AAAarti

Aarti

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Aarti has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Utilising Machine Learning to Forecast Staff Attrition

    by Aarti, Swathi Gowroju, Saurabh Karling, Susheela Vishnoi

    Employee attrition, or the organic decrease in employees within an organisation as a result of numerous unavoidable circumstances, is a big problem that costs companies a lot of money. According to the Society for Human Resource Management (SHRM), replacing an employee typically costs USD 4129 per hire. In order to solve this problem, a study was carried out to determine the root reasons of staff attrition and create a machine learning-based predictive framework. The study's objectives were to forecast attrition using four machine learning approaches and analyse organisational aspects that contribute to attrition. Surpassing prior state-of-the-art research, the suggested optimised Extra Trees Classifier (ETC) technique was able to predict staff attrition with an outstanding 93% accuracy. Furthermore, Employee Exploratory Data Analysis (EEDA) was utilised to ascertain critical elements impacting attrition. The results showed that age, job level, hourly rate, and monthly income all had a big impact on attrition rates. Organisations can target and improve the factors found in the study to address employee attrition with the use of these insights and the suggested methodology.


  • Lung Cancer Detection Using Machine Learning

    by Aarti, Saurabh Karling, A. Swathi

    Since lung cancer is a dangerous illness that affects a large number of people, early detection and treatment are essential. The precise kind and location of the cancer within the body determine which treatment interventions are best. Early detection of lung cancer cells increases the likelihood of a successful course of therapy, especially in the early stages prior to metastasis. Since the results of present methods are frequently erratic and time-consuming, the creation of a computer-aided system for early cancer detection is important. The problem still exists despite earlier attempts by researchers. A potential remedy is Convolutional Neural Networks (CNN), which show improved precision and efficacy in differentiating between instances with and without cancer. With remarkable validation accuracy and precision of 94% and 95%, respectively, the CNN architecture provides an effective tool for prompt and precise diagnosis.

  • A Comprehensive Survey and Analysis of Bank Employee Retention Policies

    by Aarti, Saurabh Karling, Susheela Vishnoi

    The study compares staff retention strategies used in the banking and insurance sectors. Employers use employee retention as a technique to keep talented and skilled individuals in their firm and lower the cost of employee turnover. Employee happiness is one of the crucial elements that aids any firm in keeping its top workers. HR analytics is used in decision-making processes to boost productivity and improve returns on capital investments for firms by using data collection, predictive models, and HR indicators. This article describes HR analytics and outlines its three main characteristics: necessity, method, and application, in order to help readers understand how HR has changed. According to this study, there is a direct link between employee motivation and retention among bank personnel. In order to help the banking industry retain workers for longer, banks are encouraged to adapt their employee development and training practices.

  • A Comparative Analysis on Computational and Security Aspects in IoT Domain

    by Ankit Khare, Pushpendra Kumar Rajput, Raju Pal, Aarti

  • Open Access

    Deep Neural Network for Accurate Age Group Prediction through Pupil Using the Optimized UNet Model

    by Swathi Gowroju, Sandeep Kumar, Aarti, Anshu Ghimire

    Predicting age automatically from the image is a difficult task and shortening the challenge to be more concise is also a challenging task. Nevertheless, the existing implementations using manually designed features using a wide variety of input features using benchmark datasets are unsatisfactory as they suffer from unknown subject information. It is challenging to judge CNN’s performance using such approaches. The proposed system performs the segmentation through UNet without using a dense layer to perform the segmentation and classification. The proposed system uses the skip connection to hold the loss at the max-pooling layer. Also, the morphological processing and probabilistic classification served as the proposed system’s novelty. The proposed method used three benchmark datasets, MMU, CASIA, and UBIRIS, to experiment with building a training model and tested using various optimization techniques to perform an accurate segmentation. To further test and improve the quality of the proposed method, we experimented with random images. The proposed system’s accuracy is 96% when experimented on random images of subjects collected purely for experimentation. Three optimizers, namely, Stochastic Gradient Descent, RMS Prop, and Adaptive Moment Optimizer, were experimented with in the proposed system to fit the system. The average accuracy we received using optimizers is 71.9, 84.3, and 96.0 for the loss value of 2.36, 2.30, and 1.82, respectively.


  • Automated Methods for the Detection of Green Land in Satellite Images

    by Raju Pal, Subash Yadav, Aarti, Pushpendra Kumar Rajput, Anand Nayyar