Search

The results of the distance calculation used to control the movement of the robot, hanse the robot is able to avoid unknown obstacles. This obstacle robot divided into 3 parts, namely Arduino Uno as a controller, L298N driver as a motor/wheel controller and ultrasonic sensor HC-SR04 as a sending and receiving device for ultrasonic signals. The ultrasonic sensor design on the obstacle robot placed at the front of the robot with the obstacle position in front. From the data analysis, the obstacle robot can determine the accuracy level of the detected distance and can stop according to the detected obstacle distance. The test results show that the obstacle robot is less accurate in detecting the obstacles in front of it, as evidenced by the test results that there is an average error of 0.118. The obstacle robot made using an ultrasonic sensor, so it is less accurate in reading the presence of a obstacle in front of it. In the test results, the biggest error is when the robot is at a distance of 30 cm, where the robot stops at a distance of 24 cm so that there is an error of 6 cm that missed.

Today, the waste problem has become more serious, because the waste can cause environmental pollution and bad smell pollution. The less awareness of cleanliness is the main factor, especially the less awareness of throwing waste at the right place. Based on the data of the Ministry of Environment and Forestry “Environmental Ignorance Behavior” in 2008 said that around 72 percent of Indonesian less be aware of the waste problem generally with plastic waste, this waste will flow to the sea and make pollution. This research objective is to design and accomplish previous roboboat research that still has some drawbacks. This research employs digital image processing and neural network based on the tensor flow framework method to overcome less accurate waste detection as well as autopilot navigation system. The research result shows by using 3600 dataset images, the model has the lowest loss 0.9 and 64.3% average accuracy with various samples and distance.

The world is currently being hit by the COVID-19 virus. In this New Normal era, a rule is enforced that everyone must wear a mask wherever we are. Checking masks and body temperature is still done manually or by human observation, thus allowing for inaccuracies in observing and checking temperature. The problem occurred at Trunojoyo Madura University which still uses a manual mask and body temperature checking system. So, for accuracy and to reduce the risk of contracting officers. A tool was created to detect the mask and temperature automatically. In this study using a camera, temperature sensor MLX90614, and proximity sensor using Raspberry Pi. This research uses a machine learning system with the Deep Learning Convolutional Neural Network (CNN) Single Shot Detector (SSD) method. From this study, the results of mask detection obtained a success percentage of 93.4% and an error percentage of 6.6% from the entire test and obtained an average detection time of 2.63 seconds. And the average time of the whole system is 3.8 seconds. In this study, there was a delay during detection due to the heavy computational load on the system, so for further research, use a mini pc that has better performance.

In this work, we propose a digital filter design, namely moving average filter (MAF) to be implemented on echo signal and temperature data. The echo signal data is obtained from the ultrasonic transducer, while the temperature data is obtained from the PI controller. The implementation of the moving average filter on the echo signal data will compare the second-order MAF and the fourth-order MAF. The results of the test show that the use of a digital filter makes the data smoother when compared to unfiltered data. Furthermore, the comparison of orders on the MAF filter has an impact on the filter response getting closer to the ideal characteristics if using a higher order.

Technological developments are so rapid and have an impact on all fields. For example in agriculture. The expert system is part of artificial intelligence (AI) which can be used in diagnosing diseases in corn plants. Corn is a food crop that can be found in Indonesia. Erratic season changes can trigger diseases in corn plants so that it becomes a problem for farmers. The problem that is often encountered by farmers is the difficulty in diagnosing the disease from the corn plant. Therefore an expert system will be built that aims to diagnose diseases in corn plants using the forward chaining method and mobile-based certainty factor. By using the forward chaining method and the certainty factor, the accuracy value obtained by the system for 25 times the testing process is 84% and makes this system good enough to use. The system is applied to a mobile-based application so that usage can be more efficient. [ABSTRACT FROM AUTHOR]