Support Vector Machine Training Research Articles

Foreground-Back ground Segmentation using K-Means Clustering Algorithm and Support Vector Machine

Foreground-background image segmentation has been an important research problem. It is one of the main tasks in the field of computer vision whose purpose is detecting variations in image sequences. It provides candidate objects for further attentional selection, e.g., in video surveillance. In this paper, we introduce an automatic and efficient Foreground-background segmentation. The proposed method starts with the detection of visually salient image regions with a saliency map that uses Fourier transform and a Gaussian filter. Then, each point in the maps classifies as salient or non-salient using a binary threshold. Next, a hole filling operator is applied for filling holes in the achieved image, and the area-opening method is used for removing small objects from the image. For better separation of the foreground and background, dilation and erosion operators are also used. Erosion and dilation operators are applied for shrinking and expanding the achieved region. Afterward, the foreground and background samples are achieved. Because the number of these data is large, K-means clustering is used as a sampling technique to restrict computational efforts in the region of interest. K cluster centers for each region are set for training of Support Vector Machine (SVM). SVM, as a powerful binary classifier, is used to segment the interest area from the background. The proposed method is applied on a benchmark dataset consisting of 1000 images and experimental results demonstrate the supremacy of the proposed method to some other foreground-background segmentation methods in terms of ER, VI, GCE, and PRI.

Enhanced annotation of CD45RA to distinguish T cell subsets in single-cell RNA-seq via machine learning.

T cell heterogeneity presents a challenge for accurate cell identification, understanding their inherent plasticity, and characterizing their critical role in adaptive immunity. Immunologists have traditionally employed techniques such as flow cytometry to identify T cell subtypes based on a well-established set of surface protein markers. With the advent of single-cell RNA sequencing (scRNA-seq), researchers can now investigate the gene expression profiles of these surface proteins at the single-cell level. The insights gleaned from these profiles offer valuable clues and a deeper understanding of cell identity. However, CD45RA, the isoform of CD45 which distinguishes between naive/central memory T cells and effector memory/effector memory cells re-expressing CD45RA T cells, cannot be well profiled by scRNA-seq due to the difficulty in mapping short reads to genes. In order to facilitate cell-type annotation in T cell scRNA-seq analysis, we employed machine learning and trained a classifier on single-cell mRNA count data annotated with known CD45RA antibody levels provided by cellular indexing of transcriptomes and epitopes sequencing data. Among all the algorithms we tested, the trained support vector machine with a radial basis function kernel with optimized hyperparameters achieved a 99.96% accuracy on an unseen dataset. The multilayer perceptron classifier, the second most predictive method overall, also achieved a decent accuracy of 99.74%. Our simple yet robust machine learning approach provides a valid inference on the CD45RA level, assisting the cell identity annotation and further exploring the heterogeneity within human T cells. Based on the overall performance, we chose the support vector machine with a radial basis function kernel as the model implemented in our Python package scCD45RA. The resultant package scCD45RA can be found at https://github.com/BrubakerLab/ScCD45RA and can be installed from the Python Package Index (PyPI) using the command "pip install sccd45ra."

Development of Algorithm for Person Re-Identification Using Extended Openface Method

Deep learning has risen in popularity as a face recognition technology in recent years. Facenet, a deep convolutional neural network (DCNN) developed by Google, recognizes faces with 128 bytes per face. It also claims to have achieved 99.96% on the reputed Labelled Faces in the Wild (LFW) dataset. However, the accuracy and validation rate of Facenet drops down eventually, there is a gradual decrease in the resolution of the images. This research paper aims at developing a new facial recognition system that can produce a higher accuracy rate and validation rate on low-resolution face images. The proposed system Extended Openface performs facial recognition by using three different features i) facial landmark ii) head pose iii) eye gaze. It extracts facial landmark detection using Scattered Gated Expert Network Constrained Local Model (SGEN-CLM). It also detects the head pose and eye gaze using Enhanced Constrained Local Neural field (ECLNF). Extended openface employs a simple Support Vector Machine (SVM) for training and testing the face images. The system’s performance is assessed on low-resolution datasets like LFW, Indian Movie Face Database (IMFDB). The results demonstrated that Extended Openface has a better accuracy rate (12%) and validation rate (22%) than Facenet on low-resolution images.

Evaluation of four machine learning models for signal detection.

Logistic regression-based signal detection algorithms have benefits over disproportionality analysis due to their ability to handle potential confounders and masking factors. Feature exploration and developing alternative machine learning algorithms can further strengthen signal detection. Our objective was to compare the signal detection performance of logistic regression, gradient-boosted trees, random forest and support vector machine models utilizing Food and Drug Administration adverse event reporting system data. Cross-sectional study. The quarterly data extract files from 1 October 2017 through 31 December 2020 were downloaded. Due to an imbalanced outcome, two training sets were used: one stratified on the outcome variable and another using Synthetic Minority Oversampling Technique (SMOTE). A crude model and a model with tuned hyperparameters were developed for each algorithm. Model performance was compared against a reference set using accuracy, precision, F1 score, recall, the receiver operating characteristic area under the curve (ROCAUC), and the precision-recall curve area under the curve (PRCAUC). Models trained on the balanced training set had higher accuracy, F1 score and recall compared to models trained on the SMOTE training set. When using the balanced training set, logistic regression, gradient-boosted trees, random forest and support vector machine models obtained similar performance evaluation metrics. The gradient-boosted trees hyperparameter tuned model had the highest ROCAUC (0.646) and the random forest crude model had the highest PRCAUC (0.839) when using the balanced training set. All models trained on the balanced training set performed similarly. Logistic regression models had higher accuracy, precision and recall. Logistic regression, random forest and gradient-boosted trees hyperparameter tuned models had a PRCAUC ⩾ 0.8. All models had an ROCAUC ⩾ 0.5. Including both disproportionality analysis results and additional case report information in models resulted in higher performance evaluation metrics than disproportionality analysis alone.

A 96.2-nJ/class Neural Signal Processor With Adaptable Intelligence for Seizure Prediction

This work presents the world’s first neural signal processor for seizure prediction, which includes a preprocessing unit, a feature extractor, a reconfigurable support vector machine (SVM) kernel, and a postprocessing unit. Seizure prediction performance is enhanced by on-chip training for model adaptation. Design optimization is applied across the layers of abstraction to minimize the area and energy. The area of the feature extractor is reduced by 28% with an approximated energy operator (AEO). The proposed scaling-based Newton–Raphson (NR) divider reduces the required number of iterations for division by 62.5%. For alternating direction method of multipliers (ADMM)-based SVM training, the computational complexity is reduced by up to 99.9% through pointer-based matrix multiplication. By leveraging the LDL decomposition, 80% multiplications for updating weights are saved. The chip achieves a seizure prediction performance with a 92.0% sensitivity and a 0.57/h false alarm rate (FAR). The training latency is 8.44 ms with a power dissipation of 2.31 mW at 6.05 MHz. Compared with an ARM Cortex-M3 microcontroller, this work achieves a <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$124\times $ </tex-math></inline-formula> higher area efficiency and a <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$299\times $ </tex-math></inline-formula> higher energy efficiency. The chip also supports seizure detection and achieves a sensitivity of 98.6% and an FAR of 0.18/h, exceeding the state-of-the-art designs.

Retracted: Differentially Private Singular Value Decomposition for Training Support Vector Machines.

[This retracts the article DOI: 10.1155/2022/2935975.].

A support vector machine training scheme based on quantum circuits

In order to improve the training efficiency of the support vector machine, a quantum circuit training scheme based on the inner product of the quantum state for the support vector machine is proposed in this work. Firstly, on the basis of the full analysis of the computational complexity of the classical support vector machine, the kernel function which is the main factor affecting the computational complexity of the algorithm is primarily analyzed. Based on quantum mechanics and quantum computing theory, the training sample elements in the kernel function are quantized to generate the corresponding quantum states. Secondly, according to the quantum states of the training sample elements, the types and quantities of the required quantum logic gates are derived and calculated, and the quantum circuit that can generate the corresponding quantum states of the training sample elements through the evolution of the quantum initial ground states and the quantum logic gates is designed. Then, in the light of the relationship between the inner product of the quantum state and the quantum logic gate SWAP, the quantum circuit is designed to complete the exchange operation of the corresponding quantum state amplitude. The inner product of the quantum state is realized by exchanging and evolving the amplitude of the quantum state in the quantum circuit. Finally, by measuring the quantum state of the controlling qubit, the inner product solution of the kernel function is obtained, and the acceleration effect of training support vector machine is realized. The verification results show that the scheme enables the support vector machine not only to complete the correct classification, but also to operate the quantum part of the scheme on the real quantum computer . Compared with the classical algorithm, the scheme reduces the time complexity of the algorithm for the polynomial degree, greatly shortens the training time of the model, and improves the efficiency of the algorithm. The scheme has certain feasibility, effectiveness and innovation, and expands the training idea of the support vector machine.

Motor Imagery EEG Classification Based on Riemannian Sparse Optimization and Dempster-Shafer Fusion of Multi-Time-Frequency Patterns.

Motor imagery-based brain-computer interfaces (MI-BCIs) features are generally extracted from a wide fixed frequency band and time window of EEG signal. The performance suffers from individual differences in corresponding time to MI tasks. In order to solve the problem, in this study, we propose a novel method named Riemannian sparse optimization and Dempster-Shafer fusion of multi-time-frequency patterns (RSODSF) to enhance the decoding efficiency. First, we effectively combine the Riemannian geometry of the spatial covariance matrix with sparse optimization to extract more robust and distinct features. Second, the Dempster-Shafer theory is introduced and used to fuse each time window after sparse optimization of Riemannian features. Besides, the probabilistic values of the support vector machine (SVM) are obtained and transformed to effectively fuse multiple classifiers to leverage potential soft information of multiple trained SVM. The open-access BCI Competition IV dataset IIa and Competition III dataset IIIa are employed to evaluate the performance of the proposed RSODSF. It achieves higher average accuracy (89.7% and 96.8%) than state-of-the-art methods. The improvement over the common spatial patterns (SFBCSP) are respectively 9.9% and 12.4% (p < 0.01, paired t-test). These results show that our proposed RSODSF method is a promising candidate for the performance improvement of MI-BCI.

Text Classification using Incremental Learning for many classes of Support Vector Machines

This study introduces class-incremental learning (CIL). This framework improves multi-class data support vector machines (SVMs). CIL is incremental feature selection and training. Both steps update SVM classifiers as new classes are added to a system. CIL learns one binary sub-classifier and reuses classifier models for subsequent classes. Another feature selection stage follows. Testing applies the classifier to subspacerelevant vector projections. The CIL system is compatible with any binary classification approaches that are used for text analysis. According to the findings of our research, the CIL-based SVM beat the most popular batch SVM learning methods, such as divide-by-2, 1-against-1, and 1-against-rest, and trained faster. These learning methods are used to train SVMs.

Achieving Privacy-Preserving and Verifiable Support Vector Machine Training in the Cloud

With the proliferation of machine learning, the cloud server has been employed to collect massive data and train machine learning models. Several privacy-preserving machine learning schemes have been suggested recently to guarantee data and model privacy in the cloud. However, these schemes either mandate the involvement of the data owner in model training or utilize high-cost cryptographic techniques, resulting in excessive computational and communication overheads. Furthermore, none of the existing work considers the malicious behavior of the cloud server during model training. In this paper, we propose the first privacy-preserving and verifiable support vector machine training scheme by employing a two-cloud platform. Specifically, based on the homomorphic verification tag, we design a verification mechanism to enable verifiable machine learning training. Meanwhile, to improve the efficiency of model training, we combine homomorphic encryption and data perturbation to design an efficient multiplication operation for the encryption domain. A rigorous theoretical analysis demonstrates the security and reliability of our scheme. The experimental results indicate that our scheme can reduce computational and communication overheads by at least 43.94% and 99.58%, respectively, compared to state-of-the-art SVM training methods.

Research on State Detection Method of Electrical Equipment Based on Wireless Sensor Network Signal Processing

False alarms and omissions of key measurement signals may even affect the reliability of decision-making in power IoT system, lead to safety accidents and bring huge economic losses. In order to improve the reliability of system operation and the information management level of electrical equipment, it is necessary to identify and extract suddenly changed signals from massive measurement signals collected by wireless sensor networks, and to detect the working state of electrical equipment by judging the source of signals. Therefore, this article studies the state detection method of electrical equipment based on wireless sensor network signal processing. In the second chapter, a cluster splitting and merging method is designed to solve the problem that the existing detection methods tend to ignore the imbalance of cluster size. In the third chapter, according to the data characteristics of measurement signals collected by wireless sensor networks, a similarity measurement criterion for composite time series of measurement signals is proposed, and the corresponding distance matrix is generated based on this criterion. In the fourth chapter, wavelet decomposition is used to decompose the initial measurement signals collected by wireless sensor networks, and then the signals are compressed twice based on compressed sensing. Then the abnormal signal data information is imported into support vector machine for training to realize the real-time detection of abnormal signals of electrical equipment state. Experimental results verify the effectiveness of the proposed algorithm.

Increase the Number of Views and Shares of COVID-19 Videos: Content Relevance and Emotional Consistency with Virus Variant Topics.

(1) Background: The coronavirus variants have posed serious challenges for the prevention and control of the COVID-19 pandemic. Individuals selectively watch and forward videos that help them reduce the damage caused by the virus. Therefore, the factors influencing video viewing and sharing in the context of the COVID-19 pandemic caused by virus variation must be explored. (2) Method: Based on a combination of uncertainty reduction theory and functional emotion theory, this paper designed hypotheses regarding how content relevance and emotional consistency affect video views and shares. We used the support vector machine (SVM) classification algorithm to measure the content relevance between videos and virus variant topics. We performed sentiment analysis of video text to evaluate the emotional consistency between videos and virus variant topics. Then, we used empirical analysis to build the model. (3) Results: The trained SVM classifier was effective in judging whether the video text was related to virus variant topics (F = 88.95%). The content relevance between COVID-19 videos and virus variant topics was generally low. The results showed that the higher the content relevance, the more views (IRR = 1.005, p = 0.017) and shares (IRR = 1.008, p = 0.009) the video received. Individuals were more willing to view (IRR = 1.625, p < 0.001) and share (IRR = 1.761, p < 0.001) COVID-19 videos with high emotional consistency with virus variant topics. (4) Conclusions: The results of empirical analysis showed that content relevance and emotional consistency between videos and virus variant topics significantly positively impacted video views and shares. The trained SVM classifier can support public health departments in monitoring and assessing the COVID-19 pandemic. Our study provides management advice while helping individuals reduce harm and inform next-step decisions.

Evolutionary computation-based machine learning for Smart City high-dimensional Big Data Analytics

Science and technology development promotes Smart City Construction (SCC) as a most imminent problem. This work aims to improve the comprehensive performance of the Smart City-oriented high-dimensional Big Data Management (BDM) platform and promote the far-reaching development of SCC. It comprehensively optimizes the calculation process of the BDM platform through Machine Learning (ML), reduces the dimension of the data, and improves the calculation effect. To this end, this work first introduces the concept of SCC and the BDM platform application design. Then, it discusses the design concept of using ML technology to optimize the calculation effect of the BDM platform. Finally, the Tensor Train Support Vector Machine (TT-SVM) model is designed based on dimension reduction data processing. The proposed model can comprehensively optimize the BDM platform, and the model is compared with other models and evaluated. The research results show that the accuracy of the reduced dimension classification of the TT-SVM model is more than 95. The lowest average processing time for the model’s reduced dimension classification is about 1ms. The model’s highest data processing accuracy is about 98%, and the average processing time is between 1.0–1.5ms. Compared with traditional models and BDM platforms, the proposed model has a breakthrough performance improvement, so it plays an important role in future SCC. This work has achieved a great breakthrough in big data processing, and innovatively improved the application mode of high-dimensional big data technology by integrating multiple technologies. Therefore, the finding provides targeted technical reference for algorithms in BDM platform and contributes to the construction and improvement of Smart City.

Soybean Pod Morphology Classification Based on Machine Vision and Convolutional Neural Network

Pod morphology is one of the most crucial indicators for breeding high-quality soybeans. Therefore, the accurate classification of pod morphology is pivotal. Aiming at the problem that the morphology of soybean pods cannot be accurately classified, we proposed an automatic classification method based on machine vision and convolutional neural networks in this paper. First, we designed an image acquisition system to obtain soybean pod images. Then, a convolutional neural network model was designed to extract the deep features of soybean pods in the images. Finally, the deep feature training support vector machine (SVM) classifier was used to classify soybean pods of different forms, and the traditional features are designed to compare the morphological classification of soybean pods. The classification accuracies of this method were 98.8%, 99.2%, and 98.1% for straight, curved scythe, and bowhead bean pods, respectively, with an average classification accuracy of 98.7%, and the classification accuracy of deep features is 5.5% higher than that of traditional feature extraction. Experimental results prove that the proposed automatic classification method is feasible for soybean pod morphology classification, and it also has potential in classification of other characteristics of soybean, such as leaves, grains, and diseases.

Machine learning prediction of above-ground biomass in pure Calabrian pine (Pinus brutia Ten.) stands of the Mediterranean region, Türkiye

Above-ground biomass (AGB) is an important component for identifying carbon stocks, monitoring the impacts of climate change, and evaluating merchantable timber. Accurate prediction of forest AGB is central to the correct interpretation of these components and to produce usable data for planners and researchers. In this study, remotely sensed time-series data derived from Landsat 8 (reflectance (R) and vegetation indices (VI)), topographic (T) and climate (C) data were used as independent variables to predict AGB of pure Calabrian pine (Pinus brutia Ten.) stands using multiple regression analysis (MLR) and support vector machines (SVM) methods. The AGB modeling was done by using independent variables individually and by combining variables, and the AGB maps of the most successful models obtained from MLR and SVM methods were produced. It was determined that the most successful variable group was the VI when the independent variables were used one by one (MLR Training R2 = 0.50, SVM Training R2 = 0.67). The most successful predictions in AGB modeling were obtained with combining all independent variables and using the SVM method (Training R2 = 0.85, Validation R2 = 0.69). In the combination of independent variables, VI and C data made the greatest contribution to the success of the AGB prediction. The ‘green leaf index’ vegetation indices had the most significant effect on the modeling AGB. In this study, T and C in addition to spectral data has increased the AGB estimation performance. It has been found that the SVM method yielded higher model accuracy than MLR method in predicting AGB. Overall, the spectral data and the SVM method can contribute to improving the accuracy of AGB estimates and provide an effective approach towards the capability for forest ecosystem monitoring.

CNN-SVM Spectrum Sensing in Cognitive Radio Based on Signal Covariance Matrix

Among the basic components of cognitive radio technology is spectrum sensing technology. Cooperative spectrum sensing is also a crucial factor research directions of spectrum sensing. Due to the problems of channel fading and hidden nodes, the spectrum sensing based on a single node cannot meet the requirements of the cognitive radio system for the primary user (PU) detection performance. A spectrum sensing algorithm is based on CNN-SVM and covariance matrix. In this algorithm, the covariance matrix of the signal is input into the convolutional neural network for feature extraction. Secondly, the result of the fully connected layer is taken as the input of the support vector machine for training to obtain a classifier, and finally, spectrum sensing is performed. The simulation outcomes demonstrate that the algorithm suggested in this research works outperform other algorithms in this paper. When the signal-to-noise ratio is -14 dB, the false alarm probability is 0.1, the number of secondary users is 32, and the detection probability reaches 0.81.

Identifying the 3FHL Catalog. VI. Swift Observations of 3FHL Unassociated Objects with Source Classification via Machine Learning

The Third Catalog of Hard Fermi Large Area Telescope Sources (3FHL) reports the detection of 1556 objects at E > 10 GeV. However, 177 sources remain unassociated and 23 are associated with a ROSAT X-ray detection of unknown origin. Pointed X-ray observations were conducted on 30 of these unassociated and unknown sources with Swift−XRT. A bright X-ray source counterpart was detected in 21 out of 30 fields. In five of these 21 fields, we detected more than one X-ray counterpart, totaling 26 X-ray sources analyzed. Multiwavelength data was compiled for each X-ray source detected. We find that 21 out of the 26 X-ray sources detected display the multiwavelength properties of blazars, while one X-ray source displays the characteristics of a Galactic source. Using trained decision tree, random forest, and support vector machine models, we predict all 21 blazar counterpart candidates to be BL Lacertae objects (BL Lacs). This is in agreement with BL Lacs being the most populous source class in the 3FHL.

Lithological Mapping of Kohat Basin in Pakistan Using Multispectral Remote Sensing Data: A Comparison of Support Vector Machine (SVM) and Artificial Neural Network (ANN)

Artificial intelligence (AI)-based multispectral remote sensing has been the best supporting tool using limited resources to enhance the lithological mapping abilities with accuracy, supported by ground truthing through traditional mapping techniques. The availability of the dataset, choice of algorithm, cost, accuracy, computational time, data labeling, and terrain features are some crucial considerations that researchers continue to explore. In this research, support vector machine (SVM) and artificial neural network (ANN) were applied to the Sentinel-2 MSI dataset for classifying lithologies having subtle compositional differences in the Kohat Basin’s remote, inaccessible regions within Pakistan. First, we used principal component analysis (PCA), minimum noise fraction (MNF), and available maps for reliable data annotation for training SVM and (ANN) models for mapping ten classes (nine lithological units + water). The ANN and SVM results were compared with the previously conducted studies in the area and ground truth survey to evaluate their accuracy. SVM mapped ten classes with an overall accuracy (OA) of 95.78% and kappa coefficient of 0.95, compared to 95.73% and 0.95 by ANN classification. The SVM algorithm was more efficient concerning computational efficiency, accuracy, and ease due to available features within Google Earth Engine (GEE). Contrarily, ANN required time-consuming data transformation from GEE to Google Cloud before application in Google Colab.

BREAST CANCER HISTOLOGICAL IMAGES CLASSIFICATION AND PERFORMANCE EVALUATION OF DIFFERENT CLASSIFIERS

Breast cancer is a serious trouble and one of the greatest causes of death for women throughout the world. Computer-aided diagnosis (CAD) techniques can help the doctor make more credible decisions. We have determined the possibility of knowledge transfer from natural to histopathological [IX][XII] images by employing a pre-trained network ResNet-50.This pre-trained network has been utilized as a feature generator and extracted features are used to train support vector machine (SVM), random forest, decision tree, and K nearest neighbor(KNN) classifiers[X]. We altered the softmax layer to support the vector machine classifier, random forest classifier, decision tree classifier, and k-nearest neighbor classifier, to evaluate the classifier performance of each algorithm. These approaches are applied for breast cancer classification and evaluate the performance and behavior of different classifiers on a publicly available dataset named Bttheeak-HIS dataset. In order to increase the efficiency of the ResNet[III] model, we preprocessed the data before feeding it to the network. Here we have applied to sharpen filter and data augmentation techniques, which are very popular and effective image pre-processing techniques used in deep models.

Comparing Conventional and Deep Feature Models for Classifying Fundus Photography of Hemorrhages.

Diabetic retinopathy is an eye-related pathology creating abnormalities and causing visual impairment, proper treatment of which requires identifying irregularities. This research uses a hemorrhage detection method and compares the classification of conventional and deep features. Especially, the method identifies hemorrhage connected with blood vessels or residing at the retinal border and was reported challenging. Initially, adaptive brightness adjustment and contrast enhancement rectify degraded images. Prospective locations of hemorrhages are estimated by a Gaussian matched filter, entropy thresholding, and morphological operation. Hemorrhages are segmented by a novel technique based on the regional variance of intensities. Features are then extracted by conventional methods and deep models for training support vector machines and the results are evaluated. Evaluation metrics for each model are promising, but findings suggest that comparatively, deep models are more effective than conventional features.