CHIPSET

Periodontal Disease Detection with Machine Learning Technology From Radiographic Images : An Interdisciplinary Study Of Dentistry and Computer Science

Yusra Fadhillah — 2024-10-31

This study aims to evaluate the effectiveness of the Convolutional Neural Network (CNN) model in identifying periodontal disease using dental images. With the applied method, the CNN model was trained using a dataset consisting of 40 dental images and tested on 55 images to evaluate its ability to classify the images as healthy or periodontal. The evaluation results showed that the CNN model achieved an overall accuracy of 91.16%. The model precision for healthy images reached 92.39%, while the precision for unhealthy images was 91.05%. Recall sensitivity for healthy images is 91.16%, and for F1-Score images is 91.07%. The data shows that the model has better performance in identifying healthy images compared to periodontal images. To improve the performance of the model, data augmentation techniques such as rotation, flipping, and scaling were applied, which gave a slight improvement to the results. However, the limited size of the dataset seems to be an obstacle in achieving higher accuracy. Therefore, this study recommends expanding the dataset size and applying more complex model architectures or transfer learning techniques to improve detection performance. The conclusion of this study shows that CNN models have potential for periodontal disease detection, but need further development to improve accuracy and reliability. This research contributes to the development of medical detection technology and opens a path for further research in improving periodontal disease detection systems using CNN technology.

RANCANG BANGUN ALAT UKUR KUALITAS TANAH UNTUK REKOMENDASI TANAMAN BERBASIS MIKROKONTROLER

Yuni Anggraini — 2024-10-31

Indonesia is known as an agrarian country which is very suitable as a farming area. In farming, of course, many factors affect the growth and development of planted plants. One of the factors that influence this is soil quality. Therefore, research was conducted to make design a soil quality measuring instrument for microcontroller-based plant recommendations. The purpose of this design is that the system can measure soil quality and send measurement information and recommend plants that are suitable for planting on a particular land through the Android application. This soil quality measuring device uses an ESP32 microcontroller equipped with Wifi, a DS18B20 sensor, a Soil Moisture sensor, and a soil pH sensor. The system performs input processing using the Tsukamoto fuzzy logic method. Where the results obtained in this design test are the system can send the results of soil quality measurements and recommendations for suitable plants to be planted then can send measurement information and recommendations through the Android application. So it can be concluded that the soil quality measurement tool for recommending plants can work well and has fulfilled the purpose of making this tool.

Prototype Pendeteksi Kebakaran Hutan Berbasis Internet

Gizan Guswan — 2024-10-31

Astimesadvance,forestsareincreasinglythreatenedanddamaged,oneofwhichisforest fires.Forestfiresoccurduetotwofactors:naturalfactorsandhumanfactors.Naturalfactorscausingforest fires include climate change and rising temperatures. Another factor is human activitythat damages forests for purposes such as industrial interests and land expansion. Currently,forest fires have been designated as a national natural disaster by the government because theyhave caused significant losses across various sectors. Forest fire management is generallyconducted through firefighting and post-fire handling, alongside prevention campaigns aimedat discouraging forest burning among communities. Early warning systems and detection arecrucialforforestfireprevention. Thetechnicalaspectissupportedbygovernmentinfrastructuresuch as observation towers to monitor fire-prone areas. Forest or peatland fires can start fromsmall ignition points and escalate into large blazes. During Indonesia's dry seasons, numerousignitionpointstypicallyoccurinKalimantanandSumatra,fueledbydrygrass,wood,andotherflammable materials. To identify fire-prone areas, the Keetch-Byram Drought Index method iscommonly used. This method assesses fire hazard based on dryness levels in specific regions.Accurate analysis helps prevent and manage land fires effectively. Regular education andoutreachprogramsareessentialtoraiseawarenessamongthepublicaboutthedangersofforestfires,preventionmethods,andproperfiremanagement.Theseeffortsaimtoincreasecommunity involvement in forest conservation. Furthermore, education serves as a means todemonstratepracticalfirefightingtechniquesandstrategiesdirectlyinthefield."

Alat Filling Adonan Cair Otomatis Untuk UMKM Berbasis Mikrokontroler

Hana Putri Ariyadi — 2024-10-31

Alat ini dirancang untuk mendukung kegiatan produksi pada UMKM, terutama dalam bidang pembuatan kue yang melibatkan adonan cair dalam produksinya. Seringkali pemilik usaha kue tersebut mengalami kerugian. Kerugian tersebut disebabkan oleh pengisian adonan yang kurang tepat karena dilakukan secara manual sehingga adonan tersebut memiliki ukuran yang tidak sama. Dengan menggunakan sensor dan komponen elektronik seperti mikrokontroler, pompa diafragma, dan sensor water flow, alat ini mampu memastikan isi atau volume adonan yang dikeluarkan sama pada setiap cetakan, sehingga dapat mengurangi risiko kerugian akibat ukuran kue yang tidak sama besar. Alat ini diharapkan dapat menjadi solusi dalam mengatasi ketidaktepatan saat pengisian adonan cair secara manual, sehingga kue yang dihasilkan sama besar untuk setiap cetakannya. Pengujian alat menunjukkan bahwa alat mampu bekerja pada adonan yang memiliki niali viskositas sekitar 1500-3000 cP. Alat ini dapat mengisi adonan sama banyak dengan rata-rata persentase keberhasilan 98,46% dengan 4 nilai viskositas yang berbeda.

RANCANG BANGUN ALAT PELATIHAN PARKIR MOBIL BERBASIS MIKROKONTROLER

Gery Adnediel — 2024-10-31

The increasingly limited parking area certainly requires someone to be more proficient in parking a car. Arduino is an electronic board device equipped with open source software, where this device is included in the ATMega microcontroller family and functions as a single-board microcontroller designed to facilitate the use of electronics in various fields released by Atmel. The ultrasonic sensor HC-SR04 is an ultrasonic sensor that works like a sonar system on Bats and Dolphins where in this sensor there is a sender and receiver, this sensor has a range specification of 2 cm - 400 cm with a resolution of 0.3 cm, and an angle range of less than 15 degrees. To prevent failure or mistakes when parking a car usually takes longer to learn than learning to drive a car itself. LCD (Liquid Crystal Display) functions as a display medium that uses liquid crystals as a display of data, characters, letters and graphics.

Design Of A Portable Mini Pump It Up System Based On Mini Computer For Children's Gross Motor Improvement

Lucky Prima — 2024-10-31

The increasing influence of smartphones on young children has raised concerns about the delayed development of gross motor skills, particularly in early childhood. This issue is significant in Indonesia, which ranks fifth in ASEAN for birth rates, resulting in a large population of children at risk. Excessive smartphone use by children leads to decreased physical activity, potentially causing health problems such as obesity and reduced physical fitness.

The objective of this study is to design and develop a portable system, called the "Mini Pump It Up," based on a mini-computer (Raspberry Pi 5), that encourages children to engage in more physical activities. This device is intended to divert children from excessive smartphone usage, thereby stimulating their gross motor skills development. Additionally, the system is designed to be used anywhere without requiring an external power source.

The research concludes that the system successfully operates in portable mode without the need for a power supply, sustaining functionality for 3 hours, 10 minutes, and 15 seconds. Furthermore, the system effectively captures the interest of children, as evidenced by 84.21% of the 19 children participants choosing to interact with the product instead of engaging with smartphones.