A Novel Cervical Cancer Detection Using Contrast Overlap Feature-Based Segmentation with Neural Network Classifier R. S. Karthic, K. R. Aravind Britto, R. Ragumadhavan, R. Vimala International Journal of Computational Intelligence Systems, 2025 Cervical cancer is another prime cause of women’s casualties due to its detection and diagnosis in advanced stages. Modern computer-aided processing exploits magnetic resonance imaging, computed tomography, positron emission tomography, and advanced artificial intelligence to improve early detection of this cancer. In this study, a Contrast Overlap Segmentation Method (COSM) was introduced and described. The extracted features were first classified as high/low based on their contrast intensity to classify different regions. The classification was further extended using a neural network with two hidden layers for accuracy improvement and training initialization. The neural network outcomes were normalized using the ReLU function to identify overlapping and non-overlapping regions to ensure that the infected region in any intensity region was identified. The neural network was trained using a labeled dataset to ensure that high-region segmentation was performed with better sensitivity. Thus, the training process was augmented for segmented and input training sets with better pixel feature classifications. In results section, experimental analysis is using CCAgT cervical cancer dataset. This dataset provides 9339 smear images of cervical cancer cells under 15 slides. For the highest classification rate, the proposed COSM improved the accuracy, precision, and sensitivity by 10.45, 9.62, and 12.38%, respectively. The mean error and computing time were reduced by 9.77 and 7.85%, respectively. The proposed method experienced overhead when handling variable feature distributions. Such distributions require a maximum-to-minimum grouping-based normalization, which is lacking in this method.
Machine Learning Model for the Prediction of an E-Vehicle's Battery Life Cycle Mahesh Prasanna K, R. S. Karthic, B Harish Babu, Prachi Ramesh Patil, Radha Raman Chandan, et al. International Conference on Edge Computing and Applications Icecaa 2022 Proceedings, 2022 A useful substitute for a traditional car is an electric vehicle. Rechargeable batteries, which are much more efficient than traditional fuels like gasoline and diesel, are used to power the majority of these vehicles. The benefits of batteries can occasionally be outweighed by other reasons. It also takes into account the battery's rapid depreciation. The purpose of this study is to offer a resolution to the aforementioned problem. Three machine learning (ML) models were created and examined for this goal. A dataset with diverse battery-related data has been assembled from the MIT dataset. About 124 Li-ion batteries are included in this collection. Because most of the columns in this dataset are useless, the necessary parameters were extracted from it. Three ML models were also developed. Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting Decision Tree (GBRT) are three separate methods that were used to generate the models. The dataset's acquired features were then used to train the models. The effectiveness of the models was then evaluated to identify the best method that can be applied to the prediction of the battery cycle by looking at the accuracy and loss values of all three algorithms. After accuracy and error analyses, it is concluded that the SVM method is the best. The highest accuracy, 97.3, was generated by the SVM algorithm. It was also more effective because it had the smallest MAE value.
LabVIEW based analysis on electronic intravenous drip & hr monitoring system International Journal of Scientific and Technology Research, 2019
