Auto Hyperparameter Tuning Approach for Connection of Industrial IOT 4.0 Devices Using Long Short-Term Memory (LSTM) Classification Approach

• Published in: 2024 3rd International Conference for Innovation in Technology (INOCON) pp. 1 - 5
• Main Authors: Garg, Kaushiv, Singh Gill, Kanwarpartap, Aggarwal, Priyanshi, Singh, Mukesh, Banerjee, Deepak
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-03-2024
• Subjects: Algorithms; Computational modeling; Data models; Deep learning; Heating systems; Indexes; IOT; LSTM; Machine Learning; Optimization; Temperature measurement; Temperature sensors; Time series analysis
• DOI: 10.1109/INOCON60754.2024.10511754

Improving how well a machine learning model works is very much based on adjusting the hyperparameters. LSTM networks are used a lot in predicting sequences and analyzing time series. They are a type of recurrent neural networks. This work shows a way to make the process of finding the best settings for a computer model more automatic. It pays close attention to LSTM models. We will find the most important settings for our model, like how fast it learns, how many data points it looks at once, and other important numbers. Then we will decide the range of values to look at for each of these settings. This article talks about Industry 4. 0 and how it is being used with the Industrial Internet of Things (IIoT) 4. 0This is changing how companies monitor and maintain their systems. The Heat Index is important because it tells us how hot it feels outside when we combine the temperature and humidity. It is used in farming, predicting the weather, checking the soil, keeping machines working, and running data centers. It is important to use smart and flexible ways to look at Heat Index data so we can find patterns and useful information that will help us make good decisions. This study says we should use advanced methods to analyze data in the context of Industrial Internet of Things (IIoT) 4. 0It focuses on the importance of Heat Index data and how flexible it is. It shows how we can use this information to make things better in different industries. This study shows that using automated hyperparameter tweaking for LSTM models works well.