Combining Machine Learning Research Articles

Identification of Airline Turbulence Using WOA-CatBoost Algorithm in Airborne Quick Access Record (QAR) Data

Turbulence is a significant operational aviation safety hazard during all phases of flight. There is an urgent need for a method of airline turbulence identification in aviation systems to avoid turbulence hazards to aircraft during flight. Integrating flight data and machine learning significantly enhances the efficacy of turbulence identification. Nevertheless, present studies encounter issues including unstable model performance, challenges in data feature extraction, and parameter optimization. Hence, it is imperative to propose a superior approach to enhance the accuracy of turbulence identification along airline. The paper presents a combined swarm intelligence and machine learning model based on data mining for identifying airline turbulence. Based on the theory of swarm-intelligence-based optimization algorithm, the optimal parameters of Categorical Boosting (CatBoost) are obtained by introducing the whale optimization algorithm (WOA), and the corresponding WOA-CatBoost fusion model is established. Then, the Recursive Feature Elimination algorithm (RFE) is used to eliminate the data with lower feature weights, extract the effective features of the data, and the combination with the WOA brings robust optimization effects, whereby the accuracy of CatBoost increased by 11%. The WOA-CatBoost model can perform accurate turbulence identification from QAR data, comparable to that with established EDR approaches and outperforms traditional machine learning models. This discovery highlights the effectiveness of combining swarm intelligence and machine learning algorithms in turbulence monitoring systems to improve aviation safety.

Charge govern ion-selective mechanism of YX2 desalination pore using high-throughput computations and machine learning

Energy-efficient and low-cost desalination of water continues to be a problem that society is facing. With the advances in nanotechnology, a variety of nanopore membranes have emerged for desalination. In particular, YX2 nanopores (YW, Mo, etc. and X = S, Se, Te, etc.) have been considered as promising membranes for water purification. In this work, we used a combination of high-throughput molecular dynamics simulations and machine learning to reveal the nanopore mass transfer mechanism and rationally design the YX2 nanopore. The pore size and the charge of the pore mouth were found to be the main factors affecting water permeation and salt rejection, as discovered through the machine learning study. The physical-chemical analysis provides us with a deep understanding of the charge-governed mechanism on the desalination performance of YX2 nanopores. It revealed that YX2 nanopores with a conical shape and minimized pore charges could be ideal candidates for excellent desalination performance. Based on this, we designed the YX2 pore with a specific charge distribution, which could achieve high water permeation with high salt rejection. Therefore, the combination of machine learning and high-throughput computation methods could aid in designing materials with excellent performance for desalination.

Combined Machine Learning and Molecular Dynamics Reveal Two States of Hydration of a Single Functional Group of Cationic Polymeric Brushes

Combined Machine Learning and Molecular Dynamics Reveal Two States of Hydration of a Single Functional Group of Cationic Polymeric Brushes

Use of Artificial Intelligence in the Prediction of Chiari Malformation Type 1 Recurrence After Posterior Fossa Decompressive Surgery.

Purpose The purpose of this study was to train a deep learning-based method for the prediction of postoperative recurrence of symptoms in Chiari malformation type 1 (CM1) patients undergoing surgery. Studies suggest that certain radiological and clinical features do exist in patients with treatment failure, though these are inconsistent and poorly defined. Methodology This study was a retrospective cohort study of patients who underwent primary surgical intervention for CM1 from January 2010 to May 2020. Only patients who completed pre- and postoperative 12-item short form(SF-12) surveys were included and these were used to classify the recurrence or persistence of symptoms. Forty patients had an improvement in overall symptoms while 17 had recurrence or persistence. After magnetic resonance imaging (MRI) data augmentation, a ResNet50, pre-trained on the ImageNet dataset, was used for feature extraction, and then clustering-constrained attention multiple instance learning (CLAM), a weakly supervised multi-instance learning framework, was trained for prediction of recurrence. Five-fold cross-validation was used for the development of MRI only, clinical features only, and a combined machine learning model. Results This study included 57 patients who underwent CM1 decompression. The recurrence rate was 30%. The combined model incorporating MRI, pre-operative SF-12 physical component scale (PCS), and extent of cerebellar ectopia performed best with an area under the curve (AUC) of 0.71 and an F1 score of 0.74. Conclusion This is the first study to our knowledge to explore the prediction of postoperative recurrence of symptoms in CM1 patients using machine learning methods and represents the first steptowarddeveloping a clinically useful prognostication machine learning model. Further studies utilizing a similar deep learning approach with a larger sample size are needed to improve the performance.

Machine Learning-Guided Performance Evaluation of an All-Liquid Electrochromic Device.

Electrochromic devices, capable of modulating light transmittance under the influence of an electric field, have garnered significant interest in the field of smart windows and car rearview mirrors. However, the development of high-performance electrochromic devices via large-scale explorations under miscellaneous experimental settings remains challenging and is still an urgent problem to be solved. In this study, we employed a two-step machine learning approach, combining machine learning algorithms such as KNN and XGBoost with the reality of electrochromic devices, to construct a comprehensive evaluation system for electrochromic materials. Utilizing our predictive evaluation system, we successfully screened the preparation conditions for the best-performing device, which was experimentally verified to have a high transmittance modulation amplitude (62.6%) and fast response time (5.7 s/7.1 s) at 70 A/m2. To test its stability, experiments over a long cycle time (1000 cycles) are performed. In this study, we develop an innovative framework for assessing the performance of electrochromic material devices. Our approach effectively filters experimental samples based on their distinct properties, substantially minimizing the expenditure of human and material resources in electrochromic research. Our approach to a mathematical machine learning evaluation framework for device performance has effectively propelled and informed research in electrochromic devices.

Fashion Recommendation System

Fashion recommendation systems have become increasingly essential in the e-commerce industry, providing personalized outfit suggestions to users, enhancing their shopping experience, and boosting sales. This paper presents a novel approach to fashion recommendation by combining machine learning and deep learning techniques. We leverage a comprehensive dataset of user preferences and fashion items to create a robust recommendation system. Our approach first employs collaborative filtering and matrix factorization methods to establish user-item interactions. Subsequently, deep learning models, such as neural collaborative filtering and recurrent neural networks, are utilized to capture intricate patterns within the fashion data. This combination enables the system to offer personalized fashion recommendations based on the user's historical choices, style, and real-time Behaviour. The evaluation of our system demonstrates its effectiveness in enhancing user engagement and satisfaction while increasing the platform's revenue. The proposed fashion recommendation system showcases the potential of integrating machine learning and deep learning for optimizing personalized fashion suggestions in the ever- evolving fashion e-commerce landscape. This research contributes to the broader field of recommendation systems and their applications in the fashion industry.

An artificial neural network diagnostic model for scleroderma and immune cell infiltration analysis based on mitochondria-associated genes

To establish a diagnostic model for scleroderma by combining machine learning and artificial neural network based on mitochondria-related genes. The GSE95065 and GSE59785 datasets of scleroderma from GEO database were used for analyzing expressions of mitochondria-related genes, and the differential genes were identified by Random forest, LASSO regression and SVM algorithms. Based on these differential genes, an artificial neural network model was constructed, and its diagnostic accuracy was evaluated by 10-fold crossover verification and ROC curve analysis using the verification dataset GSE76807. The mRNA expressions of the key genes were verified by RT-qPCR in a mouse model of scleroderma. The CIBERSORT algorithm was used to estimate the bioinformatic association between scleroderma and the screened biomarkers. A total of 24 differential genes were obtained, including 11 up-regulated and 13 down-regulated genes. Seven most relevant mitochondria-related genes (POLB, GSR, KRAS, NT5DC2, NOX4, IGF1, and TGM2) were screened using 3 machine learning algorithms, and the artificial neural network diagnostic model was constructed. The model showed an area under the ROC curves of 0.984 for scleroderma diagnosis (0.740 for the verification dataset and 0.980 for cross-over validation). RT-qPCR detected significant up-regulation of POLB, GSR, KRAS, NOX4, IGF1 and TGM2 mRNAs and significant down-regulation of NT5DC2 in the mouse models of scleroderma. Immune cell infiltration analysis showed that the differential genes in scleroderma were associated with follicular helper T cells, immature B cells, resting dendritic cells, memory activated CD4+T cells, M0 macrophages, monocytes, resting memory CD4+T cells and mast cell activation. The artificial neural network diagnostic model for scleroderma established in this study provides a new perspective for exploring the pathogenesis of scleroderma.

A hybrid data-driven method optimized by physical rules for online state collaborative estimation of lithium-ion batteries

Accurate online estimation of state of charge (SOC) and state of health (SOH) is crucial for safe operation and reasonable planning of battery management system (BMS). However, battery internal states are unmeasurable directly and coupled with each other, which results in serious difficulties on multi-states accurate estimation. Considering SOC estimation is deeply influenced by SOH, this paper proposes a collaborative estimation method combined machine learning algorithm with simple physical rule. Integrated the merits of the above methods, it can not only improve the estimating accuracy but also low computational burden to a large extent. Firstly, SOH acts as input of SOC in collaboration, which means SOH should have been already known before SOC estimation operation. Thus, SOH is creatively predicted based on gate recurrent unit network in ahead of SOC estimation. Subsequently, the well-trained SOC data-driven model is combined with the ampere hour (Ah) integration, which act as observation and state equation respectively in the particle filtering algorithm to realize the final estimation of SOC. This way, the sole data-driven model is well improved under physics restriction without any other computational procedure, such as online parameter identification. Simultaneously, the predicted SOH is used to fill the Ah integration expression to realize the collaboration between SOC and SOH. What's more, the SOH is further corrected by the incremental capacity peak at the checkpoint, thereby further reducing the estimation deviation. The experimental result on battery shows that the SOH estimated error is below 0.3Ah (the rated capacity is 32.5Ah) and SOC error is less than 1.5 %. What's more, the generalization capacity of the proposed method is verified on different battery types based on public datasets. Obviously, the proposed method has fairly satisfactory property and performance and can totally support its promotion into state online evaluation of battery energy storage.

A Comprehensive Review of the Impact of Machine Learning and Omics on Rare Neurological Diseases

Background: Rare diseases, predominantly caused by genetic factors and often presenting neurological manifestations, are significantly underrepresented in research. This review addresses the urgent need for advanced research in rare neurological diseases (RNDs), which suffer from a data scarcity and diagnostic challenges. Bridging the gap in RND research is the integration of machine learning (ML) and omics technologies, offering potential insights into the genetic and molecular complexities of these conditions. Methods: We employed a structured search strategy, using a combination of machine learning and omics-related keywords, alongside the names and synonyms of 1840 RNDs as identified by Orphanet. Our inclusion criteria were limited to English language articles that utilized specific ML algorithms in the analysis of omics data related to RNDs. We excluded reviews and animal studies, focusing solely on studies with the clear application of ML in omics data to ensure the relevance and specificity of our research corpus. Results: The structured search revealed the growing use of machine learning algorithms for the discovery of biomarkers and diagnosis of rare neurological diseases (RNDs), with a primary focus on genomics and radiomics because genetic factors and imaging techniques play a crucial role in determining the severity of these diseases. With AI, we can improve diagnosis and mutation detection and develop personalized treatment plans. There are, however, several challenges, including small sample sizes, data heterogeneity, model interpretability, and the need for external validation studies. Conclusions: The sparse knowledge of valid biomarkers, disease pathogenesis, and treatments for rare diseases presents a significant challenge for RND research. The integration of omics and machine learning technologies, coupled with collaboration among stakeholders, is essential to develop personalized treatment plans and improve patient outcomes in this critical medical domain.

Integration of machine learning in the supply chain for decision making: A systematic literature review

Purpose: This study presents a systematic literature review that provides a broad and holistic view of how machine learning can be used and integrated to enhance decision-making in various areas of the supply chain, highlighting its combination with other techniques and models.Design/methodology/approach: An exhaustive literature review used three sets of keywords in the Scopus and Web of Science (WoS) databases. Through a rigorous filtering process, 70 articles were selected from an initial total of 410, focusing on those that specifically addressed the intersection of machine learning and decision-making in supply chain management.Findings: Machine learning has proven to be an essential tool in the supply chain, with applications in inventory management, logistics, and transportation, among others. Its integration with other techniques has led to significant advances in decision-making, improving efficiency in complex environments. Combining machine learning methods with traditional techniques has been particularly effective, and integration with emerging technologies has opened up new application possibilities.Originality/value: Unlike previous studies that focused on specific areas, this study offers a broad perspective on the application of machine learning in the supply chain. Additionally, combining machine learning techniques with other models is highlighted, representing added value for the scientific community and suggesting new avenues for future research.

Combined Machine Learning and High-Throughput Calculations Predict Heyd-Scuseria-Ernzerhof Band Gap of 2D Materials and Potential MoSi2N4 Heterostructures.

We present a novel target-driven methodology devised to predict the Heyd-Scuseria-Ernzerhof (HSE) band gap of two-dimensional (2D) materials leveraging the comprehensive C2DB database. This innovative approach integrates machine learning and density functional theory (DFT) calculations to predict the HSE band gap, conduction band minimum (CBM), and valence band maximum (VBM) of 2176 types of 2D materials. Subsequently, we collected a comprehensive data set comprising 3539 types of 2D materials, each characterized by its HSE band gaps, CBM, and VBM. Considering the lattice disparities between MoSi2N4 (MSN) and 2D materials, our analysis predicted 766 potential MSN/2D heterostructures. These heterostructures are further categorized into four distinct types based on the relative positions of their CBM and VBM: Type I encompasses 230 variants, Type II comprises 244 configurations, Type III consists of 284 permutations, and 0 band gap comprises 8 types.

Accelerating ionizable lipid discovery for mRNA delivery using machine learning and combinatorial chemistry.

To unlock the full promise of messenger (mRNA) therapies, expanding the toolkit of lipid nanoparticles is paramount. However, a pivotal component of lipid nanoparticle development that remains a bottleneck is identifying new ionizable lipids. Here we describe an accelerated approach to discovering effective ionizable lipids for mRNA delivery that combines machine learning with advanced combinatorial chemistry tools. Starting from a simple four-component reaction platform, we create a chemically diverse library of 584 ionizable lipids. We screen the mRNA transfection potencies of lipid nanoparticles containing those lipids and use the data as a foundational dataset for training various machine learning models. We choose the best-performing model to probe an expansive virtual library of 40,000 lipids, synthesizing and experimentally evaluating the top 16 lipids flagged. We identify lipid 119-23, which outperforms established benchmark lipids in transfecting muscle and immune cells in several tissues. This approach facilitates the creation and evaluation of versatile ionizable lipid libraries, advancing the formulation of lipid nanoparticles for precise mRNA delivery.

A Novel Framework on Book-Recommendation System

With so many books available these days, effective book recommendation engines are crucial to pointing readers in the direction of choices that suit their interests. This paper introduces a prediction algorithm that uses user ratings to improve book recommendations. The program attempts to precisely forecast and rank the top 50 books for specific users by examining user-provided book ratings. The research methodology utilized in this study generates tailored recommendations by combining machine learning algorithms with collaborative filtering techniques. In order to provide predictions, collaborative filtering looks for trends in user behavior and preferences and compares users and books. To be more precise, the model finds books that people with similar preferences have liked by using similarity measures and user-item matrices. The effectiveness of the predictive model is evaluated using a sizable dataset of user-rated novels. The model is guaranteed to be resilient and adaptable to a large range of literary interests due to the dataset's broad scope in terms of genres, authors, and publishing years. Recall, accuracy, and precision are among the performance metrics used to assess how well the model can recommend books to readers based on their interests. The predictive model's ability to produce individualized book recommendations based on user ratings is demonstrated by the results. The model's prediction of the top 50 books is highly relevant and aligned with users' likes, which improves readers' browsing and selecting experience. The concept also exhibits scalability and flexibility, making it possible to accommodate growing book catalogs and changing customer preferences. All things considered, this work advances book recommendation systems by introducing a predictive model that uses user ratings to produce tailored recommendations. The approach improves reading enjoyment and encourages readers to become more deeply involved with books by making it easier for them to find interesting and engaging literary content..

Orthotropic failure criteria based on machine learning and micro-mechanical matrix adapting coefficient

Several studies have examined the use of fibrous and non-fibrous anisotropic materials in various industries and proposed failure criteria for consideration. These criteria can be categorized into theories that address specific failure modes and those that do not. However, these theories often fail to address both the representation of inherent material properties and the combination of different loading modes. To address this, a micromechanical approach called micromechanical modeling of laminates (“MACML”) has been developed, which gradually transitions from anisotropic to isotropic materials by incorporating reinforcement and adapting coefficients. MACML combines machine learning (ML) techniques and introduces a new method to identify safe and failure-prone regions in composites. This approach allows for independence from the influence of fibers by representing them as an active stress proportion of the isotropic matrix. Additionally, standard experimental procedures can be applied based on the isotropic matrix, and experimental results have been conducted to validate the established failure criteria in the MACML method.

Mapping the application research on machine learning in the field of ionic liquids: A bibliometric analysis

The aim was to gain a deep understanding of the research status and application of machine learning in the field of ionic liquids, and to identify the research hotspots and frontiers. Co-occurrence analysis, co-citation analysis, key literature citation temporal analysis and emerging word analysis were used. The results show that the knowledge base of applying machine learning in the field of ionic liquids can be divided into three parts: fundamental properties and application research, thermodynamics and phase equilibrium research, and the combination of machine learning with computational chemistry methods. The research hotspots mainly include the prediction and optimization of properties, the prediction of phase behavior, and research on machine learning algorithms. The current research frontiers in applying machine learning in the field of ionic liquids include the prediction of ionic liquid performance, the structure-property relationships of ionic liquids, and the optimization and design of ionic liquid processes.

High throughput screening of thermal interface materials by machine learning

Till now, it remains a challenge for effective prediction and screening of novel materials with high thermal conductivity, as well as further optimization of the interface thermal resistance. Normally, people have to spend long time on tedious calculations when predicting and screening these materials. In this paper, I combined machine learning with molecular dynamics simulations to investigate the thermal conductive properties of materials with the aim of significantly reducing computational consumption. I first applied molecular dynamics simulations to obtain the relevant properties of materials, then generated models for predicting physical properties by machine learning, and finally made predictions of thermophysical properties of materials. The use of machine learning significantly reduces the prediction time compared to direct molecular dynamics simulations. Especially when the XGBoost and the neural network models are employed, the prediction efficiency is significantly improved. This work guides a new way for the future screening of high-performance thermal interface materials.

A Typology of Social Media Use by Human Service Nonprofits: Mixed Methods Study.

Nonprofit organizations are increasingly using social media to improve their communication strategies with the broader population. However, within the domain of human service nonprofits, there is hesitancy to fully use social media tools, and there is limited scope among organizational personnel in applying their potential beyond self-promotion and service advertisement. There is a pressing need for greater conceptual clarity to support education and training on the varied reasons for using social media to increase organizational outcomes. This study leverages the potential of Twitter (subsequently rebranded as X [X Corp]) to examine the online communication content within a sample (n=133) of nonprofit sexual assault (SA) centers in Canada. To achieve this, we developed a typology using a qualitative and supervised machine learning model for the automatic classification of tweets posted by these centers. Using a mixed methods approach that combines machine learning and qualitative analysis, we manually coded 10,809 tweets from 133 SA centers in Canada, spanning the period from March 2009 to March 2023. These manually labeled tweets were used as the training data set for the supervised machine learning process, which allowed us to classify 286,551 organizational tweets. The classification model based on supervised machine learning yielded satisfactory results, prompting the use of unsupervised machine learning to classify the topics within each thematic category and identify latent topics. The qualitative thematic analysis, in combination with topic modeling, provided a contextual understanding of each theme. Sentiment analysis was conducted to reveal the emotions conveyed in the tweets. We conducted validation of the model with 2 independent data sets. Manual annotation of 10,809 tweets identified seven thematic categories: (1) community engagement, (2) organization administration, (3) public awareness, (4) political advocacy, (5) support for others, (6) partnerships, and (7) appreciation. Organization administration was the most frequent segment, and political advocacy and partnerships were the smallest segments. The supervised machine learning model achieved an accuracy of 63.4% in classifying tweets. The sentiment analysis revealed a prevalence of neutral sentiment across all categories. The emotion analysis indicated that fear was predominant, whereas joy was associated with the partnership and appreciation tweets. Topic modeling identified distinct themes within each category, providing valuable insights into the prevalent discussions surrounding SA and related issues. This research contributes an original theoretical model that sheds light on how human service nonprofits use social media to achieve their online organizational communication objectives across 7 thematic categories. The study advances our comprehension of social media use by nonprofits, presenting a comprehensive typology that captures the diverse communication objectives and contents of these organizations, which provide content to expand training and education for nonprofit leaders to connect and engage with the public, policy experts, other organizations, and potential service users.

BiSpec Pairwise AI: guiding the selection of bispecific antibody target combinations with pairwise learning and GPT augmentation

PurposeBispecific antibodies (BsAbs), capable of targeting two antigens simultaneously, represent a significant advancement by employing dual mechanisms of action for tumor suppression. However, how to pair targets to develop effective and safe bispecific drugs is a major challenge for pharmaceutical companies.MethodsUsing machine learning models, we refined the biological characteristics of currently approved or in clinical development BsAbs and analyzed hundreds of membrane proteins as bispecific targets to predict the likelihood of successful drug development for various target combinations. Moreover, to enhance the interpretability of prediction results in bispecific target combination, we combined machine learning models with Large Language Models (LLMs). Through a Retrieval-Augmented Generation (RAG) approach, we supplement each pair of bispecific targets’ machine learning prediction with important features and rationales, generating interpretable analytical reports.ResultsIn this study, the XGBoost model with pairwise learning was employed to predict the druggability of BsAbs. By analyzing extensive data on BsAbs and designing features from perspectives such as target activity, safety, cell type specificity, pathway mechanism, and gene embedding representation, our model is able to predict target combinations of BsAbs with high market potential. Specifically, we integrated XGBoost with the GPT model to discuss the efficacy of each bispecific target pair, thereby aiding the decision-making for drug developers.ConclusionThe novelty of this study lies in the integration of machine learning and GPT techniques to provide a novel framework for the design of BsAbs drugs. This holistic approach not only improves prediction accuracy, but also enhances the interpretability and innovativeness of drug design.

Effects of Hard-to-Measure Material Parameters on Clinching Joint Geometries Using Combined Finite Element Method and Machine Learning

<div>In this article, we investigated the effects of material parameters on the clinching joint geometry using finite element model (FEM) simulation and machine learning-based metamodels. The FEM described in this study was first developed to reproduce the shape of clinching joints between two AA5052 aluminum alloy sheets. Neural network metamodels were then used to investigate the relation between material parameters and joint geometry as predicted by FEM. By interpreting the data-driven metamodels using explainable machine learning techniques, the effects of the hard-to-measure material parameters during the clinching are studied. It is demonstrated that the friction between the two metal sheets and the flow stress of the material at high (up to 100%) plastic strain are the most influential factors on the interlock and the neck thickness of the clinching joints. However, their dependence on the material parameters is found to be opposite. First, while the friction between the two metal sheets promotes the formation of the interlock, it reduces the neck thickness and thus increases the risk of breaking in this region. Second, it is easier to form the interlock if the deformed material exhibits small flow stress at high plastic strain, but the neck thickness tends to be thinner in this case. The identified material parameters help to significantly reduce the relative error between the simulated results and the experimental results, not only in the configurations from which they are identified but also in a new configuration. This methodology shows its potential in the cases where material parameters are not available or difficult to measure.</div>

Weather Forecasting: A Comprehensive Exploration of IoT and Machine Learning

Weather forecasting play an important role in human lives.It is impacting on various human activities such as agriculture and transportation.Changes in climate conditions often lead to unpredictable weather. Conventional forecasting models sometimes provide inaccurate predictions because they don't adapt well to the dynamic nature of climate.The integration of (IoT) and Machine Learning (ML) technologies has revolutionized weather forecasting methodologies.This paper explores how combining Machine Learning (ML) algorithms with Internet of Things (IoT) devices improves weather forecasting accuracy and efficiency. By analyzing real-time data and historical patterns, this paper shows how IoT and ML can offer more accurate and timely forecasts compare to the limitations of traditional methods.Accurate weather forecasts are really important for things like farming, transportation, saving energy.In this paper the effectiveness of the algorithm is evaluated using various performance metrics including r2 score comparison,mean square error comparison. Key Words: IOT,Machine Learning,Support Vector Machine