scholarly journals Pengembangan Smart Home System Berbasis Kecerdasan Buatan untuk Memanajemen Konsumsi Energi Rumah Tangga dengan Pendekatan Finansial

2021 ◽  
Vol 4 (1) ◽  
pp. 1-10
Author(s):  
Ihsan Auditia Akhinov ◽  
Muhammad Ridwan Arif Cahyono
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Internet Of Things ◽  
Smart Home ◽  
Web Server ◽  
Black Box ◽  
Raspberry Pi ◽  
Artificial Neural ◽  
Online Web

Teknologi rumah pintar yang dikembangkan saat ini belum sepenuhnya mampu mendukung program konservasi energi yang dicanangkan pemerintah. Selain Saat ini kontrol untuk pengaturan rumah pintar masih dilakukan secara manual, belum sepenuhnya otomatis. Pada penelitian ini akan dibangun sistem rumah pintar yang dikendalikan oleh kecerdasan buatan untuk mengendalikan pemakaian energi berdasarkan besaran nilai tagihan bulanan. ESP32 digunakan sebagai perangkat Internet of Things (IoT) yang berfungsi mendeteksi keberadaan manusia dan mengukur energi listrik yang dikonsumsi. Data-data tersebut disimpan dalam online web server yang dibangun dari Raspberry Pi. Sistem ini dapat dimonitor dan dikendalikan oleh aplikasi berbasis Web. Aplikasi ini sudah diuji dengan menggunakan metode Black Box, hasilnya 100% aplikasi berjalan lancar. Artificial Neural Network diimplementasikan menggunakan bahasa Python, dengan 4 input, 2 layer, dan 4 output dimana masing-masing layer terdiri dari 4 neuron. Variabel masukan yang digunakan dalam ANN yaitu intensitas cahaya, temperatur ruangan, durasi waktu penggunaan ruangan, dan target biaya bulanan, sedangkan keluaran dari ANN ini yaitu durasi penggunaan peralatan listrik, dalam purwarupa ini yaitu durasi penggunaan AC, TV, refrigerator, dan lampu. Sistem sudah mampu berjalan dengan baik, mampu memberikan rekomendasi durasi maksimal penggunaan peralatan listrik dengan tingkat kesalahan sebesar 1,64%.

scholarly journals Desain Sistem Informasi Cerdas pada Smart Grid Berbasis Internet of Things dan Artificial Neural Network

2021 ◽  
Vol 4 (1) ◽  
pp. 11-19
Author(s):  
Muhammad Ridwan Arif Cahyono ◽  
Surya Wirawan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Internet Of Things ◽  
Smart Grid ◽  
Black Box ◽  
Raspberry Pi ◽  
Mean Square ◽  
Layer Neuron ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Smart grid merupakan sistem kelistrikan yang memungkinkan pengguna untuk melakukan proses menjual dan membeli daya listrik. Pada penelitian ini dirancang model smart grid dengan sumber daya dari listrik PLN dan panel surya yang terhubung dengan beban. Beban yang digunakan memiliki daya maksimal 40 W dan panel surya yang digunakan memiliki kapasitas 100 Wp. ESP32 digunakan sebagai perangkat Internet of Things, yang digunakan sebagai pengukur dan pengontrol daya listrik yang akan dijual atau dibeli. Raspberry Pi digunakan sebagai web server pengolah data dari smart grid. Aplikasi “Smart Grid Dikti” merupakan aplikasi berbasis android yang dapat digunakan untuk melakukan pemantauan serta pengaturan dalam sistem smart grid tersebut. Aplikasi android tersebut telah diuji coba dengan metode Black Box, dengan hasil pengujian 100% berhasil. Kecerdasan buatan berbasis Artificial Neural Network (ANN) dengan metode backpropagation diimplementasikan dalam sistem smart grid yang berfungsi sebagai pengaturan otomatis dalam proses jual dan beli daya listrik. ANN yang digunakan memiliki 3 input, 2 layer neuron, 3 output, dan masing-masing layer memiliki 4 neuron yang diimplementasikan ke dalam bahasa Python. Setelah pelatihan sebanyak 11.000 kali, didapatkan Root Mean Square  Error (RMSE) sebesar 0,12151 dan pada saat uji coba didapatkan RMSE sebesar 0,10500 dengan akurasi rata-rata sebesar 89,50%.

scholarly journals Feature Selection for Health Care Costs Prediction Using Weighted Evidential Regression

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4392
Author(s):  
Belisario Panay ◽  
Nelson Baloian ◽  
José A. Pino ◽  
Sergio Peñafiel ◽  
Horacio Sanson ◽  
...  
Keyword(s):  
Neural Network ◽  
Health Care ◽  
Artificial Neural Network ◽  
Health Care Costs ◽  
Black Box ◽  
Health Costs ◽  
Gradient Boosting ◽  
Healthcare Budget ◽  
Artificial Neural ◽  
Care Costs

Although many authors have highlighted the importance of predicting people’s health costs to improve healthcare budget management, most of them do not address the frequent need to know the reasons behind this prediction, i.e., knowing the factors that influence this prediction. This knowledge allows avoiding arbitrariness or people’s discrimination. However, many times the black box methods (that is, those that do not allow this analysis, e.g., methods based on deep learning techniques) are more accurate than those that allow an interpretation of the results. For this reason, in this work, we intend to develop a method that can achieve similar returns as those obtained with black box methods for the problem of predicting health costs, but at the same time it allows the interpretation of the results. This interpretable regression method is based on the Dempster-Shafer theory using Evidential Regression (EVREG) and a discount function based on the contribution of each dimension. The method “learns” the optimal weights for each feature using a gradient descent technique. The method also uses the nearest k-neighbor algorithm to accelerate calculations. It is possible to select the most relevant features for predicting a patient’s health care costs using this approach and the transparency of the Evidential Regression model. We can obtain a reason for a prediction with a k-NN approach. We used the Japanese health records at Tsuyama Chuo Hospital to test our method, which included medical examinations, test results, and billing information from 2013 to 2018. We compared our model to methods based on an Artificial Neural Network, Gradient Boosting, Regression Tree and Weighted k-Nearest Neighbors. Our results showed that our transparent model performed like the Artificial Neural Network and Gradient Boosting with an R2 of 0.44.

scholarly journals Security-Aware Routing Protocol Based on Artificial Neural Network Algorithm and 6LoWPAN in the Internet of Things

2022 ◽  
Vol 2022 ◽  
pp. 1-8
Author(s):  
Jiangdong Lu ◽  
Dongfang Li ◽  
Penglong Wang ◽  
Fen Zheng ◽  
Meng Wang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Internet Of Things ◽  
Routing Protocols ◽  
Intelligent Systems ◽  
Smart Devices ◽  
The Internet ◽  
Routing Mechanism ◽  
Artificial Neural ◽  
The Internet Of Things

Today, with increasing information technology such as the Internet of Things (IoT) in human life, interconnection and routing protocols need to find optimal solution for safe data transformation with various smart devices. Therefore, it is necessary to provide an enhanced solution to address routing issues with respect to new interconnection methodologies such as the 6LoWPAN protocol. The artificial neural network (ANN) is based on the structure of intelligent systems as a branch of machine interference, has shown magnificent results in previous studies to optimize security-aware routing protocols. In addition, IoT devices generate large amounts of data with variety and accuracy. Therefore, higher performance and better data handling can be achieved when this technology incorporates data for sending and receiving nodes in the environment. Therefore, this study presents a security-aware routing mechanism for IoT technologies. In addition, a comparative analysis of the relationship between previous approaches discusses with quality of service (QoS) factors such as throughput and accuracy for improving routing mechanism. Experimental results show that the use of time-division multiple access (TDMA) method to schedule the sending and receiving of data and the use of the 6LoWPAN protocol when routing the sending and receiving of data can carry out attacks with high accuracy.

Low‐Power Self‐Rectifying Memristive Artificial Neural Network for Near Internet‐of‐Things Sensor Computing

2021 ◽  
pp. 2100050
Author(s):  
Seok Choi ◽  
Yong Kim ◽  
Tien Van Nguyen ◽  
Won Hee Jeong ◽  
Kyeong‐Sik Min ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Internet Of Things ◽  
Low Power ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document