Predict Class Labels Research Articles

Heart Failure Predictive Analysis Using Decision Tree Classification

With an average age of 28 compared to Western countries, India's young population accounts for half of heart attacks in South Asia, which happen to people under 52. Autopsy reports, which identify the actual cause of death, frequently concentrate on sudden deaths in young adults that have no apparent reason or warning signs. Fat accumulation in the blood vessels of the heart is the cause of abrupt, unexpected natural deaths. The heart stops beating and loses blood as a result of these arteries narrowing or blocking. The body may exhibit subtle symptoms prior to abrupt death, such as shortness of breath, palpitations, tightness in the chest, and chest discomfort. A decision tree classification is a death dataset model that generates labelled classes at leaf nodes and makes judgments at edges to predict class labels for subsequent records. The purpose of the proposed paper study is to predict abrupt natural deaths, which are frequently brought on by smoking, by using regression analysis, a statistical technique that establishes the relationship between independent and dependent variables. The experiment's outcome, which looks at how Artificial Neural Networks (ANN) may be used to forecast heart failure, shows five records out of 50,000 patients from different hospitals. Perceptron’s, both single- and multi-layer, were used to gather patient information. Keywords: Artificial Neural Network, Linear Regression Analysis, Sudden and Unexpected Natural Deaths etc.

Exploiting data diversity in multi-domain federated learning

Federated learning (FL) is an evolving machine learning technique that allows collaborative model training without sharing the original data among participants. In real-world scenarios, data residing at multiple clients are often heterogeneous in terms of different resolutions, magnifications, scanners, or imaging protocols, and thus challenging for global FL model convergence in collaborative training. Most of the existing FL methods consider data heterogeneity within one domain by assuming same data variation in each client site. In this paper, we consider data heterogeneity in FL with different domains of heterogeneous data by raising the problems of domain-shift, class-imbalance, and missing data. We propose a method, multi-domain FL as a solution to heterogeneous training data from multiple domains by training robust vision transformer model. We use two loss functions, one for correctly predicting class labels and other for encouraging similarity and dissimilarity over latent features, to optimize the global FL model. We perform various experiments using different convolution-based networks and non-convolutional Transformer architectures on multi-domain datasets. We evaluate the proposed approach on benchmark datasets and compare with the existing FL methods. Our results show the superiority of the proposed approach which performs better in term of robust FL global model than the exiting methods.

An improve unsupervised discretization using optimization algorithms for classification problems

This paper addresses the classification problem in machine learning, focusing on predicting class labels for datasets with continuous features. Recognizing the critical role of discretization in enhancing classification performance, the study integrates equal width binning (EWB) with two optimization algorithms: the bat algorithm (BA), referred to as EB, and the whale optimization algorithm (WOA), denoted as EW. The primary objective is to determine the optimal technique for predicting relevant class labels. The paper emphasizes the significance of discretization in data preprocessing, offering a comprehensive approach that combines discretization techniques with optimization algorithms. An investigative study was undertaken to assess the efficiency of EB and EW by evaluating their classification performance using Naive Bayes and K-nearest neighbor algorithms on four continuous datasets sourced from the UCI datasets. According to the experimental findings, the suggested EB has a major effect on the accuracy, recall, and F-measure of data classification. The classification performance using EB outperforms other existing approaches for all datasets.

Contrast Agent Dynamics Determine Radiomics Profiles in Oncologic Imaging.

The reproducibility of radiomics features extracted from CT and MRI examinations depends on several physiological and technical factors. The aim was to evaluate the impact of contrast agent timing on the stability of radiomics features using dynamic contrast-enhanced perfusion CT (dceCT) or MRI (dceMRI) in prostate and lung cancers. Radiomics features were extracted from dceCT or dceMRI images in patients with biopsy-proven peripheral prostate cancer (pzPC) or biopsy-proven non-small cell lung cancer (NSCLC), respectively. Features that showed significant differences between contrast phases were identified using linear mixed models. An L2-penalized logistic regression classifier was used to predict class labels for pzPC and unaffected prostate regions-of-interest (ROIs). Nine pzPC and 28 NSCLC patients, who were imaged with dceCT and/or dceMRI, were included in this study. After normalizing for individual enhancement patterns by defining seven individual phases based on a reference vessel, 19, 467 and 128 out of 1204 CT features showed significant temporal dynamics in healthy prostate parenchyma, prostate tumors and lung tumors, respectively. CT radiomics-based classification accuracy of healthy and tumor ROIs was highly dependent on contrast agent phase. For dceMRI, 899 and 1027 out of 1118 features were significantly dependent on time after contrast agent injection for prostate and lung tumors. CT and MRI radiomics features in both prostate and lung tumors are significantly affected by interindividual differences in contrast agent dynamics.

A Survey on Relational Database Based Multi Relational Classification Algorithms

Classification on real world database is an important task in data mining. Many classification algorithms can build model only for data in single flat file as input, whereas most of real-world data bases are stored in multiple tables and managed by relational database systems. As conversion of relational data from multiple tables into a single flat file usually causes many problems, development of multi relational classification algorithms becomes popular area of research interests. Relational database based multi relational classification algorithms aim to build a model that can predict class label of unknown tuple with the help of background table knowledge. This method keeps database in it normalized form without distorting structure of database. This paper presents survey of existing multi relational classification algorithms based on relational database.

Breast Cancer Classification and Predicting Class Labels Using ResNet50

Numerous studies have been conducted using Deep Learning paradigms to detect Breast Cancer. Breast cancer is a medical condition where abnormal cells in the breast grow uncontrollably, forming tumors. If not treated, these tumors can metastasize and spread to other parts of the body, potentially leading to life-threatening consequences. In the year 2020, there were approximately 2.3 million cases of breast cancer diagnosed in women, leading to around 685,000 deaths worldwide. By the close of 2020, there existed 7.8 million women who had been diagnosed with breast cancer within the preceding five years, solidifying it as the most widespread form of cancer globally. Breast cancer is observed across all countries, affecting women at various ages post-puberty, with incidence rates tending to rise in older age groups. The aim of this paper is to classify and predict the class labels of breast cancer. To achieve this, a ResNet50 model is utilized and mammography images are employed to locate cancer within the image and classify it to emphasize the affected area. The ResNet50 identifies mass regions and classifies them as either ductal carcinoma, inflammatory, triple negative or invasive cancer. The experimentation is carried out on breast cancer dataset and achieved 90.6% accuracy both for classification as well as prediction

An overview of machine learning classification techniques

Machine learning (ML) is a key component within the broader field of artificial intelligence (AI) that employs statistical methods to empower computers with the ability to learn and make decisions autonomously, without the need for explicit programming. It is founded on the concept that computers can acquire knowledge from data, identify patterns, and draw conclusions with minimal human intervention. The main categories of ML include supervised learning, unsupervised learning, semisupervised learning, and reinforcement learning. Supervised learning involves training models using labelled datasets and comprises two primary forms: classification and regression. Regression is used for continuous output, while classification is employed for categorical output. The objective of supervised learning is to optimize models that can predict class labels based on input features. Classification is a technique used to predict similar information based on the values of a categorical target or class variable. It is a valuable method for analyzing various types of statistical data. These algorithms have diverse applications, including image classification, predictive modeling, and data mining. This study aims to provide a quick reference guide to the most widely used basic classification methods in machine learning, with advantages and disadvantages. Of course, a single article cannot be a complete review of all supervised machine learning classification algorithms. It serves as a valuable resource for both academics and researchers, providing a guide for all newcomers to the field, thereby enriching their comprehension of classification methodologies.

Clustering honey samples with unsupervised machine learning methods using FTIR data.

This study utilizes Fourier transform infrared (FTIR) data from honey samples to cluster and categorize them based on their spectral characteristics. The aim is to group similar samples together, revealing patterns and aiding in classification. The process begins by determining the number of clusters using the elbow method, resulting in five distinct clusters. Principal Component Analysis (PCA) is then applied to reduce the dataset's dimensionality by capturing its significant variances. Hierarchical Cluster Analysis (HCA) further refines the sample clusters. 20% of the data, representing identified clusters, is randomly selected for testing, while the remainder serves as training data for a deep learning algorithm employing a multilayer perceptron (MLP). Following training, the test data are evaluated, revealing an impressive 96.15% accuracy. Accuracy measures the machine learning model's ability to predict class labels for new data accurately. This approach offers reliable honey sample clustering without necessitating extensive preprocessing. Moreover, its swiftness and cost-effectiveness enhance its practicality. Ultimately, by leveraging FTIR spectral data, this method successfully identifies similarities among honey samples, enabling efficient categorization and demonstrating promise in the field of spectral analysis in food science.

Concepts of statistical learning and classification in machine learning: An overview

Statistical learning theory serves as the foundational bedrock of Machine learning (ML), which in turn represents the backbone of artificial intelligence, ushering in innovative solutions for real-world challenges. Its origins can be linked to the point where statistics and the field of computing meet, evolving into a distinct scientific discipline. Machine learning can be distinguished by its fundamental branches, encompassing supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Within this tapestry, supervised learning takes center stage, divided in two fundamental forms: classification and regression. Regression is tailored for continuous outcomes, while classification specializes in categorical outcomes, with the overarching goal of supervised learning being to enhance models capable of predicting class labels based on input features. This review endeavors to furnish a concise, yet insightful reference manual on machine learning, intertwined with the tapestry of statistical learning theory (SLT), elucidating their symbiotic relationship. It demystifies the foundational concepts of classification, shedding light on the overarching principles that govern it. This panoramic view aims to offer a holistic perspective on classification, serving as a valuable resource for researchers, practitioners, and enthusiasts entering the domains of machine learning, artificial intelligence and statistics, by introducing concepts, methods and differences that lead to enhancing their understanding of classification methods.

Heterogeneous Domain Adaptation for Multistream Classification on Cyber Threat Data

Under a newly introduced setting of multistream classification, two data streams are involved, which are referred to as source and target streams. The source stream continuously generates data instances from a certain domain with labels, while the target stream does the same task without labels from another domain. Existing approaches assume that domains for both data streams are identical, which is not quite true, since data streams from different sources may contain distinct features. Indeed, they may even have different numbers of features. Furthermore, obtaining labels for every instance in a data stream is often expensive and time-consuming. Therefore, it has become an important topic to explore if classes of labeled instances from other related streams are helpful to predict the classes of unlabeled instances in a different stream. Note that domains of source and target streams may have distinct feature spaces and data distributions. Our objective is to predict class labels of data instances in the target stream by using the classifiers trained by the source stream. We propose a framework of multistream classification by using projected data from a common latent feature space, which is embedded from both source and target domains. This framework is also crucial for enterprise system defenders to detect cross-platform attacks, such as Advanced Persistent Threats (APTs). Empirical valuation and analysis on both real-world and synthetic datasets are performed to validate the effectiveness of our proposed algorithm, comparing to state-of-the-art techniques. Experimental results show that our approach significantly outperforms other existing approaches.

Few-shot classification with multisemantic information fusion network

Metric-based methods aim to predict class labels by computing the similarity between samples using distance functions, which is the mainstream approach to few-shot learning. However, the limited representational space of feature vectors and appearance variations among congenetic samples still present challenges. We propose a Multisemantic Information Fusion Network (MIFN) to address these problems. A Lower-level Feature generator (LF-generator), which is an unsupervised module, adaptively activates high-response regions of objects to introduce discriminative semantic details. Meanwhile, a Higher-level Feature extractor (HF-extractor) learns global semantic information with human cognition to minimise the impact of appearance variations. We integrate the coarse outputs of these two modules, which complement each other to jointly promote more precise predictions. Furthermore, considering the importance of prototypes, we redefine the sampling strategy of the triplet loss and utilise it as an auxiliary loss to sharpen the decision boundary at the prototype level, facilitating subsequent classification. Our experimental results demonstrate the competitiveness of our approach in both general few-shot classification (mini-ImageNet and tiered-ImageNet) and cross-domain problems (CUB, Caltech-101, Stanford-dogs, and Stanford-cars) with minimal bells and whistles.

DeepXplainer: An interpretable deep learning based approach for lung cancer detection using explainable artificial intelligence

Background and ObjectiveArtificial intelligence (AI) has several uses in the healthcare industry, some of which include healthcare management, medical forecasting, practical making of decisions, and diagnosis. AI technologies have reached human-like performance, but their use is limited since they are still largely viewed as opaque black boxes. This distrust remains the primary factor for their limited real application, particularly in healthcare. As a result, there is a need for interpretable predictors that provide better predictions and also explain their predictions. MethodsThis study introduces “DeepXplainer”, a new interpretable hybrid deep learning-based technique for detecting lung cancer and providing explanations of the predictions. This technique is based on a convolutional neural network and XGBoost. XGBoost is used for class label prediction after “DeepXplainer” has automatically learned the features of the input using its many convolutional layers. For providing explanations or explainability of the predictions, an explainable artificial intelligence method known as “SHAP” is implemented. ResultsThe open-source “Survey Lung Cancer” dataset was processed using this method. On multiple parameters, including accuracy, sensitivity, F1-score, etc., the proposed method outperformed the existing methods. The proposed method obtained an accuracy of 97.43%, a sensitivity of 98.71%, and an F1-score of 98.08. After the model has made predictions with this high degree of accuracy, each prediction is explained by implementing an explainable artificial intelligence method at both the local and global levels. ConclusionsA deep learning-based classification model for lung cancer is proposed with three primary components: one for feature learning, another for classification, and a third for providing explanations for the predictions made by the proposed hybrid (ConvXGB) model. The proposed “DeepXplainer” has been evaluated using a variety of metrics, and the results demonstrate that it outperforms the current benchmarks. Providing explanations for the predictions, the proposed approach may help doctors in detecting and treating lung cancer patients more effectively.

A Novel Learning-Based PLST Algorithm for Multi-Label Classification

In Multi-Label Classification (MLC), each data sample is characterized by multiple labels. In ML, there is no restriction on the number of classes a data sample could belong to. Various methods are proposed to construct a model to map data samples to the class labels. Transforming the MLC problem into several binary classification problems is the baseline approach, also called the binary relevance technique. As an alternative solution, the label powerset approach transforms the MLC problem into a multi-class classification problem by building a binary classifier for every label composition. However, in Ensemble Methods (EMs), multiple classifiers are consolidated to form a multi-label ensemble classifier. In this case, each classifier predicts a class label. Thereupon, the predicted class labels are joined using an ensemble method. This paper presents a neoteric EM classifier using the Ridge Regression-based Principal Label Space Transformation (RR-PLST). In the proposed model, the PLST utilizes SVD to discover correlations between the labels and data samples. Dimensionality reduction is a well-known technique to enhance the model's precision and diminish execution time. Consequently, the OPLS technique is recruited to reduce data dimensions in the proposed model. Moreover, in the proposed model, a Q-Learning method is used to amend the initially predicted labels. To demonstrate the effectiveness of the proposed model, vast experiments are conducted on the various widely used multi-label datasets. The proposed algorithm results are compared with similar algorithms by the AP, EM, HS, Macro, and Micro F1 metrics. The experimental results demonstrate the superiority of the proposed model.

Ensemble method employing quantitative biomarkers and deep learning approach from structural magnetic resonance imaging to diagnose Alzheimer’s disease

Abstract Introduction: Alzheimer’s disease (AD) is a neurodegenerative condition that impairs activities of daily living and sharply declines gross cognitive ability. Over 152 million individuals worldwide will live with the dreaded consequence of a longer lifespan by the year 2050, making it a pressing public health issue. Magnetic resonance imaging (MRI) provides excellent soft tissue contrast and helps image the brain in vivo, non-invasively. Aims and Objectives: To summarize AD’s anatomical, physiological, and pathophysiological changes and derivation of quantifiable biomarkers from MRI to develop artificial intelligence (AI) based computer-aided detection (CAD) system to classify subjects among AD, mild cognitive impairment (MCI), and cognitively normal (CN). Materials and Methods: This retrospective study uses clinical and standardized, pre-processed, quality-controlled, and quality-checked—structural MRI imaging (diagnosed/labeled) data of 1069 subjects, age, gender, and class matched, taken from Alzheimer’s disease neuroimaging initiative. A pipeline is developed to get quantified biomarkers from the assessment of (1) cortical thickness, (2) volumetric segmentation for whole brain volumes, and (3) region of interest (ROI) areas most affected in AD. A gradient boosting method is used to predict class labels. The second approach implements a convolution neural network (CNN) model comprising 3D ROI. Results: Implemented CAD system using an ensemble gradient boosting approach has demonstrated good receiver operating characteristics characteristic and yielded balanced accuracy (BA) of 82.31%, 78.52%, and 72.73%, and the CNN approach has given better results 88.44%, 82.96%, and 74.34% for classification task AD versus CN, AD versus MCI, and MCI versus CN, respectively. Conclusion: This study has used a substantially large dataset of 1069 subjects. The deep learning-based efficient and optimal CNN model has used significantly large ROI-based 3-Dimentional volume, resulting in impressive performance improvements over comparable methods. The CNN model had given higher accuracy (6.13% for AD vs. CN, 4.44% for AD vs. MCI and 1.61% for MCI vs. CN) over gradient boosting, as the model uses significantly large ROI-based 3D brain volume and an inherent capability of it in learning most discriminative features automatically. However, quantitative biomarkers derived from brain morphometry, which accesses structural changes, yield reasonable estimates over pathophysiological alterations across the brain and augment a clinician with insightful and a holistic view, resulting in higher confidence over predicated class label by CNN and is a step closer to explainable AI. Accuracy for MCI versus CN drops as these classes share similar features and characteristics and can be improved by integrating biomarkers from other MRI modalities.

IMPROVING CLASSIFICATION PERFORMANCE USING ENSEMBLE LEARNING APPROACH

The data mining techniques are used for evaluation of the data in order to find and represent the data in such manner by which the applications are becomes beneficial. Therefore, different kinds of computational algorithms and modeling’s are incorporated for analyzing the data. These computational algorithms are help to understand the data patterns and their application utility. The data mining algorithms supports supervised as well as unsupervised techniques of data analysis. This work is aimed to investigate about the supervised learning technique specifically performance improvements on classification techniques. The proposed classification model includes the multiple classifiers namely Bayesian classifier, k-nearest neighbor and the c4.5 decision tree algorithm. By nature of the outcomes and the modeling of the data these algorithms are functioning differently from each other. Thus, a weight based classification technique is introduced in this work. The weight is a combination of outcomes provided by the implemented three classifiers in terms of their predicted class labels. Using the weighted outcomes, the final class label for the input data instance is decided. The implementation of the proposed working model is performed with the help of JAVA and WEKA classes. The results obtained by experimentation of the proposed approach with the vehicle data set demonstrate the high accurate classification results. Thus, the proposed model is an effective classification technique as compared to single model implementation for classification task.

Generating post-hoc explanations for Skip-gram-based node embeddings by identifying important nodes with bridgeness

Node representation learning in a network is an important machine learning technique for encoding relational information in a continuous vector space while preserving the inherent properties and structures of the network. Recently, unsupervised node embedding methods such as DeepWalk (Perozzi et al., 2014), LINE (Tang et al., 2015), struc2vec (Ribeiro et al., 2017), PTE (Tang et al., 2015), UserItem2vec (Wu et al., 2020), and RWJBG (Li et al., 2021) have emerged from the Skip-gram model (Mikolov et al., 2013) and perform better performance in several downstream tasks such as node classification and link prediction than the existing relational models. However, providing post-hoc explanations of unsupervised embeddings remains a challenging problem because of the lack of explanation methods and theoretical studies applicable for embeddings. In this paper, we first show that global explanations to the Skip-gram-based embeddings can be found by computing bridgeness under a spectral cluster-aware local perturbation. Moreover, a novel gradient-based explanation method, which we call GRAPH-wGD, is proposed that allows the top-q global explanations about learned graph embedding vectors more efficiently. Experiments show that the ranking of nodes by scores using GRAPH-wGD is highly correlated with true bridgeness scores. We also observe that the top-q node-level explanations selected by GRAPH-wGD have higher importance scores and produce more changes in class label prediction when perturbed, compared with the nodes selected by recent alternatives, using five real-world graphs.

Instance segmentation ship detection based on improved Yolov7 using complex background SAR images

It is significant for port ship scheduling and traffic management to be able to obtain more precise location and shape information from ship instance segmentation in SAR pictures. Instance segmentation is more challenging than object identification and semantic segmentation in high-resolution RS images. Predicting class labels and pixel-wise instance masks is the goal of this technique, which is used to locate instances in images. Despite this, there are now just a few methods available for instance segmentation in high-resolution RS data, where a remote-sensing image’s complex background makes the task more difficult. This research proposes a unique method for YOLOv7 to improve HR-RS image segmentation one-stage detection. First, we redesigned the structure of the one-stage fast detection network to adapt to the task of ship target segmentation and effectively improve the efficiency of instance segmentation. Secondly, we improve the backbone network structure by adding two feature optimization modules, so that the network can learn more features and have stronger robustness. In addition, we further modify the network feature fusion structure, improve the module acceptance domain to increase the prediction ability of multi-scale targets, and effectively reduce the amount of model calculation. Finally, we carried out extensive validation experiments on the sample segmentation datasets HRSID and SSDD. The experimental comparisons and analyses on the HRSID and SSDD datasets show that our model enhances the predicted instance mask accuracy, enhancing the instance segmentation efficiency of HR-RS images, and encouraging further enhancements in the projected instance mask accuracy. The suggested model is a more precise and efficient segmentation in HR-RS imaging as compared to existing approaches.

A COMPARATIVE STUDY ON PERFORMANCE OF BASIC AND ENSEMBLE CLASSIFIERS WITH VARIOUS DATASETS

Classification plays a critical role in machine learning (ML) systems for processing images, text and high -dimensional data. Predicting class labels from training data is the primary goal of classification. An optimal model for a particular classification problem is chosen on the basis of the model's performance and execution time. This paper compares and analyses the performance of basic as well as ensemble classifiers utilizing 10 -fold cross validation and also discusses their essential concepts, advantages, and disadvantages. In this study five basic classifiers namely Naïve Bayes (NB), Multi-layer Perceptron (MLP), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF) and the ensemble of all the five classifiers along with few more combinations are compared with five University of California Irvine (UCI) ML Repository datasets and a Diabetes Health Indicators dataset from kaggle repository. To analyze and compare the performance of classifiers, evaluation metrics like Accuracy, Recall, Precision, Area Under Curve (AUC) and F-Score are used. Experimental results showed that SVM performs best on two out of the six datasets (Diabetes Health Indicators and waveform), RF performs best for Arrhythmia, Sonar, Tic-tac-toe datasets, and the best ensemble combination is found to be DT+SVM+RF on Ionosphere dataset having respective accuracies 72.58%, 90.38%, 81.63%, 73.59%, 94.78% and 94.01% and the proposed ensemble combinations outperformed over the conventional models for few datasets.

AttentionMNIST: a mouse-click attention tracking dataset for handwritten numeral and alphabet recognition

Multiple attention-based models that recognize objects via a sequence of glimpses have reported results on handwritten numeral recognition. However, no attention-tracking data for handwritten numeral or alphabet recognition is available. Availability of such data would allow attention-based models to be evaluated in comparison to human performance. We collect mouse-click attention tracking data from 382 participants trying to recognize handwritten numerals and alphabets (upper and lowercase) from images via sequential sampling. Images from benchmark datasets are presented as stimuli. The collected dataset, called AttentionMNIST, consists of a sequence of sample (mouse click) locations, predicted class label(s) at each sampling, and the duration of each sampling. On average, our participants observe only 12.8% of an image for recognition. We propose a baseline model to predict the location and the class(es) a participant will select at the next sampling. When exposed to the same stimuli and experimental conditions as our participants, a highly-cited attention-based reinforcement model falls short of human efficiency.

Calibrated simplex-mapping classification.

We propose a novel methodology for general multi-class classification in arbitrary feature spaces, which results in a potentially well-calibrated classifier. Calibrated classifiers are important in many applications because, in addition to the prediction of mere class labels, they also yield a confidence level for each of their predictions. In essence, the training of our classifier proceeds in two steps. In a first step, the training data is represented in a latent space whose geometry is induced by a regular (n - 1)-dimensional simplex, n being the number of classes. We design this representation in such a way that it well reflects the feature space distances of the datapoints to their own- and foreign-class neighbors. In a second step, the latent space representation of the training data is extended to the whole feature space by fitting a regression model to the transformed data. With this latent-space representation, our calibrated classifier is readily defined. We rigorously establish its core theoretical properties and benchmark its prediction and calibration properties by means of various synthetic and real-world data sets from different application domains.