A paradigm shift is underway in Software Engineering, with AI systems such as LLMs playing an increasingly important role in boosting software development productivity. This trend is anticipated to persist. In the next years, we expect a growing symbiotic partnership between human software developers and AI. The Software Engineering research community cannot afford to overlook this trend; we must address the key research challenges posed by the integration of AI into the software development process. In this article, we present our vision of the future of software development in an AI-driven world and explore the key challenges that our research community should address to realize this vision.

Cyber-Physical Systems (CPSs) are implemented in many industrial and embedded control applications. Where these systems are safety-critical, correct and safe behaviour is of paramount importance. Malicious attacks on such CPSs can have far-reaching repercussions. For instance, if elements of a power grid behave erratically, physical damage and loss of life could occur. Currently, there is a trend towards increased complexity and connectivity of CPS. However, as this occurs, the potential attack vectors for these systems grow in number, increasing the risk that a given controller might become compromised. In this work, we examine how the dangers of compromised controllers can be mitigated. We propose a novel application of runtime enforcement which can secure the safety of real-world physical systems. Here, we synthesize enforcers to a new hardware architecture within PLC I/O modules to act as an effective line of defence between the cyber and the physical domains. Our enforcers prevent the physical damage that a compromised control system might be able to perform. To demonstrate the efficacy of our approach, we present several benchmarks, and show that the overhead for each system is extremely minimal.

Background: Mood disorders are commonly underrecognized and undertreated, as diagnosis is reliant on self-reporting and clinical assessments that are often not timely. Speech characteristics of those with mood disorders differs from healthy individuals. With the wide use of smartphones, and the emergence of machine learning approaches, smartphones can be used to monitor speech patterns to help the diagnosis and monitoring of mood disorders. Objective: The aim of this review is to synthesize research on using speech patterns from smartphones to diagnose and monitor mood disorders. Methods: Literature searches of major databases, Medline, PsycInfo, EMBASE, and CINAHL, initially identified 832 relevant articles using the search terms “mood disorders”, “smartphone”, “voice analysis”, and their variants. Only 13 studies met inclusion criteria: use of a smartphone for capturing voice data, focus on diagnosing or monitoring a mood disorder(s), clinical populations recruited prospectively, and in the English language only. Articles were assessed by 2 reviewers, and data extracted included data type, classifiers used, methods of capture, and study results. Studies were analyzed using a narrative synthesis approach. Results: Studies showed that voice data alone had reasonable accuracy in predicting mood states and mood fluctuations based on objectively monitored speech patterns. While a fusion of different sensor modalities revealed the highest accuracy (97.4%), nearly 80% of included studies were pilot trials or feasibility studies without control groups and had small sample sizes ranging from 1 to 73 participants. Studies were also carried out over short or varying timeframes and had significant heterogeneity of methods in terms of the types of audio data captured, environmental contexts, classifiers, and measures to control for privacy and ambient noise. Conclusions: Approaches that allow smartphone-based monitoring of speech patterns in mood disorders are rapidly growing. The current body of evidence supports the value of speech patterns to monitor, classify, and predict mood states in real time. However, many challenges remain around the robustness, cost-effectiveness, and acceptability of such an approach and further work is required to build on current research and reduce heterogeneity of methodologies as well as clinical evaluation of the benefits and risks of such approaches.

Objective: Evaluating and testing cardiac electrical devices in a closed-physiologic-loop can help design safety, but this is rarely practical or comprehensive. Furthermore, in-silico closed-loop testing with biophysical computer models cannot meet the requirements of time-critical cardiac device systems, while simplified models meeting time-critical requirements may not have the necessary dynamic features. We propose a new high-level (abstracted) physiologically-based computational heart model that is time-critical and dynamic. Methods: The model comprises cardiac regional cellular-electrophysiology types connected by a path model along a conduction network. The regional electrophysiology and paths are modeled with hybrid automata that capture non-linear dynamics, such as action potential and conduction velocity restitution and overdrive suppression. The hierarchy of pacemaker functions is incorporated to generate sinus rhythms, while abnormal automaticity can be introduced to form a variety of arrhythmias such as escape ectopic rhythms. Model parameters are calibrated using experimental data and prior model simulations. Conclusion: Regional electrophysiology and paths in the model match human action potentials, dynamic behavior and cardiac activation sequences. Connected in closed-loop with a pacing device in DDD mode, the model generates complex arrhythmia such as atrioventricular nodal reentry tachycardia. Such device-induced outcomes have been observed clinically and we can establish the key physiological features of the heart model that influence the device operation. Significance: These findings demonstrate how an abstract heart model can be used for device validation and to design personalized treatment.

Rear-end collision avoidance relies on mathematical models to calculate the safety distance. Vehicle deceleration is a key parameter for the accuracy of the models. Current models, however, assume a constant deceleration during braking, which is unrealistic. This assumption results in large over-approximation / under-approximation. In this paper, we rectify this limitation by proposing a new model that accounts for realistic vehicle deceleration during braking. Simulation results show that our approach guarantees safety. Moreover, traffic flow is improved by 21.6% compared to the widely adopted the Berkeley algorithm.

In the modelling of distributed systems, most Models of Computation (MoCs) rely on blocking communication to preserve determinism. A prominent example is Kahn Process Networks (KPNs), which supports non-blocking writes and blocking reads, and its implementable variant Finite FIFO Platforms (FFPs) which enforces boundedness using blocking writes. An issue with these models is that they mix process synchronisation with process execution, necessitating frequent blocking during synchronisation. This paper explores a recent alternative called bittide , which decouples the execution of a process from the synchronisation behaviour. Determinism and boundedness is preserved while enabling pipelined execution for better throughput. To understand the behaviour of these systems we define a formal model – a deterministic MoC called Logical Synchrony Networks (LSNs). LSNs describes a network of processes modelled as a graph, with edges representing invariant logical delays between a producer process and the corresponding consumer process. We show that this abstraction is satisfied by the KPN model, and subsequently by both the concrete FFPs and bittide architectures. Thus, we show that FFPs and bittide offer two ways of implementing deterministic distributed systems, with the latter being more performant.