Algorithm Technique Research Articles

Innovative protection schemes through hardware-in-the-loop dynamic testing.

In microgrid environments, the behaviour of Distributed Generation (DG) during fault conditions varies significantly based on DG types and penetration levels. Conventional Overcurrent Relays (OCRs) with standard time-current characteristics may exhibit limitations during excessive fault scenarios, leading to OCR operating delays and mis-coordination within the microgrid. This study proposes a novel constraint on the maximum Current Multiplier Setting (CMS) and utilizes Water Cycle Algorithm (WCA) and Particle Swarm Optimization (PSO) techniques to optimize the Time Multiplier Setting (TMS). Comparative dynamic analysis through real-time validation shows that the non-standard OCR approach outperforms the standard IEC scheme across all grid operation modes with different type, size and location of DGs. For instance, under F1 conditions, the tripping time of OCR1 was reduced from 0.0226 seconds (IEC) to 0.000981 seconds (non-standard). HIL results further affirm the efficacy of the proposed scheme. The optimization process, implemented in MATLAB and validated using ATP/EMTP simulations and SIPROTEC 7SJ62 relays, demonstrates enhanced microgrid protection coordination, improving system reliability and performance.

Optimizing Energy-Efficient in VLSI Architecture for FIR Filter in Seismic Signal Processing

This project aims to developing an optimized and energy-efficient VLSI design for FIR filters specifically designed for seismic signal processing. The process begins by converting seismic signal dataset values into binary format, and then, simulating them in MATLAB, and generating a coefficient file. This coefficient file is then analyzed using Verilog HDL code and simulated in the Xilinx Vivado 2022.2 tool to assess key parameters such as area, delay, and power. The suggested architecture lessens the complexity of computing, hardware efficiency compared to traditional FIR filters that utilize the CSE technique. This design employs a critical method known as the CSD-based Matrix-Grouped Common Subexpression Elimination (MCSE) algorithm, which significantly reduces the quantity of logic operators (LOs) and logic depths (LDs). Additionally, the design incorporates a Half-Unit Biased (HUB) rounding technique to minimize the truncation errors and cut-set retiming method to reduce the critical-path delay (CPD). This hardware-efficient FIR filter constructs integrates the CSD-based MCSE algorithm, HUB rounding, and cut-set retiming techniques to offer a reconfigurable FIR filter configuration optimized for hardware efficiency, thereby enhancing the real-time alert seismic signal processing. The implementation of an Artix-7 FPGA board including clock gating techniques to further reduces the power consumption.

Improvement of low-frequency oscillation damping in power systems using a deep learning technique

Over the last few years, machine learning tools have significantly progressed and attracted extensive applications in many parts of contemporary life. The power sector is one of the leading domains implementing such appealing and effective technologies for diverse applications as a part of the digital transformation of electric networks. A power system's low-frequency oscillation (LFO) is a non-threatening but slow-burning problem that might cause complete network failure unless adequately handled. This article proposes a state-of-the-art procedure of LFO damping in electric power networks via the sine cosine algorithm and deep learning (DL) technique. It uses two networks of power systems, in which the synchronous generator is fitted with a power system stabilizer (PSS) in the case of the first network; in the other, the synchronous machine is conjoined to the PSS that coordinates with a unified power flow controller. The proposal is developed based on the statistical assessment of the analyzed networks to improve the LFO damping via real-time adjustment of PSS parameters/variables. The proposed technique was evaluated using power system stability performance measuring criteria, such as the eigenvalue and minimum damping ratio. In the end, the effectivity of the stability-gaining procedure is also tested by time-domain simulation to implement in real-time. The study also dealt with a comparative investigation and discussion of the findings of some published works to conclude the capability of the proposed DL tool for stability improvement of the system in real-time by removing undesirable LFOs.

Enhancing thermal field prediction in a jet in cross flow through turbulent heat flux model optimization by using large eddy simulation

High fidelity big data obtained from highly accurate large eddy simulation (LES) was utilized to enhance current models for turbulent heat transfer, boosting the precision of the realizable Reynolds averaged Navier Stokes (RANS) k-ε model in forecasting film cooling thermal field. The LES analysis was conducted on a flat plate with a jet in crossflow, at a primary flow Reynolds number (Re) of around 17382. Post-validation of the LES outcomes, a data analysis, and a numerical optimization (gradient descent algorithm) technique were employed to fine-tune three chosen models for turbulent Prandtl number using data near the coolant wall. In order to demonstrate the effectiveness of these refined models for RANS simulations of various film cooling setups with distinct shapes and flow situations, a series of simulations were executed, encompassing two curved surfaces to simulate flow around leading-edge and over the blade suction side. The optimized models exhibited marked enhancement in forecasting film cooling effectiveness in both averaged lateral and longitudinal directions (achieving reductions in numerical errors of up to 68.0 % and 43.67 % respectively). These fine-tuned models were proven suitable for use across different geometries and flow conditions according to their performance in three analyzed problems.

A review of unsupervised k-value selection techniques in clustering algorithms

Purpose: Automatic grouping of data according to certain characteristics is made possible by clustering algorithms, which makes them an essential tool when working with large datasets. However, although they are unsupervised tools, they generally require the specification of the number of clusters to be formed, k, a task that may be simple for a human, but quite complex to automate. Despite the most commonly used k-value selection techniques offer acceptable results, they are not without shortcomings, suggesting that there is ample room for improvement. This paper briefly introduces clustering techniques, discusses the main shortcomings of conventional k-value selection techniques and examines the advantages and limitations of nine promising alternatives presented in recent years.Design/methodology/approach: An evaluation of the main shortcomings of classic k-value estimation techniques has been carried out, and the newest proposals have been explained and compared.Findings: New k-value estimation indices and methodologies proposed by authors guarantee better results, extending the use of these techniques to large volumes of data, and complex shapes and structures. However, no generical methodology able to overcome all the described shortcomings has still been developed.Research limitations/implications: This research is limited to the newest developed techniques for k-value estimation, including proposals published since 2019. Older proposals have not been considered, as the newest ones overcome the former’s shortcomings. A k-value estimation techniques review published in 2019 is cited in the test as a base reference.Practical implications: Although the examples listed in the text apply to industry, the techniques described and discussed in this review are applicable to any area of science that can benefit from the use of clustering techniques.Originality/value: To date, there has been no paper comparing the new k-value estimation techniques. Although there are literature reviews comparing the classical methods, these methods are nowadays nearly obsolete due to the complexity of the data usually faced.

Pothole detection and International Roughness Index (IRI) calculation using ATVs for road monitoring

The accelerated deterioration of roads is conditioned by parameters such as climate change, poor construction, and heavy vehicle traffic. Two relevant measures to monitor the condition of a road are the International Roughness Index (IRI) and the number of functional failures in a segment, mainly potholes, since they are associated with higher risks such as accidents or damage to vehicle mechanics. In the state of the art, pothole detection or International Roughness Index (IRI) calculation algorithms are proposed, but they use vehicles designed to produce less vibration and use phones that decrease the performance of the embedded sensors. In addition, some works propose complex algorithms of higher computational load that leads to use more hardware and power consumption. In this context, the present work aims to monitor the condition of a road through low-cost dedicated sensors implemented in an urban patrolling all-terrain vehicles (ATVs), where energy consumption is optimized using low-complexity signal processing techniques for noise reduction and detection algorithms. The results show an average accuracy of 90.5% in the detection of potholes, a relative error of 8.41% in the calculation of the International Roughness Index (IRI) and an average reduction of 65.4% in the monitoring time.

Variance-based global sensitivity analysis of the performance of a proton exchange membrane water electrolyzer

This study is threefold objective. First, a nonlinear one-dimensional steady-state simulation model for hydrogen production from proton exchange membrane water electrolyzer (PEMWE) is established. The model comprehensively addresses activation, diffusion overpotentials and ohmic potential drop, and particularly incorporating Nafion membrane properties in the presence of liquid water. The model is enhanced by analyzing the hydrogen crossover, introducing corresponding diffusion equations to evaluate Faraday efficiency. The model accurately quantifies voltage efficiency, hydrogen production rate and specific energy consumption, and it is validated with published experimental data found in the scientific literature. Second, a variance-based global sensitivity analysis (GSA) on the model, is employed as a metric to assess the impact of operating conditions and material characteristics on three objective functions: the hydrogen production rate; the voltage efficiency and the specific energy consumption. Third, to support the GSA analysis, genetic algorithm (GA) technique is performed to maximize hydrogen production rate while minimizing specific energy consumption. In the course of this novel investigation, it was discerned that the number of cells, the cross-sectional area of the electrolyzer, the current density and temperature all exerted a significant impact on the three objective functions. This combined approach GSA-GA provides a thorough exploration of parameter influences and an efficient optimization strategy for enhancing the model's performance. These findings provide valuable insights that can guide analysis of the performance and the optimization of the PEMWE system.

A two-stage optimization model for relief distribution to disaster survivors under two-fold uncertainty

Disasters are unforeseen occurrences requiring extensive transport deployment to support and relieve victims. Sometimes, this transportation is not feasible directly from some supply points to some destination points. Due to this tragedy, it is unclear precisely what is available at supply points, what is needed at destinations, how much transportation capacity there is, and what the routes are like. In this study, we investigate a two-stage multi-item fixed charge four-dimensional transportation problem using the concept of big data theory under the two-fold uncertainties. Here, the model’s parameters such as unit transportation costs, availabilities of items at the suppliers, fixed charges, capacities of conveyances, and demands of the items at the retailers are considered type-2 zigzag uncertain variables. Using big data theory and based on uncertain programming theory, two novel uncertain models are developed such as chance-constrained programming and expected value programming model. These two uncertain models transformed into the deterministic form via uncertainty inverse distribution theory. A critical value based reduction method with three categories (i.e., expected value, pessimistic value, and optimistic value) is applied to reduce the type-2 zigzag uncertain variable to the type-1 zigzag uncertain variable. The genetic algorithm and particle swarm optimization techniques have been proposed to find the optimal solution for the two deterministic models. The efficiency of our proposed approach is demonstrated with a real-life numerical example.

Combining algorithm techniques with mechanical and acoustic profiles for the prediction of apples sensory attributes

The research work shows the potentiality of advanced linear and nonlinear learning algorithm techniques in the prediction of apples texture sensory attributes as “hardness”, “crunchiness”, “flouriness”, “fibrousness”, and “graininess”. Starting from the information contained in the entire mechanical and acoustic curves acquired during samples compression test, the prediction performances of five different statistical tools as Partial Least Squares regression (PLS), Multilayer Perceptron (MLP), Support Vector Regression (SVR) and Gaussian Process Regression (GPR) are shown and discussed.All Predictive models validations evidence best accuracies for texture sensory attributes “hardness” and “crunchiness” and in general for GPR learning algorithm. By combining mechanical and acoustic profiles, 5-fold cross validations produce values of coefficient of determination R2 up to 0.885 (GPR) and 0.840 (GPR), respectively for “hardness” and “crunchiness”. These results, comparable to those obtained by considering a large number of mechanical and acoustic parameters extracted from acquired profiles as predictive factors, evidence a new and reliable way for the prediction of texture sensory attributes of apples. The proposed approach can overcome the necessity to define, in advance, number and type of features to be calculated from instrumental texture profiles and can be easily implemented in an automatic process.

Predicting peptide properties from mass spectrometry data using deep attention-based multitask network and uncertainty quantification.

Database search algorithms reduce the number of potential candidate peptides against which scoring needs to be performed using a single (i.e. mass) property for filtering. While useful, filtering based on one property may lead to exclusion of non-abundant spectra and uncharacterized peptides - potentially exacerbating the streetlight effect. Here we present ProteoRift, a novel attention and multitask deep-network, which can predict multiple peptide properties (length, missed cleavages, and modification status) directly from spectra. We demonstrate that ProteoRift can predict these properties with up to 97% accuracy resulting in search-space reduction by more than 90%. As a result, our end-to-end pipeline is shown to exhibit 8x to 12x speedups with peptide deduction accuracy comparable to algorithmic techniques. We also formulate two uncertainty estimation metrics, which can distinguish between in-distribution and out-of-distribution data (ROC-AUC 0.99) and predict high-scoring mass spectra against correct peptide (ROC-AUC 0.94). These models and metrics are integrated in an end-to-end ML pipeline available at https://github.com/pcdslab/ProteoRift.

Retraction Note: effective heart disease prediction using improved particle swarm optimization algorithm and ensemble classification technique

Retraction Note: effective heart disease prediction using improved particle swarm optimization algorithm and ensemble classification technique

Enhancing corporate bankruptcy prediction via a hybrid genetic algorithm and domain adaptation learning architecture

In the contemporary business landscape, accurately evaluating a company’s financial health is essential for stakeholders to mitigate risks and avert bankruptcy. This study presents an innovative approach to improving business bankruptcy prediction through the hybrid integration of Domain Adaptation Learning (DAL) and Genetic Algorithm (GA) techniques. The hybrid model harnesses DAL to address distributional changes in real-world scenarios and utilises GA’s proficiency in feature selection. Six machine learning models are rigorously evaluated against the proposed hybrid model: Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR), Gradient Boosting (GB), k-Nearest Neighbours (k-NN), and Stacking Ensemble (SE). Our hybrid model performs well on imbalanced target datasets using the Area Under the Precision–Recall Curve metric: 0.93 (RF), 0.93 (SVM), 0.89 (LR), 0.91 (GB), 0.88 (k-NN), and 0.92 (SE). These findings highlight the model’s ability to overcome the limitations of traditional approaches, offering a more reliable predictive framework for stakeholders to make informed decisions and proactively manage financial stability. Future research directions may explore the applicability of this hybrid model across different industries and the integration of additional techniques to further enhance its performance.

Solving the t -wise Coverage Maximum Problem via Effective and Efficient Local Search-based Sampling

To meet the increasing demand for customized software, highly configurable systems become essential in practice. Such systems offer many options to configure, and ensuring the reliability of these systems is critical. A widely-used evaluation metric for testing these systems is \(t\) -wise coverage, where \(t\) represents testing strength, and its value typically ranges from 2 to 6. It is crucial to design effective and efficient methods for generating test suites that achieve high \(t\) -wise coverage. However, current state-of-the-art methods need to generate large test suites for achieving high \(t\) -wise coverage. In this work, we propose a novel method called LS-Sampling-Plus that can efficiently generate test suites with high \(t\) -wise coverage for \(2\leq t\leq 6\) while being smaller in size compared to existing state-of-the-art methods. LS-Sampling-Plus incorporates many core algorithmic techniques, including two novel scoring functions, a dynamic mechanism for updating sampling probabilities, and a validity-guaranteed systematic search method. Our experiments on various practical benchmarks show that LS-Sampling-Plus can achieve higher \(t\) -wise coverage than current state-of-the-art methods, through building a test suite of the same size. Moreover, our evaluations indicate the effectiveness of all core algorithmic techniques of LS-Sampling-Plus . Further, LS-Sampling-Plus exhibits better scalability and fault detection capability than existing state-of-the-art methods.

Advances in Machine Learning for Wearable Sensors.

Recent years have witnessed tremendous advances in machine learning techniques for wearable sensors and bioelectronics, which play an essential role in real-time sensing data analysis to provide clinical-grade information for personalized healthcare. To this end, supervised learning and unsupervised learning algorithms have emerged as powerful tools, allowing for the detection of complex patterns and relationships in large, high-dimensional data sets. In this Review, we aim to delineate the latest advancements in machine learning for wearable sensors, focusing on key developments in algorithmic techniques, applications, and the challenges intrinsic to this evolving landscape. Additionally, we highlight the potential of machine-learning approaches to enhance the accuracy, reliability, and interpretability of wearable sensor data and discuss the opportunities and limitations of this emerging field. Ultimately, our work aims to provide a roadmap for future research endeavors in this exciting and rapidly evolving area.

Design of electrostatic lenses through genetic algorithm and particle swarm optimisation methods integrated with differential algebra

Genetic algorithm (GA) and particle swarm optimisation (PSO) techniques have been integrated with the differential algebra (DA) method in charged particle optics to optimise an Einzel lens. The DA method is a robust and efficient tool for the calculation of aberration coefficients of electrostatic lenses, which makes use of nonstandard analysis for ray tracing a particle as it is subjected to the field generated by a lens. In this study, initial populations of lenses with random geometrical configurations are generated. These initial populations are then subjected to GA and PSO algorithms to alter the geometry of each lens for a set number of iterations. The lens performance is evaluated by calculating the spot size using the aberrations coefficients up to third-order generated by the DA method. Moreover, a focusing column comprising two lenses and a Wien filter was optimised using GA method.

Real time patient scheduling orchestration for improving key performance indicators in a hospital emergency department

Healthcare systems worldwide are increasingly subject to in-depth analysis. Problems in healthcare systems are of concern to the general public. For example, overcrowding in emergency departments creates several issues including longer waiting times, more frequent medical errors, a longer length of stay and worsened performance indicators. Overcrowding situations reduce the availability of staff and material resources, and therefore deteriorate the quality of care. The main cause of the overcrowding in emergency departments is the permanent interferences between the scheduled patients, unscheduled patients and urgent and unscheduled patients arriving at the emergency department. The objective of the present study is to develop an innovative decision support system that minimizes these interferences, while taking into account the perturbations that can occur throughout the day. The research’s ultimate goal is to improve the performance indicators via two processes: the first is a memetic algorithm based on a four dimensional hypercube genetic algorithm and local search techniques, and the second is based on a multi-agent system which dynamically orchestrates the patient pathway (given by the scheduling algorithm). In order to test and validate our approach, experiments are designed with real data from the adult emergency department at Lille University Medical Center. Simulations showed that with our approach we were able to reduce the waiting time of patients by 28.12%.

Cost-sensitive stacked long short-term memory with an evolutionary framework for minority class detection

‘Minority attack detection’ is a matter of great concern while designing a secure network and safeguarding it against cyber criminals who attempt to breach its defenses, intrude into its systems, and gain unauthorized access to sensitive information. An adequate intrusion detection system is demanded to counter such threats involving class imbalance and high dimensionality in network traffic. In this context, an artificial intelligence-based multiclass framework MCGAL is presented, which leverages the evolutionary technique of genetic algorithm to achieve the finest feature selection and stacked long short-term memory (LSTM) for traffic classification. The proposed approach utilizes cost-sensitive LSTM by assigning greater significance to minority or rarely occurring classes, thereby addressing the challenge of misclassification in the presence of imbalanced data in a real web attack subset of the CSE-CIC-IDS2018 dataset. A comprehensive performance analysis is performed to evaluate our proposed scheme concerning various class metrics using weighted and macro averages, which reveals a classification accuracy of 100 %. An achieved weighted average of 1.00 is then compared with baseline classifiers like decision trees, AdaBoost, and support vector machines utilizing both linear and radial kernels. The results of MCGAL are also assessed with recently reported techniques on the same dataset demonstrating remarkable improvements in all metrics such as precision, recall, and F-score of minority class detection. A pair-wise comparison and Kruskal-Wallis test at a 95 % significance level further illustrate the statistical significance of the proposed scheme for minority class detection.

Algorithmic optimization of quantum optical storage in solids

Quantum memory devices with high storage efficiency and bandwidth are essential elements for future quantum networks. Solid-state quantum memories can provide broadband storage, but they primarily suffer from low storage efficiency. We use passive optimization and algorithmic optimization techniques to demonstrate nearly a sixfold enhancement in quantum memory efficiency. In this regime, we demonstrate coherent and single-photon-level storage with a high signal-to-noise ratio. The optimization technique presented here can be applied to most solid-state quantum memories to significantly improve the storage efficiency without compromising the memory bandwidth. Published by the American Physical Society 2024

An Innovative Approach for Mission Sharing and Route Planning of Swarm Unmanned Aerial Vehicles in Disaster Management

Fast and effective response in disaster situations is critical for the success of rescue operations. In this context, swarm Unmanned Aerial Vehicles (UAVs) play an important role in disaster response by rapidly scanning large areas and performing situation assessments. In this paper, we propose an innovative method for task allocation and route planning for swarm UAVs. By combining Genetic Algorithm (GA) and Ant Colony Optimization (ACO) techniques, this method aims to ensure the most efficient movement of UAVs. First, clusters are created using GA to determine the regions of the disaster area that need to be scanned. At this stage, factors such as the capacities of the UAVs, their flight times, and the breadth of their mission areas are taken into account. Each UAV is optimized to scan a specific area assigned to it. Once the clusters are formed, the routes of the UAVs within each cluster are determined by the Ant Colony Algorithm (ACA). The route planning is tested both on Google Maps and in a simulation environment. Google Maps is used to evaluate the accuracy and feasibility of route planning based on real-world conditions, while the simulation environment provides the opportunity to test the behavior of the UAVs and the effectiveness of the routes in a virtual setting. With real-time data integration, the UAVs' route planning can be updated instantly and quickly adapted to emergency situations.

POLICIAMENTO PREDITIVO E INTELIGÊNCIA ARTIFICIAL: ANÁLISE DE DESEMPENHO DO ALGORITMO DE APRENDIZADO DE MÁQUINA SUPERVISIONADO RANDOM FOREST NA PREDIÇÃO DE OCORRÊNCIAS POLICIAIS DE ROUBO NAS ZONAS DA REGIÃO METROPOLITANA DE SÃO LUÍS

Predictive policing is a concept based on the premise that it is possible to predict when and where crimes will occur again in the future by using sophisticated computer analysis based on data from previously committed crimes (UCHIDA, as cited in NORTON, 2013, pp. 32–33). The aim of this article is to analyze the spatial prediction of crimes, highlighting the importance of innovative approaches in the field of public safety management. Specifically, the article explores practical applications of using Artificial Intelligence (AI) through supervised machine learning algorithms for classification, using the emergency call records database (190) of robbery incidents in the metropolitan region of São Luís as input, and comparing results through validation techniques for the Random Forest algorithm. Through detailed analysis of these data, the potential of predictive policing is illustrated not only to anticipate criminal events but also to develop a computational tool capable of assisting and supporting strategic decision-making, significantly contributing to troop allocation management and, consequently, to the enhancement of preventive urban patrol services.