Optimal Model Selection Research Articles

A robust optimization model for green supplier selection and order allocation in a closed-loop supply chain considering cap-and-trade mechanism

Due to increasing air pollution, which is a consequence of the environmental effects of production in various industries, green supply chain management (GSCM) has attracted the attention of both scholars and practitioners. Green supplier selection is an important problem in GSCM and seeks to satisfy a firm’s environmental goals as well as its economic targets. In this paper, for the first time, a green supplier selection problem considering both green and non-green evaluation criteria in a closed-loop supply chain is studied, and a cap-and-trade mechanism as a way of controlling the air pollution caused by manufacturers is proposed. To solve this particular problem, we propose a multi-objective robust optimization (RO) model. This specific model is an effective approach to handle uncertainty. A numerical example using randomly generated data, accompanied by subsequent discussion of the proposed approach, is deployed to validate the model. The results prove that the developed model for green supplier selection is able to effectively enhance the decision-making process of the experts. By illustrating the trade-off in robustness between the model and proposed solutions, as well as the effect of the deviation penalty on the closeness of results to the achieved solution, we show how firms can make optimal decisions when assigning the parameters. Furthermore, analyses show that decreasing the allowance amount (cap) and increasing the allowance prices in the cap-and-trade system escalate the firms’ costs, but lower the amount of carbon released. Finally, we show that the cap-and-trade mechanism results in a better solution in terms of the total utility of the supply chain compared to the penalty-based system for a specific range of carbon allowance.

Echo State Networks: Novel reservoir selection and hyperparameter optimization model for time series forecasting

The use of computational intelligence models for multi-step time series forecasting tasks has presented satisfactory results in such a way that they are considered models with an excellent future for this type of problem. From the point of view of computational cost, the current alternatives combined with classical models are generating hybrid models that present even better results. Within the AutoML category, the optimization of hyperparameters and the selection of network topologies has become a challenge. Reservoir Computing, which is within the area of ​​Recurrent Neural Networks (RNN), proposes a particular model called Echo State Networks. which has been tested in different applications with excellent results; however, the difficulty in specifying the hyperparameters has been the subject of continuous study given the random nature of the set of neurons called Reservoir. Based on the Separation Ratio Graph (SRG) model for performance analysis, this paper proposes a new model, called Echo State Network - Genetic Algorithm - Separation Ratio Graph (ESN-GA-SRG), which optimizes network hyperparameters and at the same time selects the best topology for the Reservoir using the SRG coefficient, to find the reservoir that offers the most suitable dynamic behavior. The performance of this new model is evaluated on forecasting two sets of time series benchmarks with different characteristics of sampling periodicity, skewness, and stationarity. The results obtained show that the ESN-GA-SRG model was superior in predicting these time series in most cases, with statistical significance, when compared to other models that have been presented for this type of problem in the literature.

Modeling polyhydroxyalkanoates production from sugarcane vinasse by mixed microbial cultures

Sugarcane vinasse is wastewater suitable for polyhydroxyalkanoates (PHA) production by mixed cultures in a three-stage process. In this work, models representing the selection of PHA-producing microorganisms in a sequencing batch reactor (SBR) submitted to a feast-famine process and uncoupled carbon/nitrogen feeding, as well as an accumulation of PHA in a fed-batch reactor from sugarcane vinasse were developed. Sensitivity analysis of the models allowed to rank the influence of parameters and calibration was carried out applying the Box-Draper method in conjunction with the Markov Chain Monte Carlo optimization method. The optimized selection model was able to describe the SBR under different operational conditions. Optimization for each condition of the accumulation showed that higher CODt/Nitrogen ratios in the SBR induced the selection of a culture with a growth response rather than storage, contributing to elucidate the impact that the CODt/Nitrogen ratio in the SBR has on PHA accumulation.

Estimation of biomass of dung beetles (Coleoptera: Scarabaeoidea) from the Russian Far East

Data on dry biomass and body length are given for 47 species of dung beetles from the southern part of the Russian Far East. The length-to-body weight relation in specimens of 47 species of dung-beetles was calculated, to enable biomass to be estimated from information about body length. Shown, the selection of optimal models of length-weight relationship of dung-beetles depends on the types of trophodynamic relationships of beetles and its size classes. When conducting ecological studies using such an indicator as dry biomass, it is necessary to determine the biomass of individual species from regional faunas, and to determine the biomass along the length of the body of beetles, it is necessary to use exclusively models built also for regional faunas.

On Cooperative Game Approaches For Optimal Portfolio Selection

Cooperative game theory is concerned with exploring schemes for allocating payoffs among rational participants in coalitions and has produced several solution designs due to the different emphasis on criteria such as stability and fairness, but this theory has not been widely applied in the field of portfolio selection. In this paper, we explore further applications of the solution concepts of cooperative games based on the model of optimal portfolio selection developed in previous studies, which is modelled in a static form of a non-cooperative zero-sum game between investors and the market and a cooperative game between investors. We propose a risk modified Shapley value based on the tradeoff between return and risk in the financial market based on the Shapley value, and the performance of this solution shows an evident improvement. We also introduce some other solution concepts of cooperative games and give an approach to construct a nucleolus-based portfolio using Maschler's scheme to compute the nucleolus, and the results demonstrate that the allocation schemes based on the cooperative game theory perform well.

Polycystic Ovary Syndrome Detection Machine Learning Model Based on Optimized Feature Selection and Explainable Artificial Intelligence

Polycystic ovary syndrome (PCOS) has been classified as a severe health problem common among women globally. Early detection and treatment of PCOS reduce the possibility of long-term complications, such as increasing the chances of developing type 2 diabetes and gestational diabetes. Therefore, effective and early PCOS diagnosis will help the healthcare systems to reduce the disease's problems and complications. Machine learning (ML) and ensemble learning have recently shown promising results in medical diagnostics. The main goal of our research is to provide model explanations to ensure efficiency, effectiveness, and trust in the developed model through local and global explanations. Feature selection methods with different types of ML models (logistic regression (LR), random forest (RF), decision tree (DT), naive Bayes (NB), support vector machine (SVM), k-nearest neighbor (KNN), xgboost, and Adaboost algorithm to get optimal feature selection and best model. Stacking ML models that combine the best base ML models with meta-learner are proposed to improve performance. Bayesian optimization is used to optimize ML models. Combining SMOTE (Synthetic Minority Oversampling Techniques) and ENN (Edited Nearest Neighbour) solves the class imbalance. The experimental results were made using a benchmark PCOS dataset with two ratios splitting 70:30 and 80:20. The result showed that the Stacking ML with REF feature selection recorded the highest accuracy at 100 compared to other models.

Optimal model selection for k-nearest neighbours ensemble via sub-bagging and sub-sampling with feature weighting

This paper proposes two novel approaches based on feature weighting and model selection for building more accurate kNN ensembles. The first approach identifies the nearest observations using a feature weighting scheme concerning the response variable via support vectors. A randomly selected subset of features is used for the feature weighting and model construction. After building a sufficiently large number of base models on bootstrap samples, a subset of the models is selected based on out-of-bag prediction error for the final ensemble. The second approach builds base learners build on random subsamples instead of bootstrap samples with a random subset of features. The method uses feature weighting while building the models. The remaining observations from each sample are used to assess the corresponding base learner and select a subset of the models for the final ensemble. The suggested ensemble methods are assessed on 12 benchmark datasets against other classical methods, including kNN-based models. The analyses reveal that the proposed methods are often better than the others.

A hybrid Square Shaped Adaptive Neuro-Fuzzy Interference with M-PeSOA model for optimal path selection

In Vehicular cloud computing (VCC), at the time of congestion, to deal with traffic, the vehicles’ underutilized resources are shared; subsequently, these resources aren’t constrained to computing power, storage, along with internet connectivity. Nevertheless, owing to the vehicular network characteristics, attaining the QoS requirements search together with the allocation of resources in the Vehicular Cloud (VC) has turned into a complicated task. An intelligent Square Shaped (SS)-Adaptive Neuro-Fuzzy Interference (SS-ANFIS) methodology for Resource Scheduling (RS) in addition to Mean-centered Penguins Search Optimization Algorithm (M-PeSOA) for Optimal Path Selection (OPS) in the VC is proposed here for efficient resource allocation. (a) Feature extraction, (b) Vehicles clustering, (c) OPS, (d) Resource information extraction, and (e) RS included in the proposed methodology. First, the vehicular network is initialized following that the vehicle features are extracted. Next, Cluster Heads (CHs) are generated regarding which vehicles are clustered; subsequently, the multi-paths are generated. After that, by employing the M-PeSOA, the OPS procedure is conducted; thus, the VC’s resource information is extracted aimed at scheduling the resources efficiently. Lastly, by employing the SS-ANFIS, vehicles are scheduled in the optimal paths. The proposed resource allocation system’s performance is assessed, and the experiential outcomes are analogized using the sumo tool and java platform.

An Intelligent Decision Support Model for Optimal Selection of Machine Tool under Uncertainty: Recent Trends

Many scholars have been interested in the subject of machine tool selection as a result of the growing number of different machines and the continuous advancement of technology associated with these machines. The selection of an unsuitable machine tool may lead to a variety of issues, including limitations on production capacities and productivity indicators when taking into account both time and money from an industrial and practical perspective. The present strategy of selecting machine tools, known as multi-criteria decision-making (MCDM), relies on the subjective viewpoint the vast majority of the time. When selecting an appropriate machining tool, however, it is necessary to take both the subjective and objective points of view into consideration. This is due to the fact that the objective assessment accurately reflects the performance of the machine tools. As a result, the purpose of this work is to provide a strategy for selecting machine tools that are based on an innovative hybrid MCDM framework. The study was conducted under a neutrosophic environment and using triangular neutrosophic numbers (TNNs). In the beginning, the CRiteria Importance through Intercriteria Correlation (CRITIC) method is used to assess and prioritize the criteria set for the study. Then, the Additive Ratio Assessment (ARAS) method is applied to evaluate and rank four machine tools that were selected and used as alternatives in the study. The results indicate that the criteria of maximum spindle speed and linkage accuracy are the most important in determining the best machine tool. Also, the results indicate that the best alternative among the four tools used is FIDLA GTF-28. As a result, the requirements and priorities for research in the future are highlighted.

Study on Location of Bus Stop in Subway Service Area Based on Residents’ Travel Accessibility

This research aims at establishing an integrated urban public transport system with a subway route supplemented by conventional bus lines, in order to enable residents’ “door-to-door” travel. This paper first analyzed the attraction area of the subway, and then used the GIS tools to calculate and analyze residents’ accessibility to adjacent bus stops. Moreover, it created a preliminary layout of bus stops for residential areas with extremely low accessibility using an improved potential model. From the perspective of minimizing residents’ travel costs and bus stop infrastructure deployment costs, a bus stop site selection optimization model was developed. According to the characteristics of the model, the non-dominated sorting genetic algorithm II (NSGA-II) was employed to solve the optimal bus stop locations. In addition, the entropy weight technique for order of preference by similarity to ideal solution (TOPSIS) evaluation model was used to evaluate and sort candidate schemes, accordingly, and thus the optimal site selection scheme was identified. Finally, a before-after comparative analysis on residents’ travel accessibility was conducted. Results show that the proposed method can effectively improve residents’ accessibility to bus stops, which facilitates residents to transfer from conventional bus to subway. Furthermore, it provides a basis for the follow-up optimization of the connection between subway and conventional bus lines.

Deep Learning-based Prioritized Packet Classification and Optimal Route Selection in Wireless Multimedia Sensor Networks

Wireless multimedia sensor networks suffer network congestion due to increased traffic leading to data packet loss and increased energy consumption. Thus, it is essential to have a mechanism for priority-based packet classification to improve the performance and decrease the delay in real-time packets. This paper introduces priority-based packet classification using a word embedding mechanism to extract packet semantics and classification using the long short-term memory model that works based on the different characteristics of the packet header to decide the priority of each packet. Furthermore presents a hybrid meta-heuristic algorithm termed butterfly-based rider optimization algorithm, which considers the packet priority and other parameters in optimal route selection. This hybrid meta-heuristic algorithm is developed by merging rider optimization algorithm, and butterfly optimization algorithm. Finally, the experimental results validate the analytical result as well as the performance comparison between the proposed optimal route selection model and the conventional models.

Analysis of Stock Selection Model Strategy in Indonesia's Capital Market

The impact of investor behavior and decision-making on investment interest in the Indonesian capital market is ultimately tied to the stock selection model used to form an optimal portfolio. Therefore, this study aims to develop an optimal stock selection model in the Indonesian capital market. And thus, the novelty of this study relates to other studies that demonstrate how to improve investment decisions in the capital market in Indonesia. Whereas previous research focused solely on the associations between variables, this study examines the variables themselves. This investigation was carried out in the Greater Jakarta of Jabodetabek (Jakarta, Bogor, Depok, Tangerang, Bekasi). This research utilizes the Fuzzy-Analytical Hierarchy Process (FAHP) methodology. FAHP is the combination of AHP and a fuzzy concept approach. The FAHP method uses qualitative and quantitative data to make decisions. The data collection method employs primary data from the Survey Questionnaire and discussions, secondary data consisting of market data, stock price movement data from the Indonesia Stock Exchange, Indonesian Central Securities Depository, Bank Indonesia, and empirical literature about stock selection models. The results of the analysis indicate that forming the optimal portfolio in the Indonesian capital market involves predicting the price or stock return using a single factor that is thought to impact security. The primary objective assumed to be realized by the optimal portfolio formation approach on the Indonesian capital market is the optimization of stock combinations. Keywords: investor behavior, investor decision-making, capital market, investment, stocks

A Bi-Level Optimization Model for Virtual Power Plant Membership Selection Considering Load Time Series

In order to improve the level of new energy consumption and reduce the dependence of the power system on traditional fossil energy, this paper proposed a bi-level optimization model for virtual power plant member selection by means of coordination and complementarity among different power sources, aiming at optimizing system economy and clean energy consumption capacity and combining it with the time sequence of load power consumption. The method comprises the following steps: (1) The processing load, wind power, and photovoltaic data by using ordered clustering to reflect the time sequence correlation between new energy and load and (2) uses a double-layer optimization model, wherein the upper layer calculates the capacity configuration of thermal power and energy storage units in a virtual power plant and selects the new energy units to participate in dispatching by considering the utility coefficient of the new energy units and the environmental benefit of the thermal power units. The Latin hypercube sampling (LHS) method was used to generate a large number of subsequences and the mixed integer linear programming (MILP) algorithm was used to calculate the optimal operation scheme of the system. The simulation results showed that by reducing the combination of subsequences between units and establishing a reasonable unit capacity allocation model, the average daily VPP revenue increased by RMB 12,806 and the proportion of new energy generation increased by 1.8% on average, which verified the correctness of the proposed method.

Intelligent digital twin for federated learning in AIoT networks

Federated Learning (FL) promises to solve the data privacy problem by training the local model on each node and sharing the model parameters instead of the data itself. Next, the FL server applies model aggregation techniques to aggregate the received models and broadcast the resulting model to the connected clients. This study proposes a Digital Twin-based Federated Learning (DT-FL) framework to virtually monitor and controls the remotely deployed physical clients and their training process. The connection-oriented protocol, Open Connectivity Foundation (OCF) Iotivity, connects the FL clients with the FL server to ensure packet delivery. OCF Iotivity sends/receives the models’ weights to/from the server, and Hyper Text Transfer Protocol (HTTP) is used to monitor clients’ local training. After receiving partially trained models from clients, the server performs the optimal model selection using the normal distribution method by considering the performance of the model. Finally, the best-selected models are aggregated, and the final model is broadcasted to the clients. The framework utilizes Raspberrypi 4 devices as clients with limited computational capabilities, due to which the experiments are conducted with structured energy consumption data. The dataset comprises of 8 multistory residential buildings located in different geographical locations of the Republic of Korea. Each residential building is treated as an FL client and registered on DT using the IP address and port number. The DT-FL framework can be used with classification and regression datasets, and the model architecture for that data can be designed on the DT platform. The experiments are conducted with the partial and full participation of clients. The results show the minimum delay time in physical and virtual object synchronization and better performance and generalization of the global model for each client. The source code of the proposed DT-FL framework is available on GitHub.

Energy, Reliability, and Trust-Based Security Framework for Clustering-Based Routing Model in WSN

Currently, analysts in a variety of countries have developed various protocols for WSN clustering. Among them, the significant one is LEACH (low-energy adaptive cluster hierarchical) that accomplishes the objective of energy balancing by occasionally varying the CHs in the region. Nevertheless, since it implements a random number method, the appropriateness of the CH is full of suspicions. As a result, this work intends to discover the optimal cluster head selection (CHS) model for maximizing energy aware and secured routing in WSN. Here, optimal CH is chosen based upon constraints such as “trust evaluation (direct and indirect trust), distance, security (risk level evaluation), distance, energy and delay”. In addition, the routing model considers the path quality determination of cluster (reliability). For choosing the best CH in WSN, slime wrap food update with cat and mouse optimization (SWFU-CMO) is deployed. Finally, the simulated outcomes verify the efficacy of presented approach related to residual energy, throughput, delay, etc.

Economic efficient use of soilless techniques to maximize benefits for farmers

<abstract> <p>The main challenge of the agricultural sector is the increasing pressure on natural resources, mainly water and arable land. Consequently, an urgent imperative arises to explore technological advancements that can boost food production in alignment with the growing demands. The Soilless Production System (SPS) emerges as a proficient approach for managing irrigation water, thereby making a significant contribution to food security. This research focuses on the efficient use of SPS and identifies the best economic use of the soilless techniques for different crops within an area characterized by limited land and water availability. The database for the study was generated through a farm survey to investigate the benefits of adopting SPSs as a sustainable agricultural practice. A linear programming approach was applied to develop an optimization model for resource allocation and crop mix selection, considering the development opportunities through the SPSs. Different scenarios were applied in the model. The results proved that adopting SPSs is a sustainable irrigation practice, since the technique promotes water use efficiency, generates profitability, and conserves the associated natural resources. The SPSs ensure sustainable use of water resources by increasing water use efficiency. The hydroponics cultivation system had 11 ± 1.7 times higher yields but required 82 ± 11 times more energy in comparison to the lettuce crop produced by the conventional production system (CPS). The result of the optimal solution shows that the total revenue of scenarios of the study is 109% of the revenue of the original value of the largest farmer. The water resources and the investment cost as constraints in the model are totally used, but the operational costs in the optimal solutions are 74% of the total operational cost in the original data. The optimal solution showed the importance of using computerized systems in which the control of the fertigation is better.</p> </abstract>

Energy Demand Forecasting and Optimizing Electric Systems for Developing Countries

Currently, developing countries are experiencing a massive shift toward industrialization. Developing countries lack the technical sophistication and infrastructure to encourage low-carbon and sustainable economic growth because of weak public awareness, regulations, and technology. Developing countries must plan the industrialization process for maximum energy efficiency of production, thereby reducing their CO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> emissions significantly by increasing energy efficiency. This paper attempts to review the current pragmatic methods for forecasting the future load demands from minutes to years ahead in developing countries, following the Preferred Reporting Items for Systematic review and Meta-Analysis Protocols (PRISMA-P). Our primary focus is to provide an optimal forecasting model selection strategy for potential researchers and forecasters. Based on the strengths and weaknesses of the different models, we will discuss the most suitable methods to tailor them to multiple applications and scenarios of load forecasting. The comparison elements are Forecast horizons, Spatio-temporal resolutions, factors affecting the load, different dimensional reduction techniques, model complexity analysis, and the MAPE for error analysis. From the results, We have found ANN hybridized with meta-heuristic techniques to be superior in most of the analysis cases. ANN’s ability to handle non-linear data, flexibility, and robustness is why. Consumption data aggregated at the national level can capture trends efficiently. Meteorological and calendar features influence short-term forecasting extensively, whereas economic factors influence long-term load patterns. Finally, we have identified the trends and research gaps from the existing literature, presenting relevant technical recommendations for improvement.

A Hybrid Incentive Program for Managing Electric Vehicle Charging Flexibility

With the mass roll-out of electric vehicles (EVs) and rapid progress in battery technology, utilizing EV charging flexibility has become a promising solution for supporting economic and secured power system operations. This work proposes a novel hybrid incentive program, which encourages EV owners to sell their charging flexibility to a charging station (CS) and achieve a win-win situation for both EV owners and the CS. Unlike existing approaches, the proposed hybrid incentive program is simultaneously featured with simplicity, consistency, and controllability. To determine the incentive payment parameters, an optimal incentive price selection model is developed. In the solution methodology, we first linearize the original problem, then develop an adaptive ADMM algorithm to efficiently solve the formulated problem. Case studies confirm the superiority of the proposed hybrid incentive program over the state-of-the-arts, achieving 22.51% of EV owners’ cost reduction, 31.18% of energy market bill reduction, and 64.13% of potential charging flexibility utilization.

An automated pipeline integrating AlphaFold 2 and MODELLER for protein structure prediction

The ability to predict a protein's three-dimensional conformation represents a crucial starting point for investigating evolutionary connections with other members of the corresponding protein family, examining interactions with other proteins, and potentially utilizing this knowledge for the purpose of rational drug design. In this work, we evaluated the feasibility of improving AlphaFold2’s three-dimensional protein predictions by developing a novel pipeline (AlphaMod) that incorporates AlphaFold2 with MODELLER, a template-based modeling program. Additionally, our tool can drive a comprehensive quality assessment of the tertiary protein structure by incorporating and comparing a set of different quality assessment tools. The outcomes of selected tools are combined into a composite score (BORDASCORE) that exhibits a meaningful correlation with GDT_TS and facilitates the selection of optimal models in the absence of a reference structure. To validate AlphaMod's results, we conducted evaluations using two distinct datasets summing up to 72 targets, previously used to independently assess AlphaFold2's performance. The generated models underwent evaluation through two methods: i) averaging the GDT_TS scores across all produced structures for a single target sequence, and ii) a pairwise comparison of the best structures generated by AlphaFold2 and AlphaMod. The latter, within the unsupervised setups, shows a rising accuracy of approximately 34% over AlphaFold2. While, when considering the supervised setup, AlphaMod surpasses AlphaFold2 in 18% of the instances. Finally, there is an 11% correspondence in outcomes between the diverse methodologies. Consequently, AlphaMod’s best-predicted tertiary structures in several cases exhibited a significant improvement in the accuracy of the predictions with respect to the best models obtained by AlphaFold2. This pipeline paves the way for the integration of additional data and AI-based algorithms to further improve the reliability of the predictions.

Selection of sales distribution channel in agricultural enterprise

According to applied TOPSIS multi-criteria decision-making method (Technique for Order of Preference by Similarity to Ideal Solution), in paper was selected adequate sales distribution channel in one enterprise active within the agro-food sector at the territory of Semberija (BiH). Decision makers, in this case represented by employed management in enterprise, have been evaluated five sales distribution channels in enterprise in line to previously defined criteria, i.e. products' characteristics, company's financial situation, consumer habits, production costs, geographic concentration, and products' assortment. The main goal of research was to create a model for optimal selection of sales channels, while derived results have been showed that the model "producer - seller (retailer) - consumer" is the most adequate towards the predefined selection criteria. In addition to the justified role of used method in selection of offered alternatives, article also represents a base that will serve in further research, whose focus would be on modernizing of existing and searching for new distribution channels in agricultural enterprises.