Search

Understanding clinical features and risk factors associated with COVID-19 mortality is needed to early identify critically ill patients, initiate treatments and prevent mortality. A retrospective study on COVID-19 patients referred to a tertiary hospital in Iran between March and November 2020 was conducted. COVID-19-related mortality and its association with clinical features including headache, chest pain, symptoms on computerized tomography (CT), hospitalization, time to infection, history of neurological disorders, having a single or multiple risk factors, fever, myalgia, dizziness, seizure, abdominal pain, nausea, vomiting, diarrhoea and anorexia were investigated. Based on the investigation outcome, decision tree and dimension reduction algorithms were used to identify the aforementioned risk factors. Of the 3008 patients (mean age 59.3 ± 18.7 years, 44% women) with COVID-19, 373 died. There was a significant association between COVID-19 mortality and old age, headache, chest pain, low respiratory rate, oxygen saturation

This work shows that fillers - short utterances like “ehm” and “uhm” - allow one to predict whether someone is above median along the Big-Five personality traits. The experiments have been performed over a corpus of 2,988 fillers uttered by 120 different speakers in spontaneous conversations. The results show that the prediction accuracies range between 74% and 82% depending on the particular trait. The proposed approach includes a feature selection step - based on Quantum Evolutionary Algorithms - that has been used to detect the personality markers, i.e., the subset of the features that better account for the prediction outcomes and, indirectly, for the personality of the speakers. The results show that only a relatively few features tend to be consistently selected, thus acting as reliable personality markers.

Introduction: Externalities from transportation, and in particular exposure to vehicle emissions have been considered a possible cause of several negative health outcomes including mortality. However, the existing findings are too inconsistent to drive a well-founded exposure-response function to be fully exploited to curb the negative impacts of transportation systems on public health. In this study, we investigate the association between exposure to air pollution and mortality. We then evaluate how using different air quality methods may result in detecting different health outcomes. Methods: We conduct an analysis of reviewing a representative sample of main published studies that specifically focused on the association between vehicle air pollution and mortality. Results: Our study finds that vehicle air pollution may increase the risk of mortality through a slightly high association. Most importantly, the risk of overall mortality increases by 5% per 10 µg/m3 increase in NO2 concentration, 2% per unit of traffic intensity on the road, and 7% per unit of distance closer to the road. Conclusion: The findings imply the role of exposure to vehicle emissions in increasing the risk of mortality. The method used to detect the health outcomes can alter the health finding from positive to null or vice versa and even extensively affect the analysis outcomes. The results suggest the need for establishing indicators to benchmark the performance of air quality methods and emphasize the necessity to integrate public health measures into the urban and transportation planning process.

Background Attachment research has been limited by the lack of quick and easy measures. We report development and validation of the School Attachment Monitor (SAM), a novel measure for largescale assessment of attachment in children aged 5–9, in the general population. SAM offers automatic presentation, on computer, of story-stems based on the Manchester Child Attachment Story Task (MCAST), without the need for trained administrators. SAM is delivered by novel software which interacts with child participants, starting with warm-up activities to familiarise them with the task. Children’s story completion is video recorded and augmented by ‘smart dolls’ that the child can hold and manipulate, with movement sensors for data collection. The design of SAM was informed by children of users’ age range to establish their task understanding and incorporate their innovative ideas for improving SAM software. Methods 130 5–9 year old children were recruited from mainstream primary schools. In Phase 1, sixty-one children completed both SAM and MCAST. Inter-rater reliability and rating concordance was compared between SAM and MCAST. In Phase 2, a further 44 children completed SAM complete and, including those children completing SAM in Phase 1 (total n = 105), a machine learning algorithm was developed using a “majority vote” procedure where, for each child, 500 non-overlapping video frames contribute to the decision. Results Using manual rating, SAM-MCAST concordance was excellent (89% secure versus insecure; 97% organised versus disorganised; 86% four-way). Comparison of human ratings of SAM versus the machine learning algorithm showed over 80% concordance. Conclusions We have developed a new tool for measuring attachment at the population level, which has good reliability compared to a validated attachment measure and has the potential for automatic rating–opening the door to measurement of attachment in large populations.

The Intergovernmental Panel on Climate Change estimates that greenhouse gas emissions (GHG) must be cut 40–70% by 2050 to prevent a greater than 2 °Celsius increase in the global mean temperature; a threshold that may avoid the most severe climate change impacts. Transportation accounts for about one third of GHG emissions in the United States; reducing these emissions should therefore be an important part of any strategy aimed at meeting the IPCC targets. Prior studies find that improvements in vehicle energy efficiency or decarbonization of the transportation fuel supply would be required for the transportation sector to achieve the IPCC targets. Strategies that could be implemented by regional transportation planning organizations are generally found to have only a modest GHG reduction potential. In this study we challenge these findings. We evaluate what it would take to achieve deep GHG emission reductions from transportation without advances in vehicle energy efficiency and fuel decarbonization beyond what is currently expected under existing regulations and market expectations. We find, based on modeling conducted in the Albuquerque, New Mexico metropolitan area that it is possible to achieve deep reductions that may be able to achieve the IPCC targets. Achieving deep reductions requires changes in transportation policy and land-use planning that go far beyond what is currently planned in Albuquerque and likely anywhere else in the United States.

Long range regional transportation plans (LRTPs) are typically evaluated with performance measures calculated for the first and final years of the planning period. We call this the endpoint modeling method. Planning periods span 20–30 or more years, and therefore the endpoint method can overlook important changes that occur during interim years as well as cumulative impacts. For example, the impact of GHG emissions accumulating in the atmosphere and chronic or deadly diseases caused by exposure to high concentrations of toxic vehicle emissions cannot be reversed by plans that only perform well in the distant future. In this study we evaluate the annual performance of a LRTP created for the Albuquerque, New Mexico metropolitan area over a 28-year period by modeling land-use, travel demand, vehicle emissions and emissions exposure using an incremental and highly integrated land-use and travel demand modeling method. We call this the annual modeling method. We find non-linear and sometimes complex changes in annual emission rates, pollution exposure and other performance measures, indicating that end of period performance metrics may not be robust indicators of average and overall plan performance, which we argue are important considerations. Furthermore, we find that the annual modeling method has a large effect on land-use, traffic and emission exposure forecasts. By the plan’s final year, the annual modeling method forecasts greater population and employment, and correspondingly greater traffic congestion and air pollutant concentrations in the region’s largest activity centers than the endpoint modeling method, which is used by most MPOs.

The discussion of whether, and to what extent, telecommuting can curb congestion in urban areas has spanned more than three decades. This study develops an integrated framework to provide the empirical evidence of the potential impacts of home-based telecommuting on travel behavior, network congestion, and air quality. In the first step, we estimate a telecommuting adoption model using a zero-inflated hierarchical ordered probit model to determine the factors associated with workers’ propensity to adopt telecommuting. Second, we implement the estimated model in the POLARIS activity-based framework to simulate the potential changes in workers’ activity-travel patterns and network congestion. Third, the MOVES mobile source emission simulator and Autonomie vehicle energy simulator are used to estimate the potential changes in vehicular emissions and fuel use in the network as a result of this policy. Different policy adoption scenarios are then tested in the proposed integrated platform. We found that compared to the current baseline situation where almost 12% of workers in Chicago region have flexible working time schedule, in the case when 50% of workers have flexible working time, telecommuting can reduce total daily vehicle miles traveled (VMT) and vehicle hours traveled (VHT) up to 0.69% and 2.09%, respectively. Considering the same comparison settings, this policy has the potential to reduce greenhouse gas and particulate matter emissions by up to 0.71% and 1.14%, respectively. In summary, our results endorse the fact that telecommuting policy has the potential to reduce network congestion and vehicular emissions specifically during rush hours.

Road pricing is advocated as an effective travel demand management strategy to alleviate traffic congestion and improve environmental conditions. This paper analyzes the impacts of cordon pricing on the population’s daily activity pattern and their exposure to particulate matter by integrating activity-based models with air quality and exposure models in the case of New York City. To estimate changes in public exposure under cordon pricing scenarios, we take a sample of employees and study their mobility behavior during the day, which is mainly attributed to the location of the work and the time spent at work. The selection of employees and their exposure during the duration of their work is due to the unavailability of exact activity patterns for each individual. We show that the Central Business District (CBD) experiences a high concentration of PM2.5 emissions. Results indicate that implementing cordon pricing scenarios can reduce the population-weighted mean of exposure to PM2.5 emissions by 7% to 13% for our sample and, in particular, by 22% to 28% for those who work in the CBD. Furthermore, using an experimental model and assuming constant conditions, we point out the positive influence on indoor exposure for two locations inside and outside the CBD in response to cordon pricing. Considering the correlation between long-term exposure to fine particulate matter and the risks of developing cardiovascular disease and lung cancer, our findings suggest that improved public health conditions could be provided by implementing cordon pricing in the New York City CBD.

The air quality impacts of a metropolitan region's long range transportation plans are generally evaluated by estimating the change in a region's vehicle emission inventory. A change in the overall quantity of vehicle emissions in a region is generally associated with lower concentrations of vehicle related air pollutants and therefore a reduction in public health risks from exposure to vehicle emissions. A major limitation of this common approach is that aggregate emission inventories provide no information about localized impacts. While some areas experience air quality improvements, air quality can become worse in others. Such aggregate analyses are ill suited for addressing contemporary transportation planning questions such as identifying vehicle emission exposure hotspots, quantifying health risks, and evaluating environmental justice concerns. In this paper we describe a computationally efficient analysis framework for evaluating a regional transportation plan with spatially detailed estimates of vehicle emission exposures and related health outcomes. We then apply our framework in a case study of fine particulate matter exposure in the Atlanta, Georgia metropolitan area and the changes expected to occur through the year 2040 under the region's long range transportation plan. We find that exposure and health risks decline from current levels by 2020 but then begin to slowly increase in some areas by 2040. We also find that low income and minority populations have the greatest health risks, confirming environmental justice concerns that have been noted in other regions.

This article presents the School Attachment Monitor, a novel interactive system that can reliably administer the Manch- ester Child Attachment Story Task (a standard psychiatric test for the assessment of attachment in children) without the supervision of trained professionals. Attachment prob- lems in children cause significant mental health issues and costs to society which technology has the potential to re- duce. SAM collects, through instrumented doll-play games, enough information to allow a human assessor to manually identify the attachment status of children. Experiments show that the system successfully does this in 87.5% of cases. In addition, the experiments show that an automatic approach based on deep neural networks can map the information collected into the attachment condition of the children. The outcome SAM matches the judgment of expert human asses- sors in 82.8% of cases. This is the first time an automated tool has been successful in measuring attachment. This work has significant implications for psychiatry as it allows profes- sionals to assess many more children cost effectively and to direct healthcare resources more accurately and efficiently to improve mental health.

Autonomous vehicles (AVs) hold great promise for increasing the capacity of existing roadways and intersections, providing more mobility to a wider range of people, and are likely to reduce vehicle crashes. However, AVs are also likely to increase travel demand which could diminish the potential for AVs to reduce congestion and cause emissions of greenhouse gases (GHG) and other air pollutants to increase. Therefore, understanding how AVs will affect travel demand is critical to understanding their potential benefits and impacts. We evaluate how adoption of AVs affects travel demand, congestion and vehicle emissions over several decades using an integrated travel demand, land-use and air quality modeling framework for the Albuquerque, New Mexico metropolitan area. We find that AVs are likely to increase demand and GHG emissions as development patterns shift to the region's periphery and trips become longer. Congestion declines along most roadways as expanded capacity from more efficient AV operation outpaces increasing demand. Most of the population can also expect a reduction in exposure to toxic vehicle emissions. Some locations will experience an increase in air pollution exposure and traffic congestion from changes in land-use and traffic patterns caused by the adoption of AVs.

Transportation projects contain many tradeoffs between environmental, social, and economic benefits and costs that affect different groups of stakeholders, each with different priorities and values. Transportation project sponsors are therefore faced with an incredibly difficult decision making task. Multi-criteria decision analysis (MCDA) provides a flexible framework for considering a wide array of potential impacts that may be used as a supplement of substitute for cost benefit analysis or unstructured decision making. In this study, we evaluate the outcome of two MCDAs, one conducted with input from technical experts and the other with input from a sample of community members for a proposed highway project in Tehran, Iran. We explore how various criteria now commonly considered in urban transportation projects are viewed by these two groups that differ in their technical expertise and values. We find that experts score the project poorly while the community scores it favorably. The results demonstrate that the outcome of seemingly objective analysis tools commonly used in the transportation field depends on who provides critical technical assessments and value judgments and therefore the importance of community involvement.

Many urban areas are perusing infill, transit oriented, and other “smart-growth” strategies to address a range of important regional goals. Denser and more mixed use urban development may increase sustainability and improve public health by reducing vehicle travel and increasing the share of trips made by transit, walking and bicycling. Fewer vehicle trips results in fewer greenhouse gas and toxic vehicle emissions, and more trips made by walking and bicycle increases physical activity. Prior research has largely focused on modeling and estimating the potential size of these and other smart-growth strategy benefits. A largely overlooked area is the potential for unexpected public health costs and environmental justice concerns that may result from increasing density. We evaluate regional land-use and transportation planning scenarios developed for the year 2040 by a metropolitan planning organization with a newly developed regional air quality modeling framework. Our results find that a set of regional plans designed by the MPO to promote smart-growth that are estimated to result in less vehicle use and fewer vehicle emissions than a more typical set of plans results in higher population exposure to toxic vehicle emissions. The smart-growth plans also result in greater income-exposure inequality, raising environmental justice concerns. We conclude that a more spatially detailed regional scale air quality analysis can inform the creation of smarter smart-growth plans.

Understanding the temporal and spatial variation of air quality (AQ) impact due to congestion pricing is important since the health and economic benefits of air quality improvements depend on the distribution of traffic-related air pollution. Aiming to improve our knowledge of the AQ impacts from congestion pricing, this study integrates a disaggregate agent-based travel demand model with a hyper-local air quality model to examine emissions, air quality, and exposure. Studying congestion pricing schemes in NYC, we find that daily single-occupancy-vehicle trips to the charging area decreases by 14.5% and 24.3% under the low and high charging schemes, respectively. Correspondingly, the PM2.5 concentration decreases by 5–25% in the Central Manhattan areas in the low-toll scenario, and by more than 10% across almost all of New York City areas in the high-toll scenario. Our results indicate non-linear relations between the adaptation of travel behavior and the resulting air quality/exposure impacts.

The goal of this chapter is to show that human behavior is not random but follows principles and laws that result into regular patterns that can be not only observed, but also automatically detected and analyzed. The word “behavior” accounts here for nonverbal behavioral cues (e.g., facial expressions, laughter, gestures, etc.) that people display, typically outside conscious awareness, during social interactions. In particular, the chapter shows that observable behavioral patterns typically account for social and psychological differences that cannot be observed directly. Therefore, the analysis of behavioral patterns is important from a human sciences point of view because it helps to understand how people work. Furthermore, it is becoming increasingly important from a technological point of view because observable behavior can be thought of as the physical, machine detectable trace of social and psychological phenomena. In particular, if it is possible to automatically detect and interpret behavioral patterns, it means that machines can make sense of social and psychological phenomena in the same way as people do.

Physical fatigue is one of the most important and highly prevalent occupational hazards in different industries. This research adopts a new analytical framework to detect workers&rsquo, physical fatigue using heart rate measurements. First, desired features are extracted from the heart signals using different entropies and statistical measures. Then, a feature selection method is used to rank features according to their role in classification. Finally, using some of the frequently used classification algorithms, physical fatigue is detected. The experimental results show that the proposed method has excellent performance in recognizing the physical fatigue. The achieved accuracy, sensitivity, and specificity rates for fatigue detection are 90.36%, 82.26%, and 96.2%, respectively. The proposed method provides an efficient tool for accurate and real-time monitoring of physical fatigue and aids to enhance workers&rsquo, safety and prevent accidents. It can be useful to develop warning systems against high levels of physical fatigue and design better resting times to improve workers&rsquo, safety. This research ultimately aids to improve social sustainability through minimizing work accidents and injuries arising from fatigue.

Vehicle traffic is responsible for a significant portion of toxic air pollution in urban areas that has been linked to a wide range of adverse health outcomes. Most vehicle air quality analyses used for transportation planning and health effect studies estimate exposure from the measured or modeled concentration of an air pollutant at a person's home. This study evaluates exposure to fine particulate matter from vehicle traffic and the magnitude and cause of exposure misclassification that result from not accounting for population mobility during the day in a large, sprawling region. We develop a dynamic exposure model by integrating activity-based travel demand, vehicle emission, and air dispersion models to evaluate the magnitude, components and spatial patterns of vehicle exposure misclassification in the Atlanta, Georgia metropolitan area. Overall, we find that population exposure estimates increase by 51% when population mobility is accounted for. Errors are much larger in suburban and rural areas where exposure is underestimated while exposure may be overestimated near high volume roadways and in the urban core. Exposure while at work and traveling account for much of the error. We find much larger errors than prior studies, all of which have focused on more compact urban regions. Since many people spend a large part of their day away from their homes and vehicle emissions are known to create "hotspots" along roadways, home-based exposure is unlikely to be a robust estimator of a person's actual exposure. Accounting for population mobility in vehicle emission exposure studies may reveal more effective mitigation strategies, important differences in exposure between population groups with different travel patterns, and reduce exposure misclassification in health studies.

This article proposes an automatic approach - based on nonverbal speech features - aimed at the automatic discrimination between depressed and non-depressed speakers. The experiments have been performed over one of the largest corpora collected for such a task in the literature (62 patients diagnosed with depression and 54 healthy control subjects), especially when it comes to data where the depressed speakers have been diagnosed as such by professional psychiatrists. The results show that the discrimination can be performed with an accuracy of over 75% and the error analysis shows that the chances of correct classification do not change according to gender, depression-related pathology diagnosed by the psychiatrists or length of the pharmacological treatment (if any). Furthermore, for every depressed subject, the corpus includes a control subject that matches age, education level and gender. This ensures that the approach actually discriminates between depressed and non depressed speakers and does not simply capture differences resulting from other factors.

Over the past 20 years, with the increase in the complexity of engines, and the combinatorial explosion of engine variables space, the engine calibration process has become more complex, costly, and time consuming. As a result, an efficient and economic approach is desired. For this purpose, many engine calibration methods are under development in original equipment manufacturers and universities. The state-of-the-art model-based steady-state design of experiments (DOE) technique is mature and is used widely. However, it is very difficult to further reduce the measurement time. Additionally, the increasingly high requirements of engine model accuracy and robust testing process with high data quality by high-quality testing facility also constrain the further development of model-based DOE engine calibration. This paper introduces a new computational intelligence approach to calibrate internal combustion engine without the need for an engine model. The strength Pareto evolutionary algorithm 2 (SPEA2) is applied to this automatic engine calibration process. In order to implement the approach on a V6 gasoline direct injection (GDI) engine test bench, a simulink real-time based embedded system was developed and implemented to engine electronic control unit (ECU) through rapid control prototyping (RCP) and external ECU bypass technology. Experimental validations prove that the developed engine calibration approach is capable of automatically finding the optimal engine variable set which can provide the best fuel consumption and particulate matter (PM) emissions, with good accuracy and high efficiency. The introduced engine calibration approach does not rely on either the engine model or the massive test bench experimental data. It has great potential to improve the engine calibration process for industries.

Aim: One of the most crucial and common occupational hazards in different industries is physical fatigue. Fatigue plays a vast role in all industries in terms of health, safety, and productivity and is continually ranked among the top-five health-related risk factors year after year. The current study focuses on a novel method to detect workers' physical fatigue employing heart rate signals. Materials and Methods: First, domain features are extracted from the heart signals utilizing different entropies and statistical tests. Then, K-nearest neighbors algorithm is used to detect the physical fatigue. The experimental results reveal that the proposed method has a good performance to recognize the physical fatigue. Results: The achieved measures of accuracy, sensitivity, and specificity rates are 78.18%, 60.96%, and 82.15%, respectively, discretely for fatigue detection. Discussion: Based on the achieved results, it is conceived that monitoring of heart rate signals is an effective tool to assess the physical fatigue in manufacturing and construction sites since there is a direct relationship between fatigue and heart rate features. The results presented in this article showed that the proposed method would work well as an effective tool for accurate and real-time monitoring of physical fatigue and help to increase workers' safety and minimize accidents. Conclusion: The results presented in this article shows that the proposed method would work well as an effective tool for accurate and real-time monitoring of physical fatigue and helps to increase workers' safety and minimize accidents.

The Latin Hypercube (LH) design problem arises in computer simulations and is employed for examination and simulation of many physical events. In order to find a (near) optimal LH design, this paper proposes a new version of Particle Swarm Optimization (PSO) algorithm, which uses a population-based optimizer as the evolutionary part and a multiple-local-search procedure as the refinement part of the algorithm. To manage the problem constraints, the proposed algorithm utilizes a Ranked Ordered Value (ROV) rule, which converts the continuous space of solutions to the point-permutation space. Furthermore, to maintain the population diversity, the meta-Lamarckian learning strategy is applied to the local search procedure of the algorithm. In order to test the proposed algorithm, we compare it with a set of existing algorithms on several problem instances. To perform a fair comparison, the best parameters for all the algorithms are found and the experiments are performed based on these parameters. The experimental results show that the proposed algorithm outperforms the existing algorithms in solving large-scale LH design problem.

Bicycle facilities are commonly invested in to reduce vehicle congestion, mitigate vehicle emissions, and promote physical activity by increasing the number of bicycle trips and reducing the number of vehicle trips. Although there has been a large amount of behavioral and observational research on bicyclists’ route and facility preferences and the traveling public’s mode choice decisions, there is surprisingly little evidence on the effectiveness of bicycle facilities in increasing the share of bicycling relative to vehicle use. Using a stated-preference survey, this study finds that more than two-thirds of current bicycle facility users in Albuquerque, New Mexico, would continue to bicycle, and nearly one-third would discontinue bicycling, if the bicycle facilities they regularly use did not exist. The most common alternative would be driving a car. The findings suggest that bicycle facilities can increase bicycle mode share and reduce driving by influencing the mode choice decisions of certain i...

The market penetration of Plug-in Electric Vehicles (PEVs) is escalating due to their energy saving and environmental benefits. In order to address PEVs impact on the electric networks, the aggregators need to accurately predict the PEV Travel Behavior (PEV-TB) since the addition of a great number of PEVs to the current distribution network poses serious challenges to the power system. Forecasting PEV-TB is critical because of the high degree of uncertainties in drivers’ behavior. Existing studies mostly simplified the PEV-TB by mapping travel behavior from conventional vehicles. This could cause bias in power estimation considering the differences in PEV-TB because of charging pattern which consequently could bungle economic analysis of aggregators. In this study, to forecast PEV-TB an artificial intelligence-based method -feedforward and recurrent Artificial Neural Networks (ANN) with Levenberg Marquardt (LM) training method based on Rough structure - is developed. The method is based on historical data including arrival time, departure time and trip length. In this study, the correlation among arrival time, departure time and trip length is also considered. The forecasted PEV-TB is then compared with Monte Carlo Simulation (MCS) which is the main benchmarking method in this field. The results comparison depicted the robustness of the proposed methodology. The proposed method reduces the aggregators’ financial loss approximately by 16 $/PEV per year compared to the conventional methods. The findings underline the importance of applying more accurate methods to forecast PEV-TB to gain the most benefit of vehicle electrification in the years to come.