Immunotherapy has emerged as a prominent approach in melanoma treatment, however a substantial number of patients do not respond effectively. This highlights the critical need to accurately predict immunotherapy responses for designing personalised treatment strategies. Current practices rely predominantly on clinical data and the expertise of oncologists; however, a deeper understanding of molecular interactions through tissue-based biomarkers offers a promising avenue for advancement. Whole-slide multiplex immunofluorescence (mIF) images enable detailed analysis of cells/tissues in their microenvironment, deepening insights into disease mechanisms. However, numerous channels, an extensive image size, and spatially dispersed information of mIF images pose analytical challenges, requiring advanced techniques to effectively learn these intricate features for optimal performance. In this study, we introduce a novel deep-learning framework, Channel Optimisation with Multi-Instance Learning (COMIL), specifically designed to classify whole-slide mIF images for predicting immunotherapy response in melanoma patients. The study demonstrates that a feature extraction method that models inter-channel relationships and captures complex interdependencies among multiple channels of mIF images enhances classification performance. Additionally, incorporating this method within an MIL framework, optimised at both the slide and instance levels, further improves the classification performance of whole-slide mIF images. Evaluated on mIF images from the Melanoma Institute Australia showed that COMIL outperformed the baseline methods, underscoring its potential in the prediction of the immunotherapy response.  

Next-generation communication systems operating in the mm-Wave and sub-THz bands face high path loss, which can be mitigated by ultra-massive antenna arrays. However, high-resolution quantization in these systems is often impractical, leading to a growing interest in low-resolution, particularly 1-bit ADCs. This letter addresses joint angle and range estimation using 1-bit massive uniform linear arrays (ULA) in narrowband near-field systems. We propose a MUSIC-based 1-bit joint angle-range estimation algorithm (JARE-MUSIC) over a near-field narrowband channel, thus, demonstrating that existing MUSIC-based methods can be adapted for effective near-field localization even under extreme quantization.

Human Activity Recognition (HAR) using radar signals has gained significant attention due to its non-intrusive nature and robustness in various environments. However, the impact of radar signal preprocessing techniques on the performance of deep learning (DL) models remains an active area of research. This study investigates how different radar domain representations affect HAR accuracy by evaluating four preprocessing methods: Time-Range (TR) maps generated via Range-Fast Fourier Transform (FFT), Range-Doppler (RD) maps obtained through sequential FFTs, and Time-Doppler (TD) features extracted using Short Time Fourier Transform (STFT) and Smoothed Pseudo Wigner Ville Distribution (SPWVD). We employ a baseline Convolutional Neural Network (CNN) and state-of-the-art Transfer Learning (TL) models to assess whether advanced preprocessing or increased model complexity yields greater performance gains. The results reveal that high-resolution TD analysis using SPWVD does not significantly enhance classification performance and incurs substantial computational overhead, limiting its realtime applicability. Conversely, the TR representation offers computational efficiency but struggles to classify complex activities with the baseline CNN accurately. RD and STFT methods provide a favourable balance between classification accuracy and computational efficiency. Notably, transitioning from the baseline CNN to TL models leads to substantial improvements in recognition accuracy: up to 29.36% for TR, 21.42% for RD, 16.66% for STFT, and 11.11% for SPWVD representations. Overall, our findings demonstrate that TL models, when combined with computationally efficient radar preprocessing techniques like RD or STFT, significantly improve recognition accuracy, offering a practical solution for real-time HAR systems.

Cardiac surgery is a critical intervention for many individuals, yet postoperative recovery poses significant challenges, especially for patients in rural or underserved areas. These challenges include access to healthcare facilities, socioeconomic barriers, low patient compliance with rehabilitation protocols, and many more. Current solutions do demonstrate promise, such as Enhanced Recovery After Surgery (ERAS) protocols, but are difficult to implement due to resource constraints and patient-specific factors. This paper proposes a novel technology-driven solution that integrates ubiquitous computing, machine learning techniques, cloud computing, and mobile/web based applications to enhance post cardiac surgery recovery. The wearable device monitors physiological parameters such as heart rate, respiration rate, and body temperature, while the app provides real-time feedback on physical therapy exercises using machine learning algorithms. Additional features include medication reminders, interactive therapy instructions, and remote communication with healthcare professionals via a dashboard and video call functionality. This solution addresses access disparities, boosts patient compliance, and minimizes financial and logistical burdens, thereby addressing common challenges with post surgery recovery and improving the whole process.

The demand for lithium-ion batteries has grown rapidly, driven by the global shift toward renewable energy, electric vehicles (EVs), and energy storage systems. In 2023, the global market for LIBs exceeded $100 billion, with a projected compound annual growth rate (CAGR) of 18% through 2030[1, 2]. Despite these economic benefits, LIB manufacturing poses environmental and economic challenges. One of the most pressing issues is the generation of waste during production, which includes defective electrodes, electrolyte residues, separator materials, and packaging.

Solid-state batteries (SSBs) represent a transformative leap in energy storage, offering significant advantages in safety, energy density, and environmental impact compared to conventional lithium-ion batteries (LIBs). However, the high costs and complex manufacturing processes of SSBs hinder their large-scale adoption. This research evaluates cost-reduction strategies and efficiency enhancements in the production of SSBs, focusing on roll-to-roll (R2R) processing. Key innovations include the integration of infrared (IR) drying systems and automated start/stop control mechanisms, combined with iterative machine calibration for quality control. The results demonstrate energy savings of ~50%, processing speed improvements of 20-50%, and manufacturing cost reductions of ~20%. These findings contribute to the broader adoption of SSB technology, paving the way for a sustainable energy future.

The integration of Artificial Intelligence (AI) and the Internet of Things (IoT) is fundamentally transforming maintenance practices in manufacturing, shifting the paradigm from reactive and preventive approaches to predictive maintenance (PdM) (Deloitte, 2017). PdM utilizes real-time data collected from IoT-enabled devices to predict potential equipment failures before they occur, allowing for timely interventions that minimize unplanned downtime and optimize maintenance schedules (Upkeep, 2023). Research by Deloitte highlights that predictive maintenance can reduce maintenance costs by up to 40%, improve equipment reliability by 30–50%, and decrease equipment downtime by 50% (2017). Additionally, IoT sensors monitor key metrics such as vibration, temperature, pressure, and operational speed, generating valuable datasets for AI algorithms to analyze. These algorithms, often leveraging machine learning, identify failure patterns and forecast future equipment performance, enabling manufacturers to make informed, proactive decisions (Upkeep, 2023).

BPM has become crucial in organizations to facilitate the management of elaborate processes within the firms, and the application of AI in business has assist with robust agenda in areas of business processes management with improving competitiveness. The role of AI in BPM is a subject of interest in this paper with specific attention paid to the fact that it can significantly expand the contours of BPM by rendering it work and resource efficient, and capable of realtime decision-making. The quantitative review of AI-BPM solutions features process mining, predictive analytics, natural language processing, and machine learning. By providing examples with real-world cases and examples this study shows how deficiencies of traditional BPM can be addressed through the use of AI. Furthermore, the paper outlines the issues and concerns with integrating AI in an organization, technical, ethical and organizational risks, and recommendations for proper integration of AI as part of innovations. Through analyzing the most recent findings and future developments regarding the application of AI in BPM, this study emphasizes the opportunities that AI can bring to the process, providing practical recommendations for enhancing BPM through AI for organizations interested in integrating AI into process management for effective and efficient long-term performance.

In this paper, our objective is to show our contribution to the development of a new Positron Emission Tomography (PET) system to reduce its impact on patients. This study was conducted as part of the RETIREX project. PET is a diagnostic system based on functional imaging that uses radioactive substances to visualize and measure the changes in different metabolic processes. There is a constant push to reduce both the radioactive dose injected into the patient and duration of the PET scan. Achieving these and providing real-time images require an innovative imaging principle. In this paper, we present our contribution to an architecture based on a new 3-photon gamma imaging PET scanner with a Liquid Xenon camera. In this project, we aim to define a new architecture for a high-throughput hardware event builder and its integration into the final PET scanner named XEMIS3 (Xenon Medical Imaging System).

This research delves into the complex relationship between Urban Green Spaces (UGS) and crime rates in four distinct U.S. cities: Orlando, Baltimore, Cincinnati, and Sacramento. Debates surrounding this correlation range from the belief that increased vegetation leads to heightened crime to the contrary perspective. Our study challenges the common assumption that more greenery equates to reduced crime, revealing nuanced and diverse patterns in the examined cities. Employing a comprehensive approach, we integrate crime data from the Federal Bureau of Investigation with satellite imagery classification using a Convolutional Neural Network (CNN). The methodology encompasses pre-processing Landsat imagery, generating spectral indices, and training the CNN for green coverage pixel classification. Acknowledging limitations such as image classification challenges, absence of multivariate analysis, spatial resolution constraints, and crime reporting biases, we underscore the necessity for future research refinements. This study prompts a reassessment of assumptions and underscores the significance of considering multiple variables to attain a thorough understanding of the intricate interplay between urban greenery and crime rates.

This article reviews recent studies on deep learningbased (DL-based) techniques for integrated sensing and communication (ISAC) systems. Both sensing and communication functions are necessary for many cutting-edge systems, such as robotics, autonomous driving, and unmanned air vehicles (UAVs). Designing a single platform providing both sensing and communication functions will reduce hardware usage and spectrum congestion while improving the system's energy efficiency. Combining both functions on the same hardware may result in some challenges that can be efficiently solved via DL-based techniques within limited hardware resources. DLbased techniques can effectively produce near-optimum solutions for waveform design, channel estimation, processing sensing data, data demodulation, eliminating interference, and many other challenges encountered in ISAC systems. Because of the advantages of deep learning, recent studies have focused on developing DL-based techniques in ISAC systems. This article aims to explore the state-of-the-art advancements in this area. It reviews the state-of-the-art DL-based techniques developed to overcome the challenges encountered in ISAC system design and development. Moreover, it presents open research problems and a list of future research topics.

In practical engineering tasks, multi-objective topology optimization (TO) problems often arise, thus requiring the introduction of the concept of Pareto-optimal solutions. In this article, a novel gradient-informed Pareto-based multi-objective TO algorithm with binary decision variables, called GPBTO, is proposed. Without loss of generality, GPBTO is tailored to solving constrained bi-objective optimization problems (CBOPs), which represents a standard case in many engineering applications. The binary space of the decision variables together with a linearization step of objectives and constraints allows efficient integer linear programming (ILP) techniques to be used for the evolution of the decision vector. The proposed algorithm represents an effective tool for solving the TO task with traditional gradient-based formulations bypassing the limitations of weighted sum (WS) approaches usually adopted in this context. Thanks to the simple implementation, the proposed GPBTO algorithm can be readily adopted for solving multi-objective TO problems involving binary decision variables. While WS is an out-of-date technology for solving multi-objective optimization problems due to its limitations, it is well-known that in the framework of TO is still the state of the art. To the author's knowledge, this is the first time that an attempt to solve Pareto-based TO with binary variables and gradients has been proposed.

The integration of intermittent renewables presents significant challenges for power system operators. Sub-hourly Unit Commitment (UC) has been suggested to quickly respond to electricity supply and demand changes. It, however, poses greater complexity than hourly UC because of increased temporal resolution and complicated inter-period dependencies. Machine Learning (ML) holds high expectations for solving sub-hourly UC, but it may still face challenges in requiring heavy training burden, learning vast combinatorial possibility, and struggling to ensure feasibility. To this end, this paper presents a novel learning-tooptimize approach that synergistically combines ML with decomposition frameworks. Our approach adopts the Surrogate Absolute-Value Lagrangian Relaxation (SAVLR) framework since its decomposition leads to easier learning by drastically reducing combinatorial complexity. Then, a generic ML model embedding Gated Recurrent Units (GRUs) and Attention in the encoder-decoder structure is developed to efficiently predict subproblem solutions. The features of GRUs and Attention allows the model to capture temporal dependencies and reduce training effort across varying subproblems. Additionally, a rule-based feasibility layer is incorporated to improve feasibility w.r.t unitlevel constraints. The effectiveness of our approach is demonstrated on the IEEE 118-bus system.

This paper presents a wireless power transfer (WPT) for a mid-sized inspection mobile robot. The objective is to transmit 100 W of power over 1 meter of distance, achieved through lightweight Litz wire coils weighing 320 g held together with a coil structure of 3.54 kg. The Wireless Power Transfer System (WPTS) is mounted onto an unmanned ground vehicle (UGV). The study addresses an investigation of coil design, accounting for misalignment and tolerance issues in resonancecoupled coils. In experimental validation, the system effectively transmits 109.7 W of power over a 1-meter distance, with obstacles present. This achievement yields a system efficiency of 47.14%, a value that is remarkably close to the maximum power transfer point (50%) when the WPTS utilises the full voltage allowance of the capacitor. The paper shows the WPTS charging speed of 5 minutes for 12 V, 0.8 Ah lead acid batteries.

This paper investigates the effects of self-inductance and mutual inductance on saggy coil magnetic resonant inductive coupling power transmission (IPT). The simulation of the saggy coil is conducted using a specialist tool called IPTVisual to visualise the phenomenon of saggy winding in the system. The results provide important intuitions for optimising saggy coil inductive coupling devices for better performance and reliability in a variety of applications. The setup of simulations and experimental shows a slight difference. The mutual inductance and coupling coefficient of two saggy coils are analysed and discussed. There is a difference of 1.74% in self-inductance in saggy coil with two fixed mounting point of 1 m distance when comparison is made between simulation and experimental results.

Quantum Computing is revolutionary paradigm that harnesses the principles of quantum mechanics such as superposition and entanglement to process the information in fundamentally new ways. It has shown potential across various fields, including Cryptography, Materials Science, Machine Learning, Optimization and many others. Among its many applications, Combinatorial Optimization problems stand out as a critical area where Quantum Computing can address problems that are often intractable for classical methods. This paper surveys current quantum approaches including Quantum Annealing, Variational Algorithms, Quantum Approximation Optimization Algorithm (QAOA) and asses their effectiveness in solving Classical Intractable Combinatorial Optimization (CICO) problems such as Max Cut Problem, Traveling Salesman Problem, Graph Coloring and Knapsack Problems. The paper explores the QAOA, approach to solve the CICO problems. Practical applications of quantum optimization approaches are highlighted in the fields such as finance, material science, communication networks. Additionally, the case studies demonstrate the algorithm's efficacy in real world scenarios. However, the paper also discusses the challenges that remain including issues related to noise, scalability and complexity of the algorithms. Finally, the survey discusses the future directions for research, emphasizing the potential of hybrid-quantum classical frameworks and the development of new quantum algorithms, aiming to enhance the practical applications in complex optimization scenarios. This survey provides valuable insights for researchers and practitioners interested in leveraging quantum advantages to solve combinatorial optimization problems effectively.

The use of quantum cryptography in everyday applications has gained attention in both industrial and academic fields. Due to advancements in quantum electronics, practical quantum devices are already available in the market, and ready for wider use. Quantum Key Distribution (QKD) is a crucial aspect of quantum cryptography, which involves generating and distributing symmetric cryptographic keys between geographically separated users using principles of quantum physics. Many successful QKD networks have been established to test different solutions. The objective of this paper is to delve into the potential of utilizing established routing design techniques in the context of quantum key distribution, a field distinguished by its unique properties rooted in the principles of quantum mechanics. However, the implementation of these techniques poses substantial challenges, including quantum memory decoherence, key rate generation, latency delays, inherent noise in quantum systems, limited communication ranges, and the necessity for highly specialized hardware. This paper conducts an in-depth examination of essential research pertaining to the design methodologies for quantum key distribution. It also explores the fundamental aspects of quantum routing and the associated properties inherent to quantum QKD. This paper elucidates the necessary steps for constructing efficient and resilient QKD networks. In summarizing the techniques relevant to QKD networking and routing, including their underlying principles, protocols, and challenges, this paper sheds light on potential applications and delineates future research directions in this burgeoning field.

Over the course of the last five decades, there has been substantial growth in conventional network routing design, transitioning from small static node networks to vast systems connecting billions of devices. This evolution has been facilitated by the separation of concerns principle, which involves integrating network functionalities into graph or random network designs and utilizing specific protocols to enable diverse communication capabilities. The landscape of quantum networks is rapidly evolving, presenting new paradigms in information transmission and processing. Routing protocols play a pivotal role in establishing efficient communication pathways within quantum networks, enabling the transmission of quantum states and entanglement across interconnected nodes. The objective of this paper is to shed light on existing entanglement routing design techniques within quantum networks. The design of quantum entanglement routing necessitates a departure from conventional network protocols due to its unique considerations of quantum entanglement and entanglement swapping. However, the implementation of these techniques is fraught with significant challenges, including quantum system decoherence and noise, limitations on communication ranges, and the need for specialized hardware. The paper initiates by surveying critical research in quantum routing design techniques, then delves into essential aspects of the routing concept, associated quantum operations, and the step-wise process for establishing efficient and resilient quantum networks. In summary, this paper provides an overview of the current landscape of quantum entanglement routing techniques. It outlines their core principles, protocols, and challenges, while also highlighting potential applications and charting future directions for research and development.