In complex environments, available moving space is often non-convex due to the presence of irregular obstacles, which complicates the mapping module’s ability to represent the environment with geometric symbols. This complexity hampers the effectiveness of the planning module, leading to increased computational and storage demands. To address these challenges posed by non-convex spaces, we propose an adaptive clustering convexification mapping-planning system (ACCMPS) for unmanned aerial vehicles (UAVs) navigating in unknown environments. Our approach introduces an adaptive space-searching algorithm that transforms non-convex areas into relatively convex sub-spaces represented by clusters through purposeful sampling. ACCMPS utilizes a sample-friendly 3D grid map for local mapping and constructs a storage-efficient cluster-based weighted graph for global representation, linking convex sub-spaces represented by clusters. This integration streamlines the mapping and path planning processes, enabling direct initial path generation from the weighted graph, rather than relying on traditional algorithms that blindly explore non-convex spaces. To optimize paths, we employ a particle filter on the initial graph-derived path to handle non-convexity, followed by optimization into a smooth Bspline trajectory via cost function minimization within relatively convex regions. A series of real-world experiments conducted in both narrow and expansive environments demonstrate the advantages of ACCMPS in terms of computational efficiency, storage consumption, and path quality compared to existing state-of-the-art methods.

Robot navigation systems in unstructured environments are increasingly common but limited by the price of sensors and computational devices. Most robot navigation systems depend on the high-price multi-line lidar to perceive the environment via constructing a 3D grid map directly. The low-price RGB cameras are usually neglected because reconstructing the 3D environment from images needs lots of computational resources. To solve this problem, a hierarchical-controlled robot visual navigation system (HCRVNS) using the RGB camera only to perceive the environment with a low computational burden is proposed in this paper. In HCRVNS, edge points of the drivable area are first extracted by lite semantic segmentation and then transformed into the ground via a transformation matrix generated by an optimization model. Compared to the wide adoption of grid-based maps, the more effective line segment-based map is generated from the edge points on the ground via the proposed adaptive clusters algorithm. An optimization-based path planning algorithm is proposed to balance the total length, curve, and distance to obstacles to match the line segment-based map. Compared to others using sequence structure, a hierarchical environment builder-controller structure with different frequencies is constructed as the backbone of HCRVNS to guarantee its real-time performance. Real-world experiments validate the robustness and effectiveness of HCRVNS, showing the proposed system has similar performance compared to its multi-line lidar-based counterparts.

The synergistic development of Internet of Things(IoT), robotics, and Artificial Intelligence (AI) is reshaping the technological paradigms of interdisciplinary laboratories and industrial ecosystems. IoT-enabled vertical farming systems demonstrate significant advantages, achieving yield enhancement while reducing carbon emissions compared to traditional agriculture, thereby providing innovative solutions for sustainable food production. The advancement of robotic technologies further expands the application dimensions of mobile intelligent sensors in vertical farm IoT networks. Based on an autonomous farming system that integrates Unmanned Aerial Vehicle (UAV), sensors, and modular vertical farming units, this study proposes a three dimensional Scene Graph (3DSG)-based hierarchical mapping method for the dynamic monitoring of plant and fruit growth. Through feedback mechanisms, the system optimizes growth conditions by adjusting lighting and nutrient delivery, while the hierarchical mapping architecture reduces detection errors and enables comprehensive 3D visualization. The main contributions of this research include: 1) Pioneering application of 3DSG technology to establish a multi-dimensional spatiotemporal representation model for plant growth processes, supporting interpretable analysis and traceable monitoring; 2) Establishing an uncertainty model through error propagation by systematically analyzing sensor models (covering various common sensor combinations) and integrating these models into 3D object pose estimation algorithms. This highlights the necessity of hierarchical abstraction levels. The system is validated through simulations and real-world experiments, providing a quantitative evaluation of object pose estimation; and 3) An IoT-driven intelligent vertical farming architecture that integrating mobile robotic perception networks and environmental regulation devices, enabling dynamic acquisition and closed-loop control of plant growth parameters. Open-source code is available at https://github.com/allenthreee/scene_graph, video link: https://youtu.be/dhc8RLmX7hc.

Pests significantly threaten global agricultural production, which causes severe yield losses through feeding and virus transmission. To mitigate yield losses caused by pests, timely and precise pest management practices are critical. Although previous efforts have advanced automated solutions for real-time environmental monitoring in agriculture, implementing precise pest management decision-making and suggestion generation remains a challenge due to complex reasoning processes in practice. In response, an enhanced pest management system, PEZEGO, is proposed to provide precise management suggestions through multimodal environmental data, a fine-tuned open vocabulary detector (OVD), and large language models (LLMs). Specifically, a mobile application and low-cost Internet of Things (IoT) devices are developed to capture images and environmental information. A hybrid convolutional low-rank adaptation method (HCLoRA) is proposed to fine-tune pretrained OVDs, enabling zero-shot pest detection for converting images to pest species and quantity information. In addition, a structured data-based retrieval augmented generation (SRAG) workflow for LLMs is proposed to provide precise pest management suggestions through automatically extracted agriculture management knowledge and Chain-of-Thought. The effectiveness of PEZEGO is validated in a case study of pest management in the U.K., including pest detection in field scenarios and management suggestion generation. Compared to advanced model fine-tuning methods, HCLoRA for YOLOWorld achieves the highest detection performance with$0.1759~AP^{h}$on pest detection. Additionally, the proposed SRAG workflow demonstrates the ability to support pest management with a 68.7% average F1 score for knowledge extraction and 77.33% accuracy for suggestion generation. Eventually, a mobile application demonstrates the practical effectiveness of the proposed system.

With the global ageing population, the diagnosis of Alzheimer's disease (AD) has become an urgent public health priority. Gene expression techniques offer the advantages of being less invasive and cost-effective, but their high dimensionality and small sample sizes make them prone to the curse of dimensionality in AD diagnosis. This study proposes a novel interpretable deep learning approach to address these challenges. We introduce a shallow sparse autoencoder for dimensionality reduction and combine it with XGBoost for classification, achieving an Area Under the Receiver Operating Characteristic curve (AUROC) of up to 95.13% . Additionally, we develop a fast, low-cost feature selection algorithm that dynamically adjusts feature elimination to enhance model efficiency. Comprehensive cross-dataset evaluation demonstrates the model's strong generalisation performance on the public datasets: Alzheimer's Disease Neuroimaging Initiative (ADNI), AddNeuroMed1 (ANM1), and ANM2. Our method also provides biological interpretability through enrichment analysis, offering insights into the mechanisms underlying AD and potential therapeutic targets. This makes our approach a promising tool for early, accurate diagnosis and clinical application.

Promoting sustainable agriculture plays a crucial role in reducing greenhouse gas (GHG) emissions, lowering the carbon footprint, and improving farm resilience. Three challenges must be overcome to achieve sustainable agriculture management. Firstly, there is a lack of reliable and sustainable fertiliser solutions to improve fertiliser use efficiency, reduce GHG emissions while maintaining crop production. In addition, how to cost-effectively quantify the response of soil carbon and GHG fluxes to different fertilisation practices. Thirdly, there is a requirement to integrate multi-source farming data and AI models into a farm management information system (FMIS) to support intelligent decisions for farmers. To address these challenges, we developed the ParellelFarm, an AI-enabled sustainable farming management system that integrates multi-source farming data and AI-driven fertiliser and soil carbon models into a multi-tenant cloud platform, to support sustainable farming. It also provides remote field visualisation and management as well as instant messaging via web and mobile clients, supporting fast and accurate labour allocation with fewer resources. It is a potential solution for a cost-effective, highly productive and sustainable modern net-zero farm.

Agent-based modeling (ABM) is a powerful simulation methodology employed to analyze complex systems by representing individual entities, known as agents, which interact autonomously within a defined set of rules. This approach is particularly effective for epidemic simulation, where capturing the nuanced interactions and behaviors of individuals is crucial for understanding disease dynamics and spread. However ABM often come with complected and slow implementation. To address the performance issue, in this paper, we introduce a Framework for Large-scale Agent-based Rapid Epidemic Simulation (FLARES), a novel GPU-accelerated framework designed to enhance the performance of agent-based infectious disease transmission model. FLARES provides robust support for parallel execution, significantly reducing the overall time consumption for high computational cost tasks, enables researchers to conduct detailed and accurate epidemic analysis of disease spread.

In the rapidly evolving field of artificial intelligence, large language models (LLMs) have attracted much attention from researchers in various fields due to their unexpected text generation and comprehension capabilities. However, the applications of LLMs for sustainable pest management are under-explored due to the heavy reliance on specialized expert knowledge. In addition, evaluating the quality of LLMs' content is another technological challenge for applying LLMs in sustainable pest management. Therefore, we propose an instruction-based prompting method that integrates pest expert knowledge into the prompt, equipping LLMs with the necessary context to generate more accurate and relevant pest management advice. Furthermore, we propose an LLM-based evaluation framework to score the generated content on Coherence, Logical Consistency, Fluency, Relevance, Comprehension, and Exhaustion. Additionally, we integrate an Expert System based on crop threshold data as a baseline to obtain scores for Accuracy on whether pests found in crop fields should take management action. Each model's score is weighted by percentage to get a final score. The results show that GPT-3.5 and GPT-4 outperform the FLAN models in most evaluation dimensions. Furthermore, while using instruction-based prompting containing domain-specific knowledge outperforms other prompting methods with an accuracy of 72%, ongoing refinements and assessments of end-user satisfaction are essential to enhance the LLMs' effectiveness and practical helpfulness in providing pest management advice.

Recently, there have been a wide spectrum of multitask learning (MTL) methods developed to model Alzheimer’s disease (AD) progression. Typical MTL studies related cognitive ability prediction focus on modeling AD progression using high-quality clinical data such as MRI and cognitive scores. These studies follow a unified regularised MTL framework to process each follow-up data from patients over time. Beginning at baseline, the framework regards cognitive ability at each followup as a task and organise task relationship through temporal smoothness in cognitive ability. There is little attention on how to design feasible experimental protocols and normalisation for reliably evaluating those regularised MTL models. In this paper, we present an empirical analysis for investigate above issues. Four typical structural regularization approaches are revisited. Four issues affecting evaluation process of regularised MTL models are evaluated by experiments: 1) evaluation indicators, 2) repeated experimental times, 3) training data size and 4) number of tasks in MTL. The results demonstrate that regularised MTL models are capable of predicting AD progression with effectiveness, in many challenging cases of curse of dimensionality, data insufficiency or single MRI data input. One important finding is that MTL can effectively reduce the over-fitting risk of model, even with limited sample size. We also discover that the temporal smoothness assumption instead limits the performance of later tasks. It encourages us to revisit the relationship between patients’ cognitive ability changes between 2 and 3 years when using MTL to model AD progression.

Alzheimer’s disease (AD), the most prevalent dementia, gradually reduces the cognitive abilities of patients while also posing a significant financial burden on the healthcare system. A variety of multi-task learning methods have recently been proposed to identify potential MRI-related biomarkers and accurately predict the progression of AD. These methods, however, all use a predefined task relation structure that is rigid and insufficient to adequately capture the intricate temporal relations among tasks. Instead, we propose a novel mechanism for directly and automatically learning the temporal relation and constructing it as an Automatic Temporal relation Graph (AutoTG). We use the sparse group Lasso to select a universal MRI feature set for all tasks and particular sets for various tasks in order to find biomarkers that are useful for predicting the progression of AD. To solve the biconvex and nonsmooth objective function, we adopt the alternating optimization and show that the two related suboptimization problems are amenable to closed-form solution of the proximal operator. To solve the two problems efficiently, the accelerated proximal gradient method is used, which has the fastest convergence rate of first-order method. We have preprocessed two latest AD datasets, and the experimental results verify our proposed novel multi-task approach outperforms several baseline methods. To demonstrate the high interpretability of our approach, we visualize the automatically learned temporal relation graph and investigate the temporal patterns of the important MRI features. The implementation source is at https://github.com/menghui-zhou/MAGPP.

Pest management is an important factor affecting agricultural and food industry products. A large number of insect species and the subtle differences bring a challenge to the accurate recognition of pests. Many studies tackle the challenge of pest recognition through deep neural networks (DNNs) and achieve significant success in terms of accuracy. However, the complex structure and a large number of parameters make DNNs difficult for end users to understand the reasons for the decision of models, which causes distrust in the classification of harmful insects and overuse of insecticides. To address the lack of explainability of DNNs, we propose an explanation generation workflow to generate concept-based explanations for pest recognition. Specifically, the concept extraction method uses a clustering algorithm to extract image segments with meaningful concepts from a portion of the training dataset. Then, concept models are trained to detect the presence of concepts in the image. Finally, the explanation generation method provides concept-based global and local explanations in the form of weighted directed graphs and concept importances, respectively. Through qualitative and quantitative analysis, the proposed workflow extracts meaningful concepts for pest recognition effectively and detects the presence of concepts in images.

In intelligent driving, situational assessment (SA) is an important technology, which helps to improve the cognitive ability of intelligent vehicles in the environment. Uncertainty analysis is very significant in situation assessment. This article proposes an SA method based on uncertainty risk analysis. Under uncertain conditions, according to the random environment model and Gaussian distribution model, the collision probability between multiple vehicles is estimated by comprehensive trajectory prediction. The proposed method considers collision probabilities of different prediction points within and outside the prediction range and obtains long-term accurate prediction results. The method is suitable for the situation risk assessment of sensor systems in the presence of unexpected dynamic obstacles, sensor failures or communication losses in traffic, and different environmental sensing accuracy. The experimental results show that in the dynamic traffic environment, the proposed scenario assessment method can not only accurately predict and assess the situation risks within the prediction range, but also provide accurate scenario risk assessment outside the prediction range.