Continuous Input Data Research Articles

Transient surrogate modeling of modally reduced structures with discontinuous loads and damping

In this work, a surrogate model for structural, transient and discontinuously excited finite element method simulations is developed. This allows to reduce the computational effort of repeated calculations of identical models under different load cases. The architecture of the surrogate combines fully connected neural network layers with long short-term memory layers. For the reproduction of different damping ratios, a categorical variable is added to the continuous input data. Based on a recursive flow of the predicted data back to the input layer, long-term dependencies do not vanish due to short-input sequences. The system dimension is reduced by applying the model-order reduction technique for modal decomposition. The high accuracy of the surrogate and the reduction of computational costs are shown on an academic example of a cantilever beam and a real-world example of a robot. The advantages of our approach are illustrated in comparison with state-of-the-art surrogates for transient finite element analysis. By using the surrogate proposed in this study, oscillations due to discontinuous excitation of mechanical structures can be reproduced. For this purpose, only short-input sequences are necessary since the excitation of the oscillations does not have to be part of the input sequence during the whole duration of the oscillations. Due to the categorical variable for the damping ratio, the surrogate can account for the influence of different damping in parameter studies.

Exploiting Motivation Subscales for Gamification of Lifelogging Application

Continuous data input is essential for lifelogging services, where users input their daily records. But whether the user can continuously input data depends mainly on the user's motivation. This article presents a new method of introducing gamification in line with the purpose of lifelogging. The authors introduce a comprehensive set of gamification features based on motivation subscales into a lifelogging service. Meanwhile, the authors elucidate which gamification features correspond to which motivation subscales are effective for lifelogging, including intrinsic motivation, introjected regulation, integrated regulation, identified regulation, and external regulation. As a case study, the authors introduce the five gamification features corresponding to each motivation subscale into work support service (WSS) designed to record and review work hours. The authors also compare and evaluate changes in user behavior before and after the introduction of the gamification features. In this way, user motivation for continuous input increases when gamification in the WSS is confirmed.

Unsupervised deep learning of landscape typologies from remote sensing images and other continuous spatial data

The identification of landscape classes facilitates the implementation of planning strategies. Although landscape patterns are key distinctive features of landscape classes, existing unsupervised clustering techniques for clustering landscapes rely on categorical input data to quantify such patterns and consider only a limited number of pattern metrics. To unlock the great potential of continuous spatial data, such as remote sensing images, for generating landscape typologies, we adapted a novel unsupervised deep learning method (Deep Convolutional Embedded Clustering; DCEC) to generate a landscape typology for Switzerland. DCEC encodes lower-dimensional representations of input images in a hidden layer, which is simultaneously used to divide the images into well-distinguishable clusters. We applied DCEC to image tiles extracted from satellite images as well as ecological, demographic and terrain layers. DCEC successfully distinguished 45 landscape classes in the continuous input data. We conclude that DCEC is a promising new method in landscape and land-system research.

An Incremental Learning Method Based on Dynamic Ensemble RVM for Intrusion Detection

Due to the dynamic changes of network data over time, static intrusion detection systems cannot adapt well to the behavioral characteristics of the input network data, resulting in reduced detection accuracy. In addition, continuous input data streams will bring huge challenges to resource storage and computing costs. Therefore, we propose an intrusion detection method of dynamic ensemble incremental learning (DEIL-RVM), and realize a dynamically adjusted ensemble intrusion detection model. In which a new overall misclassification probability weight value (OMPW) based on incremental set or data chunk is designed as the basis for updating the ensemble model, and it can be used to prune and replace the poor base component in the ensemble model. We presented a probabilistic decision function taking into account the posterior probability of each base RVM model dividing the sample into each category. The RVM with high sparsity is used as the base component to obtain the good balance between the accuracy, robustness and resource consumption, which can sacrifice less time and storage cost in ensemble incremental learning while achieving higher detection accuracy and stability in network data streams.

Impact of Coronavirus Disease 2019 on the Diagnosis and Therapy for Barrett’s Esophagus and Esophageal Cancer in the United States

Impact of Coronavirus Disease 2019 on the Diagnosis and Therapy for Barrett’s Esophagus and Esophageal Cancer in the United States

Time-delayed machine learning models for estimating groundwater depth in the Hetao Irrigation District, China

A large amount of continuous input data is used to estimate groundwater level (GWL) by using machine learning models. However, data collection is very difficult and costly in undeveloped countries. Therefore, obtaining a general model and using less input data is the key to popularizing the application of machine learning models for estimating groundwater levels. This study evaluated the potential of the kernel-based nonlinear extension of the Arps decline model (KNEA), long short-term memory network (LSTM) and gated recurrent unit (GRU) for accurately estimating GWL in the Hetao Irrigation District in China. All models were developed using monthly records from 143 monitoring wells between 1990 and 2015. Eight input combinations (including the one-month prior GWL, air temperature, global solar radiation, precipitation and amount of irrigation) were applied to explore the possibility of improving model accuracy using less input data. In addition, the general performance of the models was evaluated by cross validation. The results showed that the KNEA model was superior to the LSTM and GRU models for all input combinations using the local application. For cross-district application, the average statistical results indicated that the LSTM (RMSE = 0.45 m and R2 = 0.78) and GRU (RMSE = 0.48 m and R2 = 0.76) models performed better than the KNEA model (RMSE = 0.70 m and R2 = 0.62), and the LSTM model achieved the highest accuracy and stability. For input data, these three models had difficulty obtaining satisfactory monthly GWLs using meteorological and irrigation data without pervious GWL data. Adding meteorological data on the basis of the historical GWL greatly improved the accuracy of the models. Compared with PREC and GSR, adding temperature input had the best improvement. However, adding large-scale average irrigation data did not significantly improve the accuracy of the models. In addition, the LSTM model and input data of the historical GWLs and temperature were recommended in arid and semiarid agricultural areas with limited data.

Multimodal Emotion Recognition Using Non-Inertial Loss Function

Automatic understanding of human emotion in a wild setting using audiovisual signals is extremely challenging. Latent continuous dimensions can be used to accomplish the analysis of human emotional states, behaviors, and reactions displayed in real-world settings. Moreover, Valence and Arousal combinations constitute well-known and effective representations of emotions. In this paper, a new Non-inertial loss function is proposed to train emotion recognition deep learning models. It is evaluated in wild settings using four types of candidate networks with different pipelines and sequence lengths. It is then compared to the Concordance Correlation Coefficient (CCC) and Mean Squared Error (MSE) losses commonly used for training. To prove its effectiveness on efficiency and stability in continuous or non-continuous input data, experiments were performed using the Aff-Wild dataset. Encouraging results were obtained.

RETRACTED: Campus football application based on FPGA system and GPS wearable electronic equipment

Campus football application is a Wearable innovation in sports area disassembling wearable innovation functionality for different clients and why there is such a need for these gadgets in everyday existence. It shows how persuasive the various sensors are in conveying an assortment of readings, which can help from many angles, in the existing method, deep learning and machine learning-based campus football application monitoring system. In this current system, data monitoring, data sharing are significantly less accurate in the football application monitoring system. So in the proposed system Global Positioning System (GPS) and FPGA (Field Programmable Gate Array) for Campus Football Application. Wearable sensors are expanding at work, and by coordinating innovations, clients are gathering more information about themselves. The scale of the wearable design is vast, each with its function to perform in different organizations. Sports wearable include an inertia rating unit and a Global Positioning System (GPS) sensor, which can be modified for various purposes. In this audit, differences show which sensors are feasible and lead to sensor innovation for sport applications. The sport requires constant emotional assessment. This is because the details observed by the sensors are physical. The Colony Optimization Algorithm presentation classifies a portion of the assessment capabilities. Separation can give clients a picture of their performance. The sensors measure the execution details and are done by data preparation, where the channels may vary on the actual information in terms of execution. Other reliability concerns are whether the continuous data input is as accurate as the post-game information.

The Impact of Different System Call Representations on Intrusion Detection

Abstract Over the years, artificial neural networks have been applied successfully in many areas including IT security. Yet, neural networks can only process continuous input data. This is particularly challenging for security-related, non-continuous data like system calls of an operating system. This work focuses on five different options to preprocess sequences of system calls so that they can be processed by neural networks. These input options are based on one-hot encodings and learning word2vec, GloVe or fastText representations of system calls. As an additional option, we analyse if mapping system calls to their respective kernel modules is an adequate generalization step for (i) replacing system calls or (ii) enhancing system call data with additional information regarding their context. When performing such preprocessing steps it is important to ensure that no relevant information is lost during the process. The overall objective of system call analysis in the context of IT security is to categorize a sequence of them as benign or malicious behavior. Therefore, this scenario is used to evaluate different system call representations in a classification task. Results indicate that a broader range of attacks can be detected when enriching system call representations with corresponding kernel module information. Prior learning of embeddings does not achieve significant improvements. This work is an extension of the work by Wunderlich et al. [1] published in Advances in Intelligent Systems and Computing (AISC, volume 951).

Development of a Prediction Model for Demolition Waste Generation Using a Random Forest Algorithm Based on Small DataSets.

Recently, artificial intelligence (AI) technologies have been employed to predict construction and demolition (C&D) waste generation. However, most studies have used machine learning models with continuous data input variables, applying algorithms, such as artificial neural networks, adaptive neuro-fuzzy inference systems, support vector machines, linear regression analysis, decision trees, and genetic algorithms. Therefore, machine learning algorithms may not perform as well when applied to categorical data. This article uses machine learning algorithms to predict C&D waste generation from a dataset, as a way to improve the accuracy of waste management in C&D facilities. These datasets include categorical (e.g., region, building structure, building use, wall material, and roofing material), and continuous data (particularly, gloss floor area), and a random forest (RF) algorithm was used. Results indicate that RF is an adequate machine learning algorithm for a small dataset consisting of categorical data, and even with a small dataset, an adequate prediction model can be developed. Despite the small dataset, the predictive performance according to the demolition waste (DW) type was R (Pearson’s correlation coefficient) = 0.691–0.871, R2 (coefficient of determination) = 0.554–0.800, showing stable prediction performance. High prediction performance was observed using three (for mortar), five (for other DW types), or six (for concrete) input variables. This study is significant because the proposed RF model can predict DW generation using a small amount of data. Additionally, it demonstrates the possibility of applying AI to multi-purpose DW management.

A programming model for Hybrid Workflows: Combining task-based workflows and dataflows all-in-one

In the past years, e-Science applications have evolved from large-scale simulations executed in a single cluster to more complex workflows where these simulations are combined with High-Performance Data Analytics (HPDA). To implement these workflows, developers are currently using different patterns; mainly task-based and dataflow. However, since these patterns are usually managed by separated frameworks, the implementation of these applications requires to combine them; considerably increasing the effort for learning, deploying, and integrating applications in the different frameworks.This paper tries to reduce this effort by proposing a way to extend task-based management systems to support continuous input and output data to enable the combination of task-based workflows and dataflows (Hybrid Workflows from now on) using a single programming model. Hence, developers can build complex Data Science workflows with different approaches depending on the requirements. To illustrate the capabilities of Hybrid Workflows, we have built a Distributed Stream Library and a fully functional prototype extending COMPSs, a mature, general-purpose, task-based, parallel programming model. The library can be easily integrated with existing task-based frameworks to provide support for dataflows. Also, it provides a homogeneous, generic, and simple representation of object and file streams in both Java and Python; enabling complex workflows to handle any data type without dealing directly with the streaming back-end.During the evaluation, we introduce four use cases to illustrate the new capabilities of Hybrid Workflows; measuring the performance benefits when processing data continuously as it is generated, when removing synchronisation points, when processing external real-time data, and when combining task-based workflows and dataflows at different levels. The users identifying these patterns in their workflows may use the presented uses cases (and their performance improvements) as a reference to update their code and benefit of the capabilities of Hybrid Workflows. Furthermore, we analyse the scalability in terms of the number of writers and readers and measure the task analysis, task scheduling, and task execution times when using objects or streams.

Intraday renewable electricity trading: advanced modeling and numerical optimal control

As an extension of (Progress in industrial mathematics at ECMI 2018, pp. 469–475, 2019), this paper is concerned with a new mathematical model for intraday electricity trading involving both renewable and conventional generation. The model allows to incorporate market data e.g. for half-spread and immediate price impact. The optimal trading and generation strategy of an agent is derived as the viscosity solution of a second-order Hamilton–Jacobi–Bellman (HJB) equation for which no closed-form solution can be given. We construct a numerical approximation allowing us to use continuous input data. Numerical results for a portfolio consisting of three conventional units and wind power are provided.

Assessment of load on the lumbar spine using two computerised packages and REBA method

The aim of the research was a comparative analysis of the back lumbar load assessment using three methods: two with continuous input data and evaluation procedures based on mathematical relationships (ShiftBack, 3DSSPP) and one method with categorized input data and tabular load estimation procedures (REBA). For the analysis, work activities and the value of applied force were selected. Among the analyzed 24 work activities were those during which there was a symmetrical load, as well as those during which the applied force or the assumed position of the body caused a lack of load symmetry. The results show that the REBA method differentiates 24 cases of unit load into six levels, while the other two methods provide 24 different values between cases. Cases differing in load even over 100%, when assessed according to the 3DSSPP or ShiftBack do not differ in the assessment of REBA. Differences in the assessment of the same tasks between the results obtained from 3DSSPP and ShiftBack that were above 15% concern only 7 cases. A comparative analysis of the assessment of the lumbar part of the back using three methods indicates strong correlations between the results of the assessment carried out using 3DSSPP and ShiftBack. Smaller relationships were demonstrated by comparing these two methods with the REBA method.

Streamflow modeling of five major rivers that flow into the Gulf of Mexico using SWAT

It has been shown that detailed and continuous riverine discharge and nutrient input data are fundamental to the successful simulation of biogeochemical processes in the ocean using numerical models. Currently, no discharge data for the river mouths on the Mexican side of the Gulf of Mexico (GoM) is available. In the present study, the Soil and Water Assessment Tool (SWAT) was used to simulate the daily discharge of five major rivers that flow directly into the GoM. Two periods were used in the analysis: 1997 to 2013 for the Grijalva basin and 1989 to 2013 for the Usumacinta, Papaloapan, Coatzacoalcos, and Panuco basins. The model was successfully calibrated for monthly time steps using an automatized technique for the five watersheds. The sensitivity analysis of the calibration process showed that for most of the watersheds, the model was sensitive to groundwater and soil moisture parametrizations.

Numerical investigation of dynamic interaction with projectile and harmonic behaviour for T-finned machine gun barrels

Machine gun barrels differ from their rifle counterparts in terms of profile. To support high rates of sustained fire, machine gun barrels are made thicker in order to dissipate more heat and maintain their flexural rigidity and thus accuracy, but on other hand they also contribute in weight addition to weapon. This investigation deals with comparison between a conventional machine gun barrel and an improved innovative design having T-fins, both having same weight and chambered in 5.56 × 45 NATO ammunition, to compare their structural and harmonic characteristics which were parameterized by factors such as modal spectrum, directional deformation at muzzle ends during a single shot fire and harmonic behaviour at corresponding range of exciting frequencies. The solid models of both the barrels having same weight, were created using Solidworks. The continuous input data functions were generated by MATLAB using the field tested discreet data points. The generated velocity-distance functions were converted into time dependent functions using integration algorithms to calculate transient parameters such as time steps, excitation frequency range, angle of rotation of projectile and its angular velocity. The dynamic condition simulated the varying nature of forces due to eccentricity in projectile and this data was fed to a time step study using ANSYS transient structural work bench followed by modal and harmonic analysis. The results showed a significant reduction in muzzle end deformation which thus proved that the T-finned barrel, although had same weight as that of the conventional one, but had better structural and harmonic characteristics, and hence it would inherit better firing accuracy.

Bayesian Stochastic Petri Nets (BSPN) - A new modelling tool for dynamic safety and reliability analysis

An efficient formalism for safety analysis should be: (i) able to consider the failure behaviour of complex engineering systems, and (ii) dynamic in nature to capture changing conditions and have wider applicability. The current formalisms used for safety analysis are lacking in one of the above-listed criteria. Bayesian network (BN) allows the modelling of failure of systems where the inter-nodal dependencies are represented exclusively by conditional probabilities. Stochastic Petri nets (SPN) enable the study of the dynamic behaviour of complex systems; however, they lack the ability to adapt to changes in the data and operating conditions. This paper proposes a hybrid formalism that strengthens SPN with BN capabilities. The proposed formalism is graphical and uses advance feature such as predicates to perform the data updating functions. This ability enables the analysis of continuous input data without the necessity of time-slice discretization process. The proposed formalism is termed “Bayesian Stochastic Petri Nets” (BSPN). It provides a dynamic assessment of safety by capturing additional sets of data rends. In BSPN, the conditional probability is captured as a time-dependent function to allow consideration of the cumulative effect of the failure scenario. The BSPN implementation is demonstrated with an example illustrating the modelling capabilities.

An operational machine learning approach to predict mosquito abundance based on socioeconomic and landscape patterns

Socioeconomic and landscape factors influence mosquito abundance especially in urban areas. Few studies addressed how socioeconomic and landscape factors, especially at micro-scale for mosquito life history, determine mosquito abundance. We aim to predict mosquito abundance based on socioeconomic and/or landscape factors using machine learning framework. Additionally, we determine these factors’ response to mosquito abundance. We identified 3985 adult mosquitoes (majority of which were Aedes mosquitoes) in 90 sampling sites from Charlotte, NC, USA in 2017. Seven socioeconomic and seven landscape factors were used to predict mosquito abundance. Three supervised learning models, k-nearest neighbor (kNN), artificial neural network (ANN), and support vector machine (SVM) were constructed, tuned, and evaluated using both continuous input factors and binary inputs. Random forest (RF) was used to assess individual input’s relative importance and response to mosquito abundance. We showed that landscape factors alone yielded equal or better predictability than socioeconomic factors. The inclusion of both types of factors further improved model accuracy using binary inputs. kNN also had robust performance regardless of inputs (accuracy > 95% for binary and > 99% for continuous input data). Landscape factors group had higher importance than socioeconomic group (54.4% vs. 45.6%). Landscape heterogeneity (measured by Shannon index) was the single most important input factor for mosquito abundance. Landscape factors were the key for mosquito abundance. Machine learning models were powerful tools to handle complex datasets with multiple socioeconomic and landscape factors to accurately predict mosquito abundance.

A hierarchical, fuzzy inference approach to data filtration and feature prioritization in the connected manufacturing enterprise

In manufacturing, the technology to capture and store large volumes of data developed earlier and faster than corresponding capabilities to analyze, interpret, and apply it. The result for many manufacturers is a collection of unanalyzed data and uncertainty with respect to where to begin. This paper examines big data as both an enabler and a challenge for the connected manufacturing enterprise and presents a framework that sequentially tests and selects independent variables for training applied machine learning models. Unsuitable features are discarded, and each remaining feature receives a crisp numeric output and a linguistic label, both of which are measures of the feature’s suitability. The framework is tested using three datasets employing time series, binary, and continuous input data. Results of filtered models are compared to results obtained by base, unfiltered sets of features using a proposed metric of performance-size ratio. Framework results outperform base feature sets in all tested cases, and the proposed future research will be to implement it in a case study in the electronic assembly manufacture.

Cushing response-based warning system for intensive care of brain-injured patients

ObjectiveCushing response (CR) is categorized. Wavelet transform (WT) and decision tree (DT) are utilized to analyze physiological signals from neurocritical patients. A warning model is built for recognition of CR, real-time evaluation of intracranial condition and prediction of neurological outcome. MethodsPhysiological signals of neurocritical patients are preprocessed by WT and compressed by linear regression. An algorithm labels each segment as pathological, physiological, negative or uncertain CR. The DT identifies CR. Continuous data input to the established DT predicts condition at that moment and following outcome. ResultsFrom 33 neurocritical patients, 422,524 sets of physiological signals were collected. The cross-validation scores of DT ranged from 0.562 to 0.579 with averaged accuracy rate 60.6% (3.5–98.1%). The model correctly predicted the outcome of the training group, 87.9% in accuracy. The ratios of pathological CR were 9.3 ± 16.6%, 74.2 ± 29.7% and 99.7 ± 0.3% in patients of good, coma and death groups, respectively. The prediction accuracy for a test set of 103 patients reached 81.6%. ConclusionsCushing response categorization helps in identifying critical conditions and predicting outcome. SignificanceA novel concept of four categories of Cushing response is proposed to represent broader ranges of intracranial change.

Weather Forecasting Models Using Neural Networks and Adaptive Neuro Fuzzy Inference for Two Case Studies at Huoston, Texas and Dallas States

Forecasting of precipitation is one of the most challenging operational tasks done by hydrologists. This operation can be described as most complicated procedure that includes multiple specialized fields of expertise. In this research a comprehensive study was employed to forecast daily precipitation depending on different weather parameters. This was done by using two different methods which are back propagation neural networks BPNN and adaptive neuro inference system ANFIS. Two case studies were selected for this operation which are Huoston, Texas and Dallas, Texas. The high performance of the applied models in forecasting the daily precipitation was concluded especially by using auxiliary weather data with the lagged day precipitation values since the BPNN and ANFIS were able to learn from continuous input data