With the growth of modern lifestyles and the growing urbanization and reliance on fossil fuels, the need for tracking and monitoring air pollution has become more significant. This research used existing information on significant pollutants to forecast their future condition using time-series modeling. Most studies have used Autoregressive Integrated Moving Average (ARIMA) and Logistic Regression (LR) methods to analyze time-series data. Still, employing an Adaptive Neuro Fuzzy Inference System (ANFIS) for this purpose has been infrequent. Conventional time-series prediction approaches use the assumption that there is a linear connection among variables. However, in air pollution modeling, there are non-linear and intricate factors. This paper used an Adaptive Network Fuzzy Inference System with the help of Improved Genetic Algorithm (ANFIS-IGA) to predict air pollution. This work aimed to address this constraint by enhancing the precision of everyday air pollutant prediction via the analysis of time-series data using ANFIS modeling. Air pollution data, including Fine Particulate Matter (FPM), CO, SO2, O3, and NO2, is gathered from the Air Quality Open Data Platform. This research examines the surveillance and prediction of air pollution concentration in indoor and outdoor situations using the ANFIS-IGA model. The model's effectiveness was enhanced and optimized for using IGA. The results indicate that the proposed ANFIS-IGA framework achieved superior performance compared to other models, as shown by the Root Mean Square Error (RMSE) value of 0.052658.

IoT is becoming increasingly popular due to its quick expansion and variety of applications. In addition, 5G technology helps with communication and network connectivity. This work integrates C-RAN with IoT networks to provide an experimental 5G testbed. In a 5G IoT environment, this experience is utilized to enhance both perpendicular and flat localization (3D localization). DRCaG, an acronym for the proposed model, stands for a deep, complicated network with a gated layer on top. The performance of the proposed model has been demonstrated through extensive simulations in terms of learning reduction, accuracy, and matrix disorientation, with a variable signal-to-noise ratio (SNR) spanning from 20 dB to + 20 dB, which illustrates the superiority of DRCaG compared to others. An online, end-to-end solution based on deep learning techniques is presented in this study for the fast, precise, reliable, and automatic detection of diverse petty crime types. By detecting tiny crimes like hostility, bag snatching, and vandalism, the suggested system may not only identify unusual passenger behavior like vandalism and accidents but also improve passenger security. The solution performs admirably in a variety of use cases and environmental settings.