Practical Machine Learning Applications Research Articles

Machine learning empowered geographic information systems: Advancing Spatial analysis and decision making

In this era of technological innovation, the integration of machine learning techniques with Geographic Information Systems (GIS) has emerged as a transformative approach to spatial analysis and decision-making. This abstract explores the synergy between machine learning and GIS, highlighting their combined potential to unlock new insights from spatial data, automate analytical processes, and enhance predictive modeling capabilities. By leveraging machine learning algorithms such as neural networks, random forests, and support vector machines, GIS practitioners can address complex spatial challenges more effectively, ranging from land cover classification and urban growth modeling to environmental monitoring and disaster response. Through case studies and examples, this abstract demonstrates the practical applications of machine learning in GIS, illustrating its role in advancing our understanding of spatial phenomena and informing evidence-based decision-making across diverse domains. As the field continues to evolve, embracing the fusion of machine learning and GIS holds immense promise for unlocking the full potential of spatial analysis and shaping a more sustainable and resilient future. Illustrative case studies and examples showcase the practical applications of machine learning in GIS across diverse domains. From land cover classification and urban growth modeling to environmental monitoring and disaster response, machine learning algorithms offer versatile solutions to address a wide spectrum of spatial challenges. Through the fusion of machine learning and GIS, researchers and practitioners gain unprecedented insights into complex spatial phenomena, enabling them to make data-driven decisions that are both informed and actionable. Looking ahead, the fusion of machine learning and GIS holds immense promise for advancing our understanding of spatial dynamics and shaping a more sustainable and resilient future. As the field continues to evolve, embracing this interdisciplinary approach is essential for unlocking the full potential of spatial analysis, fostering innovation, and addressing pressing societal challenges at local, regional, and global scales. By leveraging the synergies between machine learning and GIS, we can chart a path towards a more data-driven, informed, and equitable world.

A machine learning classifier for automated fault detection and diagnosis (AFDD) of rooftop units, addressing practical challenges of application

There have been many recent developments to take advantage of machine learning for the task of automated fault detection and diagnosis in air-conditioning equipment. A common approach is to develop a machine learning model to classify fault status, using simulated or measurement data, and test the model’s fault diagnostic capability on the same system that was used for training. However, such models don’t generalize well to different systems. Compounding this challenge, machine learning requires a rich dataset to train the models, and many of the measurement features require additional sensors, all making the potential for practical machine learning AFDD questionable. The current paper focuses on these challenges by: (i) training a model using simulation data from three rooftop units (RTU); (ii) rebalancing the training dataset to reduce false alarms; (iii) developing a feature set that minimizes sensor cost without significantly impacting performance; (iv) testing the model’s performance on a set of laboratory measurement data from the same RTUs that were simulated for training data; (v) testing the model on a faulted RTU in the field. The results demonstrate good progress toward practical application of machine learning based AFDD for RTU, but generalization to different systems remains a challenge.

Application of machine learning in tax prediction: A review with practical approaches

This scholarly exploration delves into the dynamic intersection of machine learning (ML) and tax prediction, a realm where the fusion of advanced computational techniques and fiscal analytics heralds a new epoch in financial forecasting. The study's purpose was to meticulously dissect the efficacy of ML in tax prediction, navigating through the complexities and potentialities embedded within this innovative domain. The scope of the paper encompasses a comprehensive review of the evolution of tax prediction models, the significance of accurate tax forecasting in economic planning, and a critical analysis of previous studies, thereby laying a robust foundation for understanding the current state and future trajectory of ML in taxation. Employing a methodical approach, the study conducted a systematic review of peer-reviewed literature, focusing on the comparative analysis of various ML models, the impact of data quality on predictions, and innovative approaches in ML for enhanced tax prediction. This rigorous methodology ensured a holistic understanding of the subject matter, providing insights into both the theoretical underpinnings and practical applications of ML in tax forecasting. The main findings reveal that while ML presents unparalleled opportunities in tax prediction, it is not devoid of challenges such as data complexity, model interpretability, and ethical considerations. The study concludes that the integration of ML in tax prediction can significantly enhance accuracy and efficiency, provided these challenges are meticulously addressed. Recommendations include the adoption of appropriate ML models, emphasis on high-quality data, continuous model evaluation, and adherence to ethical practices in ML modeling. In summary, this paper offers a comprehensive and nuanced perspective on the role of ML in revolutionizing tax prediction. It serves as a guiding framework for policymakers, tax authorities, and researchers, advocating for a harmonious blend of technological innovation and ethical responsibility in the pursuit of advanced tax forecasting methods.

Exploring measure of uncertainty via a discernibility relation for partially labeled real-valued data

In practical applications of machine learning, only part of data is labeled because the cost of assessing class label is relatively high. Measure of uncertainty is abbreviated as MU. This paper explores MU for partially labeled real-valued data via a discernibility relation. First, a decision information system with partially labeled real-valued data (p-RVDIS) is separated into two decision information systems: one is the decision information system with labeled real-valued data (l-RVDIS) and the other is the decision information system with unlabeled real-valued data (u-RVDIS). Then, based on a discernibility relation, dependence function, conditional information entropy and conditional information amount, four degrees of importance on an attribute subset in a p-RVDIS are defined. They are calculated by taking the weighted sum of l-RVDIS and u-RVDIS based on the missing rate, which can be considered as four MUs for a p-RVDIS. Combining l-RVDIS and u-RVDIS provides a more accurate assessment of the importance and classification ability of attribute subsets in a p-RVDIS. This is precisely the novelty of this paper. Finally, experimental analysis on several datasets verify the effectiveness of these MUs. These findings will contribute to the comprehension of the essence of the uncertainty in a p-RVDIS.

From Text to Insights: NLP-Driven Classification of Infectious Diseases Based on Ecological Risk Factors

Numerous factors can affect the development of infectious diseases that emerge. While many are the result of natural procedures, such as the gradual emergence of viruses over time, certain ones are the result of human activity. Human activities form an integral part of our ecosystem, and especially the ecological aspect of human activities can encourage disease transmission. Additionally, Health ecologists examine changes in the biological, physical, social, and economic settings to understand how these alterations impact the mental and physical well-being of individuals. Hence, this research adopts a Framework-Based Method (FBM) in carrying out the task of classification of infectious diseases. The Framework-Based Method outlines all phases that this research follows to carry out the infectious disease classification process, providing a structured and reproducible approach. Results show that: XGB: Confusion matrix accuracy: 76%, Kappa: 73%, RF: Confusion matrix accuracy: 65%, Kappa: 60%, SVM: Confusion matrix accuracy: 63%, Kappa: 58%, ANN: Confusion matrix accuracy: 71%, Kappa: 67%, LDA: Confusion matrix accuracy: 76%, Kappa: 73%, GBM: Confusion matrix accuracy: 60%, Kappa: 53%, KNN: Confusion matrix accuracy: 43%, Kappa: 34%, and DT: Confusion matrix accuracy: 37%, Kappa: 29%. Furthermore, a Deep Learning model BERT was integrated with the best classification model XGBoots to create an interactive interface for users to carry out infectious disease classification. This integration enhances user experience and accessibility, contributing to the practical application of machine learning and Natural language processing in ecological disease classification

Practical Applications of Machine Learning–Based Systematic Investing in Agency Mortgage-Backed Securities

Practical Applications of Machine Learning–Based Systematic Investing in Agency Mortgage-Backed Securities

Evaluating machine and deep learning techniques in predicting blood sugar levels within the E-health domain

This paper focuses on exploring and comparing different machine learning algorithms in the context of diabetes management. The aim is to understand their characteristics, mathematical foundations, and practical implications specifically for predicting blood glucose levels. The study provides an overview of the algorithms, with a particular emphasis on deep learning techniques such as Long Short-Term Memory Networks. Efficiency is a crucial factor in practical machine learning applications, especially in the context of diabetes management. Therefore, the paper investigates the trade-off between accuracy, resource utilisation, time consumption, and computational power requirements, aiming to identify the optimal balance. By analysing these algorithms, the research uncovers their distinct behaviours and highlights their dissimilarities, even when their analytical underpinnings may appear similar.

Machine learning to predict ceftriaxone resistance using single nucleotide polymorphisms within a global database of Neisseria gonorrhoeae genomes.

Antimicrobial resistance (AMR) in Neisseria gonorrhoeae is an urgent global health issue. Machine learning (ML) is a powerful tool that can aid in identifying mutations and predicting their impact on AMR. The study aimed to use ML models to predict ceftriaxone susceptibility and decreased susceptibility (S/DS). A public database of N. gonorrhoeae genomes with minimum inhibitory concentration (MIC) data was used to evaluate seven ML models using 97 single nucleotide polymorphisms (SNPs) known to be associated with ceftriaxone resistance. Ceftriaxone MICs ≤ 0.064 mg/L were classified as susceptible, and ceftriaxoneMICs > 0.064 mg/L were classified as DS. The contributions of individual SNPs to predict S/DS were calculated using SHapley Additive exPlanation (SHAP) values. An ML model was retrained using different combinations of SNPs with the highest SHAP values. The performance of ML models was assessed using different metrics including area under the curve (AUC) and balanced accuracy (bAcc). The ML analyses included 9,540 N. gonorrhoeae genomes; 368 (0.04%) were classified as DS. Of the models evaluated, the model trained with a random forest classifier had the highest performance (AUC 0.965; bAcc 0.926). A model retrained the top five SNPs, according to SHAP values, demonstrated a similar performance (AUC 0.916; bAcc 0.879) as the model with 97 SNPs. An ML approach using mutations in N. gonorrhoeae can be used to predict S/DS to ceftriaxone. The results highlight a practical application of ML to identify mutations most associated with S/DS to ceftriaxone, which can aid in the development of assays to predict AMR. IMPORTANCE Antimicrobial resistance in Neisseria gonorrhoeae is an urgent global health issue. The objectives of the study were to use a global collection of 12,936 N. gonorrhoeae genomes from the PathogenWatch database to evaluate different machine learning models to predict ceftriaxone susceptibility/decreased susceptibility using 97 mutations known to be associated with ceftriaxone resistance. We found the random forest classifier model had the highest performance. The analysis also reported the relative contributions of different mutations within the ML model predictions, allowing for the identification of the mutations with the highest importance for ceftriaxone resistance. A machine learning model retrained with the top five mutations performed similarly to the model using all 97 mutations. These results could aid in the development of molecular tests to detect resistance to ceftriaxone in N. gonorrhoeae. Moreover, this approach could be applied to building and evaluating machine learning models for predicting antimicrobial resistance in other pathogens.

IWDA: Importance Weighting for Drift Adaptation in Streaming Supervised Learning Problems.

Distribution drift is an important issue for practical applications of machine learning (ML). In particular, in streaming ML, the data distribution may change over time, yielding the problem of concept drift, which affects the performance of learners trained with outdated data. In this article, we focus on supervised problems in an online nonstationary setting, introducing a novel learner-agnostic algorithm for drift adaptation, namely (), with the goal of performing efficient retraining of the learner when drift is detected. incrementally estimates the joint probability density of input and target for the incoming data and, as soon as drift is detected, retrains the learner using importance-weighted empirical risk minimization. The importance weights are computed for all the samples observed so far, employing the estimated densities, thus, using all available information efficiently. After presenting our approach, we provide a theoretical analysis in the abrupt drift setting. Finally, we present numerical simulations that illustrate how competes and often outperforms state-of-the-art stream learning techniques, including adaptive ensemble methods, on both synthetic and real-world data benchmarks.

Adaptation for Automated Drift Detection in Electromechanical Machine Monitoring.

Practical machine learning applications for streaming data can involve concept drift (the change in statistical properties of data over time), one-shot or few-shot learning (starting with only one or a few examples for each class), a scarcity of representative training data, and extreme verification latency (only the initial dataset has ground-truth labels). This work presents a framework for organizing signal processing and machine learning techniques to provide adaptive classification and drift detection. Nonintrusive load monitoring (NILM) serves as an ideal case study, as modern sensing solutions provide a wellspring of electromechanical data sources. There is a lack of training datasets that generalize across different load and fault scenarios. Accordingly, training must be accomplished with a limited set of data when deploying a NILM to a new power system. Also, loads can exhibit concept drift over time either due to faults or normal variation. NILM field data is used as an illustrative case study to demonstrate the proposed framework for adaptation and drift tracking.

Learning domain invariant representations by joint Wasserstein distance minimization

Domain shifts in the training data are common in practical applications of machine learning; they occur for instance when the data is coming from different sources. Ideally, a ML model should work well independently of these shifts, for example, by learning a domain-invariant representation. However, common ML losses do not give strong guarantees on how consistently the ML model performs for different domains, in particular, whether the model performs well on a domain at the expense of its performance on another domain. In this paper, we build new theoretical foundations for this problem, by contributing a set of mathematical relations between classical losses for supervised ML and the Wasserstein distance in joint space (i.e. representation and output space). We show that classification or regression losses, when combined with a GAN-type discriminator between domains, form an upper-bound to the true Wasserstein distance between domains. This implies a more invariant representation and also more stable prediction performance across domains. Theoretical results are corroborated empirically on several image datasets. Our proposed approach systematically produces the highest minimum classification accuracy across domains, and the most invariant representation.

Forecasting Stock Market Prices Using Machine Learning and Deep Learning Models: A Systematic Review, Performance Analysis and Discussion of Implications

The financial sector has greatly impacted the monetary well-being of consumers, traders, and financial institutions. In the current era, artificial intelligence is redefining the limits of the financial markets based on state-of-the-art machine learning and deep learning algorithms. There is extensive use of these techniques in financial instrument price prediction, market trend analysis, establishing investment opportunities, portfolio optimization, etc. Investors and traders are using machine learning and deep learning models for forecasting financial instrument movements. With the widespread adoption of AI in finance, it is imperative to summarize the recent machine learning and deep learning models, which motivated us to present this comprehensive review of the practical applications of machine learning in the financial industry. This article examines algorithms such as supervised and unsupervised machine learning algorithms, ensemble algorithms, time series analysis algorithms, and deep learning algorithms for stock price prediction and solving classification problems. The contributions of this review article are as follows: (a) it provides a description of machine learning and deep learning models used in the financial sector; (b) it provides a generic framework for stock price prediction and classification; and (c) it implements an ensemble model—“Random Forest + XG-Boost + LSTM”—for forecasting TAINIWALCHM and AGROPHOS stock prices and performs a comparative analysis with popular machine learning and deep learning models.

Distributed Stochastic Nested Optimization for Emerging Machine Learning Models: Algorithm and Theory

Traditional machine learning models can be formulated as the expected risk minimization (ERM) problem: minw∈Rd Eξ [l(w; ξ)], where w ∈ Rd denotes the model parameter, ξ represents training samples, l(·) is the loss function. Numerous optimization algorithms, such as stochastic gradient descent (SGD), have been developed to solve the ERM problem. However, a wide range of emerging machine learning models are beyond this class of optimization problems, such as model-agnostic meta-learning (Finn, Abbeel, and Levine 2017). Of particular interest of my research is the stochastic nested optimization (SNO) problem, whose objective function has a nested structure. Specifically, I have been focusing on two instances of this kind of problem: stochastic compositional optimization (SCO) problems, which cover meta-learning, area-under-the-precision recall-curve optimization, contrastive self-supervised learning, etc., and stochastic bilevel optimization (SBO) problems, which can be applied to meta-learning, hyperparameter optimization, neural network architecture search, etc. With the emergence of large-scale distributed data, such as the user data generated on mobile devices or intelligent hardware, it is imperative to develop distributed optimization algorithms for SNO (Distributed SNO). A significant challenge for optimizing distributed SNO problems lies in that the stochastic (hyper-)gradient is a biased estimation of the full gradient. Thus, existing distributed optimization algorithms when applied to them suffer from slow convergence rates. In this talk, I will discuss my recent works about distributed SCO (Gao and Huang 2021; Gao, Li, and Huang 2022) and distributed SBO (Gao, Gu, and Thai 2022; Gao 2022) under both centralized and decentralized settings, including algorithmic details about reducing the bias of stochastic gradient, theoretical convergence rate, and practical machine learning applications, and then highlight challenges for future research.

Analysis of interaction mode of ideological and political flipped classroom based on deep learning algorithm and student feedback data

By abstracting the input data using deep neural networks, we can obtain the distributed representation characteristics of related data. Compared with shallow neural network, deep neural network has stronger data representation ability. Deep learning promotes the deep research and practical application of machine learning. The continuous progress and development of society not only promote the new curriculum reform, but also put forward higher requirements for all kinds of talents. At this stage, students should learn how to maintain lifelong learning and maintain the attitude of "learning is never too old". Therefore, the concept of deep learning in the educational world was born. Ideology and politics is a comprehensive subject, which requires students to solve problems independently. The content of ideology and politics is complex and diverse, and theory is closely combined with practice, so that students can find and analyze problems independently in the process of practice. Deep learning is manifested in higher-order thinking, that is, students should be self-conscious in learning, learn to closely discuss the problems in learning with people around them, and have the ability to criticize, question, integrate construction, transfer and apply in the learning process. Based on the deep learning algorithm, this paper uses relevant theories and educational practices for reference to analyze the interaction mode of ideological and political flipped classroom and student feedback data.

Predicting money laundering sanctions using machine learning algorithms and artificial neural networks

ABSTRACT This article used machine learning (ML) and artificial neural network (ANN) algorithms to predict the likelihood of a country being sanctioned by the Basel Institute on Governance for not adhering to anti-money laundering (AML) standards. Data for this paper came from the Basel AML Index and the World Bank. The results showed that the logistic regression and support vector machine (SVM) classifiers had the highest performance and balanced accuracy scores in sanction prediction. Additionally, these two algorithms also had the highest precision, specificity, and F1 scores, indicating that they were robust in their predictions of money laundering sanctions. In contrast to the ML classifiers, the ANN model had the highest sensitivity and receiver operating characteristic scores for money laundering sanctions. The strongest predictors of sanctions are financial transparency, political and legal risks, unemployment rate, and money laundering and terrorist financing risks. These findings reinforce the potential practical applications of ML and ANN models in predicting sanctions.

Semi-supervised attribute reduction for partially labeled categorical data based on predicted label

In many practical applications of machine learning, there are a large number of partially labeled categorical data due to the high cost of labeling data. The semi-supervised learning algorithm is needed to deal with such data. This paper studies the label prediction of partially labeled categorical data and considers semi-supervised attribute reduction in a partially labeled categorical decision information system (p-CDIS) with predicted labels. The labels of unlabeled data are first predicted by means of the conditional probability. Then, uncertainty measurement for a p-CDIS with predicted labels is studied, and the dependence and conditional information entropy (CIE) are defined. Next, based on the dependence and CIE, two attribute reduction algorithms are designed. In addition, the effect of label deletion rate (LDR) on the dependence, CIE and reduction results are also studied. Finally, the results of experiments and statistical tests on 16 categorical UCI datasets show that the designed algorithms are statistically better than some state-of-the-art algorithms in classification accuracy.

Application of Machine Learning in Digital Human Resource Management

In today's high-speed information age, many problems of the traditional human resource management (HRM) system make it impossible to effectively analyze massive data in today's enterprise competition and development. Machine learning, as a novel field of research in computer science in recent decades, provides a potential solution to the current problems faced by HRM systems. This study focuses on strategic HRM, an essential means of shaping employee behavior, and a vital information transmission channel in the CEO's transformational leadership behavior. By reviewing past literature on machine learning and exploring the principles of the practical application of machine learning in HRM, this paper also focuses on the intermediary mechanism between enterprise performance and the latest progress in machine learning and HRM. Further, the study tries to summarize and refine the opportunities and challenges that HRM faces in developing HRM and possible future research directions and hotspots.

Partial Discharge Detection by Edge Computing

Edge computing is becoming a mainstream platform for practical applications of machine learning and in particular deep learning. Many systems capable of efficient execution of deep neural models in the context of edge computing are readily available or beginning to appear on the consumer market. The Jetson platform from NVIDIA, the Neural stick from Intel, and the Edge TPU designed by Google are examples of devices that enable the application of complex neural networks in edge computing. This work investigates the ability of selected edge devices to address a real-world classification problem from electrical power engineering. It consists of the detection of partial discharges (PDs) from covered conductors (CCs) on high-voltage power lines. The CCs are used in heavily forested and generally inaccessible areas where clearance zones cannot be maintained. Detection of PDs can prevent forest fires and other disasters potentially caused by prolonged contact of CCs with vegetation. The problem is suitable for an edge computing-based solution because Internet connectivity in remote areas is usually insufficient and a 2G (GSM) mobile network is available at best. Because such locations are difficult to access and usually without a suitable power supply, the proposed solution puts an emphasis also on PD detection latency and the associated power consumption. Two principal approaches to PD detection are considered. One is based on the classification of 1D time series (raw data). The second approach uses the signal transformed into a 2D spectrogram. In this case, two types of algorithms are evaluated. The first one is a novel custom stacking ensemble detector composed of 2D convolutional neural networks and a neural meta-learner on top of it. The second one uses the well-known and widely-used used ResNet deep neural model.

Robust Random Forest-Based All-Relevant Feature Ranks for Trustworthy AI.

Feature selection is a fundamental challenge in machine learning. For instance in bioinformatics, it is essential when one wishes to detect biomarkers. Tree-based methods are predominantly used for this purpose. In this paper, we study the stability of the feature selection methods BORUTA, VITA, and RRF (regularized random forest). In particular, we investigate the feature ranking instability of the associated stochastic algorithms. For stabilization of the feature ranks, we propose to compute consensus values from multiple feature selection runs, applying rank aggregation techniques. Our results show that these consolidated features are more accurate and robust, which helps to make practical machine learning applications more trustworthy.

Natural language processing of admission notes to predict severe maternal morbidity during the delivery encounter

Severe maternal morbidity and mortality remain public health priorities in the United States, given their high rates relative to other high-income countries and the notable racial and ethnic disparities that exist. In general, accurate risk stratification methods are needed to help patients, providers, hospitals, and health systems plan for and potentially avert adverse outcomes. Our objective was to understand if machine learning methods with natural language processing of history and physical notes could identify a group of patients at high risk of maternal morbidity on admission for delivery without relying on any additional patient information (eg, demographics and diagnosis codes). This was a retrospective study of people admitted for delivery at 2 hospitals (hospitals A and B) in a single healthcare system between July 1, 2016, and June 30, 2020. The primary outcome was severe maternal morbidity, as defined by the Centers for Disease Control and Prevention; furthermore, we examined nontransfusion severe maternal morbidity. Clinician documents designated as history and physical notes were extracted from the electronic health record for processing and analysis. A bag-of-words approach was used for this natural language processing analysis (ie, each history or physical note was converted into a matrix of counts of individual words (or phrases) that occurred within the document). The least absolute shrinkage and selection operator models were used to generate prediction probabilities for severe maternal morbidity and nontransfusion severe maternal morbidity for each note. Model discrimination was assessed via the area under the receiver operating curve. Discrimination was compared between models using the DeLong test. Calibration plots were generated to assess model calibration. Moreover, the natural language processing models with history and physical note texts were compared with validated obstetrical comorbidity risk scores based on diagnosis codes. There were 13,572 delivery encounters with history and physical notes from hospital A, split between training (Atrain, n=10,250) and testing (Atest, n=3,322) datasets for model derivation and internal validation. There were 23,397 delivery encounters with history and physical notes from hospital B (Bvalid) used for external validation. For the outcome of severe maternal morbidity, the natural language processing model had an area under the receiver operating curve of 0.67 (95% confidence interval, 0.63-0.72) and 0.72 (95% confidence interval, 0.70-0.74) in the Atest and Bvalid datasets, respectively. For the outcome of nontransfusion severe maternal morbidity, the area under the receiver operating curve was 0.72 (95% confidence interval, 0.65-0.80) and 0.76 (95% confidence interval, 0.73-0.79) in the Atest and Bvalid datasets, respectively. The calibration plots demonstrated the bag-of-words model's ability to distinguish a group of individuals at a substantially higher risk of severe maternal morbidity and nontransfusion severe maternal morbidity, notably those in the top deciles of predicted risk. Areas under the receiver operating curve in the natural language processing-based models were similar to those generated using a validated, retrospectively derived, diagnosis code-based comorbidity score. In this practical application of machine learning, we demonstrated the capabilities of natural language processing for the prediction of severe maternal morbidity based on provider documentation inherently generated at the time of admission. This work should serve as a catalyst for providers, hospitals, and electronic health record systems to explore ways that artificial intelligence can be incorporated into clinical practice and evaluated rigorously for their ability to improve health.