Search

Because of the rapid development of the Internet of Things, the business mode of the retail industry has changed tremendously. Smart retail is increasingly receiving academic attention. However, research on smart retail has mainly focused on shopping utility and consumers' interactions with smart technology rather than consumers' perceptions and feelings regarding smart technology. In order to fill this void, this paper incorporates perceptions (i.e., cognitive absorption) into the technology acceptance model to investigate consumer intention in smart retail. In total, 322 consumers with experience using smart retail technology are surveyed, and SEM (Structural Equation Modeling) is used for analysis. According to the findings, cognitive absorption has a considerable influence on consumers' perception of the usefulness and ease of use of smart retail technology, which, in turn, affects consumer adoption and recommendation intentions on this smart technology. Theoretical and practical recommendations are made, as well as future research directions. [ABSTRACT FROM AUTHOR]

Accurate tracking of shelves in markets is necessary for efficient and real-time management of stock and products. Smart technologies assist in determining the positions of items and the movement to or from the shelves. Recently, several shelf tracking systems have been proposed utilizing sensor fusion, image processing, deep learning, and the Internet of Things. However, these systems suffer from the imbalance calibration of load cell sensors, high cost of hardware installation, and low positioning accuracy. Therefore, we propose an accurate online Weighing Distribution Positional Model that enables accurate load cell calibration and tracks item position and weight on shelves utilizing the load cells sensor fusion and deep learning. The load cell sensors are used to weigh shelves, and cameras are used to record the item’s movement which is analyzed by image processing. Four well-known machine learning algorithms are tested on the system to identify the best operative environment. The system and the algorithms are evaluated using a real-world dataset consisting of item weights, and the Artificial Neural Network (ANN) was found more accurate than the others with 97.61% accuracy and zero error tolerance. [ABSTRACT FROM AUTHOR]

In recent years, word embedding models receive tremendous research attentions due to their capability of capturing textual semantics. This study investigates the issue of employing word embedding models into storage-constrained edge devices for personalized item-of-interest recommendation in a smart store. The challenge lies in that the existing embedding models are often too large to fit into a storage-constrained edge device. One naive idea is to reside the word embedding model in a secondary storage and process recommendation with that storage. However, this idea suffers from the burden of additional traffics. To this end, we propose a framework called Word Embedding Quantization (WEQ) which constructs an index upon a given word embedding model and stores the index in the primary storage to enable the use of the word embedding model by edge devices. One challenge for using the index is that the exact user profile is no longer ensured. However, we find that there are opportunities for computing the correct recommendation results by knowing only an inexact user profile. In this paper, we propose a series of techniques that leverage the opportunities for computing candidates with the goal of minimizing the accessing cost to a secondary storage in edge devices. Experiments are performed to verify the efficiency of the proposed techniques, demonstrating the feasibility of the proposed framework. [ABSTRACT FROM AUTHOR]

Featured Application: A smart store customer relationship management system to estimate the customer's age and gender for simplifying the shopping experience by facilitating personalized product recommendation and advertisement to promote the smart trading along with developing an inventory for future business promotion. The COVID-19 pandemic markedly changed the human shopping nature, necessitating a contactless shopping system to curb the spread of the contagious disease efficiently. Consequently, a customer opts for a store where it is possible to avoid physical contacts and shorten the shopping process with extended services such as personalized product recommendations. Automatic age and gender estimation of a customer in a smart store strongly benefit the consumer by providing personalized advertisement and product recommendation; similarly, it aids the smart store proprietor to promote sales and develop an inventory perpetually for the future retail. In our paper, we propose a deep learning-founded enterprise solution for smart store customer relationship management (CRM), which allows us to predict the age and gender from a customer's face image taken in an unconstrained environment to facilitate the smart store's extended services, as it is expected for a modern venture. For the age estimation problem, we mitigate the data sparsity problem of the large public IMDB-WIKI dataset by image enhancement from another dataset and perform data augmentation as required. We handle our classification tasks utilizing an empirically leading pre-trained convolutional neural network (CNN), the VGG-16 network, and incorporate batch normalization. Especially, the age estimation task is posed as a deep classification problem followed by a multinomial logistic regression first-moment refinement. We validate our system for two standard benchmarks, one for each task, and demonstrate state-of-the-art performance for both real age and gender estimation. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic markedly changed the human shopping nature, necessitating a contactless shopping system to curb the spread of the contagious disease efficiently. Consequently, a customer opts for a store where it is possible to avoid physical contacts and shorten the shopping process with extended services such as personalized product recommendations. Automatic age and gender estimation of a customer in a smart store strongly benefit the consumer by providing personalized advertisement and product recommendation; similarly, it aids the smart store proprietor to promote sales and develop an inventory perpetually for the future retail. In our paper, we propose a deep learning-founded enterprise solution for smart store customer relationship management (CRM), which allows us to predict the age and gender from a customer’s face image taken in an unconstrained environment to facilitate the smart store’s extended services, as it is expected for a modern venture. For the age estimation problem, we mitigate the data sparsity problem of the large public IMDB-WIKI dataset by image enhancement from another dataset and perform data augmentation as required. We handle our classification tasks utilizing an empirically leading pre-trained convolutional neural network (CNN), the VGG-16 network, and incorporate batch normalization. Especially, the age estimation task is posed as a deep classification problem followed by a multinomial logistic regression first-moment refinement. We validate our system for two standard benchmarks, one for each task, and demonstrate state-of-the-art performance for both real age and gender estimation.

The retail industry is on a decline due to the redirection of the consumers towards the e-commerce business. In order to prevent this trend from severely damaging the business of offline stores, it is necessary to understand the drawbacks of the current offline retail sector. The timeintensive exercise and the lack of convenience are the major reasons why people evade the offline shopping. This paper proposes a smart store solution, based on Proximity technologies, not only as an alternative to conventional methods but also as an advancement to the existing systems in place. It also consists of an informative mobile application that assists the customer activities in the scope of the store, beginning from his entry in the smart parking area to his exit after a successful checkout via digital payments. This innovation will help revive the stagnating offline retail industry by adding unique and attractive features that make offline shopping more intuitive, engaging, efficient and convenient. [ABSTRACT FROM AUTHOR]

This work shows that total reflection X-ray fluorescence (TXRF) is a fast, easy and successful tool to determine the presence of potentially toxic elements in atmospheric aerosols precipitations on tree leaves. Leaves are collected in eleven parks of different geographical areas of the Brescia city, Northern Italy, for environmental monitoring purposes. Two sample preparation procedures are considered: microwave acid digestion and the novel SMART STORE method for direct analysis. The latter consists in sandwiching a portion of the leaf between two organic foils, metals free, to save it from contamination and material loss. Mass composition of macro, micro and trace elements is calculated for digested samples, while relative elemental amount are obtained from direct analysis. Washed and unwashed leaves have a different composition in terms of trace elements. Differentiation occurs according to Fe, Pb and Cu contributions, considered as most representative of air depositions, and probably related to anthropogenic sources. Direct analysis is more representative of the composition of air precipitations. Advantages and drawbacks of the presented methods of sample preparation and TXRF analysis are discussed. Results demonstrate that TXRF allows to perform accurate and precise quantitative analysis of digested samples. In addition, direct analysis of leaves may be used as a fast and simple method for screening in the nanograms range. [ABSTRACT FROM AUTHOR]

• Internet of Things (IoT) is explored for smart stores and generally the retail sector. • Smart services transform the customer experience holistically through the various applications in store. • A field exploration is providing an overview of the drivers of smart retail service diffusion and the relevant challenges. • Security is a major challenge and concern for businesses installing IoT devices in their journey to smart store transformations. The digitally disruptive environment has evolved rapidly due to the introduction of new advancements within the field of smart applications. Applications of one of the most prominent technologies, Internet of Things (IoT), often appear in the retail sector, where smart services have transformed the customer experience holistically. Presented in this paper are the findings from an exploratory field study in the retail service sector, which drew on the views of experienced practitioners about the smart store experience and the associated changes. The paper presents an overview of the drivers of smart retail service diffusion and the relevant challenges, such as the business expectations and the heterogeneity of devices. The arising themes indicate that IoT security is a major challenge for businesses installing IoT devices in their journey towards smart store transformation. The paper highlights the importance of a secure data-sharing IoT environment that respects customer privacy as the smart experience in-store offers data-driven insights and services. Implications for research and practice are discussed in terms of the customer experience relevant to the identified challenges. [ABSTRACT FROM AUTHOR]