Ph.D. Student, Electrical and Electronics Engineering, University of the Philippines, Diliman
Melchizedek I. Alipio is currently a Ph.D. in Electrical and Electronics Engineering student under the Ubiquitous Computing Laboratory of the Electrical and Electronics Engineering Insititute of the University of the Philippines Diliman. He finished his bachelor's and master's degree in Electronics Engineering in 2010 and 2013, respectively.
His research interests include transport protocols in Wireless Sensor Networks (WSN), Internet of Things testbed implementations in Smart Cities and Agriculture and Data Analytics. He is also currently affiliated with the Institute of Electrical and Electronics Engineers (IEEE) and Internet Society (ISOC) and published several works in the field of sensor networks.
PTC Young Scholar 1: Digital Development
Tuesday, 23 January 2018
The Philippines is no stranger to successive tech trends and innovations brought about by information and communication technology (ICT), all of which are reshaping the business landscape. There is the spread of mobile devices and solutions in the consumer market and companies’ increasing reliance on big data, smart tools, and the Internet-of-Things (IoT). In addition, small-scale industries such as retail supermarkets and groceries in local communities are starting to upgrade with simple devices such as cameras and sensors.
This research work is in the process of developing a smart retail system for local small supermarket owners to monitor, analyze and predict shopper’s behavior, purchase history, and floor traffic. To identify the number and location of shoppers within an indoor store market, a network of radio-frequency identification (RFID) tags and camera are used. Human indoor localization is performed thru Received Signal Strength Indication (RSSI), trilateration and image processing wherein the volume of shoppers for every aisle is accurately determined which could be viewed and monitored by the retail market owner. In addition, this information can be utilized to generate predictions for in-store marketing strategies. With the use of predictive analytics such as machine learning algorithm, store owners can be informed which product has the highest sales within the day, product preference, potential marketing campaign and shelf display effectiveness. Furthermore, this work focuses on designing a low-cost IoT-based retail system that can be easily implemented and adapted by local owners in the community.