Terms Of Prediction Research Articles

Short Term and Long term Building Electricity Consumption Prediction Using Extreme Gradient Boosting

Background: Electricity is considered as the essential unit in today’s high-tech world. The electricity demand has been increased very rapidly due to increased urbanization,(smart buildings, and usage of smart devices to a large extent). Building a reliable and accurate electricity consumption prediction model becomes necessary with the increase in demand for energy. From recent studies, prediction models such as support vector regression (SVR), gradient boosting decision tree (GBDT), artificial neural network (ANN), random forest (RF), and extreme gradient boosting (XGBoost) have been compared for the prediction of electricity consumption and XGBoost is found to be the most efficient method that leads to the motivation for the research. Objective: The objective of this research is to propose a model that performs future electricity consumption prediction for different time horizons: short term prediction and long term prediction using the extreme gradient boosting method and reduce prediction errors. Also, based on the prediction of the electricity consumption, the best and worst predicted days are being recognized. Methods: The method used in this research is the extreme gradient boosting for future building electricity consumption prediction. The extreme gradient boosting method performs predictions for different time horizons(short term and long term) for different seasons(summer and winter). The model was designed for a house building located in Paris. Results: The model has been trained and tested on the dataset and its prediction is accurate with the low rate of errors compared to other machine learning techniques. The model predicts accurately with RMSE of 140.45 and MAE of 28, which is the least value for errors when compared to the baseline prediction models. Conclusion: A model that is robust to all the conditions should be built by enhancing the prediction mechanism such that the model should be dependent on a few factors to make electricity consumption prediction.

A DBULSTM-Adaboost Model for Sea Surface Temperature Prediction.

Sea surface temperature (SST) is an important parameter to measure the energy and heat balance of sea surface. The change of sea surface temperature has an important impact on the marine ecosystem, marine climate and marine environment. Therefore, sea surface temperature prediction has become an significant research direction in the field of ocean. This article proposes a DBULSTM-Adaboost model based on ensemble learning. The model is composed of Deep Bidirectional and Unidirectional Long Short Term Memory (DBULSTM) and Adaboost strong learner. DBULSTM can capture the forward and backward dependence of time series, and the DBULSTM model is integrated with Adaboost strong learner to reduce the variance and bias of prediction and realize the short and medium term prediction of SST at a single point scale. Experimental results show that the model can improve the accuracy and stability of SST prediction. Experiments on the East China Sea and South China Sea with different prediction lengths show that the model is almost superior to other classical models in different sea areas and at different prediction levels. Compared with full-connected LSTM (FC-LSTM) model, the root-mean-square error is reduced by about 0.1.

Traffic Congestion Monitoring Using Smart Traffic Control Approach for Emergency Vehicle

Abstract: The efficiency and robustness increased after using embedded technology for monitoring and control applications. Due to traffic load, intensity can get stuck or they are delayed in reaching their destination. The system describes an intelligent and complex application that helps to clear traffic and to improve security while having fast response of the emergency services. By making use of embedded and wireless communication we can develop an application to clear the traffic while coming in the path. There is a system called as “Intelligent traffic light controller”. Where traffic light intelligently decides based on the total traffic on all adjacent roads. This paper presents the current framework of decision support systems for traffic management based on short and medium term predictions and includes some reflections on their likely evolution, based on current scientific research and the evolution of the availability of new types of data and their associated methodologies. When unexpected and unplanned events such as natural disasters, traffic accidents or even terrorist attacks happen, it is necessary to prepare a quick evacuation process and the provisioning of the quickest access routes for emergency services units.

Predicting the Spread of Vessels in Initial Stage Cervical Cancer through Radiomics Strategy Based on Deep Learning Approach

Novel methods and materials are used in healthcare applications for finding cancer in various parts of the human system. To select the most suitable therapy plan for individuals with domestically progressed cervical cancer, robustness metrics are required to estimate their early phase. The goal of the research is to increase the effectiveness of cervical cancer patients' detection by using deep learning-based radiomics assessment of magnetic resonance imaging (MRI). From March 2016 to November 2019, 125 patients with early-stage cervical cancer provided 980 dynamic X1 contrast-enhanced (X1DCE) and 850 X2 weighted imaging (X2WI) MRI images for training and testing. A convolutional neural network model was used to estimate cervical cancer state based on the specified characteristics. The X1DCE exhibited high discriminative outcomes than X2WI MRI in terms of prediction ability, as calculated by the confusion matrix assessment and receiver operating characteristic (ROC) curve approach. The mean maximum region under the curve of 0.95 was found using an attentive ensemble learning method that included both MRI sequencing (Sensitivity = 0.94, Specificity = 0.94, and accuracy = 0.96). Whenever compared with conventional radiomic approaches, the results show that a variety of radiomics based on deep learning might be created to help radiologists anticipate vascular invasion in patients with cervical cancer before surgery. Based on radiomics technique, it has proven to be an effective tool for estimating cervical cancer in its early stages. It would help people choose the best therapy method for them and make medical judgments.

Dynamical Minimal Flavour Violating inverse seesaw

The Inverse Seesaw mechanism is dynamically realised within the Minimal Lepton Flavour Violation context. Lepton number, whose breaking is spontaneously realised, is generalised to a global Abelian factor of the whole flavour symmetry, that also plays the role of the Peccei-Quinn symmetry. The associated Goldstone boson is a Majoraxion that solves the Strong CP problem and represents a Dark Matter candidate.Three distinct scenarios are identified in terms of flavour symmetry and transformation properties of the exotic neutral leptons that enrich the Standard Model spectrum. The associated phenomenology is studied, focusing on the deviations from unitarity of the PMNS mixing matrix. The strongest constraints arise from the determination of the number of active neutrinos through the invisible width of the Z, the comparison of the measured W boson mass with its prediction in terms of the Fermi constant from muon decay, and the null searches for the radiative rare muon decay and μ → e conversion in nuclei. The heavy neutral leptons may have masses of a few TeV, leaving open the possibility for a direct detection at future colliders.The impact of the recent measurement of the W mass at the CDF II detector has also been considered, which, in one of the scenarios, points to a sharp prediction for the masses of the heavy neutral leptons at about 2 − 3 TeV.

“Ther cam a Privee Theef, Men Clepeth Deeth”: A Tale of Two Plagues and of Altered Perspectives

This article contrasts the 14th century Black Death (Bubonic Plague), particularly in England where its effects are well-attested, with the contemporary COVID-19 pandemic, in terms of similarities and (potential) consequences. The two pandemics, as the paper will argue, have much in common. They are also very different in terms of the death toll as well as, in particular, how modern technology and medical science have been able to deal with COVID-19 arguably much better than 14th century Europe was able to cope with the Black Death. Even so, both plagues have demonstrably impacted society and, in the case of the recent pandemic, we have yet to witness all of its effects. Some careful analysis will be made of the rather dramatic impact of the Black Death in England which, in particular, resulted in the decline of feudalism. I argue that this was the result of a changed perspective. Drawing on that example, this article considers how the current plague may also be changing perspectives in order to make some tentative, longer term predictions about our future.

Automated and efficient local adaptive regression for principal component-based reduced-order modeling of turbulent reacting flows

Principal Component Analysis can be used to reduce the cost of Computational Fluid Dynamics simulations of turbulent reacting flows by reducing the dimensionality of the transported variables through projection of the thermochemical state onto a lower-dimensional manifold. However, because of the nonlinearity of the principal component source terms, nonlinear regression techniques must be utilized for the source terms in terms of the principal components. Unfortunately, widely available and utilized nonlinear regression techniques can have prohibitive computational requirements and/or accuracy that is highly dependent on user experience in ad hoc tuning of model architecture and hyperparameters. In this work, a new nonlinear regression approach is proposed that is both computationally efficient and automated so does not require any user input. The approach is evaluated through a priori prediction of principal component source terms using data from a Direct Numerical Simulation of a turbulent nonpremixed n-heptane/air jet flame. In particular, the proposed framework consists of local regressions whose complexity is adapted according to the local nonlinearity of the data: local linear regression when accurate enough and local Artificial Neural Networks when nonlinear regression is required. The number of local clusters for local regression is determined automatically using the Davies-Bouldin index. In addition, Bayesian optimization is utilized for model training (i.e., to select the best architectures and hyperparameters of the nonlinear regressions in an unsupervised fashion), eliminating ad hoc hand-tuning and/or expensive grid searches. Overall, compared to a single, global neural network, the new local adaptive regression approach is shown to have comparable accuracy but 69% less training time due to the utilization of local linear regression and faster training of local neural networks.

Applying SARIMA, ETS, and hybrid models for prediction of tuberculosis incidence rate in Taiwan.

BackgroundTuberculosis (TB) remained one of the world’s most deadly chronic communicable diseases. Future TB incidence prediction is a benefit for intervention options and resource-allocation planning. We aimed to develop rapid univariate prediction models for epidemics forecasting employment.MethodsThe surveillance data regarding Taiwan monthly TB incidence rates which from January 2005 to June 2017 were utilized for simulation modelling and from July 2017 to December 2020 for model validation. The modeling approaches including the Seasonal Autoregressive Integrated Moving Average (SARIMA), the Exponential Smoothing (ETS), and SARIMA-ETS hybrid algorithms were constructed and compared. The modeling performance of in-sample simulating training sets and pseudo-out-of-sample validating sets were evaluated by metrics of the root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE), and mean absolute scaled error (MASE).ResultsA total of 191,526 TB cases with a highest incidence rate in 2005 (72.5 per 100,000 person-year) and lowest in 2020 (33.2 per 100,000 person-year), from January-2005 to December-2020 showed a seasonality and steadily declining trend in Taiwan. The monthly incidence rates data were utilized to formulate these forecasting models. Through stepwise screening and assessing of the accuracy metrics, the optimized SARIMA(3,0,0)(2,1,0)12, ETS(A,A,A) and SARIMA-ETS-hybrid models were respectively selected as the candidate models. Regarding the outcome assessment of model performance, the SARIMA-ETS-hybrid model outperformed the ARIMA and ETS in the short term prediction with metrics of RMSE, MAE MAPE, and MASE of 0.084%, 0.067%, 0.646%, and 0.870%, during the pseudo-out-of-sample forecasting period. After projecting ahead to the long term forecasting TB incidence rates, ETS model showed the best performance resulting as a 41.69% (range: 22.1–56.38%) reduction of TB epidemics in 2025 and a 54.48% (range: 33.7–68.7%) reduction in 2030 compared with the 2015 levels.ConclusionThis time series modeling might offer us a rapid surveillance tool for facilitating WHO’s future TB elimination milestone. Our proposed SARIMA-ETS or ETS model outperformed the SARIMA in predicting less or 12–30 months ahead of epidemics, and all models showed better in short or medium-term forecasting than long-term forecasting.

A spatiotemporal risk prediction of wildlife-vehicle collisions using machine learning for dynamic warnings

Introduction: The technology in the automotive industry is becoming increasingly safer in the age of automated driving, but the number of accidents is still high, especially in wildlife-vehicle collisions (WVCs). To better avoid these accidents, patterns involved in these accidents must be detected. Method: This paper presents a spatiotemporal risk prediction of WVCs, including various road and environmental characteristics. A process of data preparation using GIS automated by Python scripts was developed to enable a spatiotemporal link of diverse features for the subsequent predictive data analysis. Different machine learning (ML) approaches were applied- random forest (RF), feedforward neural networks (FNN), and support vector machine classifier (SVM) - including automated ML to predict the risk of WVCs. Therefore, a dataset of approximately 731,000 accidents reported to the police in Bavaria over a period of 10 years (2010–2019) was used. In addition, non-accidents were randomly generated in Python over time and space for the supervised ML processes. As the actual risk probability for WVCs and non-WVCs is not entirely known, the impact of different training ratios between accidents and non-accidents was tested on the risk prediction quality (RPQ) (25%, 50%, 75%, 90% WVCs) of the double-weighted sensitivity and single-weighted specificity rate. Results: The test yielded high mean values of RPQ as an indicator for a suitable WVC prediction. Both RF (86.6%) and FNN (86.7%) were identified as suitable choices for WVC risk prediction in terms of RPQ. The SVM yielded a lower prediction quality, even though acceptable results could be achieved within a shorter runtime. Practical Applications: Spatial transferability was verified since the algorithm was trained on the dataset of Bavaria (excluding Upper Bavaria) and successfully tested in Upper Bavaria. WVC forecasts were also proven through training with datasets from 2010-2017 and in prediction for 2018 and 2019.

Experimental validation of a subject-specific finite element model of lumbar spine segment using digital image correlation.

Pathologies such as cancer metastasis and osteoporosis strongly affect the mechanical properties of the vertebral bone and increase the risk of fragility fractures. The prediction of the fracture risk with a patient-specific model, directly generated from the diagnostic images of the patient, could help the clinician in the choice of the correct therapy to follow. But before such models can be used to support any clinical decision, their credibility must be demonstrated through verification, validation, and uncertainty quantification. In this study we describe a procedure for the generation of such patient-specific finite element models and present a first validation of the kinematics of the spine segment. Quantitative computed tomography images of a cadaveric lumbar spine segment presenting vertebral metastatic lesions were used to generate the model. The applied boundary conditions replicated a specific experimental test where the spine segment was loaded in compression-flexion. Model predictions in terms of vertebral surface displacements were compared against the full-field experimental displacements measured with Digital Image Correlation. A good agreement was obtained from the local comparison between experimental data and simulation results (R2 > 0.9 and RMSE% <8%). In conclusion, this work demonstrates the possibility to apply the developed modelling pipeline to predict the displacement field of human spine segment under physiological loading conditions, which is a first fundamental step in the credibility assessment of these clinical decision-support technology.

The use of corticosteroids in the lateral sinus augmentation surgical procedure: A systematic review and meta-analysis.

The lateral maxillary sinus augmentation (MSA) procedure has good predictability in terms of the success of bone regeneration with a low incidence of postoperative infections, estimated between 2% and 5.6%. Although the use of antibiotics is an established and standardized prophylactic measure for MSA procedures, the addition of corticosteroids still varies among clinician preference and clinical judgment. The aim of this systematic review was to identify whether the administration of corticosteroids during the MSA surgical procedure affects postoperative symptoms including swelling, pain, and infection rate. A literature search through PubMed, EMBASE, Ovid MEDLINE, and Web of Science indices, according to PICO criteria, was conducted to identify whether MSA peri-operative use of corticosteroids reduces the incidence of complications and patient morbidity. A single arm meta-analysis was performed due to the lack of randomized controlled trials (RCTs) comparing groups treated with or without peri-operative corticosteroids. The intracluster correlation co-efficient (ICC) and design effect were calculated to adjust for the clustering design. In the 37 studies included, a total of 1599 patients (378 Cort, 1221 No-Cort) were analyzed. Before and after taking account of clustering, there was statistically significant effect of corticosteroids on swelling, pain, wound dehiscence, trismus, and hematoma. The complication rates postoperatively were comparable between the two study groups, however slight differences existed in the incidence of active suppuration (1.7% [95% CI 0.7-3.9] Cort vs. 3.2% [2.2-4.5] No-Cort), wound dehiscence (3.9% [1.3-11.2] Cort vs. 2.1% [1.0-4.1] No-Cort) and trismus (2.7% [0.8-8.4] Cort vs. 1.4% [0.8-2.5] No-Cort). Although the event rate of the 1-to-2-week postoperative complications did not differ between the two groups, the lack of conclusive data and research comparing peri-operative corticosteroid use makes it impossible to draw definitive conclusions and more evidence and studies designed for this specific purpose are needed.

Minimum relevant features to obtain AI explainable system for predicting breast cancer in WDBC

The potential to explain why a machine learning model produces a certain prediction in incomprehensible terms is becoming increasingly crucial, as it provides accountability and confidence in the algorithm's decision-making process. The interpretation of complex models is difficult. Various approaches to dealing with this issue are being offered. These problems are typically handled in tree ensemble methods by assigning priority levels to input features globally or for a specific prediction. We show that current feature attribution approaches are inconclusive, and develop solutions using SHAP (SHapley Additive Explanation) values, LIME (Local Interpretable Model-Agnostic Explanations), and the Skope Rules package. We employ feature selection methods from SHAP and LIME in this work, which uses the Breast cancer Wisconsin data sets. In the suggested method, features are chosen at the first level of feature selection using Decision tree entropy values. Based on the SHAP and LIME reports, level 2 features are chosen from fewer options. The features are tested on a Decision Tree (DT) model and a DT and Support Vector Machine (SVM) ensemble. Experiments suggest that the ensemble works better as compared to DT. We have also used the Skope Rules package to generate global rules for generalization.

Finite Element Modeling of Powder Compaction: Mini-Tablets in Comparison with Conventionally Sized Tablets.

Mini-tablets are considered a promising solid dosage form in the pharmaceutical industry due to advantages such as dosing accuracy, efficiency as a drug delivery system, and alleged improvement in mechanical properties. Nevertheless, only a few experimental studies are available in the literature regarding this topic and technical aspects, such as punch's shape and size effect on the stress and density distribution in the compact mini-tablets, are still not fully investigated. In this paper, the influence of powder properties and process parameters, such as punch shape and size, on the evolution of mechanical properties during the tableting process and the potential occurrence of tablet defects are investigated using the mechanistic modeling approach, Finite Element Method (FEM). The numerical simulation cases consist of four different die sizes, mini-tablets of 2 mm, and 3 mm, and conventionally sized tablets of 8 mm and 11.28 mm. Each tablet size is simulated using four distinctive excipients, Avicel®PH-102, Kollidon®VA64, Pearlitol®100SD, and Supertab®11SD, and two different punch geometries, a flat-face punch, and a bevel edge punch. The model predictions in terms of stress and density distribution at different stages of the compaction process indicate similar behavior in terms of density and stress distribution profiles between the conventionally sized tablets and mini-tablets for a particular excipient. Based on tablet size, small localized differences are noted (e.g., low-density regions, high shear bands, and heterogeneous density profiles), suggesting a possible risk of tableting defects for conventionally sized tablets compared to mini-tablets. Furthermore, it is observed that bevel-edged tablets could facilitate the formation of cracks, leading to possible capping failure.

Smart Sensing and AI for Physical Therapy in IoT Era

It is well known that medical spending increase with disability status. Per capita spending for people with five or more limitations in activities of daily living (ADLs) is nearly five times the amount incurred by those with limitations in only one instrumental activities of daily living (IADLs). Physical therapy is the way to improve the motor capabilities however it takes a lot of time, it requires physiotherapists services, is often painful and the outcome are evaluated in subjective way. New technologies including smart sensors were adopted in healthcare including wearable solutions for cardiac and respiratory activity monitoring and successfully are contributing to reduce the costs of services. In the case of motor activity and particularly in physical rehabilitation the developments are still reduced the physical therapy services are using as hardware mechanical equipment without sensing, embedded processing and internet connectivity that significatively reduce the possibility to measure and evaluate the physical training outcomes in objective way. In this paper the disruptive solutions for physical therapy are presented that are based on hot technologies such as smart sensors, IoT, virtual reality (VR), mixed reality (MR), and artificial intelligence (AI). Applied AI may conduct to develop models, classifiers (gait classification) and short term or medium term prediction of physical therapy outcomes. Highly motivation of the patients under physical rehabilitation can be increased promoting serious game characterized by VR and MR scenarios.

Multisource forest inventories: A model-based approach using k-NN to reconcile forest attributes statistics and map products

Forest map products are widely used and have taken benefit from progresses in the multisource forest inventory approaches, which are meant to improve the precision of forest inventory estimates at high spatial resolution. However, estimating errors of pixel-wise predictions remains difficult, and reconciling statistical outcomes with map products is still an open and important question.We address this problem using an original approach relying on a model-based inference framework and k-nearest neighbours (k-NN) models to produce pixel-wise estimations and related quality assessment. Our approach takes advantage of the resampling properties of a model-based estimator and combines it with geometrical convex-hull models to measure respectively the precision and accuracy of pixel predictions. A measure of pixel reliability was obtained by combining precision and accuracy.The study was carried out over a 7,694 km2 area dominated by structurally complex broadleaved forests in centre of France. The targeted forest attributes were growing stock volume, basal area and growing stock volume increment. A total of 819 national forest inventory plots were combined with auxiliary data extracted from a forest map, Landsat 8 images, and 3D point clouds from both airborne laser scanning and digital aerial photogrammetry. k-NN models were built independently for both 3D data sources. Both selected models included 5 auxiliary variables, and were generated using 5 neighbours, and most similar neighbours distance measure. The models showed relative root mean square error ranging from 35.7% (basal area, digital aerial photogrammetry) in calibration to 63.4% (growing stock volume increment, airborne laser scanning) in the validation set. At pixel level, we found that a minimum of 86.4% of the predictions were of high precision as their bootstrapped coefficient of variation fall below calibration’s relative root mean square error. The amount of extrapolation varied from 4.3% (digital aerial photogrammetry) to 6.3% (airborne laser scanning). A relationship was found between extrapolation and k-NN distance, opening new opportunities to correct extrapolation errors. At the population level, airborne laser scanning and digital aerial photogrammetry performed similarly, offering the possibility to use digital aerial photogrammetry for monitoring purposes.The proposed method provided consistent estimates of forest attributes and maps, and also provided spatially explicit information about pixel predictions in terms of precision, accuracy and reliability. The method therefore produced high resolution outputs, significant for either decision making or forest management purposes.

ANAID-ICH nomogram for predicting unfavorable outcome after intracerebral hemorrhage.

Diffusion-weighted imaging lesions (DWILs) are associated with unfavorable outcome in intracerebral hemorrhage (ICH). We proposed a novel predictive nomogram incorporating DWILs. A total of 738 patients with primary ICH in a tertiary hospital were prospectively enrolled as a training cohort. DWILs were defined as remote focal hyperintensities on DWI corresponding to low intensities on apparent diffusion coefficient images and remote from the focal hematoma. The outcome of interest was modified Rankin Scale scores of 4-6 at 90 days after onset. Multivariate logistic regression was used to construct a nomogram. Model performance was tested in the training cohort and externally validated with respect to discrimination, calibration, and clinical usefulness in another institute. Additionally, the nomogram was compared with the ICH score in terms of predictive ability. Overall, 153 (20.73%) and 23 (15.54%) patients developed an unfavorable outcome in the training and validation cohorts, respectively. The multivariate analysis revealed that age, National Institutes of Health Stroke Scale (NIHSS) score, anemia, infratentorial location, presence of DWILs, and prior ICH were associated with unfavorable outcome. Our ANAID-ICH nomogram was constructed according to the aforementioned variables; the area under the receiver operating characteristic curve was 0.842 and 0.831 in the training and validation sets, respectively. With regard to the 90-day outcome, the nomogram showed a significantly higher predictive value than the ICH score in both cohorts. The ANAID-ICH nomogram comprising age, NIHSS score, anemia, infratentorial location, presence of DWILs, and prior ICH may facilitate the identification of patients at higher risk for an unfavorable outcome.

A dynamic graph representation learning based on temporal graph transformer

The graph neural network has received significant attention in recent years because of its unique role in mining graph-structure data and its ubiquitous application in various fields, such as social networking and recommendation systems. Although most work focuses on learning low-dimensional node representation in static graphs, the dynamic nature of real-world networks makes temporal graphs more practical and significant. In this paper, we propose a dynamic graph representation learning method based on a temporal graph transformer (TGT), which can efficiently preserve high-order information and temporally evolve structural properties by incorporating an update module, an aggregation module, and a propagation module in a single model. The experimental results on three real-world networks demonstrate that the TGT outperforms state-of-the-art baselines for dynamic link prediction and edge classification tasks in terms of both accuracy and efficiency.

An optimized AdaBoost Multi-class support vector machine for driver behavior monitoring in the advanced driver assistance systems

Advanced Driver Assistance System (ADAS) is a Cyber-Physical System (CPS) application mainly developed for human–machine interaction. We employ the CPS information on ADAS while driving to not only improve the car’s driving conditionbut also alter the driving concepts to improve the functionality and safety of the vehicle. The driver can review the vehicle's feedback information in order to improve the ADAS system's ability to help in driving and completing the process of human–computer interaction. The data obtained during this interaction process are mainly high dimensional and consist of noisy/irrelevant features that pose an important obstacle to our ability to better grasp the car's driving states. In this study, we proposed an AdaBoost Multi-class Support Vector Machine (MSVM) with Cat Mouse Optimizer (CMO) algorithm for ADAS intrusion detection. The evolutionary algorithm is used in this research to tackle the drawbacks related with MSVM such as kernel, poor performance, minimum accuracy, overfitting issues, stability, and so on. Metaheuristics algorithms are an excellent and trustworthy solution for modeling MSVM parameters and producing optimal outcomes. As a result, we used the CMO method to optimize the MSVM parameters.From this, both normal and abnormal behaviors are predicted that affect the driving system.The experimental data is acquired from the power supply voltage data generated by the Jiangxi bus company. Data pre-processing is the major step to clean up, normalize and reshape the data for further processing. The low dimensionality features are extracted and finally, AdaBoostMSVM with CMO algorithm classifies both normal and anomalyactivities of driving vehicles. The results show that, in the majority of cases, the proposed model provides more accurate predictions in terms of accuracy, recall, precision, F-score, post hoc Nemenyi test, and Friedman test.Using performance metrics, the proposed method achieved 91.45 % accuracy, 94.45 % F-score, 93.89 % precision, and 94.90 % recall, outperforming other existing methods.

Incremental Capacity Curve Health-Indicator Extraction Based on Gaussian Filter and Improved Relevance Vector Machine for Lithium–Ion Battery Remaining Useful Life Estimation

Accurate prediction of the remaining useful life (RUL) of lithium–ion batteries is the focus of lithium–ion battery health management. To achieve high–precision RUL estimation of lithium–ion batteries, a novel RUL prediction model is proposed by combining the extraction of health indicators based on incremental capacity curve (IC) and the method of improved adaptive relevance vector machine (RVM). First, the IC curve is extracted based on the charging current and voltage data. To attenuate the noise effects on the IC curve, Gaussian filtering is used and the optimal filtering window is determined to remove the noise interference. Based on this, the peak characteristics of the IC curve are analyzed and four groups of health indicators are extracted, and the strong correlation between health indicators and capacity degradation is determined using Pearson correlation analysis. Then, to optimize the traditional fixed kernel parameter RVM model, an RVM regression model whose kernel parameters are optimized by the Bayesian algorithm is established. Finally, four sets of datasets under CS2 battery in the public dataset of the University of Maryland are carried out for experimental validation. The validation results show that the improved RVM model has better short–term prediction performance and long–term prediction stability, the RUL prediction error is less than 20 cycles, and the mean absolute error is less than 0.02. The performance of the improved RVM model is better than that of the traditional RVM model.

Negative correlation between word-level surprisal and intersubject neural synchronization during narrative listening

Word-predictability measures, such as surprisal, have been used to show that linguistic prediction is an essential neural mechanism for successful comprehension. However, the neural dynamic of this mechanism may differ across individuals listening to the same narrative, revealing possible idiosyncrasies. Therefore, in this study, we investigated the ability of the surprisal measure to address the linguistic prediction in terms of the intersubject phase synchronization (ISPS) among healthy volunteers listening to a narrative during continuous functional Magnetic Resonance Imaging (fMRI) scanning.The data of twenty-seven participants, acquired in a previous study, were re-analyzed to estimate the ISPS associated with an audiobook listening, played forward and backward. Mean ISPS differences between playing conditions were first analyzed across the whole brain. ISPS time-series during the forward condition was explained with both a lexical-only and a semantics-weighted lexical surprisal model of the narrative word series to detect correlations between ISPS and word surprisal values.Compared to the backward condition, mean ISPS was significantly higher during forward condition in a broad network encompassing frontal, temporal, and parietal areas. The lexical-only model disclosed significant negative ISPS-surprisal correlations in the angular gyrus bilaterally, precuneus, left inferior parietal lobule, left middle frontal gyrus, left cerebellum, and left inferior frontal gyrus. The semantics-weighted surprisal model disclosed significant negative ISPS-surprisal correlations in the right angular gyrus, right precuneus, and left inferior frontal gyrus.Besides engaging language-related areas, narrative processing induces significant ISPS levels beyond the language network. The negative ISPS-surprisal correlations observed would signal divergent neural dynamics among individuals, leading to lower group synchronization, when the words to be integrated are characterized by higher surprisal levels. These results provide further support to the use of language models, such as the surprisal, to explain the neural processes of narrative comprehension and additional information into how the human brain exploits predictions during language comprehension.