Search results

This paper aims to evaluate the performance of the Mashhad No. 5 wastewater treatment plant (WWTP) using a combination of data mining (regression) algorithms and artificial neural networks.

In this research, the performance of WWTP located in Mashhad, Iran, has been evaluated using two data mining models, neural network and regression model.

The proposed model has the potential of implementing in other WWTPs in Iran or other countries.

The authors would also like to thank Mashhad No.5 WWTP for data access.

The purpose of this paper is to design a simple and accurate a-posteriori Lagrangian-based error estimator is developed for the class of backward differentiation formula (BDF) algorithms with variable time step size, and the adaptive time-stepping in BDF algorithms is demonstrated for efficient time-dependent simulations in fluid flow and heat transfer.

The Lagrange interpolation polynomial is used to predict the time derivative, and then the accurate primary result is obtained by the Gauss integral, which is applied to evaluate the local error. Not only the generalized formula of the proposed error estimator is presented but also the specific expression for the widely applied BDF1/2/3 is illustrated. Two essential executable MATLAB functions to implement the proposed error estimator are appended for practical applications. Then, the adaptive time-stepping is demonstrated based on the newly proposed error estimator for BDF algorithms.

The validation tests show that the newly proposed error estimator is accurate such that the effectivity index is always close to unity for both linear and nonlinear problems, and it avoids under/overestimation of the exact local error. The applications for fluid dynamics and coupled fluid flow and heat transfer problems depict the advantage of adaptive time-stepping based on the proposed error estimator for time-dependent simulations.

In contrast to existing error estimators for BDF algorithms, the present work is more accurate for the local error estimation, and it can be readily extended to practical applications in engineering with a few changes to existing codes, contributing to efficient time-dependent simulations in fluid flow and heat transfer.

This study develops a model and algorithm to solve the decentralized resource-constrained multi-project scheduling problem (DRCMPSP) and provides a suitable priority rule (PR) for coordinating global resource conflicts among multiple projects.

This study addresses the DRCMPSP, which respects the information privacy requirements of project agents; that is, there is no single manager centrally in charge of generating multi-project scheduling. Accordingly, a three-stage model was proposed for the decentralized management of multiple projects. To solve this model, a three-stage solution approach with a repeated negotiation mechanism was proposed.

The experimental results obtained using the Multi-Project Scheduling Problem LIBrary confirm that our approach outperforms existing methods, regardless of the average utilization factor (AUF). Comparative analysis revealed that delaying activities in the lower project makespan produces a lower average project delay. Furthermore, the new PR LMS performed better in problem subsets with AUF < 1 and large-scale subsets with AUF > 1.

A solution approach with a repeated-negotiation mechanism suitable for the DRCMPSP and a new PR for coordinating global resource allocation are proposed.

The purpose of the study is distributed generation planning in a radial delivery framework to identify an appropriate location with a suitable rating of DG units energized by renewable energy resources to scale back the power loss and to recover the voltage levels. Though several algorithms have already been proposed through the target of power loss reduction and voltage stability enhancement, further optimization of the objectives is improved by using a combination of heuristic algorithms like DE and particle swarm optimization (PSO).

The identification of the candidate buses for the location of DG units and optimal rating of DG units is found by a combined differential evolution (DE) and PSO algorithm. In the combined strategy of DE and PSO, the key merits of both algorithms are combined. The DE algorithm prevents the individuals from getting trapped into the local optimum, thereby providing efficient global optimization. At the same time, PSO provides a fast convergence rate by providing the best particle among the entire iteration to obtain the best fitness value.

The proposed DE-PSO takes advantage of the global optimization of DE and the convergence rate of PSO. The different case studies of multiple DG types are carried out for the suggested procedure for the 33- and 69-bus radial delivery frameworks and a real 16-bus distribution substation in Tamil Nadu to show the effectiveness of the proposed methodology and distribution system performance. From the obtained results, there is a substantial decrease in the power loss and an improvement of voltage levels across all the buses of the system, thereby maintaining the distribution system within the framework of system operation and safety constraints.

A comparison of an equivalent system with the DE, PSO algorithm when used separately and other algorithms available in literature shows that the proposed method results in an improved performance in terms of the convergence rate and objective function values. Finally, an economic benefit analysis is performed if a photo-voltaic based DG unit is allocated in the considered test systems.

Five-level rectifiers have received widespread attention because of their excellent performance in high-voltage and high-power applications. Taking a five-level rectifier with only four-IGBT for this study, a sliding mode predictive control (SMPC) algorithm is proposed to solve the problem of poor dynamic performance and poor anti-disturbance ability under the traditional model predictive control with the PI outer loop.

First, mathematical models under the two-phase stationary coordinate system and two-phase synchronous rotating coordinate system are established. Then, the design of the outer-loop sliding mode controller is completed by establishing the sliding mode surface and design approach rate. The design of the inner-loop model predictive controller was completed by discretizing the mathematical model equations. The modulation part uses a space vector modulation technique to generate the PWM wave.

The sliding mode predictive control strategy is compared with the control strategy with a PI outer loop and a model predictive inner loop. The proposed control strategy has a faster dynamic response and stronger anti-interference ability.

For the five-level rectifier, the advantages of fast dynamic influence and parameter insensitivity of sliding mode control are used in the voltage outer loop to replace the traditional PI control, and which is integrated with the model predictive control used in the current inner loop to form a novel control strategy with a faster dynamic response and stronger immunity to disturbances. This novel strategy is called sliding mode predictive control (SMC).

The purpose of this paper is to perform a comparative analysis of the delay associated in running two real-time machine learning-based applications, namely, a video quality assessment (VQA) and a phishing detection application by using the edge, fog and cloud computing paradigms.

The VQA algorithm was developed using Android Studio and run on a mobile phone for the edge paradigm. For the fog paradigm, it was hosted on a Java server and for the cloud paradigm on the IBM and Firebase clouds. The phishing detection algorithm was embedded into a browser extension for the edge paradigm. For the fog paradigm, it was hosted on a Node.js server and for the cloud paradigm on Firebase.

For the VQA algorithm, the edge paradigm had the highest response time while the cloud paradigm had the lowest, as the algorithm was computationally intensive. For the phishing detection algorithm, the edge paradigm had the lowest response time, and the cloud paradigm had the highest, as the algorithm had a low computational complexity. Since the determining factor for the response time was the latency, the edge paradigm provided the smallest delay as all processing were local.

The main limitation of this work is that the experiments were performed on a small scale due to time and budget constraints.

A detailed analysis with real applications has been provided to show how the complexity of an application can determine the best computing paradigm on which it can be deployed.

Assembly lines are widely employed in manufacturing processes to produce final products in a flow efficiently. The simple assembly line balancing problem is a basic version of the general problem and has still attracted the attention of researchers. The type-I simple assembly line balancing problems (SALBP-I) aim to minimise the number of workstations on an assembly line by keeping the cycle time constant.

This paper focuses on solving multi-objective SALBP-I problems by utilising an artificial bee colony based-hyper heuristic (ABC-HH) algorithm. The algorithm optimises the efficiency and idleness percentage of the assembly line and concurrently minimises the number of workstations. The proposed ABC-HH algorithm is improved by adding new modifications to each phase of the artificial bee colony framework. Parameter control and calibration are also achieved using the irace method. The proposed model has undergone testing on benchmark problems, and the results obtained have been compared with state-of-the-art algorithms.

The experimental results of the computational study on the benchmark dataset unequivocally establish the superior performance of the ABC-HH algorithm across 61 problem instances, outperforming the state-of-the-art approach.

This research proposes the ABC-HH algorithm with local search to solve the SALBP-I problems more efficiently.

Climate change is a problem that concerns all of us. Despite the information produced by organizations such as the Expert Team on Climate Change Detection and Indices and the United Nations, only a few cities have been planned taking into account the climate changes indices. This paper aims to study climatic variations, how climate conditions might change in the future and how these changes will affect the activities and living conditions in cities, specifically focusing on Mexico city.

In this approach, two distinct machine learning regression models, k-Nearest Neighbors and Support Vector Regression, were used to predict variations in climate change indices within select urban areas of Mexico city. The calculated indices are based on maximum, minimum and average temperature data collected from the National Water Commission in Mexico and the Scientific Research Center of Ensenada. The methodology involves pre-processing temperature data to create a training data set for regression algorithms. It then computes predictions for each temperature parameter and ultimately assesses the performance of these algorithms based on precision metrics scores.

This paper combines a geospatial perspective with computational tools and machine learning algorithms. Among the two regression algorithms used, it was observed that k-Nearest Neighbors produced superior results, achieving an R² score of 0.99, in contrast to Support Vector Regression, which yielded an R² score of 0.74.

The full potential of machine learning algorithms has not been fully harnessed for predicting climate indices. This paper also identifies the strengths and weaknesses of each algorithm and how the generated estimations can then be considered in the decision-making process.

Research shows that postsecondary students are largely unaware of the impact of algorithms on their everyday lives. Also, most noncomputer science students are not being taught about algorithms as part of the regular curriculum. This exploratory, qualitative study aims to explore subject-matter experts’ insights and perceptions of the knowledge components, coping behaviors and pedagogical considerations to aid faculty in teaching algorithmic literacy to postsecondary students.

Eleven semistructured interviews and one focus group were conducted with scholars and teachers of critical algorithm studies and related fields. A content analysis was manually performed on the transcripts using a mixture of deductive and inductive coding. Data analysis was aided by the coding software program Dedoose (2021) to determine frequency totals for occurrences of a code across all participants along with how many times specific participants mentioned a code. Then, findings were organized around the three themes of knowledge components, coping behaviors and pedagogy.

The findings suggested a set of 10 knowledge components that would contribute to students’ algorithmic literacy along with seven behaviors that students could use to help them better cope with algorithmic systems. A set of five teaching strategies also surfaced to help improve students’ algorithmic literacy.

This study contributes to improved pedagogy surrounding algorithmic literacy and validates existing multi-faceted conceptualizations and measurements of algorithmic literacy.

Lean manufacturing (LM) is prevalent in the manufacturing industry; thus, focusing on fast and accurate lean tool implementation is the new paradigm in manufacturing. Value stream mapping (VSM) is one of the many LM tools. It is understood that combining LM implementation with VSM tools can generate better outcomes. This paper aims to develop an expert system for optimal sequencing of VSM tools for lean implementation.

A proposed artificial neural network (ANN) model is based on the analytic network process (ANP) devised for this study. It will facilitate the selection of VSM tools in an optimal sequence.

Considering different types of wastes and their level of occurrence, organizations need a set of specific tools that will be effective in the elimination of these wastes. The developed ANP model computes a level of interrelation between wastes and VSM tools. The ANN is designed and trained by data obtained from numerous case studies, so it can predict the accurate sequence of VSM tools for any new case data set.

The design and use of the ANN model provide an integrated result of both empirical and practical cases, which is more accurate because all viable aspects are then considered. The proposed modeling approach is validated through implementation in an automobile manufacturing company. It has resulted in benefits, namely, reduction in bias, time required, effort required and complexity of the decision process. More importantly, according to all performance criteria and subcriteria, the main goal of this research was satisfied by increasing the accuracy of selecting the appropriate VSM tools and their optimal sequence for lean implementation.