Modern Machine Learning Techniques Research Articles

The Kramers turnover in terms of a macro-state projection on phase space

We have investigated how Langevin dynamics is affected by the friction coefficient using the novel algorithm ISOKANN, which combines the transfer operator approach with modern machine learning techniques. ISOKANN describes the dynamics in terms of an invariant subspace projection of the Koopman operator defined in the entire state space, avoiding approximations due to dimensionality reduction and discretization. Our results are consistent with the Kramers turnover and show that in the low and moderate friction regimes, metastable macro-states and transition rates are defined in phase space, not only in position space.

Reconstructing S-matrix Phases with Machine Learning

An important element of the S-matrix bootstrap program is the relationship between the modulus of an S-matrix element and its phase. Unitarity relates them by an integral equation. Even in the simplest case of elastic scattering, this integral equation cannot be solved analytically and numerical approaches are required. We apply modern machine learning techniques to studying the unitarity constraint. We find that for a given modulus, when a phase exists it can generally be reconstructed to good accuracy with machine learning. Moreover, the loss of the reconstruction algorithm provides a good proxy for whether a given modulus can be consistent with unitarity at all. In addition, we study the question of whether multiple phases can be consistent with a single modulus, finding novel phase-ambiguous solutions. In particular, we find a new phase-ambiguous solution which pushes the known limit on such solutions significantly beyond the previous bound.

How much can personality predict prosocial behavior?

Explaining prosocial behavior is a central goal in classic and contemporary behavioral science. Here, for the first time, we apply modern machine learning techniques to uncover the full predictive potential that personality traits have for prosocial behavior. We utilize a large-scale dataset ( N = 2707; 81 personality traits) and state-of-the-art statistical models to predict an incentivized measure of prosocial behavior, Social Value Orientation (SVO). We conclude: (1) traits explain 13.9% of the variance in SVO; (2) linear models are sufficient to obtain good prediction; (3) trait–trait interactions do not improve prediction; (4) narrow traits improve prediction beyond basic personality (i.e., the HEXACO); (5) there is a moderate association between the univariate predictive power of a trait and its multivariate predictive power, suggesting that univariate estimates (e.g., Pearson’s correlation) can serve as a useful proxy for multivariate variable importance. We propose that the limited usefulness of nonlinear models may stem from current measurement practices in personality science, which tend to favor linearly related constructs. Overall, our study provides a benchmark for how well personality predicts SVO and charts a course toward better prediction of prosocial behavior.

Predicting NFL Point Spreads via Machine Learning

This paper describes sports quantitative analysis research which investigates the use of statistics and modern machine learning methods applied to the problem of predicting the point spreads for United States (US) National Football League (NFL) football games. Insights and results are presented for several modern machine learning techniques for both exploratory analysis and predictive analysis. The case study presented here and the results thereof may be quite useful for those involved in the huge global sports betting arena both the gaming industry and the bettors therein. NFL game statistics also provides a rich source of relevant real-world data for the deployment of several modern data science methodologies and is thus a great teaching tool for the university classroom. Since sports gambling has now made its way onto college campuses with a growing number of schools signing million dollar deals with sports books and casinos, the topic of this article is of even more current relevance.

Heritage Identification of Monument Using Deep Learning

Abstract: There are many beautiful and colorful countries in the world which are famous for their culture and heritage. The historical landmarks of such countries convey a great deal through their magnificent structures and rich heritage. The extensive past and legacy of such nations are apparent in the splendid palaces, fortresses, towers, shrines, and cathedrals that are scattered throughout the entirety of their land. We need to protect cultural monuments and landmarks as they are one of the sources of inspiration for future generations. Traditional methods for monument identification often rely on manual inspection or rudimentary computer vision techniques, which can be time-consuming and error-prone. We can provide the best solutions using modern machine learning and deep learning techniques. In our model, we used an approach based on deep learning for the automated identification of heritage monuments from images. We leveraged the power of convolutional neural networks (CNNs) to extract hierarchical features from monument images and train a classifier to recognize different architectural styles and structures. We evaluated our approach on a dataset comprising diverse monument images collected from public archives and online repositories. We applied various pre-processing techniques such as image resizing, normalization of pixel values, and data augmentation. We analyzed and further improved the model’s performance for heritage identification of monuments.

Abstract 5887: Identifying new immunotherapy targets using machine learning and ex vivo validation

Abstract Overview: Immunotherapy has revolutionized cancer treatment. However, existing immune checkpoint inhibitors (CPI) yield low response rates in most cancers, highlighting the need for new therapeutic options. Traditional immune-oncology (IO) target discovery relies on preclinical models, which struggle to recapitulate human tumor complexity, limiting translation potential. Attention is thus directed at harnessing multimodal patient molecular data with modern machine learning (ML) techniques to identify new IO targets which may have higher clinical viability. Approach: We posed IO target discovery as a binary classification task, training ML systems on known candidate drug targets that have progressed to stage I or higher clinical trials. We constructed a rich knowledge graph database to support model development. Graph nodes (n=11,919) comprised genes with edges linking genes involved in n=99,275 protein-protein interactions (PPIs; PMID: 28936969). Genes were labelled with n=6,387 gene-disease associations alongside bulk exome and transcriptome (RNAseq) features from n=1,317 CPI-treated patients (PMID: 33508232). We considered the role of different immune subsets by incorporating cell type-specific PPIs from single cell RNAseq atlases of n=350 samples (PMID: 31786210). To capture how antigen processing affects immunotherapy response, we also examined the immunopeptidome of n=60 patients (PMID: 30556813). Causal data on immune responses to genetic perturbation stemmed from n=7 publicly available CRISPR tumor-T cell co-cultures and n=15,442 SNP-phenotype links. Lastly, we used interpretability analysis to understand drivers of model predictions and elucidate critical genes that influence multiple IO target pathways. Results: Firstly, we developed an ensemble ML approach which achieved test ROC-AUC>0.75. Next, we used a graph-based ML framework which yielded superior performance (test ROC-AUC>0.90). Orthogonal validation confirmed these models can discriminate known targets by trial phase (p<0.001), predict patient response in new CPI trials (p<0.05), and identify genes that rank highly in unseen genome-wide CRISPR screens. Targets from both methods have entered experimental validation in patient-derived explants and organoid-immune co-cultures. Already, we have identified 2 novel targets predicted to relate to macrophage activity. Early data suggest that perturbing them leads to macrophage repolarization. Further validation experiments are ongoing. Conclusions: We will reveal candidate targets, showing that our method is effective at uncovering new IO targets and can identify critical nodes in biological networks that might be attractive hits. In addition, deciphering data types that drive model predictions provides a broader immunobiological understanding of anti-tumor immune responses. Thus, our results endorse using ML and multimodal data for novel IO target discovery. Citation Format: Marcellus Augustine, Nuno Rocha Nene, Krupa Thakkar, Danwen Qian, Evelyn Fitzsimons, Benjamin S. Simpson, Chris Watkins, Charles Swanton, Kevin Litchfield. Identifying new immunotherapy targets using machine learning and ex vivo validation [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 5887.

Responsible machine learning for United States Air Force pilot candidate selection

The United States Air Force (USAF) continues to be plagued by a chronic pilot shortage, one that could be exacerbated by an accompanying shortfall in the commercial airlines. As a result, efforts have increased to alleviate this shortage by finding methods to reduce pilot training attrition. We contribute to these efforts by setting forth a decision support system (DSS) for pilot candidate selection using modern machine learning techniques. In view of the recent Responsible Artificial Intelligence Strategy published by the United States Department of Defense, this research leverages interpretable and explainable machine learning methods to create traceable and equitable models that may be responsibly and reliably governed. These models are used to regress candidates’ average merit assignment selection system scores based on information available for selection and prior to training. More specifically, using data provided by the USAF from 2010 to 2018, this paper develops and analyzes multiple interpretable models based on Gaussian Bayesian networks, as well as multiple black-box models rendered explainable by SHAP values and conformal prediction. A preferred pair of interpretable and explainable models is selected and embedded within a DSS for USAF pilot candidate selection boards: the Air Force Pilot Applicant Selection System. The utilization of this DSS is explored, the analyses it enables are discussed, and relevant USAF policymaking issues are examined.

Unleashing the potential of fNIRS with machine learning: classification of fine anatomical movements to empower future brain-computer interface.

In this study, we explore the potential of using functional near-infrared spectroscopy (fNIRS) signals in conjunction with modern machine-learning techniques to classify specific anatomical movements to increase the number of control commands for a possible fNIRS-based brain-computer interface (BCI) applications. The study focuses on novel individual finger-tapping, a well-known task in fNIRS and fMRI studies, but limited to left/right or few fingers. Twenty-four right-handed participants performed the individual finger-tapping task. Data were recorded by using sixteen sources and detectors placed over the motor cortex according to the 10-10 international system. The event's average oxygenated Δ HbO and deoxygenated Δ HbR hemoglobin data were utilized as features to assess the performance of diverse machine learning (ML) models in a challenging multi-class classification setting. These methods include LDA, QDA, MNLR, XGBoost, and RF. A new DL-based model named "Hemo-Net" has been proposed which consists of multiple parallel convolution layers with different filters to extract the features. This paper aims to explore the efficacy of using fNRIS along with ML/DL methods in a multi-class classification task. Complex models like RF, XGBoost, and Hemo-Net produce relatively higher test set accuracy when compared to LDA, MNLR, and QDA. Hemo-Net has depicted a superior performance achieving the highest test set accuracy of 76%, however, in this work, we do not aim at improving the accuracies of models rather we are interested in exploring if fNIRS has the neural signatures to help modern ML/DL methods in multi-class classification which can lead to applications like brain-computer interfaces. Multi-class classification of fine anatomical movements, such as individual finger movements, is difficult to classify with fNIRS data. Traditional ML models like MNLR and LDA show inferior performance compared to the ensemble-based methods of RF and XGBoost. DL-based method Hemo-Net outperforms all methods evaluated in this study and demonstrates a promising future for fNIRS-based BCI applications.

Machine learning decision support model for discharge planning in stroke patients.

Efficient discharge for stroke patients is crucial but challenging. The study aimed to develop early predictive models to explore which patient characteristics and variables significantly influence the discharge planning of patients, based on the data available within 24 h of admission. Prospective observational study. A prospective cohort was conducted at a university hospital with 523 patients hospitalised for stroke. We built and trained six different machine learning (ML) models, followed by testing and tuning those models to find the best-suited predictor for discharge disposition, dichotomized into home and non-home. To evaluate the accuracy, reliability and interpretability of the best-performing models, we identified and analysed the features that had the greatest impact on the predictions. In total, 523 patients met the inclusion criteria, with a mean age of 61 years. Of the patients with stroke, 30.01% had non-home discharge. Our model predicting non-home discharge achieved an area under the receiver operating characteristic curve of 0.95 and a precision of 0.776. After threshold was moved, the model had a recall of 0.809. Top 10 variables by importance were National Institutes of Health Stroke Scale (NIHSS) score, family income, Barthel index (BI) score, FRAIL score, fall risk, pressure injury risk, feeding method, depression, age and dysphagia. The ML model identified higher NIHSS, BI, and FRAIL, family income, higher fall risk, pressure injury risk, older age, tube feeding, depression and dysphagia as the top 10 strongest risk predictors in identifying patients who required non-home discharge to higher levels of care. Modern ML techniques can support timely and appropriate clinical decision-making. This study illustrates the characteristics and risk factors of non-home discharge in patients with stroke, potentially contributing to the improvement of the discharge process. STROBE guidelines.

Construction and Application of a Traditional Chinese Medicine Syndrome Differentiation Model for Dysmenorrhea Based on Machine Learning.

Dysmenorrhea is one of the most common ailments affecting young and middle-aged women, significantly impacting their quality of life. Traditional Chinese Medicine (TCM) offers unique advantages in treating dysmenorrhea. However, an accurate diagnosis is essential to ensure correct treatment. This research integrates the age-old wisdom of TCM with modern Machine Learning (ML) techniques to enhance the precision and efficiency of dysmenorrhea syndrome differentiation, a pivotal process in TCM diagnostics and treatment planning. A total of 853 effective cases of dysmenorrhea were retrieved from the CNKI database, including patients' syndrome types, symptoms, and features, to establish the TCM information database of dysmenorrhea. Subsequently, 42 critical features were isolated from a potential set of 86 using a selection procedure augmented by Python's Scikit-Learn Library. Various machine learning models were employed, including Logistic Regression, Random Forest Classifier, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Artificial Neural Networks (ANN), each chosen for their potential to unearth complex patterns within the data. Based on accuracy, precision, recall, and F1-score metrics, SVM emerged as the most effective model, showcasing an impressive precision of 98.29% and an accuracy of 98.24%. This model's analytical prowess not only highlighted the critical features pivotal to the syndrome differentiation process but also stands to significantly aid clinicians in formulating personalized treatment strategies by pinpointing nuanced symptoms with high precision. The study paves the way for a synergistic approach in TCM diagnostics, merging ancient wisdom with computational acuity, potentially innovating the diagnosis and treatment mode of TCM. Despite the promising outcomes, further research is needed to validate these models in real-world settings and extend this approach to other diseases addressed by TCM.

Machine learning for the management of biochar yield and properties of biomass sources for sustainable energy

AbstractBiochar is emerging as a potential solution for biomass conversion to meet the ever increasing demand for sustainable energy. Efficient management systems are needed in order to exploit fully the potential of biochar. Modern machine learning (ML) techniques, and in particular ensemble approaches and explainable AI methods, are valuable for forecasting the properties and efficiency of biochar properly. Machine‐learning‐based forecasts, optimization, and feature selection are critical for improving biomass management techniques. In this research, we explore the influences of these techniques on the accurate forecasting of biochar yield and properties for a range of biomass sources. We emphasize the importance of the interpretability of a model, as this improves human comprehension and trust in ML predictions. Sensitivity analysis is shown to be an effective technique for finding crucial biomass characteristics that influence the synthesis of biochar. Precision prognostics have far‐reaching ramifications, influencing industries such as biomass logistics, conversion technologies, and the successful use of biomass as renewable energy. These advances can make a substantial contribution to a greener future and can encourage the development of a circular biobased economy. This work emphasizes the importance of using sophisticated data‐driven methodologies such as ML in biochar synthesis, to usher in ecologically friendly energy solutions. These breakthroughs hold the key to a more sustainable and environmentally friendly future.

Survival prediction of glioblastoma patients using modern deep learning and machine learning techniques

In this study, we utilized data from the Surveillance, Epidemiology, and End Results (SEER) database to predict the glioblastoma patients’ survival outcomes. To assess dataset skewness and detect feature importance, we applied Pearson's second coefficient test of skewness and the Ordinary Least Squares method, respectively. Using two sampling strategies, holdout and five-fold cross-validation, we developed five machine learning (ML) models alongside a feed-forward deep neural network (DNN) for the multiclass classification and regression prediction of glioblastoma patient survival. After balancing the classification and regression datasets, we obtained 46,340 and 28,573 samples, respectively. Shapley additive explanations (SHAP) were then used to explain the decision-making process of the best model. In both classification and regression tasks, as well as across holdout and cross-validation sampling strategies, the DNN consistently outperformed the ML models. Notably, the accuracy were 90.25% and 90.22% for holdout and five-fold cross-validation, respectively, while the corresponding R2 values were 0.6565 and 0.6622. SHAP analysis revealed the importance of age at diagnosis as the most influential feature in the DNN's survival predictions. These findings suggest that the DNN holds promise as a practical auxiliary tool for clinicians, aiding them in optimal decision-making concerning the treatment and care trajectories for glioblastoma patients.

An improved Approach for Sustainable Risk Management Practices in Modern Businesses

The complexity of the business environment, which is shaped by dynamic economic, environmental, and social factors, makes it more important for companies to develop sustainable risk management practices. This research proposes a novel approach that combines traditional methods with modern machine learning techniques in response to the complex challenges faced by contemporary businesses in balancing risk and sustainability. Our study uses a public bank loan default dataset as a case study to address missing data systematically through robust imputation mechanisms and transform categorical variables using feature encoding. Spearman correlation analysis helps us understand complex variable relationships and guides subsequent feature selection. The decision tree classifier, a powerful machine learning algorithm known for its interpretability, is applied to identify key factors contributing to risk assessment. The hierarchical structure of the decision tree not only reveals important variables but also provides an explicit representation of the decision-making process. ROC curve analysis shows how well our predictive model can differentiate potential loan defaults.

Results Obtained from a Pivotal Validation Trial of a Microsatellite Analysis (MSA) Assay for Bladder Cancer Detection through a Statistical Approach Using a Four-Stage Pipeline of Modern Machine Learning Techniques.

Several studies have shown that microsatellite changes can be profiled in urine for the detection of bladder cancer. The use of microsatellite analysis (MSA) for bladder cancer detection requires a comprehensive analysis of as many as 15 to 20 markers, based on the amplification and interpretations of many individual MSA markers, and it can be technically challenging. Here, to develop fast, more efficient, standardized, and less costly MSA for the detection of bladder cancer, we developed three multiplex-polymerase-chain-reaction-(PCR)-based MSA assays, all of which were analyzed via a genetic analyzer. First, we selected 16 MSA markers based on 9 selected publications. Based on samples from Johns Hopkins University (the JHU sample, the first set sample), we developed an MSA based on triplet, three-tube-based multiplex PCR (a Triplet MSA assay). The discovery, validation, and translation of biomarkers for the early detection of cancer are the primary focuses of the Early Detection Research Network (EDRN), an initiative of the National Cancer Institute (NCI). A prospective study sponsored by the EDRN was undertaken to determine the efficacy of a novel set of MSA markers for the early detection of bladder cancer. This work and data analysis were performed through a collaboration between academics and industry partners. In the current study, we undertook a re-analysis of the primary data from the Compass study to enhance the predictive power of the dataset in bladder cancer diagnosis. Using a four-stage pipeline of modern machine learning techniques, including outlier removal with a nonlinear model, correcting for majority/minority class imbalance, feature engineering, and the use of a model-derived variable importance measure to select predictors, we were able to increase the utility of the original dataset to predict the occurrence of bladder cancer. The results of this analysis showed an increase in accuracy (85%), sensitivity (82%), and specificity (83%) compared to the original analysis. The re-analysis of the EDRN study results using machine learning statistical analysis proved to achieve an appropriate level of accuracy, sensitivity, and specificity to support the use of the MSA for bladder cancer detection and monitoring. This assay can be a significant addition to the tools urologists use to both detect primary bladder cancers and monitor recurrent bladder cancer.

From High-Throughput Experimentation to Data-Driven Analysis in the Development of Liquid Electrolytes for Lithium-Ion Batteries

Lithium-ion batteries (LIBs) are considered one of the best candidates to meet the skyrocketing demand for high energy density energy storage systems that was sparked by increasing popularity of portable electronics, electro-mobility and the necessary shift towards renewable energy sources.1 While the demand for energy storage systems rises rapidly, research moves forward rather sluggishly due to the complex interplay between the various active and inactive materials of a battery. One of the bottlenecks is the large time requirement and limited knowledge gain of typical, sequential experiments where one experiment is performed after the other. To mitigate this limitation, high-throughput experimentation (HTE) setups have been designed, where multiple experiments are performed in parallel rather than in sequence. Although they are common in other fields of research, high-throughput methods have not been widely adopted in battery research yet.2 Nevertheless, once a HTE setup is established, the bottleneck tends to move from the experiment to the data processing and analysis. Suitable tools to circumvent this are modern machine learning (ML) techniques, recognized as invaluable tools for accelerated material development. In most studies conducted for LIBs, only a limited number of electrolyte formulations is considered for a given set of individual electrolyte components due to aforementioned limitations of experimental capabilities. In this work, we have employed a unique HTE setup that is capable of applying electrochemical impedance spectroscopy (EIS) to 96 liquid electrolytes in a broad temperature range in parallel to study one of the fundamental bulk properties of liquid electrolytes; the ionic conductivity.Two large datasets of ionic conductivities were acquired for electrolytes consisting of lithium hexafluorophosphate (LiPF6), ethylene carbonate (EC), ethyl methyl carbonate (EMC) and either vinylene carbonate (VC) or propylene carbonate (PC) in the temperature range of -30 to 60 °C. Conducting salt concentration as well as solvent ratios were varied in wide ranges and experimental results bundled with all necessary metadata in an in-house developed .json file format for each individual experiment. More than 5000 individual conductivity values have been determined for 128 different electrolyte formulations in total. The conductivity datasets were used by our project partners in different ML approaches. Linear and Gaussian process regression were used to unravel the impact of individual electrolyte components on the ionic conductivity.3 Symbolic regression was used to discover an equation that directly models the conductivity based on the electrolyte formulation and has some common features with the empirical Debye-Hückel-Onsager equation.4 Active learning was used to improve an initial predictive model with as little additional experiments as possible in order to generate an accurate model for a given dataset.5 The presented work serves as a proof of concept in a system where the relation between parameters and observable are comparatively simple and is the foundation for applying similar principles of data processing, metadata handling and ML application to more complex experiments like galvanostatic cycling.

Artificial Neural Network-Based Computational Algorithm of Inverse Sumudu Transform Applied to Surface Transient Electromagnetic Sounding Method

Abstract ––The paper discusses the results of the development of a deep learning-based algorithm of the inverse Sumudu transform applied to the problem of on-ground non-stationary electromagnetic sounding. The Sumudu transform has potential for solving forward geoelectric problems in three-dimensional earth models because, unlike using the Laplace or Fourier transform, the Sumudu image of a real function is also a real function. Thus, there is no need to use complex numbers in subsequent calculations, which reduces computational costs and memory requirements in case of successful determination of the Sumudu image of the function. The disadvantages of the approach include the absence of an explicit method for calculating the inverse transform. The inversion can be done by solving the corresponding Fredholm integral equation of the first kind, but this is a poorly conditioned task leading to high requirements for the accuracy of the Sumudu image. The use of modern machine learning techniques can provide a method that is more robust to noise in the input data. This paper describes the process of creating a training dataset and developing a neural network algorithm; we evaluate the accuracy and performance of the obtained solution. The proposed method can contribute to the development of new approaches to physical processes modeling as well as to analysis, processing and interpretation of measured geophysical data.

Predicting asthma using imbalanced data modeling techniques: Evidence from 2019 Michigan BRFSS data

Studies in the past have examined asthma prevalence and the associated risk factors in the United States using data from national surveys. However, the findings of these studies may not be relevant to specific states because of the different environmental and socioeconomic factors that vary across regions. The 2019 Behavioral Risk Factor Surveillance System (BRFSS) showed that Michigan had higher asthma prevalence rates than the national average. In this regard, we employ various modern machine learning techniques to predict asthma and identify risk factors associated with asthma among Michigan adults using the 2019 BRFSS data. After data cleaning, a sample of 10,337 individuals was selected for analysis, out of which 1,118 individuals (10.8%) reported having asthma during the survey period. Typical machine learning techniques often perform poorly due to imbalanced data issues. To address this challenge, we employed two synthetic data generation techniques, namely the Random Over-Sampling Examples (ROSE) and Synthetic Minority Over-Sampling Technique (SMOTE) and compared their performances. The overall performance of machine learning algorithms was improved using both methods, with ROSE performing better than SMOTE. Among the ROSE-adjusted models, we found that logistic regression, partial least squares, gradient boosting, LASSO, and elastic net had comparable performance, with sensitivity at around 50% and area under the curve (AUC) at around 63%. Due to ease of interpretability, logistic regression is chosen for further exploration of risk factors. Presence of chronic obstructive pulmonary disease, lower income, female sex, financial barrier to see a doctor due to cost, taken flu shot/spray in the past 12 months, 18–24 age group, Black, non-Hispanic group, and presence of diabetes are identified as asthma risk factors. This study demonstrates the potentiality of machine learning coupled with imbalanced data modeling approaches for predicting asthma from a large survey dataset. We conclude that the findings could guide early screening of at-risk asthma patients and designing appropriate interventions to improve care practices.

Personalized Exercise Program Design with Machine Learning in Sensor Networks

The use of wearable solutions and sensors has reached the point of modern machine learning (ML) techniques in recent years. It contains the different programs that help to develop personalized opportunities for the betterment of the individuals. The research shed light upon the functions of ML and distributed sensor networks (DSN) in promoting healthcare among users. It can be said that the functions of the ML help to develop good fitness among the users, which results in good health. This dissertation consists of different kinds of ML algorithms and the usage of DSNs for the development of physical exercise programs. It has been found that most individuals use the sensors for their benefit in developing good health. The use of machine learning techniques not only helps to record an individual's health data but also sends emergency information to the nearest medical center for the user's benefit. The use of ML helps to the identification of the location of an individual with the help of GPS measures of real-time distance and users' health activities.

Advancing Financial Forecasts: A Deep Dive into Memory Attention and Long-Distance Loss in Stock Price Predictions

In the context of the rapid evolution of financial markets, the precise prediction of stock prices has become increasingly complex and challenging, influenced by a myriad of factors including macroeconomic indicators, company financial conditions, and market sentiment. A model integrating modern machine learning techniques has been introduced in this study, aimed at enhancing the accuracy of stock price prediction. To more effectively capture long-term dependencies in time series data, a novel memory attention module has been innovatively integrated and a unique long-distance loss function has been designed. Through a series of experimental validations, the effectiveness and superiority of this model in the realm of stock price prediction have been demonstrated, especially evident in the R2 evaluation metric, where an impressive score of 0.97 has been achieved. Furthermore, the purpose, methodology, data sources, and key results of this research have been elaborately detailed, aiming to provide fresh perspectives and tools for the field of stock price prediction and lay a solid foundation for future related studies. Overall, this research has not only enhanced the accuracy of stock price prediction but also made innovative contributions in terms of methodology and practical applications, bringing new thoughts and possibilities to the domain of financial analysis and prediction.

Analysis on Cybersecurity Threats in Modern Banking and Machine Learning Techniques for Fraud Detection

Analysis on Cybersecurity Threats in Modern Banking and Machine Learning Techniques for Fraud Detection