The development of artificial intelligence systems capable of understanding and reasoning about complex real-world scenarios is a significant challenge. In this work we present a novel approach to enhance and exploit LLM reactive capability to address complex problems and interpret deeply contextual real-world meaning. We introduce a method and a tool for creating a multimodal, knowledge-augmented formal representation of meaning that combines the strengths of large language models with structured semantic representations. Our method begins with an image input, utilizing state-of-the-art large language models to generate a natural language description. This description is then transformed into an Abstract Meaning Representation (AMR) graph, which is formalized and enriched with logical design patterns, and layered semantics derived from linguistic and factual knowledge bases. The resulting graph is then fed back into the LLM to be extended with implicit knowledge activated by complex heuristic learning, including semantic implicatures, moral values, embodied cognition, and metaphorical representations. By bridging the gap between unstructured language models and formal semantic structures, our method opens new avenues for tackling intricate problems in natural language understanding and reasoning.

Marine heatwaves (MHWs), an extreme climate phenomenon, pose significant challenges to marine ecosystems and industries, with their frequency and intensity increasing due to climate change. This study introduces an integrated deep learning approach to forecast short-to-long-term MHWs on a global scale. The approach combines graph representation for modeling spatial properties in climate data, imbalanced regression to handle skewed data distributions, and temporal diffusion to enhance forecast accuracy across various lead times. To the best of our knowledge, this is the first study that synthesizes three spatiotemporal anomaly methodologies to predict MHWs. Additionally, we introduce a method for constructing graphs that avoids isolated nodes and provide a new publicly available sea surface temperature anomaly graph dataset. We examine the trade-offs in the selection of loss functions and evaluation metrics for MHWs. We analyze spatial patterns in global MHW predictability by focusing on historical hotspots, and our approach demonstrates better performance compared to traditional numerical models in regions such as the middle south Pacific, equatorial Atlantic near Africa, south Atlantic, and high-latitude Indian Ocean. We highlight the potential of temporal diffusion to replace the conventional sliding window approach for long-term forecasts, achieving improved prediction up to six months in advance. These insights not only establish benchmarks for machine learning applications in MHW forecasting but also enhance understanding of general climate forecasting methodologies.

Traditional machine learning has played a key role in geospatial predictions, but its limitations have become more distinct over time. One significant drawback of traditional ML is that they often rely on structured geospatial data, such as raster or vector formats, affecting their ability to handle unstructured or multimodal data (Pierdicca & Paolanti, 2022). Additionally, traditional models may face challenges in capturing complex spatial patterns and regional variations, leading to challenges with data sparsity and uneven distribution, which could affect the accuracy and generalizability of predictions (Nikparvar & Thill, 2021). In contrast, large language models (LLMs) have shown great promise across various fields by processing vast amounts of data and reasoning across multiple modalities (Chang et al., 2024). By integrating textual, visual, and contextual information, LLMs can introduce novel covariates for geospatial predictions, thus enhancing traditional approaches. However, extracting geospatial knowledge from LLMs poses its challenges. Although using geographic coordinates (i.e., latitude and longitude) was a straightforward way to retrieve location-specific information, this approach often yields suboptimal results, particularly when dealing with complex spatial relationships and regional characteristics. As a result, the traditional model does not easily to harness the full potential of multi-modal data, hindering its effectiveness in applications demanding comprehensive, cross-modal insights.

State-of-the-art algorithms are reported to be almost perfect at distinguishing the vibrations arising from healthy and damaged machine bearings, according to benchmark datasets at least. However, what about their application to new data? In this paper, we are able to confirm that neural networks for bearing fault detection can be crippled by incorrect hyperparameterisation, and also that the correct hyperparameter settings can actually change when transitioning to new data. The paper weaves together multiple methods to explain the behaviour of the hyperparameters of a wide-kernel convolutional neural network and how to set them. Since guidance already exists for generic hyperparameters like minibatch size, we focus on how to set architecture-specific hyperparameters such as the width of the convolutional kernels, a topic which might otherwise be obscure. We reflect different data properties by fusing information from seven different benchmark datasets, and our results show that the kernel size in the first layer in particular is sensitive to changes in the data. Looking deeper, we use manipulated copies of one dataset in an attempt to spot why the kernel size sometimes needs to change. The relevance of sampling rate is studied by using different levels of resampling, and spectral content is studied by increasingly filtering out high frequencies. At the end of our paper we conclude by stating clear guidance on how to set the hyperparameters of our neural network architecture.

The rapid adoption of electric vehicles (EVs) in modern transport systems has made energy-aware routing a critical task in their successful integration, especially within large-scale networks. In cases where an EV's remaining energy is limited and charging locations are not easily accessible, some destinations may only be reachable through an energy-optimal path: a route that consumes less energy than all other alternatives. The feasibility of such energy-efficient paths depends heavily on the accuracy of the energy model used for planning, and thus failing to account for vehicle dynamics can lead to inaccurate energy estimates, rendering some planned routes infeasible in reality. This paper explores the impact of vehicle dynamics on energy-optimal path planning for EVs. We develop an accurate energy model that incorporates key vehicle dynamics parameters into energy calculations, thereby reducing the risk of planning infeasible paths under battery constraints. The paper also introduces two novel online reweighting functions that allow for a faster, pre-processing free, pathfinding in the presence of negative energy costs resulting from regenerative braking, making them ideal for real-time applications. Through extensive experimentation on real-world transport networks, we demonstrate that our approach considerably enhances energy-optimal pathfinding for EVs in both computational efficiency and energy estimation accuracy.

Inferring affordable (i.e., graspable) parts of arbitrary objects based on human specifications is essential for robots advancing toward open-vocabulary manipulation. Current grasp planners, however, are hindered by limited vision-language comprehension and time-consuming 3D radiance modeling, restricting real-time, open-vocabulary interactions with objects. To address these limitations, we propose GLOVER, a unified Generalizable Open-Vocabulary Affordance Reasoning framework, which fine-tunes the Large Language Models (LLMs) to predict visual affordance of graspable object parts within RGB feature space. We compile a dataset of over 10,000 images from human-object interactions, annotated with unified visual and linguistic affordance labels, to enable multi-modal fine-tuning. GLOVER inherits world knowledge and common-sense reasoning from LLMs, facilitating more fine-grained object understanding and sophisticated tool-use reasoning. To enable effective real-world deployment, we present Affordance-Aware Grasping Estimation (AGE), a non-parametric grasp planner that aligns the gripper pose with a superquadric surface derived from affordance data. In evaluations across 30 real-world scenes, GLOVER achieves success rates of 86.0% in part identification and 76.3% in grasping, with speeds approximately 330 times faster in affordance reasoning and 40 times faster in grasping pose estimation than the previous state-of-the-art.

Monitoring agricultural activities is important to ensure food security. Remote sensing plays a significant role for large-scale continuous monitoring of cultivation activities. Time series remote sensing data were used for the generation of the cropping pattern. Classification algorithms are used to classify crop patterns and mapped agriculture land used. Some conventional classification methods including support vector machine (SVM) and decision trees were applied for crop pattern recognition. However, in this paper, we are proposing Deep Neural Network (DNN) based classification to improve the performance of crop pattern recognition and make a comparative analysis with two (2) other machine learning approaches including Naive Bayes and Random Forest.

Categorical data composed of nominal valued attributes are ubiquitous in knowledge discovery and data mining tasks. Due to the lack of well-defined metric space, categorical data distributions are difficult to intuitively understand. Clustering is a popular technique suitable for data analysis. However, the success of clustering often relies on reasonable distance metrics, which happens to be what categorical data naturally lack. Therefore, the cluster analysis of categorical data is considered a critical but challenging problem. This paper introduces the new finding that the order relation among attribute values is the decisive factor in clustering accuracy, and is also the key to understanding the categorical data clusters. To automatically obtain the orders, we propose a new learning paradigm that allows joint learning of clusters and the orders. It turns out that clustering with order learning achieves superior clustering accuracy, and the learned orders provide intuition for understanding the cluster distribution of categorical data. Extensive experiments with statistical evidence and case studies have verified the effectiveness of the new ``order is all you need'' insight and the proposed method.

This paper introduces a methodology based on Denoising AutoEncoder (DAE) for missing data imputation. The proposed methodology, called mDAE hereafter, results from a modification of the loss function and a straightforward procedure for choosing the hyper-parameters. An ablation study shows on several UCI Machine Learning Repository datasets, the benefit of using this modified loss function and an overcomplete structure, in terms of Root Mean Squared Error (RMSE) of reconstruction. This numerical study is completed by comparing the mDAE methodology with eight other methods (four standard and four more recent). A criterion called Mean Distance to Best (MDB) is proposed to measure how a method performs globally well on all datasets. This criterion is defined as the mean (over the datasets) of the distances between the RMSE of the considered method and the RMSE of the best method. According to this criterion, the mDAE methodology was consistently ranked among the top methods (along with SoftImput and missForest), while the four more recent methods were systematically ranked last. The Python code of the numerical study will be available on GitHub so that results can be reproduced or generalized with other datasets and methods.

Sign language translation, especially in gloss-free paradigm, is confronting a dilemma of impracticality and unsustainability due to growing resource-intensive methodologies. Contemporary state-of-the-arts (SOTAs) have significantly hinged on pretrained sophiscated backbones such as Large Language Models (LLMs), embedding sources, or extensive datasets, inducing considerable parametric and computational inefficiency for sustainable use in real-world scenario. Despite their success, following this research direction undermines the overarching mission of this domain to create substantial value to bridge hard-hearing and common populations. Committing to the prevailing trend of LLM and Natural Language Processing (NLP) studies, we pursue a profound essential change in architecture to achieve ground-up improvements without external aid from pretrained models, prior knowledge transfer, or any NLP strategies considered not-from-scratch. Introducing Signformer, a from-scratch Feather-Giant transforming the area towards Edge AI that redefines extremities of performance and efficiency with LLM-competence and edgy-deployable compactness. In this paper, we present nature analysis of sign languages to inform our algorithmic design and deliver a scalable transformer pipeline with convolution and attention novelty. We achieve new 2nd place on leaderboard with a parametric reduction of 467-1807x against the finests as of 2024 and outcompete almost every other methods in a lighter configuration of 0.57 million parameters.