Flood detection networks often fail when fixed infrastructure such as gateways or cellular towers is damaged. Multi-agent systems (MAS) operating over ad hoc peer-to-peer networks offer a resilient alternative by enabling sensors to self-organize, reroute data, and forward alerts cooperatively. This work simulates and compares two MAS organizational models for IoT-based flood monitoring: Flat MAS and Federated MAS. Flat MAS rely on peer-to-peer communication, allowing sensors to exchange acknowledgments and reroute messages through neighbors during connectivity loss. Federated MAS use selected gateways to coordinate clusters and maintain inter-gateway failover links, improving system continuity. Results show that Flat MAS respond faster under partial failure, while Federated MAS achieve higher delivery success and recover more effectively from gateway outages.

Connected and autonomous vehicles across land, water, and air must often operate in dynamic, unpredictable environments with limited communication, no centralized control, and partial observability. These real-world constraints pose significant challenges for coordination, particularly when vehicles pursue individual objectives. To address this, we propose a decentralized Multi-Agent Reinforcement Learning (MARL) framework that enables vehicles, acting as agents, to communicate selectively based on local goals and observations. This goal-aware communication strategy allows agents to share only relevant information, enhancing collaboration while respecting visibility limitations. We validate our approach in complex multi-agent navigation tasks featuring obstacles and dynamic agent populations. Results show that our method significantly improves task success rates and reduces time-to-goal compared to non-cooperative baselines. Moreover, task performance remains stable as the number of agents increases, demonstrating scalability. These findings highlight the potential of decentralized, goal-driven MARL to support effective coordination in realistic multi-vehicle systems operating across diverse domains.

Timely and coordinated flood response is often hindered by fragmented data and delayed situational awareness. This paper presents a multi-agent system (MAS) that integrates geolocated social media posts and IoT sensor data to enable dynamic and high-confidence flood detection and alerting. Each agent is responsible for a specific function, including filtering noisy tweets, validating water level readings, and clustering incident reports. In a simulated urban flood scenario, the system significantly improved event coverage, reduced response time, and lowered false alarms by validating information across multiple sources. These results highlight the potential of intelligent agent collaboration to enhance real-time disaster monitoring and response.

This study investigates the effect of sampling techniques on cancer type classification across five categories: breast, kidney, colon, lung, and prostate. We evaluate the impact of three sampling strategies: (i) Simple Random Oversampling/Undersampling, (ii) Stratified Random Sampling, and (iii) Synthetic Minority Oversampling Technique (SMOTE) on the performance of seven different machine learning models. Results show that incorporating sampling noticeably improves model performance, with SMOTE achieving the highest gains. On average, sampling improved F1 scores by 11.44%, highlighting its critical role in addressing class imbalance in medical datasets. These findings provide a practical and reproducible approach to mitigate data imbalance in biomedical machine learning workflows.

Deep Reinforcement Learning (DRL) has become a critical approach for Object Tracking (OT) due to its ability to handle the sequential decision-making processes inherent in tracking tasks. By iteratively refining predictions and adapting to changes in object appearance or motion, DRL-based methods offer robust performance in complex tracking scenarios. However, most existing DRL-based OT methods have primarily focused on algorithmic framework design, often overlooking the optimization of configurations, such as action space, state space, reward function, and DRL algorithm. This oversight is significant, as optimal configuration choices can enhance DRL framework performance by up to 64%. Addressing this gap, our study investigates the impact of various configuration setups on the performance of DRL-based systems, specifically for Single Object Tracking (SOT) with a fixed camera view. Through theoretical analyses and experimentation, we demonstrate that appropriate configurations can improve tracking precision and system adaptability. The insights from this study provide a foundational guide for optimizing DRL applications in SOT with a fixed camera view, paving the way for more robust and efficient implementations in practical scenarios.

Object Tracking is essential for many computer vision applications, such as autonomous navigation, surveillance, and robotics. Unlike Passive Object Tracking (POT), which relies on static camera viewpoints to detect and track objects across consecutive frames, Active Object Tracking (AOT) requires a controller agent to actively adjust its viewpoint to maintain visual contact with a moving target in complex environments. Existing AOT solutions are predominantly single-agent-based, which struggle in dynamic and complex scenarios due to limited information gathering and processing capabilities, often resulting in suboptimal decision-making. Alleviating these limitations necessitates the development of a multi-agent system where different agents perform distinct roles and collaborate to enhance learning and robustness in dynamic and complex environments. Although some multi-agent approaches exist for AOT, they typically rely on external auxiliary agents, which require additional devices, making them costly. In contrast, we introduce the Collaborative System for Active Object Tracking (CSAOT), a method that leverages multi-agent deep reinforcement learning (MADRL) and a Mixture of Experts (MoE) framework to enable multiple agents to operate on a single device, thereby improving tracking performance and reducing costs. Our approach enhances robustness against occlusions and rapid motion while optimizing camera movements to extend tracking duration. We validated the effectiveness of CSAOT on various interactive maps with dynamic and stationary obstacles.

Software engineers are increasingly adding semantic search capabilities to applications using a strategy known as Retrieval Augmented Generation (RAG). A RAG system involves finding documents that semantically match a query and then passing the documents to a large language model (LLM) such as ChatGPT to extract the right answer using an LLM. RAG systems aim to: a) reduce the problem of hallucinated responses from LLMs, b) link sources/references to generated responses, and c) remove the need for annotating documents with meta-data. However, RAG systems suffer from limitations inherent to information retrieval systems and from reliance on LLMs. In this paper, we present an experience report on the failure points of RAG systems from three case studies from separate domains: research, education, and biomedical. We share the lessons learned and present 7 failure points to consider when designing a RAG system. The two key takeaways arising from our work are: 1) validation of a RAG system is only feasible during operation, and 2) the robustness of a RAG system evolves rather than designed in at the start. We conclude with a list of potential research directions on RAG systems for the software engineering community.

Large language models (LLMs) enable state-of-the-art semantic capabilities to be added to software systems such as semantic search of unstructured documents and text generation. However, these models are computationally expensive. At scale, the cost of serving thousands of users increases massively affecting also user experience. To address this problem, semantic caches are used to check for answers to similar queries (that may have been phrased differently) without hitting the LLM service. Due to the nature of these semantic cache techniques that rely on query embeddings, there is a high chance of errors impacting user confidence in the system. Adopting semantic cache techniques usually requires testing the effectiveness of a semantic cache (accurate cache hits and misses) which requires a labelled test set of similar queries and responses which is often unavailable. In this paper, we present VaryGen, an approach for using LLMs for test input generation that produces similar questions from unstructured text documents. Our novel approach uses the reasoning capabilities of LLMs to 1) adapt queries to the domain, 2) synthesise subtle variations to queries, and 3) evaluate the synthesised test dataset. We evaluated our approach in the domain of a student question and answer system by qualitatively analysing 100 generated queries and result pairs, and conducting an empirical case study with an open source semantic cache. Our results show that query pairs satisfy human expectations of similarity and our generated data demonstrates failure cases of a semantic cache. Additionally, we also evaluate our approach on Qasper dataset. This work is an important first step into test input generation for semantic applications and presents considerations for practitioners when calibrating a semantic cache.

The rapid growth of both the Industrial Internet of Things (IIoT) and Artificial Intelligence (AI) results in a high demand for AI applications in devices. To achieve high levels of accuracy, AI applications typically require a large amount of annotated data. Accessing such data is challenging in various applications such as healthcare, finance and information security. Federated learning (FL) is one of the strategies that was proposed to overcome this challenge. Specifically, FL enables the AI model in the centralized system to be trained without any prior knowledge of the information on the devices. Recent FLs have the disadvantage that they are dependent upon a centralized system, and thus are susceptible to single points of failure. This paper proposes a strategy that employs FL in a decentralized environment where devices can communicate with each other to increase the accuracy of the AI model in each device. Furthermore, we evaluate the proposed strategy in the image classification task with the ResNet50 architecture and the CIFAR-10 dataset. The evaluation shows that the ResNet50 model trained in the decentralized environment can achieve comparable results to the model trained in the centralized environment.

Machine reading comprehension (MRC) is a challenging task in natural language processing that demonstrates the language understanding of the machine. An approach to tackle this challenge requires the machine to answer the question about the given context when needed and abstain from answering when there is no answer. Recent works attempted to solve this challenge with various comprehensive neural network architectures for sequences such as SAN, U-Net, EQuANt, and others that were trained on the SQuAD 2.0 dataset containing unanswerable questions. However, the robustness of these approaches has not been evaluated. In this paper, we propose a data augmentation approach that converts answerable questions to unanswerable questions in the SQuAD 2.0 dataset by altering the entities in the question to its antonym from ConceptNet which is a semantic network. The augmented data is, then, fitted into the U-Net question answering model to evaluate the robustness of the model.

Machine Learning (ML) techniques in clinical decision support systems are scarce due to the limited availability of clinically validated and labelled training data sets. We present a framework to (1) enable quality controls at data submission toward ML appropriate data, (2) provide in-situ algorithm assessments, and (3) prepare dataframes for ML training and robust stochastic analysis. We developed and evaluated PiMS (Pandemic Intervention and Monitoring Systems): a remote monitoring solution for patients that are Covid-positive. The system was trialled at two hospitals in Melbourne, Australia (Alfred Health and Monash Health) involving 109 patients and 15 clinicians.

In many real-world applications such as the inspection of powerlines, the automated detection of anomalies can minimise damage and reduce costs that result from the presence of unknown anomalies. Technologies such as LiDAR scans obtained from Unmanned Aerial Vehicles (UAV) are becoming prominent due to the data depth they provide. In the context of powerline transmission, investigators must search for anomalous elements such as line defects or obstructions. Such occurrences are not always apparent and detecting them requires extensive analysis of data within vast areas of wilderness. Automating this process can reduce time and labor costs. We propose a methodology to define what constitutes an anomaly within mapped real-world scenes, and a technique to address different types of anomalies. The notion of unknowns and knowns composed of unknown to both human and machine, known to human and unknown to machine, unknown to human and known to machine, and known to both human and machine is considered to develop a novel framework that detects anomalous patterns. For the purpose of evaluation, we introduce synthetic anomalous data points through our data augmentation methods. Our framework achieved 63.78% accuracy in detecting the points known to the machine and unknown to the machine from the Sensat Urban validation scene. Within the scene, 78.22% of the incorrectly classified data were detected as unknown to the machine. Furthermore, our framework achieved 84.34% accuracy in detecting the synthetic data and 35.5% accuracy in detecting those data as anomalies.