Conventional retail store inventory management systems rely on stockroom actions. However, especially in big scale retail stores, a certain amount of goods is placed on the display shelves. The items placed on the display shelves are not counted until their tags are identified by a cash register and marked as sold in the inventory management system. In this study, we propose a smart shelf that is capable of counting the specific items placed on it by detecting the location and the weight of the items. Our approach assumes that specific items in a retail store are placed in a specified location on each shelf, which is a widely preferred approach. The identified product information is then transferred to the inventory management system through the local network connection, and products on the display shelves can be counted in real time. The results show that the location and weight of the items can be identified with remarkable accuracy.

Wireless sensor network is a popular area for both academic research and commercial applications. A wireless sensor network is made up of several sensor nodes connected over various wireless infrastructures such as Wi-Fi, Bluetooth, ZigBee, or WiMAX. Determining the relative or absolute position of the sensor nodes is essential information for many applications. In this work, we present a novel method for estimating the position of sensor nodes using the Received Signal Strength Indicator and Time of Arrival metrics of the preferred wireless communication infrastructure. Localization results based on both of the metrics and comparison of them with respect to distance between the nodes are presented, and a novel combined method using both the RSSI and ToA based distance estimations is presented. The proposed method estimates the position of the WSN using both methods, but the result of a single method is preferred depending on the distance between the nodes since within the first 5 m. The RSSI based method is superior to ToA and for farther distances ToA outperforms RSSI. The measurement results show that the combined method reduces the estimation error and performs better than both methods it is based on.

Detecting and identifying individuals with high body temperature can be critical for preventing the spread of diseases with high body temperature as a symptom like COVID-19. Thermal cameras or manual temperature inspection methods are widely used to identify elevated body temperature. In this work, we propose a novel method to identify and track people with higher disease risk, including the body temperature change of each person in a specified community and other risk factors like family backgrounds, habits, and social life. Results show that each person's body temperature can be tracked and recorded with the user’s ID number every time the user passes from specific locations equipped with RFID readers. By using an artificial intelligence-supported risk scoring system, a risk factor is evaluated based on the parameters defined accordingly. If the evaluated risk score of the user is above a specific value, the system generates an alarm to isolate the person with a high-risk score. Therefore, isolating any potentially infected individual helps health professionals reduce the spreading speed of infections through isolated communities.

Precision of production in industry is a hot area and companies are seeking for solutions to make data-drive decisions to optimize the processes of production and calculate gain/loss during manufacturing. Making a right decision with huge reports always takes time and executive or decision makers always seek user-friendly, automatised applications to help. This paper offers a server-side infrastructure for IoT applications that targets to provide an end-to-end solution to smart factories on production lines. Solution designed as a middleware application in which northbound and southbound systems are connected to each other. Collected data is stored and integrated with BI tool to present gain/loss during production to executive management and same output can be used for MES-MOM operations. OPC-UA is selected as southbound protocol as it can be considered the most used protocol in industrial IoT. Moreover, solution can be enhanced with any other protocol with slight changes in configurations.