Feature selection is one of the most popular and crucial methods of data processing used in different machine learning and data mining approaches to avoid high dimensionality and increase classification accuracy. Additionally, attribute selection aids in accelerating machine learning algorithms, improving prediction accuracy, data comprehension, decreasing data storage space, and minimizing the computational complexity of learning algorithms. For this reason, several feature selection approaches are used. To determine the essential feature or feature subsets needed to achieve classification objectives, several feature selection techniques have been suggested in the literature. In this research, different widely employed feature selection strategies have been evaluated by using different datasets to see how efficiently these techniques may be applied to achieve high performance of learning algorithms, which improves the classifier's prediction accuracy.

Adsorption is one of the promising strategies for aqueous dye remediation. A lot of attention has been paid to textile wastewater treatment using smart materials. In this study, we formed the N-FeO to test its properties by using FTIR and TEM technique. We also tested AC, N-FeO and mixed N-FeO/AC to investigate the adsorption efficiency of lipophilic cationic dye (LCD) removal from aqueous solutions of each individually under. The results showed that the removal percentage of lipophilic cationic dye by using activated crbon was increasing significantly with AC wight (Pvalue < 0.01), and the highst removal was to 0.1 ppm of dye (52%). While the lowest dye removal percentage was 14.3% of 1ppm dye concentration and 0.05g AC. The rmoval of dye, by using N-FeO, was depant on the concentration of dye and the amount of N-FeO. The highst percentage of dye removal was 45% ±3.69 of 0.1 ppm concentration with using 0.3g and 0.35 g of N-FeO. While the lowest removal percentage of dye was 7.3%±2.49 of 1ppm with using 0.05g of N-FeO. The using of N-FeO/AC mixture leads to a significant removal percentage of dye in different concentrations compared with using each of them a lone. By this mixture, the highest removal of dye reached to 98%±3.47, 92%±3.96, and 88%±1.44 of 0.1ppm, 0.5ppm, and 1ppm respectively by using 0.35g of N-FeO/AC mixture. While the lowest dye removal percentage was 54%±1.1, 46%±0.98, and 40%±2.49 of 0.1ppm, 0.5ppm, and 1ppm respectively by using 0.05g of N-FeO/AC mixture. This study suggested that the increase in adsorption at low dye concentration was due to the availability of active sites that were saturated While the adsorbing surface area will increase with the N-FeO/AC mixture, the percentage of dye removal at constant temperature will also increase, and it is nessesary to using more chemometric test of this mixture for testing the best removal environment of this kind of dye.

Nowadays increasing dimensionality of data produces several issues in machine learning. Therefore, it is needed to decrease the number of features by choosing just the most important ones and eliminating duplicate features, also reducing the number of features that are important to the model. For this purpose, many methodologies known as Feature Selection are applied. In this study, a feature selection approach is proposed based on Swarm Intelligence methods, which search for the best points in the search area to achieve optimization. In this paper, a wrapper feature selection technique based on the Dragonfly algorithm is proposed. The dragonfly optimization technique is used to find the optimal subset of features that could accurately classify breast cancer as benign or malignant. Many times, the fitness function is defined as classification accuracy. In this study, hard vote classes are employed as a model developed to evaluate feature subsets that have been chosen. It is used as an evaluation function (fitness function) to evaluate each dragonfly in the population. The proposed ensemble hard voting classifier utilizes a combination of five machine-learning algorithms to produce a binary classification for feature selection: Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), Naive Bayes (NB), Decision Tree (DT), and Random Forest (RF). According to the results of the experiments, the voting ensemble classifier has the greatest accuracy value among the single classifiers. The proposed method showed that when training the subset features, the accuracy generated by the voting classifier is high at 98.24%, whereas the training of all features achieved an accuracy of 96.49%. The proposed approach makes use of the UCI repository's Wisconsin Diagnostic Breast Cancer (WDBC) Dataset. Which consists of 569 instances and 30 features.

The nano-particles are not limited to the domain of physics rather it is now days used for the applications in information technology and bio-informatics whereby the assorted streams can be integrated. In this research paper, the analysis of the nano-particles related to the brain waves are taken so that the predictions on the datasets can be done for effective discovery and identification of the brain related diseases. This manuscript is having focus on the usage of machine learning based approach for the predictive analysis of the brain related diseases and found that the need to integrate the information technology to biological domains are quite mandatory for the medical sciences.