Unmanned System for Gasoline Level Monitoring Paputungan, Irving V; Dhiaulhaq, Faiz; Oktiawati, Unan Y ...
Journal of physics. Conference series,
07/2021, Volume:
1969, Issue:
1
Journal Article
Peer reviewed
Open access
Abstract
In order to ensure the remaining volume of liquid inside a tank that is normally checked manually and frequently, an unmanned monitoring system is proposed. The proposed system is developed ...based on the concept of Internet of Things (IoT). This paper presents a prototype for tank level monitoring. The prototype utilises SRF HC-SR04 sensor to measure the liquid level. Arduino Uno microcontroller is implemented to assist the data processing before any notification is sent to the user. The remaining liquid volume and LED notification are shown as the output of the prototype. Some testing have been conducted to observe if the prototype works fine and to measure any error during implementation. Result shows that the relative error is less than 2% and the standard deviation is less than 5%.
The need for disaster preparedness becomes very important in Indonesia. Due to its geographical situation, within a ring of fire, Indonesia is prone to several disasters such as earth-quake and ...volcano eruption. This paper presents the design of a context-aware system to pre-emptively notify and provide some information to the population around Merapi volcano. The information contains some dangerous area and safe-place/shelter based on the user location. The proposed design can also notify the level of danger that might be encountered by the user and the mitigation path within a certain distance.
There is a healthcare program in Indonesia called Pos Pelayanan Terpadu (Posyandu). Services such as nutritional counselling, immunization service, health education and birth preparedness are ...conducted in the program. All the information collected form such program is still in paper-based document, called Kartu Menuju Sehat (KMS). A development of an electronic KMS (e-KMS) is proposed. This paper presents several related works on e-KMS for Indonesia. This paper derives requirements towards the most workable features for e-KMS based on the literatures.
This paper presents a design of Telegram bot to support Campus information sharing. The communication method used is Webhooks. Webhooks is able to provide zero latency and handle multiple requests ...concurrently during communication within the Telegram bot. Such bot serves the information via specific commands. The Telegram bot prototype shows that even though Webhooks is able to provide information as requested, Webhooks setting is difficult and trickier.
Broiler chicken is a livestock that is characterized by fast growing. Temperature and humidity become the most important factors during their growth. Unmonitored and uncontrolled temperature and ...humidity within the cage can lead to reduced productivity and high rate of mortality. This paper presents a prototype that is able to monitor such factors automatically. A prototype of sensor using DHT11 and Arduino DUE microcontroller has been developed. Android-based app is deployed to support the prototype. A web-based application is also built to show the monitoring result comprehensively. The result shows that the sensor is able to continuously capture the current temperature and humidity of the chicken cage for some periods. After the implementation, the number of death chicks are decreasing from 5 to 4 chicks per day. Controlling both factors will be the future work.
An unmanned monitoring system is proposed in order to ensure the remaining volume of fluid inside a tank. Internet of Things (IoT) concept is used when developing such system. IoT device has been ...known able to support faster and more efficient procedure in any automatic monitoring. Arduino-based microcontroller is implemented as the main IoT component. In order to communicate within the network system, the proposed IoT uses a data transfer protocol. This paper presents a comparison between Message Queuing Telemetry Transport (MQTT) protocol and Hyper-Text Transfer Protocol (HTTP). The comparison is based on the Quality of Service (QoS) parameters that are captures during data transmission from the IoT device to the server using certain standards for both protocols. Data transmission and retrieval shall not be affected by the environment, be free from error and the data is not broken or lost. Delay, Throughput, Packet Loss, and Packet Delivery are the QoS parameters used in the testing. The experiment was conducted for 6 days. Based on the results comparison, it can be concluded that the perfomance of MQTT protocol is far better than HTTP for each parameters. That is the reason why MQTT is more suitable to support Arduino-based IoT device to monitor fluid volume.
Person's emotions can be observed from their facial expressions. When a person feels certain emotions, his/her facial expression will usually change, such as wrinkles on the forehead, blinking of the ...eyes, or changes in the color of the facial skin. This paper describes how to use the Convolutional Neural Network (CNN) to identify a person's emotions based on facial expressions observed in facial images. CNN is part of deep learning method that is widely used to analyze information from images and often gives good results. Three different datasets, Facial Expression Recognition 2013 (FER2013), Cohn-Kanade Dataset (CK+), and Karolinska Directed Emotional Faces (KDEF), were used to build and test the CNN model. Such datasets contain some grayscale images in jpeg format and has been labeled with seven emotion classes (Anger, Disgust, Fear, Happy, Sad, Surprise, and Neutral). In order to detect the seven classes of emotions, the CNN architecture was built using four convolution layers and two fully connected layers. During testing, the highest performance was achieved by the KDEF dataset with an Accuracy of 0.82, Precision 0.84, Recall 0.82, and F1-score 0.81. The most easily recognizable emotion classes are Disgust and Happy, while the emotion class that is most difficult to recognize is Sad.
SLA is a contract between service providers and consumers, mandating specific numerical target values which the service needs to achieve. For service providers, detecting and preventing SLA violation ...becomes very important to enhance customer trust and avoid penalty charges. Therefore, it is necessary for providers to detect and forecast possible service violations. However, this is difficult to achieve when dealing with service violation in a cloud-based system due to multiple Quality of Service (QoS) parameters. In this work, manifold learning is used to reduce the high dimensionality problem arising from multiple QoS data into 1-D output of violation level (low, medium, high) data. From the transformed data, service violation will be detected as well as predicted based on violation level data. The violation level is obtained from aggregate value of each QoS weightage. Based on QoS data of 14 days, manifold learning is able to scale down 5 various parameters into a single parameter before detection and prediction process is performed. The prediction accuracy of Support Vector Regression as the time series analysis technique used is able to achieve 80%.
PDF
