In the cultivation of swallow nests, swallow breeders experience problems, especially in maintaining the temperature and humidity of the room in the wallet bird house. Swallow breeders must be able to maintain a stable temperature and humidity and maintain the safety of the swallow from owl pests. When the temperature is hot, the swallow room will become dry so that the nest becomes damaged and the swallow feels uncomfortable living in the nest. Based on this, a control and monitoring system for swallow nest cultivation based on Android was created. This system can help reduce the temperature and humidity in the swallow nest room using a dew machine that works automatically and the swallow room door can open/close automatically using an application on a smartphone. This system can work well if given a supply voltage of AC220V and DC12V. The dew machine will work (ON) if the temperature is above 29°C or the humidity is less than 70%. The sensor read data will be sent by the NodeMCU to the blynk server and displayed on the smartphone. The swallow room door can be opened or closed based on the light intensity value measured on the LDR sensor which is then sent to the NodeMCU to drive the motor driver and stepper motor. With this system, farmers are expected to be able to monitor and control the condition of swallow’s nests using the blynk application on smartphones in real time.
Breast cancer has the largest prevalence in the world in 2020, with 2,261,419 cases or 11.7%. It is also the leading cause of cancer death, accounting for 6.9% of all cancer deaths. Asia and Indonesia have the greatest prevalence and mortality rates. This is an urgent issue that must be addressed. Ultrasonography (USG) is advised for assessing the features of breast nodules. Breast nodules on ultrasound pictures are interpreted using the Breast Imaging, Reporting, and Data System (BIRADS) category, which has five features. Yet, the probability of a False Positive Result (FPR) on ultrasound imaging is relatively high. Computer Aided Diagnosis (CAD) was created to reduce FPR. However, CAD research based on many BIRADS traits is currently margined. As a result, based on three BIRADS characteristics, namely the margin, posterior, and orientation aspects, this study aims to proposed the methode for diagnosing breast nodule malignancy. The proposed method consists of 4 stages, namely, pre-processing, automatic segmentation, features extraction, and classification. Pre-processing adaptive median filter maximum window size is 11 pixels, linear histogram normalizing, and Reduction Anisotropic Diffusion (SRAD) filter were used to construct the method. The neutrosophic watershed method was used in the suggested automatic segmentation. Based on the nodule's margin, orientation, and posterior, 10 features were proposed: nodule width, gradient, slenderness, margin sharpness, shadow indicators, skewness, energy, entropy, dispersion, and solidity. MLP is a classification approach. The test used 94 nodule pictures and yielded an accuracy of 88.30%, a sensitivity of 82.35%, a specificity of 91.67%, a Kappa of 0.7449, and an AUC of 0.865. As a result, it is feasible to conclude that the proposed method is capable of detecting malignancy in breast nodules in ultrasound images. To make the proposed method more reliable in the future, automatic RoI can be developed.
Meningkatnya kebutuhan akan informasi, pemantauan, dan pengendalian sistem monitoring terhadap peralatan, industri, otomotif, dan bahkan farmasi membuat teknologi monitoring secara real time dibutuhkan. Sistem Monitoring dirancang agar mesin produksi dapat dimonitor secara realtime, sehingga pengawasan suatu proses produksi menjadi effisien. Sistem ini memanfaatkan controller PLC (Programmable logic controller) sebagai pengatur dari sistem monitoring yang dikomunikasikan dengan Scada sebagai software untuk memproses data yang dihasilkan dapat ditampilkan melalui PC secara realtime. Implementasi dari Rancang Bangun Sistem Monitoring Prototype Mesin Packaging Berbasis PLC dapat menampilkan data dari waktu permesinan, dari Running time, Minor Stop Time dan Breakdown Time. Dimana klasifikasi waktu tersebut di buat secara otomatis sehingga dapat memudahkan para operator dalam mendata waktu permesinan dan memonitor kegiatan produksi me njadi lebih mudah dan terstruktur. Data dari PLC yang didapatkan akan ditransmisikan kepada Sercer OPC yang terhubung dengan SCADA Intouch Wonderware sebagai display untuk proyek akhir ini. Dari sepuluh kali pengambilan data, waktu running yang diterima dari PLC ke PC (Wonderware) dan sebaliknya dari PC (Wonderware) ke PLC sistem ini merespon dengan baik ketika fungsi dijalankan. Dimana terdapat perbedaan waktu atau delay sebesar 0,27s pada tombol ON dan 0,33s pada tombol OFF dengan penekanan dengan Software dan Hardware. Penekanan dengan software mendapatkan waktu tunda yang lebih besar dikarenakan melewati server dahulu untuk menghubungkan PLC ke PC (Wonderware). Kata kunci: PLC, Scada, Monitoring, Sistem, human error.
AbstrakTeknologi pengenalan wajah sudah banyak diimplementasikan dalam kehidupan sehari-hari. Untuk mendeteksi wajah pada suatu citra dibutuhkan kecepatan dan keakurasian yang cepat dan tepat. Salah satu metode pendeteksian wajah yang bisa digunakan adalah metode Viola Jones. Machine learning yang bisa diimplementasikan untuk metode ini adalah Adaboost dan SVM. Tujuan Penelitian ini adalah membandingkan kelebihan dan kekurangan dari 2 jenis machine learning tersebut. Hasil akurasi metode viola jones dengan machine learning Adaboost yaitu 90%. Total gambar yang digunakan adalah 50 dengan 30 sampel terdapat wajah dan 20 sampel yang tidak memiliki wajah. Sedangkan pada machine learning SVM tingkat keakurasian yang didapat yaitu sebesar 50%. Rata-rata waktu komputasi yang didapat pada metode AdaBoost sebesar 1,9s dan SVM sebesar 31,19s. Persentase nilai Sensitivitas metode AdaBoost didapat sebesar 86,66% dan SVM sebesar 80%. Nilai Spesifisitas untuk AdaBoost 95% dan untuk SVM yaitu 4,76% . Hal ini karena SVM menempatkan banyak sampel dalam kelompok yang ada wajah meskipun sampel tidak memiliki wajah. Sehingga penelitian ini menyimpulkan bahwa metode machine learning yang lebih efisien adalah dengan menggunakan metode AdaBoost. AbstractFace recognition technology has been widely implemented in everyday life. To detect faces in an image, speed and accuracy are needed quickly and accurately. face detection using face detection Viola Jones method. Machine learning used is Adaboost and SVM. The results in quite high accuracy in the viola jones method with the Adaboost machine learning that is 90%. from 50 experiments with 30 samples with faces and 20 samples without faces. Whereas in the machine learning SVM the level of accuracy obtained is equal to 50%. The average computing time obtained in the AdaBoost method is 1,9s and SVM is 31,19s. The percentage of the Sensitivity value of the AdaBoost method was 86,66% and SVM was 80%, and the Specificity value for AdaBoost was 95% while for SVM it was 4,76% because SVM placed many samples in groups with faces even though the sample had no faces. This indicates that a more efficient machine learning method is using the AdaBoost method.
Branching transformers are transformers located at the branching of the Medium Voltage (TM) network. The output from this transformer will be forwarded to the homes of the public/PLN customers. The loss of voltage in the branching transformer due to a disturbance in the electricity network cannot be known by PLN officers before receiving a report from the public, so the duration of the blackout is very long. This is certainly very detrimental to the community and PLN. Voltage Loss Detector is designed to detect loss/ready voltage on branching transformers. This tool uses a ZMPT101B voltage sensor to detect voltage, an Arduino uno microcontroller and a GSM SIM800L module to send messages. After testing, this tool successfully sends a message when the voltage is ready/loss. The voltage values read by the ZMPT101B sensor on the R, S and T phases are 223.36 volts, 222.02 volts and 220.18 volts, while the voltage using a multimeter measuring instrument is 223 volts, 222 volts and 220 volts. The highest time Delay in receiving messages in the room is 20 seconds. The highest time Delay in receiving messages outdoors is 15 seconds. The signal quality of the GSM SIM800L module will affect the Delay in receiving messages. With this tool, power outages in branching transformers will be immediately noticed by PLN officers for follow-up.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.