Machine Learning Classification Algorithms Research Articles

Comparison of Machine Learning Algorithms for Species Family Classification using DNA Barcode

Classifying plant species within the Liliaceae and Amaryllidaceae families presents inherent challenges due to the complex genetic diversity and overlapping morphological traits among species. This study explores the difficulties in accurate classification by comparing 11 supervised learning algorithms applied to DNA barcode data, aiming to enhance the precision of species family classification in these taxonomically intricate plant families. The ribulose-1,5-bisphosphate carboxylase-oxygenase large sub-unit (rbcL) gene, selected as a DNA barcode locus for plants, is used to represent species within the Amaryllidaceae and Liliaceae families. The experimental results demonstrate that nearly all tested models achieve accurate species classification into the appropriate families, with an accuracy rate exceeding 97%, except for the Naïve Bayes model. Regarding computational time, the Random Forest model requires significantly more time for training than other models. Regarding memory usage, the Least Squares Support Vector Machine with a polynomial kernel, and Regularized Logistic Regression consume more memory than other models. These machine learning models exhibit strong concordance with NCBI's classifications when predicting families using the test dataset, effectively categorizing species into the Amaryllidaceae and Liliaceae families.

PMFCC Features for Music Classification Using the Modified KNN Algorithm

From ancient period Music is a integral part of human life. People prefered to listen Music while relaxing. All over the world nowadays music is used as supporting medication for healing mental illness and many other diseases. The origin of Indian Music is Indian Classical Raga, having a melodious combination of Rhythm and notes. There are various users like music-composers, e-learners, music therapists are frequently retrieving Indian classical Raga based music. The vast retrieval of Raga based music made it necessary to classify Indian music on Raga. This paper proposes an a new algorithm to classify an Indian Music using Raga information which further will be useful for song recommendation, personalizing collection, and musicologists for various purpose.
 In this paper, the combined Pitch and MFCC based PMFCC features are extracted and processed by Modified K Nearest Neighbor algorithm. The performance of PMFCC and Pitch Class Distribution features is compared using traditional machine learning classification algorithms and Modified Variant K Nearest Neighbor (MVKNN). The PMFCC features outperformed with the Modified KNN algorithm. The accuracy of PMFCC features with Modified KNN algorithm is found 96.11% for our Our dataset and 93.65% for Compmusic standard dataset.

A combined neural network mechanism for categorizing the normal and cancer cells

The dangerous form of acute lymphocytic leukemia damages the bone marrow tissue and white blood cells. Unformed white blood cells multiply and exchange healthy cells in the bone marrow. Everything spreads fast and, if not noticed, can be dangerous in some months. As a result, computer assisted diagnosis of acute lymphocytic leukemia has the possible to protect several lives, but it needs a high-precision categorization of malignant cells, that is difficult due to the graphical similarity of malignant and normal cells. Though deep convolutional neural networks and the classic machine learning algorithms have exposed excellent results in classifying blood cell images, they have not been able to make effective use of the long-term correlation between some important image attributes and image labeling. This study introduced Long short-term memory (LSTM) to solve this difficulty. This study actually combines VGG16 neural networks and LSTM, which provide the VGG16-LSTM framework, which improves the recognizing of image content and learns the structural features of images, as well as initiate big data training in clinical image processing. The transfer learning approach was used to transfer pre-trained weight parameters to the VGG16 area in the ImageNet database, and the custom loss function was used to train and integrate the network quickly and accurately with the weight parameters. Experimental findings reveal that the suggested network approach is more relevant and effective in categorizing cancer cell images than other existing methods.

Efficient Multiple Channels EEG Signal Classification Based on Hierarchical Extreme Learning Machine

The human brain can be seen as one of the most powerful processors in the world, and it has a very complex structure with different kinds of signals for monitoring organics, communicating to neurons, and reacting to different information, which allows large developments in observing human sleeping, revealing diseases, reflecting certain motivations of limbs, and other applications. Relative theory, algorithms, and applications also help us to build brain-computer interface (BCI) systems for different powerful functions. Therefore, we present a fast-reaction framework based on an extreme learning machine (ELM) with multiple layers for the ElectroEncephaloGram (EEG) signals classification in motor imagery, showing the advantages in both accuracy of classification and training speed compared with conventional machine learning methods. The experiments are performed on software with the dataset of BCI Competition II with fast training time and high accuracy. The final average results show an accuracy of 93.90% as well as a reduction of 75% of the training time as compared to conventional deep learning and machine learning algorithms for EEG signal classification, also showing its prospects of the improvement of the performance of the BCI system.

Research on Feature Extraction of Underwater Acoustic Target Radiation Noise Based on Machine Learning Algorithm

Underwater acoustic target recognition is a very important technology in the field of underwater acoustics, with great economic and military value. Feature extraction technology for underwater acoustic target radiation noise signals is the key to achieving acoustic target recognition. This study aims at the feature extraction task of acoustic targets and extracts 10 types of 252-dimensional feature vectors from three domains: time domain, frequency domain, and auditory domain. Through 7 machine learning algorithms for classification and recognition experiments, the experimental results show that the recognition performance of the ensemble classifier is much better than that of a single classifier. For different types of features, this study combines three ensemble learning algorithms and feature selection algorithms to select the original 252-dimensional features. The feature selection experiment shows that the wrapper feature selection algorithm has the best effect, and the feature vector dimension can be reduced to 40 dimensions. The recognition accuracy rate is not less than 92.8%, which provides feature extraction guidance for acoustic target recognition based on feature extraction.

Automatic identification of schizophrenia employing EEG records analyzed with deep learning algorithms.

Electroencephalography is a method of detecting and analyzing electrical activity in the brain. This electrical activity can be recorded and processed to aid in the clinical diagnosis of mental disorders. In this study, a novel system for classifying schizophrenia patients from EEG recordings is presented. The developed algorithm decomposes the EEG signals into a system of radial basis functions using the method of fuzzy means. This decomposition helps to obtain the information from the various electrodes of the EEG and allows separating between healthy controls and patients with schizophrenia. The proposed method has been compared with classical machine learning algorithms, such as, K-Nearest Neighbor, Adaboost, Support Vector Machine, and Bayesian Linear Discriminant Analysis. The results show that the proposed method obtains the highest values in terms of balanced accuracy, recall, precision and F1 score, close to 93% in all cases. The model developed in this study can be implemented in brain activity analysis systems that help in the prediction of patients with schizophrenia.

Classification of chronic kidney disease based on machine learning techniques

<span>In recent years, indescribable suffering from various kidney diseases has been experienced by people all over the world. The situation has been significantly worse because of chronic kidney disease (CKD). Only through an early diagnosis of CKD may kidney disease be hinder in its early stages from progressing. However, it is easier to detect the chronic kidney disease with the aid of machine learning (ML) classifier algorithms sooner than any other existing methods. The present work proposes an approach for potentially predicting CKD infection while considering patient health dataset information into consideration, employing nine distinct ML algorithms; random forest (RF), naïve bayes (NB), support vector machine (SVM), decision tree (DT), logistic regression (LR), extreme gradient boosting (XGB), adaptive boosting (ADB), k-nearest neighbors (KNN), and neural network (NN). Machine learning algorithms had been utilized and conducted in four experiments, then they were compared using five performance measures; F1-score, precision, accuracy, recall and run time are used to evaluate the performance. Results had shown that AdaBoost (ADA) outperformed other techniques with achieved accuracy of 99.17%.</span>

Comparative analysis of machine learning algorithms for land use and land cover classification using google earth engine platform

This study evaluates different machine learning algorithms for land use and land cover classification using Sentinel-2 Level-1C data with 10-meter spatial resolution. The algorithms include Random Forest (RF), Classification and Regression Trees (CART), Support Vector Machines (SVM), Naive Bayes (NB), and Gradient Boosting (GTB). The classification was performed on the Google Earth Engine (GEE) platform. Results highlight variations in land cover classification among algorithms, with RF and CART identifying cropland as dominant, SVM indicating fallow land presence, NB revealing significant forest cover, and GTB emphasizing cropland importance. Accuracy assessment was performed to evaluate the performance of the algorithms, considering metrics such as producer accuracy, consumer accuracy, overall accuracy, and Kappa coefficient. SVM demonstrates the highest overall accuracy and agreement with reference data. The study contributes insights for land management and planning, and GEE proves valuable for LULC classification.
 
 

Research on filtering and classification method for white-feather broiler sound signals based on sparse representation

Aiming at the problems in the existing white-feather broiler sound signal classification research, such as not considering the information and requirements in the real engineering application scenarios, not finding new applicable sound features, not providing the basis for the selection of classification learners, and the problems in the existing white-feather broiler sound signal filtering research, such as not carrying out in-depth research, not considering the signal characteristics, not analyzing the filtering effects in detail. Therefore, in this paper, the authors cleverly combined four methods of signal filtering, signal classification, machine learning, and sparse representation to propose a filtering and classification method for white-feather broiler sound signals based on sparse representation. Specifically, in terms of signal filtering, the signal characteristics of the white-feather broiler sound signal was carefully analyzed, a combination of noise reduction processing and signal reconstruction was newly proposed, and three classic and effective approximation algorithms were adopted, then the optimal filtering method of “using OMPA for noise reduction processing, and using 50-atom OMPA for signal reconstruction” was obtained. In terms of signal classification, in addition to the time-frequency domain and Mel-Frequency Cepstral Coefficients (abbr. MFCCs), time-frequency parameter features from sparse representations were newly extracted, and a total of 60-dimensional sound features were calculated on the frame signals, thus the data set was created. Feature engineering was performed on the data set, finally, the high-quality data set was obtained. Several common machine learning classification algorithms were used to train classification learners on the data set, and random forest with better performance was selected for parameter optimization. The parameter-optimized classification learner achieved the highest average prediction accuracy of 94.09%. Majority voting was newly proposed to process the prediction results to get the required signal classification result. On this basis, a new definition of classification accuracy suitable for white-feather broiler sound signals was newly proposed. Test results in real engineering application scenarios show that, the classification accuracy achieved by the proposed method on unknown white-feather broiler sound signals is about 88.89%. Compared with the existing research, the optimal filtering method considers the signal characteristics for the first time and achieves good filtering effects. The trained classification learner obtains excellent prediction effects and achieves good classification effects on several real sound types. This study is an important supplement to existing research on animal sound signal processing and classification, and provides important reference for the subsequent white-feather broiler health monitoring research.

Venous thromboembolic disease in admitted blunt trauma patients: what matters?

BackgroundVenous thromboembolic events (VTE) are a significant cause of morbidity and mortality following traumatic injury. We examined demographic characteristics, chemoprophylaxis, and outcomes of VTE patients with blunt trauma requiring hospitalization.MethodsA retrospective review of adult blunt trauma hospitalizations with and without VTE between 2012 and 2019 was conducted. Deaths in the emergency department were excluded. Univariate and multivariable analyses, including machine learning classification algorithms for VTE, were performed.ResultsOf 10,926 admitted adult blunt trauma patients, 177 had VTE events. VTE events occurred at a median of 6 [IQR 3–11] days, with 7.3% occurring within 1 day of admission. VTE patients were more often male, and more often underwent surgery. They had higher injury severity as well as longer intensive care unit and hospital lengths of stay. While VTE occurred throughout the spectrum of injury severity, 27.7% had low injury severity (ISS < = 9). In multivariable analyses, both heparin and enoxaparin had reduced adjusted odds ratios for VTE.ConclusionApproximately 7.3% of VTE events occurred within one day of admission. A substantial proportion of VTE events occurred in patients with low injury severity (ISS < = 9). Subcutaneous unfractionated heparin and enoxaparin chemoprophylaxis were both inversely associated with VTE. These findings underscore the need for vigilance for VTE identification in blunt trauma patients throughout their hospitalization and VTE prevention efforts.

Forecasting Liver Disorders with Machine Learning Models

Liver disorders encompass a spectrum of ailments that impact the liver, a crucial organ responsible for a variety of vital bodily functions. These functions encompass metabolic processes, detoxification, protein synthesis, and the production of bile. Liver maladies can arise from various sources, such as viral infections (e.g., hepatitis), excessive alcohol consumption, conditions related to obesity (like non-alcoholic fatty liver disease), autoimmune conditions, genetic predisposition, or exposure to toxins. Common signs and symptoms may encompass fatigue, jaundice, abdominal discomfort, and digestive problems. In our study, we gather data and employ five distinct machine learning classification algorithms: Random Forest, Decision Tree, Naïve Bayes, K-Nearest Neighbor, and XG Boost. After constructing models and evaluating their performance, we observed that XG Boost achieved an impressive accuracy rate of 99.8%.

Simulating reservoir capillary pressure curves using image processing and classification machine learning algorithms applied to petrographic thin sections

Reservoir rock porosity and capillary pressure data are fundamental parameters to understand the physical properties of rocks. Porosity, which shows the rock's void fraction to its bulk volume, can be measured by s techniques such as He-porosimetry, mercury injection capillary pressure (MICP) analysis, point counting analysis, and image analysis. Image analysis has for many years been used to obtain relevant data from digital microscopic images. Segmentation of images is an important technique used to partition an image into distinctive components to extract useful data. When an image is segmented, it is simplified, making it easier to understand its component parts. In this research, two-dimensional (2D) rock thin section image processing is initially applied to determine porosity. To achieve this, the K-means clustering algorithm was used to automatically segment and measure the digital rock porosity. In this regard, one hundred and nine samples were selected from approximately one thousand 2D petrographic thin-section images of the Dorood Oilfield reservoir rocks and were digitally processed and evaluated. The porosity values estimated from the image analysis agree with the porosity derived from whole-rock core analysis with a correlation coefficient of 67 %. Moreover, petrographic studies distinguished five microfacies, which relate to lagoon, shoal, mid and outer ramp depositional environments associated with a carbonate homoclinal ramp. In addition. three distinct Hydraulic Flow Units(HFUs) were determined based on K-means clustering by applying the Elbow method. Based on those clusters, permeability was estimated from HFU porosity distributions with high correlation coefficient (R = 90 %). Pore-throat size distributions and Pc curves were then estimated from thin-section image analysis based on the Pittman equations for different mercury saturation percentages. The estimated Pc curves derived from image analyses show an acceptable correlation with SCAL-derived Pc curves. Comparison between RT/HFU and depositional settings show that RT1/HFU1 belongs to the lagoon and outer ramp depositional settings, RT2/HFU2 belongs to shoal and mid carbonate ramp environments and RT3/HFU3 belongs to a shoal environment.

Optimizing Machine Learning Algorithms for Heart Disease Classification and Prediction

According to the World Health Organization (WHO), cardiovascular disease is one of the leading causes of death worldwide. Thus, the prevention of this kind of illness is considered as a huge human health challenge. Additionally, the diagnostic process often involves a combination of clinical examination, laboratory tests, and other diagnostic procedures, which can be complex and time-consuming. However, advances in medical technology and research have led to improved methods for diagnosing heart disease, which can help to improve patient outcomes. Furthermore, Machine Learning (ML) methods have shown promise in helping to improve the diagnosis of heart disease. Each method requires specific parameters to produce good results. In this paper, we propose a diagnosis support system based on optimized Machine Learning algorithms, which is Artificial Neural Network (ANN), Support Vector Machine (SVM), K_Nearest Neighbour (KNN), Naive Bayes (NB), and Decision Tree (DT) to analyze the major cardiovascular risk factors, such as age, gender, high blood pressure, etc. To train and validate the ML models, a medical dataset of 558 patients with atherosclerosis is used. In this work, we achieved a 96.67% as promising accuracy level for the atherosclerosis prediction with ANN.

Slip Risk Prediction Using Intelligent Insoles and a Slip Simulator

Slip and fall accidents are the leading cause of injuries for all ages, and for fatal injuries in adults over 65 years. Various factors, such as floor surface conditions and contaminants, shoe tread patterns, and gait behavior, affect the slip risk. Moreover, the friction between the shoe outsoles and the floor continuously changes as their surfaces undergo normal wear over time. However, continuous assessment of slip resistance is very challenging with conventional measurement techniques. This study addresses this challenge by introducing a novel approach that combines sensor fusion technology and machine learning techniques to create intelligent insoles designed for fall risk prediction. In addition, a state-of-the-art slip simulator, capable of mimicking the foot’s motion during a slip, was developed and utilized for the assessment of slipperiness between various shoes and floor surfaces. Data acquisition involved the collection of pressure data and three-axial accelerations using instrumented shoe insoles, complemented by friction coefficient measurements via the slip simulator. The collected dataset includes four types of shoes, three floor surfaces, and four surface conditions, including dry, wet, soapy, and oily. After preprocessing of the collected dataset, the simulator was used to train five different machine learning algorithms for slip risk classification. The trained algorithms provided promising results for slip risk prediction for different conditions, offering the potential to be employed in real-time slip risk prediction and safety enhancement.

Quantitative assessment of Land use/land cover changes in a developing region using machine learning algorithms: A case study in the Kurdistan Region, Iraq

The identification of land use/land cover (LULC) changes is important for monitoring, evaluating, and preserving natural resources. In the Kurdistan region, the utilization of remotely sensed data to assess the effectiveness of machine learning algorithms (MLAs) for LULC classification and change detection analysis has been limited. This study monitors and analyzes LULC changes in the study area from 1991 to 2021 using a quantitative approach with multi-temporal Landsat imagery. Five MLAs were applied: Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN), K-Nearest Neighbor (KNN), and Extreme Gradient Boosting (XGBoost). The results showed that the RF algorithm produced the most accurate maps of the three-decade study period, accompanied by a high kappa coefficient (0.93–0.97) compared with the SVM (0.91–0.95), ANN (0.91–0.96), KNN (0.92–0.96), and XGBoost (0.92–0.95) algorithms. Consequently, the RF classifier was implemented to categorize all obtainable satellite images. Socioeconomic changes throughout these transition periods were revealed by the change detection results. Rangeland and barren land areas decreased by 11.33 % (−402.03 km2) and 6.68 % (−236.8 km2), respectively. The transmission increases of 13.54 % (480.18 km2), 3.43 % (151.74 km2), and 0.71 % (25.22 km2) occurred in agricultural land, forest, and built-up areas, respectively. The outcomes of this study contribute significantly to LULC monitoring in developing regions, guiding stakeholders to identify vulnerable areas for better land use planning and sustainable environmental protection.

Optimizing application and algorithm complexity of machine learning methods in traffic classification

As the Internet continues to evolve, it has become crucial for Internet Service Providers to analyze and classify their network flows. This enables them to identify suspicious activities and offer personalized services. Machine learning has been extensively deployed in network traffic classification, presenting a promising but challenging avenue. One of the primary challenges in applying machine learning to network traffic classification is reducing the computational resources used in training and implementing the model. By devising lightweight algorithms, traffic flow can be classified using fewer computational resources, effectively curtailing the escalating costs associated with the growing volume and transmission rate of traffic. In this study, we compare the performance of three classic machine learning algorithms - logistic regression, support vector machine, and shallow feedforward neural network - by employing them to classify mobile countries of origin, aiming to use as few features as possible. Remarkably, by utilizing only four features from the dataset, these three algorithms achieved an accuracy rate of 89%. This underscores the potential for computational and cost efficiency in network traffic classification with optimized machine learning methods.

Research on the diagnosis of corona virus disease 2019(COVID-19) based on machine-learning

In recent years, the Corona Virus Disease 2019(COVID-19) has brought a huge impact on people's daily life and the normal operation of society, and as machine learning research deepens, this technology could help detect viruses such as the novel coronavirus. According to this, how to accurately, quickly and effectively analyze and classify laboratory results with multiple indicators through the method of machine learning is the object of this paper. In order to explore the classification performance of various machine learning classification algorithms on laboratory results, linear and non-linear methods were used respectively to analyze and classify the laboratory results. In linear analysis, distance discriminant and fisher discriminant were used to explore the classification effect of linear classification on laboratory results. The non-linear analysis mainly used Adaptive Boosting(AdaBoost) and Random Forest algorithm which are widely used to test the classification effect under the influence of multiple indexes. In this paper, python and other tools were used to classify samples of different combinations by using the idea of cross validation. By comparing the running time and detection accuracy, it was found that Adaboost algorithm is applicable in most cases and was a relatively fast and accurate classification method. In addition, Random Forest algorithm had similar accuracy, but it might have better performance on a large data set.

Classification of present faults in rotating machinery based on time and frequency domain feature extraction

The need for an effective and efficient maintenance process increases with the level of complexity of modern rotating machinery. This paper introduces a methodology for transforming raw vibration signals into adequate inputs for machine learning classification algorithms in order to identify present faults in rotating machinery. It complements a previous study by the same authors, which covers the processing of vibrational signals by determining the optimal sampling frequency and using appropriate filters for the raw data. The first part of this study covers feature extraction using time and frequency-domain techniques and correlation matrices are plotted to determine which extracted features are significantly connected and what is the level of their correlation. The study continues with the use of Neighborhood Component Analysis (NCA) where weight factors of the features are calculated in terms of recognizing the present rotating machinery faults. Only the ones with the highest level of importance have been used as input for the classification algorithms. The MATLAB Add-in Classification Learner has been used for training and testing various classification algorithms. K-nearest neighbors classifier (KNN), Support vector machines (SVM), and Wide Neural Network (NN) showed the highest accuracy in distinguishing ten different fault conditions. For this case study, the MaFaulda vibration dataset has been used and ten operating conditions have been considered: normal, imbalance, horizontal misalignment, vertical misalignment, and three faults in the underhang bearing and the overhang bearing.

Binding affinity predictions with hybrid quantum-classical convolutional neural networks

Central in drug design is the identification of biomolecules that uniquely and robustly bind to a target protein, while minimizing their interactions with others. Accordingly, precise binding affinity prediction, enabling the accurate selection of suitable candidates from an extensive pool of potential compounds, can greatly reduce the expenses associated to practical experimental protocols. In this respect, recent advances revealed that deep learning methods show superior performance compared to other traditional computational methods, especially with the advent of large datasets. These methods, however, are complex and very time-intensive, thus representing an important clear bottleneck for their development and practical application. In this context, the emerging realm of quantum machine learning holds promise for enhancing numerous classical machine learning algorithms. In this work, we take one step forward and present a hybrid quantum-classical convolutional neural network, which is able to reduce by 20% the complexity of the classical counterpart while still maintaining optimal performance in the predictions. Additionally, this results in a significant cost and time savings of up to 40% in the training stage, which means a substantial speed-up of the drug design process.

Machine learning algorithms in microbial classification: a comparative analysis

This research paper presents an overview of contemporary machine learning methodologies and their utilization in the domain of healthcare and the prevention of infectious diseases, specifically focusing on the classification and identification of bacterial species. As deep learning techniques have gained prominence in the healthcare sector, a diverse array of architectural models has emerged. Through a comprehensive review of pertinent literature, multiple studies employing machine learning algorithms in the context of microbial diagnosis and classification are examined. Each investigation entails a tabulated presentation of data, encompassing details about the training and validation datasets, specifications of the machine learning and deep learning techniques employed, as well as the evaluation metrics utilized to gauge algorithmic performance. Notably, Convolutional Neural Networks have been the predominant selection for image classification tasks by machine learning practitioners over the last decade. This preference stems from their ability to autonomously extract pertinent and distinguishing features with minimal human intervention. A range of CNN architectures have been developed and effectively applied in the realm of image classification. However, addressing the considerable data requirements of deep learning, recent advancements encompass the application of pre-trained models using transfer learning for the identification of microbial entities. This method involves repurposing the knowledge gleaned from solving alternate image classification challenges to accurately classify microbial images. Consequently, the necessity for extensive and varied training data is significantly mitigated. This study undertakes a comparative assessment of various popular pre-trained CNN architectures for the classification of bacteria. The dataset employed is composed of approximately 660 images, representing 33 bacterial species. To enhance dataset diversity, data augmentation is implemented, followed by evaluation on multiple models including AlexNet, VGGNet, Inception networks, Residual Networks, and Densely Connected Convolutional Networks. The results indicate that the DenseNet-121 architecture yields the optimal performance, achieving a peak accuracy of 99.08%, precision of 99.06%, recall of 99.00%, and an F1-score of 98.99%. By demonstrating the proficiency of the DenseNet-121 model on a comparatively modest dataset, this study underscores the viability of transfer learning in the healthcare sector for precise and efficient microbial identification. These findings contribute to the ongoing endeavors aimed at harnessing machine learning techniques to enhance healthcare methodologies and bolster infectious disease prevention practices.