Search

This study introduces an enhanced version of the discrete choice model combining embedded neural architecture to enhance predictive accuracy while preserving interpretability in choice modeling across temporal dimensions. Unlike the traditional architectures, which directly utilize raw data without intermediary transformations, this study introduces a modified approach incorporating temporal embeddings for improved predictive performance. Leveraging the Phones Accelerometer dataset, the model excels in predictive accuracy, discrimination capability and robustness, outperforming traditional benchmarks. With intricate parameter estimates capturing spatial orientations and user-specific patterns, the model offers enhanced interpretability. Additionally, the model exhibits remarkable computational efficiency, minimizing training time and memory usage while ensuring competitive inference speed. Domain-specific considerations affirm its predictive accuracy across different datasets. Overall, the subject model emerges as a transparent, comprehensible, and powerful tool for deciphering accelerometer data and predicting user activities in real-world applications.

Reliability is now widely recognized across various industries, including manufacturing. This study investigates a system composed of five components, one of which is a bridge network. The components are assumed to follow the generalized unit half logistic geometric distribution (GUHLGD) with equal failure rates over time. The following three improvement methods are considered: reduction, cold duplication, and hot duplication. The reliability function and mean time to failure (MTTF) are employers liability equivalence factors (REFs). Additionally, the λ fractiles of both the original and enhanced systems are obtained. Numerical results illustrate the effectiveness of these techniques, with cold duplication shown to be the most effective, offering higher reliability and MTTF compared to hot duplication. The enhanced system outperforms the original system overall.

In this paper, we proposed a sustainable inventory model with a learning effect for imperfect quality items under different kinds of fuzzy environments like crisp, general fuzzy, cloudy fuzzy, and monsoon fuzzy. We divided the mathematical model into three parts under the learning effect according to the real-time fuzzy components (crisp, cloudy, and monsoon environments) of the demand rate of the items. We minimized the total inventory cost with respect to cycle length in each environment under the proposed assumptions. The non-linear optimization technique is applied for the algorithm and the solution method to find the decision variable. Finally, we compared the total inventory cost under different fuzzy environments and our finding is that the fuzzy monsoon environment is a more effective fuzzy environment than crisp and cloudy fuzzy environments. We have presented a numerical example for the validation of the proposed model and have shown the impact of the inventory input parameters on the cycle length and total inventory fuzzy cost. The managerial insights and future scope of this proposed study have been shown in the sensitivity analysis and conclusion. The limitations, application, future extension and scope, and social implementation have been shown in this research study.

Reliability assessments are pivotal in evaluating system quality and have found extensive application in manufacturing. This research delves into a system comprising five components, one of which is a bridge network. The components are presumed to follow a Bilal lifetime distribution with a failure rate that changes over time. Four distinct methods are employed to enhance the components within the system. This study involves the computation of δ-fractiles and reliability equivalence factors (REFs). Additionally, a numerical case study is provided to elucidate the theoretical findings.

In this study, a supply chain model is proposed with preservation technology under learning fuzzy theory for deteriorating items where the demand rate depends on the selling price and also treats as a triangular fuzzy number. The deterioration rate of any item cannot be eliminated due to its natural process, but it can be controlled with the help of preservation technology. Some harmful gases are emitted during the preservation process due to deteriorating items that harm the environment. In general, it can be easily seen that most of the sellers offer a trade credit policy to their regular buyers. In this paper, the retailer’s inventory stock reduces due to demand and deterioration. It is also assumed that some units are defective due to machine defects or delivery inefficiency. The retailer accepted the policy of trade credit offered by the seller. The aim of this paper is to enhance the profit of the supply chain partners. We proposed a theorem to get the optimal values of the selling price and cycle length. The retailer’s total profit is a function of selling price and cycle length, and the retailer’s total profit is optimized with respect to selling price and cycle length under trade-credit. Numerical examples are also presented for the validation of the present study, and sensitivity analysis is also discussed to know the robustness of the supply chain model. Managerial insight and observation have been given in the sensitivity section. Limitations and future work of this paper have been presented in the conclusion section.

Assuming the significance of sustainability, it is considered necessary to ensure the conservation of our natural resources, in addition to minimizing waste. To promote significant sustainable effects, factors including production, transportation, energy usage, product control management, etc., act as the chief supports of any modern supply chain model. The buyer performs the firsthand inspection and returns any defective items received from the customer to the vendor in a process that is known as first-level inspection. The vendor uses the policy of recovery product management to obtain greater profit. A concluding inspection is accomplished at the vendor’s end in order to distinguish the returned item as belonging to one of four specific categories, namely re-workable, reusable, recyclable, and disposable, a process that is known as second-level inspection. Then, it is observed that some defective items are suitable for a secondary market, while some are reusable, and some can be disassembled to shape new derived products, and leftovers can be scrapped at the disposal cost. This ensures that we can meet our target to promote a cleaner drive with a lower percentage of carbon emissions, reducing the adverse effects of landfills. The activity of both players in this model is presented briefly in the flowchart shown in the abstract. Thus, our aim of product restoration is to promote best practices while maintaining economic value, with the ultimate goal of removing the surrounding waste with minimum financial costs. In this regard, it is assumed that the demand rate is precise in nature. The learning effect and fuzzy environment are also considered in the present model. The proposed model studies the impacts of learning and carbon emissions on an integrated green supply chain model for defective items in fuzzy environment and shortage conditions. We optimized the integrated total fuzzy profit with respect to the order quantity and shortages. We described the vendor’s strategy and buyer’s strategy through flowcharts for the proposed integrated supply chain model, and here, in the flowchart, R-R-R stands for re-workable, reusable, and recyclable. The demand rate was treated as a triangular fuzzy number. In this paper, a numerical example, sensitivity analysis, limitations, future scope, and conclusion are presented for the validation of the proposed model.

An imprecise demand rate creates problems in profit optimization in business scenarios. The aim is to nullify the imprecise nature of the demand rate with the help of the cloudy fuzzy method. Traditionally, all items in an ordered lot are presumed to be of good quality. However, the delivered lot may contain some defective items, which may occur during production or maintenance. Inspection of an ordered lot is indispensable in most organizations and can be treated as a type of learning. The learning demonstration, a statistical development expressing declining cost, is necessary to achieve any cyclical process. Further, defective items are sold immediately after the screening process as a single lot at a discounted price, and the fraction of defective items follows an S-shaped learning curve. The trade-credit policy is adequate for suppliers and retailers to maximize their profit during business. In this paper, an inventory model is developed with learning and trade-credit policy under the cloudy fuzzy environment where the demand rate is treated as a cloudy fuzzy number. Finally, the retailer’s total profit is maximized with respect to order quantity. Sensitivity analysis is presented to estimate the robustness of the model.