Advanced Information Systems Engineering Workshops

Perceiving information and extracting insights from data is one of the major challenges in smart manufacturing. Real-time data analytics face several challenges in real-life scenarios, while there is a huge treasure of legacy, enterprise and operational data remaining untouched. The current paper exploits the recent advancements of (deep) machine learning for performing predictive and prescriptive analytics on the basis of enterprise and operational data aiming at supporting the operator on the shopfloor. To do this, it implements algorithms, such as Recurrent Neural Networks for predictive analytics, and Multi-Objective Reinforcement Learning for prescriptive analytics. The proposed approach is demonstrated in a predictive maintenance scenario in steel industry.

Industry 4.0 has shifted the manufacturing related processes from conventional processes within one organization to collaborative processes across different organizations. For example, product design processes, manufacturing processes, and maintenance processes across different factories and enterprises. This complex and competitive collaboration requires the underlying system architecture and platform to be flexible and extensible to support the demands of dynamic collaborations as well as advanced functionalities such as big data analytics. Both operation and condition of the production equipment are critical to the whole manufacturing process. Failures of any machine tools can easily have impact on the subsequent value-added processes of the collaboration. Predictive maintenance provides a detailed examination of the detection, location and diagnosis of faults in related machineries using various analyses. In this context, this paper explores how the FIWARE framework supports predictive maintenance. Specifically, it looks at applying a data driven approach to the Long Short-Term Memory Network (LSTM) model for machine condition and remaining useful life to support predictive maintenance using FIWARE framework in a modular fashion.

Massive amounts of data produced by railway systems are a valuable resource to enable Big Data analytics. Despite its richness, several challenges arise when dealing with the deployment of a big data architecture into a railway system. In this paper, we propose a four-layers big data architecture with the goal of establishing a data management policy to manage massive amounts of data produced by railway switch points and perform analytical tasks efficiently. An implementation of the architecture is given along with the realization of a Long Short-Term Memory prediction model for detecting failures on the Italian Railway Line of Milano - Monza - Chiasso.

The core problem of the application of MES (Manufacturing Execution System) in intelligent manufacturing systems is integration, which solves the problem of the data interoperation between the distributed manufacturing systems. The previous researches on MES integration rarely considered the problem of system data security access. A three-level data security access mechanism based on the independence of the system administrators, security administrators, and security auditors is proposed which integrated into the MES integration framework to guarantee the business and engineering data security access for the related distributed clients. The principle is using the domain to make the logical isolation for different clients and data sources and applying the pre-defined data sharing rules for safe access. In the proposed MES integration framework model, the data interoperation between MES and the engineering software systems is discussed which includes ERP (Enterprise Resource Management), CAPP (Computer Aided Process Planning), DNC (Distribution Numerical Control), WMS (Warehouse Management System), and SCADA (Supervisory Control and Data Acquisition), etc., the implementation method of personalized data display GUI is discussed as well. The study is based on the KMMES developed by Wuhan KM-Software of China, and it has been deployed in over forty companies from the sections of aerospace, automotive, shipbuilding and other industries.

The technological foundation of smart manufacturing consists of cyber-physical systems and the Internet-of-Things (IoT). Despite smart manufacturing has become a key paradigm to promote the integration of manufacturing processes using digital technologies, the manufacturing processes themselves are designed by human experts in a traditional way and have limited ability to adapt their behavior to exceptional circumstances. We leverage the fact that each IoT device in a smart factory can be coupled with a digital twin – that is, a software artefact that faithfully represents the physical system using real-time sensor data – to envision a software architecture to support adaptation of the manufacturing process when divergence from reference practices occur.

Healthcare providers generally spend excessive time on administrative tasks at the expense of direct patient care. The emergence of new artificial intelligence and natural language processing technologies gives rise to innovations that could relieve them of this burden. In this paper, we present a pipeline structure for building dialogue summarization systems. Our pipeline summarizes a consultation of a patient with a care provider and automatically generates a report compliant with medical formats. Four pipeline components are used to generate a report based on audio input. The outputs of each component are analyzed to determine the most important challenges and issues. The current proof-of-concept, which was applied to eight doctor-to-patient sessions concerning ear infection, shows that automatic dialogue summarization and reporting is achievable, but requires improvements to increase completeness.

Sustainable agriculture is crucial to society since it aims at supporting the world’s current food needs without compromising future generations. Recent developments in Smart Agriculture and Internet of Things have made possible the collection of unprecedented amounts of agricultural data with the goal of making agricultural processes better and more efficient, and thus supporting sustainable agriculture. These data coming from different types of IoT devices can also be combined with relevant information published in online social networks and on the Web in the form of textual documents. Our objective is to integrate such heterogeneous data into knowledge bases that can support farmers in their activities, and to present global, real-time and comprehensive information to researchers. Semantic technologies and linked data provide a possibility for data integration and for automatic information extraction. This paper aims to give a brief review on the current semantic web technology applications for agricultural corpus, then to discuss the limits and potentials in construction and maintenance of existing ontologies in agricultural domain.

This paper applies a smart tourism approach to tourist destination marketing campaigns through the analysis of tourists’ reviews from TripAdvisor to identify significant patterns in the data. The proposed method combines topic modelling using Structured Topic Analysis with sentiment polarity, information on culture, and purchasing power of tourists for the development of a Decision Tree (DT) to predict tourists’ experience. For data collection and analysis, several custom-made python scripts were used. Data underwent integration, cleansing, incomplete data processing, and imbalance data treatments prior to being analysed. The patterns that emerged from the DT are expressed in terms of rules that highlight variable combinations leading to negative or positive sentiment. The generated predictive model can be used by destination management to tailor marketing strategy by targeting tourists who are more likely to be satisfied at the destination according to their needs.

Digital technologies have impacted almost every aspect of our society, including how people participate in activities that matter to them. Indeed, digital participation allows people to be involved in different societal activities at an unprecedented scale through the use of Information and Communication Technologies (ICT). Still, enabling participation at scale requires making it seamless for people to: interact with a variety of software platforms, get information from connected physical objects and software services, and communicate and collaborate with their peers. Toward this objective, this paper introduces and formalizes the concept of Social Participation Network, which captures the diverse participation relationships – between people, digital services and connected things – supporting participatory processes. The paper further presents the early design of an associated online service to support the creation and management of Social Participation Networks. The design advocates the instantiation of Social Participation Networks within distinct participation contexts—spanning, e.g., private institutions, neighbor communities, and governmental institutions—so that the participants’ information and contributions to participation remain isolated and private within the given context.

There is an increasing interest in corporate sustainability and how companies should include it to satisfy user’s requirements concerning social, economic, and environmental impacts. Research about sustainability in computer science aims to offer methods, techniques and tools to lessen the impact of new technologies on the environment, to offer a better world, a smarter life, to the next generations. Information systems must participate in the collective effort to move towards sustainable development, and software and application companies must lead a CSR strategy to achieve this aim. Moreover, beyond an individual company approach, sustainability should be seen as an integral quality of any software (as well as safety, performance or reliability). All of this seem obvious at a time when applications and programs of all kinds are ubiquitous in everyday life. Nevertheless, the challenges of sustainable development have still not been considered in certain key sectors such as the development of information technology. A lot of ecolabels exist for a lot of different products, although not for software sustainability. We propose in this work an ecolabel for software sustainability, based on a set of relevant criteria found in different works.

This paper presents an exploratory approach for the governance of Society in the context of Smarter Life. By answering the challenges of the era of Digitalisation, facing profound societal changes, benefiting from multiple innovations, information systems and services play an outstanding role in improving and enhancing life of humans and contribute to the progress in Smarter Life. This exploratory approach is based on information, whilst information systems and services contribute to developing new practices, creating new situations, generating new added value. In this perspective, information and knowledge can be viewed as information common good, which is in the heart of service design. It is essential that services are designed in an exploratory way, by involving multidisciplinary, multi-institutional, even multi-national actors, whose active participation would lead to the development of new value-added services. This can be done thanks to a protected place adapted to co-construction of information services, Tiers-Lieu for Services (TLS). To assist the dynamics of the servitised Society and support its governing in a sustainable way, an institutional instrument, called people-public-private-partnerships for services (4PS), is presented.