Abstract:

Increasing numbers of objects in our day life are controlledby computers: phones, aircraft, cars, buildings, manufac-turing machines, musical instruments, etc. In these so-called cyber-physical systems (CPSs), computers interactdirectly with the physical world through sensors and actua-tors. Those systems are becoming the key infrastructure andbackbone of our society and are at the heart of revolutionarychanges in our daily lives and economy. The sophisticationand complexity of CPSs keeps increasing, since they mustrealize more functions with limited resources, which makesthem increasingly difficult to build and manage. In partic-ular, the cyber (software) part of these systems is growingrapidly, and has become a key part in CPS, as they arethe basis of operation for these systems. Artificial intelli-gence (AI) has a fundamental influence on all areas of econ-omy, administration and society. AI is now also affectingsoftware engineering; providing robust approaches for soft-ware development in order to analyze and evaluate complexsoftware and its development processes. Repository mining,machine Learning, big data analytics and software visual-ization enable targeted insights and powerful predictions forsoftware quality, software development and software projectmanagement. The research community has shown a keeninterest in this emerging field. In this report, we presenta pre-organization summary of the workshop to be held onFebruary 2021, at KIT Bhubaneswar, co-located with the 14th Innovations in Software Engineering Conference (ISEC2021).

Keywords:
Software Engineering, AI, Big Data, Simulation, CPS

1. MOTIVATION AND OBJECTIVE

Software-intensive systems of today are dynamic, adap-tive, context-aware, large and dependable. Designing suchsoftware requires a new approach where the data-driven de-cisions have to be a part of the solution architecture. Tech-niques such as recommendation mechanism, path planning,prediction of operational failures and dealing with unsafeconditions are going to be a part of the solution itself. De-veloping complex software also has to be “smart.” There isa growing need to instill intelligence in the software devel-opment process. In order to understand the complex op-erational behavior of software, it is required to combinedata-driven machine learning approaches with traditionalprogram analysis. There is a need of the hour to com-bine data-driven machine intelligence with human intelli-gence (insights and domain knowledge) to effectively makethe software development (requirement, design, testing, de-ployment and operation management) intelligent. The re-search community has shown a keen interest in this emerg-ing field. ICSE is regularly organizing workshop like RAISE,and AAAI has hosted a similar workshop called “IntelligentSE”[1].

2. TARGETED AUDIENCE

This workshop aims at gathering researchers and practitioners addressing the challenges induced by the software aspects of AI, in order to identify synergy, common problems, solutions and visions for the future of this area. Strong interactions among participants will be favored to provide constructive feedback for accepted workshop papers and develop future collaborations and community building.

3. TOPICS AND SCHEDULE

The workshop is composed of three tracks which are:

• AI in Bioengineering
• SE in Cyber-Physical Systems
• AI in Education Technology

Since the workshop is being conducted in the online mode due to the COVID-19 pandemic, the workshop will be con-ducted in the seminar mode. A bunch of domain experts from industry and academia will be delivering invited talks on the following tracks. In each track there will be two speakers. Therefore in this workshops there are total six invited speakers. The detail theme of the tracks are given in the following subsection

3.1 Track 1: AI in Bio-engineering

Bio-CPS are considered to be an integration of computational elements within biological systems. In a sense, Bio-CPS can be compared to the Cyber-Physical systems, in which the challenge is to make biological systems working along with computer systems. In biological systems the complexity is required in order to make the system more stable. By contrast, in cyber systems engineering, the complexity needs to be avoided as far as it is possible because it can bring instabilities. However, cyber systems complexity, even not desired, stems from the numerous interactions between components. Consequently, the main concern in Bio-CPS design is how to make these two kinds of systems coupling together to perform a common task with a high level of confidence.

BioCPS have far-reaching applications in real-life. Some of them include revolutionizing the healthcare system, med-ical instrumentation, medical technologies, and modelling diseases, infections, and the human immuno-response.

3.2 Track 2: AI in Cyber-Physical

While machine learning is widely practiced in cognitive domains, such as NLP, computer vision, speech recognition, etc, its impact on cyber-physical systems is only recently being understood. An important hurdle towards the deploy-ment of machine learning in industrial systems is that ma-chine learning has developed in Computer Science, where as its applications in industrial domains require significant do-main knowledge in disciplines that are remote from Computer Science. On the other hand, a large arsenal of ready-to-use machine learning tools and libraries exist (including ones supported by standard industrial modeling platforms like MATLAB), and therefore the domain expert can be readily trained to use these tools and techniques for advancing their industrial processes and design (R&D) activities.

3.3 Session I: AI in Education

Education has been accepted as a project for social and political transformation, with the development of each individual not only for her economic gains, but also for building a just and humane society. It also needs to promote aware-ness and build agency for sustainable development and harmonious co-existence. Global policy documents such as the Education for All, Millennium Development Goals and the Sustainable Development Goals, emphasize universal education.

Poor investment in education results in poor quality of teacher education, and inadequate academic infrastructure. Teachers are unable and/or unwilling to provide support to the learning processes. In this context, digital technologies (aka Information and Communication Technologies, or ICT in short), are sometimes seen as a solution that can address curricular resource shortage, teacher shortage and teacher quality.

Applying both AI and CPS concepts in developing educational technologies can significantly improve these implementations and ensure efficiency. This is an up and coming field which includes the development of hardware and software facilitating both teaching and learning on various
scales. Radical new ideas and platforms are coming up ev-ery day and modelling the interactions between the humancomponent and the system can be effectively modeled usingAI and CPS concepts.

4. ORGANIZERS