Abstract—Dramatic growing in global trading causes inventory levels and their processes in supply chain getting more complex. Therefore, an effective inventory and warehousing management is strongly required in order to reduce errors that may cause by labor resources. One of important duties in warehouse processes is correctly updating stock keeping unit. Since, the errors of this notification may cause delay when the loads have to wait due to out of stock. It will affect to the whole supply chain causing lost in time and cost. In addition, an inaccurate updating may initiate unnecessary ordering which also causes an extra cost. Considering to current inventory management system applying RFID tags, its performance might be affected from metal, liquids or other sources of radio interference. This paper contributes new idea for reducing the errors in warehouse management system. Instead of using on warehouse employees and nor barcode and RFID tags, the machine vision technology is substituted called stock monitoring units dominating in storage areas. The proposed system uses commodity product, which is affordable so it is practical to install stock monitoring units in existing warehousing system requiring small amount of additional cost. Form a number of experiments, the effective of stock monitoring system is evaluated by comparing both time and cost before and after implementation. The experimental outcomes show excellent performance in term of both time and cost.
Index Terms—Monitoring system, stock keeping unit, warehouse and inventory system, machine vision in automated warehouse management system.
Pornsiri Chatpreecha is with the Panyapiwat Institute of Management (PIM), Nontaburi, Thailand (e-mail: email@example.com).
Chadaporn Keatmanee is with Thai-Nichi Institute of Technology (TNI), Bangkok, Thailand (e-mail: firstname.lastname@example.org).
Cite: Pornsiri Chatpreecha and Chadaporn Keatmanee, "Stock Monitoring Unit in Storage Areas Enable Flexibility, Productivity, and Reliability of Warehousing System," International Journal of Machine Learning and Computing vol. 8, no. 6, pp. 613-618, 2018.