Implementation Of Algorithm Research Articles

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.

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

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

Predictive Analytics for Customer Retention: A Data-Driven Framework for Proactive Engagement and Satisfaction Management

This comprehensive article examines the implementation of predictive analytics and data-driven frameworks for enhancing customer retention in modern business environments. The article explores how advanced analytics, machine learning algorithms, and proactive engagement strategies can significantly improve customer satisfaction and reduce churn rates. Through detailed article analysis of usage patterns, engagement metrics, and customer behavior, the article demonstrates the effectiveness of sophisticated intervention strategies in maintaining strong customer relationships. The article investigates the development and implementation of satisfaction score algorithms, real-time monitoring systems, and customized support mechanisms that enable organizations to identify and address potential issues before they lead to customer attrition. Furthermore, it evaluates the impact of integrated feedback systems and sentiment analysis in creating more responsive and effective customer retention strategies. The article provides valuable insights into how organizations can leverage data analytics to create more personalized and proactive customer engagement approaches, ultimately leading to improved customer lifetime value and business sustainability.

Implementing Mathematics of Arrays in Modern Fortran: Efficiency and Efficacy

Mathematics of Arrays (MoA) concerns the formal description of algorithms working on arrays of data and their efficient and effective implementation in software and hardware. Since (multidimensional) arrays are one of the most important data structures in Fortran, as witnessed by their native support in its language and the numerous operations and functions that take arrays as inputs and outputs, it is natural to examine how Fortran can be used as an implementation language for MoA. This article presents the first results, both in terms of code and of performance, regarding this union. It may serve as a basis for further research, both with respect to the formal theory of MoA and to improving the practical implementation of array-based algorithms.

Implementation and Performance Evaluation of Quantum Machine Learning Algorithms for Binary Classification

Implementation and Performance Evaluation of Quantum Machine Learning Algorithms for Binary Classification

АЛГОРИТМИ ПРОГРАМНОЇ РЕАЛІЗАЦІЇ ЦИФРОВИХ СТАТИСТИЧНО ОПТИМАЛЬНИХ РЕГУЛЯТОРІВ АСИНХРОННИХ ЕЛЕКТРОПРИВОДІВ ІЗ СТОХАСТИЧНИМИ НАВАНТАЖЕННЯМИ

The paper is devoted to the development of algorithms for the programm implementation of digital statistically optimal regulators of electric drives, which are under the influence of dynamic loads that change according to stochastic laws. On the basis of continuous transfer functions of statistically optimal regulators for similar loads, which can be approximated by exponential and exponential-cosine correlation functions, the following algorithms were obtained in the form of recurrent difference equations, which can be implemented by software. Recommendations have been developed for the accuracy of determining the parameters of the corresponding digital regulators. Ref. 11, fig. 5.

Stroke triage using the FAST-ED score shortens process times in large vessel occlusion strokes in a physician staffed pre-hospital emergency medical (PHEM) system.

The impact of streamlining algorithms for stroke patients on process times in pre-hospital emergency medicine (PHEM) is not well investigated. We analyzed the changes in pre- and in-hospital process times after implementation of a streamlining algorithm in a physician staffed PHEM system. We conducted a prospective observational study and analyzed process times of adult stroke patients attended by emergency physicians (EP) of the city of Göttingen PHEM service after implementation of a streamlining algorithm including stroke triage using the FAST-ED score. Stroke patients with standard emergency treatment attended before the implementation served as a control group. All patients were transported directly to the University Medical Center Göttingen (UMG) and received endovascular therapy (EVT) and/or systemic thrombolytic therapy. Of 75 suitable patients eligible in the study group, 37 (49.3%) received EVT and were compared to 44 patients in the control group. Pre-hospital process times did not differ significantly. Median door-to-CT time (12 vs 18 min, p = 0.017) and door-to-lysis time (20 vs 24 min, p = 0.005) were significantly shorter in the study group. Door-to-groin time was also shortened in the study group (42 vs 49 min) but not significantly (p = 0.088). Our findings indicate that a PHEM streamlining algorithm (namely the FAST-ED score) can significantly shorten in-hospital process times without delaying pre-hospital care. This improved coordination between PHEM and in-hospital emergency medicine (IHEM) may enhance neurological outcomes for stroke patients. Further research is needed to confirm these results and assess their applicability in other healthcare settings.

Optimization of SM2 Algorithm Based on Polynomial Segmentation and Parallel Computing

The SM2 public key cryptographic algorithm is widely utilized for secure communication and data protection due to its strong security and compact key size. However, the intensive large integer operations it requires pose significant computational challenges, which can limit the performance of Internet of Things (IoT) terminal devices. This paper introduces an optimized implementation of the SM2 algorithm specifically designed for IoT contexts. By segmenting large integers as polynomials within a modified Montgomery modular multiplication algorithm, the proposed method enables parallel modular multiplication and reduction, thus addressing storage constraints and reducing computational redundancy. For scalar multiplication, a Co-Z Montgomery ladder algorithm is employed alongside Single Instruction Multiple Data (SIMD) instructions to enhance parallelism, significantly improving efficiency. Experimental results demonstrate that the proposed scheme reduces the computation time for the SM2 algorithm’s digital signature by approximately 20% and enhances data encryption and decryption efficiency by about 15% over existing methods, marking a substantial performance gain for IoT applications.

EXPLORING ELECTROMECHANICAL SYSTEMS IN THE DEVELOPMENT OF NEXT-GENERATION ELECTRIC POWERTRAINS

In the rapidly evolving electric vehicle industry, the study of electromechanical systems in next-generation electric powertrains is of particular relevance. This is driven by the need to enhance energy efficiency, reduce costs, and improve the reliability of vehicles. The article examines the role of innovative materials, advanced design methods, and control algorithms in creating high-efficiency and reliable electric powertrains. Specifically, the impact of nanomaterials such as graphene and carbon nanotubes on reducing motor weight and increasing heat dissipation is analyzed, contributing to improved efficiency and extended driving range. The adoption of additive manufacturing (3D printing) and digital twins accelerates prototyping and component optimization in electric powertrains. Adaptive control algorithms ensure optimal system performance in real-time, enhancing overall efficiency and reliability. Research methods included the analysis of modern materials and technologies, prototyping using additive manufacturing, and the implementation of predictive and adaptive control algorithms. The results demonstrate significant improvements in the performance of electric powertrains due to the use of innovative materials and cutting-edge design technologies. Conclusions confirm that the application of advanced materials and adaptive control algorithms is critical for ensuring the sustainable development of the electric vehicle industry. Future research prospects focus on further refining materials and technologies to enhance scalability and reduce production costs, making electric powertrains more accessible and efficient.

Design of a microservices-based architecture for residential energy efficiency monitoring

With the significant advancement of electrical infrastructure in the context of smart buildings and smart homes, the need arises to overcome the limitations of the traditional energy efficiency control system based on service-oriented architecture (SOA). To address these challenges, this study proposes a distributed architecture based on microservices, with the main objective of improving the performance and stability of these systems. This proposal seeks to enable end users to effectively monitor and control their electrical devices while effectively integrating them into a wide network of power systems. The proposed architecture relies on a series of cloud services that enable better performance and control in energy efficiency management, highlighting key features of microservices such as fault tolerance, performance, and scalability. Using a structural methodology centered on pre-existing components and an iterative approach, a versatile and scalable architecture was designed that addresses current challenges in energy efficiency management. The results show a significant impact on key performance indicators such as demand response, energy savings, and power quality, highlighting the resilience and scalability of the proposed architecture. The conclusions highlight the importance of energy efficiency in reducing the environmental impact and costs associated with electric power, suggesting future improvements in data access and the implementation of advanced machine learning algorithms.

Lefser: Implementation of metagenomic biomarker discovery tool, LEfSe, in R.

LEfSe is a widely used Python package and Galaxy module for metagenomic biomarker discovery and visualization, utilizing the Kruskal-Wallis test, Wilcoxon Rank-Sum test, and Linear Discriminant Analysis. R/Bioconductor provides a large collection of tools for metagenomic data analysis but has lacked an implementation of this widely-used algorithm, hindering benchmarking against other tools and incorporation into R workflows. We present the lefser package to provide comparable functionality within the R/Bioconductor ecosystem of statistical analysis tools, with improvements to the original algorithm for performance, accuracy, and reproducibility. We benchmark the performance of lefser against the original algorithm using human and mouse metagenomic datasets. Our software, lefser, is distributed through the Bioconductor project (https://www.bioconductor.org/packages/release/bioc/html/lefser.html), and all the source code is available in the GitHub repository https://github.com/waldronlab/lefser. Institute for Implementation Science in Population Health, Department of Epidemiology and Biostatistics, City University of New York School of Public Health, New York, NY, United States. E-mail: Sehyun.Oh@sph.cuny.edu (S.O.). Supplementary data are available at Bioinformatics online.

Approximate Counting of Linear Extensions in Practice

We investigate the problem of computing the number of linear extensions of a given partial order on n elements. The problem has applications in numerous areas, such as sorting, planning, and learning graphical models. The problem is #P-hard but admits fully polynomial-time approximation schemes. However, the polynomial complexity bounds of the known schemes involve high degrees and large constant factors, rendering the schemes only feasible when n is some dozens. We present novel schemes, which stem from the idea of not requiring provable polynomial worst-case running time bounds. Using various new algorithmic techniques and implementation optimizations, we discover schemes that yield speedups by several orders of magnitude, enabling accurate approximations even when n is in several hundreds.

Enhancing electrostatic spray-painting efficiency with modified high-voltage conductors: A numerical study on pulsed electric fields

This study presents a numerical simulation of electrostatic spraying using a rotary bell sprayer equipped with a high-voltage control ring conductor. The effects of the electric field generated by constant and pulsed voltages at various frequencies applied to the electrostatic rotary bell sprayer (ERBS) with the control ring are explored. Using the OpenFOAM computational fluid dynamics framework, the simulations employ a three-dimensional Eulerian-Lagrangian method. The implemented algorithm models fully turbulent airflow using a Large Eddy Simulation (LES) approach, along with detailed modeling of spray dynamics, electric fields, and droplet tracking. The primary objective is to investigate the influence of different voltage application modes on the spraying process, with a focus on optimizing droplet consistency and control. The impacts of constant and pulsed voltages on spray plume formation, droplet volumes, and critical spraying stages are examined. Through in-depth analysis of electric field distributions, interface charge densities, and velocity fields, the complex interactions governing pulsed and constant voltage spraying processes are elucidated. The results show that pulsed voltage applied to the control ring shapes the spray plume and alters droplet behavior, though with limited effectiveness. In contrast, applying a pulsed voltage of −40 kVrms to the sprayer’s body cup at frequencies of 800 Hz and 1600 Hz significantly improves spray characteristics, resulting in a modified torus shape and a narrower size range of larger droplets compared to constant voltage condition of −40 kV. This leads to a more uniform droplet size distribution, consistent paint film, and minimal overspray. Consequently, transfer efficiency (TE) increases by 6% at 800 Hz and 4.8% at 1600 Hz compared to constant voltage. This indicates that 800 Hz is the optimal frequency for applying pulsed fields, due to its notable effectiveness in improving deposition efficiency and minimizing material waste.

Isogeometric analysis of adhesion between visco-hyperelastic material based on modified exponential cohesive zone model

This work suggests a reliable contact algorithm for simulating adhesion between soft bodies based on the isogeometric analysis. To accurately characterize adhesion-contact regional effects, a modified exponential cohesive zone model is proposed by incorporating a real contact area influence factor into the original exponential cohesive zone model. Considering the nonlinear large-deformation effect on soft bodies, numerical implementations of isogeometric analysis and bi-potential contact algorithm are proceeded, which provide a continuous normal field of contact interface and precise determination of contact forces. This comprehensive framework is implemented on our in-house isogeometric computing platform, and depicting the ability to recover from large deformations as well as time-dependent mechanical properties of soft bodies through the visco-hyperelastic model. Numerical examples encompassing debonding scenarios involving edges, centers, as well as smooth and rough surfaces, demonstrate the validity on present algorithm with adhesive contact mechanism. The adhesive effects on soft bodies are investigated detailedly via the influences on material viscosity and surface roughness. It has a prospect on providing a valuable reference for future studies especially on analyzing the interfacial adhesion behaviors of biomimetic structures.

AI-Assisted Application for Pediatric Drug Dosing.

Technology in the medical field is continuously advancing due to its numerous subdomains and the ever-growing medical needs of people. Information systems have become integral to doctors' daily routines in patient care, offering flexibility and support in repetitive tasks, thereby allowing more time for critical activities. This paper presents the implementation of a machine learning algorithm, leveraging natural language processing (NLP) and labeling techniques, to analyze medical leaflets from Romania. The aim is to assist pediatricians in determining appropriate treatment doses for children based on various parameters such as age, weight, and other significant factors.

Measurement of Sea Surface Characteristics from Radar Images Using Gradient Methods

Introduction. Remote sensing and monitoring of the sea surface are of great importance in such fields, as operational oceanography, environmental monitoring, etc. The ability to quickly assess the state of the sea surface is particularly relevant in areas that pose a danger to shipping, where rapid and accurate response becomes critical. Modern radars represent information as digital image series largely reminiscent to a frame series in a video stream, thus enabling the use of gradient methods originally designed for and proven successful in video analysis.Aim. Determination of sea wave characteristics from radar images using gradient motion estimation methods. The use of gradient methods will allow implementing additional tools for processing radar image series obtained from sea backscatter.Materials and methods. To assess the characteristics of the sea surface from radar images, gradient methods were used. To train the methods, a series of synthetic images of the sea surface obtained by mathematical modeling were used. To evaluate the effectiveness of the gradient methods, two representative experimental radar image series provided by the Institute of Oceanography RAS were employed.Results. Using gradient methods, the direction and speed of waves were calculated from several consecutive radar observations. Regression models of the dependence of calculated values on the specified ones were constructed. The Farneback and TV-L1 methods proved to be effective especially for obtaining the direction of the sea waves.Conclusion. An algorithm for evaluating speed and direction of the sea surface displacement using gradient methods was pre-trained using simulated model data. The implemented methods and algorithms for assessing the speed and direction of sea waves were validated using two experimental image series obtained from shipborne navigational radars.

IMPLEMENTASI ALGORITMA FUZZY PADA SISTEM KONTROL AQUAPONIK PADI

Aquaponics is an agricultural system that combines fish and plant cultivation in one closed system. In an aquaponics system, the water used for fish cultivation is also used to irrigate plants with rice aquaponics as one example. However, monitoring and controlling aquaponic systems is still done manually, which has many shortcomings, including requiring a relatively long time and accuracy that is not guaranteed, especially in large-scale aquaponics management. Implementing the fuzzy algorithm in the rice aquaponics control system aims to make it easier for farmers to monitor the condition of the rice and control the water change system in the pond in real time via the Blynk application on their smartphone. This system combines ESP-32 technology, fuzzy algorithms, and the Internet of Things (IoT) to monitor and control the rice aquaponics system. The results of data collection from the implementation of the fuzzy algorithm in the rice aquaponics control system show that the tool functions well. This tool can monitor the condition of rice and control the water change system in the pond in real time using the Blynk application. The level of accuracy of implementing the fuzzy algorithm for monitoring rice conditions was 99.61% and the accuracy of implementing the fuzzy algorithm for pump control of the water change system was 98.95%.

A super element model for failure analysis of masonry buildings under lateral in-plane loading

This study developed a discrete element-based approach called Super Element Model to estimate the non-linear behavior and damage propagation of multi-story and multi-span masonry buildings subjected to in-plane lateral loads. To this aim, the piers and spandrels were substituted by a super element constituted by four large isosceles triangular panels and eight connector links, while the cross-joint areas remained rectangular. Two vertical/horizontal links also represent the connection of the super element of piers/spandrels to the cross-joint panels at each end. The large panels were assumed to behave elastically and inelasticity was only concentrated at the connector links. All the connector links were bi-component springs considering axial and shear behavior. With the help of masonry stress–strain curve, a simplified bi-linear behavior was extracted for springs. Thanks to the appropriate geometrical configuration of the piers’ equivalent super element, a dynamic interaction was provided between lateral capacity and normal stresses originating from lateral loads. After presenting a step-by-step algorithm for the model implementation in commercial software, two full-scale masonry buildings were chosen for validation purposes. The obtained results proved the proposed Super Element Model is reliable and user-friendly.

Dual-Frequency Multi-Constellation Global Navigation Satellite System/Inertial Measurements Unit Tight Hybridization for Urban Air Mobility Applications

A global navigation satellite system (GNSS) for remotely piloted aircraft systems (RPASs) positioning is essential, thanks to the worldwide availability and continuity of this technology in the provision of positioning services. This makes the GNSS technology a critical element as malfunctions impacting on the determination of the position, velocity and timing (PVT) solution could determine safety issues. Such an aspect is particularly challenging in urban air mobility (UAM) scenarios, where low satellite visibility, multipath, radio frequency interference and cyber threats can dangerously affect the PVT solution. So, to meet integrity requirements, GNSS receiver measurements are augmented/fused with other aircraft sensors that can supply position and/or velocity information on the aircraft without relying on any other satellite and/or ground infrastructures. In this framework, in this paper, the algorithms of a hybrid navigation unit (HNU) for UAM applications are detailed, implementing a tightly coupled sensor fusion between a dual-frequency multi-constellation GNSS receiver, an inertial measurements unit and the barometric altitude from an air data computer. The implemented navigation algorithm is integrated with autonomous fault detection and exclusion of GPS/Galileo/BeiDou satellites and the estimation of navigation solution integrity/accuracy (i.e., protection level and figures of merit). In-flight tests were performed to validate the HNU functionalities demonstrating its effectiveness in UAM scenarios even in the presence of cyber threats. In detail, the navigation solution, compared with a real-time kinematic GPS receiver used as the reference centimetre-level position sensor, demonstrated good accuracy, with position errors below 15 m horizontally and 10 m vertically under nominal conditions (i.e., urban scenarios characterized by satellite low visibility and multipath). It continued to provide a valid navigation solution even in the presence of off-nominal events, such as spoofing attacks. The cyber threats were correctly detected and excluded by the system through the indication of the valid/not valid satellite measurements. However, the results indicate a need for fine-tuning the EKF to improve the estimation of figures of merit and protection levels associated to the navigation solution during the cyber-attacks. In contrast, solution accuracy and integrity indicators are well estimated in nominal conditions.

Accelerating radio astronomy imaging with RICK

This paper presents an implementation of radio astronomy imaging algorithms on modern High Performance Computing (HPC) infrastructures, exploiting distributed memory parallelism and acceleration throughout multiple GPUs. Our code, called RICK (Radio Imaging Code Kernels), is capable of performing the major steps of the w-stacking algorithm presented in Offringa et al. (2014) both inter- and intra-node, and in particular has the possibility to run entirely on the GPU memory, minimising the number of data transfers between CPU and GPU. This feature, especially among multiple GPUs, is critical given the huge sizes of radio datasets involved.After a detailed description of the new implementations of the code with respect to the first version presented in Gheller et al. (2023), we analyse the performances of the code for each step involved in its execution. We also discuss the pros and cons related to an accelerated approach to this problem and its impact on the overall behaviour of the code. Such approach to the problem results in a significant improvement in terms of runtime with respect to the CPU version of the code, as long as the amount of computational resources does not exceed the one requested by the size of the problem: the code, in fact, is now limited by the communication costs, with the computation that gets heavily reduced by the capabilities of the accelerators.