needed for diagnosis. The study suggests that the proposed algorithm has the potential to enhance breast cancer diagnosis and reduce cost and time. Further information on the study can be found in the International Journal of Computational Intelligence Systems. [Extracted from the article]

A patent application titled "Machine Learning and Natural Language Processing (NLP)-based System for System-on-chip (SoC) Troubleshooting" has been made available online. The inventors propose a method and apparatus for troubleshooting integrated circuits (ICs) using natural language processing and machine learning. The system clusters troubleshooting queries into semantically similar categories, retrieves resolution data from an expert system library, and generates recommendations for users. The invention aims to alleviate the strain on customer service resources by applying artificial intelligence to troubleshooting semiconductor devices. [Extracted from the article]

Researchers from Universitas Tunas Pembangunan conducted a study on the Shopee app, an Indonesian marketplace, during the COVID-19 outbreak. They analyzed feedback from Google Play Store reviews using sentiment analysis techniques such as Support Vector Machines (SVM) and Random Forest. The results showed that the SVM model had a higher accuracy rate of 84.71% compared to the Random Forest model's accuracy rate of 82.21%. The study identified common positive and negative sentiments expressed in the reviews, which can be used for quality improvement and evaluation by the Shopee company. [Extracted from the article]

• Proposed a combination of biological properties and deep learning for cancelable ECG. • Proposed a novel cancelable ECG system using deep learning for human authentication. • Presented an efficient system satisfies all cancelable requirements with high performance. • Two different datasets PTB and ECG-ID are used to evaluate the system. Recently, electrocardiogram (ECG) signals have received a high level of attention as a physiological signal in the field of biometrics. It has presented great possibilities for its strength against counterfeit. However, the ECG feature templates are irreplaceable, and a compromised template implies a permanent loss of identity. Therefore, several studies have been introduced biometric template protection techniques such as cancelable techniques to protect the original template in case it is stolen or lost. In this research, a cancelable ECG approach is proposed to protect the ECG feature template for human authentication. In our system, we first employed some image processing techniques for preprocessing the input ECG signals. Then, a deep transfer learning approach is employed to extract the deep ECG features. Later, the proposed cancelable approach based on DNA and amino acid is applied to protect the deep feature templates. Lastly, a Support Vector Machine (SVM) is employed for authentication. Extensive experiments on two commonly used datasets coupled with comprehensive theoretical analysis demonstrate the highest accuracy of the proposed system and the strong resilience of the system to various security and privacy attacks. Results show that the proposed cancelable method meets all requirements of cancelable biometrics such as irreversibility , revocability, and unlinkability. [ABSTRACT FROM AUTHOR]

Kernel recursive least squares (KRLS) is a widely used online machine learning algorithm for time series predictions. In this article, we present the mixed-precision KRLS, producing equivalent prediction accuracy to double-precision KRLS with a higher training throughput and a lower memory footprint. The mixed-precision KRLS applies single-precision arithmetic to the computation components being not only numerically resilient but also computationally intensive. Our mixed-precision KRLS demonstrates the 1.32, 1.15, 1.29, 1.09, and $1.08\times $ training throughput improvements using 24.95%, 24.74%, 24.89%, 24.48%, and 24.20% less memory footprint without losing any prediction accuracy compared to double-precision KRLS for a 3-D nonlinear regression, a Lorenz chaotic time series, a Mackey-Glass chaotic time series, a sunspot number time series, and a sea surface temperature time series, respectively. [ABSTRACT FROM AUTHOR]

In this article, we discuss two novel sparse versions of the classical nearest-centroid classifier. The proposed sparse classifiers are based on $\ell _{1}$ and $\ell _{2}$ distance criteria, respectively, and perform simultaneous feature selection and classification, by detecting the features that are most relevant for the classification purpose. We formally prove that the training of the proposed sparse models, with both distance criteria, can be performed exactly (i.e., the globally optimal set of features is selected) at a linear computational cost. Especially, the proposed sparse classifiers are trained in $O(mn)+O(m\log k)$ operations, where $n$ is the number of samples, $m$ is the total number of features, and $k \leq m$ is the number of features to be retained in the classifier. Furthermore, the complexity of testing and classifying a new sample is simply $O(k)$ for both methods. The proposed models can be employed either as stand-alone sparse classifiers or fast feature-selection techniques for prefiltering the features to be later fed to other types of classifiers (e.g., SVMs). The experimental results show that the proposed methods are competitive in accuracy with state-of-the-art feature selection and classification techniques while having a substantially lower computational cost. [ABSTRACT FROM AUTHOR]

Kernel-based extreme learning machine (KELM), as a natural extension of ELM to kernel learning, has achieved outstanding performance in addressing various regression and classification problems. Compared with the basic ELM, KELM has a better generalization ability owing to no needs of the number of hidden nodes given beforehand and random projection mechanism. Since KELM is derived under the minimum mean square error (MMSE) criterion for the Gaussian assumption of noise, its performance may deteriorate under the non-Gaussian cases, seriously. To improve the robustness of KELM, this article proposes a mixture correntropy-based KELM (MC-KELM), which adopts the recently proposed maximum mixture correntropy criterion as the optimization criterion, instead of using the MMSE criterion. In addition, an online sequential version of MC-KELM (MCOS-KELM) is developed to deal with the case that the data arrive sequentially (one-by-one or chunk-by-chunk). Experimental results on regression and classification data sets are reported to validate the performance superiorities of the new methods. [ABSTRACT FROM AUTHOR]

The K-means algorithm is among the most commonly used data clustering methods. However, the regular K-means can only be applied in the input space, and it is applicable when clusters are linearly separable. The kernel K-means, which extends K-means into the kernel space, is able to capture nonlinear structures and identify arbitrarily shaped clusters. However, kernel methods often operate on the kernel matrix of the data, which scale poorly with the size of the matrix, or suffer from the high clustering cost due to the repetitive calculations of kernel values. Another issue is that algorithms access the data only through evaluation of K (x i , x j) , which limits many processes that can be done on data through the clustering task. This paper proposes a method to combine the advantages of the linear and nonlinear approaches by using derived corresponding approximate finite-dimensional feature maps based on spectral analysis. Applying approximate finite-dimensional feature maps have been discussed before only in the context of Support Vector Machines (SVM) problems. We suggest using this method in the kernel K-means context as it does not require storing a huge kernel matrix in memory, calculates cluster centers more efficiently, and accesses the data explicitly in the feature space; thus taking advantage of K-means extensions in that space. We demonstrate that our Explicit Kernel Minkowski Weighted K-means (Explicit KMWK-means) method is able to achieve high accuracy in terms of cluster recovery in the new space by applying additional Minkowski exponent and feature weights. The proposed method is evaluated by four benchmark data sets, and its performance is compared with the commonly used kernel clustering approaches. Experiments show the proposed method consistently achieves superior clustering performances while reducing the memory consumption. [ABSTRACT FROM AUTHOR]

Purpose: Up to date development in sentiment analysis has resulted in a symbolic growth in the volume of study, especially on more subjective text types, namely, product or movie reviews. The key difference between these texts with news articles is that their target is defined and unique across the text. Hence, the reviews on newspaper articles can deal with three subtasks: correctly spotting the target, splitting the good and bad content from the reviews on the concerned target and evaluating different opinions provided in a detailed manner. On defining these tasks, this paper aims to implement a new sentiment analysis model for article reviews from the newspaper. Design/methodology/approach: Here, tweets from various newspaper articles are taken and the sentiment analysis process is done with pre-processing, semantic word extraction, feature extraction and classification. Initially, the pre-processing phase is performed, in which different steps such as stop word removal, stemming, blank space removal are carried out and it results in producing the keywords that speak about positive, negative or neutral. Further, semantic words (similar) are extracted from the available dictionary by matching the keywords. Next, the feature extraction is done for the extracted keywords and semantic words using holoentropy to attain information statistics, which results in the attainment of maximum related information. Here, two categories of holoentropy features are extracted: joint holoentropy and cross holoentropy. These extracted features of entire keywords are finally subjected to a hybrid classifier, which merges the beneficial concepts of neural network (NN), and deep belief network (DBN). For improving the performance of sentiment classification, modification is done by inducing the idea of a modified rider optimization algorithm (ROA), so-called new steering updated ROA (NSU-ROA) into NN and DBN for weight update. Hence, the average of both improved classifiers will provide the classified sentiment as positive, negative or neutral from the reviews of newspaper articles effectively. Findings: Three data sets were considered for experimentation. The results have shown that the developed NSU-ROA + DBN + NN attained high accuracy, which was 2.6% superior to particle swarm optimization, 3% superior to FireFly, 3.8% superior to grey wolf optimization, 5.5% superior to whale optimization algorithm and 3.2% superior to ROA-based DBN + NN from data set 1. The classification analysis has shown that the accuracy of the proposed NSU − DBN + NN was 3.4% enhanced than DBN + NN, 25% enhanced than DBN and 28.5% enhanced than NN and 32.3% enhanced than support vector machine from data set 2. Thus, the effective performance of the proposed NSU − ROA + DBN + NN on sentiment analysis of newspaper articles has been proved. Originality/value: This paper adopts the latest optimization algorithm called the NSU-ROA to effectively recognize the sentiments of the newspapers with NN and DBN. This is the first work that uses NSU-ROA-based optimization for accurate identification of sentiments from newspaper articles. [ABSTRACT FROM AUTHOR]

Purpose: The current challenge for forecasting smart meters electricity consumption lies in the uncertainty and volatility of load profiles. Moreover, forecasting the electricity consumption for all the meters requires an enormous amount of time. Most papers tend to avoid such complexity by forecasting the electricity consumption at an aggregated level. This paper aims to forecast the electricity consumption for all smart meters at an individual level. This paper, for the first time, takes into account the computational time for training and forecasting the electricity consumption of all the meters. Design/methodology/approach: A novel hybrid autoregressive-statistical equations idea model with the help of clustering and whale optimization algorithm (ARSEI-WOA) is proposed in this paper to forecast the electricity consumption of all the meters with best performance in terms of computational time and prediction accuracy. Findings: The proposed model was tested using realistic Irish smart meters energy data and its performance was compared with nine regression methods including: autoregressive integrated moving average, partial least squares regression, conditional inference tree, M5 rule-based model, k-nearest neighbor, multilayer perceptron, RandomForest, RPART and support vector regression. Results have proved that ARSEI-WOA is an efficient model that is able to achieve an accurate prediction with low computational time. Originality/value: This paper presents a new hybrid ARSEI model to perform smart meters load forecasting at an individual level instead of an aggregated one. With the help of clustering technique, similar meters are grouped into a few clusters from which reduce the computational time of the training and forecasting process. In addition, WOA improves the prediction accuracy of each meter by finding an optimal factor between the average electricity consumption values of each cluster and the electricity consumption values for each one of its meters. [ABSTRACT FROM AUTHOR]

• A novel and safe double screening rule is proposed for accelerating ENSVM. • A more efficient region is constructed to improve the efficiency of our DSR. • Our DSR can simultaneously screen out the inactive features and samples. • Our DSR guarantees that the identified feature and sample must be inactive. Elastic net support vector machine (ENSVM) is an effective and popular classification technique. It has been widely used in many practical applications. However, solving large-scale problems still remains challenging. Inspired by its sparsity, a safe double screening rule (DSR) is proposed for accelerating ENSVM. Its main idea is to reduce the scale of the model by discarding the inactive features and samples simultaneously. In this way, the computational speed can be accelerated. Another superiority of DSR is safety, i.e., the discarded features and samples must be inactive. Its key strategy is to estimate the region containing optimal solution based on the feasible solution and duality gap. Thus, the DSR can be embedded into the process of solving the model until the algorithm converges. In addition, the safe keeping rule is constructed to identify the active features and samples. So, the DSR only needs to work on the remaining set after safe keeping. In this way, the screening process of DSR can be accelerated. Moreover, the Stochastic Dual Coordinate Ascent (SDCA) method is employed as an efficient solver. Numerical experiments on an artificial dataset and eighteen benchmark datasets demonstrate the feasibility and validity of our proposed method. [ABSTRACT FROM AUTHOR]

The main computational cost of building a support vector machine (SVM) training model lies in tuning the hyperparameters, including the kernel parameters and penalty constant C. This paper introduces a new kernel, the random radial basis function (RRBF) kernel, which all kernel parameters can be assigned to randomly. The key idea of the RRBF is to extend a one-dimensional parameter to d -dimensional parameters by simple modification of the traditional RBF kernel. We prove the universal approximation capability of a SVM with the RRBF kernel, proposing a simple model selection algorithm. The experiments on benchmark datasets show that SVM with the RRBF kernel clearly outperforms the traditional RBF kernel and other popular kernels, and the results are quite insensitive to C. Compared with other kernels, a SVM with the RRBF kernel is not sensitive to the penalty constant C , and it can be tuned in a wide range. Additionally, this property also enables a SVM to find the hyperparameters quickly. A simulation of parameter sensitivity study also show that a SVM is more stable w.r.t. to the different choices of kernel parameters. [ABSTRACT FROM AUTHOR]

• RPSVM-2V satisfies both principles for incomplete- and complete-view data. • We develop another two efficient MVL extensions, i.e., RSVM-2K and RMKL. • The generalization error bounds of our proposed models are analyzed. • The extensive experiments confirm the effectiveness of our proposed models. • Spectral analysis verifies that reduced kernel can retain most information. Multi-view learning (MVL) is a promising direction and most MVL methods work under the assumption that data are complete in all views. However, this assumption is often violated in practice due to the difficulties of high cost, equipment failure, and so on. Besides, the amount of data with missing views is particularly huge. Therefore, it is challenging yet valuable to fully leverage the large-scale incomplete-view data. Enlightened by the reduced support vector machine (RSVM) and multi-view privileged support vector machine (PSVM-2V), this paper proposes an efficient kernel method called reduced PSVM-2V (RPSVM-2V). It can not only provide a novel solution to process incomplete-view data, but also can be adjusted to address large-scale complete-view learning problem efficiently. In addition, the idea of replacing the full kernel with a smaller rectangular reduced kernel is extended to develop another two MVL methods, i.e., reduced SVM-2K (RSVM-2K) and reduced multiple kernel learning method (RMKL). Furthermore, we analyze the generalization error bounds of RPSVM-2V and two extensions by using Rademacher complexity. The comprehensive experiments demonstrate that our proposed models can achieve comparable performance with less time and memory cost. The spectral analysis has further verified the effectiveness of the reduced kernel used in our models. [ABSTRACT FROM AUTHOR]

Sign language is the main type of communication of the deaf community. However, most people do not know this language, which causes communication problems for many people. Many technological solutions have been proposed to overcome this issue. Some use the concept of wearable devices, but gesture recognition in a video sequence is a cheaper and less intrusive solution. In this work, we address the problem of gesture recognition in video. To do so, we employ a two-step method with feature space mapping and classification. First, the body parts of each subject in a video are segmented through a deep neural network architecture. Then, we use Gait Energy Image to encode the motion of the body parts in a compact feature space. Small datasets are usually a problem in this type of application, leading to sparse representation in the feature space. To contour this problem, we evaluate SMOTE as a data augmentation technique in the feature space and classical dimensionality reduction techniques. We evaluate our method on three challenging Brazilian sign language (Libras) datasets, CEFET/RJ-Libras, MINDS-Libras, and LIBRAS-UFOP, achieving global accuracies of 85.40±3.13%, 84.66±1.78%, and 64.91±3.79%, respectively, with singular value decomposition and support vector machine. [ABSTRACT FROM AUTHOR]

Suitability of shallow (one-hidden-layer) networks with translation-invariant kernel units for function approximation and classification tasks is investigated. It is shown that a critical property influencing the capabilities of kernel networks is how the Fourier transforms of kernels converge to zero. The Fourier transforms of kernels suitable for multivariable approximation can have negative values but must be almost everywhere nonzero. In contrast, the Fourier transforms of kernels suitable for maximal margin classification must be everywhere nonnegative but can have large sets where they are equal to zero (e.g., they can be compactly supported). The behavior of the Fourier transforms of multivariable kernels is analyzed using the Hankel transform. The general results are illustrated by examples of both univariable and multivariable kernels (such as Gaussian, Laplace, rectangle, sinc, and cut power kernels). [ABSTRACT FROM AUTHOR]

In this article, an improved nonparallel support vector machine (INPSVM) is proposed for pattern classification. INPSVM inherits almost all advantages of nonparallel support vector machine (NPSVM), i.e., the kernel trick can be directly applied for the nonlinear case and the matrix inversion is avoided. These are completely different from the twin support vector machine (TSVM). Moreover, the INPSVM classifier has some incomparable advantages over TSVM and NPSVM. First, it can effectively eliminate the negative effect of noise, especially feature noise around the decision boundary. Second, the novel classifier has higher classification accuracy for both linear and nonlinear data sets compared with the other algorithms. Finally, a large number of experiments show that INPSVM is superior to other algorithms in efficiency, accuracy, and robustness. [ABSTRACT FROM AUTHOR]

Fractional calculus and entropy are two essential mathematical tools, and their conceptions support a productive interplay in the study of system dynamics and machine learning. In this article, we modify the fractional entropy and propose the cumulative permuted fractional entropy (CPFE). A theoretical analysis is provided to prove that CPFE not only meets the basic properties of the Shannon entropy but also has unique characteristics of its own. We apply it to typical discrete distributions, simulated data, and real-world data to prove its efficiency in the application. This article demonstrates that CPFE can measure the complexity and uncertainty of complex systems so that it can perform reliable and accurate classification. Finally, we introduce CPFE to support vector machines (SVMs) and get CPFE-SVM. The CPFE can be used to process data to make the irregular data linearly separable. Compared with the other five state-of-the-art algorithms, CPFE-SVM has significantly higher accuracy and less computational burden. Therefore, the CPFE-SVM is especially suitable for the classification of irregular large-scale data sets. Also, it is insensitive to noise. Implications of the results and future research directions are also presented. [ABSTRACT FROM AUTHOR]

The classification in imbalanced datasets is one of the main problems for machine learning techniques. Support vector machine (SVM) is biased to the majority class samples, and the minority class samples may incorrectly be considered as noise. Therefore, SVM has poor predictive accuracy for imbalanced datasets and generates inaccurate classification models. Existing class imbalance learning (CIL) techniques can make SVM less sensitive to class imbalance, but these methods suffer from issues related to noise and outliers. Moreover, despite the solid theoretical basis and good classification performance, SVM is not appropriate for the classification of large-scale datasets because the training complexity of SVM is closely related to the dataset size. Class imbalance learning (CIL) using Fuzzy adaptive resonance theory (ART) and intuitionistic fuzzy twin SVM (CIL-FART-IFTSVM), which can be applied to address the class imbalance issue in the presence of noise and outliers and large scale datasets, is proposed to overcome these substantial difficulties. In this method, we modify the distribution of the datasets using fuzzy adaptive resonance theory (Fuzzy ART) as a clustering method to overcome the imbalance problem. Then, after data reduction, IFTSVM is utilized to find excellent non-parallel hyperplanes in the generated data points. Finally, a coordinate descent system with shrinking by an active set is applied to reduce the computational complexity. Forty-five imbalanced datasets are considered to validate the performance of the proposed CIL-FART-IFTSVM method. The Friedman test and the bootstrap technique with 95 % confidence intervals are applied to quantify the results statistically. The experimental results indicate that the method proposed in this paper has a better performance compared with other methods, and the training time is significantly better than that of other classifiers for large-scale datasets. [ABSTRACT FROM AUTHOR]

Real-world database applications possess massive data collections with different data formats such as continuous, discrete or nominal. Continuous data makes the analysis process more complex as the data can take any value within a particular range and so granule mining has been used recently with techniques such as neighbourhood rough sets to discover granules in continuous data. This approach is yet to address the granule resolution design concepts, so this paper presents a novel method, Hierarchical Clustering-based Granulation (HCluG) to improve the granule identification of continuous data by combining hierarchical clustering with neighborhood rough sets, reducing user involvement in granule resolution parameters tuning and introducing an automated granule discovery method. HCluG comprises a feature selection method to evaluate the quality of the granules generated with the proposed granule approximations. Experimental results show HCluG reduces the number of selected features while improving the classification performance. HCluG outperforms the rough sets-based feature selection baselines when used with K-Nearest Neighbours and Radial Basis Function Support Vector Machine on average and performs better on average than using the complete feature set. This method can be used in data analysis to achieve high classification performance with a fewer number of features and less user involvement. [ABSTRACT FROM AUTHOR]

• A novel instance selection method referred to as BPLSH is proposed. • Numerous experiments are conducted to demonstrate the superiority of BPLSH. • The results show that BPLSH is fast in handling large datasets. • BPLSH strikes a good balance between preservation rate and classification error. Support vector machines (SVMs) are powerful classifiers that have high computational complexity in the training phase, which can limit their applicability to large datasets. An effective approach to address this limitation is to select a small subset of the most representative training samples such that desirable results can be obtained. In this study, a novel instance selection method called border point extraction based on locality-sensitive hashing (BPLSH) is designed. BPLSH preserves instances that are near the decision boundaries and eliminates nonessential ones. The performance of BPLSH is benchmarked against four approaches on different classification problems. The experimental results indicate that BPLSH outperforms the other methods in terms of classification accuracy, preservation rate, and execution time. The source code of BPLSH can be found in https://github.com/mohaslani/BPLSH. [ABSTRACT FROM AUTHOR]

Arrhythmia constitute a common clinical problem in cardiology. The diagnosis is often made using electrocardiographic (ECG) signals but manual ECG interpretation by experts is expensive and time-consuming. In this work, we developed and validated an arrhythmia classification model based on handcrafted features, which was more computationally efficient than traditional deep learning models. The classification model comprised (i) a specific feature extraction function based on the homeomorphically irreducible tree (HIT) graph pattern, (ii) multilevel feature generation based on maximum absolute pooling, (iii) Chi2 feature selector, and (iv) standard support vector machine classifier. We trained and validated the model on a large dataset comprising 12-leads ECGs acquired from more than 10,000 subjects. Performance metrics were reported for seven- (Case 1) and four-class (Case 2) arrhythmia diagnosis. High classification accuracy rates of 92.95% and 97.18% were attained for Case 1 and Case 2, respectively, that were comparable with those of deep learning on the same ECG dataset. The model achieved excellent classification results at low computational cost, which underscores the potential for real world application of the proposed HIT-based ECG classification model. [ABSTRACT FROM AUTHOR]

This paper presents a novel hardware architecture of the Tensorial Support Vector Machine (TSVM) based on Shallow Neural Networks (NN) for the Single Value Decomposition (SVD) computation. The proposed NN achieves a comparable Mean Squared Error and Cosine Similarity to the widely used one-sided Jacobi algorithm. When implemented on an FPGA, the NN offers $324\times $ faster computations than the one-sided Jacobi with reductions up to 58% and 67% in terms of hardware resources and power consumption respectively. When validated on a touch modality classification problem, the NN-based TSVM implementation has achieved a real-time operation while consuming about 88% less energy per classification than the Jacobi-based TSVM with an accuracy loss of at most 3%. Such results offer the ability to deploy intelligence on resource-limited platform for energy-constrained applications. [ABSTRACT FROM AUTHOR]

The aim of unsupervised domain adaptation is to leverage the knowledge in a labeled (source) domain to improve a model’s learning performance with an unlabeled (target) domain—the basic strategy being to mitigate the effects of discrepancies between the two distributions. Most existing algorithms can only handle unsupervised closed set domain adaptation (UCSDA), i.e., where the source and target domains are assumed to share the same label set. In this article, we target a more challenging but realistic setting: unsupervised open set domain adaptation (UOSDA), where the target domain has unknown classes that are not found in the source domain. This is the first study to provide learning bound for open set domain adaptation, which we do by theoretically investigating the risk of the target classifier on unknown classes. The proposed learning bound has a special term, namely, open set difference, which reflects the risk of the target classifier on unknown classes. Furthermore, we present a novel and theoretically guided unsupervised algorithm for open set domain adaptation, called distribution alignment with open difference (DAOD), which is based on regularizing this open set difference bound. The experiments on several benchmark data sets show the superior performance of the proposed UOSDA method compared with the state-of-the-art methods in the literature. [ABSTRACT FROM AUTHOR]