Machine Learning Classification Methods Research Articles

Prediction and Detection of Cervical Malignancy Using Machine Learning Models.

Human papillomavirus and other predicting factors are responsible causing cervical cancer, and early prediction and diagnosis is the solution for preventing this condition. The objective is to find out and analyze the predictors of cervical cancer and to study the issues of unbalanced datasets using various Machine Learning (ML) algorithm-based models. A multi-stage sampling strategy was used to recruit 501 samples for the study. The educational intervention was the video-assisted counseling which is consisted of two educational methods: a documentary film and face-to- face interaction with women followed by reminders. Following the collection of baseline data from these subjects, they were encouraged to undergo Pap smear screening. Women having abnormal Pap tests were sent for biopsy. Machine learning classification methods such as Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), Multi-layer Perceptron (MLP) and Naive Bayes(NB) were used to evaluate the unbalanced input and target datasets. Merely 398 women out of 501 showed an interest to participate in the study, but only 298 stated a willingness for cervical screening. Atypical malignant cells were discovered on the cervix of 26 women who had abnormal pap tests. These women had guided for further tests, such as a cervical biopsy, and seven women had been diagnosed with cervical cancer. LR in models 1, 2, and 4 showed 88% to 94% sensitivity with 84% to 89% accuracy, respectively for cervical cancer prediction, whereas DT in models 3, 5, and 6 algorithms exhibited 83% to 84% sensitivity with 84% to 88% accuracy, respectively. The NB and LR algorithms produced the highest area under the ROC curve for testing dataset, but all models performed similarly for training data. In current study , Logistic Regression and Decision Tree algorithms were identified as the best-performed ML algorithm classifiers to detect the significant predictors.

The House Price Prediction Using Machine Learning Algorithm: The Case of Jinan, China

House prices increase substantially in China from 1998. Because of expensive house prices, most Chinese people have only one chance to select suitable houses. Therefore, building a house price prediction model based on housing conditions is significant for customers to make decisions. This paper collects the estate market data of Jinan city from the HomeLink website and performs several feature selection algorithms to get critical features for house price prediction. The paper compares the classical machine learning methods for the problem, including Multiple Linear Regression, Random Forest, and Catboost. After cross-validation tests, the CatBoost, algorithm with the lowest Mean Square Error (MSE) is regarded as the most accurate algorithm to predict house prices. The analytic results show that the house price is dominated by the location features such as area and block.

Experimental analysis of machine learning methods to detect Covid-19 from x-rays

To automate the detection of covid-19 patients most have proposed deep learning neural networks to classify patients using large databases of chest x-rays. Very few used classical machine learning methods. Machine learning methods may require less computational power and perform well if the data set is small. We experiment with classical machine learning methods on three different data sources varying in size from 55 to almost 4000 samples. We experiment with four feature extraction methods of Gabor, SURF, LBP, and HOG. Backpropagation neural networks and k-nearest neighbor classifiers are combined using one of the four combining methods of bagging, RSM, ARCx4 boosting and Ada-boosting. Results show that using the proper feature extraction and feature selection methods very high performance can be reached using simple backpropagation neural network classifiers. Regardless of combiner method used, the best classification rate achieved was 99.06% for the largest data set, and 100% for the smallest data set.

Support Vector Machine for Predicting Candlestick Chart Movement on Foreign Exchange

Foreign Exchange, commonly called Forex, is a form of investment in the non-real sector in great demand. Forex is a marketplace that specializes in foreign exchange trading. Technology advancements have made it easy to monitor investment conditions in real time and present them in an easyto - understand graphical form. As a result, predictions are closely related to investment, starting from market sentiment and economic conditions to technical matters. One of the Artificial Intelligence methods that can be used in classifying is the Support Vector Machine (SVM). SVM is a machine learning classification method based on the Structural Risk Minimization (SRM) principle to find the best hyperplane that separates two classes in the input space that determines the classification decision function by minimizing empirical risk. This study used candlestick patterns to predict foreign exchange chart movements using the Support Vector Machine (SVM) classification method. The purpose of this study was to measure the accuracy of the Support Vector Machine method in making predictions using candlestick patterns so that it can assist traders in making decisions in forex trading. The accuracy level obtained from the data classification results reached 90.72% with a precision of 87.69%. With a relatively good level of accuracy, the Support Vector Machine (SVM) method can be used to predict chart movements in foreign exchange using candlesticks to indicate the current trend’s direction.

A Hybrid Model Based on Deep Features and Ensemble Learning for the Diagnosis of COVID-19: DeepFeat-E

COVID-19, which has been declared a pandemic disease, has affected the lives of millions of people and caused a major epidemic. Despite the development of vaccines and vaccination to prevent the transmission of the disease, COVID-19 case rates fluctuate worldwide. Therefore, rapid and reliable diagnosis of COVID-19 disease is of critical importance. For this purpose, a hybrid model based on transfer learning methods and ensemble classifiers is proposed in this study. In this hybrid approach, called DeepFeat-E, the diagnosis process is performed by using deep features obtained from transfer learning models and ensemble classifiers consisting of classical machine learning methods. To test the proposed approach, a dataset of 21,165 X-ray images including 10,192 Normal, 6012 Lung Opacity, 1345 Viral Pneumonia and 3616 COVID-19 were used. With the proposed approach, the highest accuracy was achieved with the deep features of the DenseNet201 transfer learning model and the Stacking ensemble learning method. Accordingly, the test accuracy was 90.17%, 94.99% and 94.93% for four, three and two class applications, respectively. According to the results obtained in this study, it is seen that the proposed hybrid system can be used quickly and reliably in the diagnosis of COVID-19 and lower respiratory tract infections.

HYBRIDIZATION OF THE NAIVE BAYES CLASSIFICATION METHOD IN THE FRESHWATER FISH SEED SELLER CLASSIFICATION MODEL

Freshwater fish seed sellers play several roles in the supply chain process in the freshwater fish farming business. The role of the seller of freshwater fish seeds in this process is to distribute fish seeds which are one of the upstream sources in the supply chain process. Freshwater fish cultivators must select competent freshwater fish seed sellers so the supply chain process can run well. A large number of freshwater fish seed sellers in the market remind freshwater fish cultivators to choose the quality of the freshwater fish seed seller in terms of seed quality, low prices, shipping that can reach many areas, ergonomic packaging, and others. This study proposes Hybrid Naïve Bayes Classifiers (HNBCs) as a machine learning method for classification. This study aimed to compare the seed seller classification method in which the appropriate pattern of seed seller was identified by hybridization of Naïve Bayes Classifiers (NBCs), and then the researchers conducted performance appraisal and evaluation. The results are beneficial for freshwater fish cultivators and researchers which will enable them to formulate their plans according to the predicted results. The proposed method has produced significant results by achieving a training data accuracy of 82.61% and the testing data accuracy of 73.91%.

Deep learning based depression detection from social media text

Depression perception be a complex task on social media Complex properties associated with mental illness. There was a recent development in this area of research; social media platforms have established themselves as growing popularity. A basic part of people`s daily life. Social media platforms and their users share goals Relationships where the user's personal life is reflected on these platforms at several levels. Aside from the complexity associated with detecting mental illness through social media platforms, it is inherently difficult to obtain an enough annotated training data, so a supervised deep learning approach such as deep neural networks the implementation has not yet been widely implemented. We tried to find them for these reasons. The most effective deep learning model of the architectures selected in the previous architecture Achievements of supervised learning methods. The selected model will be used for recognition online users showing depression. Due to the limited amount of unstructured text data Extracted from social media text. Recently, Deep learning has been effectively used to a variety of application challenges, including stock market forecasting, traffic flow and accident risk forecasting, and mental disease diagnosis. Furthermore, deep learning has been used to predict sadness on social media and has outperformed classical machine learning method.

A Review of Machine Learning Algorithms for Retinal Cyst Segmentation on Optical Coherence Tomography

Optical coherence tomography (OCT) is an emerging imaging technique for diagnosing ophthalmic diseases and the visual analysis of retinal structure changes, such as exudates, cysts, and fluid. In recent years, researchers have increasingly focused on applying machine learning algorithms, including classical machine learning and deep learning methods, to automate retinal cysts/fluid segmentation. These automated techniques can provide ophthalmologists with valuable tools for improved interpretation and quantification of retinal features, leading to more accurate diagnosis and informed treatment decisions for retinal diseases. This review summarized the state-of-the-art algorithms for the three essential steps of cyst/fluid segmentation: image denoising, layer segmentation, and cyst/fluid segmentation, while emphasizing the significance of machine learning techniques. Additionally, we provided a summary of the publicly available OCT datasets for cyst/fluid segmentation. Furthermore, the challenges, opportunities, and future directions of artificial intelligence (AI) in OCT cyst segmentation are discussed. This review is intended to summarize the key parameters for the development of a cyst/fluid segmentation system and the design of novel segmentation algorithms and has the potential to serve as a valuable resource for imaging researchers in the development of assessment systems related to ocular diseases exhibiting cyst/fluid in OCT imaging.

Online payment fraud: from anomaly detection to risk management

Online banking fraud occurs whenever a criminal can seize accounts and transfer funds from an individual’s online bank account. Successfully preventing this requires the detection of as many fraudsters as possible, without producing too many false alarms. This is a challenge for machine learning owing to the extremely imbalanced data and complexity of fraud. In addition, classical machine learning methods must be extended, minimizing expected financial losses. Finally, fraud can only be combated systematically and economically if the risks and costs in payment channels are known. We define three models that overcome these challenges: machine learning-based fraud detection, economic optimization of machine learning results, and a risk model to predict the risk of fraud while considering countermeasures. The models were tested utilizing real data. Our machine learning model alone reduces the expected and unexpected losses in the three aggregated payment channels by 15% compared to a benchmark consisting of static if-then rules. Optimizing the machine-learning model further reduces the expected losses by 52%. These results hold with a low false positive rate of 0.4%. Thus, the risk framework of the three models is viable from a business and risk perspective.

Application of tree-based machine learning classification methods to detect signals of fluoroquinolones using the Korea Adverse Event Reporting System (KAERS) database

ABSTRACT Background Safety issues for fluoroquinolones have been provided by regulatory agencies. This study was conducted to identify signals of fluoroquinolones reported in the Korea Adverse Event Reporting System (KAERS) using tree-based machine learning (ML) methods. Research design and methods All adverse events (AEs) associated with the target drugs reported in the KAERS from 2013 to 2017 were matched with drug label information. A dataset containing label-positive and -negative AEs was arbitrarily divided into training and test sets. Decision tree, random forest (RF), bagging, and gradient boosting machine (GBM) were fitted on the training set with hyperparameters tuned using five-fold cross-validation and applied to the test set. The ML method with the highest area under the curve (AUC) scores was selected as the final ML model. Results Bagging was selected as the final ML model for gemifloxacin (AUC score: 1) and levofloxacin (AUC: 0.9987). RF was selected in ciprofloxacin, moxifloxacin, and ofloxacin (AUC scores: 0.9859, 0.9974, and 0.9999 respectively). We found that the final ML methods detected additional signals that were not detected using the disproportionality analysis (DPA) methods. Conclusions The bagging-or-RF-based ML methods performed better than DPA and detected novel AE signals previously unidentified using the DPA methods.

Multi‐task deep neural networks for just‐in‐time software defect prediction on mobile apps

SummaryWith the development of smartphones, mobile applications play an irreplaceable role in our daily life, which characteristics often commit code changes to meet new requirements. This characteristic can introduce defects into the software. To provide immediate feedback to developers, previous researchers began to focus on just‐in‐time (JIT) software defect prediction techniques. JIT defect prediction aims to determine whether code commits will introduce defects into the software. It contains two scenarios, within‐project JIT defect prediction and cross‐project JIT defect prediction. Regardless of whether within‐project JIT defect prediction or cross‐project JIT defect prediction all need to have enough labeled data (within‐project JIT defect prediction assumes that have plenty of labeled data from the same project, while cross‐project JIT defect prediction assumes that have sufficient labeled data from source projects). However, in practice, both the source and target projects may only have limited labeled data. We propose the MTL‐DNN method based on multi‐task learning to solve this question. This method contains the data preprocessing layer, input layer, shared layers, task‐specific layers, and output layer. Where the common features of multiple related tasks are learned by sharing layers, and the unique features of each task are learned by the task‐specific layers. For verifying the effectiveness of the MTL‐DNN approach, we evaluate our method on 15 Android mobile apps. The experimental results show that our method significantly outperforms the state‐of‐the‐art single‐task deep learning and classical machine learning methods. This result shows that the MTL‐DNN method can effectively solve the problem of insufficient labeled training data for source and target projects.

Non-Destructive Detection of Chicken Freshness Based on Electronic Nose Technology and Transfer Learning

As a non-destructive detection method, an electronic nose can be used to assess the freshness of meats by collecting and analyzing their odor information. Deep learning can automatically extract features and uncover potential patterns in data, minimizing the influence of subjective factors such as selecting features artificially. A transfer-learning-based model was proposed for the electronic nose to detect the freshness of chicken breasts in this study. First, a 3D-printed electronic nose system is used to collect the odor data from chicken breast samples stored at 4 °C for 1–7 d. Then, three conversion to images methods are used to feed the recorded time series data into the convolutional neural network. Finally, the pre-trained AlexNet, GoogLeNet, and ResNet models are retrained in the last three layers while being compared to classic machine learning methods such as K Nearest Neighbors (KNN), Random Forest (RF), and Support Vector Machines (SVM). The final accuracy of ResNet is 99.70%, which is higher than the 94.33% correct rate of the popular machine learning model SVM. Therefore, the electronic nose combined with conversion to images shows great potential for using deep transfer learning methods for chicken freshness classification.

Machine Learning Methods Improve Specificity in Newborn Screening for Isovaleric Aciduria

Isovaleric aciduria (IVA) is a rare disorder of leucine metabolism and part of newborn screening (NBS) programs worldwide. However, NBS for IVA is hampered by, first, the increased birth prevalence due to the identification of individuals with an attenuated disease variant (so-called "mild" IVA) and, second, an increasing number of false positive screening results due to the use of pivmecillinam contained in the medication. Recently, machine learning (ML) methods have been analyzed, analogous to new biomarkers or second-tier methods, in the context of NBS. In this study, we investigated the application of machine learning classification methods to improve IVA classification using an NBS data set containing 2,106,090 newborns screened in Heidelberg, Germany. Therefore, we propose to combine two methods, linear discriminant analysis, and ridge logistic regression as an additional step, a digital-tier, to traditional NBS. Our results show that this reduces the false positive rate by 69.9% from 103 to 31 while maintaining 100% sensitivity in cross-validation. The ML methods were able to classify mild and classic IVA from normal newborns solely based on the NBS data and revealed that besides isovalerylcarnitine (C5), the metabolite concentration of tryptophan (Trp) is important for improved classification. Overall, applying ML methods to improve the specificity of IVA could have a major impact on newborns, as it could reduce the newborns' and families' burden of false positives or over-treatment.

EBHI: A new Enteroscope Biopsy Histopathological H&E Image Dataset for image classification evaluation

Background and purpose:Colorectal cancer has become the third most common cancer worldwide, accounting for approximately 10% of cancer patients. Early detection of the disease is important for the treatment of colorectal cancer patients. Histopathological examination is the gold standard for screening colorectal cancer. However, the current lack of histopathological image datasets of colorectal cancer, especially enteroscope biopsies, hinders the accurate evaluation of computer-aided diagnosis techniques. Therefore, a multi-category colorectal cancer dataset is needed to test various medical image classification methods to find high classification accuracy and strong robustness. Methods:A new publicly available Enteroscope Biopsy Histopathological H&E Image Dataset (EBHI) is published in this paper. To demonstrate the effectiveness of the EBHI dataset, we have utilized several machine learning, convolutional neural networks and novel transformer-based classifiers for experimentation and evaluation, using an image with a magnification of 200×. Results:Experimental results show that the deep learning method performs well on the EBHI dataset. Classical machine learning methods achieve maximum accuracy of 76.02% and deep learning method achieves a maximum accuracy of 95.37%. Conclusion:To the best of our knowledge, EBHI is the first publicly available colorectal histopathology enteroscope biopsy dataset with four magnifications and five types of images of tumor differentiation stages, totaling 5532 images. We believe that EBHI could attract researchers to explore new classification algorithms for the automated diagnosis of colorectal cancer, which could help physicians and patients in clinical settings.

Superpixel segmentation integrated feature subset selection for wetland classification over Yellow River Delta.

Wetlands are one of the world's most significant and vulnerable ecosystems. The wetlands of the Yellow River Delta are subject to multiple influences of ocean tidal action and the massive sediment deposits of the Yellow River, resulting in a more complex and unstable composition of land cover types. To better distinguish the wetlands in the region, we conducted the classification using an object-oriented combined with feature preference machine learning approach. To alleviate the pretzel phenomenon in pixel-based classification, a superpixel segmentation method using the watershed algorithm with H-minima labeling was used to segment the images at the optimal scale. The best feature subset for classification was filtered using the recursive feature elimination cross-validation approach, which extracts multiple spectral indices from the images.A random forest classifier combining superpixel segmentation and feature selection methods was proposed for the wetland classification. The model improves the classification accuracy of wetlands compared to three classical pixel-based machine learning classification methods. And the overall accuracy was 91.74% and the kappa coefficient was 0.9078, both of which were improved by about 4.53% and 0.0506, respectively, compared with the best-performing random forest classifier in pixel-oriented. The results showed that this method can effectively improve the classification accuracy of the Yellow River Delta wetlands compared with the previous studies.

Nuclear Magnetic Resonance-Based Metabolomics Approach Revealed the Intervention Effect of Using Complementary and Alternative Medicine (CAM) by CKD Patients.

Chronic kidney disease (CKD) is the end point of a number of systemic chronic diseases. The prevalence of CKD is increasing worldwide and recent epidemiological studies are showing the high prevalence of renal failure in CKD patients using complementary and alternative medicines (CAMs). Clinicians believe that biochemical profiles of CKD patients using CAM (referred here to as CAM-CKD) may be different compared to those on standard clinical treatment and should be managed differently. The present study aims to explore the potential of the NMR-based metabolomics approach to reveal the serum metabolic disparity between CKD and CAM-CKD patients with respect to normal control (NC) subjects and if the differential metabolic patterns can provide rationale for the efficacy and safety of standard and/or alternative therapies. Serum samples were obtained from 30 CKD patients, 43 CAM-CKD patients, and 47 NC subjects. The quantitative serum metabolic profiles were measured using 1D 1H CPMG NMR experiments performed at 800 MHz NMR spectrometer. The serum metabolic profiles were compared using various multivariate statistical analysis tools available on MetaboAnalyst (freely available web-based software) such as partial least-squares discriminant analysis (PLS-DA) and random forest (a machine learning) classification method. The discriminatory metabolites were identified based on variable importance in projection (VIP) statistics and further evaluated for statistical significance (i.e., p < 0.05) using either Student t-test or ANOVA statistics. PLS-DA models were capable of clustering CKD and CAM-CKD with considerably high values of Q 2 and R 2. Compared to CAM-CKD patients, the sera of CKD patients were characterized by (a) elevated levels of urea, creatinine, citrate, glucose, glycerol, and phenylalanine and phenylalanine-to-tyrosine ratio (PTR) and (b) decreased levels of various amino acids (such leucine, isoleucine, valine, and alanine), high-density lipoproteins, lactate, and acetate. These changes suggested that CKD patients manifest severe oxidative stress, hyperglycemia (with dampened glycolysis), increased protein energy wasting, and reduced lipid/membrane metabolism. Statistically significant and strong positive correlation of PTR with serum creatinine levels suggested the role of oxidative stress in the progression of kidney disease. Significant differences in metabolic patterns between CKD and CAM-CKD patients were observed. With respect to NC subjects, the serum metabolic changes were more aberrant in CKD patients compared to CAM-CKD patients. The aberrant metabolic changes in CKD patients with manifestations of higher oxidative stress compared to CAM-CKD patients could explain clinical discrepancies between CKD and CAM-CKD patients and further advocate the use of different treatment strategies for CKD and CAM-CKD patients.

The miniJPAS survey quasar selection – II. Machine learning classification with photometric measurements and uncertainties

ABSTRACTAstrophysical surveys rely heavily on the classification of sources as stars, galaxies, or quasars from multiband photometry. Surveys in narrow-band filters allow for greater discriminatory power, but the variety of different types and redshifts of the objects present a challenge to standard template-based methods. In this work, which is part of a larger effort that aims at building a catalogue of quasars from the miniJPAS survey, we present a machine learning-based method that employs convolutional neural networks (CNNs) to classify point-like sources including the information in the measurement errors. We validate our methods using data from the miniJPAS survey, a proof-of-concept project of the Javalambre Physics of the Accelerating Universe Astrophysical Survey (J-PAS) collaboration covering ∼1 deg2 of the northern sky using the 56 narrow-band filters of the J-PAS survey. Due to the scarcity of real data, we trained our algorithms using mocks that were purpose-built to reproduce the distributions of different types of objects that we expect to find in the miniJPAS survey, as well as the properties of the real observations in terms of signal and noise. We compare the performance of the CNNs with other well-established machine learning classification methods based on decision trees, finding that the CNNs improve the classification when the measurement errors are provided as inputs. The predicted distribution of objects in miniJPAS is consistent with the putative luminosity functions of stars, quasars, and unresolved galaxies. Our results are a proof of concept for the idea that the J-PAS survey will be able to detect unprecedented numbers of quasars with high confidence.

Application of Machine Learning Predictive Models for Early Detection of Glaucoma Using Real World Data

Early detection of glaucoma is critically important for the prevention of irreversible blindness. We developed a predictive analytic framework through temporal data carpentry and applications of a suite of machine learning and logistic regression methods for the early prediction of glaucoma using electronic health records (EHR) from over 650 hospitals and clinics across the USA. Four different machine-learning classification methods were applied using the whole dataset for predictive analysis. The accuracy, sensitivity, specificity, and f1 score were calculated using five-fold cross-validation to train and refine the models. The XGBoost, multi-layer perceptron (MLP), and random forest (RF) performed comparably well based on the area under the receiver operating characteristics curve (AUC) score of 0.81 for predicting glaucoma one year before the onset of the disease compared to the logistic regression (LR) score of 0.73. This study suggests that the ML methods can capture potential pre-glaucoma patients in advance before the occurrence of clinical symptoms from their history of EHR encounters, thus possibly leading to earlier intervention and preventive treatment.

Machine Learning Advances in Predicting Peptide/Protein-Protein Interactions Based on Sequence Information for Lead Peptides Discovery.

Peptides have shown increasing advantages and significant clinical value in drug discovery and development. With the development of high-throughput technologies and artificial intelligence (AI), machine learning (ML) methods for discovering new lead peptides have been expanded and incorporated into rational drug design. Predictions of peptide-protein interactions (PepPIs) and protein-protein interactions (PPIs) are both opportunities and challenges in computational biology, which will help to better understand the mechanisms of disease and provide the impetus for the discovery of lead peptides. This paper comprehensively reviews computational models for PepPI and PPI predictions. It begins with an introduction of various databases of peptide ligands and target proteins. Then it discusses data formats and feature representations for proteins and peptides. Furthermore, classical ML methods and emerging deep learning (DL) methods that can be used to train prediction models of PepPI and PPI are classified into four categories, and their advantages and disadvantages are analyzed. To assess the relative performance of different models, different validation protocols and evaluation indexes are discussed. The goal of this review is to help researchers quickly get started to develop computational frameworks using these integrated resources and eventually promote the discovery of lead peptides.

EXtreme gradient boosting-based classification of bacterial mixtures in water and milk using wireless microscopic imaging of quorum sensing peptide-conjugated particles

Numerous bacteria can cause water- and foodborne diseases and are often found in bacterial mixtures, making their detection challenging. Specific bioreceptors or selective growth media are necessary for most bacterial detection methods. In this work, we collectively used five quorum sensing-based peptides identified from bacterial biofilms to identify 10 different bacterial species (Bacillus subtilis, Campylobacter jejuni, Enterococcus faecium, Escherichia coli, Legionella pneumophila, Listeria monocytogenes, Pseudomonas aeruginosa, Salmonella Typhimurium, Staphylococcus aureus, Vibrio parahaemolyticus) and their mixtures in water and milk. Four different machine learning classification methods were used: k-nearest neighbors (k-NN), decision tree (DT), support vector machine (SVM), and eXtreme Gradient Boosting (XGBoost). Peptides were crosslinked to submicron particles, and peptide-bacteria interactions on paper microfluidic chips caused the particle aggregation. A wireless, pocket fluorescence microscope (interfaced with a smartphone) counted such particle aggregations. XGBoost showed the best accuracy of 83.75% in identifying bacterial species from water samples using 320 different datasets and 91.67% from milk samples using 140 different datasets (5 peptide features per dataset). Each peptide's contribution to correct classification was evaluated. The results were concentration-dependent, allowing the identification of a dominant species from bacterial mixtures. Using XGBoost and the previous milk database, we tested 14 blind samples of various bacterial mixtures in milk samples, with an accuracy of 81.55% to predict the dominant species. The entire process could be completed within a half hour. The demonstrated system can provide a handheld, low-cost, easy-to-operate tool for potential hygiene spot-checks, public health, or personal healthcare.