Publish in OALib Journal

ISSN: 2333-9721

APC: Only $99


Any time

2020 ( 21 )

2019 ( 187 )

2018 ( 194 )

2017 ( 220 )

Custom range...

Search Results: 1 - 10 of 201319 matches for " Deepa Shenoy P. "
All listed articles are free for downloading (OA Articles)
Page 1 /201319
Display every page Item
WSN Integrated Cloud Computing for N-Care System (NCS) Using Middleware Services
Chandrakant N,,Bijil A P,,Puneeth P,,Deepa Shenoy P
International Journal of Innovative Technology and Exploring Engineering , 2013,
Abstract: The number of wireless devices with powerful sensing capabilities is constantly growing. A mobile phone is an example of a device that is packed with several powerful sensors. Cloud computing is another area that been in focus over the last decade. Cloud computing can be defined as an architectural abstraction that provides scalability and reliability based on requirement. The challenge lies in the fact that sensors for different purposes are heterogeneous in nature. We propose a framework called the N-Care System that utilizes heterogeneous wireless networks to collect data, cloud services to provide additional computational capabilities and provides information for different types of end users. A wireless sensor network consisting of sensors that possess both sensing and transmitting capabilities forms a communication back-bone that can capture a wide variety of data. Multiple sensors are grouped in to a cluster that consists of an internet capable computing device called cluster head that collects data from the constituent sensor nodes and pushes it in to a cloud based database. End users can log in and access data from sensors that fall under the user’s domain.
Dynamic Object Detection, Tracking and Counting in Video Streams for Multimedia Mining
Vibha L,Chetana Hegde,P Deepa Shenoy,Venugopal K R
IAENG International Journal of Computer Science , 2008,
EMID: Maximizing Lifetime of Wireless Sensor Network by Using Energy Efficient Middleware Service
Chandrakant N,P Deepa Shenoy, Venugopal K R, Tejas J,Harsha D,L M Patnaik
International Journal of Innovative Technology and Creative Engineering , 2011,
Abstract: This paper introduces the processing of raw data from sensor nodes located at different places within the vicinity of header node. The middleware service of header node evaluates the assignment and requirement of each node that comes under its vicinity. Based on header node instructions each sensor node is in one of two modes: Active mode or Sleep mode. We have developed a software program to compute the essence of each node based on the raw information provided by each sensor node. If raw data of current sensor node is static at certain time interval or if the raw data of current sensor node is equal to the raw data of other sensor node, then the current node will be treated as qualified node to go to sleep for the time period of maxSleepTime. The proposed algorithm is well suited for military application or monitoring unmanned area.
Statistical classification of magnetic resonance images of brain employing random forest classifier
Joshi S.,Deepa Shenoy P.,Venugopal K. R.,Patnaik L.M.
International Journal of Machine Intelligence , 2009,
Abstract: Data mining in brain imaging is an emerging field of high importance for providing prognosis,treatment, and a deeper understanding of how the brain functions. Dementia due to Alzheimer’s diseaseconstitutes the fourth most common disorder among the elderly. Early detection of dementia and correctstaging of the severity of dementia is critical to select the optional treatment. The present study wasdesigned to classify and categorize brain images of dementia patients into three distinct classes i.e., Normal,Moderately diseased, and Severe. Decision Forest Classifier was employed to classify the various MagneticResonance Images (MRIs) of dementia patients. Results of screening the MRIs are organized byclassification and finally grouped into the three categories, i.e., Normal, Moderate and Severe. Experimentalresults obtained indicated that the proposed method performs relatively well with the classification accuracyreaching nearly 99.32% in comparison with the already existing algorithms.
Classification and treatment of different stages of alzheimer’s disease using various machine learning methods
Sandhya Joshi,Vibhudendra Simha G.G.,Deepa Shenoy P.,Venugopal K.R.
International Journal of Bioinformatics Research , 2010,
Abstract: There has been a steady rise in the number of patients suffering from Alzheimer’s disease (AD)all over the world. Medical diagnosis is an important but complicated task that should be performedaccurately and efficiently and its automation would be very useful. The patient’s records are collected fromNational Institute on Aging, USA. The Sample consisted of initial visits of 496 subjects seen either as controlor as patients. Patients were concerned about their memory at the National Institute on Aging. It alsoconsisted of patients and caregiver interviews. This research work presents different models for theclassification of different stages of Alzheimer’s disease using various machine learning methods such asNeural Networks, Multilayer Perceptron, Bagging, Decision tree, CANFIS and Genetic algorithms. Theclassification accuracy for CANFIS was found to be 99.55% which was found to be better when compared toother classification methods. Based on the outcome of classification accuracies, various management andtreatment strategies such as pharmacotherapeutic and non pharmacotherapeutic interventions for mild,moderate and severe AD were elucidated, which can be of enormous use for the medical professionals indiagnosis and treatment of AD.
Recovery based Time Synchronization for Wireless Networks
Anita Kanavalli,P Deepa Shenoy,Venugopal K R,L M Patnaik
International Journal on Computer Science and Engineering , 2011,
Abstract: Time synchronization schemes in Wireless Sensor Net- works have been subjected to various security threats and attacks. In this paper we throw light on some of these at- tacks. Nevertheless we are moreconcerned with the pulse delay attack which cannot be countered using any of the cryptographic techniques. We propose an algorithm called Resync algorithm which not only detects the delay attack but also aims to rectify the compromised node and intro- duce it back in the network for the synchronization process. In-depth analysis has been done in terms of the rate of suc- cess achieved in detecting multiple outliers i.e. nodes under attack and the level of accuracy obtained in the offset values after running the Resync algorithm.
Cancer Prognosis Prediction Using Balanced Stratified Sampling
J S Saleema,N Bhagawathi,S Monica,P Deepa Shenoy,K R Venugopal,L M Patnaik
Computer Science , 2014, DOI: 10.5121/ijscai.2014.3102
Abstract: High accuracy in cancer prediction is important to improve the quality of the treatment and to improve the rate of survivability of patients. As the data volume is increasing rapidly in the healthcare research, the analytical challenge exists in double. The use of effective sampling technique in classification algorithms always yields good prediction accuracy. The SEER public use cancer database provides various prominent class labels for prognosis prediction. The main objective of this paper is to find the effect of sampling techniques in classifying the prognosis variable and propose an ideal sampling method based on the outcome of the experimentation. In the first phase of this work the traditional random sampling and stratified sampling techniques have been used. At the next level the balanced stratified sampling with variations as per the choice of the prognosis class labels have been tested. Much of the initial time has been focused on performing the pre_processing of the SEER data set. The classification model for experimentation has been built using the breast cancer, respiratory cancer and mixed cancer data sets with three traditional classifiers namely Decision Tree, Naive Bayes and K-Nearest Neighbor. The three prognosis factors survival, stage and metastasis have been used as class labels for experimental comparisons. The results shows a steady increase in the prediction accuracy of balanced stratified model as the sample size increases, but the traditional approach fluctuates before the optimum results.
Forecasting Stock Time-Series using Data Approximation and Pattern Sequence Similarity
R. H. Vishwanath,S. Leena,K. C. Srikantaiah,K. Shreekrishna Kumar,P. Deepa Shenoy,K. R. Venugopal,S. S. Iyengar,L. M. Patnaik
Computer Science , 2013,
Abstract: Time series analysis is the process of building a model using statistical techniques to represent characteristics of time series data. Processing and forecasting huge time series data is a challenging task. This paper presents Approximation and Prediction of Stock Time-series data (APST), which is a two step approach to predict the direction of change of stock price indices. First, performs data approximation by using the technique called Multilevel Segment Mean (MSM). In second phase, prediction is performed for the approximated data using Euclidian distance and Nearest-Neighbour technique. The computational cost of data approximation is O(n ni) and computational cost of prediction task is O(m |NN|). Thus, the accuracy and the time required for prediction in the proposed method is comparatively efficient than the existing Label Based Forecasting (LBF) method [1].
A Linear Belief Function Approach to Portfolio Evaluation
Liping Liu,Catherine Shenoy,Prakash P. Shenoy
Computer Science , 2012,
Abstract: By elaborating on the notion of linear belief functions (Dempster 1990; Liu 1996), we propose an elementary approach to knowledge representation for expert systems using linear belief functions. We show how to use basic matrices to represent market information and financial knowledge, including complete ignorance, statistical observations, subjective speculations, distributional assumptions, linear relations, and empirical asset pricing models. We then appeal to Dempster's rule of combination to integrate the knowledge for assessing an overall belief of portfolio performance, and updating the belief by incorporating additional information. We use an example of three gold stocks to illustrate the approach.
Restless legs syndrome
Ovallath S, Deepa P
Journal of Parkinsonism & Restless Legs Syndrome , 2012, DOI: http://dx.doi.org/10.2147/JPRLS.S37451
Abstract: tless legs syndrome Review (774) Total Article Views Authors: Ovallath S, Deepa P Published Date October 2012 Volume 2012:2 Pages 49 - 57 DOI: http://dx.doi.org/10.2147/JPRLS.S37451 Received: 28 August 2012 Accepted: Published: 17 October 2012 Sujith Ovallath, P Deepa James Parkinson's Movement Disorder Research Centre, Kannur Medical College, Kerala, India Background: Restless legs syndrome (RLS) is a common sleep-related disorder characterized by abnormal sensation and an urge to move the lower limbs. Symptoms occur at rest in the evening or at night, and they are alleviated by moving the affected extremity or by walking. Although the exact etiopathogenesis of RLS remains elusive, the rapid improvement of symptoms with dopaminergic agents suggests that dopaminergic system dysfunction may be a basic mechanism. Dopaminergic agents are the best-studied agents, and are considered first-line treatment of RLS. Objective: To review the diagnostic criteria, clinical features, etiopathogenesis, and the treatment options of RLS. Methods: The suggestions are based on evidence from studies published in peer-reviewed journals, or upon a comprehensive review of the medical literature. Results/conclusion: Extensive data are available for proving the link between the dopaminergic system and RLS. A possible genetic link also has been studied extensively. Dopamine agonists, especially pramipexole and ropinirole, are particularly useful in the treatment of RLS. Pharmacological treatment should however be limited to those patients who suffer from clinically relevant RLS with impaired sleep quality or quality of life.
Page 1 /201319
Display every page Item

Copyright © 2008-2017 Open Access Library. All rights reserved.