Masalah dalam industri terkait kehilangan data suhu dan kelembaban sering terjadi akibat gangguan perangkat atau hilangnya koneksi. Data ini penting untuk menentukan kelayakan produk yang akan didistribusikan. Untuk mengatasi permasalahan tersebut, dikembangkan inovasi LSTM-IOT, yaitu perangkat IoT yang terintegrasi dengan model Long Short-Term Memory (LSTM) dalam arsitektur Environment Intelligence. Arsitektur ini telah dioptimalkan melalui eksperimen menggunakan berbagai jenis optimizer, seperti Adam, RMSprop, AdaGrad, SGD, Nadam, dan Adadelta. Dari hasil optimasi, kombinasi Nadam Optimizer dengan arsitektur terpilih menunjukkan kinerja unggul dengan nilai Mean Square Error (MSE) sebesar 5,844 x10⁻⁵, Mean Absolute Error (MAE) sebesar 0,005971, dan Root Mean Square Error (RMSE) sebesar 0, 007645. Arsitektur Environment Intelligence versi (a) dengan Nadam Optimizer terbukti paling efektif dalam memproses data sensor, sehingga dipilih untuk integrasi dengan perangkat LSTM-IOT. Implementasi LSTM-IOT dalam skenario dunia nyata dilakukan pada wadah web lokal yang memungkinkan akses real-time ke data suhu dan kelembaban di berbagai lokasi. Halaman web berbasis Streamlit ini menampilkan visualisasi data, performa LSTM, dan hasil prediksi. Uji fungsional menunjukkan bahwa LSTM-IOT memenuhi kebutuhan perusahaan, termasuk penyimpanan data dalam database internal serta prediksi kondisi lingkungan hingga 150 menit ke depan. Dengan fitur prediksi dan pemantauan yang canggih, perangkat ini memberikan solusi efisien dan bernilai tinggi bagi perusahaan dalam memantau kondisi lingkungan secara akurat dan proaktif. Abstract Problems in the industry related to temperature and humidity data loss are often caused by device interference or loss of connection. This data is important to determine the feasibility of the product to be distributed. To overcome these problems, an LSTM-IOT innovation was developed, namely an IoT device that is integrated with the Long Short-Term Memory (LSTM) model in the Environment Intelligence architecture. This architecture has been optimized through experiments using different types of optimizers, such as Adam, RMSprop, AdaGrad, SGD, Nadam, and Adadelta. From the optimization results, the combination of Nadam Optimizer with the selected architecture shows superior performance with a mean square error (MSE) value of 5.844 x 10⁻⁵, a mean absolute error (MAE) of 0.005971, and a root mean square error (RMSE) of 0.007645. The Environment Intelligence architecture version (a) with Nadam Optimizer proved to be the most effective in processing sensor data, so it was chosen for integration with LSTM-IOT devices. The implementation of LSTM-IOT in real-world scenarios is carried out on a local web container that allows real-time access to temperature and humidity data in various locations. This Streamlit-based webpage displays data visualizations, LSTM performance, and prediction results. Functional tests show that LSTM-IOT meets the needs of the company, including data storage in an internal database and prediction of environmental conditions for up to the next 150 minutes. With advanced prediction and monitoring features, these devices provide efficient and high-value solutions for companies to monitor environmental conditions accurately and proactively.
English
Masalah dalam industri terkait kehilangan data suhu dan kelembaban sering terjadi akibat gangguan perangkat atau hilangnya koneksi. Data ini penting untuk menentukan kelayakan produk yang akan didistribusikan. Untuk mengatasi permasalahan tersebut, dikembangkan inovasi LSTM-IOT, yaitu perangkat IoT yang terintegrasi dengan model Long Short-Term Memory (LSTM) dalam arsitektur Environment Intelligence. Arsitektur ini telah dioptimalkan melalui eksperimen menggunakan berbagai jenis optimizer, seperti Adam, RMSprop, AdaGrad, SGD, Nadam, dan Adadelta. Dari hasil optimasi, kombinasi Nadam Optimizer dengan arsitektur terpilih menunjukkan kinerja unggul dengan nilai Mean Square Error (MSE) sebesar 5,844 x10⁻⁵, Mean Absolute Error (MAE) sebesar 0,005971, dan Root Mean Square Error (RMSE) sebesar 0, 007645. Arsitektur Environment Intelligence versi (a) dengan Nadam Optimizer terbukti paling efektif dalam memproses data sensor, sehingga dipilih untuk integrasi dengan perangkat LSTM-IOT. Implementasi LSTM-IOT dalam skenario dunia nyata dilakukan pada wadah web lokal yang memungkinkan akses real-time ke data suhu dan kelembaban di berbagai lokasi. Halaman web berbasis Streamlit ini menampilkan visualisasi data, performa LSTM, dan hasil prediksi. Uji fungsional menunjukkan bahwa LSTM-IOT memenuhi kebutuhan perusahaan, termasuk penyimpanan data dalam database internal serta prediksi kondisi lingkungan hingga 150 menit ke depan. Dengan fitur prediksi dan pemantauan yang canggih, perangkat ini memberikan solusi efisien dan bernilai tinggi bagi perusahaan dalam memantau kondisi lingkungan secara akurat dan proaktif. Abstract Problems in the industry related to temperature and humidity data loss are often caused by device interference or loss of connection. This data is important to determine the feasibility of the product to be distributed. To overcome these problems, an LSTM-IOT innovation was developed, namely an IoT device that is integrated with the Long Short-Term Memory (LSTM) model in the Environment Intelligence architecture. This architecture has been optimized through experiments using different types of optimizers, such as Adam, RMSprop, AdaGrad, SGD, Nadam, and Adadelta. From the optimization results, the combination of Nadam Optimizer with the selected architecture shows superior performance with a mean square error (MSE) value of 5.844 x 10⁻⁵, a mean absolute error (MAE) of 0.005971, and a root mean square error (RMSE) of 0.007645. The Environment Intelligence architecture version (a) with Nadam Optimizer proved to be the most effective in processing sensor data, so it was chosen for integration with LSTM-IOT devices. The implementation of LSTM-IOT in real-world scenarios is carried out on a local web container that allows real-time access to temperature and humidity data in various locations. This Streamlit-based webpage displays data visualizations, LSTM performance, and prediction results. Functional tests show that LSTM-IOT meets the needs of the company, including data storage in an internal database and prediction of environmental conditions for up to the next 150 minutes. With advanced prediction and monitoring features, these devices provide efficient and high-value solutions for companies to monitor environmental conditions accurately and proactively.
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.