Level measurement models using image-based classifiers (pixel-based datasets) are used for estimation purposes. Preprocessing is thought-provoking in proceeding out the image filter technique and classifying the level. The level scenario of a two non-interacting tank system plays a vital role in predicting the level. Level monitoring is done using the supervised learning method using instance-based filters (Gabor Filter) and selected base classifiers for level measurements. The main scope of this case study is to improve the level measurements from the two non-interacting tank scenarios using Artificial Intelligent algorithms. The suggested article includes the finest feature selection process to increase the accuracy performance attained by the designated classifiers like IBK Instance base classifier for different neighborhood values and Tree category algorithm like Random Forest. The performance accuracy in level prediction obtained is 81.356%, the weighted Average of Receiver operator characteristics of (ROC) 0.931 are obtained by Random Forest Tree Category Classifier.

Control valves are a progressively vital element of recent industrial instrumentation all over the world since these control valves are basically pneumatic devices composed of all mechanical parts their performance is less compared to the ideal one and due to constant moving parts wear and tear degrades over time. Control valves usually called the final control element in any process are used to control continuous flow, level, pressure, and temperature. The signal received from the conventional controller gives the signal for opening the CV (Control Valve) partially, fully open, or fully closed. The control signal is proportional to the magnitude of error with respect to time. The control valve is opened and closed automatically by giving the pressure to open and close using I/P converters in cascade with Pneumatic, Hydraulic, or electrical actuators with positioners. A plant can perform optimally if the performance of the control valve is monitored and maintained. The aim of this article is to initiate the studies in the direction of obtaining accuracy in stem positioning through image inputs and to demonstrate this yielding output as control valve stem position using machine learning algorithms, part of artificial intelligence enables identifying the stem position in less time using digital image processing. The proposed systems comprise of images of different stem positions is fed to the Weka software tool, preprocessed using Pyramid Histogram of Oriented Gradients (PHOG) feature filter and trained using pre-planned classifiers, the performance accuracy of stem levels by experiment-based attribute selection, iteration on ranking thresholds and SMOTE with triple iterations on class levels is calculated. The results show the performance with the maximum accuracy of 92.4051% and weighted average Receiver Operator Characteristics (ROC) values of 0.978. Hence such smart measurements using Machine learning algorithms which is a part of artificial intelligence provide us a vital role in predicting the CV stem position in less time using image processing filters.