1,721,057 research outputs found
A Novel Framework for Smart Home Human Activity Identification using Binary Cuckoo Search Metaheuristic
No full textME ThesisHuman activity recognition has been a topic of attraction among researchers and
developers because of its enormous usage in widespread region of human life. The varied
human activities and the way they are executed at individual level are the main
challenges to be recognized in human behavior modeling. In this thesis a novel
methodology is proposed that recognizes human activities from the behavior of
individuals in a smart home environment. The dataset considered in the work is captured
using Bluetooth Low Energy (BLE), a popular technology for indoor localization. The
proposed framework is a binary cuckoo search based stacking model that collectively
exploits multiple base learners for human activities recognition from the gathered
accelerometer sensors data mounted on wearable and mobile devices. The work is tested
on the newly developed SPHERE dataset to recognize user activities in smart home
environment. The experimental results showcase the effectiveness of the proposed
approach, outperforming other recent existing techniques on the dataset, giving high
predictive accuracy value of 93.77 % via 10-fold cross validation
Intelligent Most Popular Location Prediction in Cloud Environment through Facebook Check-ins using Multi-Model Ensembling Approach
No full textMaster of Engineering -CSEWith the advent of check-in functionality in Facebook, people are able to share more
information with the world. Almost every person is using social networking sites
nowadays, but the amounts of information they share are appreciated by few.
In this research, a new model has been designed for identification of Facebook checkins
dataset for predicting most popular places for the user that he/she would like to
check-in. Two different machine learning environments, Apache Mahout and R Tool,
have been used for predicting most popular places. Each platform has its different
classification algorithms. These two machine learning platforms through Ensembling
technique have been compared and their analysis has been listed out. In both
environments, unique multilevel ensemble model is generated for prediction of
Facebook more popular places.
In the first module, Facebook check-ins dataset has been used on R tool on a
standalone machine, machine learning algorithms have been executed on the given
dataset to foresee accuracy for the most famous area. Support Vector Machines model
has been chosen as a powerful model since it gives the most astounding accuracy of
77.03% after Conditional Inference Tree model and k-Nearest Neighbors Machine
model. Further, these 3 models are ensembled leading to 82.12% accuracy. After that
k-fold method is applied, this gives the highest accuracy of 88.18%. In the second
module, the Mahout Classification machine learning algorithm has been implemented.
For Ensembling technique, the top three models have been chosen; afterward these
three models are ensembled to get the highest accuracy. The ensemble model of
Facebook check-ins accomplishes 91.66% of accuracy.
The experimental outcomes have likewise been assessed utilizing 9768 instances that
distinctly support the most extreme accuracy through Ensembling and utilize less
execution time in machine learning environment
Prediction of Pediatric Irritable Bowel Syndrome using Machine Learning Ensemble Approach
No full textMaster of Engineering -CSEMachine learning Ensembling approach has the potential to resolve Irritable Bowel Syndrome(IBS) problem. Machine learning techniques have numerous benefits that include high flexibility and power, lack of parametric assumptions, etc. The researchers do not properly understand the causes of the IBS. The researchers found that the IBS caused due to the combination of the physical and the mental health problems.Ensemble methods combine the predictions from the various machine learning algorithms which use these predictions as inputs for the second-level learning models.
This research focuses on detection of Irritable Bowel Syndrome (IBS) using machine learning ensemble approach. The experimental analysis is performed using various machine learning models: Support vector machines (SVM), Neural Network, Linear Regression, Random Forest, Decision tree, AdaBoost (Adaptive Boosting), Naive Bayes, Boosted tree, Multilayerperceptrone, and Binary Discriminate analysis. The data was collected from the Website of UMASS Medical School. The collected data wasof the pediatric patients. The data was used to predict the presence of IBS in pediatric patients. In our research, we ensemble ten different models to build a new model having high accuracy to predict a pediatric patient is IBS or not. The implementation of proposed ensemble model was done in R language. The RRF model was used for feature selection task. We used R language for the implementation of the proposed ensemble model. The RRF model was used for feature selection task. Preliminary results of the experiment show that our model is 93.32% accurate in predicting whether a pediatric patient is IBS positive or not
Modified Ant Colony Optimization Algorithm for Traveling Salesman Problem
No full textM.Tech. (Computer Science and Applications)Ant colony optimization is a technique for optimization that was introduced in the early 1990’s. The inspiring source of ant colony optimization is the foraging behavior of real ant colonies. This behavior is exploited in artificial ant colonies for the search of approximate solutions to discrete optimization problems, to continuous optimization problems, and to important problems in telecommunications, such as routing and load balancing. First, we study with the biological inspiration of ant colony optimization algorithms and how this biological inspiration can be transferred into an algorithm for Traveling Salesman Problem (TSP). Then, ant colony optimization outlined in more general terms in the context of discrete optimization, and some of the nowadays best performing ant colony optimization variants are studied. This research approach lies at initial stage at present, and a new modified ant algorithm is proposed for the traditional ant algorithm easily appears precocious and stagnation behavior phenomenon in this paper. And the various parameter of ant colony algorithm is adjusted. Selecting a typical TSP instance to experiment, the results are indicated that the new modified ant colony algorithm has a better ability to search the global optimal solution and have better stability.School of Mathematics and Computer Applications, Thapar University, Patial
Detection Framework for Content Based Cybercrime in Online Social Networks
Full text linkThe recent development of social media poses new challenges to the research community in
analyzing online interactions among people. Social networking sites offer great opportunities for
connecting people with each other, but also increase the vulnerability of young people to
undesirable phenomena, such as content-based cybercrime. This may cause many serious and
negative impacts on a person’s life and even lead to committing suicide. Cybercrime has emerged
as a money-driven industry with malicious intent towards online social networks. Cyber-criminals
aim to manipulate vulnerable areas in cyber-space by playing on human understanding and making
a profit. They threaten minors, especially adolescents, who are not adequately overseen whilst
online.
In the recent past, the issues of Content-based Cybercrime have gained considerable attention.
Social media providers seek for accurate and efficient way of recognizing offensive content for
shielding their users. Content-based Cybercrime detection is one of the conspicuous area of data
mining that deals with the recognition and examination of bully contents usually presented in social
media. The current work emphasizes on cyberbullying, one of the prominent problems that arose
due to the increasing fame of social network and its fast acceptance in our day-to-day survives.
The social network provides a convenient platform for the cyber predators to bully their preys
especially targeting young youth. In severe cases, the victims have attempted suicide due to
humiliation, insult, and hostile messages left by the predators.
xv
To address this issue, there is an urgent need for a robust content based cybercrime detection
framework. This thesis proposes three techniques for efficient detection of content-based
cybercrime in online social networks. First one, cuckoo inspired SVM approach, aims to
concurrently optimize the parameters and feature selection with a target to build the quality of
SVM. This chapter proposes a novel hybrid model that is the integration of Cuckoo Search and
SVM, for feature selection and parameter optimization for efficiently solving the problem of
content-based cybercrime detection. In second approach, multiconfiguration detection technique,
has been proposed to explore possible combinations of various preprocessing, feature selection
and classification methodologies using the cuckoo search metaheuristic approach. This approach
seeks to improve the performance of content based cybercrime detection system. In third approach,
a novel cuckoo inspired stacking ensemble framework has been proposed that is the integration of
cuckoo search and several machine learning models. The proposed framework automatically seeks
for near-optimal combinations of classification techniques along with their tuning parameters for
efficiently solving the detection problem of content-based cybercrime in multimedia platforms.
The performance of the proposed approaches has been evaluated by testing on four different
datasets obtained from Twitter, ASKfm and FormSpring to identify bully terms. The results of the
proposed approaches demonstrate significant improvement in the performance of classification on
all the datasets in comparison to recent existing models. The experimental results demonstrate the
high efficiency and effectiveness of the proposed approaches. These approaches outperformed
other recent techniques on all the datasets, giving high predictive recall value via 10-fold crossvalidatio
Efficient Evolutionary Based Clustering Approaches for Health Care Data
No full textGood health care is one of the most significant factors which can make a contribution to the
individual well-being of everyone in the modern world. The detection of diseases is a crucial
and difficult task in healthcare. The recognition of diseases from numerous features or signs
is a prime issue which is not free from false presumptions frequently followed with the aid of
unpredictable effects. The healthcare enterprise gathers large amounts of disease data that
unfortunately, are not mined to decide concealed facts for effective diagnosing. As the
quantity of stored data increases, clustering play a vital role in extracting knowledge and
finding patterns to provide better care and effective diagnostic capabilities. Clustering aims to
arrange a set of data objects into clusters; such that objects inside a cluster are “similar” to
each other than they are to objects in the different clusters. There are various numbers of
applications for clustering which includes marketing, scientific and engineering, ecommerce,
image segmentation business etc. The current work in the thesis focuses on the two diseases
namely Wisconsin Breast Cancer and Epileptic seizure. The work relies on the finding the
optimal solution based on clustering techniques. The proposed clustering techniques based
evolutionary algorithms namely GA-clustering, PSO-clustering and DE-clustering are applied
on breast cancer wisconsin dataset and their effectiveness is evaluated on the basis of DB
index and classification parameters. In another work, a novel partitioning based clustering
using DE approach is proposed that is applied on epileptic seizure recognition dataset and its
results are compared with DE-clustering approach on the basis of cluster validity measures
namely DB index, Dunn index and computational time. So, clustering techniques are of vital
importance that it organizes the data, thereby generating patterns that can be further utilized
for better analysis of diseases
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
- …
