http://localhost:8080/xmlui/handle/123456789/439 2026-06-23T06:19:01Z http://localhost:8080/xmlui/handle/123456789/3434 Title: A Novel Hybrid Framework for Cuff-Less Blood Pressure Estimation based On Vital Bio Signals processing using Machine Learning Authors: Shinde, Santosh A; Rajeswari, P. Raja Abstract: Blood Pressure is one among the most important physiological parameters for assessing the overall well being of an individual. It plays pivotal role in the detection of many cardiovascular diseases specially Hypertension. Traditional Cuff-Based BP measurements techniques have several drawbacks and they are significantly inconvenient to patients, moreover continuous BP measurement is difficult. Lot of research is currently going on for Cuff-Less BP Estimation and several techniques are researched out in the researcher’s community. However, most of the existing approaches lack the required level of accuracy, generality and they are not experimented out on a large population of having heterogeneous subjects with varied demographic features. In this paper we propose a novel hybrid signal processing approach using machine learning for continuous estimation of BP without the need for calibration. Our proposed framework has reached satisfactory results in terms of Mean Absolute Error (MAE) for mean arterial pressure (MAP) Estimation. 2020-04-10T00:00:00Z http://localhost:8080/xmlui/handle/123456789/2966 Title: IM_LR: An approach for Direct and Indirect Discrimination Prevention Authors: Wakchaure, M.A.; Sane, S. S. Abstract: Discrimination and privacy preservation are major challenges of data mining. Technique based on impact minimization to prevent discrimination has been reported in the literature. The technique computes fitness of generated frequent rules based on their antecedent, a pre-defined threshold and discrimination measure ‘elift’ to modify discriminating rules. This paper deals with a method called ‘IMLR’. IMLR computes fitness of generated frequent rules based on their antecedent (attributes on left hand side of the rule) as well as consequences (class label on right hand side of the rule), a pre-defined threshold and offers selection of desired discrimination measures such as ‘elift’, ‘slift’, ‘olift’ etc. to modify discriminating rules. Experimentation results carried out using two well-known datasets ‘Adult’ and ‘German’ show that IMLR when used with certain discrimination measure provides better results in terms of various performance parameters such as DDPD, DDPP, IDPD, IDPP, Missed cost and Ghost cost when compared with reported technique 2019-05-15T00:00:00Z http://localhost:8080/xmlui/handle/123456789/2962 Title: A Novel Algorithm for Multi-label Classification by Exploring Feature and Label Dissimilarities Authors: Tidake V. S.; Sane S. S. Abstract: Selection of appropriate nearest neighbors greatly affects predictive accuracy of nearest neighbor classifier. Feature similarity is often used to decide the set of k nearest neighbors. Predictive accuracy of multi-label kNN could further be enhanced if in addition to the feature similarity, difference in feature values and dissimilarity of the instance labels are also taken into account to decide the set of k nearest neighbors. This paper deals with an algorithm called “ML-FLD” that not only takes into account features similarity of the instances, but also considers feature difference and label dissimilarity in order to decide the k nearest neighbors of a given unseen instance for the prediction of its labels. The algorithm when tested using well-known datasets and checked with the existing well known algorithms, provides better performance in terms of example based metrics such as hamming loss, ranking loss, one error, coverage, average precision, accuracy, F measure as well as label-based metrics like macro-averaged and micro-averaged F measure. 2019-07-04T00:00:00Z http://localhost:8080/xmlui/handle/123456789/2829 Title: A Novel Energy Efficient and SLA-Aware Approach for Cloud Resource Management Authors: Sane, Shirish S.; Shelar, Madhukar Abstract: Server virtualization is a well-known technique for virtual machine (VM) placement and consolidation and has been studied extensively by several researchers. This article presents a novel approach called aiCloud that advocates segmentation of hosts or physical machines (PMs) into four different classes that facilitates quick selection of PMsto reduce the time required to search host machines, called host search time (HST). The framework also introduces VM_Acceptance_State, a condition that avoids host overloading, which leads to significant reduction of SLA time per active host (SLATAH) that in turn reduces SLA violation (SLAV). The performance of aiCloud has been compared with other approaches using standard workload traces. Empirical evaluation presented shows that aiCloud has least HST and outperforms other approaches in terms of SLA violations and ESV (Energy and SLA Violation) and therefore may be an attractive strategy for efficient management of cloud resources 2019-06-02T00:00:00Z