Data generated from sources such as wearable sensors, medical imaging, personal health records, pathology records, and public health organizations have resulted in a massive information increase in the medical sciences over the last decade. Advances in computational hardware, such as cloud computing, Graphical Processing Units (GPUs), and Tensor Processing Units (TPUs), provide the means to utilize these data. Consequently, many Artificial Intelligence (AI)-based methods have been developed to infer from large healthcare data. Here, we present an overview of recent progress in artificial intelligence and biosensors in medical and life sciences. We discuss the role of machine learning in medical imaging, precision medicine, and biosensors for the Internet of Things (IoT). We review the most recent advancements in wearable biosensing technologies that use AI to assist in monitoring bodily electro-physiological and electro-chemical signals and disease diagnosis, demonstrating the trend towards personalized medicine with highly effective, inexpensive, and precise point-of-care treatment. Furthermore, an overview of the advances in computing technologies, such as accelerated artificial intelligence, edge computing, and federated learning for medical data, are also documented. Finally, we investigate challenges in data-driven AI approaches, the potential issues that biosensors and IoT-based healthcare generate, and the distribution shifts that occur among different data modalities, concluding with an overview of future prospects.

The sizing of microgrids depends on the type of load and its operational hours. The significance of understanding the load operational characteristics in special purpose islanded microgrids is much needed for economic system sizing. The load operation of special-purpose microgrids often consumes high power for a short duration and remains idle most of the time, thus reducing the load factor. The inclusion of such loads in microgrid sizing causes huge capital costs making islanded microgrids an unfeasible solution. The islanded microgrid under study is an agricultural microgrid in a village having a small Crab Processing Plant (CPP) and a Domestic Sector (DS). The CPP constitutes the major power consumption. The community has a unique load consumption trend that is dependent on the highly uncertain parameter of availability of the crabs. Interestingly, crab availability is an independent parameter and cannot be accurately scheduled. The existing system sizing of the microgrid is performed based on the conventional methods that consider the CPP for full-day operation. However, the microgrid sources, especially the storage system may be reflected as oversized if the crab processing plants do not operate for several days due to the uncertain behavior of CPP causing enormous power wastage. In this paper, an integrated fixed and operational mode strategy for uncertain heavy loads is formulated. The proposed algorithm is based on the optimal sizing methodology aided by the load scheduling control strategy. The Particle Swarm Optimization technique is used for the optimal sizing integrated with the fuzzy logic controller to manage the available load. The membership functions are available excess power and the state of the charge of storage that defines the operational conditions for CPP. Based on input membership functions, the fuzzy controller decides on power dispatch in DS or CPP, keeping considerable SoC available for night hours. The simulation result shows that the time-dependent fuzzy controller approach manages to provide power to both sectors under optimal sizing while reducing the overall cost by 24% less than the existing microgrid.

This study proposes an integrated control–optimization framework for harmonic mitigation in two-level, grid-connected inverters with battery energy storage operating under unbalanced grid conditions. A proportional–resonant controller in the stationary $\alpha \beta$ frame and a proportional–integral controller in the synchronous $dq$ frame are compared, with controller gains optimized using PSO, GA, and a hybrid PSO–GA approach. The hybrid method achieves superior trade-offs among THD, convergence speed, and computational effort. For the PR controller, hybrid PSO–GA reduces THD to 1.07%, satisfying IEEE 1547 and IEC 61727 standards, while for the PI controller it achieves 2.70%, outperforming standalone PSO (4.12%) and GA (3.38%). The hybrid-optimized gains further minimize tracking error indices (IAE, ISE, ITAE, ITSE), ensuring precise steady-state current regulation. Convergence analysis shows that hybrid PSO–GA attains optimal solutions within three iterations for both controllers, faster than GA and comparable to PSO for the PR case. Simulation studies on the IEEE 13-bus unbalanced feeder in DIgSILENT PowerFactory validate the proposed framework. Results confirm that the PR controller delivers a 60.36% THD reduction and tenfold ISE improvement over the optimized PI design, establishing a robust and scalable solution for harmonic suppression in unbalanced grid-tied energy systems.

Sliding mode control (SMC) has emerged as a robust and adaptive strategy for grid-tied inverters. It has unique attributes which make it an appropriate control choice under increasingly complex power systems. However, there are a limited number of review articles which comprehensively explore the true potential of SMC for grid-tied inverter applications. This systematic review has been structured to explore SMC techniques with respect to certain challenges, i.e., stability challenges, unbalanced conditions, low inertia scenarios, and harmonics distortion. The classification of various SMC techniques is presented with respect to their control law and sliding surfaces design. The comparative analysis indicates the dominance of artificial intelligence (AI)-assisted control systems, which represent a paradigm shift in modern-era control systems. Key performance matrices, i.e., total harmonics distortion (THD) reduction, tracking accuracy, and response time, etc. are compared across various SMC techniques. Moreover, this review identifies possible research gaps regarding the conceptual integration of quantum computing with SMC. Furthermore, several future directions are presented in this article to make SMC more robust and reliable for the next generation of AI-dominated grid-tied inverter applications.

The cathode material design is a persistent challenge in the development of next-generation rechargeable batteries. The cathode performance is critically influenced by certain key parameters, i.e., composition, crystal structures, ion transport, and degradation behaviour. Moreover, techno-economic and sustainable considerations also play a pivotal role in the viable cathode material design. In recent years, the integration of static machine learning models with conventional experimental techniques has significantly enhanced the cathode material design. However, the sequential nature of cathode discovery has not been fully captured by these techniques as they do not update their decision strategy based on prior outcomes. In this review, reinforcement learning (RL) as a decision making technique for cathode material design has been evaluated. Firstly, cathode design space, including major cathode families, optimisation objectives, and key material variables have been explored. Afterwards, cathode discovery has been presented in terms of RL states, actions, rewards, policies, environments, constraints, and feedback. The key focus of this review is to analyse how RL can support the composition selection, dopant, and crystal structure optimisation. The review also discusses the current limitations of RL based cathode design including data scarcity, dataset bias, limited cathode specific benchmarks, reward function design, physical validity, and experimental validations. The future directions have been proposed for physics informed and experimentally validated RL infrastructure that integrates the density functional theory, molecular dynamics, artificial intelligence and human expertise.