The ability to model the behaviour of arbitrary dynamic system is one of the most useful properties of recurrent networks. Dynamic ridge polynomial neural network (DRPNN) is a recurrent neural ...network used for time series forecasting. Despite the potential and capability of the DRPNN, stability problems could occur in the DRPNN due to the existence of the recurrent feedback. Therefore, in this study, a sufficient condition based on an approach that uses adaptive learning rate is developed by introducing a Lyapunov function. To compare the performance of the proposed solution with the existing solution, which is derived based on the stability theorem for a feedback network, we used six time series, namely Darwin sea level pressure, monthly smoothed sunspot numbers, Lorenz, Santa Fe laser, daily Euro/Dollar exchange rate and Mackey-Glass time-delay differential equation. Simulation results proved the stability of the proposed solution and showed an average 21.45% improvement in Root Mean Square Error (RMSE) with respect to the existing solution. Furthermore, the proposed solution is faster than the existing solution. This is due to the fact that the proposed solution solves network size restriction found in the existing solution and takes advantage of the calculated dynamic system variable to check the stability, unlike the existing solution that needs more calculation steps.
In this paper a novel application of a particular type of spiking neural network, a Polychronous Spiking Network, was used for financial time series prediction. It is argued that the inherent ...temporal capabilities of this type of network are suited to non-stationary data such as this. The performance of the spiking neural network was benchmarked against three systems: two "traditional", rate-encoded, neural networks; a Multi-Layer Perceptron neural network and a Dynamic Ridge Polynomial neural network, and a standard Linear Predictor Coefficients model. For this comparison three non-stationary and noisy time series were used: IBM stock data; US/Euro exchange rate data, and the price of Brent crude oil. The experiments demonstrated favourable prediction results for the Spiking Neural Network in terms of Annualised Return and prediction error for 5-Step ahead predictions. These results were also supported by other relevant metrics such as Maximum Drawdown and Signal-To-Noise ratio. This work demonstrated the applicability of the Polychronous Spiking Network to financial data forecasting and this in turn indicates the potential of using such networks over traditional systems in difficult to manage non-stationary environments.
Forecasting of oil production plays a vital role in petroleum engineering and contributes to supporting engineers in the management of petroleum reservoirs. However, reliable production forecasting ...is difficult to achieve, particularly in view of the increase in digital oil big data. Although a significant amount of work has been reported in the literature in relation to the use of machine learning in the oil and gas domain, traditional forecasting approaches have limited potential in terms of representing the complex features of time series data. More specifically, in a high-dimensional nonlinear multivariate time series dataset, a shallow machine is incapable of inferring the dependencies between past and future values. In this context, a novel forecasting model for petroleum production is proposed in this work. The model is a deep-gated recurrent neural network consisting of multiple hidden layers, where each layer has a number of nodes. The proposed model has a low-complexity architecture and the capacity to track long-interval time-series datasets. To evaluate the robustness of our model, the proposed technique was benchmarked with various standard approaches. The extensive empirical results demonstrate that the proposed model outperforms existing approaches.
Machine learning algorithms have been used for detection (and possibly) prediction of Alzheimer's disease using genotype information, with the potential to enhance the outcome prediction. However, ...detailed research about the analysis and the detection of Alzheimer's disease using genetic data is still in its primitive stage. The aim of this paper was to evaluate the scientific literature on the use of various machine learning approaches for the prediction of Alzheimer's disease based solely on genetic data. To identify gaps in the literature, critically appraise the reporting and methods of the algorithms, and provide the foundation for a wider research programme focused on developing novel machine learning based predictive algorithms in Alzheimer's disease. A systematic review of quantitative studies was conducted using three search engines (PubMed, Web of Science and Scopus), and included studies between <inline-formula> <tex-math notation="LaTeX">1^{\mathrm {st}} </tex-math></inline-formula> of January 2010 and <inline-formula> <tex-math notation="LaTeX">31^{\mathrm {st}} </tex-math></inline-formula> December 2021. Keywords used were 'Alzheimer's disease(s)', 'GWAS, 'Artificial intelligence' and their synonyms. After applying the inclusion/exclusion criteria, 24 studies were included. Machine learning methods in the reviewed papers performed in a wide range of ways (0.59 to 0.98 AUC). The main findings showed that high risk of bias in the analysis can be linked to feature selection, hyperparameter search and validation methods.
River flooding is a natural phenomenon that can have a devastating effect on human life and economic losses. There have been various approaches in studying river flooding; however, insufficient ...understanding and limited knowledge about flooding conditions hinder the development of prevention and control measures for this natural phenomenon. This paper entails a new approach for the prediction of water level in association with flood severity using the ensemble model. Our approach leverages the latest developments in the Internet of Things (IoT) and machine learning for the automated analysis of flood data that might be useful to prevent natural disasters. Research outcomes indicate that ensemble learning provides a more reliable tool to predict flood severity levels. The experimental results indicate that the ensemble learning using the Long-Short Term memory model and random forest outperformed individual models with a sensitivity, specificity and accuracy of 71.4%, 85.9%, 81.13%, respectively.
Massive Open Online Courses (MOOCs) have shown rapid development in recent years, allowing learners to access high-quality digital material. Because of facilitated learning and the flexibility of the ...teaching environment, the number of participants is rapidly growing. However, extensive research reports that the high attrition rate and low completion rate are major concerns. In this paper, the early identification of students who are at risk of withdrew and failure is provided. Therefore, two models are constructed namely at-risk student model and learning achievement model. The models have the potential to detect the students who are in danger of failing and withdrawal at the early stage of the online course. The result reveals that all classifiers gain good accuracy across both models, the highest performance yield by GBM with the value of 0.894, 0.952 for first, second model respectively, while RF yield the value of 0.866, in at-risk student framework achieved the lowest accuracy. The proposed frameworks can be used to assist instructors in delivering intensive intervention support to at-risk students.
Massive open online courses (MOOCs) have been experiencing increasing use and popularity in highly ranked universities in recent years. The opportunity of accessing high quality courseware content ...within such platforms, while eliminating the burden of educational, financial, and geographical obstacles has led to a rapid growth in participant numbers. The increasing number and diversity of participating learners has opened up new horizons to the research community for the investigation of effective learning environments. Learning Analytics has been used to investigate the impact of engagement on student performance. However, the extensive literature review indicates that there is little research on the impact of MOOCs, particularly in analyzing the link between behavioral engagement and motivation as predictors of learning outcomes. In this paper, we consider a dataset, which originates from online courses provided by Harvard University and the Massachusetts Institute of Technology, delivered through the edX platform. Two sets of empirical experiments are conducted using both statistical and machine learning techniques. Statistical methods are used to examine the association between engagement level and performance, including the consideration of learner educational backgrounds. The results indicate a significant gap between success and failure outcome learner groups, where successful learners are found to read and watch course material to a higher degree. Machine learning algorithms are used to automatically detect learners who are lacking in motivation at an early time in the course, thus providing instructors with insight in regards to student withdrawal.
The significant increase in drug abuse cases prompts developers to investigate techniques that mimic the hallucinations imagined by addicts and abusers, in addition to the increasing demand for the ...use of decorative images resulting from the use of computer technologies. This research uses Deep Dream and Neural Style Transfer technologies to solve this problem. Despite the significance researches on Deep Dream technology, there are several limitations in existing studies, including image quality and evaluation metrics. We have successfully addressed these issues by improving image quality and diversifying the types of generated images. This enhancement allows for more effective use of Deep Dream in simulating hallucinated images. Moreover, the high-quality generated images can be saved for dataset enlargement, like the augmentation process. Our proposed deepy-dream model combines features from five convolutional neural network architectures: VGG16, VGG19, Inception v3, Inception-ResNet-v2, and Xception. Additionally, we generate Deep Dream images by implementing each architecture as a separate Deep Dream model. We have employed autoencoder Deep Dream model as another method. To evaluate the performance of our models, we utilize normalized cross-correlation and structural similarity indexes as metrics. The values obtained for those two quality measures for our proposed deepy-dream model are 0.1863 and 0.0856, respectively, indicating effective performance. When considering the content image, the metrics yield values of 0.8119 and 0.3097, respectively. Whiefor the style image, the corresponding quality measure values are 0.0007 and 0.0073, respectively.
Sentiment analysis is an emerging research field that can be integrated with other domains, including data mining, natural language processing and machine learning. In political articles, it is ...difficult to understand and summarise the state or overall views due to the diversity and size of social media information. A number of studies were conducted in the area of sentiment analysis, especially using English texts, while Arabic language received less attention in the literature. In this study, we propose a detection model for political orientation articles in the Arabic language. We introduce the key assumptions of the model, present and discuss the obtained results, and highlight the issues that still need to be explored to further our understanding of subjective sentences. The main purpose of applying this new approach based on Rough Set (RS) theory is to increase the accuracy of the models in recognizing the orientation of the articles. We present extensive simulation results, which demonstrate the superiority of the proposed model over other algorithms. It is shown that the performance of the proposed approach significantly improves by adding discriminating features. To summarize, the proposed approach demonstrates an accuracy of 85.483%, when evaluating the orientation of political Arabic datasets, compared to 72.58% and 64.516% for the Support Vector Machines and Naïve Bayes methods, respectively.
In this paper, a novel application of machine learning algorithms is presented for student levelling. In multicultural countries such as UAE, there are various education curriculums where the sector ...of private schools and quality assurance is supervising various private schools for many nationalities. As there are various education curriculums in United Arab Emirates, specifically Abu Dhabi, to meet expats’ needs, there are different requirements for registration and success. In addition, there are different age groups for starting education in each curriculum. Every curriculum follows different education methods such as assessment techniques, reassessment rules, and exam boards. Currently, students who transfer to other curriculums are not correctly placed to their appropriate year group as a result of the start and end dates of each academic year as well as due to their date of birth, in which students who are either younger or older for that year group can create gaps in their learning and performance. In addition, pupils’ academic journeys are not stored which create a gap for the schools to track their learning process. In this paper, we propose a computational framework applicable in multicultural countries such as United Arab Emirates in which multi-education systems are implemented. Machine Learning are used to provide the appropriate student’ level aiding schools to provide a smooth transition when assigning students to their year groups and provide levelling and differentiation information of pupils for a smooth transition between one education curriculums to another, in which retrieval of their progress is possible. For classification and discriminant analysis of pupils levelling, three machine learning classifiers are utilised including random forest classifier, Artificial Neural Network, and combined classifiers. The simulation results indicated that the proposed machine learning classifiers generated effective performance in terms of accuracy.