In recent times, particulate matter (PM2.5) is one of the most critical air quality contaminants, and the rise of its concentration will intensify the hazard of cleanrooms. The forecasting of the concentration of PM2.5 has great importance to improve the safety of the highly pollutant-sensitive electronic circuits in the factories, especially inside semiconductor industries. In this paper, a Single-Dense Layer Bidirectional Long Short-term Memory (BiLSTM) model is developed to forecast the PM2.5 concentrations in the indoor environment by using the time series data. The real-time data samples of PM2.5 concentrations were obtained by using an industrial-grade sensor based on edge computing. The proposed model provided the best results comparing with the other existing models in terms of mean absolute error, mean square error, root mean square error, and mean absolute percentage error. These results show that the low error of forecasting PM2.5 concentration in a cleanroom in a semiconductor factory using the proposed Single-Dense Layer BiLSTM method is considerably high.

Adequate air ventilation systems and maintaining environmental air quality are essential things that need to be considered to create an excellent industrial environment in a company. Operating or maintaining ecological air quality is a challenge for companies to optimize the existing work environment. Especially at the economic and business level in the company are facing the main problems. In this case, monitoring and predicting future air quality are needed to maintain air quality conditions. PM10 concentration, humidity, and temperature were used to predict annual and seasonal indoor air quality using a recurrent neural network (RNN) and long short‐term memory (LSTM). In this paper, we propose the IAQP method for air quality management systems that combines indoor air quality forecasting based on real‐time data. To measure indoor air quality, we predict the outcome from the IIoT sensor and LoRa sensor. The result of prediction is that the multilevel RNN model outperformed the LSTM, as the model demonstrated excellent results and feasibility.

System reliability is essential for improving operational efficiency and increasing revenue in the telecommunications sector. Recently, Machine Learning (ML) methodologies have shown significant promise in addressing system failures, network interruptions, and overall reliability challenges. Despite growing interest in this area, the broad scope of existing research can be overwhelming, making it difficult for novice researchers to identify key patterns, techniques, and gaps in the literature. This paper presents a comprehensive Systematic Mapping Study (SMS), covering 1,647 retrieved articles, revealed that research is heavily concentrated on fiber-based technologies (FTTH, PON, broadband) with limited focus on linking ML to enhance system reliability and to business outcomes such as churn and revenue. The Systematic Literature Review (SLR) applied a PRISMA-guided selection, resulting in 14 high-quality studies that were analyzed in depth. This review covers the period from 2019 to 2025, with particular attention to ML applications in network churn prediction, fault diagnosis, FTTH (Fiber to the Home) demand forecasting, system dependability, network optimization, and predictive maintenance. From the results of the SMS and SLR, we proceeded to the Latent Dirichlet Allocation (LDA) stage, where we categorized the findings into 10 emerging topics. Among these, four topics—Topic 2, Topic 3, Topic 6, and Topic 10—show notable upward trends. The paper concludes focus on High-Performance PON Systems and User-Centric Optical Networks. The taxonomy from this paper identified methodologies and an exploration of promising future research directions in ML for system dependability and network development, providing valuable insights for both scholars and practitioners.