Showing papers in "Procedia Computer Science in 2016"
••
TL;DR: A network with CNN architecture and data augmentation is developed which can identify the intricate features involved in the classification task such as micro-aneurysms, exudate and haemorrhages on the retina and consequently provide a diagnosis automatically and without user input.
642 citations
••
TL;DR: A performance comparison between different machine learning algorithms: Support Vector Machine (SVM), Decision Tree (C4.5), Naive Bayes (NB) and k Nearest Neighbors (k-NN) on the Wisconsin Breast Cancer datasets is conducted and Experimental results show that SVM gives the highest accuracy with lowest error rate.
501 citations
••
TL;DR: A review of MRI-based brain tumor segmentation methods using state-of-the-art algorithms with a focus on recent trend of deep learning methods.
489 citations
••
TL;DR: The focus of this research is understanding how blockchain can be exploited to create decentralised, shared economy applications that allow people to monetise, securely, their things to create more wealth.
428 citations
••
TL;DR: A model for intrusion detection system using random forest classifier is built and empirical result show that proposed model is efficient with low false alarm rate and high detection rate.
357 citations
••
TL;DR: K-Medoids is better in terms of execution time, non sensitive to outliers and reduces noise as compared to K-Means as it minimizes the sum of dissimilarities of data objects.
309 citations
••
TL;DR: The different medical applications and the most common technologies used in WBANs are presented and a matching between each application and the corresponding suitable technology is studied.
284 citations
••
TL;DR: The experimental results show that unsupervised feature selection algorithms benefits machine learning tasks improving the performance of clustering.
267 citations
••
TL;DR: A literature review is conducted, different fuzzy models that have been applied to the decision making field are explored, and some applications of fuzzy TOPSIS are presented.
226 citations
••
TL;DR: Cost and performance of popularly used cryptographic algorithms DES, 3DES, AES, RSA, RSA and blowfish are implemented and analyzed in detail to show an overall performance analysis, unlike only theoretical comparisons.
207 citations
••
TL;DR: The aim of this article is to develop an architecture based on an ontology capable of monitoring the health and workout routine recommendations to patients with chronic diseases.
••
TL;DR: The paper proposes the advantages of having ICT in Indian agricultural sector, which shows the path for rural farmers to replace some of the conventional techniques by utilizing water resource efficiently and also reducing labour cost.
••
TL;DR: Models for intrusion detection are built by using machine learning classification algorithms namely Logistic Regression, Gaussian Naive Bayes, Support Vector Machine and Random Forest, and Experimental results shows that Random Forest Classifier out performs the other methods in identifying whether the data traffic is normal or an attack.
••
TL;DR: Overall performance of adaboost ensemble method is better than bagging as well as standalone J48 decision tree as a base learner along with standalone data mining technique J48 to classify patients with diabetes mellitus using diabetes risk factors.
••
TL;DR: This paper compares the various techniques used for Sentiment Analysis by analyzing various methodologies and finds several methods for accomplishing this task to be superior.
••
TL;DR: The paper throws light upon how these factors can make the smart city initiative a successful project and identifies six significant pillars for developing the framework as: S ocial, Magement, E conomic, L egal, Tchnology and S ustainability (SMELTS).
••
TL;DR: The key goal of the paper is to identify the relationship between these three concepts: data lakes, fast data and data lakes.
••
TL;DR: Preliminary results on three real IoT datasets show that C4.5 and C5.0 have better accuracy, are memory efficient and have relatively higher processing speeds, compared to ANNs and DLANNs, which can provide highly accurate results but are computationally expensive.
••
TL;DR: A co-word method based on keywords from funded project is proposed to map the research trends and shows that Game Theory, Supply Chain Management, Complex Network, Data Mining, Optimize, Risk Management, and Data Envelopment Analysis are hot topics.
••
TL;DR: An overview of the current state ofsoft computing techniques is given and the advantages and disadvantages of soft computing compared to traditional hard computing techniques are described.
••
TL;DR: The Sentinel-1 support in the GAMMA Software is described, a high-level software package used by researchers, service providers and operational users in their SAR, InSAR, PSI and offset tracking work.
••
TL;DR: A framework that can proficiently find the tenets to foresee the risk level of patients in view of the given parameter about their health is planned, demonstrating that the framework has extraordinary potential in anticipating the coronary illness risk level all the more precisely.
••
TL;DR: This paper discusses the data mining technique i.e. association rule mining and provides a new algorithm which may helpful to examine the customer behaviour and assists in increasing the sales.
••
TL;DR: The proposed method of pre-processing relies on the bindings of slang words on other coexisting words to check the significance and sentiment translation of the slang word and clearly indicates improvements in accuracy of classification.
••
TL;DR: A comprehensive study of the state-of-the-art VM placement and consolidation techniques used in green cloud which focus on improving the energy efficiency is presented, revealing pitfalls and suggesting improvisation methods along this direction.
••
TL;DR: An automatic and effective tomato fruit grading system based on computer vision techniques is proposed and it was observed that the proposed method was successful with 96.47% accuracy in evaluating the quality of the tomato.
••
TL;DR: This paper collects and analyzes the current practice on maturity models, by analyzing a collection of maturity models from literature.
••
TL;DR: The motivation for the challenge, its data sets, tasks and baseline systems, and the results obtained by participating teams show great promise; many systems beat the provided baselines and some even perform better than comparable supervised systems.
••
TL;DR: The experimental results indicate that the proposed wavDAE method outperforms the state-of-the-art classifiers both in efficiency and accuracy.
••
TL;DR: This work considers Variational Bayes (VB) as alternative inference process and shows that, notwithstanding VB inference is an order of magnitude faster, it outperforms GS in terms of accuracy.