Dony Novaliendry, Mansoor Farooq, K.K. Sivakumar, Prasanta Kumar Parida, Bommisetti Yamini Supriya
Breast cancer ranks high among the most lethal forms of the disease in women. Mammograms are widely used by radiologists for the early detection of breast cancer. Low-contrast pictures are common in mammography, which makes it tedious and time-consuming to isolate suspicious areas. Today's healthcare system places a premium on early detection and a precise diagnosis of breast cancer. As time has progressed, the IoT has evolved to the point where we can now analyze both live and historical data with the use of AI and ML techniques. In order to improve medical diagnoses, medical IoT integrates medical devices and AI applications with healthcare infrastructure. The majority of women with breast cancer don't make it because the disease isn't detected early enough with the present standard of care. Therefore, medical practitioners and researchers are confronted with a significant challenge in identifying breast cancer at an early stage. To address the challenge of diagnosing breast cancer at an early stage, we present a medical IoT-based diagnostic system capable of distinguishing between persons with malignant and benign conditions in an IoT setting. While the Support Vector Machine (SVM) and Multilayer Perceptron (MLP) were employed as reference classifiers, artificial neural networks (ANNs) and convolutional neural networks (CNNs) with hyperparameter tuning were used for malignant vs. benign classification. Since hyper parameters have such a direct impact on the behaviors of training algorithms, they are crucial to the success of machine learning algorithms. © 2024, Ismail Saritas. All rights reserved.
Department of Electronic, Engineering Faculty, Universitas Negeri Padang, Padang, Indonesia; Department of Management Studies, University of Kashmir, Hazratbal, Jammu & Kashmir, Srinagar, India; School of Liberal Arts and Sciences, Mohan Babu University, AP, Tirupati, India; School of Rural Management, KIIT University, Odisha, India; Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, AP, Vaddeswaram, India
