Controlling drum level is a major and crucial control objective in thermal power plant steam boilers. The drum level as a controlled variable is highly characterized by complex non-linear process dynamics as well as measurement noise and long-time delays. Developing a data-driven process model is particularly advantageous as it could be built from ongoing operational data. Such a model could be used to assist existing controllers by providing predictions regarding the drum level. The aim of this paper is to develop such a model and to propose a control architecture that can be easily integrated into existing control hardware. For that purpose, different neural networks are used, Multilayer Perceptron (MLP), Nonlinear Autoregressive Exogenous (NARX), and Long Short Term (LSTM) neural networks. LSTM and MLP were able to capture the dynamics of the process, but LSTM showed superior performance. The results demonstrate that the use of traditional machine learning criteria to evaluate a process model is not necessarily adequate. Using the model in an open-loop and a closed-loop simulation is more suitable to test its ability to capture the dynamics of the process. A novel architecture that integrates the process model within an existing closed-loop controller is proposed. The architecture uses adaptive weights to ensure that a good model is given more influence than a bad model on the controller’s output.

Control of liquid level & flow are the most interest domain in process control industry. Generally process parameter of the liquid flow system is varied frequently during the operation. So the selection of the level of process parameters i.e. input variables seems to be important for achieving the optimum flow rate. In the present work focus is given on the identification of the proper combination of the input parameters in liquid flow rate process. Flow sensor output, pipe diameter, liquid conductivity & viscosity have been taken as input parameter; flow rate obtained from test is taken as response parameter. Till now several researchers have been performed various optimization methods for optimized the parameters of the process plant. But still computational time & convergence speed of the applied optimization techniques for the modelling of the nonlinear process system is still an open challenge for the modern research. In this research we proposed three evolutionary algorithms are used to optimize the process parameters of the nonlinear model implemented by ANOVA to mitigate the unbalance, convergence speed and reduce the total computational time. Overall research performed into three stage, in first phase nonlinear equation ANOVA has been used for mathematical model for the process, In second stage three evolutionary algorithms: GA, PSO & DE are applied for parametric optimization of liquid flow process to maximize the response parameter & in last phase comparative study performed on simulated results based on confirmed test & validated our proposed methodology.

In the modern era agriculture development is the highly contribute field of food security. Data Science is one of the top analysis experimental methods for forecasting and mapping synchronize. In our study, we experiment with three major parameters (Rainfall, Relative Humidity and Temperature) that can be affected crop production rate as well as area-based mapping. To complete the procedure, the cluster groping and prediction system has created a machine learning BOT combined analysis system. Bangladesh and its 13 areas with 46 years of data have visualized with proper analysis and build up a 2D map of each separate production area. Multi Linear Regression (MLR) and KMean Clustering is the main key point algorithm for the production analysis. Experiment analyzing, we can see that some elements of our environment are closely associated with the productivity of the crop. An untactful environmental change on parameters (Rainfall, Humidity, and Temperature) reduces agricultural productivity by 32-38%. Developed model accuracy 91.25% forecasting methodological analysis for production mapping and prediction. Extreme population food security has ensured ICT and Agriculture combine BOT & EVPM method is essential for the scientific world. This study will allow farmers to choose the proper crop in the right environmental condition, which will play a key role in strengthening the economy of the country.

Biometric systems have been used in a wide range of applications. In this paper, we have introduced an online signature verification system using deep neural network models. The proposed system is designed to be used in a production environment and has accuracies on par with the state-of-the-art signature verification methods. It authenticates much faster than most of the existing signature verification systems (less than 2 seconds). To achieve better accuracies and faster training times, a feature vector with 42 features, both static and dynamic, is obtained from the signature sample. This feature vector is fed into the user identification model, which predicts the identity of the user with about 99% accuracy and based on this prediction, the user authentication model predicts if the signature is genuine or forged for that recognized user, with about 98% accuracy. The best possible accuracy achieved by the proposed system for 40 users is 97.5% and EER about 2%. The dataset from the Signature Verification Competition 2004 (SVC2004) was used to assess the performance of the proposed system. The results show that the proposed system competes with and even outperforms existing methods.

The system proposed can be used to regular checkup of the COVID patients while maintaining the social distancing. Also, the data sensed by the sensors is directly sent to doctor, reducing the cost of paying regular visits to doctor. The Iot platform used in the system helps to transfer the real time patient’s data remotely to host device. Daily health record can be maintained and can be viewed easily on graphs charts ease for doctors to see any abrupt changes in oxygen level or rise in temperature. To track the patient health micro-controller is in turn interfaced to an LCD display and wi-fi connection to send the data to the web-server (wireless sensing node). In case of any abrupt changes in patient heart-rate or body temperature alert is sent about the patient using IoT. This system also shows patients temperature and heartbeat tracked live data with timestamps over the Internetwork.