Recent advanced technology enables Android smartphone suitable for quality evaluation of food. In this research, image processing technique was used to detect food color additives. In this research, a smartphone application was developed to determine the availability of color additives in food products. Local food namely geplak was made by adding food grade (i.e. tartrazine and erythrosine) and non-food grade (Rhodamin B and Methanyl Yellow) additives in three concentrations. A mobile phone captured geplak images resulting 1200 images which were divided into 1000 images for training and 200 images for validation. Image data was processed with the python programming language of tensorflow function. The output of python in nominal weight was then trained and tested by using a convolutional neural networks (CNN) method. The weights were then processed by Android Studio version 3.2.1 using.java as backend from CNN and.xml as an application layout. Validation result showed that the program successfully determined class of food additive in high degree accuracy of 98 %.

The transportation sector plays an important role in realizing a smart city. The increase in the number of vehicles is currently not supported by an increase in road capacity. Traffic jams or congestion will occur in many places. Congestion will increase the accident rate, bad effect on economic growth, and increase gas emissions. Effective traffic management is necessary to reduce congestion levels and its side effects. A traffic light is one of traffic management methods. Traffic lights control the flow of traffic at road intersections, zebra crossings, and other traffic flow points. Conventional traffic lights work on a pre-programmed time sequence. This system is effective if the vehicle density is relatively constant. The density of vehicles from various directions fluctuates with time. To increase the effectiveness of using traffic light, an adaptive system is needed. In this study, a simple adaptive traffic light mechanism was developed based on congestion on the road using computer vision. Vehicle congestion is detected using the YOLOv3 object detection which detects the type of vehicle. The detection system used by YOLOv3 with pretrained weight COCO has a true positive value for motorbikes of 60%, cars (light vehicles) 93%, and trucks/buses (heavy vehicles) 100%. The processing speed of the Jetson Nano mini-PC with the OpenCV library on the GPU is 2 times faster than the process with the CPU.