Past Behavior Research Articles

Deep Learning-Based Freight Recommendation System for Freight Brokerage Platform

Platform-based businesses in the logistics market are evolving under the influence of digital transformation. Transforming the freight market into an environment where various types of freight can be traded across multiple markets and locations. Freight brokerage platforms have revolutionized the trading relationship between freight owners and vehicle owners. However, this type of system has also introduced inefficiencies, such as unestablished contracts, leading to unnecessary costs and delays. To address this issue, a freight recommendation system can assist users in finding what they are looking for while aiming to reduce failed contracts. With current advances in deep learning, complex patterns based on users’ past behaviors and preferences can be learned, enabling more accurate and personalized recommendations. This study proposes a deep learning-based freight recommendation system to provide personalized services and reduce failed contracts on freight brokerage platforms. The system is built by creating a freight transaction dataset, classifying freight categories through natural language processing and text mining techniques, and incorporating externally derived data on transportation distances. The deep learning model is trained using Autoencoder, Word2Vec, and Graph Neural Networks (GNN), with recommendation logic implemented to suggest suitable freight matches for vehicle owners. This system is expected to increase the market efficiency of the freight logistics industry and is a key step toward improving the long-term profit structure.

Structural and Pasting Properties of Lentil Starch: A Comprehensive Review

ABSTRACTLentils are highly nutritious as they are rich in both proteins and starch, making them a crucial component of the human diet. This review article focuses on the morphology, microstructure, and pasting properties of lentil starch (LS). The LS exhibits poor crystallinity due to its high amylose‐to‐amylopectin ratio as reflected in its pasting behavior. The shapes of the LS granule range a wide variety, starting from huge ovals to small rounds, as captured in the scanning electron microscope (SEM). Fourier transform infrared (FTIR) spectroscopy displays the arrangement of starch molecules at the vicinity of the granule surface and detects the presence of additional functional groups in the modified starches. X‐ray diffraction (XRD) demonstrates both the qualitative and quantitative alterations in the crystalline domains of starch granules effectively. Nuclear magnetic resonance (NMR), in particular 13C CP/MAS have successfully examined the structural order of amylolyzed LS concentrations and amylose–lipid complex at the molecular level. This review might be of interest to the professionals involved in food and pharmaceuticals on product development using lentil as one of the ingredients in their formulations.

Improving the Dynamics of an Electrical Drive Using a Modified Controller Structure Accompanied by Delayed Inputs

This paper presents the operation of a modified speed controller with a standard PI/PID structure that includes the preprocessing of the controller’s input signal, focusing on the past behavior of control errors. The modification involves adding a delay line, with the outputs of the individual line segments summed with a weighting method, as detailed in the paper. One of the significant advantages of this method is its use of a standard industrial controller structure, which makes it highly practical and easily implementable in existing systems. By relying on well-established control frameworks, this approach reduces the need for specialized hardware or complex modifications, allowing for smoother integration and lower implementation costs. The delay-based signal shaping shows excellent properties for the electric drive system powered by a hard-switching PWM converter. The set of weighted delays acts as a filter whose parameters are chosen using the quality function to test different configurations for optimal performance. When tested in a speed control system for a Permanent Magnet Synchronous Motor, the modifications improved the control quality index, indicating better performance and efficiency. Importantly, the system allows for reducing or eliminating the gain in the differentiating part of the controller, which decreases motor current chattering and noise. This paper includes an experimental verification of the proposed solution in a laboratory setting under semi-industrial conditions.

Machine Learning Insights into the Last 400 Years of Etna Lateral Eruptions from Historical Volcanological Data

Volcanic hazard assessment is generally based on past eruptive behavior, assuming that previous activity is representative of future activity. Hazard assessment can be supported by Artificial Intelligence (AI) techniques, such as machine learning, which are used for data exploration to identify features of interest in the data. Here, we applied a machine learning technique to automate the analysis of these datasets, handling intricate patterns that are not easily captured by explicit commands. Using the k-means clustering algorithm, we classified effusive eruptions of Mount Etna over the past 400 years based on key parameters, including lava volume, Mean Output Rate (MOR), and eruption duration. Our analysis identified six distinct eruption clusters, each characterized by unique eruption dynamics. Furthermore, spatial analysis revealed significant sectoral variations in eruption activity across Etna’s flanks. These findings, derived through unsupervised learning, offer new insights into Etna’s eruptive behavior and contribute to the development of hazard maps that are essential for long-term spatial planning and risk mitigation.

Understanding the time-dependent rheological behavior of seawater mixed cement paste with fly ash

Due to the relative scarcity of freshwater resources in coastal regions, the use of seawater in concrete construction has great potential due to its benefits in cost and resource. To further advance the application of seawater concrete, a deeper understanding of its rheological properties is essential. This study investigates the effects of fly ash on the time-dependent rheological behavior of seawater cementitious paste, such as yield stress, plastic viscosity, and structural build-up rate. The underlying mechanisms are analyzed using the theories of water film thickness (WFT), ion concentration, and hydration heat. The research findings confirm that the rheological parameters of seawater paste are generally higher than those of deionized water paste, regardless of the cementitious compositions. As fly ash content increases, the plastic viscosity of seawater paste increase, while the fluidity and dynamic yield stress decreases. Further analysis reveals that the decrease in the yield stress with fly ash content is well related to the increase in the WFT, but it cannot sufficiently explain the change of yield stress over time. Instead, the amount of hydration products in seawater paste shows a linear increasing relationship with the dynamic yield stress at 65 min. By contrast, the plastic viscosity can be related to the ion concentration in the interstitial solution, wherein an increase in the concentration of Ca2+ corresponds to an increase in the plastic viscosity. Moreover, the rheological parameters increase over time, with the growth rates between 5 and 35 minutes being higher than those between 35 and 65 minutes, possibly due to the rapid early hydration of the binder materials. This study offers a fundamental theoretical support for the use of seawater in various concrete applications.

Micromechanics and microstructure based machine learning approach: Unveiling the role of porosity and hydrated phases on the tensile behaviour of cement pastes

Micromechanics and microstructure based machine learning approach: Unveiling the role of porosity and hydrated phases on the tensile behaviour of cement pastes

A Solution to Reduce the Impact of Patients’ No-Show Behavior on Hospital Operating Costs: Artificial Intelligence-Based Appointment System

Background: Patient no-show behavior is a critical factor complicating hospital resource optimization and causing waste. The inefficiency caused by patients’ no-shows and the resulting increased operating costs negatively affect the hospitals’ financial structure and service quality. For this reason, health managers must make accurate predictions about whether patients will attend an appointment and plan the appointment system within the framework of these predictions. This research aims to optimize the hospital appointment system by making accurate predictions regarding the no-show behavior of the patients, based on recorded data. Methods: An artificial intelligence-based appointment system has been developed according to patients’ demographics and past behavior patterns. The forecast results and realized performance results were compared. The artificial intelligence we have developed continuously improves appointment assignments by learning from past and current data. Results: According to the findings, the artificial intelligence-based appointment system increased the rate of patients attending appointments by 10% per month. Likewise, the hospital capacity utilization rate increased by 6%. Conclusions: Findings from the study confirmed that no-show risks could be managed in the appointment process through artificial intelligence. This artificial intelligence-based design for appointment systems significantly decreases hospital costs and improves service quality performance.

Predicting food consumption using contextual factors: An application of machine learning models

Abstract Background Improving diet quality relies on making manageable adjustments to eating behaviours. Personalised nutrition interventions hold promise for modifying behaviour. Machine learning (ML) offers a novel approach to examining dietary behaviours in personalised nutrition by leveraging data on past behaviours and environmental contexts. This study aims to investigate whether contextual factors at eating occasions (EO) can predict food consumption to enhance diet quality. Methods Cross sectional data from the Measuring Eating in Everyday Life Study (MEALS) were analysed (n = 675, 18-35y). A smartphone food diary app recorded dietary intakes at EO for 3-4 non-consecutive days, also capturing social-environmental (e.g., activity) and physical-environmental factors (e.g., consumption location). Participant characteristics were collected via an online survey. Food groups intake (servings per EO) followed Australian Dietary Guidelines. This study benchmarked two established models, gradient boost decision tree and random forest, which have previously shown high performance in similar tasks. Performance was evaluated using 10-fold cross-validation, measuring mean absolute error (MEA), root mean square error (RMSE), and R squared. Feature importance analysis identified key variables for predicting food consumption. Results ML predicts most food groups at EO using contextual factors, with slight differences between actual and predicted consumption (<1 serving per EO). For fruits, dairy, and meat, MEA values were 0.35, 0.34, and 0.56 servings, respectively (RMSE values: 0.61, 0.50, and 0.80 servings). Self-efficacy, age and consumption location were influential in most ML models. Conclusions ML offers insights into contextual factors and food consumption, suggesting directions for precision nutrition interventions. Future research should identify positive influences of contextual factors on dietary behaviours and incorporate these insights into interventions. Key messages • Machine learning can effectively predict food consumption based on contextual factors at eating occasions. • Understanding the influence of contextual factors such as consumption location on food consumption can inform the development of precision nutrition interventions aimed at improving diet quality.

Links between adolescent binge drinking and midlife alcohol use behaviors by age, sex, and race/ethnicity.

Alcohol use is increasing among adults in midlife (i.e., ages 35-60), but few studies examine specific alcohol use behaviors in this age group. We examined measures of typical drinks, maximum drinks, binge drinking, and high-intensity drinking by age, sex, and race/ethnicity among midlife adults, as well as the prospective association between age 18 binge drinking and midlife behaviors. Data from 5180 respondents participating in the national Monitoring the Future Panel study who were aged 35-60 in 2022 (followed since they were in 12th grade in 1980-2005) were used to estimate past 30-day midlife drinking behaviors (i.e., typical drinks, maximum drinks, binge, and high-intensity drinking) by age group, sex, and race/ethnicity. Associations between age 18 binge drinking status and midlife drinking outcomes were examined, as well as moderation by sociodemographic characteristics. Across ages 35-60, the mean typical number of drinks on drinking days within the past month ranged from 1.4 to 1.8; the mean maximum drinks ranged from 2.3 to 3.2. Past-month binge and high-intensity drinking prevalence ranged from 19.1% to 31.2% and 3.6% to 8.1%, respectively. Estimates of drinking behaviors were generally higher among respondents aged 35-40 (vs. older age groups), males (vs. females), those identifying as White (vs. other racial/ethnic groups), and those who reported age 18 binge drinking (vs. not). Adolescent binge drinking was a stronger predictor of high-intensity drinking among females than males and of typical and maximum drinks among older (age 60) than younger (age 35) respondents. Binge and high-intensity drinking were reported by a meaningful percentage of the US midlife adults. Binge drinking in adolescence was a predictor of subsequent alcohol-related risks. These long-term connections were especially strong among females. Age 18 binge drinking was a stronger predictor of high-intensity drinking at age 60 than earlier in midlife, underscoring that adolescent binge drinking is a key indicator of risk across the lifespan.

Examining the effect of post-depositional processes on the preservation and identification of stone tool residues from temperate environments: An experimental approach.

Studying taphonomy is crucial for understanding how post-depositional processes impact archaeological remains. This knowledge is pivotal for accurately interpreting the archaeological record. Although taphonomy has a long tradition in archaeology, it is less developed in the analysis of stone tool residues compared to other subdisciplines. To address this gap, our study aims to further develop our understanding of the preservation potential of stone tool residues in temperate environments through actualist experiments. To achieve this, we develop a multidimensional experimental program that features the first biweekly monitoring of weathering processes on residues over a one-year cycle, aiming to understand the short-term effects of weathering immediately after tool discard. Additionally, the program involves the study of longer-term burial and weathering visual effects on different residue types within various previously unexplored depositional environments. This approach allows us to observe the visual effects of both weathering and burial processes and to improve our understanding of the different mechanisms involved in the diagenesis of stone tool residues. While known factors such as microbial activity and soil acidity play a primary role in residue decay, specific stone tool-related factors also prove important, underscoring the need to develop further a specific branch of taphonomy related to stone tool residues. Moreover, our results show that certain residue types may survive within these environments that are often considered as being hostile. A residue analysis of stone tools from temperate contexts may thus contribute unique data that can improve our understanding of past human behaviour. Future research with more diverse residue types and depositional conditions will permit further refinement of our understanding of how taphonomy affects residue preservation and enhance the reliability of residue identifications. As such, stone tool residue analysis will become firmly rooted within broader functional approaches to address how humans use stone tools and how this affects stone tool variability.

The Time of the Stones: A Call for Palimpsest Dissection to Explore Lithic Record Formation Processes

The dissection of archaeological palimpsests has become a crucial process for achieving a diachronic understanding of the history of human groups. However, its widespread application to archaeological deposits has been hampered by both methodological and theoretical limitations, as well as by the inherent characteristics of the deposits. This paper explores whether overcoming these barriers, both methodological and theoretical, truly represents a significant shift in understanding past human behaviour, thereby motivating the pursuit of shorter timescales. To this end, we have analysed the lithic assemblages of Unit Xb from the Neanderthal site of El Salt (Alcoi, Iberian Peninsula) focusing on lithic attributes and raw material analyses, enabling the definition of raw material units and refitting sets. Considering these variables, we have applied archaeostratigraphic and spatial analyses in order to generate units of analysis whose content is compared to that of the entire unit. The defined archaeostratigraphic units display different spatial distributions and lithic composition. Some of them are attached to certain hearths and composed of refitted sets, while other units are related to areas without combustion evidence and integrated with bigger and heavier single products. Through this approach, here, we show that reducing the spatiotemporal scale of the record helps to unravel behavioural variability, reducing interpretative errors implicit in the assemblage-as-a-whole approach. This highlights the role of temporal resolution in reconstructing site formation processes and challenges research perspectives that assert the unnecessary or impossible nature of palimpsest dissection.

Evaluation of the Multiple Regression Analysis Algorithm on Stock Market Prediction

Financial time series is one of the most challenging applications of modern time series forecasting. The financial time series is closely related to noise, non-stationary, and deterministic chaos. The characteristics suggest that no complete information can be obtained from the past behavior of financial markets to fully capture the dependency between future prices and that of the past. The data collection method was collected from the Stock Market Online Application "MetaTrader version 4" type "Daily" with a time range from "03/09/2001 to 25/07/2012", as many as 2052 data", with the attributes "Date, Open, High, Low, Close, Volume" with the main attribute "Close" using the Support vector machine algorithm, artificial neural network, and multiple linear regression. The conclusion of the value that is close to the series value is the value by testing on the support vector machine algorithm, with the parameter for the RMSE value that is close to the "0" value obtained from the measurement results on the SVM algorithm on the RBF kernel (radial base function) with a value of "gamma" γ = 100 with the value of RMSE = 0.000, and SE = 0.000. with prediction accuracy error = 0.976

Social trust, past behavior, and willingness to pay for environmental protection: evidence from China

Social trust, past behavior, and willingness to pay for environmental protection: evidence from China

The Effects of Ester and Ether Polycarboxylate Superplasticizers on the Fluidity and Setting Behavior of Alkali-Activated Slag Paste.

This study aims to investigate the comparative performance of ester- and ether-based polycarboxylate superplasticizers in maintaining the fluidity and controlling the setting time of alkali-activated slag (AAS) paste. The experiments employed rheological tests, mini-slump tests, ultrasonic pulse velocity (UPV) measurements, and gel permeation chromatography (GPC) analysis. The results indicate that ether-based superplasticizers maintain fluidity approximately 25% longer than their ester-based counterparts and extend the setting time by about 30%. The enhanced performance of ether-based superplasticizers is attributed to their superior molecular stability in highly alkaline environments, which mitigates early polymer degradation. Additionally, the Na2O/SiO2 ratio was maintained at 1:1 throughout the experiments to ensure consistency in the activation process. The relationship between fluidity loss and the onset of setting occurs more rapidly in AAS paste than in conventional cement-based systems. These findings provide valuable insights for the development of environmentally friendly construction materials by optimizing the use of superplasticizers in alkali-activated systems.

A closed-loop recycling of wastewater derived from aqueous carbonation of basic oxygen furnace slag in cement paste production

Aqueous carbonation (AC) treatment is a promising method for enhancing the cementitious activity of Ca- and Mg-rich solid wastes, such as basic oxygen furnace slag (BOFS), while also reducing carbon emissions. However, the carbonated filtrate (CF) solution generated during the AC process poses significant environmental challenges and limits its large-scale application. This paper, therefore, explores the feasibility of recycling CF in cement paste production as a strategy for managing AC wastewater. The study examines the impact of CF on the physico-mechanical properties, hydration behavior and microstructure of cement pastes (pure and blended with either 10% as-received or carbonated BOFS), compared to those prepared with tap water (TW) and carbonated water (CW). The results indicate that carbonated solutions (CF and CW) promote the hydration of aluminate phase in cement, with a more pronounced effect observed for CW. The solid suspensions in CF, particularly nesquehonite, restrict the growth space for calcium silicate hydrates (C-S-H) in the paste matrix, resulting in the formation of foil-like Type II C-S-H and lowering compressive strength. However, the additional nucleation sites provided by calcite crystals in carbonated BOFS (C-BOFS) accelerate cement hydration in CF-based pastes and mitigate strength loss by promoting the formation of more fibrillary C-S-H. Furthermore, the addition of a superplasticizer reduces interparticle forces in the C-BOFS-CF paste, further enhancing strength development and achieving a 28-day strength comparable to that of the control sample (OPC-TW paste).

Longitudinal single-subject neuroimaging study reveals effects of daily environmental, physiological, and lifestyle factors on functional brain connectivity.

Our behavior and mental states are constantly shaped by our environment and experiences. However, little is known about the response of brain functional connectivity to environmental, physiological, and behavioral changes on different timescales, from days to months. This gives rise to an urgent need for longitudinal studies that collect high-frequency data. To this end, for a single subject, we collected 133 days of behavioral data with smartphones and wearables and performed 30 functional magnetic resonance imaging (fMRI) scans measuring attention, memory, resting state, and the effects of naturalistic stimuli. We find traces of past behavior and physiology in brain connectivity that extend up as far as 15 days. While sleep and physical activity relate to brain connectivity during cognitively demanding tasks, heart rate variability and respiration rate are more relevant for resting-state connectivity and movie-watching. This unique data set is openly accessible, offering an exceptional opportunity for further discoveries. Our results demonstrate that we should not study brain connectivity in isolation, but rather acknowledge its interdependence with the dynamics of the environment, changes in lifestyle, and short-term fluctuations such as transient illnesses or restless sleep. These results reflect a prolonged and sustained relationship between external factors and neural processes. Overall, precision mapping designs such as the one employed here can help to better understand intraindividual variability, which may explain some of the observed heterogeneity in fMRI findings. The integration of brain connectivity, physiology data and environmental cues will propel future environmental neuroscience research and support precision healthcare.

Forecasting the Volatility of Tuna Fish Prices in North Sumatra using the ARCH Method in the Period January - April 2024

Tuna (Euthynnus affinis) is one of the most important fisheries commodities in Indonesia with significant economic value, especially in its contribution to fisheries export revenue. However, the price of tuna experiences significant fluctuations that can affect local and national economic stability. This study analyzes the daily price fluctuations of tuna in the North Sumatra market from January 1, 2024 to April 29, 2024 using a time series analysis approach. Daily price data were collected and analyzed to identify existing price patterns and volatility. The Autoregressive Conditional Heteroskedasticity (ARCH) model was selected to address the heteroscedasticity in the data, which suggests that the volatility of tuna prices can be well predicted based on past price behavior. The analysis steps include identifying the optimal ARCH model using the Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF), as well as testing parameter significance and normality assumptions to validate the model fit. The results show that the ARMA (1,0,0) model is the optimal one to model the price volatility of yellow tuna with the MAPE obtained of 2.382. compared to the ARMA-ARCH method with the MAPE value obtained of 2,747. Because it still contains heteroskedasticity effects, even though the results are good, the prediction results do not closely match the original data. The model is effective in improving price forecasting accuracy, which is important to support decision-making in risk management and economic planning in the fisheries sector. The findings contribute to understanding the dynamics of the yellowtail market and optimizing strategies for fisheries management.

A Conceptual Framework of the Retirement Savings Behavior among Civil Servants in Malaysia

The feasibility of maintaining a comfortable standard of living for civil servants in Malaysia is frequently questioned due to their reliance on pensions as the primary source of retirement funds, which may not suffice to cover the rising retirement costs. To address this issue, civil servants could consider accumulating savings during their working years instead of solely depending on pension disbursements. This academic discourse examines the effect of the independent variables of attitudes towards retirement savings (financial risk tolerance, past behaviours, and subjective norms as psychological elements) and financial considerations (tax incentives) on retirement savings behaviour. Additionally, the research also explores the moderating role of perceived government policy and perceived behavioural control with its antecedents, namely financial literacy, self-control between the independent variables, and retirement savings behaviour among civil servants in Malaysia. Drawing from the extended interactive theory of planned behaviour, amalgamated theories comprising the interactive theory of planned behaviour, rationale choice theory, and the behavioural economic model and existing literature, this article introduces a conceptual framework detailing the determinants influencing the RSB of civil servants in Malaysia. The proposed framework has the potential to benefit various stakeholders, particularly civil servants seeking to prepare adequately for their retirement years.

Rheology of flexible fiber-reinforced cement pastes: Maximum packing fraction determination and structural build-up analysis

The maximum packing fraction (φfm) of flexible fibers is an essential parameter for understanding the rheological behavior of flexible fiber-reinforced cement paste (FFRCP). However, direct measurement of φfm of flexible fibers is still lacking. In this study, a shear rheology-based method for direct measurement of φfm was proposed and the assumption of fiber conformation under shear was verified by micro-CT. Based on this, a yield stress model for FFRCP was constructed to explain the entanglement and friction effects in the fiber network. Finally, static yield stress tests and small amplitude oscillatory shear (SAOS) tests were carried out to explore the structural build-up of FFRCP. It was found that the proposed method enables direct determination of φfm through only a few viscosity-fiber content data for a given FFRCP. Furthermore, the proposed model can describe the static yield stress of FFRCP well. Finally, the relative structural build-up rate of FFRCP follows a similar trend as the relative yield stress, with a critical relative fiber volume fraction (0.299) as the boundary. Subsequently, the relative structural build-up gradually deviates from the relative yield stress due to the limiting effect of the fibers.

Long-term tracking of social structure in groups of rats

Rodents serve as an important model for examining both individual and collective behavior. Dominance within rodent social structures can determine access to critical resources, such as food and mating opportunities. Yet, many aspects of the intricate interplay between individual behaviors and the resulting group social hierarchy, especially its evolution over time, remain unexplored. In this study, we utilized an automated tracking system that continuously monitored groups of male rats for over 250 days to enable an in-depth analysis of individual behavior and the overarching group dynamic. We describe the evolution of social structures within a group and additionally investigate how past behaviors influence the emergence of new social hierarchies when group composition and experimental area changes. Notably, we find that conventional individual and pairwise tests exhibit a weak correlation with group behavior, highlighting their limited accuracy in predicting behavioral outcomes in a collective context. These results emphasize the context-dependence of social behavior as an emergent property of interactions within a group and highlight the need to measure and quantify social behavior in more naturalistic environments.