Powerful Machine Research Articles

Random forest models reveal academic and financial factors outweigh demographics in predicting completion of a year-round veterinary program.

The purpose of this study was to develop random forest classifier models (a type of supervised machine learning algorithm) that could (1) predict students who will or will not complete the DVM degree requirements and (2) identify the top predictors for academic success and completion of the DVM degree. The study utilized Ross University School of Veterinary Medicine student records from 2013 to 2022. Twenty-four variables encompassing demographic (eg, age, race), academic (eg, grade point average), and financial aid (eg, outstanding balances) data were assessed in 11 cross-validated random forest machine learning models. One model was built assessing all years of data and 10 individual models were developed for each enrollment year to compare how the top predictors of success varied among the years. Consistently, only academic and financial factors were identified as being features of importance (predictors) in all models. Demographic factors such as race were not important for predicting student success. All models performed very well to excellently based on multiple performance metrics including accuracy, ranging from 96.1% to 99%, and the areas under the receiver operating characteristic curves, ranging from 98.1% to 99.9%. The random forest algorithm is a powerful machine learning prediction model that performs well with veterinary student academic records and is customizable such that variables important to each veterinary school's student population can be assessed. Identifying predictors of success as well as at-risk students is essential for providing targeted curricular interventions to increase retention and achieve timely completion of a DVM degree.

Revolutionizing Cardio Vascular Disease Diagnosis Through Lasso Regression Model

Cardiovascular diseases (CVDs) are among the most prevalent and fatal health conditions globally, necessitating early and accurate diagnosis to mitigate risk and enhance treatment outcomes. Traditional diagnostic methods often rely on a combination of clinical assessments and static risk models, which can be constrained by their inability to handle the complexity and interrelationships of multiple risk factors. In this research, we propose a novel approach to revolutionizing cardiovascular disease diagnosis through the application of the Lasso (Least Absolute Shrinkage and Selection Operator) regression model, a powerful machine learning technique for feature selection and predictive modeling. The Lasso regression model is particularly advantageous for high-dimensional medical datasets, where multiple clinical features may be correlated. By applying Lasso, we aim to address two critical challenges in cardiovascular disease prediction: identifying the most relevant predictors from large and complex datasets and reducing model over-fitting, which is common when working with a large number of co-variates. Our results demonstrated that the Lasso model significantly improves prediction accuracy when compared to traditional logistic regression and other machine learning models. Lasso regression has the potential to revolutionize cardiovascular disease diagnosis by providing a data-driven, efficient, and interpretable solution that bridges complex medical datasets with practical clinical decision-making. Keywords: Cardio vascular diseases (CVD), Machine learning models, Losso regression model.

Machine learning unveils key Redox signatures for enhanced breast Cancer therapy

BackgroundBreast cancer remains a leading cause of mortality among women worldwide, necessitating innovative prognostic models to enhance treatment strategies.MethodsOur study retrospectively enrolled 9,439 breast cancer patients from 12 independent datasets and single-cell data from 12 patients (64,308 cells). Moverover, 30 in-house clinical cohort were collected for validation. We employed a comprehensive approach by combining ten distinct machine learning algorithms across 108 different combinations to scrutinize 88 pre-existing signatures of breast cancer. To affirm the efficacy of our developed model, immunohistochemistry assays were performed. Additionally, we investigated various potential immunotherapeutic and chemotherapeutic interventions.ResultsThis study introduces an Artificial Intelligence-aided Redox Signature (AIARS) as a novel prognostic tool, leveraging machine learning to identify critical redox-related gene signatures in breast cancer. Our results demonstrate that AIARS significantly outperforms existing prognostic models in predicting breast cancer outcomes, offering a robust tool for personalized treatment planning. Validation through immunohistochemistry assays on samples from 30 patients corroborated our results, underscoring the model’s applicability on a wider scale. Furthermore, the analysis revealed that patients with low AIARS expression levels are more responsive to immunotherapy. Conversely, those exhibiting high AIARS were found to be more susceptible to certain chemotherapeutic agents, including vincristine.ConclusionsOur study underscores the importance of redox biology in breast cancer prognosis and introduces a powerful machine learning-based tool, the AIARS, for personalized treatment strategies. By providing a more nuanced understanding of the redox landscape in breast cancer, the AIARS paves the way for the development of redox-targeted therapies, promising to enhance patient outcomes significantly. Future work will focus on clinical validation and exploring the mechanistic roles of identified genes in cancer biology.

Analysis of the Principle and Applications of Four-stroke Engines in Transportation

Abstract. Four-stroke engines a type of internal combustion engine (IC engine) that can turn the heat provided from the fuel to work, and they are mainly classified as two groups, which are gasoline engines and diesel engines. Four-stroke engines can be applied to high power machines because of its high thermal efficiency. In four-stroke engines, the piston reaches the dead center four times in the cylinder to complete a cycle. This cycle includes the taking in of gas, the compression, the ignition, the expansion and the exhaustion of gas. In gasoline engine, this cycle is called the Otto cycle, and in diesel engine, this cycle is called the Diesel cycle. The greatest difference between these two engines is that they burn different types of fuel. In that way, the procedure of converting the heat to work is different. To help this cycle performs better economically and more efficiently, additional attachments such as hybrid engine and computer assistance are used. This research summarizes and analyses the application of four-stroke engines in land transportation, in aviation and in marine transportation, and this article gives a possible prediction to the future trend of the technology advancements of engines in transportation based on the analyses.

Exploring Diversity and Abundance of Stingless Bee using Clustering Approach

Stingless bees are paramount in food chain as they are important pollinators of field crops. Recent studies revealed that these bees are seriously threatened by climate change and rapid urbanization across the world. It is thus important to study the relationship between the stingless bee’s diversity and the characteristics of the locations they inhibit. At the same time, clustering algorithms is a powerful machine learning approach in exploring unsupervised data. Consequently, this study aims to explore the stingless bee diversity in Malaysia through hierarchical, k-means and DBSCAN clustering. The dataset of this study consists of individual stingless bees collected from 12 locations. It comprises 14 environmental features, 3 physical characteristics, 35 species count, 12 genera counts and 3 diversity-and-abundance weights. A four-stage methodology is employed in the study. The results show that DBSCAN effectively groups data into clusters that are well-defined, but the results are less informative. In contrast, hierarchical and k-means clustering are found producing results that provide clearer insights, with hierarchical clustering delivering notably richer results.

Permutation-equivariant quantum convolutional neural networks

Abstract The Symmetric group $S_{n}$ manifests itself in large classes of quantum systems as the invariance of certain characteristics of a quantum state with respect to permuting the qubits. Subgroups of $S_{n}$ arise, among many other contexts, to describe label symmetry of classical images with respect to spatial transformations, such as reflection or rotation. Equipped with the formalism of geometric quantum machine learning, in this study we propose the architectures of equivariant quantum convolutional neural networks (EQCNNs) adherent to $S_{n}$ and its subgroups. We demonstrate that a careful choice of pixel-to-qubit embedding order can facilitate easy construction of EQCNNs for small subgroups of $S_{n}$. Our novel EQCNN architecture corresponding to the full permutation group $S_{n}$ is built by applying all possible QCNNs with equal probability, which can also be conceptualized as a dropout strategy in quantum neural networks. For subgroups of $S_{n}$, our numerical results using MNIST datasets show better classification accuracy than non-equivariant QCNNs. The $S_{n}$-equivariant QCNN architecture shows significantly improved training and test performance than non-equivariant QCNN for classification of connected and non-connected graphs. When trained with sufficiently large number of data, the $S_{n}$-equivariant QCNN shows better average performance compared to $S_{n}$-equivariant QNN . These results contribute towards building powerful quantum machine learning architectures in permutation-symmetric systems.

AI-driven canine cataract detection: a machine learning approach using support vector machine

ABSTRACT The pivotal role of the Support Vector Machine becomes evident in addressing the impact of aging and genetics on canine cataract development. Timely detection, crucial for preventing illness in dogs, is facilitated by Artificial Intelligence. This proves especially beneficial for veterinarians grappling with detection challenges. Within the realm of Artificial Intelligence, the subset of Machine Learning emerges as a promising avenue for tackling intricate tasks. The current study introduces a model for grading canine cataracts through images captured on standard mobile phone cameras. Notably, the proposed system centers around harnessing the power of the Support Vector Machine, a potent Machine Learning algorithm tailored for classifying (grading) cataracts based on images. Rigorous evaluation, employing K-fold Cross-validation, validates the images’ reliability. Both binary-class and multi-class experimentation contribute to the dataset. Impressively, the accuracy rates for the trained classification model stand at 83% (without Cross-validation) and 81% (with Cross-validation for K = 10), underscoring the robustness of the approach.

Controller design and optimal sizing of battery energy storage system for frequency regulation in a multi machine power system

Frequency regulation is one of the key components needed to keep the power grid stable and reliable in the case of an imbalance between generation and load. This study looks at several control techniques for Battery Energy Storage Systems (BESSs) to keep the frequency stable in the power system during generation/load disruptions. This research aims to build several BESS controllers, including the proportional-integral (PI), proportional integral derivative (PID), and Tilt-Integral Derivative (TID) controllers. Also, the BESS controller parameters are optimized and compared by using metaheuristics based particle swarm optimization (PSO) and the BAT algorithm. However, for practical power systems with high MVA ratings, the size of the battery energy storage systems has to be increased considerably to offset frequency deviations. Additionally, by utilizing PSO to reduce the frequency deviations within prescribed limits, this work presents the optimal BESS sizing for multimachine power systems. Furthermore, the research study examines the impact of BESS connected to various voltage levels, such as LV, MV, and HV subgrids. It also examines BESS's role in frequency management, which is an area of expertise that needs further investigation and is anticipated to have a big influence on the frequency stability of the system. Time domain simulations are carried out, which shows that the PSO based controller design is capable of stabilizing the system frequency with superior performance as well as the BESS's capability to participate effectively in frequency regulation. Additionally, this paper also implements the experimental verification through Hardware-in-the-Loop (HIL) simulations to validate the performance and robustness of the proposed control system. The WSCC 9-bus test system is used to demonstrate the BESS's efficacy. The system is modelled and simulated using the DIgSILENT PowerFactory software.

Clinical information extraction for lower-resource languages and domains with few-shot learning using pretrained language models and prompting

Abstract A vast amount of clinical data are still stored in unstructured text. Automatic extraction of medical information from these data poses several challenges: high costs of clinical expertise, restricted computational resources, strict privacy regulations, and limited interpretability of model predictions. Recent domain adaptation and prompting methods using lightweight masked language models showed promising results with minimal training data and allow for application of well-established interpretability methods. We are first to present a systematic evaluation of advanced domain-adaptation and prompting methods in a lower-resource medical domain task, performing multi-class section classification on German doctor’s letters. We evaluate a variety of models, model sizes (further-pre)training and task settings, and conduct extensive class-wise evaluations supported by Shapley values to validate the quality of small-scale training data and to ensure interpretability of model predictions. We show that in few-shot learning scenarios, a lightweight, domain-adapted pretrained language model, prompted with just 20 shots per section class, outperforms a traditional classification model, by increasing accuracy from $48.6\%$ to $79.1\%$ . By using Shapley values for model selection and training data optimization, we could further increase accuracy up to $84.3\%$ . Our analyses reveal that pretraining of masked language models on general-language data is important to support successful domain-transfer to medical language, so that further-pretraining of general-language models on domain-specific documents can outperform models pretrained on domain-specific data only. Our evaluations show that applying prompting based on general-language pretrained masked language models combined with further-pretraining on medical-domain data achieves significant improvements in accuracy beyond traditional models with minimal training data. Further performance improvements and interpretability of results can be achieved, using interpretability methods such as Shapley values. Our findings highlight the feasibility of deploying powerful machine learning methods in clinical settings and can serve as a process-oriented guideline for lower-resource languages and domains such as clinical information extraction projects.

Sentiment classification for insider threat identification using metaheuristic optimized machine learning classifiers

This study examines the formidable and complex challenge of insider threats to organizational security, addressing risks such as ransomware incidents, data breaches, and extortion attempts. The research involves six experiments utilizing email, HTTP, and file content data. To combat insider threats, emerging Natural Language Processing techniques are employed in conjunction with powerful Machine Learning classifiers, specifically XGBoost and AdaBoost. The focus is on recognizing the sentiment and context of malicious actions, which are considered less prone to change compared to commonly tracked metrics like location and time of access. To enhance detection, a term frequency-inverse document frequency-based approach is introduced, providing a more robust, adaptable, and maintainable method. Moreover, the study acknowledges the significant impact of hyperparameter selection on classifier performance and employs various contemporary optimizers, including a modified version of the red fox optimization algorithm. The proposed approach undergoes testing in three simulated scenarios using a public dataset, showcasing commendable outcomes.

Towards the genomic sequence code of DNA fragility for machine learning.

Genomic DNA breakages and the subsequent insertion and deletion mutations are important contributors to genome instability and linked diseases. Unlike the research in point mutations, the relationship between DNA sequence context and the propensity for strand breaks remains elusive. Here, by analyzing the differences and commonalities across myriads of genomic breakage datasets, we extract the sequence-linked rules and patterns behind DNA fragility. We show the overall deconvolution of the sequence influence into short-, mid- and long-range effects, and the stressor-dependent differences in defining the range and compositional effects on DNA fragility. We summarize and release our feature compendium as a library that can be seamlessly incorporated into genomic machine learning procedures, where DNA fragility is of concern, and train a generalized DNA fragility model on cancer-associated breakages. Structural variants (SVs) tend to stabilize regions in which they emerge, with the effect most pronounced for pathogenic SVs. In contrast, the effects of chromothripsis are seen across regions less prone to breakages. We find that viral integration may bring genome fragility, particularly for cancer-associated viruses. Overall, this work offers novel insights into the genomic sequence basis of DNA fragility and presents a powerful machine learning resource to further enhance our understanding of genome (in)stability and evolution.

Intraoperative Hypotension Prediction: Current Methods, Controversies, and Research Outlook.

Intraoperative hypotension prediction has been increasingly emphasized due to its potential clinical value in reducing organ injury and the broad availability of large-scale patient datasets and powerful machine learning tools. Hypotension prediction methods can mitigate low blood pressure exposure time. However, they have yet to be convincingly demonstrated to improve objective outcomes; furthermore, they have recently become controversial. This review presents the current state of intraoperative hypotension prediction and makes recommendations on future research. We begin by overviewing the current hypotension prediction methods, which generally rely on the prevailing mean arterial pressure as one of the important input variables and typically show good sensitivity and specificity but low positive predictive value in forecasting near-term acute hypotensive events. We make specific suggestions on improving the definition of acute hypotensive events and evaluating hypotension prediction methods, along with general proposals on extending the methods to predict reduced blood flow and treatment effects. We present a start of a risk-benefit analysis of hypotension prediction methods in clinical practice. We conclude by coalescing this analysis with the current evidence to offer an outlook on prediction methods for intraoperative hypotension. A shift in research toward tailoring hypotension prediction methods to individual patients and pursuing methods to predict appropriate treatment in response to hypotension appear most promising to improve outcomes.

Non-specific myocardial fibrosis in young competitive athletes: clinical significance and risk prediction by a powerful machine learning-based model.

Non-specific myocardial fibrosis (NSMF) is a heterogeneous entity. We aimed to evaluate young athletes with and without NSMF to establish potentially clinically significance. We analysed data from 328 young athletes. We identified 61 with NSMF and compared them with 75 matched controls. Athletes with NSMF were divided into Group 1 (n = 28) with 'minor' fibrosis and Group 2 (n = 33) with non-insertion point fibrosis, defined as 'major'. Athletes were followed-up for adverse events. Finally, we tested various machine learning (ML) algorithms to create a prediction model for 'major' fibrosis. We created 4 different classifiers. Athletes of black ethnicity were more likely to have a subepicardial pattern (OR: 5.0, p = 0.004). Athletes with 'major' fibrosis demonstrated a higher prevalence of lateral T-wave inversion (TWI) ( < 0.001) and ventricular arrhythmias (VEs > 500/24h, p = 0.046; non-sustained VT, p = 0.043). Athletes with 'minor' fibrosis demonstrated higher right ventricular volumes (p = 0.013), maximum Watts (p = 0.022) and maximum VO2 (p = 0.005). Lateral TWI (p = 0.026) and VO2 < 44mL/min/Kg (p = 0.040) remained the only significant predictors for 'major' fibrosis. During follow up, athletes with 'major' fibrosis were 9.1 times more likely to exhibit adverse events (OR 13.4, p = 0.041). All ML models outperformed the benchmark method in predicting significant MF, best accuracy achieved by the random forest classifier (90%). Lateral TWI and reduced exercise performance are associated with higher burden of fibrosis. Fibrosis was associated with increased ventricular arrhythmia and adverse events. A comprehensive assessment can help develop a ML-based model for significant fibrosis, which could also guide clinical practice and appropriate CMR referrals.

ISETECH-Statistics and Machine Learning Based Decision-Making for Diet Beverage Choice and Recommendation through Software Application

Positioned within the realm of ubiquitous beverage chains acclaimed for their diverse coffee and tea offerings, this investigation deeply explores the intricate nutritional dynamics and caloric compositions of these widely consumed beverages. At its core, the research aims to streamline decision-making for individuals actively seeking health-conscious beverage alternatives. This comprehensive endeavour unfolds through an integrated methodology that combines hypothesis testing and other statistical techniques with the establishment of a robust decision support system, complemented by powerful machine learning techniques. Distinctively, the paper integrates an intuitive React application (ReactApp) into the robust Fast API framework. Users engage seamlessly with the decision support system, as Fast API efficiently manages data processing, interfaces with machine learning algorithms, and delivers personalized recommendations to the ReactApp front. In essence, this interdisciplinary initiative epitomizes the fusion of nutritional science, statistical analysis, machine learning, and modern web technologies, providing a holistic and pioneering solution for selecting health-conscious beverage alternatives. One of the most noteworthy outcomes of our research lies in the compelling results we've achieved. Our predictive model has demonstrated exceptional performance: We achieved an impressive Accuracy Rate of 83.67%, signifying the high precision of our recommendations in identifying health-conscious beverage alternatives. Simultaneously, the F1-Score, which harmonizes precision and recall, stands at a commendable 82.21%, indicating a well-balanced and effective decision support system. Our model's ability to recall health-conscious choices is also strong, with a Recall rate of 83.67%. Furthermore, we assessed the model's agreement with observed data using Cohen's Kappa, which yielded a substantial score of 78.01%. This indicates not only the model's predictive power but also its ability to capture agreement beyond what might occur by chance alone. These results, seamlessly integrated into our research narrative, underscore the effectiveness and reliability of our approach. They constitute a rare and valuable contribution to the field, promising a novel pathway for informed and health-driven consumer choices, firmly supported by our rigorous methodology and advanced machine learning outcomes.

Analysis of the Severity of Heterogeneity Protection Forest based on SVM and PCA

Forest heterogeneity indicates the forest condition on producing more carbon into environment. Semidang Bukit Kabu Hunting Park Forest is a nature reserve lies over two districts of Central Bengkulu and Seluma, Bengkulu Province, which should have a heterogeneous forest to protect its natural resources. However, the data showed that the condition of it does not appear to have dense forest heterogeneity anymore, and its rate still remain unknown. Remote sensing as one of tools to help the remote monitoring was believed to be helpful to this question. This study showed changes in the heterogeneity from 2016 to 2021. Sentinel-2 imageries were occupied to help the process of classification of forest and non-forest areas. Support Vector Machine, as one of powerful machine learning tools, was also help the process with the integrating of Principal Component Analysis to optimize forest characteristics. This study indicates that there are significant reductions of forest heterogeneity over the area. The number of forest (heterogeny areas) continues to decline from 8122 ha in 2016 to 4339 ha in 2021. Furthermore, this study had proven that the algorithm of support vector machines showed significant performance to build the model towards the data with overall accuracy rate of 0.9434 and a kappa index of 0.9833.

Comprehensive Evaluation Method for High-Performance Milling of Inconel 718 Alloy

The aim of this paper was to develop and verify a method for evaluating the high-performance milling of Inconel 718 alloy under accelerated tool wear conditions. The method considered parameters such as cutting-force components, total machine power consumption, cutting-edge wear, and material removal rate. The study compared high-feed milling and plunge milling, using sets of cutting parameters that are appropriate for both techniques. The results indicate that high-feed milling was more efficient, achieving higher material removal rates and lower tool wear. On the other hand, plunge milling was characterized by a lower axial force component (Fz), which can positively affect machining accuracy. The paper highlights that the proposed evaluation method can also be applied to other hard-to-machine materials, and plunge milling offers a competitive alternative for roughing operations in the milling of Inconel 718 alloy.

LHC di-lepton searches for Z′ bosons which explain measurements of b → sl+l− transitions

Several current measurements of b→sl+l− processes are in tension with Standard Model predictions, whereas others (e.g. RK and RK⁎) are in reasonable agreement with them. We examine some recent Z′ models that fit the data as a whole appreciably better than does the Standard Model, confronting the models with ATLAS resonance searches in the e+e− and μ+μ− channels. The models are constrained by both channels; we find that the searches rule out less than one fifth of the allowed range of MZ′. We estimate that the HL-LHC can roughly double the current sensitivity in MZ′, but to cover the whole of the parameter space would take a more powerful machine, such as a 100 TeV pp collider.

Perancangan Perancangan Sistem Trasmisi Mesin Pres Hidrolik Kapasitas 3 Ton Dengan Penggerak Motor listrik

Technological advances have encouraged improvements in the industrial sector in developing countries, including Indonesia. This is of course supported by several factors, including the use of modern equipment as a substitute for human labor. It can be said here that the more modern an industry is, the more machine power is used while the less human power is needed. As human needs become increasingly greater, the machine industry is currently also developing very rapidly. Developments in the industrial sector are marked by the creation of various types of machines that can assist human activities. The use of machines can help human activities or work to be more efficient in terms of completion time, as well as reducing the risk of work accidents. Currently, machines are used as tools that have high automation and precision. Therefore, many people use machines for everything, one of which is a pressing machine. A pressing machine is a tool made to compress or press an object, the power source can come from hydraulics, human power, electric motors and others. The aim of this final project is to design a transmission system for a 3 Ton Semi-Automatic Hydraulic Press Machine with an electric motor drive. It can increase the author's knowledge, insight and experience regarding planning a machine. Conclusion Ball bearings with type 6203 require an installation time of 1 minute 35 seconds and removal of 1 minute 32 seconds. Ball bearings of type 6305 receive a pressure of 400 psi to be installed on the shaft, and when released the pressure produced is the same, namely 400 psi to be able to leave the shaft. A type 6206 ball bearing with a shaft length of 77 mm takes 3 minutes 32 seconds to install, while the same shaft length takes 3 minutes 22 seconds to remove from the shaft.

Single- and Multiswitch Fault-Tolerant Inverter Topology With Preserved Output Power and Extreme Learning Machine Fault Detector

Single- and Multiswitch Fault-Tolerant Inverter Topology With Preserved Output Power and Extreme Learning Machine Fault Detector

Enhancing photovoltaic cell design with multilayer sequential neural networks: A study on neodymium-doped ZnO nanoparticles

Multilayer sequential neural networks, a powerful machine learning model, demonstrate the ability to learn intricate relationships between input features and desired outputs. This study focuses on employing such models to design photovoltaic cells. Specifically, neodymium (Nd)-doped ZnO nanoparticles (NPs) were utilized as a photoanode for fabricating dye-sensitized solar cells (DSSCs). A natural dye extracted from Spinacia oleracea was employed, while two types of electrolytes, liquid and gel (polyethylene glycol-based), were used for comparative analysis. Extensive material characterization of the photoanode highlights the impact of Nd content on the physicochemical properties of ZnO. Notably, when the doped photoanode and gel electrolyte were combined, a substantial 110% improvement in power conversion efficiency (PCE) was achieved. Building on these findings, the machine learning model in this research accurately predicts the current-voltage (I-V) curve values for such photoanodes, with an impressive accuracy of 98%. Additionally, the model illuminates the significance of variables like crystal distortion, texture coefficient, and doping concentration, underscoring their importance in the context of photovoltaic cell design.