IEEE-2019: Improving Heart Disease Prediction Using Feature
Selection Approaches
Abstract: Heart
Disease is the disorder of heart and blood veins. It is very difficult for
medical practitioners and doctors to predict accurate about heart disease
diagnosis. Data science is one of the more important things in early prediction
and solves large data problems now days. This research paper describes the
prediction of heart disease in medical field by using data science. As many
researches done research related to that problem but the accuracy of prediction
is still needed to be improved. So, this research focuses on feature selection
techniques and algorithms where multiple heart disease datasets are used for
experimentation analysis and to show the accuracy improvement. By using the
Rapid miner as tool; Decision Tree, Logistic Regression, Logistic Regression
SVM, Naïve Bayes and Random Forest; algorithms are used as feature selection
techniques and improvement is shown in the results by showing the accuracy.
IEEE-2019: Disease Influence Measure Based Diabetic Prediction with
Medical Data Set Using Data Mining
Abstract: The
problem of diabetic prediction has been well studied in this paper. The disease
predictions have been explored using various methods of data mining. The use of
medical data set on the prediction of diabetic mellitus has been analyzed. This
paper performs a detailed survey on disease prediction using data mining
approaches based on diabetic data set. The presence of disease has been
identified using the appearance of various symptoms. However, the methods use
different features and produces varying accuracy. The result of prediction
differs with the methods/measures/ features being used. Towards diabetic
prediction, a Disease Influence Measure (DIM) based diabetic prediction has
been presented. The method preprocesses the input data set and removes the
noisy records. In the second stage, the method estimates disease influence
measure (DIM) based on the features of input data point. Based on the DIM
value, the method performs diabetic prediction. Different approaches of disease
prediction have been considered and their performance in disease prediction has
been compared. The analysis result has been presented in detail towards the
development.
IEEE-2018: A Novel Mechanism for
Fast Detection of Transformed Data Leakage
Abstract: Data
leakage is a growing insider threat in information security among organizations
and individuals. A series of methods have been developed to address the problem
of data leakage prevention (DLP). However, large amounts of unstructured data
need to be tested in the Big Data era. As the volume of data grows dramatically
and the forms of data become much complicated, it is a new challenge for DLP to
deal with large amounts of transformed data. We propose an Adaptive weighted
Graph Walk model (AGW) to solve this problem by mapping it to the dimension of
weighted graphs. Our approach solves this problem in three steps. First, the
adaptive weighted graphs are built to quantify the sensitivity of tested data
based on its context. Then, the improved label propagation is used to enhance
the scalability for fresh data. Finally, a low-complexity score walk algorithm
is proposed to determine the ultimate sensitivity. Experimental results show
that the proposed method can detect leaks of transformed or fresh data fast and
efficiently.
IEEE-2018: Machine Learning Methods
for Disease Prediction with Claims Data
Abstract: One of the primary challenges of healthcare delivery is
aggregating disparate, asynchronous data sources into meaningful indicators of
individual health. We combine natural language word embedding and network
modeling techniques to learn meaningful representations of medical concepts by
using the weighted network adjacency matrix in the GloVe algorithm, which we
call Code2Vec. We demonstrate that using our learned embeddings improve neural
network performance for disease prediction. However, we also demonstrate that
popular deep learning models for disease prediction are not meaningfully better
than simpler, more interpretable classifiers such as XGBoost. Additionally, our
work adds to the current literature by providing a comprehensive survey of
various machine learning algorithms on disease prediction tasks.
IEEE 2017: Privacy and Secure Medical Data Transmission and Analysis for Wireless Sensing Healthcare System
IEEE 2017: Privacy-Preserving Location-Proximity for Mobile Apps
Abstract :Location Based
Services (LBS) have seen alarming privacy breaches in recent years. While there
has been much recent progress by the research community on developing
privacy-enhancing mechanisms for LBS, their evaluation has been often focused
on the privacy guarantees, while the question of whether these mechanisms can
be adopted by practical LBS applications has received limited attention. This
paper studies the applicability of Privacy-Preserving Location Proximity (PPLP)
protocols in the setting of mobile apps. We categorize popular location social
apps and analyze the tradeoffs of privacy and functionality with respect to
PPLP enhancements. To investigate the practical performance trade-offs, we
present an in-depth case study of an Android application that implements Inner
Circle, a state-of-the-art protocol for privacy preserving location proximity.
This study indicates that the performance of the privacy-preserving application
for coarsegrained precision is comparable to real applications with the same
feature set.
Click for more details
IEEE 2017: IoT based Home Security through Digital Image Processing
Algorithms
Abstract- This paper gives an outline for automatic system to
control and secure the home, based on digital image processing with the help of
Internet of Things (IoT). The system consists of a sensor, digital camera,
database in the fog and the mobile phone. Sensors are placed in the frame of
the door which alerts camera, to capture an image who intends to enter the
house, then sends the image to the database or dataset that is stored in the
fog. Image analysis is performed to detect and recognize and match the image
with the stored dataset of the authenticated people or pets. If the image
captured does not match with the dataset then an alert message is send to the
owner of the house. The image processing algorithms are considered for the
processing spatial and time complexity of the image captured to cross check
with the dataset stored in the fog.
Click for more details
No comments:
Post a Comment