Prediction Of Behavior Research Articles

Investigation of a constitutive law for the prediction of the mechanical behavior of WEEE recycled polymer blends

This research focuses on a mechanical study of an acrylonitrile–butadiene–styrene (ABS)/ polycarbonate (PC) blend totally derived from Waste Electrical and Electronic Equipment (WEEE) recycling. First, an experimental work was developed in laboratory for the preparation of different mixtures of ABS/PC blend. Then, mechanical tensile tests were performed on the injected specimens and the stress/strain experimental data were gathered to be used in the modelling part. In order to enable the prediction of the mechanical response of the blend, G’Sell and Jonas constitutive law was considered for this purpose. An optimization method based on the Generalized Reduced Gradient (GRG) nonlinear algorithm was developed to identify the input parameters governing the mechanical model. In addition, an uncertainty parametric study was assessed to qualitatively and quantitatively evaluate the constitutive law sensitivity versus the parameter uncertainty. Monte Carlo simulations were performed and the convergence of the numerical model was proved in terms of means and standard deviation statistical data. The results showed an excellent agreement between the numerical approach and the experiments. Besides, it was highlighted the crucial role of coupling uncertainty parametric study with modelling for accurately describing the mechanical behavior of the blend.

Prediction of electrohydrodynamic printing behavior using machine learning approaches

Prediction of electrohydrodynamic printing behavior using machine learning approaches

Effect of moisture change on water retention behavior of unsaturated silty soil under loading–unloading conditions

Earthen embankments either natural or constructed artificially often comprise of unsaturated soils being considered stronger in terms of compressibility and permeability. However, the internal nomenclature of unsaturated soils due to the presence of air, water, and soil particles makes it more complex while such soils interact with moisture under the circumstances of applied stress history during the earthen structure’s life span. To investigate this behavior, this study is designed to understand the soil–water interaction and quantify the retention behavior during loading and unloading conditions. To serve this idea, custom-designed static compaction tests were carried out under un-drained water and drained air conditions at the applied stress history. The results show application of loading and unloading cycles impact water retention behavior of soil with varying soil water contents. During the initial stages of the loading process, suction increases with decreasing void ratio due to the heterogeneous distribution of water in the soil. However, there is a unique increasing trend in suction at the reloading or wetting phases of the water retention curve for all moisture contents. To examine the impact on the void ratio, the experimental data have been compared with the selected model incorporating suction, void ratio, and degree of saturation for prediction of soil water retention behaviors. The model prediction deviates from the experimental data and shifts away from the model prediction indicating that the loading–unloading sequence coupled with the variation in moisture does affect the soil behavior.

Salmon Consumption Behavior Prediction Based on Bayesian Optimization and Explainable Artificial Intelligence

Salmon Consumption Behavior Prediction Based on Bayesian Optimization and Explainable Artificial Intelligence

Tourists Behavior Prediction through Online Reviews by Analyzing their Sentiments using Machine Learning Approach

Sentiment Analysis is that part of research area where different people opinions or sentiments are extracted in form of textual data from various websites. In this paper sentiment analysis has been described along with machine learning techniques on tourist’s reviews to see their behavior towards various tourist places, hotels and other services provided by tourism industry. Emotions in the form of tourist’s reviews extracted are interpreted and classified by preprocessing of data and further feature extraction is done through machine learning highly efficient technique called deep learning. In this paper, the proposed idea has been given to use deep learning methods like CNN, RNN and LSTM rather than using machine learning classical algorithms like SVM, Naive Bayes, KNN, RF etc. Also, comparison of various machine learning and deep learning techniques working on tourist sentiments has been done here in this paper to show that deep learning techniques analyze and classify emotions and polarity with deep layers efficiently where on the other hand classical algorithms of machine learning give results not better than deep learning techniques. In this way sentiment analysis has been done and the proposed idea of this research paper is change in the machine learning techniques or methods from classical algorithms to neural network deep learning methods which in future definitely will give better results to analyze deeply the sentiments of tourists to find out the liking and disliking of various tourist places, hotels and related tourism services that will help tourism business industry to work on the gap in existing services provided by them and system can become more efficient in future. Such improved tourism system will give benefits to tourists or users in terms of better services and undoubtedly it will help tourism industry to enhance business in future. Keywords—sentiment analysis, machine learning, deep learning, tourist reviews.

Modeling and Prediction of Demand Response Based on Deep Quantum Neural Networks

Demand Response (DR) plays a crucial role in modern power networks, addressing the challenges posed by increasing renewable energy integration, grid modernization, and sustainability goals. By modifying electricity consumption patterns in response to signals such as price fluctuations or grid conditions, DR helps balance supply and demand on the grid, reduce peak demand, alleviate grid congestion, and integrate renewable energy resources more effectively. However, effective DR strategies require accurate modeling and prediction of DR behavior. In this research, a novel modeling and prediction strategy for DR that integrates deep learning and quantum computing principles is proposed. The approach involves two main phases: preprocessing and prediction. During preprocessing, input data undergo normalization using an improved Z-score technique. Subsequently, the normalized data are processed by the Modified Deep Quantum Neural Network (MDQNN) model during the prediction phase. MDQNN, an enhanced version of Deep Quantum Neural Networks (DQNN), employs angle encoding to enhance prediction accuracy by effectively identifying patterns. The efficacy of this strategy is demonstrated through comprehensive analyzes, highlighting its potential to enhance DR prediction accuracy and contribute to the advancement of power network optimization and sustainability objectives.

User Profile Construction Based on High-Dimensional Features Extracted by Stacking Ensemble Learning

Online social networks, as platforms for personal expression, have evolved into complex networks integrating political and social dimensions. This evolution has shifted the focus of network governance from addressing hacking activities to mitigating unpredictable social behaviors, such as the malicious manipulation of public opinion, the doxing of ordinary users, and cyberbullying. However, the sparsity of data and the concealed nature of user behavior pose significant challenges to existing network reconnaissance technologies. In this study, we focus on constructing user profiles on online social network platforms by extracting features to build deep user profiles based on behavioral patterns. Drawing inspiration from the 5Cs principle of credit evaluation, we refine it into a 3Cs principle tailored for user profiling on social network platforms and associate it with user behavioral patterns. To further analyze user behavior, a high-dimensional feature extraction method is proposed using an improved stacking ensemble learning model. Based on experimental data analysis, the most suitable base algorithms for high-dimensional feature extraction are identified. Experimental results demonstrate that the integration of high-dimensional features improved the behavior prediction accuracy of the profiling model by 9.26% on balanced datasets and enhanced the AUC (area under the curve) metric by 3.69% on imbalanced datasets. The proposed method effectively increases the depth and generalization performance of user profiling.

Warped matrix-variate Gaussian processes with structured kernels for multi-step-ahead driving behaviour prediction

Warped matrix-variate Gaussian processes with structured kernels for multi-step-ahead driving behaviour prediction

Social Media's Influence on Business Decision-Making: A Study of Communication Networks in Management Practices

The investigation reveals how business leaders use social media tools to make decisions while managing communication within their teams. This research analyzes how companies use social media to support their business strategies while studying its effects on important decisions and interactions between stakeholders. This study analyzes business decision making with support vector machines, decision trees, neural networks, and random forests to reveal patterns in social media data effectiveness. Analysis using neural networks shows a notable improvement in decision efficiency through social media data which achieves 85% accuracy rates. Random forests outperformed other algorithms by 10% when it came to customer behavior prediction while decision trees improved market response by 15%. Businesses that use social media for immediate customer interaction and team innovation adapt better to fast-changing markets. This study helps businesses better understand how social media works in today's market by providing tools to improve their communication methods and business decision making.

Classification Framework for Assessing Anthropogenic Sedimentary Facies

As the mass of human-made materials now surpasses that of Earth’s total dry biomass, there is a critical need for sedimentologists to account for anthropogenic materials when analyzing depositional environments. To address this, a classification scheme is presented that extends traditional sedimentological models to encompass the diversity of modern sediments and their complex dynamics. Through relying on established sedimentological principles, the framework incorporates bed-scale, grain-scale, and sedimentary structure descriptors, as well as a methodology for describing the composition of a deposit and flexible nomenclature. It is designed to be integrative and adaptable, permitting the incorporation of additional descriptions as necessary, and is applicable across depositional settings that are dominated by either natural or anthropogenic processes. The scheme offers a practical, systematic approach to categorize and analyze the textures and structures of anthropogenic sediments, facilitating the reconstruction of modern and geologically recent environments. This unifying starting point enables more detailed predictions of material behavior and their environmental impacts, with implications for recycling, reuse, and management strategies. Furthermore, standardized nomenclature will enhance the capacity for data comparability across field sites, facilitating further understanding of our environment. Applications of this classification scheme include many interdisciplinary possibilities, overlapping with archeology, environmental monitoring, and engineering. By adopting this classification, sedimentologists can forge a deeper understanding of the stratigraphic record of the Anthropocene, contribute to developing more comprehensive strategies to manage Earth’s changing landscapes, and better understand our future geological record.

Typhoon Eye-Induced Misalignment Effects on the Serviceability of Floating Offshore Wind Turbines: Insights Typhoon SOULIK

The northern Taiwan Strait, characterized by deep waters and high wind energy density, presents significant potential for developing floating offshore wind turbines (FOWTs). However, the region is prone to typhoons, with substantial variations in wind speed and direction during typhoon eye passages, posing challenges to FOWT safety and performance. This study investigates the serviceability of a 10 MW FOWT installed offshore of Hsinchu under typical wind and wave conditions during the eye of Typhoon SOULIK. Wind and wave data were sourced from the ERA5 reanalysis database. Simulations were conducted using OrcaFlex 11.4c, which enables fully coupled dynamic analysis of the entire FOWT system, including the mooring system, platform, tower, turbine, and nacelle, facilitating accurate predictions of system behavior in complex offshore environments. This study evaluated scenarios of maximum wind speed, significant wave height, wind–wave misalignment, and minimum wind speed during typhoon eye passage, considering both idle and power production modes in accordance with IEC TS 61400-3-2 requirements. The results indicate that platform yaw motion exceeds IEC limits during typhoon events, particularly in power production mode. This highlights the need for reducing platform motion. It is recommended to further develop control strategies or implement an active control system for the platform to ensure operational reliability. This research provides critical insights into FOWT design and operational challenges in typhoon-prone regions.

Nighttime driver behavior prediction using taillight signal recognition via CNN-SVM classifier

Nighttime driver behavior prediction using taillight signal recognition via CNN-SVM classifier

A Freight Truck Stopping Behavior Prediction Approach Based on Trajectory Dataset

A Freight Truck Stopping Behavior Prediction Approach Based on Trajectory Dataset

Machine learning algorithms based approach on prediction of mechanical behaviour of PLA/brass composites manufactured by additive manufacturing

Machine learning algorithms based approach on prediction of mechanical behaviour of PLA/brass composites manufactured by additive manufacturing

Simulation of Pedestrian Behaviour in Traffic Situations Using Risk-Based A* Pathfinding

Abstract Fatally injured vulnerable road users, especially pedestrians who collided with motorised vehicles, account for 31% of all recorded fatalities in urban traffic in the EU. Autonomous vehicles will improve this situation in the future, reducing the impact of the human factor in critical traffic situations. The development of autonomous driving functions requires simulation environments to train certain behaviours. Consequently, these simulations need well represented vulnerable road users. In this paper, an approach for accurate prediction of pedestrian behaviour at street crossings is presented. The suggested solution involves an agent-based model working with A* pathfinding and risk-based areas, validated by a drone dataset on German road crossings.

Prediction of temperature-dependent mechanical behavior of metals based on thermodynamic strength and deformation theory

Prediction of temperature-dependent mechanical behavior of metals based on thermodynamic strength and deformation theory

Fast prediction of curing residual stress in polymer‐matrix composites by a deep learning method

AbstractCuring residual stress (CRS) is common in polymer‐matrix composites due to the anisotropic properties of materials. Finite element method (FEM), the most extensively used approach for curing behavior prediction, is usually complicated and time‐consuming. To achieve a fast prediction of process‐induced stresses, a convolutional neural network (CNN) is established based on the FEM. Firstly, a fully coupled methodology is built and validated through distortions of experimentally manufactured laminates. Then, it is applied to generate models with different stacking layers, and the residual stress is computed and serves as the dataset of the deep learning model. Finally, the construction and hyperparameters are determined, and the good generalization performance proves the high accuracy of the current model. Besides, the CNN method (<1 s) greatly reduces the computational time compared with the FEM (>14 min). The supervised machine learning method shows great potential in promoting efficiency in stacking sequence designing and optimization of composites.Highlights A fully coupled model was built to predict the curing behavior of composites. The numerical model was validated by the deformation of unsymmetrical composites. A FEM‐CNN method was proposed for the fast prediction of curing residual stress. Compared with FEM, this machine learning method is accurate and efficient.

Learning behaviour prediction and multi-task recommendation based on a knowledge graph in MOOCs

ABSTRACT One challenging issue in improving the teaching and learning methods in MOOCs is to construct potential knowledge graphs from massive learning resources. Therefore, this study proposes knowledge graphs driving online learning behaviour prediction and multi-learning task recommendation in MOOCs. Based on the knowledge graphs supported by multi-entities and features, the authors designed a novel deep learning model to fully calculate and optimise iterative learning processes, explore key semantics and potential values of learning behaviours, integrate multi-task items and flexibly analyse learners’ multi-entities and related features. Assisted by knowledge concept semantics and the formation of knowledge graphs, multi-entities of learning behaviours are fused and associated, which might be the leading trend of knowledge graphs. Sufficient experiments have proved that the whole work might ensure learning behaviour prediction and multi-task selection that can enable the knowledge graph to improve learning behaviours in MOOCs.

Optimizing Learning Path Design in Mobile Learning Platforms for Online Courses

With the rapid advancement of information technology, online education, particularly vocational education, has become a vital avenue for enhancing skills and knowledge. Vocational education necessitates flexible and personalized learning path design to accommodate the diverse needs and behaviors of learners. Mobile learning platforms, as a pivotal form of modern online education, provide learners with the convenience of accessing educational resources anytime and anywhere. However, existing methods for optimizing learning paths exhibit notable limitations, primarily in accurately capturing learners’ dynamic behaviors and in providing personalized and intelligent path design. Therefore, how to optimize learning paths based on learners’ dynamic behavior data has become a research hotspot in academia and educational practice. At present, many studies focus on matching analysis based on students’ static characteristics with course content but overlook learners’ behavioral changes and dynamic needs during the learning process. Traditional recommendation algorithms and rule-based path design methods are difficult to cope with complex learning behaviors and diverse learner needs. This study addresses these limitations by proposing an optimization model for mobile learning path design based on multi-view prediction of dynamic student behaviors. The model extracts mobile interaction features from student groups, constructs a multiple mobile behavior collaborative encoder, and employs multiple task label prediction techniques to achieve personalized and intelligent optimization of learning paths. The results demonstrate that this approach significantly enhances the learning efficiency and experience of learners, offering novel insights and technological support for the path design of mobile learning platforms.

A fishing vessel operational behaviour identification method based on 1D CNN-LSTM

Abstract The identification of fishing vessel operations holds significant importance in addressing fishing industry issues, such as overfishing and illegal, unreported and unregulated fishing (IUUF). Many countries utilise data from vessel monitoring systems (VMSs) or automatic identification systems (AISs) to monitor fishing activities. These data include vessel trajectories, headings and speeds, among others. We aimed to analyse the fishing behaviours of three types of fishing gear used by vessels (trawl, purse seine and gill net) and identify the types of gear employed by the vessels. Therefore, a 1D CNN-LSTM fishing vessel operational behaviour prediction model was proposed by combining a one-dimensional convolutional (1D CNN) neural network and a long short-term memory (LSTM) neural network. The model utilises 1D CNN to extract local features from fishing vessel trajectories and employs LSTM to capture the time series information in the data, eventually classifying fishing gears. The results show that the proposed model achieves a classification accuracy of 92% in categorising fishing vessel operational trajectories. This study significantly contributes to preventing IUUF, curtailing overfishing, and enhancing fisheries management strategies.