Maximum Margin Research Articles

Robust and compact maximum margin clustering for high-dimensional data

In the field of machine learning, clustering has become an increasingly popular research topic due to its critical importance. Many clustering algorithms have been proposed utilizing a variety of approaches. This study focuses on clustering of high-dimensional data using the maximum margin clustering approach. In this paper, two methods are introduced: The first method employs the classical maximum margin clustering approach, which separates data into two clusters with the greatest margin between them. The second method takes cluster compactness into account and searches for two parallel hyperplanes that best fit to the cluster samples while also being as far apart from each other as possible. Additionally, robust variants of these clustering methods are introduced to handle outliers and noise within the data samples. The stochastic gradient algorithm is used to solve the resulting optimization problems, enabling all proposed clustering methods to scale well with large-scale data. Experimental results demonstrate that the proposed methods are more effective than existing maximum margin clustering methods, particularly in high-dimensional clustering problems, highlighting the efficacy of the proposed methods.

A very low-profile CPW based conformal antenna for wearable/implantable applications.

In wireless communication standard 4G and 5G, the body centric network plays an important role for the wireless communication between various devices. This research relates to a wide-band conformal co-planar waveguide (CPW) antenna for wearable applications. The proposed CPW antenna is printed on 0.1 mm thick bio-compatible polymide substrate whose dielectric constant and permittivity are 3.5 and 0.02 respectively. The total area of the antenna is around 17.5 × 15 mm2 which is significantly smaller than the wearable antennas proposed in literature. The proposed antenna is designed to operate in new ISM band 5.8 GHz with the bandwidth of 5.3-6.3 GHz with 2:1 Voltage Standing Wave Ratio (VSWR). The antenna is printed on the flexible substrate and hence robustness of device is evaluated by bending analysis. It reveals the superior performance of the designed CPW antenna over the desired spectrum of operation. Specific Absorption Rate (SAR) is calculated after placing the antenna at various places of human phantom model and showed that SAR values are below 1.6 W/Kg which is the maximum margin recommended by Federal Communication Commission (FCC), i.e when tested with 1 g and 10 g of human tissue of phantom model, for the test frequency range of 5.5-6.1GHz, SAR value falls between 0.9987 and 0.921 W/Kg respectively. The antenna also shows the radiation efficiency around 92% with overall realized gain 5.2 dBi which are substantial values for wearable applications. The outcomes of this research revealed the feasibility of the recommended antenna becoming a major contender of future Internet of Things (IoT) applications.

Pengaruh Kualitas Produk dan Kualitas Pelayanan terhadap Keputusan Pembelian di Optik Sejahtera Depok

The aim of this research is to obtain the necessary data and information and process it as comparison material with theories from library research to fulfill the requirements for writing a dissertation. find out how product quality influences purchasing decisions and find out how service quality influences purchasing decisions at Optik Sejahtera Depok. As well as to find out simultaneously the influence of product quality and service quality in purchasing decision making at Optik Sejahtera Depok. The following research analysis uses a quantitative approach analysis and the research population includes a purchasing decision population of 312 people. 76 The sample used in this research, the sampling technique used is non-probability, the sampling technique used is purposive sampling, and the determination formula The sample size is considered appropriate to represent the entire population, the Slovin formula is used, and the maximum margin is used. The maximum error or error is used. This formula sets the acceptable value to be 0.10 or 10% or 76 respondents. Product quality results can have a significant impact on purchasing decisions because the t count is 2.204 > 1.992 in the t table, and sig.< 0> t table 1.992 and the Sig. < 0> Table 3.12 and Sig value. <;0.05 (0.000 <0.05).

Margin-Maximized Norm-Mixed Representation Learning for Autism Spectrum Disorder Diagnosis With Multi-Level Flux Features.

Early diagnosis and timely intervention are significantly beneficial to patients with autism spectrum disorder (ASD). Although structural magnetic resonance imaging (sMRI) has become an essential tool to facilitate the diagnosis of ASD, these sMRI-based approaches still have the following issues. The heterogeneity and subtle anatomical changes place higher demands for effective feature descriptors. Additionally, the original features are usually high-dimensional, while most existing methods prefer to select feature subsets in the original space, in which noises and outliers may hinder the discriminative ability of selected features. In this article, we propose a margin-maximized norm-mixed representation learning framework for ASD diagnosis with multi-level flux features extracted from sMRI. Specifically, a flux feature descriptor is devised to quantify comprehensive gradient information of brain structures on both local and global levels. For the multi-level flux features, we learn latent representations in an assumed low-dimensional space, in which a self-representation term is incorporated to characterize the relationships among features. We also introduce mixed norms to finely select original flux features for the construction of latent representations while preserving the low-rankness of latent representations. Furthermore, a margin maximization strategy is applied to enlarge the inter-class distance of samples, thereby increasing the discriminative ability of latent representations. The extensive experiments on several datasets show that our proposed method can achieve promising classification performance (the average area under curve, accuracy, specificity, and sensitivity on the studied ASD datasets are 0.907, 0.896, 0.892, and 0.908, respectively) and also find potential biomarkers for ASD diagnosis.

Regression-Based Hyperparameter Learning for Support Vector Machines.

Unification of classification and regression is a major challenge in machine learning and has attracted increasing attentions from researchers. In this article, we present a new idea for this challenge, where we convert the classification problem into a regression problem, and then use the methods in regression to solve the problem in classification. To this end, we leverage the widely used maximum margin classification algorithm and its typical representative, support vector machine (SVM). More specifically, we convert SVM into a piecewise linear regression task and propose a regression-based SVM (RBSVM) hyperparameter learning algorithm, where regression methods are used to solve several key problems in classification, such as learning of hyperparameters, calculation of prediction probabilities, and measurement of model uncertainty. To analyze the uncertainty of the model, we propose a new concept of model entropy, where the leave-one-out prediction probability of each sample is converted into entropy, and then used to quantify the uncertainty of the model. The model entropy is different from the classification margin, in the sense that it considers the distribution of all samples, not just the support vectors. Therefore, it can assess the uncertainty of the model more accurately than the classification margin. In the case of the same classification margin, the farther the sample distribution is from the classification hyperplane, the lower the model entropy. Experiments show that our algorithm (RBSVM) provides higher prediction accuracy and lower model uncertainty, when compared with state-of-the-art algorithms, such as Bayesian hyperparameter search and gradient-based hyperparameter learning algorithms.

TKR-FSOD: Fetal Anatomical Structure Few-Shot Detection Utilizing Topological Knowledge Reasoning.

Fetal multi-anatomical structure detection in Ultrasound (US) images can clearly present the relationship and influence between anatomical structures, providing more comprehensive information about fetal organ structures and assisting sonographers in making more accurate diagnoses, widely used in structure evaluation. Recently, deep learning methods have shown superior performance in detecting various anatomical structures in ultrasound images but still have the potential for performance improvement in categories where it is difficult to obtain samples, such as rare diseases. Few-shot learning has attracted a lot of attention in medical image analysis due to its ability to solve the problem of data scarcity. However, existing few-shot learning research in medical image analysis focuses on classification and segmentation, and the research on object detection has been neglected. In this paper, we propose a novel fetal anatomical structure fewshot detection method in ultrasound images, TKR-FSOD, which learns topological knowledge through a Topological Knowledge Reasoning Module to help the model reason about and detect anatomical structures. Furthermore, we propose a Discriminate Ability Enhanced Feature Learning Module that extracts abundant discriminative features to enhance the model's discriminative ability. Experimental results demonstrate that our method outperforms the state-of-the-art baseline methods, exceeding the second best method with a maximum margin of 4.8% on 5-shot of split 1 under 4CC. The code is publicly available at: https://github.com/lixi92/TKR-FSOD.

Homocentric quadratic surfaces and maximum margin approach for imbalanced data classification

Homocentric quadratic surfaces and maximum margin approach for imbalanced data classification

Preventive-Corrective Cyber-Defense: Attack-Induced Region Minimization and Cybersecurity Margin Maximization

Preventive-Corrective Cyber-Defense: Attack-Induced Region Minimization and Cybersecurity Margin Maximization

Margin Maximization of Text Classification based on Support Vector Machine

Abstract: This project focuses on developing a margin maximization model for topic categorization using Support Vector Machines (SVM). Topic categorization aims to classify text documents into predefined topic categories. The proposed model leverages SVM's ability to create a hyperplane with maximum margin between different topics, enhancing the classification performance. The project begins with dataset preparation, where a labeled dataset covering a wide range of topics is gathered. The text data undergoes preprocessing, including cleaning, normalization, and conversion into numerical representations. Feature extraction techniques such as TF-IDF or word embeddings are employed to capture important features related to topics. The dataset is split into training and testing sets, with the training set used to train the SVM model. The SVM model is trained with a focus on maximizing the margin, utilizing techniques like soft-margin SVM or the kernel trick to handle non-linear separable data. Hyperparameters of the SVM model are tuned to optimize its performance. The trained SVM model is then used to predict the topics of the testing data, and its performance is evaluated using standard metrics such as accuracy, precision, recall, and F1 score. The findings of this project demonstrate the effectiveness of the margin maximization model for topic categorization using SVM

Prospective Margin Estimates Predict Local Tumor Progression Following Microwave Ablation of Small Renal Masses.

To evaluate the relationship between prospectively generated ablative margin estimates and local tumor progression (LTP) among patients undergoing microwave ablation (MWA) of small renal masses (SRMs). Between 2017 and 2020, patients who underwent MWA for SRM were retrospectively identified. During each procedure, segmented kidney and tumor shapes were coregistered with intraprocedural helical CT images obtained after microwave antenna placement. Predicted ablation zone shape and size were then overlaid onto the resultant model, and a model-to-model distance algorithm was employed to calculate multiple ablative margin estimates. LTP was modeled as a function of each margin estimate by hazard regression. Models were evaluated using hazard ratios and Akaike information criterion. Receiver operating characteristic curve area under the curve was also estimated using Harrell's and Uno's C indices (HI and UI, respectively). One hundred and twenty-eight patients were evaluated (median age 72.1years). Mean tumor diameter was 2.4 ± 0.9cm. LTP was observed in nine (7%) patients. Analysis showed that decreased estimated margin size as measured by first quartile (Q1; 25th percentile), maximum, and average ablative margin metrics was significantly associated with risk of LTP. For every one millimeter increase in Q1, maximum, and mean ablative margin, the hazard of LTP increased 67% (HR: 1.67; 95% CI = 1.25-2.20, UI = 0.93, HI = 0.77), 32% (HR: 1.32; 95% CI 1.09-1.60; UI = 0.93; HI = 0.76), and 48% (HR: 1.48; 95% CI 1.18-1.85; UI = 0.83; HI = 0.75), respectively. Prospectively generated ablative margin estimates can be used to predict the risk of local tumor progression following microwave ablation of small renal masses. LEVEL OF EVIDENCE 3: Retrospective cohort study.

Autonomous Vehicles as Viewed by Future Users in Poland

The article discusses the issue of how potential users perceive automated and autonomous vehicle (AV) technology, emphasizing that its sophistication and reliability are crucial for the safety of driving vehicles with a level of automation starting from the third degree. Safety plays a significant role in determining public acceptance of autonomous vehicles. Without the acceptance of potential users and their willingness to use smart electric vehicles, it is challenging to talk about the rapid implementation of autonomous vehicles, despite their undeniable benefits. The article presents an analysis of survey results regarding public opinion in Poland on this matter. The survey utilized various methods, including CAWI surveys, Focus Group Interviews (FGI), and Individual In-depth Interviews (IDI). The CAWI survey involved 1067 respondents in Poland, with a 95% confidence level and a maximum margin of error of 3%, representing a representative sample of the Polish population aged 16 and above. The article examines issues that illustrate respondents’ acceptance levels concerning perceived security and trust in AVs. The obtained results are compared with opinions from surveys conducted in other countries. Additionally, the article attempts to identify reasons for the low assessment of the technologies among respondents and proposes measures to boost confidence in automated and autonomous vehicles.

Semi-supervised learning with constrained virtual support vector machines for classification of remote sensing image data

We introduce two semi-supervised models for the classification of remote sensing image data. The models are built upon the framework of Virtual Support Vector Machines (VSVM). Generally, VSVM follow a two-step learning procedure: A Support Vector Machines (SVM) model is learned to determine and extract labeled samples that constitute the decision boundary with the maximum margin between thematic classes, i.e., the Support Vectors (SVs). The SVs govern the creation of so-called virtual samples. This is done by modifying, i.e., perturbing, the image features to which a decision boundary needs to be invariant. Subsequently, the classification model is learned for a second time by using the newly created virtual samples in addition to the SVs to eventually find a new optimal decision boundary. Here, we extend this concept by (i) integrating a constrained set of semi-labeled samples when establishing the final model. Thereby, the model constrainment, i.e., the selection mechanism for including solely informative semi-labeled samples, is built upon a self-learning procedure composed of two active learning heuristics. Additionally, (ii) we consecutively deploy semi-labeled samples for the creation of semi-labeled virtual samples by modifying the image features of semi-labeled samples that have become semi-labeled SVs after an initial model run. We present experimental results from classifying two multispectral data sets with a sub-meter geometric resolution. The proposed semi-supervised VSVM models exhibit the most favorable performance compared to related SVM and VSVM-based approaches, as well as (semi-)supervised CNNs, in situations with a very limited amount of available prior knowledge, i.e., labeled samples.

Prediction of the thermal behavior of multi-walled carbon nanotubes-CuO-CeO2 (20-40-40)/water hybrid nanofluid using different types of regressors and evolutionary algorithms for designing the best artificial neural network modeling

For conducting an analysis of the experimental data, it is imperative to establish a mathematical correlation between the input and output variables. This entails executing a curve fitting or regression procedure on the data, for which numerous methodologies exist. Within the scope of present investigation, the design variables encompass the solid volume fraction (φ) and temperature. Thermal conductivity (TC) of MWCNT-CuO-CeO2 (20-40-40)/water hybrid nanofluid (HNF) is also the objective function. Ten different types of regressors are utilized for regression operations which are Multiple Linear Regression (MLR), Decision Tree (D-Tree), Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), Extreme Learning Machine (ELM), Radial Basis Function (RBF), Adaptive Neuro-Fuzzy Inference System (ANFIS), Gaussian Process Regression (GPR), Multivariate Polynomial Regression (MPR) and Group Method of Data Handling (GMDH). Once the governing equations linking the design variables and the objective functions have been established, these equations can be employed to forecast the simulation data. By substituting the above input values into the equations, we can calculate the corresponding output values for the TC of the HNF. The results obtained from the MPR algorithm are compared to the experimental data. For the GPR, MLR, D-Tree, ELM, MPR, MLP, RBF, SVM, ANFIS, and GMDH algorithms, the maximum margin of error is found to be 0.031, 0.02579, 0.028946, 0.033889, 0.01568, 0.02515, 0.03485, 0.03, 0.0385, and 0.0178, respectively. Moreover, the kernel density estimation diagram indicates the gap between experimental data and data predicted by regression algorithms. Finally, it is evident that the MPR algorithm demonstrates to have a reduced residual dispersion, with the residuals approaching zero.

Escalation of Growth and Yield in Mungbean by Sink Manipulation: An Approach for Minimizing Pod Picking Episode

Farmers’ frequently experience difficulties with their mungbean (indeterminate type) crops harvests due to continuous picking that prolong the pod-picking episode and cause an economic crisis. To solve these issues, deflowering strategies (sink manipulation) were employed in this study following the randomized complete block design. A series of deflowering strategies were started from 40 days after sowing (DAS) to 55 DAS; resulting reduced pod production as well as pod picking episode (3 to 4 times) with 6.8-36.8% seed yield compared to control. The minimum seed yield reduction was 6.8%; deflowering at 55 DAS; with the maximum gross margin Tk.112,800 ha−1. Considering relative yield, yield reduction, and gross margin, 50 or 55 days produced flower (which would be matured within 60-65 DAS) could be considered for obtaining the economic seed yield.
 Bangladesh Agron. J. 2023, 26(1): 48-55

Maximum margin and global criterion based-recursive feature selection

In this research paper, we aim to investigate and address the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. We identify two main challenges associated with these methods. Firstly, the feature ranking criterion utilized in these approaches is inconsistent with the maximum-margin theory. Secondly, the computation of the criterion is performed locally, lacking the ability to measure the importance of features globally. To overcome these challenges, we propose a novel feature ranking criterion called Maximum Margin and Global (MMG) criterion. This criterion utilizes the classification margin to determine the importance of features and computes it globally, enabling a more accurate assessment of feature importance. Moreover, we introduce an optimal feature subset evaluation algorithm that leverages the MMG criterion to determine the best subset of features. To enhance the efficiency of the proposed algorithms, we provide two alpha seeding strategies that significantly reduce computational costs while maintaining high accuracy. These strategies offer a practical means to expedite the feature selection process. Through extensive experiments conducted on ten benchmark datasets, we demonstrate that our proposed algorithms outperform current state-of-the-art methods. Additionally, the alpha seeding strategies yield significant speedups, further enhancing the efficiency of the feature selection process.

Growth faults and avalanches: Reconstructing Paleoarchean basins in the Pilbara and Kaapvaal cratons

Four new volcano-sedimentary complexes (VSC's), respectively c. 3510, 3460, 3430, and 3320 Ma old, are identified in the East Strelley, Coongan, and Kelly belts of the East Pilbara craton and compared with the extraordinarily complete c. 3450 Ma Buck Reef-VSC in the southern African Kaapvaal craton. The VSC’s reveal an intricate relationship between volcanic deposition, sedimentation, development of syndepositional fault arrays, both extensional and contractional, and magmatism. The geometry and kinematics of these fault systems were analyzed after restoring the tilt of the stratigraphic sequences back to the depositional horizontal. The growth fault arrays are interpreted to have been generated by lack of lateral support of depositional basin margin prisms as known from present-day deltas and passive margins. This ‘basin margin collapse’ scenario for deformation and kinematics of the topmost section of the crust relies on topographic relief combined with vertical crustal oscillation. The relationship between supracrustal collapse and coeval deformation on deeper-seated detachments within the basement of the Pilbara remains as yet unsolved.The restoration corroborates the (semi-)circular basin architecture we proposed in 2017, which preceded, and is unrelated to, the present-day configuration of granitoid complexes and greenstone belts. The new findings also assess an early, syndepositional presence of the east–west Warrawoona Lineament as a major dividing line of as yet unknown structural character between two areas of basin superposition.For the Coonterunah Subgroup a multistorey architecture is established: the Table Top/Coucal-VSC with its near-water level chert top is overlain by regularly bedded Double Bar Basalt. The ensemble is truncated by the newly introduced tectono-stratigraphic Bergamina Unit, interpreted as a mega-avalanche emplaced somewhere between 3496 and 3466 Ma, possibly time-equivalent to the Duffer Fm.The crustal depths of the detachments below the (water-level) tops of all VSC’s identified, in other words the thicknesses of the VSC’s, are used as proxy for determining minimum basin centre depths ranging from 1000 to 3800 m. The greatest depth was reached in the North and South Coongan Basins, where voluminous bimodal volcanism of the Duffer Fm, maximum subsidence and deposition rates resulted in maximum basin margin instability.

Support vector machine with eagle loss function

SVM utilizes the hinge loss function and maximum margin to find the separating hyperplane. In SVM, only the boundary instances/support vectors confine the separating hyperplane, making it susceptible to noisy samples near the decision boundary. This work proposes a novel noise-robust eagle loss function and presents Eagle-SVM based on the proposed loss function. The formulation of the eagle loss function was motivated by examining the state-of-the-art loss assignment policy. It allocates the loss value as per instance significance. The more important instances are assigned higher loss values, whereas those corresponding to outliers and noise are assigned lower loss values. The experiments were conducted on the benchmark datasets downloaded from the UCI repository to compare the performance of the proposed variant of SVM with hinge loss SVM, pinball loss SVM, ϵ-pinball loss SVM, SVM-CL, relabel SVM, 2medianSVM and 2meanSVM. The experimental results demonstrate that the eagle loss SVM outperforms all the state-of-the-art variants of SVM and is robust due to the incorporation of the novel loss assignment policy.

A comprehensive experimental study on thermal conductivity of ZrO2-SiC /DW hybrid nanofluid for practical applications: Characterization, preparation, stability, and developing a new correlation

This study mainly intended to identify changes in the thermal conductivity of distilled water (DW) because of the addition of Zirconium oxide (ZrO2) and Silicon carbide (SiC) nanoparticles. Keeping this in view, the study considered hybrid nanofluid samples developed with the help of ZrO2 (dp: 20 nm)-SiC (dp: 45––60 nm) nanoparticles. Initially, the research involved conducting XRD, TEM, EDX and FESEM tests which allowed for conducting phase and structural analysis and also facilitated the study of nanoparticles’ microstructure. In the next step, a magnetic stirrer and ultrasonic vibrator were used in sequential steps for dispersing and homogenizing Nanomaterials in distilled water. The volume concentration (φ) was kept between 0.025 and 0.1 % during the synthesis of samples. Then the samples were checked to evaluate their thermal conductivity through the transient hot wire method. In this way, the thermal conductivity of all samples was evaluated for temperatures between 20 and 60 °C. The results indicated a positive association of the thermal conductivity of nanofluid with parameters like temperature and solid volume fraction. It was noted that ZrO2-SiC/DW hybrid nanofluid depicted a nearly 25.75 % increase in thermal conductivity at a 0.1 % volume fraction of nanoparticles and a temperature of 60 °C. The value of the thermal conductivity ratio of ZrO2-SiC/DW was determined using the proposed mathematical correlation. The fitting method was applied to experimental data which depicted the R-Square value of 0.9906 which is considerably high. It was found that the proposed equation gave an acceptable value of the maximum margin of deviation (i.e.,1.15 %).

Data augmentation and refinement for recommender system: A semi-supervised approach using maximum margin matrix factorization

Collaborative filtering (CF) has become a popular method for developing recommender systems (RSs) where ratings of a user for new items are predicted based on her past preferences and available preference information of other users. Despite the popularity of CF-based methods, their performance is often greatly limited by the sparsity of observed entries. In this study, we explore the data augmentation and refinement aspects of Maximum Margin Matrix Factorization (MMMF), a widely accepted CF technique for rating predictions, which has not been investigated before. We exploit the inherent characteristics of MMMF to assess the confidence level of algorithm’s prediction of individual rating and propose a semi-supervised approach for rating augmentation based on self-training. We hypothesize that any CF algorithm’s predictions with low confidence are due to some deficiency in the training data and hence, the performance of the algorithm can be improved by adopting a systematic data augmentation strategy. We iteratively use some of the ratings predicted with high confidence to augment the training data and remove low-confidence entries through a refinement process. By repeating this process, the system learns to improve prediction accuracy. Our method is experimentally evaluated on several state-of-the-art CF algorithms and leads to informative rating augmentation, improving the performance of the baseline approaches.

Maximal Margin Support Vector Machine for Feature Representation and Classification.

High-dimensional small sample size data, which may lead to singularity in computation, are becoming increasingly common in the field of pattern recognition. Moreover, it is still an open problem how to extract the most suitable low-dimensional features for the support vector machine (SVM) and simultaneously avoid singularity so as to enhance the SVM's performance. To address these problems, this article designs a novel framework that integrates the discriminative feature extraction and sparse feature selection into the support vector framework to make full use of the classifiers' characteristics to find the optimal/maximal classification margin. As such, the extracted low-dimensional features from high-dimensional data are more suitable for SVM to obtain good performance. Thus, a novel algorithm, called the maximal margin SVM (MSVM), is proposed to achieve this goal. An alternatively iterative learning strategy is adopted in MSVM to learn the optimal discriminative sparse subspace and the corresponding support vectors. The mechanism and the essence of the designed MSVM are revealed. The computational complexity and convergence are also analyzed and validated. Experimental results on some well-known databases (including breastmnist, pneumoniamnist, colon-cancer, etc.) show the great potential of MSVM against classical discriminant analysis methods and SVM-related methods, and the codes can be available on https://www.scholat.com/laizhihui.