Prediction Of Different Types Research Articles

Weather impact on macroscopic traffic stream variables prediction using recurrent learning approach

Accurate prediction of the macroscopic traffic stream variables is essential for traffic operation and management in an intelligent transportation system. Adverse weather conditions like fog, rainfall, and snowfall affect the driver’s visibility, vehicle mobility, and road capacity. The rainfall effect on traffic is not directly proportional to the distance between the weather station and the road because of terrain feature constraints. The prolonged rainfall weakens the drainage system, affects soil absorption capability, which causes waterlogging. The weather event has a spatiotemporal correlation with traffic stream variables, as waterlogging on the road due to rainfall affects the traffic on adjacent roads. The spatiotemporal and prolonged impact of rainfall is not studied in the literature. In this research, we examine whether the inclusion of the rainfall variable improves the traffic stream variables prediction of a deep learning model or not. We use the RNN and LSTM models to capture the spatiotemporal correlation between traffic and rainfall data using past and current traffic and weather information. To capture the prolonged impact of rainfall more extended past sequence of rainfall data than traffic data is used in this study. The roads prone to waterlogging are more affected due to rainfall compared to freeways. Thus we examine the effect of rain on traffic stream variables prediction for different types of roads. The test experiments show that the inclusion of weather data improves the prediction accuracy of the model. The LSTM outperforms other models to capture the spatiotemporal relationship between the rainfall and traffic stream variables.

Fracture behavior of high-strength bolted steel connections at elevated temperatures

In fire events, to utilize catenary effect and accommodate large deformation in beams demands a sufficient deformation capacity and ductility in steel bolted connections, which is not well considered in design practice. Therefore, for performance-based fire safety design, it becomes very essential to accurately predict the fracture behavior of steel bolted connections at elevated temperatures. However, experimentally predicting their fracture behavior is very costly at elevated temperatures and limited by the scale of structural components. Therefore, this paper proposes a numerical analysis approach and investigates the fracture behavior of high-strength bolted steel connections at elevated temperatures based on the validated numerical analysis approach. The temperature-dependent material properties including true stress-strain curves and fracture parameters in a three-stage fracture model (describing the pure tension, pure shear, and combined tension and shear fracture behavior) for high-strength ASTM A325 bolt and A572 Grade 50 steel are firstly calibrated from and validated against their tensile and shear test results. They are further validated against the test results on single-bolted and multi-bolted connections at elevated temperatures, which were not used in the calibration of these material properties. The validated material properties and fracture parameters are finally proposed for fracture prediction of different types of bolted connections under various loading conditions at elevated temperatures. This study shows the potential of reasonable prediction of the fracture behavior for the steel bolted connections at elevated temperatures and under complicated loading conditions using a numerical analysis approach. According to the numerical analysis results, the degradation of shear fracture resistance of A325 bolts at elevated temperatures is more significant than that of A572 Grade 50 steel plate, which may lead to a bolt shear failure mode for these connections with a large end distance at high temperatures (>400 °C). It is also found that the fracture failure mode can significantly influence the degradation of the load and deformation capacities of high-strength steel bolted connections at elevated temperatures. With the bolt shear failure mode, the degradation of load and deformation capacities of steel bolted connections are more significant than that with plate tearing-out failure mode.

Spam detection and high-quality features to analyse question –answer pairs

Purpose In community question and answer (CQA) services, because of user subjectivity and the limits of knowledge, the distribution of answer quality can vary drastically – from highly related to irrelevant or even spam answers. Previous studies of CQA portals have faced two important issues: answer quality analysis and spam answer filtering. Therefore, the purposes of this study are to filter spam answers in advance using two-phase identification methods and then automatically classify the different types of question and answer (QA) pairs by deep learning. Finally, this study proposes a comprehensive study of answer quality prediction for different types of QA pairs. Design/methodology/approach This study proposes an integrated model with a two-phase identification method that filters spam answers in advance and uses a deep learning method [recurrent convolutional neural network (R-CNN)] to automatically classify various types of questions. Logistic regression (LR) is further applied to examine which answer quality features significantly indicate high-quality answers to different types of questions. Findings There are four prominent findings. (1) This study confirms that conducting spam filtering before an answer quality analysis can reduce the proportion of high-quality answers that are misjudged as spam answers. (2) The experimental results show that answer quality is better when question types are included. (3) The analysis results for different classifiers show that the R-CNN achieves the best macro-F1 scores (74.8%) in the question type classification module. (4) Finally, the experimental results by LR show that author ranking, answer length and common words could significantly impact answer quality for different types of questions. Originality/value The proposed system is simultaneously able to detect spam answers and provide users with quick and efficient retrieval mechanisms for high-quality answers to different types of questions in CQA. Moreover, this study further validates that crucial features exist among the different types of questions that can impact answer quality. Overall, an identification system automatically summarises high-quality answers for each different type of questions from the pool of messy answers in CQA, which can be very useful in helping users make decisions.

Identification of miRNA Biomarkers for Diverse Cancer Types Using Statistical Learning Methods at the Whole-Genome Scale.

Genome-wide analysis of miRNA molecules can reveal important information for understanding the biology of cancer. Typically, miRNAs are used as features in statistical learning methods in order to train learning models to predict cancer. This motivates us to propose a method that integrates clustering and classification techniques for diverse cancer types with survival analysis via regression to identify miRNAs that can potentially play a crucial role in the prediction of different types of tumors. Our method has two parts. The first part is a feature selection procedure, called the stochastic covariance evolutionary strategy with forward selection (SCES-FS), which is developed by integrating stochastic neighbor embedding (SNE), the covariance matrix adaptation evolutionary strategy (CMA-ES), and classifiers, with the primary objective of selecting biomarkers. SNE is used to reorder the features by performing an implicit clustering with highly correlated neighboring features. A subset of features is selected heuristically to perform multi-class classification for diverse cancer types. In the second part of our method, the most important features identified in the first part are used to perform survival analysis via Cox regression, primarily to examine the effectiveness of the selected features. For this purpose, we have analyzed next generation sequencing data from The Cancer Genome Atlas in form of miRNA expression of 1,707 samples of 10 different cancer types and 333 normal samples. The SCES-FS method is compared with well-known feature selection methods and it is found to perform better in multi-class classification for the 17 selected miRNAs, achieving an accuracy of 96%. Moreover, the biological significance of the selected miRNAs is demonstrated with the help of network analysis, expression analysis using hierarchical clustering, KEGG pathway analysis, GO enrichment analysis, and protein-protein interaction analysis. Overall, the results indicate that the 17 selected miRNAs are associated with many key cancer regulators, such as MYC, VEGFA, AKT1, CDKN1A, RHOA, and PTEN, through their targets. Therefore the selected miRNAs can be regarded as putative biomarkers for 10 types of cancer.

Visually guided homing of bumblebees in ambiguous situations: A behavioural and modelling study.

Returning home is a crucial task accomplished daily by many animals, including humans. Because of their tiny brains, insects, like bees or ants, are good study models for efficient navigation strategies. Bees and ants are known to rely mainly on learned visual information about the nest surroundings to pinpoint their barely visible nest-entrance. During the return, when the actual sight of the insect matches the learned information, the insect is easily guided home. Occasionally, modifications to the visual environment may take place while the insect is on a foraging trip. Here, we addressed the ecologically relevant question of how bumblebees' homing is affected by such a situation. In an artificial setting, we habituated bees to be guided to their nest by two constellations of visual cues. After habituation, these cues were displaced during foraging trips into a conflict situation. We recorded bumblebees' return flights in such circumstances and investigated where they search for their nest entrance following the degree of displacement between the two visually relevant cues. Bumblebees mostly searched at the fictive nest location as indicated by either cue constellation, but never at a compromise location between them. We compared these experimental results to the predictions of different types of homing models. We found that models guiding an agent by a single holistic view of the nest surroundings could not account for the bumblebees' search behaviour in cue-conflict situations. Instead, homing models relying on multiple views were sufficient. We could further show that homing models required fewer views and got more robust to height changes if optic flow-based spatial information was encoded and learned, rather than just brightness information.

Holistic Prediction of the pKa in Diverse Solvents Based on a Machine-Learning Approach.

While many approaches to predict aqueous pKa values exist, the fast and accurate prediction of non-aqueous pKa values is still challenging. Based on the iBonD experimental pKa database (39 solvents), a holistic pKa prediction model was established using machine learning. Structural and physical-organic-parameter-based descriptors (SPOC) were introduced to represent the electronic and structural features of the molecules. The models trained with a neural network or the XGBoost algorithm showed the best prediction performance with a low MAE value of 0.87 pKa units. The approach allows a comprehensive mapping of all possible pKa correlations between different solvents and it was validated by predicting the aqueous pKa and micro-pKa of pharmaceutical molecules and pKa values of organocatalysts in DMSO and MeCN with high accuracy. An online prediction platform was constructed based on the current model, which can provide pKa prediction for different types of X-H acidity in the most commonly used solvents.

Systematic Analysis of Fine-Grained Mobility Prediction With On-Device Contextual Data

User mobility prediction is widely considered by the research community. Many studies have explored various algorithms to predict where a user is likely to visit based on their contexts and trajectories. Most of existing studies focus on specific targets of predictions. While successful cases are often reported, few discussions have been done on what happens if the prediction targets vary: whether coarser locations are easier to be predicted, and whether predicting the immediate next location on the trajectory is easier than predicting the destination. On the other hand, while spatiotemporal tags and content information are commonly used in current prediction tasks, few have utilized the finer grained, on-device user behavioral data, which are supposed to be more informative and indicative of user intentions. In this paper, we conduct a systematic study on the mobility prediction using a large-scale real-world dataset that contains plentiful contextual information. Based on a series of learning models, including a Markov model, two recurrent neural network models, and a multi-modal learning method, we perform extensive experiments to comprehensively investigate the predictability of different types of granularities of targets and the effectiveness of different types of signals. The results provide insightful knowledge on what can be predicted along with how, which sheds light on the real-world mobility prediction from a relatively general perspective.

El Niño Diversity Across Boreal Spring Predictability Barrier

AbstractEl Niño exerts widespread hydroclimate impacts during boreal summer. However, the current prediction of El Niño across boreal spring has the most severe forecast errors, partially due to the lack of understanding diversified El Niño onset and decay. Here we show, through nonlinear k‐means cluster analysis of evolutions of 40 El Niño events since 1870, El Niño exhibits complex and diverse flavors in its onset and decay across boreal spring predictability barrier. We detected three types of El Niño onset and three types of decay. Each type exhibits distinct coupled dynamics, precursors, and hydroclimate impacts. The results guide the prediction of different types of El Niño transition amid spring predictability barrier and global land precipitation during early and late boreal summer. The new classification offers a metric to evaluate performances of climate models and to project future change of El Niño properties and its predictability.

What Personal Information Can a Consumer Facial Image Reveal? Implications for Marketing ROI and Consumer Privacy

Massive availability of individuals’ facial images through online uploads and CCTV surveillance, combined with lacking regulation, presents potential for companies to obtain richer consumer data -- at the risk of privacy violations through exposure of personal information in such images. Building on rich survey data and supermarket video and receipt information, we provide systematic evaluation of relative predictability of different types of personal information -- through deep learning on facial images. We find facial images provide versatile statistical signals on individual's behaviors, preferences, character, personality, and beliefs. A large part of such predictive power is attributable to basic demographics extracted from the face. However, image artifacts, observable facial features, and deep image features extracted by a neural net all contribute to prediction accuracy beyond demographics. Using empirical evidence, a decision theory proof, and a simulation study, we argue such incremental information can meaningfully increase return on investment (ROI) when used for targeting. The limited accuracy of predictions from facial images attenuates the privacy risks to some degree, however, the variety of signals from a facial image is surprising. Prejudice caused by human decision makers' exposure to such statistical information is a substantial concern. We hope our results and the novel data we release with this work inspire research in the emerging area of facial analysis.

Current State of the Art for Survival Prediction in Cancer Using Data Mining Techniques

Background: Cancer treatment is expensive and results in a lot of side effects, and thus survival prediction is necessary for the patients as well as the clinician. Data mining technology has been used in the medical domain to extract interesting information. Cancer prognosis is such an application in medicine. Objective: This study focuses on identifying the technologies used in the recent past for predicting the survival of cancer patients. Supervised, semi-supervised and unsupervised techniques have been used over the years successfully for the survival prediction of different types of cancer. Methods: A systematic literature review process has been followed in this study to discover the future directions of the research. This study focuses on uncovering the gaps in recent studies. Results and Conclusion: It has been found that the present system lacks structured information of the patients. Also, there are a lot of different cancer types that are still unexplored in terms of survival prediction, mainly due to the unavailability of sufficient data. Hence a lot can be improved if researchers may get their hands on required data for the research.

Risk factors of interstitial lung diseases in clinically amyopathic dermatomyositis.

BackgroundClinically amyopathic dermatomyositis (CADM) is a unique sub-type of idiopathic inflammatory myopathies with a high prevalence of interstitial lung disease (ILD). Poor prognosis of the patients was strongly associated with rapid progressive ILD. The aim of this study was to identify risk factors for prediction of different types of ILD in CADM.MethodsIn this study, data of 108 inpatients with CADM were collected, including 87 with ILD. The baseline clinical data and laboratory parameters, including myositis-specific and associated antibodies and tumor-associated antigens were analyzed to identify risk factors for acute or subacute interstitial pneumonitis (A/SIP) and chronic interstitial pneumonitis (CIP).ResultsIn 87 patients with CADM-ILD, 39 (36.1%) were A/SIP, and 48 (44.4%) were CIP. There were 22 (20.4%) patients with asymptomatic ILD who were detected by routine high resolution computed tomography. Cytokeratin-19 fragment (CYFRA21-1) was significantly higher in CADM-ILD than that in CADM patients without ILD; carcinoembryonic antigen and neuron-specific enolase were significantly elevated in A/SIP than that in CIP. Patients with A/SIP had a higher positive rate of anti-melanoma differentiation-associated gene 5 (MDA5), while patients with CIP had a higher positive rate of anti PL-12 and anti-Ro-52. Logistic regression analysis indicated that elevation of CYFRA21-1 was a risk factor for ILD, higher titer of anti-MDA5 indicated increased likelihood for A/SIP, and higher titer of anti-Ro-52 was also clearly associated with CIP.ConclusionsThis study indicated that the prevalence of ILD was high in CADM. Asymptomatic ILD has been previously underestimated. Anti-MDA5 was a risk factor for the presence of A/SIP, and CYFRA21-1 was a risk factor for ILD.

Usage and implementation of neuro-fuzzy systems for classification and prediction in the diagnosis of different types of medical disorders: a decade review

In classification and prediction of different types of medical disorders the neuro-fuzzy systems (NFS) are playing vital and significant role. To avoid false diagnosis the NFS assists medical practitioners to a greater extent in automating the domain dealing with medical disorders. With the passage of time the NFS approach has become apparent to enhance accuracy in dealing with a wide range of complicated research problems in the field of medical diagnosis. In this paper the author presents the literature review of the research done in implementing NFS in the field of medical diagnosis for current decade. Total of 100 publications in chronological advancement and up-gradation in models are considered for the time period of 10 years. A detailed study of each disease is carried out to discuss how NFS methodologies have been applied for classification and prediction in the diagnosis of different types of medical disorders. Ten (10) most severe medical disorders i.e. cancer, cardiovascular, depression and anxiety, diabetes, communicable, kidney, liver, neuro-degenerative, respiratory and thyroid has been undertaken for the study. Based on the study carried out it has been observed that NFS found to be effective as compared to the application of other AI techniques in medical diagnosis. Study reveals that effectiveness of NFS increases significantly when integrated with other AI approaches. This review adds into the knowledge of different researchers working in the field of medical diagnosis and will also give the comprehensive view of the effectiveness of the NFS techniques being used in medical diagnosis. The paper also incorporates a few research publications that were submitted in 2019 to incorporate the latest advances in medical science implementation of NFS.

Science mapping approach to assisting the review of mine water disaster prediction and evaluation in China between 2009 and 2019

Mine water inrush occurs frequently in China, and it can cause serious economic losses and heavy casualties. Thus, it is very important to realize risk assessment of mine water inrush. After collecting 4082 journal documents on risk assessment of mine water inrush from 2009 to 2019 in CNKI journal database, and using CiteSpace visualization software to do data analysis, the research hotspot and frontier trend in mine water inrush research in China are obtai ned. The prevention and prediction of different types of water disasters is a major trend in this field.

Experimental and Computational Fluid Dynamics Validation of Correlations for Dry Pressure Drop in Trays without Downcomer

AbstractThe dry tray pressure drop (ΔPd) is a design parameter that provides preliminary information about the total pressure drop. This work aimed to assess correlations for ΔPd prediction for different types of trays without downcomer and to evaluate the effects of the free area ratio (φ) and the hole diameter (d) on ΔPd. Assessment was performed by comparing results of several correlations with those from an experimentally validated computational fluid dynamics simulation. The study shows that the correlations of Červenka and Kolář, Bennett, Agrawal and Cook, and Stichlmair and Mersmann predicted the dry pressure drop satisfactorily. The correlation of Bennett, Agrawal and Cook can be recommended for the prediction of ΔPd for a wide range of geometries and operation conditions. Also, φ has a higher influence on ΔPd than d.

Prediction of building electricity usage using Gaussian Process Regression

The prediction of building energy use is the basis for smart building operation, which optimizes building performance through control and low-energy strategy. For reducing computation complexity and improving calculation accuracy, a comparative study of online electricity data predictions for different types of buildings was conducted. This study is also intended to assess the capability and accuracy of the supervised machine learning methods, with which the kernel algorithms of predictions were developed. Specifically, in this study, large-scale real data collected from the building energy management system were used in the online energy consumption forecasting, which is specially designed for optimized control, real-time fault detection, diagnosis and abnormality alarms. Firstly, the characteristics of building energy profiles and data reliability were addressed. Mathematical algorithms were introduced and their previous applications in building energy usage prediction were summarized, including the evaluation criteria that are effective for energy use predictions in buildings. The reliability and efficiency of the proposed algorithms were then demonstrated through the comparison between the monitored actual data and the predicted results. It is found that Gaussian Process Regression (GPR) can give acceptable predictions on the energy consumption of office buildings with an equilibrium of data prediction accuracy with the average deviations of below 15% and low computation time. Additionally, the statistical evaluation criteria proposed by ASHRAE can also be satisfied. For hotels and shopping malls where complex functions were applied in these buildings, their accuracy are not better or even the same as those of simplified models, due to the significant effects of the factors involving occupant's activities and schedules as well as data reliability on building energy usage. Our result revealed that GPR is a reliable method and can still generate highly accurate predictions when a large data set with a small time interval and complex energy use patterns obtained from real building measurements rather than simulated data are involved.

Temporal Prediction of Multiapplication Consolidated Workloads in Distributed Clouds

With their fast development and deployment, a large number of cloud services provided by distributed cloud data centers have become the most important part of Internet services. In spite of numerous benefits, their providers face some challenging issues, e.g., dynamic resource scaling and power consumption. Workload prediction plays a crucial role in addressing them. Accuracy and fast learning are the key performances. Its consistent efforts have been made for their improvement. This paper proposes an integrated prediction method that combines the Savitzky–Golay filter and wavelet decomposition with stochastic configuration networks to predict workload at the next time slot. In this approach, a task time series is first smoothed by the SG filter, and the smoothed one is then decomposed into multiple components via wavelet decomposition. Based on them, an integrated model is, for the first time, established and can well characterize the statistical features of both trend and detailed components. Experimental results demonstrate that it achieves better prediction results and faster learning speed than some representative prediction methods. Note to Practitioners —Workload prediction plays an important role in constructing scalable and green distributed cloud data centers. This paper presents a novel and fundamental methodology to achieve accuracy and fast learning for workload prediction. It develops an integrated prediction approach that combines the Savitzky–Golay filter and wavelet decomposition with stochastic configuration networks to predict workload at the next time slot. In order to establish a fine prediction model for the obtained information while achieving better prediction results and faster learning speed, this paper proposes an integrated method, SGW-S, to build a prediction model of a task time series and determine its optimal model parameters. The experimental results in the real-world data set show that the proposed method outperforms baseline methods in predicting the large-scale task time series. The proposed approach can aid the design and optimization of industrial cloud data centers and practitioners’ prediction of different types of task time series.

Прогноз неантиклинальных ловушек углеводородов различных типов в юрских комплексах северо-востока Западной Сибири

Прогноз неантиклинальных ловушек углеводородов различных типов в юрских комплексах северо-востока Западной Сибири

Towards real-time respiratory motion prediction based on long short-term memory neural networks

Radiation therapy of thoracic and abdominal tumors requires incorporating the respiratory motion into treatments. To precisely account for the patient’s respiratory motions and predict the respiratory signals, a generalized model for predictions of different types of patients’ respiratory motions is desired. The aim of this study is to explore the feasibility of developing a long short-term memory (LSTM)-based generalized model for the respiratory signal prediction. To achieve that, 1703 sets of real-time position management (RPM) data were collected from retrospective studies across three clinical institutions. These datasets were separated as the training, internal validity and external validity groups. Among all the datasets, 1187 datasets were used for model development and the remaining 516 datasets were used to test the model’s generality power. Furthermore, an exhaustive grid search was implemented to find the optimal hyper-parameters of the LSTM model. The hyper-parameters are the number of LSTM layers, the number of hidden units, the optimizer, the learning rate, the number of epochs, and the length of time lags. The obtained model achieved superior accuracy over conventional artificial neural network (ANN) models: with the prediction window equaling to 500 ms, the LSTM model achieved an average relative mean absolute error (MAE) of 0.037, an average root mean square error (RMSE) of 0.048, and a maximum error (ME) of 1.687 in the internal validity data, and an average relative MAE of 0.112, an average RMSE of 0.139 and an ME of 1.811 in the external validity data. Compared to the LSTM model trained with default hyper-parameters, the MAE of the optimized model results decreased by 20%, indicating the importance of tuning the hyper-parameters of LSTM models to obtain superior accuracies. This study demonstrates the potential of deep LSTM models for the respiratory signal prediction and illustrates the impacts of major hyper-parameters in LSTM models.

Linking the North American Dipole to the Pacific Meridional Mode

AbstractThe North American dipole (NAD) represents a meridional dipole of sea level pressure anomalies over the western tropical North Atlantic and northeastern North America. This study demonstrates that the NAD is intimately linked to the development of the Pacific meridional mode (PMM). In addition to the North Pacific Oscillation, the NAD provides another important remote forcing source to trigger the PMM. The NAD influences the PMM through both direct and indirect pathways. The direct effect is that the winter NAD influences the sea surface temperature (SST) and surface winds over the northeastern subtropical Pacific (NESP) through concurrent anticyclonic flow associated with the NAD, which tends to generate a weak initial warming over the NESP region during late winter and early spring. The indirect effect is that the NAD first induces SST cooling over the northern tropical Atlantic during spring, and the northern tropical Atlantic SST cooling then generates a low‐level anticyclonic flow anomaly over the NESP, which further strengthens the surface warming over the NESP, thereby causing the development of the PMM in the following months. The NAD can also exert an influence on the El Niño–Southern Oscillation through its effects on the PMM. In particular, El Niño episodes led by the combined NAD‐PMM events tend to take the form of the central Pacific El Niño, rather than the canonical eastern Pacific El Niño. We suggest that a better understanding of the NAD‐PMM‐El Niño–Southern Oscillation dynamic link could be useful for the prediction of different types of El Niño event.

Churn prediction and social neighbour influences for different types of user groups in virtual worlds

AbstractIn virtual worlds (VWs), users have more VW games alternatives, whereas VW companies consequently suffer from high customer turnover rate and low customer loyalty. Therefore, building a churn prediction model to facilitate subsequent churn management and customer retention is important. The churn behaviours and the impact of social neighbour influences to customer churn may be different for different types of users. Accordingly, we segment users into stable, unstable, and solitary user groups according to their social contact behaviours in VWs. Novel segmentation‐based churn prediction approaches are proposed for churn prediction in VWs by building prediction models for each type of user groups and considering the effect of social neighbour influences for different user groups. The proposed approaches are evaluated by conducting experiments with a dataset collected from a VW platform. The experimental results show different churn prediction performances under different user groups. The segmentation‐based churn prediction approaches perform better than do general approaches without considering user groups. Moreover, the results also reveal that social neighbour influences have a positive impact on stable and unstable users. The proposed work contributes to investigating the social neighbour influences on churn prediction for different types of user groups in VWs.