Performance Evaluation Module Research Articles

A decision support framework to improve flow management in a supply chain subject to risks

ABSTRACT This research aims at developing an approach to assess the probability of meeting customer service level, while considering various risk factors present in a supply chain (supply disruptions, uncertainties in lead times, labour shortages, transport disruptions etc.). The work is conducted in tight collaboration with a leading actor of an aeronautical industry. Our model enables a better management of supply chain flows by improving two KPIs of interest for the company that operates in a MTO environment: on-time delivery (OTD) and depth of delay (DOD), by varying the repartition of flows between possible production and transportation modes. Change in transportation mode is indeed considered as a risk mitigation lever leading to sustainable operations. We first collect input data, which includes data related to the characteristics of the system under study (flow diagram, data pertaining to parameters such as lead time, cost, capacity…) and supply chain risks mapping. Then, we develop a discrete event simulation (DES) model considering supply chain risks to determine the best flow repartition enabling to satisfy KPIs considered. A performance evaluation module enables to calculate the probability distribution of the chosen KPIs. Finally, a multi-scenario analysis is conducted by varying different parameters that have an impact on OTD, DOD and the total cost.

Developing a data-driven hydraulic excavator fuel consumption prediction system based on deep learning

With the aggravation of the global energy crisis, fuel consumption has become a key indicator for excavator manufacturers and policymakers. However, traditional experimental and theoretical approaches, which are complicated to calculate and dependent on the laboratory environment, are difficult to be applied in engineering. A data-driven prediction system consisting of data acquisition, feature decomposition, fuel consumption prediction, and performance evaluation modules, is developed to achieve excavator fuel consumption prediction during operation. The characteristic parameters of excavator energy consumption are collected through the established data acquisition module and the superfluous noise is eliminated by the feature decomposition module. A prediction model based on Informer is proposed in the fuel consumption prediction module to solve the drawback that the neural network model cannot capture key information in long series data in parallel, thus improving the prediction accuracy. Finally, the effectiveness of different prediction methods is verified by the performance prediction module.

Soil suitability classification for crop selection in precision agriculture using GBRT-based hybrid DNN surrogate models

The main reason for agricultural productivity decline is farmers' failure to choose the appropriate crop for their soil. It is important for farmers to understand which crops are suitable for different soil types based on their characteristics. Due to the vast variety of soil types worldwide, farmers often struggle to choose the most profitable crop for their land. To improve crop yields, a crop selection system has been developed using GBRT-based deep learning surrogate models. Gradient Boosted Regression Tree (GBRT) has been combined with a Bayesian optimization (BO) algorithm to determine the most optimal hyperparameters for the deep neural network. The optimized hyperparameters are then applied during the testing phase. Further, the impact of each input parameter on the individual outputs is evaluated using explainable artificial intelligence (XAI). The crop recommendation system comprises data preparation, classification, and performance evaluation modules. A classification method based on confusion matrices and performance matrices, as well as feature analysis using density plots and correlation plots, follows. The crop selection system categorizes the experimental dataset into 12 classes, with three for each of the four crops. The dataset includes soil-specific physical and chemical features such as sand, silt, clay, pH, electric conductivity (EC), soil organic carbon (SOC), nitrogen (N), phosphorus (P), and potassium (K). The developed surrogate model is highly accurate, precise, and reliable, with an F1-Score of 1.0 for all classes in the dataset, indicating exact accuracy and recall. The DNN-based classification model achieves an average classification accuracy of 1.00.

A design model for spiral wound heat exchangers which accounts for property variation, longitudinal heat conduction, and heat-in-leak

• A combined analytical-numerical design model for cryogenic SWHE is developed. • Analytical sizing module finds the optimum configuration of SWHE. • The effects of property variation, LHC, and heat-in-leak are investigated. • LHC impact is negligible compared to property variation and heat-in-leak. • A sensitivity analysis on the input constraint is performed. Spiral Wound Heat Exchangers (SWHEs) can be a good and reliable choice for serving as the main heat exchanger in the cryogenic gas liquefaction cycles using throttling process such as the Linde-Hampson cycle. In this application, a high pressure hot gas stream has to be cooled down via transferring heat to a low pressure cold gas in a high-effectiveness heat exchanger. Present research has been organized to develop a design model which is able to find the optimum SWHE configuration for gas liquefaction cycles. The model has to be capable of considering the important physical phenomena in the cryogenic temperature ranges, including variation of fluid properties with temperature, longitudinal heat conduction (LHC) through separating walls, and heat-in-leak. Therefore, a combined analytical-numerical design model has been developed in the present study. The design model is essentially composed of two stand-alone modules, i.e. an analytical sizing module and a numerical performance evaluation module. To develop the design model, first, the geometrical characteristics of SWHE are studied and primary geometrical parameters are recognized. Then, the analytical sizing module is developed which is able to determine the optimum values of primary geometrical parameters of SWHE minimizing the heat transfer surface area based on the input design requirements. Afterwards, a 1D finite difference numerical module is presented in which important physical phenomena can be considered in the evaluation of the thermo-hydraulic performance of all types of counter flow or parallel flow heat exchangers as well as SWHEs. Finally, the two modules are combined to construct a design model. Two examples in which the low pressure superheated vapor helium is intended to cool down the high pressure supercritical helium flowing inside the tubes are also provided to demonstrate the applicability of the proposed combined model, and also, to elucidate its sensitivity to the input constraints. It was concluded that while variations of fluid properties and the external heat fluxes due to the radiation and convection have significant influence on the performance of cryogenic SWHE, the LHC is of minor importance and can be neglected. Moreover, decreasing the shell-side allowable pressure drop from 10 kPa to 2 kPa, causes the heat exchanger length and its outside diameter to increase by 79% and 48%, respectively.

Developing a wind power forecasting system based on deep learning with attention mechanism

Large-scale wind power grid integration is challenging, requiring accurate and stable wind power forecasting to reduce operational risk and improve the scheduling efficiency of the grid. Previous studies have emphasized data preprocessing and parameter optimization. Studies on feature mining for the input layer, particularly the hidden layer, are limited, hindering further forecasting accuracy and stability improvements. To address this gap, a novel wind power forecasting system consisting of feature decomposition, self-attention, forecasting, optimization, and performance evaluation modules, is developed in this study. The feature decomposition module is used to remove superfluous noise components inherent in wind power data. A dual-stage self-attention mechanism is proposed in the self-attention module to determine the importance of driving features in the input and hidden layers, rather than focusing on all f/eatures equally. A deep learning model is used with the optimization module, built into the forecasting module. A performance evaluation module is constructed to provide a synthetical evaluation of the forecasting system. Numerical experiments are conducted to validate the effectiveness of the system and demonstrate its superiority.

Digital Human Performance Evaluation in the Public and Private Sectors

Increased controlling functions are a natural part of the day-to-day activities of companies operating in market conditions. Its successful functioning determines the market value of the company. In addition to measuring organizational performance, it also has a vital role in monitoring and evaluating individual performance on an ongoing basis, thus providing continuous feedback to employees and managers. Accordingly, the IT sector and modern IT solutions are taking a significant part in the operation of companies. With the development of these solutions, Industry 4.0 is already taking companies into the world of modern ICT technologies and is appearing at all levels of companies. Companies developing ERP systems are increasingly focusing on the dissemination of performance evaluation modules as part of controlling. Not only ERP systems but also serious HRM support solutions have emerged, and controlling has been complemented by measuring the performance not only of the whole organization but also of individual employees. Today, various publications discuss the fact that the cards have begun to be dealt with again in markets where companies must meet a myriad of conditions to stay afloat. We are not talking here about their ability to develop but merely about their efforts to maintain their market position. This is the environment in which controlling, which now covers a much more comprehensive range of areas, including human resources, is working. This process of controlling has extended from large companies to public interest entities, as they must operate effectively in the same environment as other companies with a similar profile but a different organizational structure, typically private. Not to mention the fact that the labor market is the same, where recruitment is not enough, but retention is just as necessary.

Design and Research of Physical Education Platform Based on Artificial Intelligence

With the continuous development of information technology, conventional physical education teaching methods are no longer applicable. In order to ensure the objectivity of college physical education evaluation, this paper designs a set of college physical education management information system based on artificial intelligence technology. The weighting algorithm in the student performance evaluation module and teacher performance evaluation module in the system adopts the intelligent algorithm based on FNN neural network. Experimental verification shows that the intelligent algorithm based on the FNN neural network can effectively predict the students’ score in the national college physical education examination, which can provide a more objective basis for teacher performance evaluation.

A Generic AI-Based Technique for Assessing Student Performance in Conducting Online Virtual and Remote Controlled Laboratories

Due to the COVID-19 pandemic and the development of educational technology, e-learning has become essential in the educational process. However, the adoption of e-learning in sectors such as engineering, science, and technology faces a particular challenge as it needs a special Laboratory Learning Management System (LLMS) capable of supporting online lab activities through virtual and controlled remote labs. One of the most challenging tasks in designing such LLMS is how to assess a student’s performance while an experiment is being conducted and how stuttering students can be automatically detected while experimenting and providing the appropriate assistance. For this, a generic technique based on Artificial Intelligence (AI) is proposed in this paper for assessing student performance while conducting online labs and implemented as a performance evaluation module in the LLMS. The performance evaluation module is designed to automatically detect the student performance during the experiment run time and triggers the LLMS virtual assistant service to provide struggling students with the appropriate help when they need it. Also, the proposed performance assessment technique is used during the lab exam sessions to support the automatic grading process conducted by the LLMS Auto-Grading Module. The proposed performance evaluation technique has been developed based on analyzing the student’s mouse dynamics to work generally with any type of simulation or control software used by virtual or remote controlled laboratories; without the need for special interfacing. The study has been applied to a novel dataset built by the course instructors and students simulating a circuit on TinkerCad. Using mouse dynamics fetching, the system extracts features and evaluates them to determine if the student has built the experiment steps in the right way or not. A comparison study has been developed between different Machine Learning (ML) models and a number of performance metrics are calculated. The study confirmed that Artificial Neural Network (ANN) and Support Vector Machine (SVM) are the best models to be used for automatically evaluating student performance while conducting the online labs with a precision reaching up to 91%.

Complex simulation model of functioning mine telecommunication system using Power Line Communication technology

This paper considers a modern development of telecommunication systems as a part of electrical complexes of underground facilities, namely, application of PLC technologies for complexing electrical systems. A description is provided of the main tool of experimental studies of such systems, a simulation model of operation, its structure, development sequence and main elements, as well as an experimental validation of the model.The proposed model will allow solving a wide range of problems in the process of studying telecommunications systems and power supply systems for underground structures. Model development included the formulation of complex research tasks, the creation of the conceptual model, the formation of a set of requirements for the modeling algorithm, the development of a mathematical model, creating a simulation program in C++ with the use of JBuilder, the company Embarcadero version 10.3, as well as the verification of the simulation model. Based on the considered structure of the PLC network, it is proposed to include an information generation module, a connection module, a transmission line module, a modulation, encoding and decoding module, an information processing and noise reduction module, a subscriber module and a performance evaluation module in the model of integration of power supply and telecommunications systems for underground structures. To solve the problem verify the model was developed methods of research the effectiveness of various algorithms for transmission power supply networks underground structures, allowing an informed choice of data transfer methods and rational selection of the non-necessity to implement the methods selected equipment and conducted a series of experimental studies on real industrial underground facilities.

Neumann-Michell theory-based multi-objective optimization of hull form for a naval surface combatant

A numerical multi-objective optimization procedure is proposed here to describe the development and application of a practical hydrodynamic optimization tool, OPTShip-SJTU. Three components including hull form modification module, hydrodynamic performance evaluation module and optimization module consist of this tool. The free-form deformation (FFD) method and shifting method are utilized as parametric hull surface modification techniques to generate a series of realistic hull forms subjected to geometric constraints, and the Neumann-Michell (NM) theory is implemented to predict the wave drag. Moreover, NSGA-II, a muti-objective genetic algorithm, is adopted to produce pareto-optimal front, and kriging model is used for predicting the total resistance during the optimization process to reduce the computational cost. Additionally, the analysis of variance (ANOVA) method is introduced to represent the influence of each design variable on the objective functions. In present work, a surface combatant DTMB Model 5415 is used as the initial design, and optimal solutions with obvious drag reductions at specific speeds are obtained. Eventually, three of optimal hulls are analyzed by NM theory and a RANS-based CFD solver naoe-FOAM-SJTU respectively. Numerical results confirm the availability and reliability of this multi-objective optimization tool.

A recommendation system for meta-modeling: A meta-learning based approach

Various meta-modeling techniques have been developed to replace computationally expensive simulation models. The performance of these meta-modeling techniques on different models is varied which makes existing model selection/recommendation approaches (e.g., trial-and-error, ensemble) problematic. To address these research gaps, we propose a general meta-modeling recommendation system using meta-learning which can automate the meta-modeling recommendation process by intelligently adapting the learning bias to problem characterizations. The proposed intelligent recommendation system includes four modules: (1) problem module, (2) meta-feature module which includes a comprehensive set of meta-features to characterize the geometrical properties of problems, (3) meta-learner module which compares the performance of instance-based and model-based learning approaches for optimal framework design, and (4) performance evaluation module which introduces two criteria, Spearman's ranking correlation coefficient and hit ratio, to evaluate the system on the accuracy of model ranking prediction and the precision of the best model recommendation, respectively. To further improve the performance of meta-learning for meta-modeling recommendation, different types of feature reduction techniques, including singular value decomposition, stepwise regression and ReliefF, are studied. Experiments show that our proposed framework is able to achieve 94% correlation on model rankings, and a 91% hit ratio on best model recommendation. Moreover, the computational cost of meta-modeling recommendation is significantly reduced from an order of minutes to seconds compared to traditional trial-and-error and ensemble process. The proposed framework can significantly advance the research in meta-modeling recommendation, and can be applied for data-driven system modeling.

Employee Performance Appraisal System Using Fuzzy Logic

Evaluation of employee performance is an important element in enhancing the quality of the work and improves employees' motivation to perform well. It also presents a basis for upgrading and enhancing of an organization. Periodical employees' performance evaluation in an organization assists management to recognize its strengths and weaknesses. This paper presents a design and implementation of a performance appraisal system using the fuzzy logic. In addition to the normal process of performance evaluation modules, the system contains step by step inference engine processes. These processes demonstrate several calculation details in relations composition and aggregation methods such as min operator, algebraic product, sup-min and sup-product. The system has foundation to add-on analysis module to analyze and report the final result using various similarity measures. MS Access database was used to maintain the data, build the inference logic and develop all setting user interfaces.

Lifecycle Health Assessment Model for Sustainable Healthy Buildings

A system to analyze, assess and manage the health performance of resources and spaces throughout the project lifecycle shall be established to ensure sustainable healthy buildings. Decisions made in the planning, design, construction, and operation and management (O&M) phases must help sustain the health performance of buildings at the level specified by clients or the relevant laws. For this reason, it is necessary to develop a model to ensure the consistent management of performance, as such performance varies according to the decisions made by project participants in each phase. The purpose of this research is to develop a Lifecycle Health Assessment Model (LHA) for sustainable healthy buildings. The developed model consists of four different modules: the Health-friendly Resources Database (HRDB) module, which provides health performance data regarding resources and spatial elements; the Lifecycle Health-performance Tree (LHT) module, which analyzes the hierarchy of spatial and health impact factors; the Health Performance Evaluation (HPE) Module; and the Lifecycle Health Management Module, which analyzes and manages changes in health performances throughout the lifecycle. The model helps ensure sustainable health performances of buildings.

BIM기반 건축물 설계 과정에서 실시간 에너지 성능 분석을 위한 기술 개발에 관한 연구 - 열관류율 분석을 중심으로

This study intended to introduce the method of designing an eco-friendly building based on BIM(Building Information Modeling) and BIM-based application. The proposed application aimed to generate the environmental performance of the designed alternative automatically in real-time manner in the process of architectural design. We focused on the feasibility of BIM-based eco-friendly design process and the applicability of the developed application for the architectural design practice. In this manner, in the end of paper, we proposed the so-call EcoBIM which is the performance evaluation module for the designed alternative using BIM in the real-time manner and the new design process with it. EcoBIM generate the coefficient of overall heat transmission of wall, roof and slab of the designed alternative with their physical characteristics such as thickness, thermal resistance and so on.

The simulation-based performance measurement in an evaluation module for Faborg-Sim simulation software

It is possible to evaluate production system performance measurement and organizational alternative structures with dynamic simulation methods for efficiency of cost and productivity. The parameters which are vary for different organizational structures and scope of production systems are examined in a mutual simulation-based performance measurement system. In general, the simulation-based performance measurement criteria are lead time, lead time deviation, utilization rate, and work-in-process as goal achievements of logistics and delivery rate in performance evaluation module. In this study, an evaluation module is developed and integrated to system simulation results as a part of the research project of “Development of Simulation Software for Facility Organizing, Production System Structuring, and Performance Measuring (Faborg-Sim)” at Suleyman Demirel University Industrial Engineering Department which is supported by The Scientific and Technological Research Council of Turkey (TUBITAK).

Self-adaptive robot training of stroke survivors for continuous tracking movements

BackgroundAlthough robot therapy is progressively becoming an accepted method of treatment for stroke survivors, few studies have investigated how to adapt the robot/subject interaction forces in an automatic way. The paper is a feasibility study of a novel self-adaptive robot controller to be applied with continuous tracking movements.MethodsThe haptic robot Braccio di Ferro is used, in relation with a tracking task. The proposed control architecture is based on three main modules: 1) a force field generator that combines a non linear attractive field and a viscous field; 2) a performance evaluation module; 3) an adaptive controller. The first module operates in a continuous time fashion; the other two modules operate in an intermittent way and are triggered at the end of the current block of trials. The controller progressively decreases the gain of the force field, within a session, but operates in a non monotonic way between sessions: it remembers the minimum gain achieved in a session and propagates it to the next one, which starts with a block whose gain is greater than the previous one. The initial assistance gains are chosen according to a minimal assistance strategy. The scheme can also be applied with closed eyes in order to enhance the role of proprioception in learning and control.ResultsThe preliminary results with a small group of patients (10 chronic hemiplegic subjects) show that the scheme is robust and promotes a statistically significant improvement in performance indicators as well as a recalibration of the visual and proprioceptive channels. The results confirm that the minimally assistive, self-adaptive strategy is well tolerated by severely impaired subjects and is beneficial also for less severe patients.ConclusionsThe experiments provide detailed information about the stability and robustness of the adaptive controller of robot assistance that could be quite relevant for the design of future large scale controlled clinical trials. Moreover, the study suggests that including continuous movement in the repertoire of training is acceptable also by rather severely impaired subjects and confirms the stabilizing effect of alternating vision/no vision trials already found in previous studies.

A single-trial analytic framework for EEG analysis and its application to target detection and classification

Modern neuroimaging technologies afford a non-invasive view into the functions of the human brain with great spatial (fMRI) and temporal resolution (EEG). However, common signal analytic methods require averaging over many trials, which limits the potential for practical application of these technologies. In this paper we advance a novel single-trial analysis method for EEG and demonstrate this approach with a target detection task. The method utilizes a framework consisting of multiple processing modules that can be applied in whole or in part, including noise mitigation, source–space transformation, discriminant analysis, and performance evaluation. The framework introduces an enhanced noise mitigation technology based on Directed Components Analysis (DCA) that improves upon existing spatial filtering techniques. Source–space transformation, utilizing a finite difference model (FDM) of the human head, estimates activity measures of the cortical sources involved in task performance. Such a source–space discrimination provides measurement invariance between training and testing sessions and holds the promise of providing a degree of classification not possible with scalp-recorded EEG. The framework's discrimination modules interface with performance evaluation modules to generate classification performance statistics. When applied to EEG acquired during performance of a target detection task, this method demonstrated that neural signatures of target recognition correctly classified up to 87% of targets in a rapid serial visual presentation (RSVP) of target/non-target images. On average, the single-trial classification method resulted in greater than 60% improvement over behavioral performance for target detection.

Infrared target tracking with kernel-based performance metric and eigenvalue-based similarity measure

An infrared target tracking framework is presented that consists of three main parts: mean shift tracking, its tracking performance evaluation, and position correction. The mean shift tracking algorithm, which is a widely used kernel-based method, has been developed for the initial tracking for its efficiency and effectiveness. A performance evaluation module is applied for the online evaluation of its tracking performance with a kernel- based metric to unify the tracking and performance metric within a kernel-based tracking framework. Then the tracking performance evaluation result is input into a controller in which a decision is made whether to trigger a position correction process. The position correction module employs a matching method with a new eigenvalue-based similarity measure computed from a local complexity degree weighted covariance matrix. Experimental results on real-life infrared image sequences are presented to demonstrate the efficacy of the proposed method.

Modeling, scheduling, and performance evaluation for wafer fabrication: a queueing colored Petri-net and GA-based approach

In this paper, we propose a modeling tool named Queueing Colored Petri nets (QCPN) for performance evaluation and scheduling for wafer fabrication. The main idea of this tool is to combine colored timed Petri nets with the queueing systems, and it aims to make simulation over the model more efficient. Due to the wide acceptance of priority rules in the wafer manufacturing industry, we also proposed a mechanism to realize priority rules in the QCPN models. Since it is known that no single rule can dominate in any circumstance, we proposed a genetic algorithm (GA) to search for the optimal combination of a number of priority rules based on the status and performance measures of the fab. Our approach can be considered as taking the advantage of the lot execution sequence generated by priority rules to guide the search. This approach can reduce the solution space and help us find the good solution more quickly. In addition, the QCPN-based GA scheduler can greatly reduce the computation time so that this GA scheduler can meet the need for a rapidly changing environment. Note to Practitioners-Performance evaluation and scheduling are two functions required by fab managers and engineers. This paper proposed a tool which consists of a simulator and a scheduler. By connecting to the Manufacturing Execution System (MES) and providing the scheduling rules, we can see how the fab runs virtually with the simulator. General information such as throughput and average cycle time and specific information like lot activity history can be obtained. This can be used for decision making, delivery prediction, bottleneck seeking, and testing of newly developed heurisitcs. The implementation cost is only on data communication between the MES and the simulator and the incorporation of rule modules. The scheduler, which takes the simulator as the performance evaluation module, can generate the suitable scheduling rule based on the current fab status, preference of performance criteria, and rule candidates. There is almost no extra cost after the simulator is connected to the MES. The scheduler can be easily made faster by common parallelization techniques.

Parallel Genetic Algorithms for Optimizing Resource Utilization in Large-Scale Construction Projects

This paper presents the development of a parallel multiobjective genetic algorithm framework to enable an efficient and effective optimization of resource utilization in large-scale construction projects. The framework incorporates a multiobjective optimization module, a global parallel genetic algorithm module, a coarse-grained parallel genetic algorithm module, and a performance evaluation module. The framework is implemented on a cluster of 50 parallel processors and its performance was evaluated using 183 experiments that tested various combinations of construction project sizes, numbers of parallel processors and genetic algorithm setups. The results of these experiments illustrate the new and unique capabilities of the developed parallel genetic algorithm framework in: (1) Enabling an efficient and effective optimization of large-scale construction projects; (2) achieving significant computational time savings by distributing the genetic algorithm computations over a cluster of parallel processors; and (3) requiring a limited and feasible number of parallel processors/computers that can be readily available in construction engineering and management offices.