Search results

We propose a machine learning based methodology to deal with data collected from a mobile application asking users their opinion regarding fashion products. Based on different machine learning techniques, the proposed approach relies on the data value chain principle to enrich data into knowledge, insights and learning experience.

Online interaction and the usage of social media have dramatically altered both consumers’ behaviors and business practices. Companies invest in social media platforms and digital marketing in order to increase their brand awareness and boost their sales. Especially for fashion retailers, understanding consumers’ behavior before launching a new collection is crucial to reduce overstock situations. In this study, we aim at providing retailers better understand consumers’ different assessments of newly introduced products.

By creating new product-related and user-related attributes, the proposed prediction model attends an average of 70.15% accuracy when evaluating the potential success of new future products during the design process of the collection. Results showed that by harnessing artificial intelligence techniques, along with social media data and mobile apps, new ways of interacting with clients and understanding their preferences are established.

From a practical point of view, the proposed approach helps businesses better target their marketing campaigns, localize their potential clients and adjust manufactured quantities.

The originality of the proposed approach lies in (1) the implementation of the data value chain principle to enhance the information of raw data collected from mobile apps and improve the prediction model performances, and (2) the combination consumer and product attributes to provide an accurate prediction of new fashion, products.

During the past decades, several researchers have introduced devices that use sonar systems to detect and/or to determine the object location or to measure the distance to an object using reflected sound waves. The purpose of this paper is to use sonar sensor with textile structure and to test it for detection of objects.

In this study, a sonar system based on intelligent textiles approach for detection of objects has been developed. In order to do this, ultrasonic sensor has been integrated to textile structures by using conductive yarns. Furthermore, an electronic circuit has been designed; PIC 16F877 microcontroller unit has been used to convert the measured signal to meaningful data and to assess the data. The algorithm enabling the objects detection has also been developed. Finally, smart textile structure integrated with ultrasonic sensor has been tested for detection of objects.

Beam shape is presented related to identified object and compared with the actual one given in sensor's datasheet in order to test the efficiency of the proposed method of detection. The achieved results showed that the determined beam pattern matches with the actual one given in its datasheet. Therefore, it can be concluded that the integration of sensor was successful.

This is the first time in the literature that a sonar sensor was integrated into textile structure and tested for detection of objects.