Search

Driver behavior is one of the principal factors associated with road accidents. Much research to date focusing on Machine learning technology has been successfully applied to identifying driving styles and recognizing unsafe behaviors. In this paper, the development of an android mobile application (Driver Alert) is described, with the aim of collecting data from mobile phone sensors data to identify certain patterns and understand drivers' behaviors. Additional information was recorded regarding weather and traffic information, using public API's to complement the data directly collected from the vehicle. Four machine learning models (K-Means, Algorithm Agglomerative Hierarchical, Random Forest and Support Vector Machines) were tested and compared to identify different driver profiles. A native mobile application named DriverAlert was developed to support collect data and make it available, through an online dashboard, to drivers and researchers. Due to the available tools and libraries, it possesses, Python language was used, as it is a powerful programming language for workloads in data science, machine learning, and scientific computing. [ABSTRACT FROM AUTHOR]

High-fidelity computer simulations of childbirth remain prohibitively expensive and time consuming, making them impractical for guiding decision-making during obstetric emergencies. Cheap computer simulations that preserve the accuracy of high-fidelity models can be developed using surrogate modeling. Two common approaches to surrogate modeling are physics-based reduced order modeling (ROM) and machine learning (ML), with the latter gaining popularity as the scientific computing community seeks to leverage advances from other, mostly non-physics-based, computational strategies. Although ROM and ML have been compared for various problems, to our knowledge, such a comparison for simulations of vaginal deformations is currently missing. This study provides a baseline numerical comparison between methods from these two fundamentally different approaches. Since there are many methods falling into each modeling approach, to provide a fair and natural comparison, we select a basic model from each category, with each allowing (i) a straightforward implementation in commercial software packages, and (ii) use by practitioners with limited experience in the field. As a benchmark for the numerical comparison of the ROM and ML approaches, we use the finite element (FE) modeling of the ex vivo deformations of rat vaginal tissue subjected to inflation testing to study the effect of a pre-imposed tear. From the ROM strategies, we consider a simplified Galerkin ROM (G-ROM) that is based on the linearization of the underlying nonlinear equations. From the ML strategies, we select a feed-forward neural network to create mappings from constitutive model parameters and luminal pressure values to either the FE displacement history (in which case we denote the resulting model ML) or the proper orthogonal decomposition (POD) coefficients of the displacement history (in which case we denote the resulting model POD-ML). The numerical investigation of G-ROM, ML, and POD-ML takes place in the reconstructive regime. The numerical results show that the G-ROM outperforms the ML model in terms of offline central processing unit (CPU) time for model training, online CPU time required to generate approximations, and relative error with respect to the FE models. The G-ROM achieves superior error performance to the best ML model with 11 POD basis functions. With higher-dimensional POD bases, the G-ROM achieves a relative error 3 orders of magnitude lower than that of the best ML model with an online CPU time still on the same order of magnitude as the best ML model. The POD-ML model improves on the speed performance of the ML, having online CPU times comparable to those of the G-ROM given the same size of POD bases. However, the POD-ML model does not improve on the error performance of the ML and is still outperformed by the G-ROM for POD bases of size greater than 11. This baseline numerical investigation serves as a starting point for future computer simulations that consider state-of-the-art G-ROM and ML strategies, and the in vivo geometry, boundary conditions, and material properties of the human vagina, as well as their changes during labor. [ABSTRACT FROM AUTHOR]

The technological progress in computer science (particularly, in machine learning) has contributed to the improvement of medical services, both in detecting and treating diseases. The large volumes of data, that are overwhelming for human experts (doctors, nurses), can easily be managed by automated systems, as long as we have the computational resources. Obviously, human experts are still essential in the process - we think of the use of computer science in medicine as a collaboration between medical staff and artificial intelligence. The usual types of data that can be processed by automated systems are text, sound, and image types. In this paper, we approach the diagnosis subject and focus on data consisting of sound. We created a heart murmur detection system - it analyzes recordings and tells the user whether the sound samples indicate a heart murmur or not, based on a trained machine learning model. One of the main advantages of our system is the fact that we ran a large number of experiments, with different configurations of denoising techniques and features taken into consideration. We were able to draw some interesting conclusions, for example, we found out which features are the most important for the classification and which features are not worth computing. Also, our work denotes a thorough understanding of sound processing. [ABSTRACT FROM AUTHOR]

Social networking platforms will be a tool for people to share their positive and negative emotions. Suicide ideation detection is one of the important fields in social network analysis. Exploiting the data published on social networking platforms will help to prevent suicide and reduce the rate of suicide in the world. The purpose of this study is to review the effects of using social networking platforms to identify and categorize suicidal ideation. In addition to presenting the most popular methods used in computer science to discern between suicide notes and non-suicide notes. [ABSTRACT FROM AUTHOR]

The auto-scaling feature is fundamental to serverless computing, and it automatically allows applications to scale as needed. Hence, this allows applications to be configured to adapt to current traffic and demands and acquire resources as necessary without the need to manage servers directly. Auto-scaling is an important principle in developing serverless applications that is considered and increasingly recognized by academia and industry. Despite the strong interest in auto-scaling in serverless computing in the scientific and industrial community, no clear, comprehensive, and systematic investigation has been conducted. As part of the study of automatic scaling in serverless computing, key strategies and approaches are investigated during the lifecycle of cloud applications. This research examines three key approaches to automatically scaling serverless computing applications in the taxonomy presented. These approaches include machine learning (ML)-based, frameworks-based, and models-based. Additionally, we provide an overview of key performance metrics essential to the auto-scaling process of cloud applications and discuss the requirements. It discusses key concepts and limitations of serverless computing approaches, challenges, future directions, and research opportunities. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is a fast-growing research area in computer science that aims to mimic cognitive processes through a number of techniques. Supervised machine learning, a subfield of AI, includes methods that can identify patterns in high-dimensional data using labeled 'ground truth' data and apply these learnt patterns to analyze, interpret, or make predictions on new datasets. Supervised machine learning has become a significant area of interest within the medical community. Radiology and neuroradiology in particular are especially well suited for application of machine learning due to the vast amount of data that is generated. One devastating disease for which neuroimaging plays a significant role in the clinical management is stroke. Within this context, AI techniques can play pivotal roles for image-based diagnosis and management of stroke. This overview focuses on the recent advances of artificial intelligence methods – particularly supervised machine learning and deep learning – with respect to workflow, image acquisition and reconstruction, and image interpretation in patients with acute stroke, while also discussing potential pitfalls and future applications. • Artificial Intelligence (AI) is a growing subfield of computer science that aims to mimic cognitive processes through a number of techniques. • Superficial AI, which is comprised of techniques that learn patterns with the use of labels of 'ground truth' data, have become a significant area of interest within the medical community. As images are, in essence, volumes of mineable data, radiology is a field of medicine particularly well suited to supervised AI techniques. • AI techniques could play pivotal roles in neuroradiology, particular in the diagnosis and management of time sensitive diseases such as stroke. • Several AI techniques, comprised of machine and deep learning methods, have shown incredible promise as an adjunct to a neuroradiologist's workflow, particularly within stroke imaging. • Although encouraging, there are data protection and medicolegal implications that must be considered for widespread clinical use of AI techniques. [ABSTRACT FROM AUTHOR]

• Neuroscience is rapidly adopting machine-learning in many forms. • Overfitting of parameters in machine-learning is well-known but also misunderstood. • Over-hyping can occur when analyses are optimized, and despite cross-validation. • Over-hyping threatens the integrity of the machine-learning neuroscience literature. • Alternative methods are provided that allow detection and prevention of over-hyping. Machine learning has enhanced the abilities of neuroscientists to interpret information collected through EEG, fMRI, and MEG data. With these powerful techniques comes the danger of overfitting of hyperparameters which can render results invalid. We refer to this problem as 'overhyping' and show that it is pernicious despite commonly used precautions. Overhyping occurs when analysis decisions are made after observing analysis outcomes and can produce results that are partially or even completely spurious. It is commonly assumed that cross-validation is an effective protection against overfitting or overhyping, but this is not actually true. In this article, we show that spurious results can be obtained on random data by modifying hyperparameters in seemingly innocuous ways, despite the use of cross-validation. We recommend a number of techniques for limiting overhyping, such as lock boxes, blind analyses, pre-registrations, and nested cross-validation. These techniques, are common in other fields that use machine learning, including computer science and physics. Adopting similar safeguards is critical for ensuring the robustness of machine-learning techniques in the neurosciences. [ABSTRACT FROM AUTHOR]

Medical decision support systems have been on the rise with technological advances and they have been the subject of many studies. Developing an effective medical decision support system requires a high amount of accuracy, precision, and sensitivity as well as time efficiency that is inversely proportional to the complexity of the model. Hepatitis C virus (HCV) infection is one of the most important causes of chronic liver disease worldwide. In this study, data discovery has been made by applying data science processes, and the HCV has been estimated with machine learning methods. By analyzing and visualizing the values in the data set, features that may be important for HCV was determined, and HCV estimation was made using various machine learning methods, pre-processing and feature extraction. According to the features obtained from this study, the estimation of HCV can be made automatically and can be a decision support system that helps the researchers and clinicians. In this study, HCV was obtained with 99.31% accuracy by adding new features and eliminating imbalances between classes. The model in this study can be used as an alternative method in the prediction of Hepatitis C-related diseases. • In this study, data analysis was performed and HCV was estimated by ML methods. • Thanks to the new features obtained, HCV estimation can be made automatically. • In this study, HCV prediction success was increased with the newly obtained features. [ABSTRACT FROM AUTHOR]

Gas-particle flows can be well described by highly resolved simulations (HRS). Limited by the daunting computational cost, HRS at scale remains infeasible. Many methods are proposed to strike tradeoffs between accuracy and computational cost. Here, we design a machine learning (ML) based alternate mode to accelerate HRS without sacrificing accuracy. Spatiotemporal samples (~1.3 × 106) generated from two-fluid model-based HRS of gas-particle flows are trained for developing artificial neural network (ANN) and long short-term memory (LSTM) models. Simple time-series predictions consisting of repeated ANN iterations can accurately predict the flow field in ~10−3 s. Hybrid accelerations combining CFD and the offline trained ML in time scale can approximate to the time-series highly resolved flow fields within 1% error, saving 40% computing time. This work may contribute to a new transformative paradigm that how scientific computing can leverage ML to improve gas-particle simulations without new device requirements. [Display omitted] • Gas-particle flow fields are well predicted via ANN and LSTM. • Simple ML can accurately predict the flow field in ~10−3 s. • Highly resolved simulations are accelerated by combining CFD & ML within 1% error, saving 40% computing time. • Accelerated simulation is deployed on the CPU devices supporting multi-core parallel computation. [ABSTRACT FROM AUTHOR]

Permutation variable importance measure (PVIM) based on random forest and Morris' screening design are two effective techniques for measuring the variable importance in high dimensions. The former technique is developed in the machine learning discipline and widely used in bioinformatics, while the latter technique is popular in scientific computing. We present three main contributions to variable importance analysis (VIA). First, through theoretical derivation, we show that the PVIM converges to double the non-standardized Sobol' total effect index. This observation indicates that the PVIM is especially useful for variable screening as it captures both the individual and interaction effects. Second, three numerical examples with different types of model behavior are presented for comparing the performances of these two techniques. The main conclusions are as follows. For high-dimensional additive or approximately additive models, the PVIM is much more efficient than Morris' screening design when used for both variable importance ranking and variable screening. For high-dimensional models mainly governed by interaction effects, the performance of PVIM degrades, but it is still a competitive technique. Finally, the two techniques are applied to an environmental multi-indicators system for improving the robustness of the partial order structure of this system. [ABSTRACT FROM AUTHOR]

• We perform a comparison of fake news detection in three languages and two platforms. • We employ platform/language independent feature sets. • Our results show that BOW representation is competitive with recent approaches. The debate around fake news has grown recently because of the potential harm they can have on different fields, being politics one of the most affected. Due to the amount of news being published every day, several studies in computer science have proposed models using machine learning to detect fake news. However, most of these studies focus on news from one language (mostly English) or rely on characteristics of social media-specific platforms (like Twitter or Sina Weibo). Our work proposes to detect fake news using only text features that can be generated regardless of the source platform and are the most independent of the language as possible. We carried out experiments from five datasets, comprising both texts and social media posts, in three language groups: Germanic, Latin, and Slavic, and got competitive results when compared to benchmarks. We compared the results obtained through a custom set of features and with other popular techniques when dealing with natural language processing, such as bag-of-words and Word2Vec. [ABSTRACT FROM AUTHOR]

Social media marketing is an essential and important tool for start-up firms, which can help start-up firms remedy the marketing limitations through ease and relatively low costs. Predicting start-up firms' social media engagement level can allow them to gauge the effectiveness of their social media marketing efforts and can provide numerous benefits related to strategic marketing processes. This study focuses on developing a methodology involving data science processes and machine learning models to account for the ongoing advancement of business intelligence methodologies. This study gathered data of 8,434 start-up firms from Twitter, generated social media-based features, and created machine learning models to predict the social media engagement level of each firm. The results show that deep learning provides the best accuracy in predicting the engagement levels. The results also show that the number of tweets by the firms, the number of retweets received, and the number of likes received have the most significance in determining the effectiveness of social media marketing activities. • Social media marketing prediction through engagement level is an important process for start-up firms. • Start-up firms can utilise data scientific analytical process and machine learning methods to predict the social media engagement level. • A prediction methodology is established using data science and machine learning approaches for social media marketing analysis. • A new marketing prediction for start-up firms is made, improving business intelligence process. [ABSTRACT FROM AUTHOR]

We are interested in mesh-free formulas based on the Monte-Carlo methodology for the approximation of multi-dimensional integrals, and we investigate their accuracy when the functions belong to a reproducing-kernel space. A kernel typically captures regularity and qualitative properties of functions "beyond" the standard Sobolev regularity class. We are interested in the issue whether quantitative error bounds can be a priori guaranteed in applications (including mathematical finance, scientific computing, and machine learning). Our main contribution is a numerical study of the error discrepancy function based on a comparison between several numerical strategies, when one varies the choice of the kernel, the number of approximation points, and the dimension of the problem. We consider two strategies in order to localize to a bounded set the standard kernels defined in the whole Euclidian space (exponential, multiquadric, Gaussian, truncated), namely, on one hand the class of periodic kernels defined via a discrete Fourier transform on a lattice and, on the other hand, a class of transport-based kernels. Relying on the Poisson formula on a lattice together with heuristic arguments, we study the derivation of theoretical bounds for the discrepancy function of periodic kernels. Then, for four kernels of particular interest we perform extensive numerical experiments and generate the optimal distributions of points and the discrepancy error functions. Our numerical results validate our theoretical observations and, importantly, provide us with quantitative estimates for the error made with a kernel-based strategy as opposed to a purely random strategy. [ABSTRACT FROM AUTHOR]