Linear Kernel Support Vector Machine Research Articles

Preliminary Study on the Identification of Aerobic Vaginitis by Artificial Intelligence Analysis System

To develop an artificial intelligence vaginal secretion analysis system based on deep learning and to evaluate the accuracy of automated microscopy in the clinical diagnosis of aerobic vaginitis (AV). In this study, the vaginal secretion samples of 3769 patients receiving treatment at the Department of Obstetrics and Gynecology, West China Second Hospital, Sichuan University between January 2020 and December 2021 were selected. Using the results of manual microscopy as the control, we developed the linear kernel SVM algorithm, an artificial intelligence (AI) automated analysis software, with Python Scikit-learn script. The AI automated analysis software could identify leucocytes with toxic appearance and parabasal epitheliocytes (PBC). The bacterial grading parameters were reset using standard strains of lactobacillus and AV common isolates. The receiver operating characteristic (ROC) curve analysis was used to determine the cut-off value of AV evaluation results for different scoring items were obtained by using the results of manual microscopy as the control. Then, the parameters of automatic AV identification were determined and the automatic AV analysis scoring method was initially established. A total of 3769 vaginal secretion samples were collected. The AI automated analysis system incorporated five parameters and each parameter incorporated three severity scoring levels. We selected 1.5 μm as the cut-off value for the diameter between Lactobacillus and common AV bacterial isolates. The automated identification parameter of Lactobacillus was the ratio of bacteria ≥1.5 μm to those <1.5 μm. The cut-off scores were 2.5 and 0.5, In the parameter of white blood cells (WBC), the cut-off value of the absolute number of WBC was 103 μL－1 and the cut-off value of WBC-to-epithelial cell ratio was 10. The automated identification parameter of toxic WBC was the ratio of toxic WBC toWBC and the cut-off values were 1% and 15%. The parameter of background flora was bacteria<1.5 μm and the cut-off values were 5×103 μL－1 and 3×104 μL－1. The parameter of the parabasal epitheliocytes was the ratio of PBC to epithelial cells and the cut-off values were 1% and 10%. The agreement rate between the results of automated microscopy and those of manual microscopy was 92.5%. Out of 200 samples, automated microscopy and manual microscopy produced consistent scores for 185 samples, while the results for 15 samples were inconsistent. We developed an AI recognition software for AV and established an automated vaginal secretion microscopy scoring system for AV. There was good overall concordance between automated microscopy and manual microscopy. The AI identification software for AV can complete clinical lab examination with rather high objectivity, sensitivity, and efficiency, markedly reducing the workload of manual microscopy.

Comparison of Discriminant Analysis and Support Vector Machine on Mixed Categorical and Continuous Independent Variables for COVID-19 Patients Data

Purpose: Numerous factors can affect the duration of COVID-19 recovery. One method involves utilizing natural herbal medication. This study seeks to determine the variables influencing the duration of COVID-19 recovery and to compare discriminant analysis and support vector machine models using COVID-19 patient data from West Sumatra.Methods: Two data mining methods, Discriminant Analysis and Support Vector Machine with different types of kernels (linear, polynomial, and radial basis function), were employed to categorize the time of COVID-19 recovery in this work. The study utilized 428 data points, with 75% allocated for training data and 25% for testing data. The independent factors were evaluated by determining the selection variables' information value (IV) to gauge their influence on the dependent variable. Data resampling techniques were employed to tackle the problem of data imbalance. This study employs data resampling techniques, including undersampling, oversampling, and SMOTE. The balancing accuracy of Discriminant Analysis and Support Vector Machine was examined.Result: The Discriminant Analysis with SMOTE achieved a balanced accuracy of 66.50%, outperforming the linear kernel Support Vector Machine with SMOTE, which had a balanced accuracy of 63.20% in this dataset.Novelty: This study assessed the novelty, originality, and value by comparing Discriminant Analysis and SVM algorithms with categorical and continuous independent variables. This research explores techniques for managing imbalanced data using undersampling, oversampling, and SMOTE, with variable selection based on information value assessment.

N-gram and Kernel Performance Using Support Vector Machine Algorithm for Fake News Detection System

The modern technological advancements have made it simpler for fake news to circulate online. The researchers have developed several strategies to overcome this obstacle, including text classification, distribution network analysis, and human-machine hybrid methods. The most common method is text categorization, and many researchers offer deep learning and machine learning models as remedies. An Indonesian language fake news detection system based on news headlines was developed in this work using the Support Vector Machine (SVM) kernel and n-gram. The objective of this research is to identify the model that produces the best performance outcomes. The system deployment on the web will employ the model that produces the greatest outcomes. According to the research findings, the linear kernel SVM algorithm produces the best results, with an accuracy value of 0.974. Furthermore, the bigram feature used in the development of a classification model does not increase the precision of fake news identification in Indonesian. Utilizing the unigram function yields the most accurate results.

Unlocking the Potential: A Deep Learning Approach for Objective Screening of AML with NPM1 Mutation Via Holotomography

Introduction: As the clinical significance of genetic mutations becomes clearer, diagnostic classifications are continuously evolving, making judicious decisions about implementing costly genetic testing for diagnosis crucial. Intriguing observations suggest that Myelodysplastic Syndrome (MDS) or MDS/Myeloproliferative Neoplasm with NPM1 mutation can rapidly progress to Acute Myeloid Leukemia (AML), leading to ambiguity in acute leukemia diagnosis. Consequently, this finding has led to ambiguity surrounding the diagnostic criteria for acute leukemia with low blast counts. Holotomography (HT) is a cutting-edge microscope that utilizes refractive index (RI) as a contrast medium. It not only provides 2D or 3D images but also offers numerical information about every pixel of cells, promising a more objective diagnosis. Previous studies have successfully distinguished mature cells and blasts using HT. In this study, our aim is to construct a sophisticated deep learning model using data from HT to predict the presence of NPM1 mutations in blasts. This research endeavor holds the potential to enable early detection of these mutations in hematologic malignancies and facilitate the effective utilization of valuable medical resources. Methods: We utilized HT to analyze blasts of AML with mutated NPM1 (experimental group) and AML not otherwise specified (control group) but exhibiting similar morphological characteristics from May 2021 to May 2022. We analyzed a total of 648 blasts from 15 patients in the experimental group and 762 blasts from 24 patients in the control group. Cell segmentation for Rule-based features was performed using ilastik version 1.3.3 and MATLAB 2022a. After the initial segmentation using ilastik's machine learning pixel classification feature, further refinements were made in MATLAB, based on prior knowledge of the size and topology of each structure. Subsequently, volumetric and morphological information was measured within these segments. The cell data of each patient were divided into a training set and a test set. The deep learning algorithm, built using the training set, was then validated with data from the test set. For the deep learning and prediction tasks, we employed a Convolutional Neural Network algorithm (Figure). The classification process involved utilizing both the Rule-based features and the entire feature set, where a linear kernel Support Vector Machine was used. Additionally, we employed the Ensemble average approach, where multiple cells' scores (numerical values associated with the probabilities of each classification) were averaged, and the classification with the highest score was selected as the final prediction. Finally, the deep learning model was validated using previously unused test set data through the Receiver Operating Characteristic (ROC) curve. Results: The dry mass of the nucleolus was significantly increased in AML, NOS; Exp, 0.29341 ± 0.014499 pg; Control, 0.71184 ± 0.033521 pg ( P&amp;lt;0.05). The dry mass of the cytoplasm was higher in AML with mutated NPM1, showing a higher value than that of the nucleolus; Exp, 45.7334 ± 0.50003 pg; Control, 42.9807 ± 0.63882 pg (P&amp;lt;0.05). When validating the deep learning model constructed based on individual cells, the area under the ROC curve (AUC) was found to be 0.8836. Even within the same individual, the cell morphology can be heterogeneous. Therefore, when the data from 5 cells were treated as a single entity for validating the deep learning model, the AUC was 0.9944. Conclusions: It is widely acknowledged that the NPM1 protein, typically localized in the nucleolus, undergoes relocation to the cytoplasm as a result of NPM1 mutation. In this investigation, we devised an advanced deep learning model leveraging numerical data derived from HT, enabling us to prognosticate variations in protein expression based on NPM1 mutations. The HT numerical data exhibited distinctive variations in both nuclear and cytoplasmic analyses contingent on NPM1 mutations. Given the current uncertainty in leukemia diagnosis, partly attributable to the costly selection of genetic testing, we are optimistic that the integration of HT with our sophisticated deep learning model will pave the way for early diagnosis prediction before conducting additional genetic tests.

Vision-based chicken meat freshness recognition system using RGB color moment features and support vector machine

Chicken meat is a highly sought-after food product among various segments of the general population, known for its high nutritional value and easy accessibility. Presently, meat identification is primarily conducted manually, relying on visual inspection or tactile assessment of the meat's color and texture. However, this approach presents several limitations, particularly when consumers lack the discernment to differentiate the quality of chicken meat freshness. This research aims to identify the freshness level of chicken meat using the Support Vector Machine method, employing the extraction of RGB color moment features to determine the freshness of the meat. The feature extraction process involves calculating the percentage of intensity values for R (Red), G (Green), and B (Blue) in each chicken meat image. Based on the image processing results, the percentage of intensity values, particularly in the R and B parameters, can be used as determining factors. The study involves software testing using fresh and non-fresh chicken meat. The developed system can identify the freshness level of fresh chicken meat with an accuracy rate of 71.6% using the linear kernel SVM and 60.5% using the RBF kernel SVM. This research represents a significant step toward the automation of chicken meat freshness assessment, potentially reducing food waste and enhancing food safety in the food industry. Further research and development could improve the system's accuracy and expand its applications in various food quality control settings.Chicken meat is a highly sought-after food product among various segments of the general population, known for its high nutritional value and easy accessibility. Presently, meat identification is primarily conducted manually, relying on visual inspection or tactile assessment of the meat's color and texture. However, this approach presents several limitations, particularly when consumers lack the discernment to differentiate the quality of chicken meat freshness. This research aims to identify the freshness level of chicken meat using the Support Vector Machine method, employing the extraction of RGB color moment features to determine the freshness of the meat. The feature extraction process involves calculating the percentage of intensity values for R (Red), G (Green), and B (Blue) in each chicken meat image. Based on the image processing results, the percentage of intensity values, particularly in the R and B parameters, can be used as determining factors. The study involves software testing using fresh and non-fresh chicken meat. The developed system can identify the freshness level of fresh chicken meat with an accuracy rate of 71.6% using the linear kernel SVM and 60.5% using the RBF kernel SVM. This research represents a significant step toward the automation of chicken meat freshness assessment, potentially reducing food waste and enhancing food safety in the food industry. Further research and development could improve the system's accuracy and expand its applications in various food quality control settings.

Backward Elimination for Feature Selection on Breast Cancer Classification Using Logistic Regression and Support Vector Machine Algorithms

Breast cancer is a prevalent form of cancer that afflicts women across all nations globally. One of the ways that can be done as a prevention to reduce elevated fatality due to breast cancer is with a detection system that can determine whether a cancer is benign or malignant. Logistic Regression and Support Vector Machine (SVM) classification algorithms are often used to detect this disease, but the use of these two algorithms often doesn’t give optimal results when applied to datasets that have many features, so additional algorithm is needed to improve classification performance by using Backward Elimination feature selection. The comparison of Logistic Regression and SVM algorithms was carried out by applying feature selection to breast cancer data to see the best model. The breast cancer dataset has 30 features and two classes, Benign and Malignant. Backward Elimination has reduced features from 30 features to 13 features, thereby increasing the performance of both classification models. The best classification was obtained by using the Backward Elimination feature selection and linear kernel SVM with an increase in accuracy value from 96.14% to 97.02%, precision from 98.06% to 99.49%, recall from 90.48% to 92.38%, and the AUC from 0.95 to 0.96.

Identification of preclinical dementia according to ATN classification for stratified trial recruitment: A machine learning approach.

The Amyloid/Tau/Neurodegeneration (ATN) framework was proposed to identify the preclinical biological state of Alzheimer's disease (AD). We investigated whether ATN phenotype can be predicted using routinely collected research cohort data. 927 EPAD LCS cohort participants free of dementia or Mild Cognitive Impairment were separated into 5 ATN categories. We used machine learning (ML) methods to identify a set of significant features separating each neurodegeneration-related group from controls (A-T-(N)-). Random Forest and linear-kernel SVM with stratified 5-fold cross validations were used to optimize model whose performance was then tested in the ADNI database. Our optimal results outperformed ATN cross-validated logistic regression models by between 2.2% and 8.3%. The optimal feature sets were not consistent across the 4 models with the AD pathologic change vs controls set differing the most from the rest. Because of that we have identified a subset of 10 features that yield results very close or identical to the optimal. Our study demonstrates the gains offered by ML in generating ATN risk prediction over logistic regression models among pre-dementia individuals.

Noninvasive radiomic analysis of enhanced CT predicts CTLA4 expression and prognosis in head and neck squamous cell carcinoma

Developing a radiomic model to predict CTLA4 expression levels and assessing its prognostic accuracy for patients. Medical imaging data were sourced from the TCIA database, while transcriptome sequencing data were derived from the TCGA database. We utilized a linear kernel SVM algorithm to develop a radiomic model for predicting CTLA4 gene expression. We then assessed the model’s clinical relevance using survival and Cox regression analyses. Performance evaluations of the model were illustrated through ROC, PR, calibration, and decision curves. (1) Bioinformatics analysis: Kaplan–Meier curves indicated that increased CTLA4 expression correlates with enhanced overall survival (OS) (p < 0.001). Both univariate and multivariate analyses revealed that high CTLA4 expression served as a protective factor for OS (HR = 0.562, 95% CI 0.427–0.741, p < 0.001). (2) Radiomics evaluation: the ROC curve demonstrated that the AUC for the SVM radiomics model was 0.766 in the training set and 0.742 in the validation set. The calibration curve affirmed that the model's prediction probability for high gene expression aligns with the actual outcomes. Furthermore, decision curve analysis (DCA) indicated that our model boasts robust clinical applicability. CTLA4 expression level serves as an independent prognostic factor for HNSCCs. Using enhanced CT images, the SVM radiomic model effectively predicts CTLA4 expression levels. As a result, this model offers strong prognostic insights for HNSCCs, guiding precise diagnosis, treatment, and assisting in clinical decision-making.

Recurrence prediction of lung adenocarcinoma using an immune gene expression and clinical data trained and validated support vector machine classifier.

Immune microenvironment plays a critical role in cancer from onset to relapse. Machine learning (ML) algorithm can facilitate the analysis of lab and clinical data to predict lung cancer recurrence. Prompt detection and intervention are crucial for long-term survival in lung cancer relapse. Our study aimed to evaluate the clinical and genomic prognosticators for lung cancer recurrence by comparing the predictive accuracy of four ML models. A total of 41 early-stage lung cancer patients who underwent surgery between June 2007 and October 2014 at New York University Langone Medical Center were included (with recurrence, n=16; without recurrence, n=25). All patients had tumor tissue and buffy coat collected at the time of resection. The CIBERSORT algorithm quantified tumor-infiltrating immune cells (TIICs). Protein-protein interaction (PPI) network and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis were conducted to unearth potential molecular drivers of tumor progression. The data was split into training (75%) and validation sets (25%). Ensemble linear kernel support vector machine (SVM) ML models were developed using optimized clinical and genomic features to predict tumor recurrence. Activated natural killer (NK) cells, M0 macrophages, and M1 macrophages showed a positive correlation with progression. Conversely, T CD4+ memory resting cells were negatively correlated. In the PPI network, TNF and IL6 emerged as prominent hub genes. Prediction models integrating clinicopathological prognostic factors, tumor gene expression (45 genes), and buffy coat gene expression (47 genes) yielded varying receiver operating characteristic (ROC)-area under the curves (AUCs): 62.7%, 65.4%, and 59.7% in the training set, 58.3%, 83.3%, and 75.0% in the validation set, respectively. Notably, merging gene expression with clinical data in a linear SVM model led to a significant accuracy boost, with an AUC of 92.0% in training and 91.7% in validation. Using ML algorithm, immune gene expression data from tumor tissue and buffy coat may enhance the precision of lung cancer recurrence prediction.

MOBA GAME REVIEW SENTIMENT ANALYSIS USING SUPPORT VECTOR MACHINE ALGORITHM

MOBA as one of the many popular subgenres today, Mobile Legend, Arena of Valor, League of Legend and Lokapala based on the large number of downloads can be mentioned as popular MOBA games, but the rating of these four applications is below 4.0 on the Google Play platform Store, this happens because some users may think that this mobile MOBA game has several advantages, but also some disadvantages that affect ratings. This study aims to determine the results of sentiment analysis on mobile MOBA games using Google Play Store reviews. Then it is processed using Python programming to create a model with the linear kernel Support Vector Machine (SVM) algorithm to classify the dataset. From the results of the classification model test using 19,579 data, where there were 10,017 positive sentiment data and 9,562 negative sentiment data and the distribution of train data and test data was 70%: 30%, obtained an accuracy of 82.64% and then re-evaluated using the Cross Validation method using 5 times so that an accuracy of 83.38% is obtained Keywords: MOBA, Sentiment Analysis, Machine Learning, SVM, Cross Validation

Automatic Life Detection Based on Efficient Features of Ground-Penetrating Rescue Radar Signals.

Good feature engineering is a prerequisite for accurate classification, especially in challenging scenarios such as detecting the breathing of living persons trapped under building rubble using bioradar. Unlike monitoring patients' breathing through the air, the measuring conditions of a rescue bioradar are very complex. The ultimate goal of search and rescue is to determine the presence of a living person, which requires extracting representative features that can distinguish measurements with the presence of a person and without. To address this challenge, we conducted a bioradar test scenario under laboratory conditions and decomposed the radar signal into different range intervals to derive multiple virtual scenes from the real one. We then extracted physical and statistical quantitative features that represent a measurement, aiming to find those features that are robust to the complexity of rescue-radar measuring conditions, including different rubble sites, breathing rates, signal strengths, and short-duration disturbances. To this end, we utilized two methods, Analysis of Variance (ANOVA), and Minimum Redundancy Maximum Relevance (MRMR), to analyze the significance of the extracted features. We then trained the classification model using a linear kernel support vector machine (SVM). As the main result of this work, we identified an optimal feature set of four features based on the feature ranking and the improvement in the classification accuracy of the SVM model. These four features are related to four different physical quantities and independent from different rubble sites.

Unipolar and Bipolar Depression Detection and Classification Based on Actigraphic Registration of Motor Activity Using Machine Learning and Uniform Manifold Approximation and Projection Methods.

Modern technology frequently uses wearable sensors to monitor many aspects of human behavior. Since continuous records of heart rate and activity levels are typically gathered, the data generated by these devices have a lot of promise beyond counting the number of daily steps or calories expended. Due to the patient's inability to obtain the necessary information to understand their conditions and detect illness, such as depression, objectively, methods for evaluating various mental disorders, such as the Montgomery-Asberg depression rating scale (MADRS) and observations, currently require a significant amount of effort on the part of specialists. In this study, a novel dataset was provided, comprising sensor data gathered from depressed patients. The dataset included 32 healthy controls and 23 unipolar and bipolar depressive patients with motor activity recordings. Along with the sensor data collected over several days of continuous measurement for each patient, some demographic information was also offered. The result of the experiment showed that less than 70 of the 100 epochs of the model's training were completed. The Cohen Kappa score did not even pass 0.1 in the validation set, due to an imbalance in the class distribution, whereas in the second experiment, the majority of scores peaked in about 20 epochs, but because training continued during each epoch, it took much longer for the loss to decline before it fell below 0.1. In the second experiment, the model soon reached an accuracy of 0.991, which is as expected given the outcome of the UMAP dimensionality reduction. In the last experiment, UMAP and neural networks worked together to produce the best outcomes. They used a variety of machine learning classification algorithms, including the nearest neighbors, linear kernel SVM, Gaussian process, and random forest. This paper used the UMAP unsupervised machine learning dimensionality reduction without the neural network and showed a slightly lower score (QDA). By considering the ratings of the patient's depressive symptoms that were completed by medical specialists, it is possible to better understand the relationship between depression and motor activity.

Machine learning model predicts the occurrence of acute kidney injury after open surgery for abdominal aortic aneurysm repair.

Abdominal aortic aneurysm is a pathological condition in which the abdominal aorta is dilated beyond 3.0 cm. The surgical options include open surgical repair (OSR) and endovascular aneurysm repair (EVAR). Prediction of acute kidney injury (AKI) after OSR is helpful for decision-making during the postoperative phase. To find a more efficient method for making a prediction, this study aims to perform tests on the efficacy of different machine learning models. Perioperative data of 80 OSR patients were retrospectively collected from January 2009 to December 2021 at Xiangya Hospital, Central South University. The vascular surgeon performed the surgical operation. Four commonly used machine learning classification models (logistic regression, linear kernel support vector machine, Gaussian kernel support vector machine, and random forest) were chosen to predict AKI. The efficacy of the models was validated by five-fold cross-validation. AKI was identified in 33 patients. Five-fold cross-validation showed that among the 4 classification models, random forest was the most precise model for predicting AKI, with an area under the curve of 0.90±0.12. Machine learning models can precisely predict AKI during early stages after surgery, which allows vascular surgeons to address complications earlier and may help improve the clinical outcomes of OSR.

Identification of biomarkers predictive of metastasis development in early-stage colorectal cancer using network-based regularization

Colorectal cancer (CRC) is the third most common cancer and the second most deathly worldwide. It is a very heterogeneous disease that can develop via distinct pathways where metastasis is the primary cause of death. Therefore, it is crucial to understand the molecular mechanisms underlying metastasis. RNA-sequencing is an essential tool used for studying the transcriptional landscape. However, the high-dimensionality of gene expression data makes selecting novel metastatic biomarkers problematic. To distinguish early-stage CRC patients at risk of developing metastasis from those that are not, three types of binary classification approaches were used: (1) classification methods (decision trees, linear and radial kernel support vector machines, logistic regression, and random forest) using differentially expressed genes (DEGs) as input features; (2) regularized logistic regression based on the Elastic Net penalty and the proposed iTwiner—a network-based regularizer accounting for gene correlation information; and (3) classification methods based on the genes pre-selected using regularized logistic regression. Classifiers using the DEGs as features showed similar results, with random forest showing the highest accuracy. Using regularized logistic regression on the full dataset yielded no improvement in the methods’ accuracy. Further classification using the pre-selected genes found by different penalty factors, instead of the DEGs, significantly improved the accuracy of the binary classifiers. Moreover, the use of network-based correlation information (iTwiner) for gene selection produced the best classification results and the identification of more stable and robust gene sets. Some are known to be tumor suppressor genes (OPCML-IT2), to be related to resistance to cancer therapies (RAC1P3), or to be involved in several cancer processes such as genome stability (XRCC6P2), tumor growth and metastasis (MIR602) and regulation of gene transcription (NME2P2). We show that the classification of CRC patients based on pre-selected features by regularized logistic regression is a valuable alternative to using DEGs, significantly increasing the models’ predictive performance. Moreover, the use of correlation-based penalization for biomarker selection stands as a promising strategy for predicting patients’ groups based on RNA-seq data.

Design and Study of Zombie Enterprise Classification and Recognition Systems Based on Ensemble Learning

The existence of a large number of zombie enterprises will affect the economic development and hinder the transformation and upgrading of economic industries. To improve the accuracy of zombie enterprise identification, this paper takes multidimensional enterprise data as the original data set, divides it into training set and validation set, and gives the corresponding data pre-processing methods. Combined with 14 standardized features, an integrated learning model for zombie enterprise classification and recognition is constructed and studied based on three pattern recognition algorithms. By using the idea of integration and the cross-validation method to determine the optimal parameters, the Gradient Boosting Decision Tree (GBDT), linear kernel Support Vector Machine (SVM) and Deep Neural Network (DNN) algorithms with classification accuracies of 95%, 96% and 96%, respectively, are used as sub-models, and a more comprehensive strong supervision model with a classification accuracy of 98% is obtained by the stacking method in combination with the advantages of multiple sub-models to analyze the fundamental information of 30885 enterprises. The study improves the accuracy of zombie enterprise identification to 98%, builds enterprise portraits based on this, and finally visualizes the classification results through the platform, which provides an auxiliary means for zombie enterprise classification and identification.

Acacia dealbata classification from aerial imagery acquired using unmanned aerial vehicles

Non-native plant species can have a negative impact in the ecosystems and in local economies when they spread uncontrollably. Monitoring tools can support their management and spread. In this paper, an exploratory approach is presented for pixelwise detection of Acacia dealbata from UAV-based imagery acquired from RGB and multispectral sensors. Four machine learning algorithms - k-nearest neighbors (KNN), random forest (RF), adaptive boosting (AdaBoost) and a linear kernel SVM (LSVM) - are trained using four datasets (hue, saturation and value - HSV, multispectral - MSP, RGB and a combination of all features) and their classification performance is evaluated. RF classifier obtained the overall best performance, with an accuracy above 86% in all data combinations, with LSVM showing the poorer results. Obtained results are encouraging for monitoring invasive species and can serve as a base for future improvements to detect invasive species.

Analisis Sentimen Terhadap Program Kampus Merdeka Menggunakan Naive Bayes Dan Support Vector Machine

In order to prepare students to face the rapid development of technology, changes in work life and skills, students must be better prepared to face the progress of the times. Universities must be able to carry out innovative learning processes so that students achieve optimal learning outcomes which include aspects of knowledge, skills and attitudes. So the MBKM program was launched to answer these demands. However, MBKM has pros and cons in its implementation, so it is necessary to analyze and evaluate policies to improve performance through feedback from the public by conducting sentiment analysis of MBKM policies on twitter users from 2019 to 2022 with the hashtag #kampusmerdeka. This study used the Naïve Bayes and SVM algorithms to determine accuracy based on sentiment classification. The data used 1118 data with positive sentiment 618 data and negative sentiment 500 data. This study resulted in an accuracy of 86%, precision of 87% and recall of 80% with testing data using the Naïve Bayes algorithm. Then using the linear kernel SVM algorithm with the same testing data resulted in accuracy of 93%, precision of 100% and recall of 84%. Therefore, it is important to conduct studies to improve the MBKM program so that its implementation is clearly in accordance with existing procedures.

Combining deep-wavelet neural networks and support-vector machines to classify breast lesions in thermography images

Breast cancer is among the leading causes of cancer death among women. The occurrence of breast cancer is similar both in developed countries and in underdeveloped and developing nations, although mortality is higher in underdeveloped countries due to late detection. Even though mammography is the most used technique for the differential diagnosis of breast cancer, breast thermography can be used as a complementary technique, more accurate than self-examination but accurate enough to guide the use of a mammogram. However, thermal imaging is still difficult for radiologists to understand. Machine learning can help improve this scenario. Deep Wavelet Neural Networks are convolutional neural networks that do not necessarily learn, as they may have predefined filter banks as their neurons. In this work, we propose a deep hybrid architecture to support breast thermography imaging diagnosis based on five-layer Deep-Wavelet Neural Networks, to extract attributes of regions of interest from mammograms, and linear kernel support vector machines for final classification. Classical classifiers such as Bayesian classifiers, single hidden layer multilayer perceptrons, decision trees, Random Forests, and support vector machines were tested. The results showed that it is possible to detect and classify injuries with an average accuracy of 99% and an average kappa of 0.99, employing a 5-layer deep-wavelet network and a linear kernel support vector machine as the final classifier. Using a deep neural network with prefixed weights from the Wavelets Transform filter bank, it was possible to extract attributes and thus take the problem to a universe where it can be solved with relatively simple decision boundaries like those composed by linear kernel support vector machines. This shows that these new deep networks can be important in building complete solutions to improve breast thermography imaging results to support clinical diagnosis.

Deep-Wavelets and convolutional neural networks to support breast cancer diagnosis on thermography images

ABSTRACT Breast cancer is the most dangerous type of cancer and one of the most lethal for women, both in underdeveloped and central countries. Breast thermography is an emerging imaging technique that can be applied as a complementary procedure for screening breast lesions. However, the low knowledge about the interpretation of these images by mastologists makes it difficult to adopt them in clinical practice. Computer-aided detection (CAD) systems can assist medical professionals in this task. Deep learning techniques have contributed to obtaining good results in the classification of biomedical images in general. In this work, we propose Deep-Wavelet Neural Networks (DWNN), convolutional architectures based on the general theory of Wavelets to extract features from images. For classification of thermographic images, we propose hybrid architectures based on deep network for feature extraction, Random Forests for selection of the most statistically relevant features and linear kernel support vector machines for final layer classification. We compare DWNN with next-gen deep networks. Our dataset consists of 336 thermographic images, classified into healthy (no lesion), cyst, benign lesion and malignant lesion. Experimental results show that the 6-layer DWNN achieved accuracy, sensitivity, specificity, kappa and precision above 98%. These results show that DWNN are competitive deep architectures that can be used to optimise thermographic image analysis and clinical adoption.

Performances of whole-brain dynamic and static functional connectivity fingerprinting in machine learning-based classification of major depressive disorder.

BackgroundAlterations in static and dynamic functional connectivity during resting state have been widely reported in major depressive disorder (MDD). The objective of this study was to compare the performances of whole-brain dynamic and static functional connectivity combined with machine learning approach in differentiating MDD patients from healthy controls at the individual subject level. Given the dynamic nature of brain activity, we hypothesized that dynamic connectivity would outperform static connectivity in the classification.MethodsSeventy-one MDD patients and seventy-one well-matched healthy controls underwent resting-state functional magnetic resonance imaging scans. Whole-brain dynamic and static functional connectivity patterns were calculated and utilized as classification features. Linear kernel support vector machine was employed to design the classifier and a leave-one-out cross-validation strategy was used to assess classifier performance.ResultsExperimental results of dynamic functional connectivity-based classification showed that MDD patients could be discriminated from healthy controls with an excellent accuracy of 100% irrespective of whether or not global signal regression (GSR) was performed (permutation test with P < 0.0002). Brain regions with the most discriminating dynamic connectivity were mainly and reliably located within the default mode network, cerebellum, and subcortical network. In contrast, the static functional connectivity-based classifiers exhibited unstable classification performances, i.e., a low accuracy of 38.0% without GSR (P = 0.9926) while a high accuracy of 96.5% with GSR (P < 0.0002); moreover, there was a considerable variability in the distribution of brain regions with static connectivity most informative for classification.ConclusionThese findings suggest the superiority of dynamic functional connectivity in machine learning-based classification of depression, which may be helpful for a better understanding of the neural basis of MDD as well as for the development of effective computer-aided diagnosis tools in clinical settings.