Feature Classification Methods Research Articles

Timely ICU Outcome Prediction Utilizing Stochastic Signal Analysis and Machine Learning Techniques with Readily Available Vital Sign Data.

The ICU is a specialized hospital department that offers critical care to patients at high risk. The massive burden of ICU-requiring care requires accurate and timely ICU outcome predictions for alleviating the economic and healthcare burdens imposed by critical care needs. Existing research faces challenges such as feature extraction difficulties, low accuracy, and resource-intensive features. Some studies have explored deep learning models that utilize raw clinical inputs. However, these models are considered non-interpretable black boxes, which prevents their wide application. The objective of the study is to develop a new method using stochastic signal analysis and machine learning techniques to effectively extract features with strong predictive power from ICU patients' real-time time series of vital signs for accurate and timely ICU outcome prediction. The results show the proposed method extracted meaningful features and outperforms baseline methods, including APACHE IV (AUC = 0.750), deep learning-based models (AUC = 0.732, 0.712, 0.698, 0.722), and statistical feature classification methods (AUC = 0.765) by a large margin (AUC = 0.869). The proposed method has clinical, management, and administrative implications since it enables healthcare professionals to identify deviations from prognostications timely and accurately and, therefore, to conduct proper interventions.

Relative Feature Classification Method for Diabetic Retinopathy Detection from Scanned Eye Images

Relative Feature Classification Method for Diabetic Retinopathy Detection from Scanned Eye Images

Machine learning-based hyperspectral wavelength selection and classification of spider mite-infested cucumber leaves.

Two-spotted spider mite (Tetranychus urticae) is an important greenhouse pest. In cucumbers, heavy infestations lead to the complete loss of leaf assimilation surface, resulting in plant death. Symptoms caused by spider mite feeding alter the light reflection of leaves and could therefore be optically detected. Machine learning methods have already been employed to analyze spectral information in order to differentiate between healthy and spider mite-infested leaves of crops such as tomatoes or cotton. In this study, machine learning methods were applied to cucumbers. Hyperspectral data of leaves were recorded under controlled conditions. Effective wavelengths were identified using three feature selection methods. Subsequently, three supervised machine learning algorithms were used to classify healthy and spider mite-infested leaves. All combinations of feature selection and classification methods yielded accuracy of over 80%, even when using ten or five wavelengths. These results suggest that machine learning methods are a powerful tool for image-based detection of spider mites in cucumbers. In addition, due to the limited number of wavelengths, there is also substantial potential for practical application.

Exploring Feature Selection and Classification Techniques to Improve the Performance of an Electroencephalography-Based Motor Imagery Brain-Computer Interface System.

The accuracy of classifying motor imagery (MI) activities is a significant challenge when using brain-computer interfaces (BCIs). BCIs allow people with motor impairments to control external devices directly with their brains using electroencephalogram (EEG) patterns that translate brain activity into control signals. Many researchers have been working to develop MI-based BCI recognition systems using various time-frequency feature extraction and classification approaches. However, the existing systems still face challenges in achieving satisfactory performance due to large amount of non-discriminative and ineffective features. To get around these problems, we suggested a multiband decomposition-based feature extraction and classification method that works well, along with a strong feature selection method for MI tasks. Our method starts by splitting the preprocessed EEG signal into four sub-bands. In each sub-band, we then used a common spatial pattern (CSP) technique to pull out narrowband-oriented useful features, which gives us a high-dimensional feature vector. Subsequently, we utilized an effective feature selection method, Relief-F, which reduces the dimensionality of the final features. Finally, incorporating advanced classification techniques, we classified the final reduced feature vector. To evaluate the proposed model, we used the three different EEG-based MI benchmark datasets, and our proposed model achieved better performance accuracy than existing systems. Our model's strong points include its ability to effectively reduce feature dimensionality and improve classification accuracy through advanced feature extraction and selection methods.

A Multimodal Music Feature Extraction and Classification Method Based on Deep Learning

A Multimodal Music Feature Extraction and Classification Method Based on Deep Learning

Advanced Ensemble Classifier Techniques for Predicting Tumor Viability in Osteosarcoma Histological Slide Images

Background: Osteosarcoma is considered as the primary malignant tumor of the bone, emanating from primitive mesenchymal cells that form osteoid or immature bone. Accurate diagnosis and classification play a key role in management planning to achieve improved patient outcomes. Machine learning techniques may be used to augment and surpass existing conventional methods towards an analysis of medical data. Methods: In the present study, the combination of feature selection techniques and classification methods was used in the development of predictive models of osteosarcoma cases. The techniques include L1 Regularization (Lasso), Recursive Feature Elimination (RFE), SelectKBest, Tree-based Feature Importance, while the following classification methods were applied: Voting Classifier, Decision Tree, Naive Bayes, Multi-Layer Perceptron, Random Forest, Logistic Regression, AdaBoost, and Gradient Boosting. Some model assessment was done by combining metrics such as accuracy, precision, recall, F1 score, AUC, and V score. Results: The combination of the Tree-Based Feature Importance for feature selection and Voting Classifier with Decision Tree Classifier proved to be giving a higher performance compared to all other combinations, where such combinations helped in correct classification of positive instances and wonderful minimization of false positives. Other combinations also gave significant performances but slightly less effective, for example, L1 Regularization with the Voting Classifier, RFE with the Voting Classifier. Conclusion: This work presents strong evidence that advanced machine learning with ensemble classifiers and robust feature selection can result in overall improvement of the diagnostic accuracy and robustness for the classification of osteosarcoma. Research on class imbalance and computational efficiency will be its future research priority.

Digitization Of Tulu Handwritten Scripts- A Literature Survey

Applications for handwritten script digitization include automated form processing, archival preservation, document digitization, handwriting recognition software, and historical document research. The performance of the recognition algorithms, the complex nature of the script, and the handwriting quality all affect how accurate the digitization is. Significant research on handwritten text recognition in scripts like Latin, Chinese, Arabic, and Japanese is reported. Still in its infancy, the work described on handwritten Indic scripts necessitates extensive research in this area. This thorough analysis offers an open view of different feature extraction and classification methods for the offline and online identification of handwritten Indic scripts.The primary objective of this paper is to explore the accuracy and efficiency of recognition systems by analyzing several state-of-the-art studies and comparing and evaluating various techniques for Tulu script handwritten character recognition. This paper aims to describe various advancements reported over the last few decades in the field of handwritten scripts recognition.

Optimization method of dynamic reconfiguration in virtual power plants

With the continuous expansion of distributed energy resources (DERs), virtual power plants (VPPs) have emerged as an efficient solution for their aggregation and management. This study proposes a dynamic reconfiguration method for VPPs, addressing the problem of optimally aggregating DERs within a VPP. To enhance DER participation, an innovative membership rewards mechanism is introduced. Furthermore, we develop a method for DER feature extraction and classification to deeply understand their performance. We also assess DERs' willingness to participate, which is the precondition for effective aggregation. The core of our method is an optimized strategy for multi-stage dynamic planning of VPPs, designed to accommodate the dynamic evolution of DERs and electricity markets conditions, and formulated as a two-layer model to offer optimal solutions for DERs aggregation. Numerical simulations validate the superiority of our method in economic benefits and operational efficiency of VPP, highlighting our contributions to enhance the feasibility and efficiency of VPP aggregation through multi-stage planning, dynamic adaptability, and strategic incentives.

Machine learning-based wood anatomy identification: towards anatomical feature recognition

Summary Computer vision-based wood identification has been successfully applied to recognize tree species using digital images of wood sections or surfaces. However, this image-to-species approach can only recognize a limited number of species due to two main reasons: 1) the lack of a good reference database requiring high-quality standardized images from multiple individuals of hundreds or even thousands of traded timber species, and 2) species not included in the reference database cannot be identified without expert knowledge. Another bottleneck is that the feature extraction process used by these species recognition approaches is a black box, thereby creating a discrepancy between machine learning features and wood anatomical features. This discrepancy prevents wood anatomists from understanding how these machine-learning algorithms work. Here, we survey currently existing methods used in feature extraction, classification, and deep learning methods applied in wood identification along with their pitfalls and opportunities. As an example of how the field could move forward, we launch the idea of building an image-to-features-to-species identification approach based on microscopic wood images as well as text files comprising wood anatomical descriptions. If we can manage machine learning-based algorithms to recognize the main wood anatomical traits that experts use to identify species in a (semi-)automated way, this would boost wood identification in two ways: (1) extensive reference databases for each species would become less crucial as the databases are ordered at the trait level, (2) timber identification would become more feasible for species that have not yet been included in the reference database as long as wood anatomical descriptions are available.

Heart Sound Signals Classification with Image Conversion Employed

The number of patients with cardiovascular diseases worldwide is increasing rapidly, while medical resources are increasingly scarce. Heart sound classification, as the most direct means of discovering cardiovascular diseases, is attracting the attention of researchers around the world. Although great progress has been made in heart sound classification in recent years, most of them are based on traditional statistical feature methods and temporal dimension features. These traditional temporal dimension feature representation and classification methods cannot achieve good classification accuracy. This paper proposes a new partition attention module and Fusionghost module, and the entire network framework is named PANet. Without segmentation of the heart sound signal, the heart sound signal is converted into a bispectrum and input into the proposed framework for feature extraction and classification tasks. The network makes full use of multi-scale feature extraction and feature map fusion, improving the network feature extraction ability. This paper conducts a comprehensive study of the performance of different network parameters and different module numbers, and compares the performance with the most advanced algorithms currently available. Experiments have shown that for two classification problems (normal or abnormal), the classification accuracy rate on the 2016 PhysioNet/CinC Challenge database reached 97.89%, the sensitivity was 96.96%, and the specificity was 98.85%.

Improved empirical mode decomposition bagging RCSP combined with Fisher discriminant method for EEG feature extraction and classification

BackgroundTraditional Common Spatial Pattern (CSP) algorithms for Electroencephalogram (EEG) signal classification are sensitive to noise and can produce low accuracy in small sample datasets. New methodTo solve the problem, an improved Empirical Mode Decomposition (EMD) Bagging Regularized CSP (RCSP) algorithm is proposed. It filters EEG signals through improved EMD, inhibits high-frequency noise, retains effective information in the characteristic frequency band, and uses Bagging algorithm for data reconstruction. Feature extraction is performed with regularization of spatial patterns and Fisher linear discriminant analysis for feature classification. T-test is used for classification. ResultsThe improved EMD Bagging RCSP algorithm has improved accuracy and robustness compared to CSP and its derivatives. The average classification rate is increased by about 6%, demonstrating the effectiveness and correctness of the proposed algorithm.Comparison with existing methods: The proposed algorithm outperforms CSP and its derivatives by retaining effective information and inhibiting high-frequency noise in small sample EEG datasets. ConclusionsThe proposed EMD Bagging RCSP algorithm provides a reliable and effective method for EEG signal classification and can be used in various applications, including brain-computer interfaces and clinical EEG diagnosis.

Enhanced multimodal biometric recognition systems based on deep learning and traditional methods in smart environments.

In the field of data security, biometric security is a significant emerging concern. The multimodal biometrics system with enhanced accuracy and detection rate for smart environments is still a significant challenge. The fusion of an electrocardiogram (ECG) signal with a fingerprint is an effective multimodal recognition system. In this work, unimodal and multimodal biometric systems using Convolutional Neural Network (CNN) are conducted and compared with traditional methods using different levels of fusion of fingerprint and ECG signal. This study is concerned with the evaluation of the effectiveness of proposed parallel and sequential multimodal biometric systems with various feature extraction and classification methods. Additionally, the performance of unimodal biometrics of ECG and fingerprint utilizing deep learning and traditional classification technique is examined. The suggested biometric systems were evaluated utilizing ECG (MIT-BIH) and fingerprint (FVC2004) databases. Additional tests are conducted to examine the suggested models with:1) virtual dataset without augmentation (ODB) and 2) virtual dataset with augmentation (VDB). The findings show that the optimum performance of the parallel multimodal achieved 0.96 Area Under the ROC Curve (AUC) and sequential multimodal achieved 0.99 AUC, in comparison to unimodal biometrics which achieved 0.87 and 0.99 AUCs, for the fingerprint and ECG biometrics, respectively. The overall performance of the proposed multimodal biometrics outperformed unimodal biometrics using CNN. Moreover, the performance of the suggested CNN model for ECG signal and sequential multimodal system based on neural network outperformed other systems. Lastly, the performance of the proposed systems is compared with previously existing works.

Genetic Clustering Algorithm-Based Feature Selection and Divergent Random Forest for Multiclass Cancer Classification Using Gene Expression Data

AbstractComputational identification and classification of clinical disorders gather major importance due to the effective improvement of machine learning methodologies. Cancer identification and classification are essential clinical areas to address, where accurate classification for multiple types of cancer is still in a progressive stage. In this article, we propose a multiclass cancer classification model that categorizes the five different types of cancers using gene expression data. To perform efficient analysis of the available clinical data, we propose feature selection and classification methods. We propose a genetic clustering algorithm (GCA) for optimal feature selection from the RNA-gene expression data, consisting of 801 samples belonging to the five major classes of cancer. The proposed feature selection method reduces the 1621 gene expressions into a cluster of 21 features. The optimum feature set acts as input data to the proposed divergent random forest. Based on the features computed, the proposed classifier categorizes the data samples into 5 different classes of cancers, including breast cancer, colon cancer, kidney cancer, lung cancer, and prostate cancer. The proposed divergent random forest provided performance improvisation in terms of accuracy with 95.21%, specificity with 93%, and sensitivity with 94.29% which outperformed all the other existing multiclass classification algorithms.

Extracting Dynamic Information of Temporal Clinical Data to Predict the Outcome in Critically Ill Patients.

Outcome prediction is essential for the administration and treatment of critically ill patients. For those patients, clinical measurements are continuously monitored and the time-varying data contains rich information for assessing the patients' status. However, it is unclear how to capture the dynamic information effectively. In this work, multiple feature extraction methods, i.e. statistical feature classification methods and temporal modeling methods, such as recurrent neural network (RNN), were analyzed on a critical illness dataset with 18415 cases. The experimental results show when the dimension increases from 10 to 50, the RNN algorithm is gradually superior to the statistical feature classification methods with simple logic. The RNN model achieves the largest AUC value of 0.8463. Therefore, the temporal modeling methods are promising to capture temporal features which are predictive of the patients' outcome and can be extended in more clinical applications.

An Affective EEG Analysis Method Without Feature Engineering

Emotional electroencephalography (EEG) signals are a primary means of recording emotional brain activity.Currently, the most effective methods for analyzing emotional EEG signals involve feature engineering and neuralnetworks. However, neural networks possess a strong ability for automatic feature extraction. Is it possible to discardfeature engineering and directly employ neural networks for end-to-end recognition? Based on the characteristics of EEGsignals, this paper proposes an end-to-end feature extraction and classification method for a dynamic self-attention network(DySAT). The study reveals significant differences in brain activity patterns associated with different emotions acrossvarious experimenters and time periods. The results of this experiment can provide insights into the reasons behind thesedifferences.

DDoS Attack Detection Using ML/DL Techniques

The increasing integration of IoT devices has heightened the vulnerability of networks to sophisticated and evolving cyber threats, particularly DDoS attacks, which can severely disrupt service availability. Leveraging machine learning algorithms, this research aims to enhance the proactive identification of anomalous patterns indicative of DDoS attacks within IoT environments. By employing a combination of feature extraction, classification, and ensemble learning methods, the proposed model demonstrates promising results in distinguishing between normal network behaviour and malicious activities associated with DDoS attacks. The study contributes to the advancement of security measures in IoT networks, offering a proactive and adaptive solution to mitigate the impact of DDoS attacks, ultimately bolstering the resilience of interconnected systems in the evolving landscape of cyber threats. This study presents a novel approach for the detection of Distributed Denial of Service (DDoS) attacks in Internet of Things (IoT) networks using machine learning techniques.

The application of machine learning on brain imaging features of different narcolepsy subtypes.

Narcolepsy is a central hypersomnia disorder, and differential diagnoses between its subtypes can be difficult. Hence, we applied machine learning to analyze the positron emission tomography (PET) data of patients with type 1 or type 2 narcolepsy, and patients with type 1 narcolepsy and comorbid schizophrenia, to construct predictive models to facilitate the diagnosis. This is a retrospective and prospective case-control study of adolescent and young adult patients with type 1 or type 2 narcolepsy, and type 1 narcolepsy and comorbid schizophrenia. All participants received 18-F-fluorodeoxy glucose PET, sleep studies, neurocognitive tests, sleep questionnaires, and human leukocyte antigen typing. The collected PET data were analyzed by feature selections and classification methods in machine learning to construct predictive models. A total of 314 participants with narcolepsy were enrolled; 204 had type 1 narcolepsy, 90 had type 2 narcolepsy, and 20 had type 1 narcolepsy and comorbid schizophrenia. We used three filter methods for feature selection followed by a comparative analysis of classification methods. To apply a small number of regions of interest (ROI) and high classification accuracy, the Naïve Bayes classifier with the Term Variance as feature selection achieved the goal with only three ROIs (left basal ganglia, left Heschl, and left striatum) and produced an accuracy of higher than 99%. The accuracy of our predictive model of PET data are promising and can aid clinicians in the diagnosis of narcolepsy subtypes. Future research with a larger sample size could further refine the predictive model of narcolepsy.

A Learning Approach for The Identification of Network Intrusions Based on Ensemble XGBoost Classifier

The limitation of signature-based Intrusion Detection systems has given rise for the popularity of Machine learning (ML) approaches r for building such intrusion detection systems (IDSs). ML is a sub-filed of Artificial Intelligence that enables algorithms to learn from data and its applications have been widely accepted and used in many domains. To achieve a promising ML-based model that can identify attacks and intrusions in networks and the cyber space, different stages of machine learning approach like pre-processing, attribute selection, model building, hyper parameter tuning can be very important. CICIDS2017 intrusion dataset was used for all the experimentations. This study focuses on building cyber threat detection model based on the ensemble feature selection and classification method. Innovative approaches were used for the analysis and pre-processing of the dataset. Thereafter, XGboost algorithm was used for selecting relevant features from the default input attributes in each of the captures. Thereafter, the reduced features were employed in the identification of cyber intrusions. The average accuracy achieved in the 8 captures of the dataset is 98% while precision is 0.98. Also, recall is 0.98, f1-score is 0.98 while AUC ROC score is 0.99. The study concluded that XGBoost-based model was able to achieve promising results based on the proper dataset encoding, feature importance-based feature selection and tuning of the algorithm for intrusion identification.

Optimization of the visual communication path of data news in the context of the Internet

Abstract Visual news belongs to a kind of data news, which uses emerging technology to bring users a new reading experience and improve the news dissemination effect. In this paper, we utilize the self-attention mechanism and BiLSTM model to extract the content of data news documents and select and classify the audio features of data news by the AdaBoost algorithm. ResNet50 is used as the backbone network, combined with multiple residual unit modules for news multi-scale image feature extraction, and the text, audio and image features of the data news are fused by constructing a multimodal feature adaptive fusion model to further optimize the visual display of the data news. This paper verifies the model’s effectiveness for the data news visualization technique through multiple perspectives, including training loss curve, performance comparison, and ablation experiment. The results show that the loss value of the model based on the Self-Attention-BiLSTM model for news text feature extraction is 0.211 after 150 iterations. The AdaBoost-based news audio feature classification method has an average classification accuracy of 97.56% for the positive diagonal when the noise is raised from 0dB to 30 dB. By adding the residual unit module to the ResNet50 backbone network, the accuracy of the multi-scale image feature extraction model has been improved by 2.77% compared to the single backbone network. The information age requires the full integration of technology and news and combining the corresponding Internet platform for the visual display of data news in order to promote the expansion of the visual communication path of data news.

A Time–Frequency Residual Convolution Neural Network for the Fault Diagnosis of Rolling Bearings

A time–frequency residual convolution neural network (TFRCNN) was proposed to identify various rolling bearing fault types more efficiently. Three novel points about TFRCNN are presented as follows: First, by constructing a double-branch convolution network in the time domain and the frequency domain, the respective features in the time domain and the frequency domain were extracted to ensure the rich and complete feature representation of raw data sources. Second, specific residual structures were designed to prevent learning degradation of the deep network, and global average pooling was adopted to improve the network’s sparsity. Third, TFRCNN was better than the other models in terms of prediction accuracy, robustness, generalization ability, and convergence. The experimental results demonstrate that the prediction accuracy rate of TFRCNN, trained using mixing load data, reached 98.88 to 99.92% after optimizing the initial learning rate and choosing the optimizer and loss function. It was verified that TFRCNN can adaptively learn to extract deep fault features, accurately identify bearing fault conditions, and overcome the limitations of classical shallow feature extraction and classification methods, as well as common convolution neural networks. Hence, this investigation revealed TFRCNN’s potential for bearing fault diagnosis in practical engineering applications.