Implementing Machine Learning Research Articles

Fundamentals and recent developments of free-space optical neural networks

Machine learning with artificial neural networks has recently transformed many scientific fields by introducing new data analysis and information processing techniques. Despite these advancements, efficient implementation of machine learning on conventional computers remains challenging due to speed and power constraints. Optical computing schemes have quickly emerged as the leading candidate for replacing their electronic counterparts as the backbone for artificial neural networks. Some early integrated photonic neural network (IPNN) techniques have already been fast-tracked to industrial technologies. This review article focuses on the next generation of optical neural networks (ONNs), which can perform machine learning algorithms directly in free space. We have aptly named this class of neural network model the free space optical neural network (FSONN). We systematically compare FSONNs, IPNNs, and the traditional machine learning models with regard to their fundamental principles, forward propagation model, and training process. We survey several broad classes of FSONNs and categorize them based on the technology used in their hidden layers. These technologies include 3D printed layers, dielectric and plasmonic metasurface layers, and spatial light modulators. Finally, we summarize the current state of FSONN research and provide a roadmap for its future development.

A Maturity Model to Determine the Degree of Utilization of Machine Learning in Production Planning and Control Processes

The presented work introduces a maturity model for evaluating Machine Learning implementations, with a primary focus on Production Planning and Control processes, as well as broader organizational and technical aspects in companies. This model emerges as a response to the research gap identified in the analysis of 14 existing maturity models, which served as foundational bases for the development of this novel approach. By examining success factors and obstacles at different maturity levels, categorized according to defined dimensions and overarching design fields, this model can serve as a catalyst for bridging the research gap between models demanded in practice and the scholary exploration of topics related to Machine Learning in corporate processes. Notably, the structured design of this maturity model ensures accessibility for small and medium sized enterprises (SMEs).

The use of image classification to estimate flamingo abundance from aerial, drone and satellite imagery

The Lesser Flamingo Phoeniconaias minor is a Near Threatened species known to be highly gregarious and that can concentrate in large numbers at core foraging and breeding sites, yet is also known to disperse widely in search of suitable foraging habitat. The density of flamingos at occupied sites, together with frequent dispersal between foraging sites, poses significant challenges to obtaining reliable counts and associated population estimates. Our study tested the use of unmanned aerial vehicles (drones) imagery and high-resolution satellite imagery for producing density estimates of Lesser Flamingos at the only known breeding site in South Africa (Kamfers Dam, Northern Cape Province). We implemented a supervised classification approach using multiple supervised classification algorithms, including xgbTree, randomForest, nnet and GBM. The four supervised classification models performed very well at classifying flamingos from both drone and satellite imagery, with classification accuracies ranging between 0.98 and 0.99. The inclusion of an additional predictor (other than RGB bands) yielded the highest variable importance score and greatly increased model accuracy and predictive performance. Estimates of adult flamingos from drone imagery acquired across nesting mudflats on 5 February (n = 1 320) and 14 February (n = 330) 2019 suggested a 75% decline in incubating adults. Furthermore, a total of 16 134 (15 973–16 295) flamingos were estimated from drone imagery on 1 March 2019, and 17 291 (17 118–17 290) flamingos from satellite imagery on 19 March 2019. The modelled size of the creche across dates suggested a loss of 234 birds (4.5%) during the period of assessment, with the highest count estimating 5 218 juveniles. Our study successfully implemented machine learning classifiers that were able to detect and derive highly accurate counts of Lesser Flamingos from both drone and satellite imagery. This use of machine learning could greatly improve the efficiency of monitoring and associated conservation efforts underway for the Lesser Flamingo.

Predicting negative attitudes towards suicide in social media texts: prediction model development and validation study.

Implementing machine learning prediction of negative attitudes towards suicide may improve health outcomes. However, in previous studies, varied forms of negative attitudes were not adequately considered, and developed models lacked rigorous external validation. By analyzing a large-scale social media dataset (Sina Weibo), this paper aims to fully cover varied forms of negative attitudes and develop a classification model for predicting negative attitudes as a whole, and then to externally validate its performance on population and individual levels. 938,866 Weibo posts with relevant keywords were downloaded, including 737,849 posts updated between 2009 and 2014 (2009-2014 dataset), and 201,017 posts updated between 2015 and 2020 (2015-2020 dataset). (1) For model development, based on 10,000 randomly selected posts from 2009 to 2014 dataset, a human-based content analysis was performed to manually determine labels of each post (non-negative or negative attitudes). Then, a computer-based content analysis was conducted to automatically extract psycholinguistic features from each of the same 10,000 posts. Finally, a classification model for predicting negative attitudes was developed on selected features. (2) For model validation, on the population level, the developed model was implemented on remaining 727,849 posts from 2009 to 2014 dataset, and was externally validated by comparing proportions of negative attitudes between predicted and human-coded results. Besides, on the individual level, similar analyses were performed on 300 randomly selected posts from 2015 to 2020 dataset, and the developed model was externally validated by comparing labels of each post between predicted and actual results. For model development, the F1 and area under ROC curve (AUC) values reached 0.93 and 0.97. For model validation, on the population level, significant differences but very small effect sizes were observed for the whole sample (χ 2 1 = 32.35, p < 0.001; Cramer's V = 0.007, p < 0.001), men (χ 2 1 = 9.48, p = 0.002; Cramer's V = 0.005, p = 0.002), and women (χ 2 1 = 25.34, p < 0.001; Cramer's V = 0.009, p < 0.001). Besides, on the individual level, the F1 and AUC values reached 0.76 and 0.74. This study demonstrates the efficiency and necessity of machine learning prediction of negative attitudes as a whole, and confirms that external validation is essential before implementing prediction models into practice.

Implementing machine learning algorithms to detect and prevent financial fraud in real-time

Implementing machine learning algorithms to detect and prevent financial fraud in real-time

Models for depression recognition and efficacy assessment based on clinical and sequencing data

Major depression is a complex psychiatric disorder that includes genetic, neurological, and cognitive factors. Early detection and intervention can prevent progression, and help select the best treatment. Traditional clinical diagnosis tends to be subjective and misdiagnosed. Based on this, this study leverages clinical scale assessments and sequencing data to construct disease prediction models. Firstly, data undergoes preprocessing involving normalization and other requisite procedures. Feature engineering is then applied to curate subsets of features, culminating in the construction of a model through the implementation of machine learning and deep learning algorithms. In this study, 18 features with significant differences between patients and healthy controls were selected. The depression recognition model was constructed by deep learning with an accuracy of 87.26 % and an AUC of 91.56 %, which can effectively distinguish patients with depression from healthy controls. In addition, 33 features selected by recursive feature elimination method were used to construct a prognostic effect model of patients after 2 weeks of treatment, with an accuracy of 75.94 % and an AUC of 83.33 %. The results show that the deep learning algorithm based on clinical and sequencing data has good accuracy and provides an objective and accurate method for the diagnosis and pharmacodynamic prediction of depression. Furthermore, the selected differential features can serve as candidate biomarkers to provide valuable clues for diagnosis and efficacy prediction.

Investigating resource-efficient neutron/gamma classification ML models targeting eFPGAs

There has been considerable interest and resulting progress in implementing machine learning (ML) models in hardware over the last several years from the particle and nuclear physics communities. A big driver has been the release of the Python package, hls4ml, which has enabled porting models specified and trained using Python ML libraries to register transfer level (RTL) code. So far, the primary end targets have been commercial field-programmable gate arrays (FPGAs) or synthesized custom blocks on application specific integrated circuits (ASICs). However, recent developments in open-source embedded FPGA (eFPGA) frameworks now provide an alternate, more flexible pathway for implementing ML models in hardware. These customized eFPGA fabrics can be integrated as part of an overall chip design. In general, the decision between a fully custom, eFPGA, or commercial FPGA ML implementation will depend on the details of the end-use application. In this work, we explored the parameter space for eFPGA implementations of fully-connected neural network (fcNN) and boosted decision tree (BDT) models using the task of neutron/gamma classification with a specific focus on resource efficiency. We used data collected using an AmBe sealed source incident on Stilbene, which was optically coupled to an OnSemi J-series silicon photomultiplier (SiPM) to generate training and test data for this study. We investigated relevant input features and the effects of bit-resolution and sampling rate as well as trade-offs in hyperparameters for both ML architectures while tracking total resource usage. The performance metric used to track model performance was the calculated neutron efficiency at a gamma leakage of 10-3. The results of the study will be used to aid the specification of an eFPGA fabric, which will be integrated as part of a test chip.

Implementasi Machine Learning Untuk Prediksi Harga Laptop Menggunakan Algoritma Regresi Linear Berganda

This article discusses the implementation of machine learning using multiple linear regression algorithms to predict laptop prices. The main objective of this research is to design an appropriate predictive model based on various features such as technical specifications and laptop brands. The research stages include literature study, collection of relevant datasets, pre-processing or data cleaning, Exploratory Data Analysis, Feature Engineering, data splitting, model building, and website development. The results show that the proposed model is able to provide price predictions with a high level of accuracy, measured using evaluation metrics such as Mean Absolute Error (MAE) which produces a value of 0.18 and R-squared (R²) which has a value of 0.68. Implementation was done by integrating Jupyter Notebook, Visual Studio Code (VS Code) and Streamlit for interactive web application development. The conclusion of this research is that the multiple linear regression algorithm is effective in predicting laptop prices, and can be used as a tool in making business decisions and pricing strategies.

Implementing machine learning models in business analytics: challenges, solutions, and impact on decision-making

This research paper explores the challenges, solutions, and impact of implementing machine learning (ML) models in business analytics. It delves into the complexities of integrating ML into decision-making processes, addressing data quality, technical infrastructure, organizational dynamics, and ethical considerations. Analyzing emerging trends and strategic recommendations, the paper provides insights for businesses seeking to leverage ML for enhanced decision-making and competitive advantage. Examining case examples and discussing future directions underscores the transformative potential of ML in reshaping industries and unlocking new opportunities for growth and success.

METHOD FOR CREATING SVM CLASSIFIER FOR DATA ANALYSIS ON FPGA

The paper explores the use of SVM classifier method for data analysis on FPGA, which, despite its effectiveness, may face challenges related to limited resources and data processing speed. In this context, there is a need to develop new methods for integrating SVM classifiers with high-performance computing hardware. The increasing demand for speed and energy efficiency requires new approaches to implementing machine learning methods. One of the key tools for data classification and analysis is the Support Vector Machine (SVM), widely used in business, science, medicine, and many other fields. Developing an efficient and optimized method for creating SVM classifiers for FPGA requires further research and development, as existing methods may be suboptimal in terms of speed and FPGA resource utilization. The article provides an overview of known hardware solutions to this problem, proposed in the current scientific literature. Additionally, the effectiveness of combining hardware and software components to achieve significant acceleration of the data analysis process is discussed. The article emphasizes the need for further research and improvement to fully realize the transformative potential of machine learning classification methods.

Data driven forest fire susceptibility mapping in Bangladesh

Forests are essential natural resources that serve to facilitate economic activity while also providing an essential impact on climate regulation and the carbon cycle. In the Chittagong hill tracts, forest fires significantly contribute to the eradication of forests and the depletion of biodiversity. As a result, addressing the forest fire hazard is crucial for mitigating its potential negative effects. By implementing machine learning (ML) and deep learning (DL) algorithms, the primary aim of this research is to determine which areas within the CHT are most prone to forest fires. Artificial Neural Network (ANN), Classification and Regression Trees (CART), Categorical Boosting (Catboost), Convolutional Neural Network (CNN), Deep Neural Network (DNN), Gradient Boosting Decision Tree (GBDT), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGboost) are among these algorithms. This research investigates 267 past forest fire incidents while incorporating fifteen predictive parameters for forest fires. The utmost accuracy is demonstrated by the Catboost model, which has an AUC value of 0.83. Applied models the Bandarbon and Rangamati regions of the Chittagong hill tracts have been thoroughly analyzed and discovered to be extremely and moderately vulnerable to forest fires due to their intricate physical and social characteristics. The Catboost model indicates that 67.38% of the total regions and 0.59% of the regions in Chittagoong hill tracts are classified as moderate and high susceptible zones, respectively. The results of this study present the models utilized in the present analysis exhibit a high level of effectiveness. Furthermore, the findings indicated that the NDVI and annual temperature had the most influence. The application of both ML and DL approaches in the Chittagong hill tracts for the first time resulted in models that exhibited excellent accuracy and precision, combining perfectly with the actual conditions on the ground. This study will undeniably assist the local government in implementing efficient governance and preservation strategies for the sustainable maintenance of forest resources, while enhancing the well-being of individuals living in and around the forest. Forest fire susceptibility assessment can be utilized in various locations worldwide that include significant natural and human-induced characteristics.

Педагогічні умови формування професійних компетентностей майбутніх учителів історії

The article elucidates the author's pedagogical conditions for fostering professional competencies in prospective history teachers. These conditions encompass the cultivation of creative thinking and the establishment of a digital educational environment within higher education institutions. The study substantiates that the effective enhancement of creative thinking transpires through the resolution of complex pedagogical problems, tasks, and scenarios, thereby underscoring the significance of problem-based learning as a pivotal methodology for addressing creative challenges. Concerning the establishment of a digital educational environment in higher education as a requisite for the proficient development of future history teachers' professional competencies, the article posits the digitalization of higher education as a critical mandate for educational reform and a key facet of information society advancement. The article also outlines major trends in the digital evolution of education, including the advancement of mobile-oriented tools, artificial intelligence, and neural networks; the implementation of machine learning, blockchain, and cryptocurrencies; the adoption of virtualization and fog computing technologies; the progression of virtual reality; and the integration of virtual assistants and chatbots.

Error analysis of machine learning methods as the educational background for its use skills formation

Introduction. Machine learning methods and elements of artificial intelligence are used to analyze random data, processes and signals. The study of relevant tools is already included in the various levels curricula. The purpose of the study is to demonstrate, using examples available to students of various specialties, that the error analysis of machine learning methods in solving specific tasks can be the basis in the educational process for the skills formation of using artificial intelligence elements.Materials and Methods. For processing random signals and data, widely available software is used: Microsoft Excel for preparing training and test samples, the Deductor analytical platform for implementing machine learning algorithms. As an example, quasi-harmonic signals with random parameters are processed for technical specialties, and the results of psycho diagnostics are used to process multidimensional random data.Results. As a typical solution of approximation technical problems, direct propagation neural network errors in using to determine random signal parameters are analyzed. As a solution of classification problems, multidimensional random data with different dimensions were processed using neural networks and the "decision tree" method. The advantages of the combined use of these two machine learning methods are analyzed. These examples and their analysis were tested in classes with university students in the disciplines of "Digital Signal Processing" and "Fundamentals of Statistics".Discussion and Conclusions. The statistical features of the obtained results, the possibilities of reducing the training sample and selective analysis of multidimensional random data are discussed. It is shown that an adequate assessment of the machine learning methods errors can significantly expand the possibilities of their application, and can be the basis for the formation of skills for their use.

Nurses' perceptions of the design, implementation, and adoption of machine learning clinical decision support: A descriptive qualitative study.

The purpose of this study was to explore nurses' perspectives on Machine Learning Clinical Decision Support (ML CDS) design, development, implementation, and adoption. Qualitative descriptive study. Nurses (n = 17) participated in semi-structured interviews. Data were transcribed, coded, and analyzed using Thematic analysis methods as described by Braun and Clarke. Four major themes and 14 sub-themes highlight nurses' perspectives on autonomy in decision-making, the influence of prior experience in shaping their preferences for use of novel CDS tools, the need for clarity in why ML CDS is useful in improving practice/outcomes, and their desire to have nursing integrated in design and implementation of these tools. This study provided insights into nurse perceptions regarding the utility and usability of ML CDS as well as the influence of previous experiences with technology and CDS, change management strategies needed at the time of implementation of ML CDS, the importance of nurse-perceived engagement in the development process, nurse information needs at the time of ML CDS deployment, and the perceived impact of ML CDS on nurse decision making autonomy. This study contributes to the body of knowledge about the use of AI and machine learning (ML) in nursing practice. Through generation of insights drawn from nurses' perspectives, these findings can inform successful design and adoption of ML Clinical Decision Support.

DIGITALIZATION OF LABOR-LAW RELATIONS: BASIC PROVISIONS AND DEVELOPMENT PROSPECTS

The updated national goals of development of the Russian Federation for the period till 2030 and on perspective till 2036, approved by the Decree of the President of the Russian Federation dated 07.05.2024 No. 309, contain the most important directions of further development of our country, including such areas as: technological leadership, digital transformation of public and municipal administration, economy and social sphere involving automation of the most part of transactions within uniform sectoral digital platforms and data-based management model taking into account the accelerated implementation of big data processing technologies, machine learning and artificial intelligence. Achievement of these goals, defined by the Russian President as fundamental for the modern development of the state and systems of public administration bodies, is impossible without strategic development of the branch of labor law. The basis for achieving these national development goals is the development of a trinity of directions: digitalization of labor law relations - expansion of the use of artificial intelligence in the field of labor and employment - development of new forms of employment, such as remote work and platform employment. The goal of digitalization of labor relations is to increase efficiency, optimize resources, improve communication and ensure more flexible and transparent personnel management. As part of the digitalization of labor relations, companies apply various tools and technologies such as electronic HR management systems, online-platforms for recruiting and manpower planning, automated systems of control of working hours, virtual workspaces and other digital solutions. New digital solutions in HR management can become one of the drivers of development of the Russian economy, allowing for adequate savings for employers. The automation of production, the expansion of hiring remote workers, optimization of the use of artificial intelligence in work processes raise the question of deepening the scientific research of these aspects in labor law.

Gear Fault Detection Method Based on Convex Hull Clustering of Autoencoder’s Latent Space

This paper presents a method of pitting failure detection in toothed gears based on the reconstruction of the gear case vibrational signal. The effectiveness of the proposed method was tested in an experiment on a power circulation test stand. The autoencoder deep neural network architecture, semi-supervised training, and validation, along with the latent data convex hull-based clustering, are presented. The proposed method offers high efficiency (0.99 F1-measure) in gear state prediction (100% in failure detection, 98.9% in normal state prediction) and provides more capabilities in terms of generalization in comparison with linear machine learning techniques such as principal component analysis and nonlinear like the generative adversarial network. Moreover, it is distinguished by high sensitivity while also being able to detect even slight surface damage (initial pitting). These findings will be of particular relevance to a range of scientists and practitioners working with gear drives who are willing to implement machine learning in signal processing and diagnosis.

Mobile App for Enhanced Anterior Cruciate Ligament (ACL) Assessment in Conscious Subjects: "Pivot-Shift Meter".

Anterior cruciate ligament (ACL) instability poses a considerable challenge in traumatology and orthopedic medicine, demanding precise diagnostics for optimal treatment. The pivot-shift test, a pivotal assessment tool, relies on subjective interpretation, emphasizing the need for supplementary imaging. This study addresses this limitation by introducing a machine learning classification algorithm integrated into a mobile application, leveraging smartphones' built-in inertial sensors for dynamic rotational stability assessment during knee examinations. Orthopedic specialists conducted knee evaluations on a cohort of 52 subjects, yielding valuable insights. Quantitative analyses, employing the Intraclass Correlation Coefficient (ICC), demonstrated robust agreement in both intraobserver and interobserver assessments. Specifically, ICC values of 0.94 reflected strong concordance in the timing between maneuvers, while signal amplitude exhibited consistency, with the ICC ranging from 0.71 to 0.66. The introduced machine learning algorithms proved effective, accurately classifying 90% of cases exhibiting joint hypermobility. These quantifiable results underscore the algorithm's reliability in assessing knee stability. This study emphasizes the practicality and effectiveness of implementing machine learning algorithms within a mobile application, showcasing its potential as a valuable tool for categorizing signals captured by smartphone inertial sensors during the pivot-shift test.

Implementation of Machine Learning to Increase the Accuracy of Forecasting the Operating Modes of Deep-Sea Pumping Stations

Implementation of Machine Learning to Increase the Accuracy of Forecasting the Operating Modes of Deep-Sea Pumping Stations

Finding influential nodes in complex networks based on Kullback–Leibler model within the neighborhood

As a research hot topic in the field of network security, the implementation of machine learning, such as federated learning, involves information interactions among a large number of distributed network devices. If we regard these distributed network devices and connection relationships as a complex network, we can identify the influential nodes to find the crucial points for optimizing the imbalance of the reliability of devices in federated learning system. This paper will analyze the advantages and disadvantages of existing algorithms for identifying influential nodes in complex networks, and propose a method from the perspective of information dissemination for finding influential nodes based on Kullback–Leibler divergence model within the neighborhood (KLN). Firstly, the KLN algorithm removes a node to simulate the scenario of node failure in the information dissemination process. Secondly, KLN evaluates the loss of information entropy within the neighborhood after node removal by establishing the KL divergence model. Finally, it assesses the damage influence of the removed node by integrating the network attributes and KL divergence model, thus achieving the evaluation of node importance. To validate the performance of KLN, this paper conducts an analysis and comparison of its results with those of 11 other algorithms on 10 networks, using SIR model as a reference. Additionally, a case study was undertaken on a real epidemic propagation network, leading to the proposal of management and control strategies for daily protection based on the influential nodes. The experimental results indicate that KLN effectively evaluates the importance of the removed node using KL model within the neighborhood, and demonstrate better accuracy and applicability across networks of different scales.

Concrete aging factor prediction using machine learning

Accurate prediction of concrete aging factor is pivotal for performance-based durability reinforced concrete design. This study introduces an innovative method leveraging machine learning techniques, employing seven algorithms: Bagging, Random Forest, AdaBoost, Gradient Boosting, XGBoost, CatBoost, and LightGBM. The dataset comprises 130 instances with seven input features describing cement type, cement content, pozzolan type, pozzolan content, w/b ratio, exposure condition, and age of concrete. Seventy models were trained across five scenarios, categorized into two groups: Group I using all features of the raw dataset, and Group II incorporating engineered features. Model performance, assessed by mean-absolute error (MAE), mean-square error (MSE), root-mean-square error (RMSE), and coefficient of determination (R²), reveals superior performance in Group II compared to Group I. Notably, the LightGBM algorithm in Scenario III outperforms all models with a remarkable MAE of 0.110, MSE of 0.018, RMSE of 0.133, and R² of 0.818. Subsequently, models from Scenarios V and IV exhibit strong performance. The implemented machine learning models demonstrate notable generalizability, effectively capturing feature interrelations without the need for resource-intensive experimental testing.