Search

Autogenerated Advertisements (AGAs) can be a concern for consumers if they suspect that Artificial Intelligence (AI) was involved. Consumers may have an opposing stance against AI, leading companies to miss profit opportunities and reputation loss. Hence, companies need ways of managing consumers’ con-cerns. As a part of designing such advices we explore consumers’ discernment ability (DA) of AGAs. A quantitative survey was used to explore consumers’ DA of AGAs. In order to do this, we administered questionnaires to 233 re-spondents. A statistical analysis including Z-tests, of these responses suggests that consumers can hardly pick out AGAs. This indicates that consumers may be guessing and thus do not possess any significant DA of our AGAs., Partly funded by The Knowledge Foundation, grants nr. 20160035, 20170215

Artificial Intelligence (AI) and Machine Learning (ML) are shaping marketing activities through digital innovations. Competition is a familiar concept for any digital retailer, and the digital transformation provides hopes for gaining a competitive edge over competitors. Those who do not adopt digital innovations risk getting outcompeted by those who do. This study aims to identify AI mar-keting (AIM) adoptions used for ad optimization with Reinforcement Learning (RL). A scoped literature review is used to find ad optimization adoptions re-search trends with RL in AIM. Scoping this is important both to research and practice as it provides spots for novel adaptations and directions of research of digital ad optimization with RL. The results of the review provide several differ-ent adoptions of ad optimization with RL in AIM. In short, the major category is Ad Relevance Optimization that takes several different forms depending on the purpose of the adoption. The underlying found themes of adoptions are Ad Attractiveness, Edge Ad, Sequential Ad and Ad Criteria Optimization. In conclusion, AIM adoptions with RL is scarce, and recommendations for future research are suggested based on the findings of the review., Partly funded by The Knowledge Foundation, grants nr. 20160035, 20170215

The district heating (DH) industry is facing an important transformation towards more efficient networks that utilise significantly lower water temperatures to distribute the heat. This change requires taking advantage of new technologies, and Machine Learning (ML) is a popular direction. In the last decade, we have witnessed an extreme growth in the number of published research papers that focus on applying ML techniques to the DH domain. However, based on our experience in the field, and an extensive review of the state-of-the-art, we perceive a mismatch between the most popular research directions, such as forecasting, and the challenges faced by the DH industry. In this work, we present our findings, explain and demonstrate the key gaps between the two communities and suggest a road-map ahead towards increasing the impact of ML research in the DH industry. © 2021 by the authors. Licensee MDPI, Basel, Switzerland., Funding: The work presented in this article was financed by the Swedish Knowledge Foundation (KK-stiftelsen http://www.kks.se/om-oss/in-english/ accessed on 15 May 2021) under grant Dnr.20170182 within the project Data Analytics for Fault Detection in District Heating (DAD) and grant Dnr.20160301 within the project Self-Monitoring for Innovation (SeMI). The Swedish agency for innovation, VINNOVA (https://www.vinnova.se/en accessed on 15 May 2021), financed the work in this article through the SAM project, Dnr. 2018-03349., Data Analytics for Fault Detection in District Heating (DAD), Self-Monitoring for Innovation (SeMI), SAM

Recommendation systems in fashion are used to provide recommendations to users on clothing items, matching styles, and size or fit. These recommendations are generated based on user actions such as ratings, reviews or general interaction with a seller. There is an increased adoption of implicit feedback in models aimed at providing recommendations in fashion. This paper aims to understand the nature of implicit user feedback in fashion recommendation systems by following guidelines to group user actions. Categories of user actions that characterize implicit feedback are examination, retention, reference, and annotation. Each category describes a specific set of actions a user takes. It is observed that fashion recommendations using implicit user feedback mostly rely on retention as a user action to provide recommendations.

Ur insikten om behovet av brukaravgifter inom transportsektorn föddes idén att skapa en arena för den samlade kompetensen i Sverige. Detta blev ARENA-projektet, vars första fas, 2006-2008, hade som mål att utveckla ett koncept för ett vägavgiftssystem för lastbilar. Den andra fasen avslutades 2011 med syftet att verifiera det utvecklade vägavgiftskonceptet genom praktiska demonstrationer. Projektet lade även grunden för en innovationsmiljö inom ITS, som är knuten till NetPort Science Park och Blekinge Tekniska Högskola. I den tredje fasen breddades anslaget till att stödja utvecklingen av samverkan och interoperabilitet mellan olika system för exempelvis trängselskatt, infra-strukturavgifter eller kilometerskatt, såväl i Sverige som internationellt. Från 2015 har ARENA övergått till att vara en långsiktig nationell kunskapsplattform för brukaravgifter inom transportsektorn. Inom ARENA drivs olika projekt beroende på de problemställningar som är aktuella i samhället. Ett av dessa handlar om att utveckla metodik för effektutvärdering av kilometerskatt för tunga fordon. Detta projekt har löpt parallellt med Vägslitageskattekommitténs arbete och som ARENA samverkat med och stöttat. Arbetet inom ARENA fokuserar på att utreda vilka effekter av en kilometerskatt som är troliga/möjliga och vilka av dessa som i sin tur är möjliga att observera och hur de kan observeras. Detta har gjorts genom bl.a. inventeringar av andra liknande initiativ och hur de har utvärderats, litteraturgenomgångar och workshops. Rapporter från detta arbete återfinns på projektets hemsida (http://www.arena-ruc.se/). Denna avslutande rapport fokuserar framförallt på övergripande slutsatser baserat på arbetet inom ARENA, samt de rekommendationer om datainsamling och utvärdering som projekt- och styrgruppen för ARENA anser är relevanta att nu gå vidare med, baserat på att ett beslut om införande av kilometerskatt inte har tagits och det är oklart huruvida beslut kommer att tas inom de närmaste åren. AREN, Metodik för effektutvärdering av kilometerskatt för tunga fordon

Over the last 15 years, distance-based road user charging schemes have been designed and deployed across the European Union. At least 10 EU countries today calculate, charge and collect fares for the use of road infrastructure following a differential model supported by positioning, communication, and other related technologies such as ANPR. As future road charging schemes are being developed, existing systems, although aimed at varying goals, will play a critical role in passing along their experiences to positively influence the development of future road charging schemes. This report set a high ambition to study the evaluation landscape in the domain of distance-based road user charging. Given the current efforts within the ARENA knowledge platform targeted toward the development of an evaluation methodology for a possible distance-based road user charging scheme in Sweden, the report was aimed at laying a solid foundation to ensure that the development of the methodology should as much as possible build on real world experiences. To that effect, 15 systems are identified and analysed, including two congestion-charging schemes (Gothenburg and Stockholm) and 13 distance-based charging schemes in Europe andother parts of the world. The predominantly literature review-based analysis aim to isolate the goals behind these different schemes, if and how the scheme was evaluated, including the questions that were raised in the evaluation, evaluation phases that were covered, the methods that were employed in collecting evaluation data, and analysing the data for possible effects. More important, the analysis aimed at understanding what proven effects were uncovered, as well as the lessons learned from the evaluation process. In order to perform an analysis, the above goals were disaggregated into concrete questions, e.g., for each specific system, what was the evaluation method employed. Secondary data was then collected mainly through Internet search within transport re

ARENA 3 sätter som mål för sitt arbete under perioden 2011-2014 att: • Stödja utvecklingen av praktiska lösningar för elektroniska vägavgiftssystem för aktuella och framtida svenska behov. • Stärka nationell kompetensuppbyggnad inom vägavgifter och ITS. • Vara naturlig mötesplats för frågor som rör vägavgifter. • Etablera nordisk samverkan för framtida certifiering och framtida behov för vägavgifter. • Utveckla säkerhets- och integritetslösningar som bidrar till säkrare vägavgiftsupptagning. • Utveckla Test Site NetPort för kvalificerade försök med partner inom ett utökat Östersjösamarbete. • Skapa en innovationsmiljö inom ITS och vägavgifter genom internationell inriktning av försöksområdet. • Genomföra seminarier och workshop, på nationell och internationell nivå inom aktuella frågeställningar., Arena 3

We present results from a simulation study, whichwas designed for investigating the potential positive impacts, i.e., the invoicing and processing time, and financial savings,when using an electronic waybill instead of paper waybillsfor road-based freight transportation. The simulation modelis implemented in an experiment for three different scenarios,where the processing time for waybills at the freight loadingand unloading locations in a particular scenario differs fromother scenarios. The results indicate that a saving of 65%–99%in the invoicing time can be achieved when using an electronicwaybill instead of paper waybills. Our study can be helpful todecision makers, e.g., managers and staff dealing with paperwaybills, to estimate the potential benefits when making deci-sions concerning the implementation of an electronic waybillsolution for replacing paper waybills.

The efficiency of road transport is typically influenced by factors such as, weather, choice of road, and time of day, and day of the week. Knowledge about interactions between different traffic-and transport related factors and their influence on the execution of transport is important in transport planning. The purpose of this paper is to study the impact of different factors on the performance of road transport. We aim to contribute to improved transport planning by analysing traffic and transport data obtained from different sources in order to support data driven decision making. Through a review of existing literature and discussions with a Swedish road transport operator, we identified factors that could be relevant to consider when planning a transport, e.g., related to weather, location of roads where the transport will take place, and planned time of the transport. As a result of variation in size, type and volume of the data representing these factors, suitable machine learning algorithms were selected, such as Decision Stump, M5 model tree, M5 regression tree, RepTree, M5 rules, and linear regression in order to study the data. Our experimental results illustrate the complexity associated to the performance of road transport systems mainly because of the dependency between the choices of influencing factors and geographic location of the road segment.

A method for assessing potential synergies among different sets of transport telematic services (TTSs) is suggested. An Intelligent Transport System enhances transport by delivering one or more TTSs. The ability to deliver multiple TTSs to address a wide range of stakeholder needs is gaining momentum, not only from a marketing perspective but also from a technological perspective. The total cost of TTSs can be reduced if they share functionalities (i.e., sub-services provided by telematic systems). We show how this synergy can be assessed with the help of clustering methods. Knowledge about possible synergies of functionalities is useful in the (re)design and eventual deployment of TTSs, especially when the underlying telematic systems are able to support multiple TTSs. To adapt the clustering method for this purpose, we suggest a mathematical formulation of synergy among functionalities of TTSs. By applying the method to a set of 32 TTSs, we obtain a cluster formation of these TTSs according to their synergy measures. Overall, the results suggest that the joint implementation of TTSs targeted toward some problem domains can lead to significant cost savings, for example, Road User Charging, Infrastructure Repair and Maintenance, and Information on the Transport of extra large goods for the management of road transport infrastructure. © The Institution of Engineering and Technology 2015.

The selection, composition and integration of Transport Telematic Services (TTSs) is crucial for achieving cooperative Intelligent Transport Systems (ITS). To enable future adaptation, models for selecting and composing TTSs needs to take into account possible future modifications, upgrades or downgrades of different TTSs without tipping off the benefit edge. To achieve this, a Strategic Service Selection Problem (SSSP) for TTSs is presented in this article. The problem involves selecting a set of TTSs that maximizes net societal benefits over a strategic time period, e.g., 10 years. The formulation of the problem offers possibilities to study design alternatives taking into account future modifications, extensions, upgrades or downgrades of different TTSs. Two decisive factors affecting the choices and modifications of TTSs are studied: 1) the effect of using Governmental policies to mandate the introduction of TTSs, e.g., Road User Charging and eCall, and 2) the effects of allowing market forces to drive the choices of TTSs. Case study results indicate that in determining combinations of TTSs that can be deployed in a period of 10 years, enforcing too many TTSs can retard the ability of the market to generate net benefits even though the results could be that more TTSs will be deployed.

The ability to generate accurate travel time predictions for road freight transport is important when, for example, estimating the arrival times for heavy goods vehicles (HGVs) in order to plan terminal activities. We present a micro-level sampling method for road travel time prediction. The method makes use of historical GPS-data in order to determine the movement of a vehicle from an origin to a destination along a specific route. The method generates a travel time distribution, which can be used to obtain the expected travel time and probabilities for deviations. The method has been illustrated and evaluated in an experiment where the effective travel time was predicted for transport between two terminals. The experiment made use of GPS data that was recorded for two HGVs during a period of two months. An important feature of the method is that it does not need road network information, such as speed limits and number of lanes., The online version on IEEE Xplore is yet to be avialble.

This study describes transport telematic services (TTSs) for road-based heavy goods vehicle (HGV) transport and suggests a method for assessing the societal value of different TTSs. For decision making related to the selection of services to promote by potential investors, for example, governmental organisations and service providers, quantified service value can simplify the decision process by enabling comparison between TTSs. Moreover, these values can serve as inputs to quantitative analysis of service architectural system designs. The authors suggest a method for assessing the societal values of TTSs using potential saving indicators (PSIs), estimated in the context of Swedish HGV freight transport. To illustrate the proposed method, 32 services are analysed, and their societal values were quantified and compared for the Swedish HGV market. Results based on estimated values of PSIs and potential percentage savings indicate the following HGV-based TTSs to be of high societal potential: transport resource optimisation, dynamic traffic information, navigation, road hindrance warning, theft alarm and recovery, accident warning information, intelligent speed adaptation, eCall, en-route driver information, transport order handling, road user charging and sensitive goods monitoring.

Transport telematic systems, also known as intelligent transportation systems, can be expensive to implement but the services they provide may offer substantial benefits. However, what services the system can provide depends on the architectural choices made, which also affects the cost of the system. We propose an optimization model to support a more informed decision before investing in a multiple service transport telematic system. The model evaluates the possible choices of services and architectures, and aims to maximize the total net societal benefit. We argue that the optimization model can provide support for strategic decisions by highlighting the consequences of adopting different system architectures, including both societal value and cost. This can be useful for decision makers, such as governments, road transport telematic service providers, and commercial road freight transport operators.

This article suggest Transport Telematic Services (TTSs) to facilitate the realization of Intelligent Truck Parking (ITP) concept i.e. ITP core services e.g. a service that can support real time reservation of truck parking space using for instance mobile phone messaging capabilities. We consider ITP to include the collection, processing and delivery of information about Truck Parking Areas (TPAs) that may take place during the planning and execution of transportation services. A key feature for ITP core services is to achieve efficient information exchange related to TPA so as to improve the overall performance of the transport system. We suggest core services seen to have a potential for achieving ITP. Our suggestions are based on studying “what” kind of information exchanges among TPA stakeholders “when” and “where” the information is exchanged in relation to transport related challenges that are addressed with such information. Hence we suggest Truck Parking facility Utilization (TPU), Goods and Vehicle Safety assurance information (GVS), Parking Location Guidance (PLG) and Parking Reservation (PAR), as ITP core services., This article is part of the project known as Intelligent Truck Parking, financed by the Swedish Transportation Administration (Trafikverket). There is an advanced version to be appearing in IET Intelligent Transport Systems Journal. The current version is published in the archives of the 19th world congress on Intelligent Transport Systems that took place in Vienna, October 2012.

TSC import 869 2012-02-06. QC 20120413

This article uses analytical methods to assess reductions in total costs of telematic systems that can result from common infrastructure utilization. Analytical methods based on clustering and K-minimum spanning tree can be adopted for finding clusters or sets which maximize reductions in total system costs due to infrastructure sharing between telematic systems. Efficient integration of telematic systems through infrastructure sharing can positively influence telematic service interoperability while reducing costs. Results show the measure of synergy for each K-value, as well as total cost savings of up to 2%.

Modeling benefits and Quality of Service (QoS) for Multi-Service Architectures (MSAs) is important to enable service providers offer the best Transport Telematic Services (TTSs) with high societal benefits to users. This study models how different QoS characteristics may influence potential benefits of MSAs for road based freight TTSs. This is achieved by modeling the QoS degradation under conditions of shared resources and including costs associated to such degradation to determine the benefits as the difference between the costs and societal value of the applications. A system performance oriented QoS measure has been introduced in coming up with a MSA benefits model, providing a possibility to capture different quality attributes, desired performance levels, and even the possibility to introduce desired priorities between applications and quality attributes., T_EU00980

The purpose of this study is to develop an optimization model that can select handling equipment and ships from a strategic level. This model can help when investing in systems for handling unitized cargo at port terminals in the context of Short Sea Shipping (SSS). Initial model results indicate that a LoLo vessel with a capacity between (500 and 1000 TEU) capable of completing a SSS voyage, when handling is completed in 48 hours will be less costly than a RoRo, which may have multiple voyages for TEU volumes greater than 1000.

As a result of their high economic costs and unforeseen impacts on society, pre-implementation evaluation of telematic systems is important and can lead to time and cost savings. This article presents an optimization perspective for evaluating conceptual options of transport telematic architecture in relation to benefits to the society. These benefits are evaluated in the context of multiple services and provide one way for comparing between alternative conceptual options for telematic system architectures that can support multiple services. An optimization model is proposed and preliminary results of beneficial services for different architecture options highlighted