Abstract
E-commerce growth is raising the demand for logistic activities, especially in the last-mile, which is considered the most ineffective part of the supply chain and a negative externalities source. Although various solutions aim to address these issues, selecting the best one is challenging due to multiple perspectives, conflicting criteria, trade-offs, and complex and sensitive urban contexts. This article proposes a 4-level hierarchical model based on the triple bottom line of sustainability that may assist decision-makers in selecting the most adequate last -mile solution for historic centers. The model was defined based on a systematic literature review; evaluated by interviewing a set of experts; and quantified according to an AHP-TOPSIS approach. This quantification focused on the historic center of Porto, Portugal. The experts considered all three sustainability dimensions similarly important. Air pollution was the most valued sub-criterion whereas Visual pollution was the least. 67 decision-maker profiles were defined, showing that environmentally oriented decision-makers prefer cargo bikes, while decision-makers who prioritize economic and social factors prefer parcel lockers. All last-mile solutions considered in the model yielded similar results, therefore suggesting a combined distribution strategy. Nevertheless, the use of parcel lockers is the most favorable solution for Porto's historic center.

Abstract
This work presents a deep learning framework for analyzing urban mobility by extracting knowledge from messages collected from Twitter. The framework, which is designed to handle large-scale data and adapt automatically to new contexts, comprises three main modules: data collection and system configuration, data analytics, and aggregation and visualization. The text data is pre-processed using NLP techniques to remove informal words, slang, and misspellings. A pre-trained, unsupervised word embedding model, BERT, is used to classify travel-related tweets using a unigram approach with three dictionaries of travel-related target words: small, medium, and big. Public opinion is evaluated using VADER to classify travel-related tweets according to their sentiments. The mobility of three major cities was assessed: London, Melbourne, and New York. The framework demonstrates consistently high average performance, with a Precision of 0.80 for text classification and 0.77 for sentiment analysis. The framework can aggregate sparse information from social media and provide updated information in near real-time with high spatial resolution, enabling easy identification of traffic-related events. The framework is helpful for transportation decision-makers in operational control, tactical-strategic planning, and policy evaluation. For example, it can be used to improve the management of resources during traffic congestion or emergencies.

Abstract
In this paper is presented firstly the traffic and emission characterization of Via de Cintura Interna (VCI), an urban highway at Oporto city, Portugal, with more than 4 000 vehicles/hour during rush hours. Emission estimates were carried through on the basis of emission factors to road transport published in the Atmospheric Emission Inventory Guidebook. A weighed emission factor has beer, calculated for nitrogen oxides (NOx) and vehicle class, according to the Portuguese fleet composition (vehicles age, type of engine and average speed). Furthermore, during a three-week period, an outdoor nitrogen dioxide (NO2) monitoring campaign was carried out in a domain around the VCl (100 m for each side), in particular near residential buildings. The results demonstrate that higher NO2 concentrations are seen in the sub-domain with higher circulation of heavy-duty vehicles and where buildings are adjacent to VCI hindering pollutant dispersion. Meteorological conditions, such as wind intensity and direction, temperature and solar radiation were monitorized too. The NO2 concentrations obtained by the monitoring campaign have been used to create scenarios of population exposure to NO2, having taken into account the time-activity patterns of residents. It was verified that higher exposures occur when the population lives in Boavista, in contrast with the favourable scenario that corresponds to life in Prelada and those working in Espinho city. The work and results presented in this paper are a part of the methodology used in the scope of the ImpactAir Project. This project, started in 2003 in Oporto city, has the main objective of evaluating the impact of urban highway (VCI) traffic emissions on air quality and the health of the local population.

Abstract
This paper focuses on the integration of multiple computational tools towards the objective of assessing emission impacts of different routes. Data from real life GPS tracks was integrated with traffic emission modelling for multiple pollutants (NOx, HC, CO and PM10) to investigate different routing strategies. The main conclusion is that different pollutants dictate different best routes. Hence, strategies for assigning relative weights to pollutants are devised in order to be able to select the best environment-friendly route. © 2012 ACM.

Abstract
Benzene is a carcinogenic and genotoxic pollutant which mainly affects the people health through the inhalation. Nevertheless, this pollutant is not frequently measured by air-quality networks. To solve this problem, some models have been published to estimate benzene concentrations in the atmosphere. However, the lack of measures makes difficult the application of complex models in order to get a detailed spatio-temporal analysis, namely in urban areas. In this work was developed a simple semi-empirical model to predict benzene concentrations based on the ratio of benzene and carbon monoxide concentrations in order to predict the concentrations of this pollutant in large areas and periods with lack of benzene measurements but with higher impact in the human health. The model was applied to an urban area, the Metropolitan Area of Oporto, for a period of 12 years (1995-2006). Monthly correlations between benzene and carbon monoxide concentrations at Custias air-quality station are significant (p = 0.01) and higher in winter (r (s) > 0.7) than in summer (0.3 > r (s) > 0.7). Estimate of the monthly ratio of the concentration of these two pollutants range between 199 and 305. The methodology validation shows good results (r (s) = 0.81) which allow, assuming the availability of carbon monoxide data, the use of this tool for areas with low benzene recorded data. The application of this methodology in the study area shows an annual average trend decrease of benzene concentrations during the study period, which may be linked to a general trend decrease of benzene emissions in European urban areas, including the study domain.

Abstract
NNIGnets is a freeware computer program which can be used for teaching, research or business applications, of Artificial Neural Networks (ANNs). This software includes presently several tools for the application and analysis of Multilayer Perceptrons (MLPs) and Radial Basis Functions (RBEs), such as stratified Cross-Validation, Learning Curves, Adjusted Rand Index, novel cost functions, and Vapnik-Chervonenkis (VC) dimension estimation, which are not usually found in other ANN software packages. NNIGnets was built following a software engineering approach which decouples operative from GUI functions, allowing an easy growth of the package. NNIGnets was tested by a variety of users, with different backgrounds and skills, who found it to be intuitive, complete and easy to use.