Search

Automated Essay Scoring (AES) tools aim to improve the efficiency and consistency of essay scoring by using machine learning algorithms. In the existing research work on this topic, most researchers agree that human-automated score agreement remains the benchmark for assessing the accuracy of machine-generated scores. To measure the performance of AES models, the Quadratic Weighted Kappa (QWK) is commonly used as the evaluation metric. However, we have identified several limitations of using QWK as the sole metric for evaluating AES model performance. These limitations include its sensitivity to the rating scale, the potential for the so-called "kappa paradox" to occur, the impact of prevalence, the impact of the position of agreements in the diagonal agreement matrix, and its limitation in handling a large number of raters. Our findings suggest that relying solely on QWK as the evaluation metric for AES performance may not be sufficient. We further discuss insights into additional metrics to comprehensively evaluate the performance and accuracy of AES models. [For the complete proceedings, see ED630829.]

Fuel Cell Electric Vehicles (FCEVs) have garnered significant attention for their eco-friendliness, offering a promising solution to address the challenges posed by greenhouse gas emissions from gasoline and diesel-powered vehicles. These vehicles utilize fuel cell technology to convert hydrogen gas into electricity, producing only water vapor and heat as byproducts. Despite their potential, FCEVs face hurdles in achieving their intended market share targets. This paper focuses on exploring the market growth of FCEVs and the role of government incentives in this context. The study delves into the dynamics between automakers, who invest in research, development, and production of FCEVs, and hydrogen suppliers, responsible for producing and supplying hydrogen at hydrogen refueling stations (HRSs). A decentralized model using the Stackelberg game approach is employed, considering the profits of each stakeholder as the main equation to derive decentralized variables. Various government incentives are examined, including subsidies for the operating and capital costs of automakers and hydrogen suppliers, along with tax credits for FCEVs. By analyzing these incentives, their impacts on the growth of the FCEV market are evaluated. The paper seeks to identify the potential reasons for the shortfall in achieving the FCEV market share target and propose viable solutions for the identified problems. Ultimately, this research aims to shed light on the significance of government support and industry collaboration in fostering the widespread adoption of fuel cell electric vehicles and achieving a sustainable, low-emission transportation system. [ABSTRACT FROM AUTHOR]

To achieve sustainable development, Electric Vehicles (EVs) are considered one of the future directions of the automotive industry, competing with Gasoline Vehicles (GVs). EEbatteries have a limited lifespan and eventually require replacement or repair. Therefore, EE battery refurbishing becomes crucial. The primary goals of battery refurbishing are to reduce costs and environmental impact associated with the production of new batteries while extending the lifespan of existing batteries. To address this, we have developed a two-period model to explain the Closed-loop Supply Chain (CLSC) process of EVs. This study aims to map the supply chain of EEbatteries and discuss strategies for determining the quantities of batteries, EVs, and GVs. The difference in this research compared to previous studies lies in the addition of the functionality of the new quantity of batteries required. The model involves four parties: new energy vehicle manufacturers, consumers, battery manufacturers, and recyclers. This research develops a two-period model. In period 1, batteries are only produced from raw materials; in period 2, used batteries will be recycled into materials. The resolution of this model employs a one-variable function optimization strategy and Nash equilibrium to maximize profits. In period 1, we find that higher production costs for new batteries lead to decreased profits for EVs and new batteries, but increased profits for GVs. In period 2, we discover that a higher recycling rate of used batteries (β) leads to increased production profits for both EVs and GVs but a decrease in new battery production. [ABSTRACT FROM AUTHOR]

The increasing popularity of electric vehicles (EVs) is increasing EV ownership and demand in the EV market. The increase in the number of EV electric vehicle owners has led to a rise in the amount of electric vehicle battery waste. Consequently, the accumulation of end-of-life (EOL) EV batteries has become a pressing problem, with the potential for environmental pollution if not properly managed. To solve this problem recycling mechanism for used EV batteries is needed. This study proposes a closed-loop supply chain approach to determine the optimal collection model for EOL electric vehicles battery recycling and low-carbon decisions. Two collection models are introduced: (i) the TR model, where third-party recyclers and retailers collect power batteries, and (ii) the TU model, involving third-party recyclers and comprehensive battery utilization enterprise (BCU enterprise). In the reverse chain, either the retailer, third-party recycler, or BCU enterprise collects spent power batteries from customers. Then the battery is transferred to the BCU enterprise. The BCU enterprise sells echelon-utilizable batteries to the echelon market and non-echelon-utilizable batteries to manufacturers. The BCU enterprise also collects post-echelon-utilized residues from the echelon market and then sells them to EV producers for recycling as raw materials. Thus, BCU enterprise transfers echelon non-echelon-utilizable batteries and post-echelon-used residues to manufacturers for raw material extraction. This paper employs mathematical modelling using the Stackelberg game to analyze the optimal collection model and low-carbon decision-making for end-of-life EV battery recycling systems within the two proposed collection models. [ABSTRACT FROM AUTHOR]

In recent years, the rapid development of electric vehicle (EV) manufacturers has been fueled by government subsidies aimed at reducing harmful gas emissions from traditional fuel sources. However, Manufacturers often face limitations in battery production capacity. So, they produce EVs in two ways. Firstly, EV manufacturers procure batteries from specialized suppliers and produce EVs independently. Secondly, manufacturers engage in vertical cooperation, collaborating with battery suppliers to jointly produce EVs. This paper examines the advantages and disadvantages of these two strategies and considers factors such as production efficiency, cost-effectiveness, and supply chain dynamics. By analyzing the outcomes of these approaches, this research aims to shed light on effective strategies for overcoming manufacturing limitations in the EV industry and fostering sustainable growth. However, as the number of EVs and subsidies has increased, governments have faced financial pressures, leading to a reduction in subsidization. This paper examines the consequences of subsidy reductions on selling prices, market demand, and the advantages within the EV supply chain. The study involves multiple stakeholders, including battery suppliers, manufacturers of ordinary brand EVs (Manufacturer A), manufacturers of well-known brand EVs (Producer B), and government subsidies. Additionally, three strategies are investigated the Non-cooperative strategy ("N" Strategy), the cooperative strategy between Manufacturer A and battery suppliers ("S-A" Strategy), and the cooperative strategy between Producer B and battery suppliers ("S-B" Strategy). This research aims to provide insights into the impact of reduced subsidies on EV market dynamics and effectivity approaches to the electric vehicle supply chain. [ABSTRACT FROM AUTHOR]

Electric vehicles (EV) are one way to reduce global environmental problems. The weakness of EV is the battery, and there are a lot of unused batteries. As we know, if the used batteries of EV are not handled properly, they will become a problem for the environment. Using unused batteries by recycling them will have a positive impact on the environment and the economy. This research will explore how EV batteries are recycled, taking into account government subsidies and corporate social responsibility (CSR) investments. Government subsidies and CSR investments can affect the price of recycled EV batteries and aim for closed supply chain decision-making (CLSC). In CLSC, the collected used batteries are classified into classes I and Π after detection. Class I batteries will be processed for remanufacturing and class Π batteries will be classified into echelon utilization. Using Stackelberg game analysis, two models of decentralized decision-making and centralized decision-making were simulated. Then, a system comparison is conducted to find out the impact of government subsidies and CSR investment on the pricing of new products, and the results show that the government subsidy policy dramatically affects the price of recycled batteries for electric vehicles, increases the waste recycling rate, and increase the CSR investment rate. Hence, it is recommended that the government enhance subsidies for the recycling of electric vehicle batteries. The benefits derived from a CLSC with centralized decision-making surpass those of decentralized decision-making. Consequently, enhancing the coordination within CLSC is crucial to maximize the advantages. [ABSTRACT FROM AUTHOR]

In recent years, one of the most popular cryptocurrency assets that has attracted the interest of many investors is Bitcoin. Due to its increasing popularity and high price volatility, forecasting Bitcoin price has become a central concern in financial market analysis. We use machine learning techniques and SHAP (SHapley Additive Explanation) interaction values to improve our forecasting accuracy. The historical dataset used for this study includes various variables such as opening price, closing price, trading volume, and other factors. In this study, four different machine learning models are used to forecast the price of Bitcoin. The machine learning models used are XGBoost, CatBoost, Random Forest, and LightGBM. After the models are trained and tested for performance by evaluating metrics and visually analyzing historical data, the four models generate different price forecasting. To understand the contribution of each feature in the forecasting of Bitcoin, the SHAP (SHapley Additive Explanation) interaction value is employed. The SHAP value provides valuable insights into the extent of influence each attribute or variable has on the forecasting. The results show that utilizing machine learning methods and SHAP interactions can provide an overview of the importance of the relationship between existing features and how much influence each attribute has on the movement of cryptocurrencies, especially Bitcoin. Therefore, this can provide a more transparent picture and insight for market participants to make better investment decisions. [ABSTRACT FROM AUTHOR]

Bayesian Networks (BNs) is a graphical representation model of some random variables and the relationship between the random variables. It is used to determine the joint probability of some random variables based on the posterior probability of each random variable. The posterior probability is calculated based on the parameters of the prior distribution. Prior distribution used in BNs includes the Dirichlet distribution. It is a conjugate prior for the multinomial distribution. Graph of BNs (belief-network structure) is determined by maximizing the probability of each random variable. One of the algorithms used to maximize it is K2 algorithm. The present research seeks to re-derive the joint probability in the belief-network structure using Dirichlet distribution, and to determine K2 algorithm for the structure. The joint probability obtained is the product of each probability of BNs random variable. The probability shows the dependence of a random variable with the others (parents). Based on these views, K2 algorithm can be used and Probability derived from the structure is considered as the product of the probability of each random variable. The probability of each random variable is calculated with the formula .... The belief-network structure is found out by determining a set of parents (πi) probably from random variables. Determination of the parents is based on the maximum probability of any random variable through algorithms K2. [ABSTRACT FROM AUTHOR]