特刊征稿内容：
Since the term “smart environment” was coined in the late 1980s, there has been an increase in the amount of interest and effort in various smart environmental scenarios. For example, the early definition of smart homes derived from home automation terminology in 1992, while the term smart city emerged in the literature in 1998 and derived from urban simulations and different knowledge bases. Nowadays, along with the evolution of technology, the Internet of Things (IoT) and machine learning (ML) increasingly play a crucial and combined role in achieving all kinds of data-centric smart environments. However, such enabling technologies also bring challenges to smart environments involved in large-scale data collection, analysis, and decision-making processes. Three typical challenges are as follows:
- Individual IoT devices generally have limited computation, storage, and network capabilities (e.g., the embedded RAM has only 4 KB in the current taxi-mounted GPS devices). Consequently, the heavy computation overhead makes conventional ML techniques impractical due to the resource constraints of IoT devices.
- An IoT system may involve the non-scalable integration of heterogeneous technologies produced by different manufacturers; thus, there is not a one-size-fits-all solution for ML implementations in smart environments.
- The distributed, diverse, and uncertain end-user situations of an IoT system would face more data privacy, security, and ethical risks from nefarious attacks within smart environments.
To address these challenges, following the software-driven trend in making computing environments programmable and software defined, smart environments should also pay more attention to software with significant heterogeneity and diversity in IoT technologies. In fact, despite the widely recognised and possibly overemphasised aspects of hardware, it is software that eventually makes an environment smart. Inspired by the well-known “mind/brain” metaphor, users essentially rely on software applications to communicate and work with smart devices and objects around them.
By considering the privacy-friendly paradigm of federated learning, we propose this Special Issue on Software-driven Federated Learning for/in Smart Environments. This Special Issue aims to bring together professionals from academia and industry to explore the latest experiences, advancements, challenges, methods, techniques, and solutions related to the engineering of federated learning systems for/in smart environments. Thus, we invite researchers, practitioners, and industry experts to submit their original contributions that cover the conjoint area of software engineering, federated learning, and smart environments, including, but not limited to, the following:
Software architectures and design patterns for constructing smart environments;
Evidential assessments on the rigor, effectiveness, and relevance of a variety of software technologies in any specific smart environment (e.g., smart city, office, home, etc.);
Empirical case studies on federated learning implementation in/for smart environments;
Experiences in building federated learning systems to enable smart environments;
Challenges and lessons learned from adopting federated learning in/for software-driven smart environments;
Negative results highlighting the areas where future studies are needed for building smart environments.
喊姐姐～给糖吃
