Personalized Cross Ontological Framework for Secured Document Retrieval in the Cloud

Vigneshwari, S.; Aramudhan, M.

doi:10.1007/s40009-015-0391-3

Cited by 11 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The positive predictive value (PPV) reflects model precision and describes how many cases in the predicted illness-free cases were correct [PPV = TP/(TP + FP)]. Precision and recall generally had an inverse relationship [f1-score = 2 × recall × precision/(recall + precision)], where the f1-score integrated both precision and sensitivity (recall) and could be used as an evaluation indicator, f1-score is called F-Measure [ 42 ].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Application of data mining for predicting hemodynamics instability during pheochromocytoma surgery

Zhao

Cui

et al. 2020

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background: Surgical resection of pheochromocytoma may lead to high risk factors for intraoperative hemodynamic instability (IHD), which can be life-threatening. This study aimed to investigate the risk factors that could predict IHD during pheochromocytoma surgery by data mining. Method: Relief-F was used to select the most important features. The accuracies of seven data mining models (CART, C4.5, C5.0, and C5.0 boosted), random forest algorithm, Naive Bayes and logistic regression were compared, the cross-validation, hold-out, and bootstrap methods were used in the validation phase. The accuracy of these models was calculated independently by dividing the training and the test sets. Receiver-Operating Characteristic curves were used to obtain the area under curve (AUC). Result: Random forest had the highest AUC and accuracy values of 0.8636 and 0.8509, respectively. Then, we improved the random forest algorithm according to the classification of imbalanced data. Improved random forest model had the highest specificity and precision among all algorithms, including relatively higher sensitivity (recall) and the highest f1-score integrating recall and precision. The important attributes were body mass index, mean age, 24 h urine vanillylmandelic acid/upper normal limit value, tumor size and enhanced computed tomography difference. Conclusions: The improved random forest algorithm may be useful in predicting IHD risk factors in pheochromocytoma surgery. Data mining technologies are being increasingly applied in clinical and medical decision-making, and provide continually expanding support for the diagnosis, treatment, and prevention of various diseases.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Accuracy was calculated by dividing the number of records predicted correctly by the total number of samples in the confusion matrix: , where the f1-score integrated both precision and sensitivity (recall) and could be used as an evaluation indicator, f1-score is called F-Measure [42].…”

Section: Model Assessmentmentioning

confidence: 99%

Application of data mining for predicting hemodynamics instability during pheochromocytoma surgery

Zhao

Cui

et al. 2020

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…The input of data from the wearable device fit bit is measured with multiple parameters like calories, steps, weight, bmi, fat and so on. The data obtained is of continuous category because each and every second data is tracked and stored in the HDFS through Cloud API in the cloud Environment [13]. The data outliers are eliminated in the process of data Extraction and Data Ingestion using the library Kafka in our application.…”

Section: Visualization Chartsmentioning

confidence: 99%

Semantic web service-based messaging framework for prediction of fitness data using Hadoop distributed file system

Sethuraman

Sasiprabha

2019

Automatika

View full text Add to dashboard Cite

Big data is coined as word of mouth in this era due to the generation of huge volume of data every second from multiple sources like logs, web sources, and sensors, electrical and electronic devices. The manipulation is performed over the injected data and is termed as Data Processing Segment. In this proposed paper the data are obtained from the wearable devices with attributes like calories, weight, fat, step count, sleep, BMI and so on. The obtained data is stored in HDFS in a persistence manner. The component Kafka acts as a queue for the real time data and regulates the data before storing in HDFS. Now Apache Spark does the streaming of data. Here the data are cleaned, applied the Machine Learning Algorithms (KNN Classifier) to obtain the model, by splitting the cleaned data into Training data and Testing Data. Now the obtained predicted result is sent to Web service Telephony ontology, which in turns communicates with ontology service repository consisting of cloud telephony services ontology and fitness activity ontology through OWL API. The classified and predicted value is analysed and intimated to the users through visualization graphs, SMS, IVR and e-mail.

show abstract

“…In [11] provided a multiple ontologies for extracting the semantic similarities for secure retrieval of document in the cloud. The proposed similarity measure identify the association between the query and the document through query expansion technique and model for personalization was developed.…”

Section: Literature Reviewmentioning

confidence: 99%

A Novel HNN-DOC for Automated Agricultural Ontology Construction on Climate Factors

Deepa*¹,

Deepa²,

Vigneshwari³

2019

IJRTE

View full text Add to dashboard Cite

Ontology has a huge potential for enhancing data association, executives, and understanding. One important criterion of domain ontologies is that they should accomplish a high level of inclusion of the domain concepts and concept relationships. However, the improvement of these ontologies is regularly a manual, time consuming, and frequently results in error. This problem leads towards the need for automation of ontology construction. Agriculture is a critical domain in our country faces problem due to the lack of knowledge on cropping pattern exclusively after the adverse effects of global warming. This paper gives a novel Hybrid Neural Network for Agricultural Ontology Construction (HNN-AGOC) for farmers through the Agro-Pedia dataset for predicting cropping automatically. The HNN-AGOC comprised of Convolutional Neural Network (CNN) for classifying the extracted features and Recursive Neural Network (RNN) for prediction in ontology construction. The algorithm was initially trained with the training dataset, and the performance analysis was performed on different performance metrics. The HNN-AGOC algorithm achieved the overall accuracy, precision, and recall values as 85.23%, 70.10%, and 80.24 % respectively.

show abstract

Personalized Cross Ontological Framework for Secured Document Retrieval in the Cloud

Cited by 11 publications

References 6 publications

Application of data mining for predicting hemodynamics instability during pheochromocytoma surgery

Application of data mining for predicting hemodynamics instability during pheochromocytoma surgery

Semantic web service-based messaging framework for prediction of fitness data using Hadoop distributed file system

A Novel HNN-DOC for Automated Agricultural Ontology Construction on Climate Factors

Contact Info

Product

Resources

About