Implementation Of Algorithm Research Articles

Finite Element Model Updating using Bayesian Optimization Algorithm

Structural engineering projects require reliable information about parameters of the designed systems that convey precise predictions about the behavior of the system under different load cases. These predictions are derived from numerical engineering models containing real structure geometry and parameters, resulting in responses using the well-established Finite Element Method (FEM). However, due to the presence of uncertainties and assumptions made during the construction of the model, the resulting response may not well represent the real structural behavior. Thus, the established approach involves supplying the numerical model with experimental data to reduce numerical-experimental error, improving the correlation between numerical and observed structural behavior of the system, in a process called Finite Element Model Updating (FEMU). Overall, engineers have developed many different approaches to solve this problem, mainly consisting of sampling or optimization algorithms, applying these methods in FEMU, damage detection, and optimization of sensor placement. The focus of this paper is on the implementation of the Bayesian Optimization Algorithm (BOA) to solve FEMU problems. BOA is a derivative-free optimization algorithm that aims to minimize the number of evaluations of the objective function by trading some computational resources for the construction and optimization of a cheaper auxiliary function, which evaluates the best point to evaluate next. This can be beneficial when heavy sampling of the optimization function can be very time-consuming or when limited evaluations are available, rendering sampling methods and some heuristic algorithms inefficient. To assess the behavior of the algorithm, many cases are analyzed from lower evaluation time to higher complexity cases and then compared with other methods, such as Bayesian Inference, Particle Swarm Optimization, and Genetic Algorithm. The first case is to optimize test functions, followed by some FEMU applications on an uncertain boundary condition beam and finally, a honeycomb plate, in which evaluation of the objective function is more expensive. Results show that BOA can attain good results in a short amount of time when applied to FEMU for low dimensionality problems compared with well-established methods. Overall, this paper reviews FEMU methods and proposes the implementation of a novel approach, demonstrating its effectiveness in solving model updating problems.

Neuro-Fuzzy: Multivariable Identification of a Pumping System with Variable Demand

Water supply systems (WSS) comprise a set of equipment, works and services aimed at supplying water, covering domestic, industrial and public consumption. WSS face challenges arising from hourly variation in demand, influenced by society's consumption patterns. These variations cause fluctuations in system pressures and energy inefficiencies. As a way of analyzing this aspect, intelligent techniques were used to identify an automated WSS with variable demand for the development of computational models. Two multivariable and non-linear models were developed based on Artificial Neural Networks (ANN) and Neuro-Fuzzy system (NF). The objective is to enable simulations of operation scenarios, analysis, design and implementation of new intelligent control algorithms. To collect the data used in training and validation, experiments were carried out throughout the system's operating region. For cross validation, tests were carried out in operating regions different from those used for training. The models were evaluated using performance criteria, such as: Root Mean Square Error (RMSE), Normalized Root Mean Square Error (NRMSE), Final Prediction Error (FPE) and Adjustment percentage. The results were obtained using an experimental bench and showed adjustments greater than 99%. The cross-validation results evaluated with performance indicators show the superiority of intelligent models in comparison to parametric and mathematical models in the multivariable and non-linear identification of water pumping systems for simulation and dynamics prediction purposes.

Open-source machine learning pipeline automatically flags instances of acute respiratory distress syndrome from electronic health records.

Physicians could greatly benefit from automated diagnosis and prognosis tools to help address information overload and decision fatigue. Intensive care physicians stand to benefit greatly from such tools as they are at particularly high risk for those factors. Acute Respiratory Distress Syndrome (ARDS) is a life-threatening condition affecting >10% of critical care patients and has a mortality rate over 40%. However, recognition rates for ARDS have been shown to be low (30-70%) in clinical settings. In this work, we present a reproducible computational pipeline that automatically adjudicates ARDS on retrospective datasets of mechanically ventilated adult patients. This pipeline automates the steps outlined by the Berlin Definition through implementation of natural language processing tools and classification algorithms. First, we used labeled chest imaging reports from two different hospitals over three different time periods to train an XGBoost model to detect bilateral infiltrates, and a subset of attending physician notes from one hospital labeled for the most common ARDS risk factor (pneumonia) to train another XGBoost model to detect a pneumonia diagnosis. Both models achieve high performance when tested on out-of-bag samples-an area under the receiver operating characteristic curve (AUROC) of 0.88 for adjudicating chest imaging reports, and an AUROC of 0.86 for detecting pneumonia on attending physician notes. Next, we integrate the models and validate the entire pipeline on a fourth cohort from a third hospital (MIMIC-III) and find a sensitivity of 93.5% - an extraordinary improvement over the 22.6% ARDS recognition rate reported for these encounters - along with a false positive rate of 18.8%. We conclude that our reproducible, automated diagnostic pipeline exhibits promising ARDS retrospective adjudication performance, thus providing a valuable resource for physicians aiming to enhance ARDS diagnosis and treatment strategies. We surmise that real-time integration of the pipeline with EHR systems has the potential to aid clinical practice by facilitating the recognition of ARDS cases at scale.

Cautiously optimistic: paediatric critical care nurses’ perspectives on data-driven algorithms in low-resource settings—a human-centred design study in Malawi

BackgroundPaediatric critical care nurses face challenges in promptly detecting patient deterioration and delivering high-quality care, especially in low-resource settings (LRS). Patient monitors equipped with data-driven algorithms that monitor and integrate clinical data can optimise scarce resources (e.g. trained staff) offering solutions to these challenges. Poor algorithm output design and workflow integration, however, are important factors hindering successful implementation. This study aims to explore nurses’ perspectives to inform the development of a data-driven algorithm and user-friendly interface for future integration into a continuous vital signs monitoring system for critical care in LRS.MethodsHuman-centred design methods, including contextual inquiry, semi-structured interviews, prototyping and co-design sessions, were carried out at the high-dependency units of Queen Elizabeth Central Hospital and Zomba Central Hospital in Malawi between March and July 2023. Triangulating these methods, we identified what algorithm could assist nurses and used co-creation methods to design a user interface prototype. Data were analysed using qualitative content analysis.ResultsWorkflow observations demonstrated the effects of personnel shortages and limited monitor equipment for vital signs monitoring. Interviews identified four themes: workload and workflow, patient prioritisation, interaction with guardians, and perspectives on data-driven algorithms. The interviews emphasised the advantages of predictive algorithms in anticipating patient deterioration, underlining the need to integrate the algorithm’s output, the (constant) monitoring data, and the patient’s present clinical condition. Nurses preferred a scoring system represented with familiar scales and colour codes. During co-design sessions, trust, usability and context specificity were emphasised as requirements for these algorithms. Four prototype components were examined, with nurses favouring scores represented by colour codes and visual representations of score changes.ConclusionsNurses in the LRS studied, perceived that data-driven algorithms, especially for predicting patient deterioration, could improve the provision of critical care. This can be achieved by translating nurses’ perspectives into design strategies, as has been carried out in this study. The lessons learned were summarised as actionable pre-implementation recommendations for the development and implementation of data-driven algorithms in LRS.

Manipulator Differential Kinematics: Part 2: Acceleration and Advanced Applications

This is the second and final article on the tutorial on manipulator differential kinematics. In Part 1, we described a method of modelling kinematics using the elementary transform sequence (ETS), before formulating forward kinematics and the manipulator Jacobian. We then described some basic applications of the manipulator Jacobian including resolved-rate motion control (RRMC), inverse kinematics (IK), and some manipulator performance measures. In this article, we formulate the second-order differential kinematics, leading to a definition of manipulator Hessian. We then describe the differential kinematics' analytical forms, which are essential to dynamics applications. Subsequently, we provide a general formula for higher-order derivatives. The first application we consider is advanced velocity control. In this section, we extend resolved-rate motion control to perform sub-tasks while still achieving the goal before redefining the algorithm as a quadratic program to enable greater flexibility and additional constraints. We then take another look at numerical inverse kinematics with an emphasis on adding constraints. Finally, we analyse how the manipulator Hessian can help to escape singularities. We have provided Jupyter Notebooks to accompany each section within this tutorial. The Notebooks are written in Python code and use the Robotics Toolbox for Python, and the Swift Simulator to provide examples and implementations of algorithms. While not absolutely essential, for the most engaging and informative experience, we recommend working through the Jupyter Notebooks while reading this article. The Notebooks and setup instructions can be accessed at https://github.com/jhavl/dkt.

Manipulator Differential Kinematics: Part I: Kinematics, Velocity, and Applications [Tutorial

Manipulator kinematics is concerned with the motion of each link within a manipulator without considering mass or force. In this article, which is the first in a two-part tutorial, we provide an introduction to modelling manipulator kinematics using the elementary transform sequence (ETS). Then we formulate the first-order differential kinematics, which leads to the manipulator Jacobian, which is the basis for velocity control and inverse kinematics. We describe essential classical techniques which rely on the manipulator Jacobian before exhibiting some contemporary applications. Part II of this tutorial provides a formulation of second and higher-order differential kinematics, introduces the manipulator Hessian, and illustrates advanced techniques, some of which improve the performance of techniques demonstrated in Part I. We have provided Jupyter Notebooks to accompany each section within this tutorial. The Notebooks are written in Python code and use the Robotics Toolbox for Python, and the Swift Simulator to provide examples and implementations of algorithms. While not absolutely essential, for the most engaging and informative experience, we recommend working through the Jupyter Notebooks while reading this article. The Notebooks and setup instructions can be accessed at https://github.com/jhavl/dkt.

Optimising fatigue, abdominal pain and faecal incontinence in people with inflammatory bowel disease (IBD-BOOST Optimise): feasibility study of a checklist and algorithm for initial nurse-led management

ObjectiveMany people with inflammatory bowel disease (IBD) experience fatigue, pain and faecal incontinence that some feel are inadequately addressed. It is unknown how many have potentially reversible medical issues underlying...

Optimizing the position of photovoltaic solar tracker panels with artificial intelligence using MATLAB Simulink

This research aims to apply an artificial intelligence (AI) system to control the position of photovoltaic (PV) panels to maximize the use of solar energy using the solar tracker. The implementation of AI algorithms to achieve optimal panel orientation, considering factors such as sunlight intensity and sun position is also discussed. The simulation results using matrix laboratory (MATLAB) Simulink can be observed on the scope, displaying the position control graph of the solar panel from sunrise to sunset. By employing proportional integral derivative (PID) control, the error is likely to be minimal, ensuring that the panel will continue to follow the sun until it sets at the maximum point of 4:00 PM. After that, the panel can be adjusted back or reset to the initial position at 6:00 AM for the following day. In a full-day simulation, the solar panel will follow the sun's movement from sunset to sunrise. At the basic level, sunrise occurs in the first hour at position 1.0, which is 6:00 AM in the minimum point at the bottom left corner of the curve, and sunset occurs in the afternoon at position 5.25, which is 4:00 PM at the maximum point in the top right corner of the curve.

AI in Financial Strategy: Continuous Monitoring for Enhanced Profitability

This article investigates the transformative impact of Artificial Intelligence (AI) in financial strategy through continuous monitoring systems designed to enhance organizational profitability. The article examines how AI-driven solutions analyze spending patterns, optimize resource allocation, and improve decision-making processes across various organizational contexts. Through comprehensive analysis of historical financial data and implementation of advanced machine learning algorithms, this research demonstrates significant improvements in cost reduction and budget optimization. The article reveals that organizations implementing AI-driven financial monitoring systems achieve substantial reductions in operational costs, enhanced accuracy in spending categorization, and improved financial decision-making capabilities. The article presents a systematic framework for implementing AI-based financial monitoring systems, including detailed methodologies for pattern recognition, expenditure analysis, and resource utilization assessment. Additionally, it explores the practical implications of AI integration in financial strategy, addressing both the opportunities and challenges organizations face during implementation. The article contributes to the growing body of knowledge on AI applications in financial management by providing actionable insights for organizations seeking to leverage artificial intelligence for improved financial performance and strategic decision-making.

Reliability of Regression Based Hybrid Machine Learning Models for the Prediction of Solar Photovoltaics Power Generation

Solar Photovoltaics (PVs) have become widespread as micro-distributed electric power generators in urban residential and commercial areas due to their affordability and minimal maintenance requirements. Despite these advantages, PV generation is intermittent, necessitating the implementation of robust predictive algorithms to capture power generation trends effectively. Accurate PV generation prediction is crucial for balancing energy demand and supply. Precise predictions help utilities use other grid resources efficiently, enhance market participation, and make informed planning decisions. Therefore, ensuring the precise performance of predictive models is imperative in the power generation industry. However, the performance of the predictive models typically fluctuates over time, necessitating a reliability assessment of their performance. This paper develops a hybrid machine learning model by integrating the support vector machine (SVM), random forest (RF), and gradient boosting machine (GBM) with multivariate adaptive regression spline (MARS) to predict the hourly PV power generation for 3-day and 7-day periods in three urban areas of North Dakota. The performance of the models has been recorded over a year, and a probability distribution model is proposed to demonstrate the hybrid algorithm’s reliability and effectiveness. Results show the proposed prediction model is more reliable for shorter prediction periods. The hybrid-MARS models significantly improve prediction reliability compared to the stand-alone MARS model. Among these models, MARS-SVM exhibits the highest reliability and consistently better accuracy than other hybrid models.

Design of mean filter using field programmable gate arrays for digital images

In this paper, we design and analysis of mean filter using field programmable gate arrays (FPGAs) for digital images, FPGAs are integrated circuits consisting of interconnections that connect programmable internal hardware blocks allows users to customize operations for a specific application. FPGA is an ideal choice for real-time image processing, these FPGA devices are controlled in Verilog or VHDL languages, allowing to design at different levels and adapt to design changes or even support new applications throughout the life of the component. Digital image filtering is the most important task in image processing and with the help of computers, image recognition involves identifying and classifying objects in an image. This paper design of mean filter for digital image processing, implementation and analysis of image processing algorithms on FPGAs. The results obtained on the FPGA are compared and analyzed with the results by MATLAB software.

A robust error sensing strategy for global active noise control in car cabins.

Global active noise control (ANC) systems reduce noise over the entire car cabin with robust performance even as the human head moves; however, they have not been implemented in real-world applications. A robust error sensing strategy is proposed in this paper that is based on which a feasible global ANC system is realized in an electric car, and real-time ANC experiments demonstrate its effectiveness. Simulations based on measured road noise show that using evenly distributed error sensors is a robust error sensing strategy for different car speeds and the upper limit frequency of 3 dB global control is inversely proportional to the equivalent distance between error sensors. Real-time experiments with a 5-seat A-class sedan demonstrate that an average noise reduction of 3.8 dB was achieved between 50 and 250 Hz with 12 evenly distributed error sensors using the four standard car audio loudspeakers as secondary sources. Virtual sensing techniques can be integrated to constitute a more practical system without obstructing the movement of human heads. The findings in this study establish a benchmark for global noise control in car cabins and can be a starting point for future optimization of the system and implementation of adaptive algorithms.

Developing and Implementing a Patient-Centered Opioid Prescribing Algorithm among Gynecological Oncology Patients.

Background: The opioid epidemic is a public health crisis. However, opioid prescription recommendations have not been established in gynecological oncology, and guidelines that incorporate patient-reported pain are lacking. Objectives: The article aims to evaluate prescribing patterns, utilization, and patient-reported pain control in gynecological oncology patients at a large tertiary academic center. Methods: This was a two-phase, prospective cohort study. For Phase 1, patients undergoing hysterectomy through the gynecological oncology division at the University of New Mexico were enrolled. Postoperative opioid use was collected and standardized to oral morphine milligram equivalents (MMEs). The factors associated with outpatient opioid use were used to develop an opioid prescription algorithm. In Phase 2, we evaluated the implementation of the prescription algorithm. For both phases, patients completed a demographic survey, satisfaction survey, and validated pain questionnaires. Results: In Phase 1, the amount of opioids used was significantly lower than the amount of opioids prescribed. Factors that correlated with postoperative opioid use included surgical procedures and last 24-hour inpatient MME use. A standardized opioid prescription algorithm was developed by incorporating these factors. In Phase 2, the opioid prescribing algorithm there was no significant difference in pain scores between the two phases. Conclusions: Opioids were substantially overprescribed in gynecological oncology patients undergoing hysterectomy. Our study found that the surgical route and last 24-hour MME inpatient usage were reliable predictors of outpatient opioid use. We developed and implemented a standardized opioid prescription algorithm that was validated by comparing the pain control measures in the two phases.

Compact hardware implementation of ZUC algorithm for NB-IoT

Compact hardware implementation of ZUC algorithm for NB-IoT

BEATRIX: An open source humanoid head platform for robotics teaching and research

This paper introduces BEATRIX, a novel robotic head designed to bridge the gap between theoretical knowledge and practical experience in the field of robotics at universities. The BEATRIX robot comprises a head actuated by a neck-like mechanism with three stepper motors, two cameras and two microphones for acquisition of visual and audio information from the environment. The robot can be connected to any external computer for the design and implementation of algorithms for applications in human–robot interaction. The proposed robotic platform has been used successfully with undergraduate and master students implementing tasks such as face detection and tracking, sound detection and tracking, robot control and graphical user interfaces. This paper includes lists of all the robot components, assembly instructions, and links to all CAD and software files, facilitating replication and further exploration. The robot design and integration of visual and audio sensors enables the development of engaging educational tutorials and robot experiments, enhancing the teaching and learning experience in robotics.

Автоматизация визуального контроля фотошаблонов для изделий микроэлектроники

The choice of a specific research topic was caused by a request for the development and implementation of automatic optical inspection at a semiconductor plant. The purpose of the work was to develop requirements, conduct technical design and create an optical control system for geometry deviations from a photomask drawing and a conductive pattern obtained using a manual stencil printer using relatively inexpensive equipment. As a result of the research, a pilot design sample of an automated optical control system using relatively inexpensive equipment was created and a computational algorithm was developed that ensures increased performance of the visual image recognition system, which allows to significantly reduce the percentage of defects. The work describes the implemented algorithm for obtaining images by an optical system and extracting images from a drawing file. Regardless of the method of obtaining an image (optical system, scanning electron microscope), there remains interest in choosing a criterion for comparing the obtained image with the reference one. The paper studies quantitative empirical metrics - Mean Square Error and Peak Signal-to-Noise Ratio for various noise reduction methods Block-Matching and 3D filtering and the classical spatial filtering method of Gaussian blur. The sensitivity of the structural similarity index metric to structural distortions of images after noise reduction is checked, taking into account the minimum values of the structural elements of metal-ceramic housings. Based on the Rosner test applied to the obtained values of the structural similarity metric, images containing defects are identified. The user interface provides for the output of the image area with a defect to the operator's screen.

Individual risk of not responding to psychotherapy in Latin America: Bringing data-informed precision care to underresourced clinical settings.

Machine learning has a great potential for prospectively forecasting individual patient response to mental health care (MHC), thereby enabling treatment personalization. However, previous efforts have been limited to populations living in predominantly higher income, developed countries. This study aimed to extend the reach of precision MHC systems by developing and testing a feasible and readily implementable algorithm for identifying patients at risk of nonresponse to routinely delivered psychotherapy in Chile, a developing country in Latin America. Data were derived from a community-based, randomized trial that tested the effects of progress feedback on naturalistically delivered psychotherapy outcome. Patients were 547 adults who were consecutively admitted to an outpatient clinic in Santiago, Chile. Treatment response was defined using norms for reliable improvement on the Outcome Questionnaire-30. Based on 10 sociodemographic and seven clinical predictors, we trained elastic net and random forest algorithms on a randomly selected training set (70%; n = 384). The best performing algorithm was tested on a hold-out sample (30%; n = 163). Reliable improvement was achieved in 42% of the cases. A random forest algorithm demonstrated moderate performance in the hold-out sample (area under the curve = .74, Brier score = .21), correctly identifying 73% of the patients who did not respond. This study developed a predictive algorithm that demonstrated moderate accuracy in identifying patients at risk of nonresponse to naturalistic psychotherapy in Chile, using routinely assessed and easy-to-collect sociodemographic and clinical information. Using such tools may represent one step toward reducing the multilayered outcome disparities faced by individuals receiving MHC in socioeconomically disadvantaged contexts. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Development of Online Auction System Using Greedy Algorithm Method Based on Model-View-Controller (MVC)

This research develops an online auction system utilizing the Django framework and Greedy algorithm to optimize the bidding process, addressing challenges in traditional auction systems such as geographical limitations, lack of transparency, and manual processes prone to errors. The study employs an Agile methodology with a Scrum approach, implementing a Model-View-Controller (MVC) architecture to separate business logic, presentation, and data management. The development of the auction application involves planning to identify system requirements, designing the architecture, implementing the backend/frontend, testing features and algorithms, deploying to the server, and conducting evaluation and adjustments based on feedback. Results demonstrate that the use of Django accelerates development and enhances system security, while the implementation of the Greedy algorithm successfully optimizes real-time bidding and winner selection processes. Key features developed include auction management, an automated bidding system, and secure payment integration.

Development and Implementation of a YOLOv5-based Adhesive Application Defect Detection Algorithm

Development and Implementation of a YOLOv5-based Adhesive Application Defect Detection Algorithm

Commodity Prediction: ML-Based Commodity Suggestion

The increasing unpredictability of climate conditions and the dynamic nature of global markets pose significant challenges to traditional agricultural practices. This study aims to develop a predictive model using machine learning and artificial intelligence to assist farmers in selecting profitable exotic crops. The model focuses on optimizing agricultural profitability by analyzing key factors such as weather conditions and region. Through the use of data-driven techniques, including a suggestion matrix and confusion matrix for recommendation, the model predicts the most suitable crops for specific regions. To ensure robust predictions, the pre-processing steps address critical issues such as missing values, outlier detection due to inconsistencies in state-scrapped data, and normalization to align with seasonal and harvesting cycles. Reliable weather data sources are also integrated to account for variance in climate conditions, which directly impacts crop yield. The proposed model, validated across various scenarios, aims to enhance agricultural efficiency by providing farmers with actionable insights, ultimately leading to higher yields and increased income through the cultivation of less-known, high-demand crops. This paper discusses the data pre-processing techniques, model validation strategies, and the practical implementation of machine learning algorithms in the agricultural sector, contributing to the advancement of smart farming practices.