Data Mining - Concepts and Techniques.

Objective Electroencephalography (EEG) analysis has been an important tool in neuroscience with applications in neuroscience, neural engineering (e.g. Brain-computer interfaces, BCI's), and even commercial applications. Many of the analytical tools used in EEG studies have used machine learning to uncover relevant information for neural classification and neuroimaging. Recently, the availability of large EEG data sets and advances in machine learning have both led to the deployment of deep learning architectures, especially in the analysis of EEG signals and in understanding the information it may contain for brain functionality. The robust automatic classification of these signals is an important step towards making the use of EEG more practical in many applications and less reliant on trained professionals. Towards this goal, a systematic review of the literature on deep learning applications to EEG classification was performed to address the following critical questions: (1) Which EEG classification tasks have been explored with deep learning? (2) What input formulations have been used for training the deep networks? (3) Are there specific deep learning network structures suitable for specific types of tasks? Approach A systematic literature review of EEG classification using deep learning was performed on Web of Science and PubMed databases, resulting in 90 identified studies. Those studies were analyzed based on type of task, EEG preprocessing methods, input type, and deep learning architecture. Main results For EEG classification tasks, convolutional neural networks, recurrent neural networks, deep belief networks outperform stacked auto-encoders and multi-layer perceptron neural networks in classification accuracy. The tasks that used deep learning fell into five general groups: emotion recognition, motor imagery, mental workload, seizure detection, event related potential detection, and sleep scoring. For each type of task, we describe the specific input formulation, major characteristics, and end classifier recommendations found through this review. Significance This review summarizes the current practices and performance outcomes in the use of deep learning for EEG classification. Practical suggestions on the selection of many hyperparameters are provided in the hope that they will promote or guide the deployment of deep learning to EEG datasets in future research.

https://iopscience.iop.org/article/10.1088/1741-2552/ab0ab5/pdf

Deep learning for electroencephalogram (EEG) classification tasks: a review.

Deep learning in spiking neural networks

This paper discusses the fourth year of the ”Sentiment Analysis in Twitter Task”. SemEval-2016 Task 4 comprises five subtasks, three of which represent a significant departure from previous editions. The first two subtasks are reruns from prior years and ask to predict the overall sentiment, and the sentiment towards a topic in a tweet. The three new subtasks focus on two variants of the basic “sentiment classification in Twitter” task. The first variant adopts a five-point scale, which confers an ordinal character to the classification task. The second variant focuses on the correct estimation of the prevalence of each class of interest, a task which has been called quantification in the supervised learning literature. The task continues to be very popular, attracting a total of 43 teams.

SemEval-2016 Task 4: Sentiment Analysis in Twitter

Context Electroencephalography (EEG) is a complex signal and can require several years of training, as well as advanced signal processing and feature extraction methodologies to be correctly interpreted. Recently, deep learning (DL) has shown great promise in helping make sense of EEG signals due to its capacity to learn good feature representations from raw data. Whether DL truly presents advantages as compared to more traditional EEG processing approaches, however, remains an open question. Objective In this work, we review 154 papers that apply DL to EEG, published between January 2010 and July 2018, and spanning different application domains such as epilepsy, sleep, brain-computer interfacing, and cognitive and affective monitoring. We extract trends and highlight interesting approaches from this large body of literature in order to inform future research and formulate recommendations. Methods Major databases spanning the fields of science and engineering were queried to identify relevant studies published in scientific journals, conferences, and electronic preprint repositories. Various data items were extracted for each study pertaining to (1) the data, (2) the preprocessing methodology, (3) the DL design choices, (4) the results, and (5) the reproducibility of the experiments. These items were then analyzed one by one to uncover trends. Results Our analysis reveals that the amount of EEG data used across studies varies from less than ten minutes to thousands of hours, while the number of samples seen during training by a network varies from a few dozens to several millions, depending on how epochs are extracted. Interestingly, we saw that more than half the studies used publicly available data and that there has also been a clear shift from intra-subject to inter-subject approaches over the last few years. About [Formula: see text] of the studies used convolutional neural networks (CNNs), while [Formula: see text] used recurrent neural networks (RNNs), most often with a total of 3-10 layers. Moreover, almost one-half of the studies trained their models on raw or preprocessed EEG time series. Finally, the median gain in accuracy of DL approaches over traditional baselines was [Formula: see text] across all relevant studies. More importantly, however, we noticed studies often suffer from poor reproducibility: a majority of papers would be hard or impossible to reproduce given the unavailability of their data and code. Significance To help the community progress and share work more effectively, we provide a list of recommendations for future studies and emphasize the need for more reproducible research. We also make our summary table of DL and EEG papers available and invite authors of published work to contribute to it directly. A planned follow-up to this work will be an online public benchmarking portal listing reproducible results.

https://iopscience.iop.org/article/10.1088/1741-2552/ab260c/pdf

Deep learning-based electroencephalography analysis: a systematic review.

Graph database management systems are widely used in scenarios where the data are intensively connected. Handling such connected data in a relational database is not an efficient task. Converting relational databases to graph ones is one of the solutions that can empower users with handling such data using the graph model features. In this paper, we propose a new algorithm to ease such conversion and overcome the limitations of the existing algorithms. The state of the art algorithms cannot handle multiple relationships types such as unary relationships and associative entities with non-foreign key attributes. Our proposed algorithm, FD2G, leverages the existence of functional dependencies information inside the input relational database to automatically perform the conversion to property graph databases. In addition, we updated the state of the art algorithm, named R2G, to handle its limitations and be able to fairly compare both algorithms performance. We evaluated FD2G against the updated R2G algorithm where it efficiently and effectively outperformed the existing one.

Using Functional Dependencies in Conversion of Relational Databases to Graph Databases

Rule based machine translation systems face different challenges in building the translation model in a form of transfer rules. Some of these problems require enormous human effort to state rules and their consistency. This is where different human linguists make different rules for the same sentence. A human linguist states rules to be understood by human rather than machines. The proposed translation model (from Arabic to English) tackles the mentioned problem of building translation model. This model employs Inductive Logic Programming (ILP) to learn the language model from a set of example pairs acquired from parallel corpora and represent the language model in a rule-based format that maps Arabic sentence pattern to English sentence pattern. By testing the model on a small set of data, it generated translation rules with logarithmic growing rate and with word error rate 11%

Machine translation model using inductive logic programming

Social networks of various kinds demonstrate a strong community effect. Actors in a network tend to form closely-knit groups; those groups are also called communities or clusters. Detecting such groups in a social network (i.e., community detection) remains a core problem in social network analysis. Among the challenges that face the researchers to come up with advanced community detection methods, there is a key challenge, which is the validation and evaluation of their methods. The limited benchmark data available, the lack of ground truth for many of the available network datasets, and the nature of the social behavior factor in the problem, turned the evaluation process to be very hard. Accordingly, understanding such challenges may help in designing good community detection methods. This chapter presents testing strategies for community detection approaches and explores a number of datasets that could be used in the testing process as well as stating some characteristics of those datasets.

Testing Community Detection Algorithms: A Closer Look at Datasets

The renewable energy generated from wind reduces the expenditure of electricity production. According to the variation and the nonlinearity of the wind data, the precise speed of the wind forecasting regrading as a major role in renewable energy systems. A great amount of wind speed forecasting algorithms were proposed to improve the forecasting reliability. In this paper, a hybrid forecasting model is presented based on Whale Optimization Algorithm (WOA) combined with Support Vector Regression (SVR) called WOA-SVR model to select the optimal hyper-parameters value of Gaussian/ Radial Base Function (RBF) and penalty factor for forecasting purposes of wind speed. In order to assess the performance of the proposed model, this paper uses daily average wind speed data of OpenEI wind speed dataset as a case study. The results are analyzed and compared with genetic algorithm (GA) and traditional SVR. Eventually, the obtained optimization results revealed that the WOA-SVR model is very competitive for wind speed prediction.

Forecast of wind speed based on whale optimization algorithm

The fuzzy Euclidean distance clustering algorithm has been well studied and used in information retrieval society for clustering documents. However, the fuzzy logic algorithm poses problems in dealing with large amount of data. In this paper we proposed results for clustering theses documents based on Euclidean distances and cluster-dependent keyword weighting. The proposed approach is based on the Fuzzy Euclidean distance clustering algorithm. The cluster dependent keyword weighting help in partitioning and categorizing the theses documents into more meaningful categories.

Aly A. Fahmy

Papers

Using Functional Dependencies in Conversion of Relational Databases to Graph Databases

Machine translation model using inductive logic programming

Testing Community Detection Algorithms: A Closer Look at Datasets

Forecast of wind speed based on whale optimization algorithm

Fuzzy clustering and categorization of text documents