Implementing Machine Learning Research Articles

Machine learning approaches for improving atomic force microscopy instrumentation and data analytics

Atomic force microscopy (AFM) is a part of the scanning probe microscopy family. It provides a platform for high-resolution topographical imaging, surface analysis as well as nanomechanical property mapping for stiff and soft samples (live cells, proteins, and other biomolecules). AFM is also crucial for measuring single-molecule interaction forces and important parameters of binding dynamics for receptor-ligand interactions or protein-protein interactions on live cells. However, performing AFM measurements and the associated data analytics are tedious, laborious experimental procedures requiring specific skill sets and continuous user supervision. Significant progress has been made recently in artificial intelligence (AI) and deep learning (DL), extending into microscopy. In this review, we summarize how researchers have implemented machine learning approaches so far to improve the performance of atomic force microscopy (AFM), make AFM data analytics faster, and make data measurement procedures high-throughput. We also shed some light on the different application areas of AFM that have significantly benefited from applications of machine learning frameworks and discuss the scope and future possibilities of these crucial approaches.

Toward reliable prediction of CO2 uptake capacity of metal–organic frameworks (MOFs): implementation of white-box machine learning

Toward reliable prediction of CO2 uptake capacity of metal–organic frameworks (MOFs): implementation of white-box machine learning

The Evaluation of Machine Learning Techniques for Isotope Identification Contextualized by Training and Testing Spectral Similarity

Precise gamma-ray spectral analysis is crucial in high-stakes applications, such as nuclear security. Research efforts toward implementing machine learning (ML) approaches for accurate analysis are limited by the resemblance of the training data to the testing scenarios. The underlying spectral shape of synthetic data may not perfectly reflect measured configurations, and measurement campaigns may be limited by resource constraints. Consequently, ML algorithms for isotope identification must maintain accurate classification performance under domain shifts between the training and testing data. To this end, four different classifiers (Ridge, Random Forest, Extreme Gradient Boosting, and Multilayer Perceptron) were trained on the same dataset and evaluated on twelve other datasets with varying standoff distances, shielding, and background configurations. A tailored statistical approach was introduced to quantify the similarity between the training and testing configurations, which was then related to the predictive performance. Wilcoxon signed-rank tests revealed that the OVR-wrapped XGB significantly outperformed the other algorithms, with confidence levels of 99.0% or above for the 133Ba, 60Co, 137Cs, and 152Eu sources. The findings from this work are significant as they outline techniques to promote the development of robust ML-based approaches for isotope identification.

Compatibility Model between Encapsulant Compounds and Antioxidants by the Implementation of Machine Learning

The compatibility between antioxidant compounds (ACs) and wall materials (WMs) is one of the most crucial aspects of the encapsulation process, as the encapsulated compounds’ stability depends on the affinity between the compounds, which is influenced by their chemical properties. A compatibility model between the encapsulant and antioxidant chemicals was built using machine learning (ML) to discover optimal matches without costly and time-consuming trial-and-error experiments. The attributes of the required antioxidant and wall material components were recollected, and two datasets were constructed. As a result, a tying process was performed to connect both datasets and identify significant relationships between parameters of ACs and WMs to define the compatibility or incompatibility of the compounds, as this was necessary to enrich the dataset by incorporating decoys. As a result, a simple statistical analysis was conducted to examine the indicated correlations between variables, and a Principal Component Analysis (PCA) was performed to reduce the dimensionality of the dataset without sacrificing essential information. The K-nearest neighbor (KNN) algorithm was used and designed to handle the classification problems of the compatibility of the combinations to integrate ML in the model. In this way, the model accuracy was 0.92, with a sensitivity of 0.84 and a specificity of 1. These results indicate that the KNN model performs well, exhibiting high accuracy and correctly classifying positive and negative combinations as evidenced by the sensitivity and specificity scores.

Development of machine learning algorithm for loop-mediated isothermal amplification including influence of temperature

To predict amplification in the Loop-Mediated Isothermal Amplification (LAMP) method, a binary model has been developed. This model assesses whether the combination of partial template binding facilitated by multiple primers aligns with a specific signature indicating amplification. For this model, 1512 settings were adjusted, encompassing variations in the extraction oligomer position from the primer, the oligomer length, the number of allowed mismatched bases, and the stringency of the homology position. The optimal set was determined based on the F1 value at a reaction temperature of 60°C, resulting in a value of 0.58. To implement machine learning by amalgamating multiple models, duplicate models were eliminated through cluster analysis. Machine learning using AutoML was performed on 108 distinct models. Consequently, the F1 values were 0.7119 at a reaction temperature of 60°C and 0.7210 at 68°C. The weak correlation between feature importance and the F1 value of the model alone suggests that machine learning utilizing this model incorporates numerous models to enhance prediction accuracy.

Implementing machine learning to predict survival outcomes in patients with resected pulmonary large cell neuroendocrine carcinoma

ABSTRACT Background The post-surgical prognosis for Pulmonary Large Cell Neuroendocrine Carcinoma (PLCNEC) patients remains largely unexplored. Developing a precise prognostic model is vital to assist clinicians in patient counseling and creating effective treatment strategies. Research design and methods This retrospective study utilized the Surveillance, Epidemiology, and End Results database from 2000 to 2018 to identify key prognostic features for Overall Survival (OS) in PLCNEC using Boruta analysis. Predictive models employing XGBoost, Random Forest, Decision Trees, Elastic Net, and Support Vector Machine were constructed and evaluated based on Area Under the Receiver Operating Characteristic Curve (AUC), calibration plots, Brier scores, and Decision Curve Analysis (DCA). Results Analysis of 604 patients revealed eight significant predictors of OS. The Random Forest model outperformed others, with AUC values of 0.765 and 0.756 for 3 and 5-year survival predictions in the training set, and 0.739 and 0.706 in the validation set, respectively. Its superior validation cohort performance was confirmed by its AUC, calibration, and DCA metrics. Conclusions This study introduces a novel machine learning-based prognostic model with a supportive web-based platform, offering valuable tools for healthcare professionals. These advancements facilitate more personalized clinical decision-making for PLCNEC patients following primary tumor resection.

Evaluation of enhanced chemical coagulation method for a case study on colloidal liquid particle in wastewater treatment: Statistical optimization analysis and implementation of machine learning

Coal mines are one of the largest sources of energy supply and generate significant volumes of wastewater. Chemical coagulation is one of the most effective methods for wastewater treatment. In this research, ferric and aluminum-based coagulants, along with polyacrylamide flocculants with positive, negative, and neutral charges, were utilized in chemical coagulation. After applying the Plackett-Burman screening method, it was found that ferric chloride coagulant, neutral flocculant, and slow mixing duration had the greatest impact. The chemical coagulation process was modeled and optimized by examining these factors using the Box–Behnken statistical design as input parameters and sedimentation velocity as the output. Under optimal conditions, the values for ferric chloride coagulant, neutral flocculant, mixing time in slow mode, and sedimentation velocity were determined to be 106.3 mg/L, 3.98 mg/L, 29.6 min, and 1.10 cm/min, respectively. Under optimal conditions, the removal percentages of pollutants, including TSS, turbidity, TDS, COD, and BOD, were obtained at 100%, 100%, 87%, 93%, and 81%, respectively. The experimental data were fitted using the BBD and ANN methods. Both models demonstrated very high agreement, but the ANN method performed better with an AAD% of 0.66, an MSE of 0.0001, and an R2 value of 0.99. All results were calculated with a confidence level above 98%, indicating that both models had very high reliability in modeling and prediction.

Deep learning neural networks for monitoring early-age concrete strength through a surface-bonded PZT sensor configuration

Monitoring the immediate evolution of concrete’s strength is essential to ensure structural integrity and construction efficiency, requiring Forecasting to avoid unforeseen and severe failures during construction. The present investigation introduces an Equivalent structural parametric (ESP) study using a surface-bonded piezo sensor and electromechanical impedance (EMI) methodology to monitor and forecast the strength of concrete by implementing machine learning and deep learning methods. The concrete hydration processes are simulated using COMSOL™ 5.5. The concrete cube’s hydration is represented by altering Young’s modulus and damping ratio to show the rate of curing. Concrete strength development is examined in terms of conductance resonant frequency (CRF) and Conductance resonant peak (CRP). Continuous conductance signature monitoring and data analysis show that CRF and CRP increase with compressive strength. The system’s mechanical impedance is measured, and EMI signatures vs. frequency plots within a specific frequency range are compared to healthy impedance graphs. A mass-spring-damper system with identical properties is identified, and relevant structural parameters are computed. Modern ML algorithms include linear regression (LR), interaction LR, fine, medium, and coarse Gaussian SVM, etc. reliably predict strength with an error rate of less than 2%. Convolutional neural networks (CNN) have advanced image-based recognition, but their usage in EMI-based structural strength assessment is still being studied. A unique strategy using 2D CNN, 2D CNN– Long short-term memory (LSTM), and 2D CNN Bidirectional-LSTM to forecast concrete structure compressive strength shows the potential of deep learning. The proposed 2D CNN-Bi-LSTM model excels in compressive strength prediction, obtaining an R2 value of 0.99 and stabilizing loss error over a few epochs.

The phase space distance between collider events

How can one fully harness the power of physics encoded in relativistic N-body phase space? Topologically, phase space is isomorphic to the product space of a simplex and a hypersphere and can be equipped with explicit coordinates and a Riemannian metric. This natural structure that scaffolds the space on which all collider physics events live opens up new directions for machine learning applications and implementation. Here we present a detailed construction of the phase space manifold and its differential line element, identifying particle ordering prescriptions that ensure that the metric satisfies necessary properties. We apply the phase space metric to several binary classification tasks, including discrimination of high-multiplicity resonance decays or boosted hadronic decays of electroweak bosons from QCD processes, and demonstrate powerful performance on simulated data. Our work demonstrates the many benefits of promoting phase space from merely a background on which calculations take place to being geometrically entwined with a theory’s dynamics.

Validating, Implementing, and Monitoring Machine Learning Solutions in the Clinical Laboratory Safely and Effectively.

Machine learning solutions offer tremendous promise for improving clinical and laboratory operations in pathology. Proof-of-concept descriptions of these approaches have become commonplace in laboratory medicine literature, but only a scant few of these have been implemented within clinical laboratories, owing to the often substantial barriers in validating, implementing, and monitoring these applications in practice. This mini-review aims to highlight the key considerations in each of these steps. Effective and responsible applications of machine learning in clinical laboratories require robust validation prior to implementation. A comprehensive validation study involves a critical evaluation of study design, data engineering and interoperability, target label definition, metric selection, generalizability and applicability assessment, algorithmic fairness, and explainability. While the main text highlights these concepts in broad strokes, a supplementary code walk-through is also provided to facilitate a more practical understanding of these topics using a real-world classification task example, the detection of saline-contaminated chemistry panels.Following validation, the laboratorian's role is far from over. Implementing machine learning solutions requires an interdisciplinary effort across several roles in an organization. We highlight the key roles, responsibilities, and terminologies for successfully deploying a validated solution into a live production environment. Finally, the implemented solution must be routinely monitored for signs of performance degradation and updated if necessary. This mini-review aims to bridge the gap between theory and practice by highlighting key concepts in validation, implementation, and monitoring machine learning solutions effectively and responsibly in the clinical laboratory.

Influence of Protected Areas in the Carbon Cycle: A Machine Learning Approach for Future Forecasting

AbstractProtected Areas (PAs) are destined to the conservation of natural resources, whose quantity and quality are menaced by Climate Change and anthropogenic pressure. The objective of this research was to quantify and forecast the Carbon Absorption of PAs, attending these factors. We used the Net Primary Productivity (NPP) and implemented machine learning algorithms, as Random Forests (RF), Gradient Boosting Trees (GBT), and Multilayer Perceptrons (MLPNN), to forecast it in four differentiated PAs of Galicia (NW Spain): the Central Massif, the Sil Canyons, Fragas do Eume, and the Tambre River. Two testing stages were carried, one in the areas where the model was trained, and another in the whole territory. Finally, we set several scenarios based on projections SSP2-4.5 and SSP 5-8.5 in and land use changes. GBT was the most accurate algorithm, with a Root Mean Squared Error (RMSE) of 0.05 kgC/m2 (5.7% of the average NPP) and correlation of 0.9. RF obtained an error of 0.07 and correlation of 80%, and MLPNN 0.06 and 86%, respectively. The GBT obtained a RMSE of 0.04 kgC/m2 and R2 of 0.95 in the first test. These results were worsened in the second test, with an RMSE of 0.09 kgC/m2 and 71% of correlation. For the SSP2-4.5 scenarios, a decrease around 7% can be expected, barely influenced by the land use. On the other hand, the SSP5-8.5 is expected to record a decrease of 5% in the NPP, with no significant differences between the land uses, but with a significant trend. All the pilot sites stick to this trend, except for the Tambre River, which was forecasted to record a slight increase of the NPP (~ 3%). The prediction and analysis of future scenarios can help the management of the territory, focusing on the mitigation of the effects of Climate Change in PAs. Graphical Abstract

Development of public health decision-making based on semantic evaluation of EHR data

The study examines the way semantic analysis of data from electronic health records (EHRs) is performed. Implementing machine learning (ML) is challenging, EHRs are essential for acquiring medical data because they include textual information from physicians about patients' ailments and treatment plans, supporting well-informed public health decision-making. The goal of the study was to allow computers to semantically comprehend assessments, physical parts, indicators, and therapies in addition to implicitly identifying medical terms in EHRs. To efficiently identify medical phrases in electronic health records, a novel cubic support vector machine with a dipper-throated optimization (CSVM-DTO) strategy is suggested. This study uses tokenization as a pre-processing step for the data gathered from public sources. The semantic data of medical terminology is then extracted using the word-2-vector technique. Next, the named entities are found using the CSVM, and their efficiency is improved by implementing the DTO technique. Based on the experimental results, we can conclude that our suggested approach outperformed other current approaches in locating the identified entities inside the EHRs.

P19-70 Gaps and needs analysis, barriers, opportunities and drivers for implementation of Artificial Intelligence and Machine Learning (AI/ML) tools in regulatory risk assessment

P19-70 Gaps and needs analysis, barriers, opportunities and drivers for implementation of Artificial Intelligence and Machine Learning (AI/ML) tools in regulatory risk assessment

Implementing machine learning techniques for customer retention and churn prediction in telecommunications

This review paper explores the application of machine learning techniques in predicting customer churn and enhancing customer retention within the telecommunications industry. The paper begins by discussing the significance of customer churn, its causes, and the limitations of traditional churn prediction methods. It then delves into machine learning algorithms, including decision trees, support vector machines, and ensemble methods. It highlights their effectiveness in handling large and complex datasets typical of the telecom sector. The discussion extends to the challenges faced in data quality, model selection, implementation, and ethical considerations in using customer data for predictive analytics. The paper also compares machine learning models with traditional methods, emphasizing the advantages of scalability, accuracy, and real-time processing. Furthermore, it identifies potential innovations, such as improved data integration, interpretable models, and personalized retention strategies. Finally, the paper reflects on future trends, predicting the growing role of AI and machine learning in telecommunications, particularly in customer service automation and network optimization. The review underscores the importance of adopting machine learning to reduce churn and improve customer retention while considering the field's ethical implications and future opportunities. Keywords: Customer Churn Prediction, Machine Learning, Telecommunications, Customer Retention, Predictive Analytics, AI in Telecom

Enhancing customer service and user experience through the use of machine learning powered intelligent chatbots

The implementation of machine learning powered intelligent chatbots have greatly enhanced customer service and user experience in various industries. With the advancements in artificial intelligence and natural language processing, chatbots have become an essential tool for businesses to effectively communicate with their customers. Machine learning algorithms enable chatbots to analyze customer queries and provide accurate responses, mimicking human conversation. This has led to an increase in customer satisfaction as chatbots can handle large volumes of inquiries and resolve them efficiently. Moreover, chatbots are available 24/7, providing round-the-clock service to customers. Implementing chatbots in businesses has also resulted in cost savings as they reduce the need for human customer service representatives. This has allowed companies to allocate their resources to other areas of their business, ultimately leading to increased productivity. In addition to improved customer service, intelligent chatbots also enhance user experience. By continuously learning from user interactions, chatbots can personalize responses and provide relevant information, making the customer experience more seamless and efficient. Furthermore, chatbots can be integrated into various platforms such as websites, social media, and messaging applications, making them easily accessible to users. This has also led to an increase in user engagement and retention rates. The potential challenges and limitations of this technology was also discussed and recommendations provided for future research in this field. Overall, the development and implementation of machine learning powered intelligent chatbots have greatly enhanced customer service and user experience, making it a valuable tool for businesses in today's digital age.

Development of fucoidan/polyethyleneimine based sorafenib-loaded self-assembled nanoparticles with machine learning and DoE-ANN implementation: Optimization, characterization, and in-vitro assessment for the anticancer drug delivery

This study aims to develop sorafenib-loaded self-assembled nanoparticles (SFB-SANPs) using the combined approach of artificial neural network and design of experiments (ANN-DoE) and to compare it with other machine learning (ML) models. The central composite design (CCD) and ML algorithms were used to screen the effects of concentrations of both the polymers (polyethyleneimine and fucoidan) on the outcome responses, i.e., particle size and entrapment efficiency with defined constraints. The prediction from different ML models (bootstrap forest, K-nearest neighbors, artificial neural network, generalized regression-lasso and support vector machines) were compared with ANN-DoE model. The ANN-DoE model showed better accuracy and predictability and outperformed all the other models. This depicted that the concept of using ANN and DoE combination approach provided the best, uncomplicated and cost-effective way to optimized the nanoformulations. The optimized formulation generated from the ANN-DoE combined model was further evaluated for characterization and anticancer activity. The optimized SFB-SANPs were prepared using the polyelectrolyte complexation method with Polyethyleneimine (PEI) as a cationic polymer and fucoidan (FCD) as an anionic. The SFB-SANPs were nanometric in size (280.4 ± 0.089 nm) and slightly anionic in nature (zeta potential = −6.03 ± 0.92 mV) with an encapsulation efficiency of 95.56 ± 0.30 %. The drug release from SFB-SANPs was controlled and sustained in the cancer microenvironment (pH 5.0). The SFB-SANPs were compatible with red blood cells (RBCs), and the % hemolysis was found to be <5.0 %. The anticancer activity of the SFB-SANPs exhibited an IC50 at 2.017 ± 0.516 μM against MDMB-231 cells, showing a significantly high inhibitory effect on breast cancer cell lines. Therefore, the nanocarriers developed using various ML tools inherit a huge promise in anticancer drug delivery.

Smartphone-sensor-based human activities classification for forensics: a machine learning approach

The accurate classification of human activities in crime scenes during forensics (criminalistics) is of utmost importance in classifying suspicious and unlawful activities, easing their acceptability and interpretability by judges during legal procedures in courts or by other non-experts in the field of forensics. This paper implements machine learning (ML) algorithms: support vector machine (SVM) and decision tree (DT), to demonstrate with a high accuracy, how data emanating from smartphones’ sensors reveal and isolate relevant information about static and dynamic human activities in criminalistics. Smartphones’ data from five different sensors (accelerometer, gravity, orientation, Gyroscope and light), related to ten recurrent crime scenes activities, grouped into three classes of events (normal, felony and none-felony events) are classified by the proposed algorithms, with novelty being the classification decisions based on the entire period of the events and not instantaneous decision makings. Three independent data-subsets were made, with permutations done between them and at each time, two sets used for training and the third set used for testing. Time- and frequency-domain features were initially used separately and then combined for the model training and testing. The best average training accuracies of 100% and 97.8% were obtained for the DT and SVM, respectively, and the testing accuracies of 89.1% were obtained for both algorithms. We therefore believe that these results will serve as a solid persuasive and convincing argument to judges and non-experts of the field of forensics to accept and easily interpret computer-aided classification of suspicious activities emanating from criminalistic studies.

Design and Implementation of a Mobile E-Commerce Platform Based-on Machine Learning

In this paper, the “STORY”, which is an e-commerce mobile platform, is developed based-on machine learning techniques in order to consolidate selling methods into a unified, efficient, and personalized environment. Also, to elevate user experiences, and cultivate a thriving e-commerce environment in Libya. STORY is designed to serve the needs of both customers and merchants, aiming to bridge the gap between consumer demands and efficient business interactions. This platform strives to provide customers with a wide range of services and functions that match their preferences, while empowering merchants with a user-friendly mobile interface for effective business management. Among its notable features, STORY boasts an image-based search function, which simplifies the process of searching for desired or similar products. Additionally, the platform integrates an intelligent recommendation system capable of tracking and analyzing customer behaviors within the platform. This system collects pertinent data to offer personalized product recommendations and tailored offers, elevating the shopping experience. The system underwent an evaluation via a questionnaire, which had overwhelmingly positive results. User feedback and satisfaction regarding the system's functionalities and performance were notably favorable.

The Accuracy of Supervised Learning Algorithm on Machine Learning Implementation: a Literature Review

Machine Learning has become an integral element in technological development, having a significant impact on various sectors of life. This study explores the contribution of Machine Learning in big data processing, automated decision making, and predictive system development. The advantages of Machine Learning, especially in supervised learning, are emphasized by discussing algorithms such as regression, Support Vector Machines (SVM), and Neural Networks. Literature research includes five journals related to supervised learning applications, highlighting findings such as the effectiveness of the Random Forest algorithm in diagnosing pregnancy, the contribution of the SVM model in predicting student study periods, and the level of accuracy with the hybrid LSH and k-NN methods for weather prediction. The practical implementation of fruit detection using cameras shows real application in facilitating price checks and fruit recognition. In conclusion, the literature review confirms the potential and relevance of Machine Learning techniques, especially supervised learning, in providing solutions to various challenges in various sectors. It is recommended that further research explore different industrial sectors or specific case studies to gain a more comprehensive and relevant perspective on current trends in the development of Machine Learning techniques

Implementation of Machine Learning Using Deep Neural Networks to Estimate the Failure Risk Caused by Leakage in Pressure Relief Devices

Implementation of Machine Learning Using Deep Neural Networks to Estimate the Failure Risk Caused by Leakage in Pressure Relief Devices