Natural Language & Time Series Prediction 2016


Notes:

Time Series Prediction may also be known as “Time Series Forecasting”.

Wikipedia:

See also:

100 Best SPSS Videos | SPSS & Dialog Systems


Recurrent neural networks for multivariate time series with missing values
Z Che, S Purushotham, K Cho, D Sontag… – arXiv preprint arXiv …, 2016 – arxiv.org
… variety of missing values. In time series prediction and other related tasks, it has been noted that missing values and their missing patterns are often correlated with the target labels, aka, informative miss- ingness. There is very …

Bayesian analysis of time series using granular computing approach
O Hryniewicz, K Kaczmarek – Applied Soft Computing, 2016 – Elsevier
… methods for the time series analysis are proven successful in many practical applications, eg, [1], [2] and [3]. Nonetheless, the Bayesian time series analysis and probability theory are not meant to process directly the information described in natural language, and according to …

Empirical analysis: stock market prediction via extreme learning machine
X Li, H Xie, R Wang, Y Cai, J Cao, F Wang… – Neural Computing and …, 2016 – Springer

Lstm-based encoder-decoder for multi-sensor anomaly detection
P Malhotra, A Ramakrishnan, G Anand, L Vig… – arXiv preprint arXiv …, 2016 – arxiv.org
… Other variants have been pro- posed for natural language generation and reconstruction (Li et al., 2015), parsing (Vinyals et al., 2015), image cap … 3) A time-series prediction based anomaly detection model LSTM-AD (Malhotra et al., 2015) gives better results for the predictable …

Deep convolutional neural network based regression approach for estimation of remaining useful life
GS Babu, P Zhao, XL Li – … conference on database systems for advanced …, 2016 – Springer
… natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th International Conference on Machine Learning, pp. 160–167. ACM (2008). 6. Connor, JT, Martin, RD, Atlas, LE: Recurrent neural networks and robust time series prediction. …

Time series prediction for evolutions of complex systems: A deep learning approach
P Jiang, C Chen, X Liu – Control and Robotics Engineering …, 2016 – ieeexplore.ieee.org
… are common supervised learning methods in statistical learning field, which have been widely applied for nonlinear time series prediction in finance … used the SVM layer to replace the SOFTMAX layer for classification task in natural language understanding, whose results show …

A soft computing framework for classifying time series based on fuzzy sets of events
J Ares, JA Lara, D Lizcano, S Suárez – Information Sciences, 2016 – Elsevier
… each event. The problem is tougher if the experts are required to express their opinions as numerical values or in natural language, as they are not able to give an exact numerical value to express their opinions. Successful …

Continuous online sequence learning with an unsupervised neural network model
Y Cui, S Ahmad, J Hawkins – Neural computation, 2016 – MIT Press
… and machine learning algorithms achieve impressive prediction accuracy on benchmark problems However, most time-series prediction benchmarks do … Similar dense distributed representations are commonly used for LSTM in natural language processing applications (Mikolov …

Layered ensemble architecture for time series forecasting
MM Rahman, MM Islam, K Murase… – IEEE transactions on …, 2016 – ieeexplore.ieee.org
Page 1. 270 IEEE TRANSACTIONS ON CYBERNETICS, VOL. 46, NO. 1, JANUARY 2016 Layered Ensemble Architecture for Time Series Forecasting Md. Mustafizur Rahman, Md. Monirul Islam, Member, IEEE, Kazuyuki Murase, and Xin Yao, Fellow, IEEE …

Fuzzy rule base ensemble generated from data by linguistic associations mining
M Št?pni?ka, M Burda, L Št?pni?ková – Fuzzy Sets and Systems, 2016 – Elsevier
… As there are many various methods for time series prediction developed but none of them generally outperforms all the others, there always … systems of fuzzy/linguistic IF–THEN rules are evaluative linguistic expressions [23], ie, special expressions of a natural language that are …

Learning over long time lags
H Salehinejad – arXiv preprint arXiv:1602.04335, 2016 – arxiv.org
… into a fixed-size representation [63]. The modified version of FFNNs by adding recurrent connections is called recurrent neural networks (RNNs), which are capable of modelling sequential data for sequence recognition, sequence production, and time series prediction [3]. …

Deep learning architecture for air quality predictions
X Li, L Peng, Y Hu, J Shao, T Chi – Environmental Science and Pollution …, 2016 – Springer
… academic and industrial attention (Bengio 2009) and has been successfully applied to image classification, natural language processing, prediction task … tasks for each station separately for the SVR and ARMA methods, which are merely time series prediction models, using data …

Software reliability prediction via relevance vector regression
J Lou, Y Jiang, Q Shen, Z Shen, Z Wang, R Wang – Neurocomputing, 2016 – Elsevier
The aim of software reliability prediction is to estimate future occurrences of software failures to aid in maintenance and replacement. Relevance vector machin.

Financial time series forecasting using rough sets with time-weighted rule voting
M Podsiadlo, H Rybinski – Expert Systems with Applications, 2016 – Elsevier
… SVM is increasingly popular in financial time series prediction (Cao, Tay, 2003, Huang, Nakamori, Wang, 2005 and Kim, 2003), and compares favorably to other neural network … it is possible to generate decision rules that can be expressed in natural language (if …then rules); • …

Towards Modeling Confidentiality in Persuasive Robot Dialogue
ID Addo, SI Ahamed, WC Chu – … Conference on Smart Homes and Health …, 2016 – Springer
… In: 2011 7th International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE), Tokushima, pp. 285–288 (2011). 10. … Gianluca, B.: Machine learning strategies for time series prediction. In: Machine Learning Summer School (2013). …

Mixed-initiative for big data: the intersection of human+ visual analytics+ prediction
S Makonin, D McVeigh, W Stuerzlinger… – … (HICSS), 2016 49th …, 2016 – ieeexplore.ieee.org
… Rather than using a natural language dialogue, which currently limits the range of understanding for the machine-agent, the use of visual metaphors can play an im- portant role as a basis of communication through workspaces. …

Exploiting twitter moods to boost financial trend prediction based on deep network models
Y Huang, K Huang, Y Wang, H Zhang, J Guan… – … on Intelligent Computing, 2016 – Springer
… In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, Doha, Qatar, A meeting of … Giacomel, F., Pereira, AC, Galante, R.: Improving financial time series prediction through output classification by a neural network ensemble …

Hand motion identification of grasp-and-lift task from electroencephalography recordings using recurrent neural networks
J An, S Cho – Big Data and Smart Computing (BigComp), 2016 …, 2016 – ieeexplore.ieee.org
… With the advent of deep learning algorithm and graphics processing units (GPU) computing, LSTMs has been widely used to model sequences in fields of Natural language processing, speech recognition and time series prediction. …

Learning-based power prediction for data centre operations via deep neural networks
Y Li, H Hu, Y Wen, J Zhang – … of the 5th International Workshop on …, 2016 – dl.acm.org
Page 1. Learning-Based Power Prediction for Data Centre Operations via Deep Neural Networks Yuanlong Li Nanyang Technological University Singapore liyuanl@ntu.edu.sg Han Hu Nanyang Technological University Singapore hhu@ntu.edu.sg …

Temporal kernel descriptors for learning with time-sensitive patterns
D Sahoo, A Sharma, SCH Hoi, P Zhao – Proceedings of the 2016 SIAM …, 2016 – SIAM
… prediction [5]. These methods address a slightly different problem and do not exploit timestamp information to improve predictability. Some efforts have been made to use tree-kernels for linking events to timestamps [24, 14], but here the focus is primarily on natural language …

Training iterative collective classifiers with back-propagation
S Fan, B Huang – … Workshop on Mining and Learning with …, 2016 – pdfs.semanticscholar.org
… iteration. RNNs were introduced decades ago [1, 3], but they have recently become prominent because of their effectiveness at modeling sequences, such as those occurring in natural language processing, eg, [6, 7, 18, 22]. …

Shallow Recurrent Neural Network for Personality Recognition in Source Code.
Y Doval, C Gómez-Rodríguez, J Vilares – FIRE (Working Notes), 2016 – ceur-ws.org
… strained and formal than natural language due to its very nature, it also allows for some personal preferences to pour down into its structure and content, giving rise to the pos- sibility of author profiling on it. … Recurrent neural networks and robust time series prediction. …

Sequentially supervised long short-term memory for gesture recognition
P Wang, Q Song, H Han, J Cheng – Cognitive Computation, 2016 – Springer
… Recurrent neural networks, including LSTM, are successfully used in time series prediction problems, such as machine translation, natural language process and music composition. In all these tasks, the outputs of RNNs are time series. …

Long short-term memory model for traffic congestion prediction with online open data
Y Chen, Y Lv, Z Li, FY Wang – … Transportation Systems (ITSC) …, 2016 – ieeexplore.ieee.org
… about the traffic jams or traffic incidents, eg “what a traffic jam, I am going to be late again.” To mining text messages, natural language processing methods … 20] JT Connor, RD Martin, and LE Atlas, “Recurrent neural networks and robust time series prediction,” IEEE Transactions …

Recurrent marked temporal point processes: Embedding event history to vector
N Du, H Dai, R Trivedi, U Upadhyay… – Proceedings of the …, 2016 – dl.acm.org
… model- ing. For instance, in Natural Language Processing, recurrent neural network has state-of-the-arts predictive performance for sequence-to-sequence translations [24], image caption- ing [38], handwriting recognition [18]. It …

Analysis and Forecasting of Time Series
V Novák, I Perfilieva, A Dvo?ák – Insight into Fuzzy Modeling – Wiley Online Library
… of fuzzy natural logic. The proposed methodology consists of three phases: analysis of time series, prediction of its future course, and evaluation of its current and future course in natural language. The analysis of time series …

Neural Network: An Alternative Statistical Model for Predicting Financial Time Series Data
MY Vandi – International Journal of Innovative Research and …, 2016 – 52.172.159.94
… 2. Neural Network In a quest to build an intelligent machine in the hope of achieving human like performance in the field of speech and pattern recognition, natural language processing, decision making in fuzzy situation etc., we have … Noisy time series prediction using recurrent …

Financial Time-Series Data Analysis Using Deep Convolutional Neural Networks
JF Chen, WL Chen, CP Huang… – … Computing and Big …, 2016 – ieeexplore.ieee.org
… a hybrid model, the combination of genetic algorithm for technical indicators and neural network for other data, as a new time series prediction method. … So far, deep learning has an outstanding result in image classification, audio or natural language processing applications. …

Robust Online Time Series Prediction with Recurrent Neural Networks
T Guo, Z Xu, X Yao, H Chen, K Aberer… – Data Science and …, 2016 – ieeexplore.ieee.org
… In this paper we focus on online time series prediction in the presence of both change points and outliers. … The LSTM achieves state-of-the-art results for problems spanning natural language processing, image captioning, handwriting recognition, and genomic analysis [20], [24 …

Forecasting of Short Time Series with Intelligent Computing
K Kaczmarek, O Hryniewicz – Challenging Problems and Solutions in …, 2016 – Springer
… 195–206 (2013)CrossRef. 9. Burda, M., Št?pni?ka, M., Št?pni?ková, L.: Fuzzy rule-based ensamble for time series prediction: progresses with … Kacprzyk, J., Zadro?ny, S.: Protoforms of linguistic data summaries: towards more general natural-language-based data mining tools. …

A Hybrid Approach for Time Series Forecasting Using Deep Learning and Nonlinear Autoregressive Neural Networks
S Narejo, E Pasero – 2016 – researchgate.net
… The traditional approaches to time series prediction, such as the ARIMA or Box Jenkins [3]-[7] undertake the time series as … learning has given marvelous performance not only in computer vision, speech recognition, phonetic recognition, natural language processing, semantic …

Guest editorial: special issue on predictive analytics using machine learning
AB Nassif, M Azzeh, S Banitaan, D Neagu – 2016 – Springer
… The proposed filter extracts natural language attributes from email text that are closely related to writer stylometry and generate … In “Combining time series prediction models using genetic algorithm to autoscaling Web applications hosted in the cloud infrastructure”, Messias et al. …

Time series prediction with simple recurrent neural networks
SA Abdulkarim – Bayero Journal of Pure and Applied Sciences, 2016 – ajol.info
… “Natural Language Grammatical Inference with Recurrent Neural Networks.” IEEE Transaction on Knowledge and Data Engineering 12(1): 126–40. … “Noisy Time Series Prediction Using Recurrent Neural Networks and Grammatical Inference.” Machine Learning 44(1): 161–83. …

Recurrent Neural Networks for One Day Ahead Prediction of Stream Flow
Z Mhammedi, A Hellicar, A Rahman, K Kasfi… – Proceedings of the …, 2016 – dl.acm.org
… The Support Vector Regression (SVR) and the Vector Auto Regression (VAR) are standard methods used for time series prediction [12, 14]. … 25 Page 2. used in many applications such as natural language process- ing and image recognition [17, 19]. …

Pattern recognition using linguistic fuzzy logic predictors
H Habiballa – AIP Conference Proceedings, 2016 – aip.scitation.org
… This method should be used not only to the time series prediction itself, but also for recognition of patterns in a signal … Preliminary results show interesting results based on the unique capability of this approach bringing natural language interpretation of particular prediction ie …

Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life
SB Giduthuri, Z Peilin, L Xiao-Li – 2016 – oar.a-star.edu.sg
… natural language processing: Deep neural networks with multitask learning. In: Proceedings of the 25th international conference on Machine learning. pp. 160–167. ACM (2008) 6. Connor, JT, Martin, RD, Atlas, LE: Recurrent neural networks and robust time series prediction. …

Paragraph Vector Representation Applied to Sequential Data……… 7
E NOVA – 2016 – research.euranova.eu
… MACHINE LEARNING & DATA SCIENCE TIME SERIES PREDICTION WITH DEEP LEARNING AND BAYESIAN METHODS … Context: In these past years, the Natural Language Processing community has seen a significant interest in learning meaningful representation of words. …

Paper Authors
B Hu, X Jiang, S Matwin – 2016 – m.ibm.com
… A natural language question answering (NLQA) service is a CEDP cognitive computing service trained to recognize natural language questions and … solution on the KDD Cup 2016 dataset by formalizing affiliation ranking as an event count time series prediction problem. …

A comparative study of predictive algorithms for business analytics and decision support systems: Finance as a case study
M Ouahilal, M El Mohajir, M Chahhou… – Information …, 2016 – ieeexplore.ieee.org
… Stock market prediction is regarded as a challenging task of financial time-series prediction. … B. Diagnostic analytics Diagnostic analytics determine why something happened, using content analytics and natural language processing to cull insights found in documents, email …

Research Interest? Theory: information theory, statistical machine learning, empirical processes, kernel methods.
Z Szabó – pdfs.semanticscholar.org
… natural language processing, structured sparsity, recommender systems) 2012–2013 US Air Force (Innovation Engine for Blogspaces; natural language processing, 2007–2011 structured sparsity, dictionary learning) Morgan Stanley (financial time series: prediction, hedging) …

Learning Quality Evaluation of MOOC Based on Big Data Analysis
Z Zhao, Q Wu, H Chen, C Wan – International Conference on Smart …, 2016 – Springer
… combine click-stream data and natural language processing (NLP) approaches to examine if students’ on-line activity and the language … valuable info out of massive data via common DM methods, such as clustering, classification, association rule, time series, prediction and so …

Traffic flow prediction with Long Short-Term Memory Networks (LSTMs)
H Shao, BH Soong – Region 10 Conference (TENCON), 2016 …, 2016 – ieeexplore.ieee.org
… Traffic prediction finds its root in time-series prediction problems in which one attempts to predict a variable at current state based on a series of past samples of the variable at … [8]. It has been proved successful in various areas such as natural language processing, speech …

Recent Developments and New Direction in Soft-Computing Foundations and Applications: Selected Papers from the 4th World Conference on Soft …
LA Zadeh, AM Abbasov, RR Yager, SN Shahbazova… – 2016 – books.google.com
… 19 MH Mammadova, ZQ Jabrayilova and FR Mammadzada Learning User Intentions in Natural Language Call Routing Systems … Optimization of Type-1 and Interval Type-2 Fuzzy Integrators in Ensembles of ANFIS Models for Time Series Prediction….. …

Bridging LSTM architecture and the neural dynamics during reading
P Qian, X Qiu, X Huang – arXiv preprint arXiv:1604.06635, 2016 – arxiv.org
… LSTM) [Hochreiter and Schmidhuber, 1997] has attracted recent in- terest and gives state-of-the-art results in many tasks, such as time series prediction, adaptive robotics and … A unified architecture for natural language pro- cessing: Deep neural networks with multitask learning. …

Exchange Rate Prediction from Twitter’s Trending Topics
F Ozcan – 2016 – sites.uci.edu
… term exchange rates. This paper is also the first paper that makes use of unsupervised learning2 in topic extraction, in exchange rate prediction using natural language processing. … falls into the second strand which uses text mining techniques in time series prediction. …

Time series forecasting of stock market index
U Agarwal, AS Sabitha – Information Processing (IICIP), 2016 …, 2016 – ieeexplore.ieee.org
… In rapid miner, time Series Prediction approach uses two main data transformational processes: … 263-270. [10] SS Abdullah, MS Rahaman and MS Rahman, “Analysis of stock market using text mining and natural language processing,” Informatics, Electronics & Vision (ICIEV …

Information Visualization Techniques for Big Data
WH Hsu – kdd.cs.ksu.edu
… Spatiotemporal sequences arise in analytical applications such as time series prediction and monitoring, sensor integration, and multimodal human-computer intelligent interaction. … Page 10. 3.2 Text Analytics: Visualizing Natural Language 3.2.1 Text Annotation and Markup …

Fuzzy Time Series: An Application in E-Commerce
A Karasan, ? Sevim, M Çinar – Handbook of Research on …, 2016 – books.google.com
… NL-Computation is of direct relevance to mechanization of natural language understanding and computation with imprecise probabilities. … and fuzzy forecasting In the proposed method, there are still limitations needed to improve such as A fuzzy time series prediction model was …

DUT-NLP-CH@ NTCIR-12 Temporalia TID Subtask.
J Pei, D Huang, J Ma, D Song, L Sang – NTCIR, 2016 – research.nii.ac.jp
… [3] CD Manning, M. Surdeanu, J. Bauer, JR Finkel, S. Bethard, and D. McClosky. The Stanford CoreNLP Natural Language Processing Toolkit. In ACL (System Demonstrations), … Google Trends 2. Time-series Prediction ARMA model to predict the “future” volume after …

Research advances in fault diagnosis and prognostic based on deep learning
G Zhao, G Zhang, Q Ge, X Liu – Prognostics and System Health …, 2016 – ieeexplore.ieee.org
… applied successfully in the field of object recognition [8] (2008), voice recognition [9] (2009) and natural language processing [10 … Aircraft engine and electric power transformer [7] Compressor valves [13] Time Series Prediction [14] Cutting states monitoring [22] Bearing fault [23 …

Randomized Deep Recurrent Neural Networks
L Pedrelli, A Micheli, DC Gallicchio – di.unipi.it
… as natural language processing, image classification and automatic playing. There are many application areas to explore where evaluate the power of DL paradigm. In the field of time series prediction where the temporal data has a multiple time-scales …

Predicting the scale of trending topic diffusion among online communities
D Kim, SC Han, S Lee, BH Kang – Pacific Rim Knowledge Acquisition …, 2016 – Springer
… The philosophies behind these techniques are very different, but each has been shown to be effective in several time-series prediction studies. 5.3 Evaluation Result. … In: Proceedings of the Third Conference on Applied Natural Language Processing, pp. 170–177. …

Recent Developments and New Direction in Soft-Computing Foundations and Applications
LA Zadeh, AM Abbasov, RR Yager, SN Shahbazova… – Springer
… 19 MH Mammadova, ZQ Jabrayilova and FR Mammadzada Learning User Intentions in Natural Language Call Routing Systems … Optimization of Type-1 and Interval Type-2 Fuzzy Integrators in Ensembles of ANFIS Models for Time Series Prediction….. …

LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection
TAM SHROFF – researchgate.net
… Other variants have been pro- posed for natural language generation and reconstruction (Li et al., 2015), parsing (Vinyals et al., 2015), image cap … 3) A time-series prediction based anomaly detection model LSTM-AD (Malhotra et al., 2015) gives better results for the predictable …

A Multi-Scale Approach to Data-Driven Mass Migration Analysis.
MN Ahmed, G Barlacchi, S Braghin… – SoGood@ ECML …, 2016 – ceur-ws.org
… The analytical frame- work consists of three separate models (a) a global push-pull model to es- timate macro-patterns, (b) a time-series prediction model for estimating … Documents are annotated applying a combination of state-of-the-art natural language processing techniques. …

Corpus based part-of-speech tagging
C Lv, H Liu, Y Dong, Y Chen – International Journal of Speech Technology, 2016 – Springer
… A genetic algorithm for the induction of natural language grammars. In Proc IJCAI-95 workshop on new approaches to learning for natural language processing (pp. 17–24). … Zuo, J., Tang, C., et al. (2004). Time series prediction based on gene expression programming. …

Advances in Intelligent Decision-Making Technology Support
JW Tweedale, G Phillips-Wren, LC Jain – Intelligent Decision Technology …, 2016 – Springer
… Fuzzy logic introduces natural language membership functions, based on underlying truth statements represented by the Boolean values of … to conduct supervised learning in AI application to solve problems where regression, classification and time series prediction are required …

Predicting unusual surges in a time series
W Sun – 2016 – library2.smu.ca
… statistics pertinent to an understanding the data.[1] Time series prediction uses previously-observed findings to predict future occurrences. … published research. Syntactic natural language parsers, in contrast, are usually inadequate …

Multiple Kernel Learning Algorithms and Their Use in Biomedical Informatics
EE Tripoliti, M Zervakis, DI Fotiadis – XIV Mediterranean Conference on …, 2016 – Springer
… they have proven to be a pow- erful tool for a wide range of different data analysis prob- lems, including optical pattern, object recognition, text categorization, time series prediction, gene expression pro- file analysis, DNA and protein analysis, natural language processing, and …

Sentiment Analysis Levels and Techniques: A Survey
P Patil, P Yalagi – space – ijiet.com
… The analysis of such emotions of users is sentiment analysis. It is a natural language processing task that uses computational approach to identify the opinion and classify it as positive, negative or neutral. … benchmarking time-series prediction tests …

Sparse sampling for sensing temporal data—building an optimized envelope
M Domb, G Leshem, E Bonchek-Dokow… – … and Applications of …, 2016 – ieeexplore.ieee.org
… We can apply dictionary learning to sequential data, for tasks such as natural language processing, video analysis; as well as to non-sequential data. … Given the sequential data, one purpose could be classification, and another, time series prediction. …

Enterprise Architecture Analytics and Decision Support
R Schmidt, M Möhring – Emerging Trends in the Evolution of Service …, 2016 – Springer
… However, this is done in natural language and does not follow a predefined or at least standardized structure. … Int. J. Forecast. 15, 421–430 (1999)CrossRefMATH. 49. Faruk, D.Ö.: A hybrid neural network and ARIMA model for water quality time series prediction. Eng. Appl. Artif. …

Training Strategies for Time Series: Learning for Filtering and Reinforcement Learning
A Venkatraman – 2016 – cs.cmu.edu
… First, we introduce a new training algorithm for time-series prediction, Data as Demonstrator (DaD), based on the DAgger approach (Ross et al., 2011a) that improves the multi-step predictive capability of time-series models. … Recursive Time Series Prediction: (3.5) …

CERN Accelerating science
SFHFB To, CAS Work – cds.cern.ch
… by Oguri, K. A Formal Model of an Artificial Neural Network Used to Store and Recognize the Semantics of Some Sentences of Natural Language (p. 919). by Pelc, T. … by Oh, SH. Neural Approach to Time Series Prediction with Noise Addition (p. 1012). by Jo, TC. …

Semi-Supervised Learning Vector Quantization method enhanced with regularization for anomaly detection in air conditioning time-series data
I Andriushchenko – 2016 – aaltodoc.aalto.fi
… This method was used for natural language classification [96], image classifica- tion [97] and Vector Quantization [2]. The actual method used as the base for developing this project’s model is using an adaptation of the self-training prin- ciple when defining a low-confidence …

An Empirical Study and Comparison for Tweet Sentiment Analysis
L Yan, H Tao – International Conference on Cloud Computing and …, 2016 – Springer
… RNN. Recurrent Neural networks (RNNs) have been a very competitive classifier for Natural Language Processing. … LSTM has been widely used for text recognition, speech recognition, and time series prediction problems, etc. 4 Data Sets. …

Avian Influenza Risk Surveillance in North America with Online Media
C Robertson, L Yee – PloS one, 2016 – journals.plos.org
… Fig 2. Data modelling, outbreak detection, and natural language processing pipeline. http://dx.doi.org/10.1371/journal.pone.0165688.g002. Once ‘outbreak … language processing. Natural Language Processing of AI-Related Twitter Messages. …

Using recurrent neural networks toward black-box system anomaly prediction
S Huang, C Fung, K Wang, P Pei… – Quality of Service …, 2016 – ieeexplore.ieee.org
… This allows it to perform certain tasks such as sequence prediction better than other neural networks. In this case, each set of hidden layer weights now only appears only once, so it is possible to applied to time series prediction. …

Design of Experiments—Statistical and Artificial Intelligence Analysis for the Improvement of Machining Processes: A Review
CH Lauro, RBD Pereira, LC Brandão… – Design of Experiments in …, 2016 – Springer
… models; inputs limited. Tolerant of imprecise data; easy to understand since it is based on natural language; models can be built on top of the experience of experts; good extrapolation capability. ANFIS. 10 %. Drawbacks: many …

A comparison of time series forecasting learning algorithms on the task of predicting event timing
NA Boukary – 2016 – espace.rmc.ca
Page 1. A COMPARISON OF TIME SERIES FORECASTING LEARNING ALGORITHMS ON THE TASK OF PREDICTING EVENT TIMING UNE COMPARAISON DES ALGORITHMS D’APPENTISSAGE DE PREVISION DES SERIES …

Deep self-organizing reservoir computing model for visual object recognition
Z Deng, C Mao, X Chen – Neural Networks (IJCNN), 2016 …, 2016 – ieeexplore.ieee.org
… It enables RNNs to be extensively used for nonlinear time series prediction [1], [2] as well as for polyphonic music generation [3], text se- quence analysis [4], and analysis of video stream data [5]. Although RNN is generally regarded to have promising po- tential and a wide …

Granular transfer learning using type-2 fuzzy HMM for text sequence recognition
S Sun, J Yun, H Lin, N Zhang, A Abraham, H Liu – Neurocomputing, 2016 – Elsevier
Context information plays an important role in text sequence recognition, but it is difficult to harness the uncertainty caused by conflicting implications. In.

A Review on Evolving Interval and Fuzzy Granular Systems
D Leite, P Costa Jr, F Gomide – researchgate.net
… In this sense, a granular system provides NL-capability [12], that is, capability to operate on information described in Natural Language. NL-capability is important because much of human knowledge is described in natural language. …

MICHAEL C. MOZER
B November – pdfs.semanticscholar.org
Page 1. Curriculum Vitae MICHAEL C. MOZER Address Department of Computer Science University of Colorado Boulder, CO 80309–0430 Phone (303) 492–4103 E-mail mozer@colorado.edu WWW http://www.cs.colorado.edu/~mozer Birthdate November 20, 1958 …

Survey on Message Filtering Techniques for On-line Social Network
MN Rajkumar, P Kayathri, V Dhurka – World Scientific News, 2016 – search.proquest.com
… The bag-of-words model is a simplifying representation used in natural language processing and information retrieval (IR). … Radial basis function networks have many uses, including function approximation, time series prediction, classification, and system control. …

An Enhanced Text Categorization Technique for Document Classification Using Neural Networks
V Kumthavalli, V Vallimayil – ijitce.co.uk
… Text categorization is the assignment of natural language documents to one or more predefined categories based on their semantic content is an important component in many information organization and management tasks [1][2]. The techniques of text categorization are …

Big sensor data applications in urban environments
LM Ang, KP Seng – Big Data Research, 2016 – Elsevier
… correlations) in the sensor data. Achieved the time series prediction of PM 2.5 12 hours ahead from the current instant and outperformed the Japanese Government PM 2.5 VENUS prediction system. [22]. Zurich, Over 50 million …

D2. 1–Real Time Stream Mining Library V1
A Benczur – h2020-streamline-project.eu
… Possbile further candidates for investigation are • Mahout linear algebra ports; • The AMIDST toolbox for time series prediction; • DL4J deep learning library with the ND4J linear algebra library. Page 17. D2.1 – Real Time Stream Mining Library V1 17 3 Utilities …

Evolutionary Feature Subset Selection with Compression-based Entropy Estimation
P Krömer, J Platoš – Proceedings of the 2016 on Genetic and …, 2016 – dl.acm.org
… 3.1 Entropy-based feature selection Various forms of entropy calculation and estimation are frequently used in many application areas, especially in com- putational linguistics, natural language processing, and in- formation processing. Berger et al. …

Learning abstract snippet detectors with Temporal embedding in convolutional neural Networks
J Liu, K Zhao, B Kusy, J Wen, K Zheng… – … (ICDE), 2016 IEEE …, 2016 – ieeexplore.ieee.org
… Interestingly, such advantages of convolutional neural networks are present not only in vision tasks, but also in speech recognition [1], [8], [12] and natural language processing [6], [7]. Now we consider the periodical time-series prediction prob- lem for data such as daily …

Human Action Recognition Using Variational Bayesian HMM with Dirichlet Process Mixture of Gaussian Wishart Emission Model
W Cho, S Kang, S Kim, S Park – World Academy of Science, Engineering …, 2016 – waset.org
… series data, with applications including speech recognition, natural language processing, protein sequence modeling and genetic alignment, general data compression, information retrieval, motion video analysis and object tracking, and financial time series prediction [1]. The …

Input displacement neuro-fuzzy control and object recognition by compliant multi-fingered passively adaptive robotic gripper
D Petkovi?, S Shamshirband, NB Anuar… – Journal of Intelligent & …, 2016 – Springer
… ANNs are a family of intelligent algorithms which can be used for time series prediction, classifica- tion, and control and identification purposes. … Linguistic variables, defined as variables whose values are sentences in a natural language (such as large or small), may be rep …

Application of machine learning: automated trading informed by event driven data
JW Leung – 2016 – dspace.mit.edu
Page 1. Application of Machine Learning: Automated Trading Informed by Event Driven Data by Jason W. Leung Submitted to the Department of Electrical Engineering and Computer Science in partial fulfillment of the requirements for the degree of …

Real time motion estimation using a neural architecture implemented on GPUs
J Garcia-Rodriguez, S Orts-Escolano… – Journal of Real-Time …, 2016 – Springer
Skip to main content Skip to sections This service is more advanced with JavaScript available, learn more at http://activatejavascript.org. …

Analyzing Causality between Actual Stock Prices and User-weighted Sentiment in Social Media for Stock Market Prediction
JT Park – 2016 – theses.ucalgary.ca
… Sentiment Analysis, also known as opinion mining is a research area to extract subjective information from the raw data through natural language processing. As public opinions and … achieve good performance in solving various problems of time series prediction. In this thesis, a …

Artificial neural network
R Akerkar, PS Sajja – Intelligent Techniques for Data Science, 2016 – Springer
… The possible applications of deep learning in the field of data science are given below. Natural language processing and natural query. … Pattern recognition, signal processing, control, time series prediction, and anomaly detection are selected usages of ANN in software today. …

User activities outliers detection; integration of statistical and computational intelligence techniques
S Mahmoud, A Lotfi… – Computational …, 2016 – Wiley Online Library
… Also, in Akhlaghinia (2010), a fuzzy predictor model is used to build the prediction model and then the results are compared with the traditional time series prediction models such as ARMA, adaptive network-based fuzzy inference system and transductive neuro-fuzzy inference …

Web Service SWePT: A Hybrid Opinion Mining Approach.
YR Baca-Gomez, AM Rebollar, P Rosso, H Estrada… – J. UCS, 2016 – jucs.org
… Opinion Mining is a broad area of Natural Language Processing and text mining, which is defined as the computational study of opinions expressed in texts regarding entities such as products, services, organizations, individuals, issues, topics, and their attributes [Liu, 2012 …

Individual investors, social media and Chinese stock market: a correlation study
Y Wu – 2016 – dspace.mit.edu
… 9 Page 16. 1.3 Literature review on Chinese NLP Natural language processing (NLP) is the ability of a computer program to understand hu- man speech as it is spoken. Human languages, usually referred to as natural languages, …

Discovering Patterns With Weak-Wildcard Gaps
CD Tan, F Min, M Wang, HR Zhang, ZH Zhang – IEEE Access, 2016 – ieeexplore.ieee.org
… pm is also a symbolic sequence. For example, in natural language processing, each word can be viewed as a pattern. To automatically extract keywords from a paper, a common approach is to count the number of occur- rences of each word or phrase. …

Harnessing disordered quantum dynamics for machine learning
K Fujii, K Nakajima – arXiv preprint arXiv:1602.08159, 2016 – arxiv.org
… lems. These problems include a variety of real-world tasks such as time-dependent signal processing, speech recognition, natural language processing, sequential mo- tor control of robots, and stock market predictions. Our …

Determining the veracity of rumours on Twitter
G Giasemidis, C Singleton, I Agrafiotis… – … Conference on Social …, 2016 – Springer
… we aggregate by taking the difference between the sentiment of tweets that support the rumour and the sentiment of tweets that deny it, ie \(S^{(i)}-A^{(i)}\). Additionally, some linguistic attributes were extracted using the popular Python library for natural language processing, nltk …

Comparison study of neural network and deep neural network on repricing GAP prediction in Indonesian conventional public bank
H Karisma, DH Widyantoro – Frontiers of Information …, 2016 – ieeexplore.ieee.org
… Washington: McGraw-Hill Series, 1997. [43] T. Du and V. Shanker, “Deep Learning for Natural Language Processing,” Eecis.Udel.Edu, pp. 1–7, 2009. … 265–272, 2011. [46] SC Prasad and P. Prasad, “Deep Recurrent Neural Networks for Time- Series Prediction,” vol. 95070, pp. …

Parallel recurrent neural network architectures for feature-rich session-based recommendations
B Hidasi, M Quadrana, A Karatzoglou… – Proceedings of the 10th …, 2016 – dl.acm.org
… a comprehensive review). RNNs have been used in image and video captioning, time series prediction, natural language processing, conversational models, text and music genera- tion, and much more. Long Short-Term Memory …

Determination of Bearing Capacity of Shallow Foundation Using Soft Computing
J Jagan, S Chowdhury, P Goyal… – Problem Solving and …, 2016 – books.google.com
Page 312. 292 Chapter 14 Determination of Bearing Capacity of Shallow Foundation Using Soft Computing Jagan J. VIT University, India Swaptik Chowdhury VIT University, India Pratik Goyal VIT University, India Pijush Samui …

Match memory recurrent networks
S Samothrakis, T Vodopivec, M Fasli… – … Joint Conference on, 2016 – ieeexplore.ieee.org
Page 1. Match Memory Recurrent Networks Spyridon Samothrakis Institute for Analytics and Data Science University of Essex Wivenhoe Park Colchester CO4 3SQ Email: ssamot@essex.ac.uk Tom Vodopivec Faculty of Computer …

Extended Metacognitive Neuro-Fuzzy Inference System for Biometric Identification
BM Padmanabhuni, K Subramanian… – Recent Advances in …, 2016 – Springer

Predictive Analytics of Social Networks
M Yang, WH Hsu, ST Kallumadi – kdd.cs.ksu.edu
… In general, time series prediction aims to generate estimates for variables of interest that are associated with future states of some domain. … Later researchers explored the use of free text corpora – ie, collections of documents for natural language text in unrestricted form – in this …

Using unsupervised clustering approach to train the Support Vector Machine for text classification
N Shafiabady, LH Lee, R Rajkumar, VP Kallimani… – Neurocomputing, 2016 – Elsevier
The use of learning algorithms for text classification assumes the availability of a large amount of documents which have been organized and labeled correctly b.

Semi-supervised support vector regression based on self-training with label uncertainty: An application to virtual metrology in semiconductor manufacturing
P Kang, D Kim, S Cho – Expert Systems with Applications, 2016 – Elsevier
… With those advantages, SVR has been successfully applied to various areas: response modeling (Kim & Cho, 2012), virtual metrology (VM) (Kang, Kim, Lee, Doh, & Cho, 2011), finance prediction (Pai & Lin, 2005), time-series prediction (Thissen, van Brakel, de Weijer, Melssen …

ELMVIS+: Fast nonlinear visualization technique based on cosine distance and extreme learning machines
A Akusok, S Baek, Y Miche, KM Björk, R Nian… – Neurocomputing, 2016 – Elsevier
This paper presents a fast algorithm and an accelerated toolbox1 for data visualization. The visualization is stated as an assignment problem between data sampl.

Persistent homology of attractors for action recognition
V Venkataraman, KN Ramamurthy… – Image Processing (ICIP …, 2016 – ieeexplore.ieee.org
… 52–57. [3] Liva Ralaivola, Florence d’Alché Buc, et al., “Dynamical modeling with kernels for nonlinear time series prediction,” in Neural … 459–463, 2014. [28] Xiaojin Zhu, “Persistent homology: An introduction and a new text representation for natural language processing,” in …

FINAL REPORT Mining Transportation Information from Social Media for Planned and Unplanned Events
J Gao – 2016 – ntl.bts.gov
… The OPL hybrid model takes advantage of the unique strengths of linear correlation in social media features and SARIMA model in time series prediction. … (2013) built a system called Dublin’s Semantic Traffic Annotator and Reasoner to use natural language processing …

Urban computing using call detail records: mobility pattern mining, next-location prediction and location recommendation
Y Leng – 2016 – dspace.mit.edu
… Recurrent Neural Network is a successful tool in natural language processing, which is applied in mobility prediction due to its acceptance of sequential input, variable input length and ability to learn the ‘meaning’ of cell towers. …

Modeling Vehicular Traffic Shock Wave with Machine Learning Approaches
J Kim – 2016 – escholarship.org
Page 1. …

Hankel matrices for use in Learning Vector Quantization
M Mohammadi – monami.hs-mittweida.de
Page 1. MASTER THESIS Mr./Mrs. Mohammad Mohammadi Hankel matrices for use in Learning Vector Quantization 2016 Page 2. Page 3. Faculty of Applied Computer and Life Sciences MASTER THESIS Hankel matrices for use in Learning Vector Quantization …

Hardware Implementation and Applications of Deep Belief Networks
I Liyangahawatte, GJ Mendis – 2016 – rave.ohiolink.edu
… deep neural networks. Applications of deep learning have been implemented and studied extensively in the areas, such as speech recognition, natural language processing (NLP), music … tion, natural language processing, generating and recognizing images, video sequences …

Research developments in the field neurocomputing
Z Munawar – Cyber and IT Service Management, International …, 2016 – ieeexplore.ieee.org
… knowledge discovery in databases (data mining). Repeat network has been widely applied for time series prediction, pattern recognition, identification and control systems, and natural language processing. V. CONCLUSION …

Neural networks: An overview of early research, current frameworks and new challenges
A Prieto, B Prieto, EM Ortigosa, E Ros, F Pelayo… – Neurocomputing, 2016 – Elsevier
This paper presents a comprehensive overview of modelling, simulation and implementation of neural networks, taking into account that two aims have emerged in t.

Artificial intelligence opportunities and an end-do-end data-driven solution for predicting hardware failures
M Orozco Gabriel – 2016 – dspace.mit.edu
… About one half of the funding has gone into deep learning, one fourth into computer vision, and one eight into natural language processing (NLP). The most … KNN K-nearest neighbor NLI Natural Language Interaction NLP Natural Language Processing …

A multi-objective approach for micro grid energy management based on fuzzy multi-agent decision-making process
M Serraji, EH Nfaoui… – International Journal of …, 2016 – inderscienceonline.com
… 2.2 Fuzzy logic controller Since linguistic rules can simplify the control of complex systems, fuzzy logic has been growing rapidly in last decade. The concept was introduced by Zadeh (1965) to be able to model the uncertainty of natural language. Page 5. 212 M. Serraji et al. …

An improved bat algorithm with artificial neural networks for classification problems
R Gillani, SM Zubair – 2016 – eprints.uthm.edu.my
Page 1. AN IMPROVED BAT ALGORITHM WITH ARTIFICIAL NEURAL NETWORKS FOR CLASSIFICATION PROBLEMS SYED MUHAMMAD ZUBAIR REHMAN GILLANI UNIVERSITI TUN HUSSEIN ONN MALAYSIA Page 2. …

Towards knowledge modeling and manipulation technologies: A survey
AT Bimba, N Idris, A Al-Hunaiyyan, RB Mahmud… – International Journal of …, 2016 – Elsevier
A system which represents knowledge is normally referred to as a knowledge based system (KBS). This article focuses on surveying publications related to knowled.

Deep Neural Networks for Sales Forecasting
N Tyrpáková – dspace.cuni.cz
Page 1. MASTER THESIS Bc. Natália Tyrpáková Deep Neural Networks for Sales Forecasting Department of Theoretical Computer Science and Mathematical Logic Supervisor of the master thesis: Mgr. Martin Pilát, Ph.D. Study programme: Informatics …

Detecting article errors in English learner essays with recurrent neural networks
M Garimella – 2016 – bir.brandeis.edu
… Keras. 4.3 Neural Network Architectures Recurrent neural networks have been found effective at many different natural language tasks perhaps because of their unique architecture. At each time step, the model has information …

Searching web documents using a summarization approach
R Qumsiyeh, R Qumsiyeh, YK Ng… – International Journal of …, 2016 – emeraldinsight.com
… must be coherent and comprehensible, which can be achieved using natural language processing to handle co-reference and the temporal dimension of information (to be introduced in Sections 3.2.2 and 3.2.5, respectively); and. …

DNN classification and forecasting of simulated energy consumption and charging behavior for electric vehicles on the island of la Réunion
J Yao, JJ Hernández-Cabrera, J Évora, K Kilgour – isl.anthropomatik.kit.edu
Page 1. Master’s Thesis DNN classification and forecasting of simulated energy consumption and charging behavior for electric vehicles on the island of la Réunion Jiacheng Yao Handover Date: 30.05.2016 Reviewers: Prof. Alexander Waibel Prof. …

Dynamic sampling in training artificial neural networks with overlapping swarm intelligence
S Qureshi, JW Sheppard – Evolutionary Computation (CEC) …, 2016 – ieeexplore.ieee.org
… Tsou and MacNish achieved the same result as Salerno when attempting to train a recurrent neural network for natural language parsing. … 5, no. 2, p. 157, 1994. [3] X. Cai, N. Zhang, GK Venayagamoorthy, and DC Wunsch, “Time series prediction with recurrent neural networks …

A novel cloud model for risk analysis of water inrush in karst tunnels
Y Wang, X Yin, H Jing, R Liu, H Su – Environmental Earth Sciences, 2016 – Springer
… Unfortunately, many concepts of the investigated objects, including water inrush, are always accompanied by multiple uncertainties. In natural language, there also exist various uncertainties, including randomness, fuzziness, incompleteness and imprecision. …

Multi-target regression via input space expansion: treating targets as inputs
E Spyromitros-Xioufis, G Tsoumakas, W Groves… – Machine Learning, 2016 – Springer
… sharing. More recently, Collobert and Weston (2008) applied a deep multi-task neural network architecture for natural language processing. A large number of multi-task learning methods stem from a regularization perspective. …

Modality of adaptive neuro-fuzzy classifier for acoustic signal-based traffic density state estimation employing linguistic hedges for feature selection
P Borkar, MV Sarode, LG Malik – International Journal of Fuzzy Systems, 2016 – Springer
… The Neuro-fuzzy classifiers define the class distributions and show the input–output relations, whereas the fuzzy systems describe the systems using natural language. Neural networks are employed for training the system parameters in neuro-fuzzy applications. …

D4. 1–Initial Design-Raw Data Preprocessing, Prediction in NFV, Self-Managed NFV Ecosystem, Network Traffic Classification and Prediction
H Assem, D López – cognet.5g-ppp.eu
Page 1. D4.1 – Initial Design – Raw Data Preprocessing, Prediction in NFV, Self-Managed NFV Ecosystem, Network Traffic Classification and Prediction Document Number D4.1 Status Final Work Package WP 4 Deliverable Type Other Date of Delivery 30/06/2016 …

Predicting viewer-perceived activity/dominance in soccer games with stick-breaking HMM using data from a fixed set of cameras
G Kobayashi, H Hatakeyama, K Ota, Y Nakada… – Multimedia Tools and …, 2016 – Springer
… The HMM is an extremely general probabilistic model that captures sequential structure in data and finds a great variety of applications, including speech recognition [31], character recognition [34, 42], natural language processing [26], genomics [35], and protein structure …

Autonomous learning of object behavior concepts and models through robotic interaction
S Roa Ovalle – 2016 – scidok.sulb.uni-saarland.de
Page 1. AUTONOMOUS LEARNING OF OBJECT BEHAVIOR CONCEPTS AND MODELS THROUGH ROBOTIC INTERACTION Thesis for obtaining the title of Doctor of Engineering of the Faculty of Mathematics and Computer Science of Saarland University by …

Reverse Engineering the Mind: Consciously Acting Machines and Accelerated Evolution
F Neukart – 2016 – books.google.com
Page 1. AutoUni – Schriftenreihe Florian Neukart Reverse Engineering the Mind Consciously Acting Machines and Accelerated Evolution Page 2. AutoUni – Schriftenreihe Band 94 Herausgegeben von/Edited by Volkswagen Aktiengesellschaft AutoUni Page 3. …

Artificial Neural Networks and Machine Learning–ICANN 2016: 25th International Conference on Artificial Neural Networks, Barcelona, Spain, September 6-9 …
AEP Villa, P Masulli, AJP Rivero – 2016 – books.google.com
… 308 Sabrina GTA Bezerra, Camila B. de Andrade, and Mêuser JS Valença Effect of Simultaneous Time Series Prediction with Various Horizons on Prediction Quality at the Example of Electron Flux in the Outer Radiation Belt of the Earth. . . . . …

DLSTM approach to video modeling with hashing for large-scale video retrieval
N Zhuang, J Ye, KA Hua – Pattern Recognition (ICPR), 2016 …, 2016 – ieeexplore.ieee.org
… Although video retrieval using natural language description or keywords is highly desirable, the majority of videos lack tag information. … An application of non- linear programming to train recurrent neural networks in time series prediction problems. …

Three Domain Modelling and Uncertainty Analysis
A Mirakyan, R De Guio – 2016 – Springer
Page 1. Energy Systems Atom Mirakyan Roland De Guio Three Domain Modelling and Uncertainty Analysis Applications in Long Range Infrastructure Planning Page 2. Energy Systems Series editor Panos M. Pardalos, Gainesville, USA Page 3. …

Enhancing web search by using query-based clusters and multi-document summaries
R Qumsiyeh, YK Ng – Knowledge and Information Systems, 2016 – Springer
… and Coverage Problems section), (ii) must be coherent and comprehensible, which can be achieved using natural language processing to … Since exponential average is extensively used in time series prediction, \(Q_{Sum}\) uses the decay rate formula in computing TD(S …

Machine Learning for Risk Prediction and Privacy in Electronic Health Records
E Lantz – 2016 – search.proquest.com
… One problem is the thousands of codes for diagnoses, medications, procedures, and tests used in the records, many quite rarely. We adopt methods from natural language processing to produce embeddings from EHR data in an unsupervised fashion. …

Topic-based analysis for technology intelligence
H Chen – 2016 – opus.lib.uts.edu.au
Page 1. FACULTY OF ENGINEERING AND INFORMATION TECHNOLOGY Topic-based Analysis for Technology Intelligence Hongshu Chen A thesis submitted for the Degree of Doctor of Philosophy University of Technology, Sydney January, 2016 …

Driver drowsiness estimation from EEG signals using online weighted adaptation regularization for regression (OwARR)
D Wu, VJ Lawhern, S Gordon… – IEEE Transactions on …, 2016 – ieeexplore.ieee.org
Page 1. 1063-6706 (c) 2016 IEEE. Personal use is permitted, but republication/ redistribution requires IEEE permission. See http://www.ieee.org/ publications_standards/publications/rights/index.html for more information. This …

Detection and Classification Of Normal and Anomaly IP Packet
AIP Packet – researchgate.net
… Robotics Artificial intelligence Vision Systems Expert system Learning Systems Natural language Processing Neural Networks Page 20. 10 … Task Evaluation the algorithm by simulation on unseen data Classification, Time series prediction, Regression, Clustering Page 22. 12 …

Genetic algorithm for entropy-based feature subset selection
P Krömer, J Platoš – Evolutionary Computation (CEC), 2016 …, 2016 – ieeexplore.ieee.org
… Berlin, Heidelberg: Springer Berlin Heidelberg, 2005, ch. The Curse of Dimensionality in Data Mining and Time Series Prediction, pp. 758–770. … [13] AL Berger, VJD Pietra, and SAD Pietra, “A maximum entropy approach to natural language processing,” Comput. Linguist., vol. …

Social Computing
W Che, Q Han, H Wang, W Jing, S Peng, J Lin, G Sun… – 2016 – Springer
… analysis for social computing, evaluation methodologies for social computing and social media, intelligent computation for social computing, natural language processing techniques … Daily ETC Traffic Flow Time Series Prediction Based on k-NN and BP Neural Network. . . . . …

Rainfall Forecasting in Sudan Using Computational Intelligence
NO Bushara – 2016 – repository.sustech.edu
… processing, data mining, Page 22. 4 and natural language processing. Furthermore other formalisms: Dempster–Shafer theory, chaos theory and many-valued logic are used in the construction of computational models [8]. In general …

Multivariate study of vehicle exhaust particles using machine learning and statistical techniques
A Suleiman – 2016 – etheses.bham.ac.uk
Page 1. MULTIVARIATE STUDY OF VEHICLE EXHAUST PARTICLES USING MACHINE LEARNING AND STATISTICAL TECHNIQUES Aminu Suleiman A thesis submitted to the University of Birmingham for the degree of DOCTOR OF PHILOSOPHY School of Engineering …

Multilayer perceptron training with multiobjective memetic optimization
P Nieminen – Jyväskylä studies in computing 247., 2016 – jyx.jyu.fi
… formal grammars, production rules, logical expressions, graphs, schemas, computer programs, taxonomies, or mixed representations including multiple types of knowledge), and domain of application (such as image recogni- tion, robotics, natural language processing, and …

An investigation of byte n-gram features for malware classification
E Raff, R Zak, R Cox, J Sylvester, P Yacci… – Journal of Computer …, 2016 – Springer
… malware. Abou-Assaleh et al. [1] made the connection with techniques in Natural Language Processing work and using a feature selection step, report- ing 98 % cross validation scores using a nearest neighbor classifier. Kolter …

On-device mobile speech recognition
MK Mustafa – 2016 – irep.ntu.ac.uk
… bespoke vocabularies to achieve high recognition rates [2]. Continuous speech recognition systems, on the other hand, attempts to use larger, natural language level, vocabularies which carry with them a significantly reduced recognition rate. …

Mining Electronic Health Records (EHR): A Survey Do Not Circulate
P Yadav, M Steinbach, V Kumar, G Simon – vk.cs.umn.edu
… exposures and lifestyle data all reside in clinical notes. Natural language processing (NLP) tools and techniques have been widely used to extract knowledge from EHR data. Clinical notes such as admission, treatment and discharge …

Hybrid Soft Computing for Multilevel Image and Data Segmentation
S De, S Bhattacharyya, S Chakraborty, P Dutta – 2016 – Springer
Page 1. Computational Intelligence Methods and Applications Hybrid Soft Computing for Multilevel Image and Data Segmentation Sourav De Siddhartha Bhattacharyya Susanta Chakraborty Paramartha Dutta Page 2. Computational Intelligence Methods and Applications …

Post-Learning Strategy and Evolutionary Architecture in Neural Networks
KG Kapanova – Computer Science, 2016 – iict.bas.bg
Page 1. Bulgarian Academy of Sciences BULGARIAN 1869 ACADEMY of SCIENCES Department of Parallel Algorithms Institute of Information and Communication Technologies 4.6. Computer Science Post-Learning Strategy and Evolutionary Architecture in Neural Networks …

Sparse coding and compressed sensing: Locally competitive algorithms and random projections
WE Hahn – 2016 – search.proquest.com
Sparse coding and compressed sensing: Locally competitive algorithms and random projections. Abstract. For an 8-bit grayscale image patch of size n x n, the number of distinguishable signals is 256(n 2 ). Natural images (eg …

Intelligent optimisation of analogue circuits using particle swarm optimisation, genetic programming and genetic folding
OJ Ushie – 2016 – dspace.brunel.ac.uk
Page 1. Intelligent Optimisation of Analogue Circuits Using Particle Swarm Optimisation, Genetic Programming and Genetic Folding by Ogri James Ushie A thesis submitted for the degree of Doctor of Philosophy Department of Electronic and Computer Engineering …

Kernel learning and applications in wireless localization
Q Wang – 2016 – rucore.libraries.rutgers.edu
… domains as tasks and applied the multi-task learning. Daumé III and Marcu [35] in- vestigated how to train a general model with data from both a source domain and a target domain for domain adaptation in natural language processing tasks. Recently, …

TO STUDY INDUCTION MOTOR EXTERNAL FAULTS DETECTION AND CLASSIFICATION USING ANN AND FUZZY SOFT COMPUTING TECHNIQUES
KJ Chudasama – 2016 – gtu.ac.in
Page 1. TO STUDY INDUCTION MOTOR EXTERNAL FAULTS DETECTION AND CLASSIFICATION USING ANN AND FUZZY SOFT COMPUTING TECHNIQUES A Thesis submitted to Gujarat Technological University for the Award of Doctor of Philosophy in …

Learning hierarchical spectral–spatial features for hyperspectral image classification
Y Zhou, Y Wei – IEEE transactions on cybernetics, 2016 – ieeexplore.ieee.org
… A. Deep Learning Deep learning, inspired by the mechanism of human vision, recently attracted more and more attentions due to its good performance in many fields such as speech recognition, com- puter vision, and natural language processing [40]–[42]. …

Designing Human-Centered Collective Intelligence
ID Addo – 2016 – search.proquest.com
… there are bound to be several Multimodal Cognitive Features involved with a typical CI system design, this study will focus specifically on investigating how to implement multimodal emotional intelligence through sentiment analysis modeling in natural language dialogue, facial …

Abul Aziz, MA, Niu, J., Zhao, X., and Li, X., Efficient and Robust Learning for Sustainable and Reacquisition-Enabled Hand Tracking; TCYB April 2016 945-958 Afonso …
BI Ahmad, JK Murphy, PM Langdon, SJ Godsill… – ieeexplore.ieee.org
Page 1. IEEE TRANSACTIONS ON CYBERNETICS, VOL. 46, NO. 12, DECEMBER 2016 3253 2016 Index IEEE Transactions on Cybernetics Vol. 46 This index covers all technical items — papers, correspondence, reviews, etc. …

Pattern discovery from unstructured and scarcely labeled text corpora
HS Bajestani – 2016 – search.proquest.com
… single nucleotide polymorphisms (SNPs). 1. Natural language data is a domain with a very high-dimensional feature space; a typical text corpus consists of hundreds of thousands of unique words. However, many meaningful and …