Showing papers in "Procedia Computer Science in 2017"
••
TL;DR: The resources used for building the models, the employed data cleaning techniques, the carried out preprocessing step, as well as the details of the employed word embedding creation techniques are described.
380 citations
••
TL;DR: A novel Deep Neural Network architecture for short term load forecasting that integrates multiple types of input features by using appropriate neural network components to process each of them and can be applied to other time series prediction tasks.
209 citations
••
TL;DR: This paper presents a method to predict the solar irradiance using deep recurrent neural networks (DRNNs), which can outperform all other methods, as the performance tests indicate.
191 citations
••
TL;DR: Transferred deep learning proved to be an efficient automatic cardiac arrhythmia detection method while eliminating the burden of training a deep convolutional neural network from scratch providing an easily applicable technique.
177 citations
••
TL;DR: A pervasive monitoring system that can send patients physical signs to remote medical applications in real time and four data transmission modes are presented taking patients risk, medical analysis needs, demands for communication and computing resources into consideration.
156 citations
••
TL;DR: The result shows that the proposed approach to understand situations in the real world with the sentiment analysis of Twitter data base on deep learning techniques achieves better accuracy performance in twitter sentiment classification than some of traditional method such as the SVM and Naive Bayes methods.
151 citations
••
TL;DR: Two opposite approaches are described and an algorithmic solution that synthesizes the main concerns is proposed that raises awareness about concerns and opportunities for businesses that are currently on the quest to help automatically detecting fake news by providing web services, but who will most certainly, on the long term, profit from their massive usage.
143 citations
••
TL;DR: These methods in the field of topic segmentation for both languages Arabic and English are investigated and it is found out that LSA, Word2Vec and GloVe depend on the used language.
133 citations
••
TL;DR: This paper aims to present the state-of-the-art security and privacy issues in big data as applied to healthcare industry and discuss some available data privacy, data security, users’ accessing mechanisms and strategies.
132 citations
••
TL;DR: This study proposes a genetic algorithm (GA) based trained recurrent fuzzy neural networks (RFNN) to diagnosis of heart diseases and the results were found to be satisfying based on comparison.
128 citations
••
TL;DR: A WSN prototype consisting of MicaZ nodes which are used to measure greenhouses’ temperature, light, pressure and humidity are presented which can be controlled from mobile phones or computers which have internet connection.
••
TL;DR: This paper proposes an application prototype for precision farming using a wireless sensor network with an IOT cloud, which represents platforms that allow to create web services suitable for the objects integrated on the Internet.
••
TL;DR: UMAFall is described, a new dataset of movement traces acquired through the systematic emulation of a set of predefined ADLs (Activities of Daily Life) and falls that offer an interesting tool to investigate the importance of the sensor placement for the effectiveness of the detection decision in FDSs.
••
TL;DR: The paper investigates three variants of Recurrent Neural Networks (RNNs) and compares them against the state-of-art methods such as Support Vector Machines (SVMs), Na¨ive Bayes (NB), Hidden Markov Models (HMMs), Hidden Semi-Markov models (HSMM) and Conditional Random Fields (CRFs).
••
TL;DR: This study attempts to build a system that can predict a person’s personality based on Facebook user information by implementing some deep learning architectures and succeeds to outperform the accuracy of previous similar research.
••
TL;DR: This paper intends to provide detailed overview based on literature of smart cities’ major security problems and current solutions, and presents several influencing factors that affect data and information security in smart cities.
••
TL;DR: Results show that applying word embedding with ensemble and SMOTE can achieve more than 15% improvement on average in F 1 score over the baseline, which is a weighted average of precision and recall and is considered a better performance measure than accuracy for imbalanced datasets.
••
TL;DR: This paper summarizes a number of peer-reviewed articles on security threats in cloud computing and the preventive methods to understand the cloud components, security issues, and risks, along with emerging solutions that may potentially mitigate the vulnerabilities in the cloud.
••
TL;DR: The details of collecting and constructing a large dataset of Arabic tweets and the annotation process are presented in detail and the challenges during the annotation are highlighted.
••
[...]
TL;DR: Investigation of the attitude of university students about the use of E-learning based on the Technology Acceptance Model indicated that attitude was a significant predictor towards student's intention to use E-Learning.
••
TL;DR: An attempt is made to determine the best feature set that results in maximum classification accuracy and the result indicates feature vector with best features having a strong influence in stress identification.
••
TL;DR: This paper proposes a method able to classify patients affected by diabetes using a set of characteristic selected in according to World Health Organization criteria, and evaluates real-world data using state of the art machine learning algorithms.
••
TL;DR: It is argued in this paper that the first phase for universal usability of IoT within the smart health domain is to ensure that digital health citizens are fully aware of what they are consenting to when they register an account with such technological artefacts.
••
TL;DR: The result of DO showed that both the ANN and AnFIS can be applied in modelling DO concentration in Agra city, and also indicate that, ANN model is slightly better than ANFIS and also indicates a considerable superiority to MLR.
••
TL;DR: Experimental results demonstrate that the method based on machine learning algorithms and semantic sentiment analysis can extract predictions of suicidal ideation using Twitter Data and verify the effectiveness of performance in term of accuracy and precision on semantic sentimentAnalysis that could thinking of suicide.
••
TL;DR: The results show that the system is able to achieve continuous glucose monitoring remotely in real-time and reveals that a high level of energy efficiency can be achieved by applying the customized nRF component, the power management unit and the energy harvesting unit altogether in the sensor device.
••
TL;DR: It is determined that such a thoroughly unprecedented model development effort will require a national commitment on par with the Manhattan Project, which yielded the first atomic bomb.
••
TL;DR: The proposed approach is used to obtain a segmented tumor region clear enough to be observed by the medical practitioner and give them more detail about the tumor in their diagnosis to develop a method for clearly distinguishing the tissues affected by the cancer.
••
TL;DR: A supervised learning method for irony detection in Arabic tweets using four groups of features whose efficiency has been empirically proved in other languages such as French, English, Italian, Dutch and Japanese is presented.
••
TL;DR: This paper proposes a framework to extract the features in an unsupervised (or self-supervised) manner using deep learning, particularly stacked LSTM Autoencoder Networks, and applies it on sensor time series data from the process industry to detect the quality of the semi-finished products and accordingly predict the next production process step.