Perbandingan Kinerja Akurasi Klasifikasi K-NN, NB dan DT pada APK Android

et al. 2023

Internal Combustion Engines are known for their unique sound characteristics. Through these sound characteristics, an experienced car mechanic will be able to diagnose the type of engine damage just by listening to the sound. This reduces the need to disassemble components to pinpoint machine faults which also contributes to a significant reduction in overall repair time. The main aim of this paper is to build a process to identify faulty machines through engine noise analysis with visual data to determine machine faults at an early stage. By capturing various types of engine sounds, data visualization uses healthy engine sounds and broken engine sounds obtained from cars as well as various types of broken engine sounds that are usually found in vehicles. This audio data will be used in audio signal processing combined with a linear regression classification algorithm. Visualization data can distinguish various types of sounds that are commonly found in damaged or damaged engines such as clicks, ticks, knocks and other types of sounds to determine the types of damage that are usually found in internal combustion engines. The data used comes from Kaggle, which is public data which is widely used as general data for data science activities. Visually, data from vehicle engines can be seen from the data on which car brand is the best in terms of sound. The results using linear regression show the R-squared score (R^2) or also called the coefficient of determination reaching 91.95%.

Section: Resultsmentioning

confidence: 99%

Diagnostic on Car Internal Combustion Engine through Noise

Sjah

Rahman

et al. 2023

“…Supervised machine learning, unsupervised machine learning and reinforcement learning. Supervised learning machines such as Support vector machines (Hindarto, 2022), Decision Trees, Logictic Regression are discussed in this research.…”

Section: Methodsmentioning

confidence: 99%

Supervised Learning from Data Mining on Process Data Loggers on Micro-Controllers

Saputra

Haryono

2023

In processing data science, data is needed as input. Sometimes the data needed does not exist in public data, this is where the purpose of this research is made. The acquisition process is so important to process information into data. After that, the data is processed to make a decision. Micro-controller in controlling conditions, such as temperature, and humidity are very common devices, and a lot of research has been done. Sometimes discussing it only shows how to create a series and save it on online platforms, such as firebase, tinger.io, and many others online platforms. So that the process of storing data on an external or online platform is an advantage for platform providers, where platform providers do not need to do business and get data for free. This is without realizing the researchers who have produced a micro-controller device. Many platforms for storing data range from hardware and software devices. Some devices are paid or open source. This research uses software tools that are open source. Because using open source-based tools it will be easy to develop and for further research purposes. The development of the following research by entering code into a micro-controller system or what is called an embedded system. Data is a very valuable asset. Because data is one of the most important components in processing in data science. And it is better to take care of the data logger. This research uses Arduino as a micro-controller and ultrasonic distance sensor and potentiometer

“…3. The Application Framework (Hindarto, 2022) is a set of components that enable the development of Android applications. This framework consists of various features such as network management, database management, and window management.…”

Section: Methodsmentioning

confidence: 99%

Smartphone Application for Support Library Operations in the Internet of Things Era

Hadianto

Santoso

2023

The library can be referred to as a storage place for books and other references. The reference can be in the form of digital storage media. Libraries if not managed properly will cause chaos in the library organization. Many books were lost due to the entry and exit of books that were out of control. Currently, the library is not only a place to store books but can be maximized by managing and adding other digital devices. The use of Radio Frequency Identification (RFID) in libraries adds sophistication to the management of books and library items. In addition, currently many libraries have taken advantage of Internet of Things Technology, by adding various sensors and integrating with cloud-based storage devices. It provides a service that makes it easy for library members to find and track the current whereabouts of books. This research does not only create a library by providing hardware in the form of sensors to be installed in the library. This paper also proposes the use of smartphones as an alternative in replacing sensor hardware. This study uses a QR Code sensor to match the book you are looking for and simulates dancing a book in blocks and bookcases. with augmented reality. The purpose of this research is to make a smart library prototype to make it easier for library members to find books or other references. The results of the experiment to find books and DVDs that have been carried out achieve an accuracy of 83.33%.