A good condition of road was very needed by the people, because the movement of goods and services, and also a lot of people activities is indirectly depending on the road condition. So for keeps the road on good quality, early detection of road damage, especially pothole must be held. This thing is very important because a small damage that is not immediately handled can be large, so that the danger will decreased. It also make the cost that needed for repair it become greater. In the other hand, detecting road damage cannot be done with a manual checking, because it will take a lot of time and money. So supporting technology is needed to detect this kind of roads hazard. One of the technology easily used to detect road damage is computer vision. In this research, we build a system that can detect a pothole on the road which is captured by the camera. The camera used here is a wireless portable camera. Also for the location tagging, the GPS sensor is used here. The vision object detection system using imageZMQ library for stream the frames and process it in the processor PC. The capturing and streaming activity performed very well from the mini portable computer camera which is attached in the vehicle. the next step of this research is making the detection performed well in the more robust computational device.
1 January 2022 in International Journal of Information and Education Technology
Technological developments have a positive impact on humans to improve their abilities in line with innovations in the field of education which are increasing day by day. One of them is by increasing intelligence through collaboration between humans and technology called augmented intelligence. In this study augmented intelligence is applied to assist humans in studying human anatomy by utilizing augmented reality technology to perform motion tracking that can control 3D assets to follow it. The anatomy learning platform that was built was named AIVE (Artificial Intelligence on Virtual Education) with an architectural system consisting of a frontend for interface needs and AR platform development, there is also a backend for streaming databases and AI algorithms. Measurement of satisfaction and interest based on the PIECES framework is also carried out to determine the user’s response to the platform being built. The results show a satisfaction level of 4.12 and an interest of 4.10 which means that users are satisfied and interested in the human anatomy tracking platform that is accessed via smartphones.
1 December 2018 in TELKOMNIKA (Telecommunication Computing Electronics and Control)
The digestive system is a vital organ, considering its function in processing food and drinks that are consumed every day so it is very important to be maintained. But sometimes people have a lack of awareness and knowledge of the initial symptoms of digestive diseases so that being a factor causing the disease to be serious can even cause death. Identification of symptoms as early as possible is very important for the diagnosis process so that immediate control measures can be taken to prevent and overcome the spread of disease. Anamnesis process is needed to get the symptoms of the disease, question and answer process between the patient and medical personnel whose results are stored in the Electronic Medical Record (EMR) in the form of narration to assist in the process of Clinical Decision Support (CDS). EMR is often difficult to do computing processing due to inappropriate grammar. For computers to process natural languages, Natural Language Processing (NLP) is used. In this study, an NLP system was created that can identify symptoms of the digestive disease by using to optimize the CDS process. The method used to identify symptoms of the disease is Named Entity Recognition (NER), which determines which tokens are included in the symptoms of the disease. The model trained with 800 epochs produces f1-score accuracy of 0.79. Experimental results show that the NER process supported by stemming and removing stopwords in pre-processes can improve system accuracy.
Introduction: A lot of hospital management systems, especially open-source ones, still lack interoperability which is holding back the effectiveness of administration. This happens due to different regulations from hospital organizations. Therefore, there must be a system that facilitates interoperability. Blockchain is a decentralized ledger system, to insert the data from the blockchain all parties must agree that the data is valid thus the data can be inserted so, all the data are immutable thus every change can be audited. Methods: We integrate the Hyperledger fabric network, an open-source modular blockchain platform, into an open-source hospital management system, openEMR. We take the changed data using debezium connect and Kafka and inserted it into the blockchain. Results: Based on our test, we managed to get average read latency at 27ms, average read throughput at 36 Read per Second, average transaction latency at 45ms, average transaction throughput at 22 Transaction per Second, and average integrated system data transfer at 111.36ms. Conclusions: All services deployed successfully at the Kubernetes without any error. All services work as they should be. One service can integrate through the internal network of the Kubernetes and from the outside cluster using ingress. OpenEMR can be used normally as indicated in the official documentation and the data change is stored in the blockchain.
The need for a better online water quality monitoring system to control and provide drinking water treatment processes is proven. Water utility company in Surabaya that called as PDAM Surabaya has few reservoirs in their water supply system which are being monitored by WTW IQ SensorNet 2020 XT. However, on that sensor devices while it can provide some of the water quality parameters value information but the sensor is passive and the internal data is still stored in the sensor itself. To solve the problem, we proposed an application of data logger to manage data collections online water quality monitoring system by using web scraping. This application built by using Python language, the application is able to collect data from the sensor by using web scraping. We have utilized Beautiful Soap library and store the data in SQL. In these research, our experiment shows the performance of the application by measuring the accuracy of data that has been scraped from sensors are around 99%, the error rate less than 1%, and MSE (Mean Square Error) around 0.35%. We also calculated the growth of the data size that is gradually increasing and also measured the correlation between the data size with the delay which shows the value of our data is around 0.0000002739. Its means that our application is able to work in real-time and the delay is not affected by the size of data.