Greenhouse gas emissions are increasing global warming significantly, hence the need for manufacturing companies to include sustainability strategies in their supply chain to reduce emissions generated by their operations. This article aims to provide a systematic literature review on integrating sustainability issues into inventory management models to support scholars and practitioners in decision-making processes according to their market requirements. Thus, this paper discusses the most relevant papers published on inventory management topics that consider environmental criteria such as greenhouse gas emissions, ecological quality controls, unsold inventory, and fixed carbon costs. Therefore, we have extended the literature review to incorporate sustainability considerations in inventory models involving an industry’s environmental and social effects. As a result, in this article, a detailed analysis of the existing literature and related weaknesses provide meaningful discussions on crucial issues for future field research avenues in the field.

Deep learning has recently been hailed as the most advanced computer vision technology for image classification. The invention of convolutional neural network (CNN) simplified the effort of feature engineering. Classification of various stages of fruit maturity using machine learning algorithms is a difficult task since it is difficult to distinguish the visual features of the fruits at different maturity stages. Fruit ripeness is critical in agriculture since it impacts the quality of the fruit. Manually determining the maturity of the fruit has various flaws, including the fact that it takes a long time, needs a lot of labor, and can lead to inconsistencies. In developing countries, agriculture is one of the most important economic sectors. Created system can be employed in the food processing business, in real-life applications where the intelligent system’s accuracy, cost, and speed will improve the production rate and allow satisfying consumer demand. With small number of image samples, the system is capable of automating assembly line related work for classifying bananas along with sufficient overall accuracy. The noninvasive method will also be used to classify other clustered fruits or horticultural crops in the future. The system can either replace or aid human operators who can focus their efforts on fruit selection. The combined merits of RGB and HSI (hyperspectral imaging) for classification of bananas were highlighted in the present study; they have possible application as a model for classification of several types of horticultural produce. The multi-input model’s quick processing time can be a useful and handy technique in the farm field during postharvest procedures. Via a combination of CNN and MLP applied to data collected using RGB and hyperspectral imaging, the multi-input model reliably recognizes bananas with an accuracy level of 98.4 percent as well as an F1-score of 0.97. The AI algorithm predicted the size (large, medium, and microscopic) and perspective (front or rear half) of banana classes with 99 percent accuracy. In comparison to previous studies that simply employed RGB imaging, the presented model revealed the value of integrating RGB imaging and HSI approaches.

The present paper analyses the impact of learning on optimal solution of inventory problems. The aim of the paper is to develop both crisp and fuzzy EOQ models for imperfect quality items under deterioration and analyse the effect of learning on holding cost, ordering cost and the number of defective items present in each lot and deal the fuzziness aspect of demand for the fuzzy model. In this paper, it is assumed that all received items are not of perfect type and after100% screening, imperfect items are dropped from the inventory and sold at an allowable proportionate discount. Due to the repetition of handling the system holding cost and ordering cost gradually decrease from one shipment to another. The optimal lot sizes of both crisp and fuzzy models are obtained by calculus method and the total profit functions for each model are also derived. The total profit function of the fuzzy model is defuzzified by using signed distance method. Numerical examples are provided to illustrate the developed models and sensitivity analysis is conducted to show the effect of number of shipments on the order quantity and the total profits of the models.

In this paper, we developed a fuzzy inventory model for time dependent Weibull deterioration and quadratic demand rate. Shortages are allowed and are partially backlogged. In the present situation, two different cases for the fuzzy inventory model are considered. Case 1: the coefficients present in the demand are the initial rate of demand (crisp) which is considered to be a constant and the rate with which the demand rate increases and also the increase in rate of change in the demand rate itself are taken to be the fuzzy numbers. Case 2: all the coefficients of the quadratic demand are considered as fuzzy numbers. The fuzziness is also introduced for the partial backlogging in both cases. In the fuzzy EOQ model, all the fuzzy related parameters are expressed in triangular fuzzy numbers. The main objective of the paper is to minimise the total cost both in crisp and fuzzy environments. To defuzzify the total cost we used the signed distance method. A numerical example is given to show the applicability of the different models. Sensitivity analysis is carried out to reflect the effect of changes in the parameters on the optimum solution.

The present article establishes both crisp and fuzzy economic order quantity (EOQ) models with proportionate discount for items with imperfect quality under learning effect in a finite time horizon. The objective of the crisp model is to determine the optimal order lot size to maximise the total profit where the demand rate is constant and the defective items follow a learning curve. Then, we discussed on two different cases of fuzzy inventory models. Case-1: Defective rate follows a learning curve and the demand rate assumed to be a triangular fuzzy number. Case-2: Defective rate, fixed ordering cost and holding cost follow the learning curve and the demand rate taken to be a triangular fuzzy number. The objective of the fuzzy models is to estimate the maximum total profit per unit time in fuzzy sense and then to derive formula of the optimal lot size for each case and the corresponding total profit functions are defuzzified by using signed distance method. Numerical examples are provided to demonstrate the developed models. Sensitivity analysis is conducted both for crisp and fuzzy models to examine the effect of number of shipments on the order quantity and total profits under various conditions.