ICMLHEED 2023 Proceeding

 

Proceeding of the Conference

Prediction Of Breast Cancer in Mammography Images Using Quantum-Based Swarm Intelligence Clustering Techniques and Deep Learning Approaches

Authors- Akshaya Kumar Dash, Nibedita Adhikari, Chittaranjan Mohapatra

Abstract- – Mammography is the most efficient approach for breast cancer (BC) screening. However, mammogram-based breast biopsy’s limited positive predictive value results in around 70% of needless biopsies with benign outcomes. Several computer-aided diagnostic (CAD) solutions have been proposed in recent years to help reduce the high rate of unneeded breast biopsies. The purpose of the research is to define a fuzzy c-means (FCM) approach based on quantum-inspired particle swarm optimization (QPSO) for clustering multidimensional data. The specified QPSO technique is used to establish cluster centres for a dataset to ad-dress this disadvantage. Pre-processing, clustering, feature extraction, and classification are the four stages of this process. Initially, z-score normalization is used to perform pre-processing. Then, using the QPSO-based FCM approach, the cluster centres for a dataset are generated. Additionally, the principal component analysis (PCA) technique is suggested for extracting features from the given data. Finally, a deep learning based classifier is presented to accurately predict BC im-ages. The proposed scheme is compared to several well-established methods. Experiments demonstrate that the proposed quantum technique has an 87.72% F-measure and 89.59% accuracy compared to other approaches currently in use.

DOI: 10.61463/ijset.icmlheed-2023.101

Automated Power Factor Correction and Energy Monitoring Using IOT

Authors- Kamble Adarsh Balkrishna1, Bhagyashree G. Sherkhane

Abstract- – This paper presents the simple and low-cost design of an IOT based automatic power factor correction (APFC) system for single-phase domestic loads. The proposed design uses relays to switch the capacitor banks in order to correct the power factor of inductive loads. An Arduino board controls the switching of relays based capacitor re-actor bank depending on power factor measured. The Arduino is programmed to non-stop monitor and calculate the power factor of the connecting load by sensing the signal from CT, PT and Zero Cross Detectors (ZCDs), and keep the power factor of the load above the reference value (0.95) by appropriately energizing the capacitors in parallel to the connecting load through relays switching so as to correct power factor close to unity. The value of power factor before and after improvement is displayed on LCD. The hardware prototype of the proposed APFC design is also developed to validate its operation. The satisfactory and acceptable results of the APFC system test have con-firmed that the suggested design yields a reliable output and can be further used in any single-phase practical application to ensure the power factor close to unity. This setup improves power factor up to 0.99. Power factor can be monitored on thing speak web-site transmitted via nodemcu module.

DOI: 10.61463/ijset.icmlheed-2023.102

Advancing Heart Disease Prediction: Integrating Transfer and Ensemble Learning

Authors- Christopher Francis Britto

Abstract- – Heart disease remains a leading cause of global mortality, necessitating accurate predictive models to enable early intervention and personalized treatment strategies. This study introduces an innovative approach to heart disease prediction through the integration of transfer learning and ensemble learning techniques. By combining these advanced methodologies, the research aims to enhance predictive accuracy, robustness, and the capacity to accommodate diverse patient profiles. The proposed method begins with the collection and harmonization of a com-prehensive dataset encompassing diverse data modalities, including patient demographics, clinical records, medical images, and genetic mark-ers. Transfer learning is then used to leverage pre-trained models from related medical domains to adapt them to the intricacies of heart disease prediction. This approach bridges the gap between limited labeled data and the substantial requirements of complex predictive models. Next, an ensemble of predictive models is developed using different algorithms tailored to specific data types. The ensemble leverages the collective in-sights of these models to improve predictive accuracy and resilience against individual model biases. To ensure practicality and efficacy, a comprehensive hyperparameter tuning regimen is implemented. Grid search or Bayesian optimization is employed to fine-tune both the trans-fer learning and ensemble composition. The proposed methodology’s effectiveness is rigorously evaluated on a diverse heart disease dataset, encompassing various conditions and patient profiles. Performance metrics including accuracy, precision, recall, and F1-score are employed to quantitatively assess the model’s predictive capabilities. Visualization of ensemble decisions further enhances interpretability and insights. Initial results highlight the transformative potential of transfer learning and ensemble techniques for heart disease prediction. The proposed method presents a robust solution that can revolutionize early diagnosis and treatment strategies in cardiology, thereby improving patient care and prognosis.

DOI: 10.61463/ijset.icmlheed-2023.1013

More Paper are coming soon.. Its under formatting…..