Centrifugal pumps are an integral part of many industrial processes and are used extensively in water supply, sewage, heating and cooling systems. While there are several review papers on machine learning-based fault diagnosis on induction motors, its application to centrifugal pumps has received relatively little attention. This work attempts to summarize and review recent research and development in machine learning-based pump condition monitoring and fault diagnosis. The paper starts with a brief explanation of pump operation including common pump faults and the main principles of the motor current signature analysis (MCSA) method. This is followed by a detailed explanation of various machine learning-based methods including the types of detected faults, experimental details and reported accuracies. The performances of different approaches are then presented systematically in a unified table. Finally, the authors discuss practical aspects and challenges related to data collection, storage and real-world implementation.

In this paper, we report the findings from a one year deployment of an automated wildlife monitoring system for analyzing the social co-location patterns of European badgers (Meles meles) residing in a dense woodland environment.\ud \ud We describe the stages of its evolution cycle, from implementation, deployment and testing, to various iterations of software optimization, followed by hardware enhancements, which in turn triggered the need for further software optimization. We report preliminary descriptive analyses of a subset of the data collected, demonstrating the significant potential our system has to generate new insights into badger behavior. The main lessons learned were: the need to factor in the maintenance costs while designing the system; to look carefully at software and hardware interactions; the importance of a rapid initial prototype deployment (this was key to our success); and the need for continuous interaction with domain scientists which allows for unexpected optimizations

The increasing adoption of wireless sensor network technology in a variety of applications, from agricultural to volcanic monitoring, has demonstrated their ability to gather data with unprecedented sensing capabilities and deliver it to a remote user. However, a key issue remains how to maintain these sensor network deployments over increasingly prolonged deployments. In this article, we present the challenges that were faced in maintaining continual operation of an automated wildlife monitoring system over a one-year period. This system analyzed the social colocation patterns of European badgers ( Meles meles ) residing in a dense woodland environment using a hybrid RFID-WSN approach. We describe the stages of the evolutionary development, from implementation, deployment, and testing, to various iterations of software optimization, followed by hardware enhancements, which in turn triggered the need for further software optimization. We highlight the main lessons learned: the need to factor in the maintenance costs while designing the system; to consider carefully software and hardware interactions; the importance of rapid prototyping for initial deployment (this was key to our success); and the need for continuous interaction with domain scientists which allows for unexpected optimizations.

This paper investigates the transformative potential of Large Language Models (LLMs) within higher education, highlighting their capacity to reshape the academic landscape. By examining the complex impact of LLMs across critical areas of Higher Education Institutions (HEIs), including the role of HEIs as gatekeepers of knowledge, providers of credentials, research centres, incubators of innovation, drivers of social change and employers. In addition to academic integrity, the future of higher education, intellectual property, and public perception. The findings of this paper indicate that LLMs can empower transformation in HEIs by revolutionising various aspects of academia. The aim is to unveil the profound implications of integrating these cutting-edge technologies. The comprehensive study in this paper reveals the significant impacts and challenges associated with using LLMs in academic settings, which is achieved through a detailed analysis of current literature. The core findings suggest that LLMs hold the promise to trigger significant advancements in higher education. This paper also discusses the innovative potential of LLMs, and it outlines a path for their effective use in HEIs, emphasising the importance of a thoughtful approach to maximise their educational benefits. HEIs must address these challenges thoughtfully, ensuring that the integration of LLMs aligns with their fundamental objectives of promoting education, critical thinking, and personal growth.

The future of Internet of Things (IoT) envisions billions of sensors integrated with the physical environment. At the same time, recharging and replacing batteries on this infrastructure could result not only in high maintenance costs, but also large amounts of toxic waste due to the need to dispose of old batteries. Recently, battery-free sensor platforms have been developed that use supercapacitors as energy storage, promising maintenance-free and perpetual sensor operation. While prior work focused on supercapacitor characterization, modelling and supercapacitor-aware scheduling, the impact of mobility on capacitor charging and overall sensor application performance has been largely ignored. We show that supercapacitor size is critical for mobile system performance and that selecting an optimal value is not trivial: small capacitors charge quickly and enable the node to operate in low energy environments, but cannot support intensive tasks such as communication or reprogramming; increasing the capacitor size, on the other hand, enables the support for energy-intensive tasks, but may prevent the node from booting at all if the node navigates in a low energy area. The paper investigates this problem and proposes a hybrid storage solution that uses an adaptive learning algorithm to predict the amount of available ambient energy and dynamically switch between two capacitors depending on the environment. The evaluation based on extensive simulations and prototype measurements showed up to 40% and 80% improvement compared to a fixed-capacitor approach in terms of the amount of harvested energy and sensor coverage.