Examinando por Autor "Benhamida, Fatima Zohra"

Mostrando 1 - 2 de 2
  • Miniatura
    Ítem
    Demand forecasting tool for inventory control smart systems
    (Croatian Communications and Information Society, 2021-06-09) Benhamida, Fatima Zohra; Kaddouri, Ouahiba; Ouhrouche, Tahar; Benaichouche, Mohammed; Casado Mansilla, Diego; López de Ipiña González de Artaza, Diego
    With the availability of data and the increasing capabilities of data processing tools, many businesses are leveraging historical sales and demand data to implement smart inventory management systems. Demand forecasting is the process of estimating the consumption of products or services for future time periods. It plays an important role in the field of inventory control and Supply Chain, since it enables production and supply planning and therefore can reduce delivery times and optimize Supply Chain decisions. This paper presents an extensive literature review about demand forecasting methods for time-series data. Based on analysis results and findings, a new demand forecasting tool for inventory control is proposed. First, a forecasting pipeline is designed to allow selecting the most accurate demand forecasting method. The validation of the proposed solution is executed on Stock&Buy case study, a growing online retail platform. For this reason, two new methods are proposed: (1) a hybrid method, Comb-TSB, is proposed for intermittent and lumpy demand patterns. CombTSB automatically selects the most accurate model among a set of methods. (2) a clustering-based approach (ClustAvg) is proposed to forecast demand for new products which have very few or no sales history data. The evaluation process showed that the proposed tool achieves good forecasting accuracy by making the most appropriate choice while defining the forecasting method to apply for each product selection.
  • Miniatura
    Ítem
    PyFF: a fog-based flexible architecture for enabling privacy-by-esign IoT-based communal smart environments
    (NLM (Medline), 2021-06) Benhamida, Fatima Zohra; Navarro, Joan; Gómez Carmona, Oihane; Casado Mansilla, Diego; López de Ipiña González de Artaza, Diego; Zaballos, Agustín
    The advent of the Internet of Things (IoT) and the massive growth of devices connected to the Internet are reshaping modern societies. However, human lifestyles are not evolving at the same pace as technology, which often derives into users' reluctance and aversion. Although it is essential to consider user involvement/privacy while deploying IoT devices in a human-centric environment, current IoT architecture standards tend to neglect the degree of trust that humans require to adopt these technologies on a daily basis. In this regard, this paper proposes an architecture to enable privacy-by-design with human-in-the-loop IoT environments. In this regard, it first distills two IoT use-cases with high human interaction to analyze the interactions between human beings and IoT devices in an environment which had not previously been subject to the Internet of People principles.. Leveraging the lessons learned in these use-cases, the Privacy-enabling Fog-based and Flexible (PyFF) human-centric and human-aware architecture is proposed which brings together distributed and intelligent systems are brought together. PyFF aims to maintain end-users' privacy by involving them in the whole data lifecycle, allowing them to decide which information can be monitored, where it can be computed and the appropriate feedback channels in accordance with human-in-the-loop principles.