Now a day's Employee Attrition prediction become a major problem in the organizations. Employee Attrition is a big issue for the organizations specially when trained, technical and key employees leave for a better opportunity from the organization. This results in financial loss to replace a trained employee. Therefore, we use the current and past employee data to analyze the common reasons for employee attrition or attrition. For the prevention of employee attrition, we applied a well known classification methods, that is, Decision tree, Logistic Regression, SVM, KNN, Random Forest, Naive bayes methods on the human resource data. For this we implement feature selection method on the data and analysis the results to prevent employee attrition. This is helpful to companies to predict employee attrition, and also helpful to their economic growth by reducing their human resource cost.

In today’s competitive business environment, retaining regular employees is a major challenge for all organizations. Retention of employees is an essential management strategy that hopes to create positive work environment and achieve lasting success. Thus, researchers turned their attention to machine learning framework to quickly find the reasons of lowering attrition and estimate staff turnover. In reality, many factors influence employees’ decisions to remain with the organization. The high dimensionality of employee data makes it difficult for data analysts to comprehend and analyses in any meaningful way within time. As a consequence, feature selection got a special focus in the research in order to improve the quality of the data analysis and discover the pertinent data. In this study, the authors propose an Enriched Employee Retention Analysis System (EERAS) that uses a novel approach with a right combination of feature selection model and machine learning techniques. The double goal of the proposed EERAS is to (1) identify the factors that influence employee turnover and (2) recommend key factors for employee retention. To achieve the aimed goals, the authors undertake an empirical analysis on a large employee dataset with four feature selection strategies: MRMR Chi-2, ANOVA and Kruskal on five different classification learning algorithms - Decision Tree, Linear Regression, Naive Bayes, Support Vector Machine, and XGBoost. The results demonstrated that feature selection improves classification accuracy while decreasing training time. In addition, the system recommends critical elements that might be incorporated into HR policy to ensure long-term staff retention.

To decipher human activities and facilitate organic computer-human interactions, facial expression recognition is crucial using four datasets JAFFE, CKPlus, KDEF and AffectNet, we achieve excellent accuracy in human face emotion classification with the VGG 16 pre-trained model with transfer learning. To obtain a comprehensive insight of the model’s decision-making process, we employ Layerwise Relevance Propagation (LRP), a method from explainable Artificial Intelligence (XAI). Only positive relevance scores are taken into account for successfully predicted test images from the datasets. Contributory pixels towards predicting the intensity of emotion are pixels with good relevance ratings. By combining emotion recognition with LRP, we can forecast emotion labels and ranks. Using a confusion matrix, we checked if our predictions were in line with reality. Our model achieved intensity prediction accuracy of 96.33% on JAFFE, 95.78% on CKPlus, 95.78% on KDEF, and 93.89% on AffectNet. A group of ten annotators work together to generate ground truth by assigning ratings of “MINIMAL, “AVERAGE, and “STRONG to each image. This study demonstrates how well our method predicts the ranks of emotion intensity and provides information on how trustworthy and interpretable the model is. Facial emotion recognition’s intensity ranking is made more robust with the addition of XAI techniques like LRP.

Personality is a unique combination of attributes that affect ideas, feelings, and behaviors. Some personality factors predict both professional success and antisocial behavior at work, according to research studies. More than 80% of Fortune 500 companies use personality tests for job screening, leadership development and team building. On the other side, due to increased internet availability, more people are self-expressing and socializing online. Particularly, Twitter, one of the most advanced social networking platforms, generates terabytes of data every day. As a result, current research studies are looking into whether online profiles and actions can reveal people's personalities. The RNN-LSTM-based Profession Recommendation System (RNN-PRS) is proposed to investigate the user's character from their social media activity by using MBTI and recommends suitable professions. In the first stages of development, RNN-PRS places primary emphasis on the collection of character-specific data. Following that, RNN-PRS performs a series of pre-processing techniques to clean up the data obtained from the dataset and get it ready for further processing. After processing, the dataset is split into training and testing portion. When training the model, k-fold cross-validation is used on the dataset with varying values of k. The RNN-PRS learning method implements RNN-LSTM learning technique in the following stage to create the final model. The cross-validation method uses test data to validate the performance of the trained model. The completed model is then evaluated using test data produced during the pre-processing stage to determine the accuracy learning algorithm. In the result analysis, the model investigates its performance over KNN, Logistic Regression, Naive Bayes and Support Vector Machine. A case study is also performed on the Twitter data to recommend a suitable profession based on their personality type. Both job seekers and hiring managers might benefit from the findings of this study in terms of narrowing down their options to the most suitable profession.

Epilepsy is a chronic neurological illness that affects millions of people throughout the world. Epilepsy affects around 50 million people globally. It is estimated that if epilepsy is correctly diagnosed and treated, up to 70% of people with the condition will be seizure-free. There is a need to detect epilepsy at the initial stages to reduce symptoms by medications and other strategies. We use Epileptic Seizure Recognition dataset to train the model which is provided by UCI Machine Learning Repository. There are 179 attributes and 11,500 unique values in this dataset. MLP, PCA with RF, QDA, LDA, and PCA with ANN were applied among them; PCA with ANN provided the better metrics. For the metrics, we received the following findings. It is 97.55% Accuracy, 94.24% Precision, 91.48% recall, 83.38% hinge loss, and 2.32% mean squared error.