240106 research outputs found
Sort by
The HCI GenAI CO2ST Calculator:Calculating and Offsetting the Carbon Footprint of Generative AI Use in Human-Computer Interaction Research
Get PDFIncreased usage of generative AI (GenAI) in Human-Computer Interaction (HCI) research has caused a sustainability crisis in computing, due to the excessive power consumption of developing and running these models. Energy consumption causes a massive carbon footprint. The exact energy usage and and subsequent carbon emissions are difficult to estimate in HCI research because HCI researchers most often use cloud-based services where the hardware and its energy consumption are hidden from plain view. The HCI GenAI CO2st Calculator is a tool designed specifically for the HCI research pipeline, to help researchers estimate the energy consumption and carbon footprint of using generative AI in their research, either a priori (allowing for mitigation strategies or experimental redesign) or post hoc (allowing for transparent documentation of carbon footprint in written reports of the research).</p
Meta-token Learning for Thermal Object Detection with Transformers
Get PDFTransformers have emerged as a dominant archi-tecture in computer vision, demonstrating strong performanceacross a range of tasks. In this work, we investigate theireffectiveness for object detection in thermal imagery, a settingoften challenged by variable environmental conditions. We focuson a long-term thermal surveillance dataset captured using astationary thermal camera subjected to diverse weather sce-narios. To address the influence of such external factors, wepropose an analysis that integrates weather information as meta-tokens alongside thermal images, enabling the model to accountfor environmental context during detection. Among the fusionstrategies explored, we find that a token-level concatenation al-lows transformers to partially exploit the auxiliary weather data,leading to improved detection performance. Our study highlightsthe potential of meta-token transformer-based architectures forrobust detection in challenging thermal environments
AI-Based Predictive Modeling and NSGA-II Optimization for Eco-Driving Route Planning in Electric Vehicles
Get PDFAsEVsreshape the automotive industry, eco-driving and route optimization become essential in reducing energy inefficiencies, especially in urban settings where frequent acceleration and deceleration degrade battery performance. This study proposes a mathematical model for EV energy consumption and applies Multi-Objective Optimization (MOO) with NSGA-II (Non-dominated Sorting Genetic Algorithm II) to minimize energy loss while extending driving range through route selection, traffic avoidance, and eco driving strategies. The framework integrates real-time traffic and weather data from theTomTomApplication Programming Interface (API) along with historical traffic records from NYC OpenData. Vehicle-specific data from the Volkswagen eGolf further trains the model under real driving conditions, producing the energy consumption dataset ETotal. Using the ETotal dataset, a predictive algorithm improves energy forecasting accuracy by incorporating traffic flow, road topology, and vehicle dynamics. Numerical simulation results confirm the model’s effectiveness in balancing energy use and travel time through Pareto-optimal decision making. The AI model generated 100 predictive route options between Times Square and the Holland Tunnel. Among these, route 2 (5.17 km) was identified as the most efficient, requiring only 1.03 kWh of energy ETotal. These findings demonstrate the potential of AI in eco-routing to extend EV range and enhance driver-assistance and autonomous vehicle systems
Gaussian Process Latent Variable Modeling for Few-Shot Time Series Forecasting
No full textAccurate time series forecasting is crucial for optimizing resource allocation, industrial production, and urban management, particularly with the growth of cyber-physical and IoT systems. However, limited training sample availability in fields like physics and biology poses significant challenges. Existing models struggle to capture long-term dependencies and to model diverse meta-knowledge explicitly in few-shot scenarios. To address these issues, we propose MetaGP, a meta-learning-based Gaussian process latent variable model that uses a Gaussian process kernel function to capture long-term dependencies and to maintain strong correlations in time series. We also introduce Kernel Association Search (KAS) as a novel meta-learning component to explicitly model meta-knowledge, thereby enhancing both interpretability and prediction accuracy. We study MetaGP on simulated and real-world few-shot datasets, showing that it is capable of state-of-the-art prediction accuracy. We also find that MetaGP can capture long-term dependencies and can model meta-knowledge, thereby providing valuable insights into complex time series patterns.</p
Data Driven Decision Making with Time Series and Spatio-Temporal Data
No full textTime series data captures properties that change over time. Such data occurs widely, ranging from the scientific and medical domains to the industrial and environmental domains. When the properties in time series exhibit spatial variations, we often call the data spatio-temporal. As part of the continued digitalization of processes throughout society, increasingly large volumes of time series and spatio-temporal data are available. In this tutorial, we focus on data-driven decision making with such data, e.g., enabling greener and more efficient transportation based on traffic time series forecasting. The tutorial adopts the holistic paradigm of 'data-governance-analytics-decision.' We first introduce the data foundation of time series and spatio-temporal data, which is often heterogeneous. Next, we discuss data governance methods that aim to improve data quality. We then cover data analytics, focusing on five desired characteristics: automation, robustness, generality, explainability, and resource efficiency. We finally cover data-driven decision making strategies and briefly discuss promising research directions. We hope that the tutorial will serve as a primary resource for researchers and practitioners who are interested in value creation from time series and spatio-temporal data.</p
A Multi-Modal Knowledge-Enhanced Framework for Vessel Trajectory Prediction
Get PDFAccurate vessel trajectory prediction facilitates improved navigational safety, routing, and environmental protection. However, existing prediction methods are challenged by the irregular sampling time intervals of the vessel tracking data from the global AIS system and the complexity of vessel movement. These aspects render model learning and generalization difficult. To address these challenges and improve vessel trajectory prediction, we propose the multi-modal knowledge-enhanced framework (MAKER) for vessel trajectory prediction. To contend better with the irregular sampling time intervals, MAKER features a Large language model-guided Knowledge Transfer (LKT) module that leverages pre-trained language models to transfer trajectory-specific contextual knowledge effectively. To enhance the ability to learn complex trajectory patterns, MAKER incorporates a Knowledge-based Self-paced Learning (KSL) module. This module employs kinematic knowledge to progressively integrate complex patterns during training, allowing for adaptive learning and enhanced generalization. Experimental results on two vessel trajectory datasets show that MAKER can improve the prediction accuracy of state-of-the-art methods by 12.08%-17.86%.Accurate vessel trajectory prediction facilitates improved navigational safety, routing, and environmental protection. However, existing prediction methods are challenged by the irregular samplingtime intervals of the vessel tracking data from the global AIS systemand the complexity of vessel movement. These aspects render modellearning and generalization difficult. To address these challengesand improve vessel trajectory prediction, we propose Multi-modAlKnowledge-Enhanced fRamework (MAKER) for vessel trajectoryprediction. To contend better with the irregular sampling time intervals, MAKER features a Large language model-guided KnowledgeTransfer (LKT) module that leverages pre-trained language modelsto transfer trajectory-specific contextual knowledge effectively. Toenhance the ability to learn complex trajectory patterns, MAKERincorporates a Knowledge-based Self-paced Learning (KSL) module. This module employs kinematic knowledge to progressivelyintegrate complex patterns during training, allowing for adaptivelearning and enhanced generalization. Experimental results on twovessel trajectory datasets show that MAKER can improve the prediction accuracy of state-of-the-art methods by 12.08%—17.86%
A Scenario-Based Framework to Optimising Eco-Wellness Tourism Development and Creating Niche Markets:A Case Study of Ardabil, Iran
Get PDFDecision-making and planning in eco-wellness tourism can vary depending on time, resources, and the perspectives of stakeholders, as it is often challenging to generalize the results of decision-making models across different scenarios. Hence, the primary objective of this study was to propose a scenario-based framework for optimising eco-wellness tourism development. For this purpose, maps of 26 factors affecting the evaluation of nature-based eco-wellness tourism, including water, climatic, and kinetic therapies, were used in the Ardabil province of Iran. Weighted criteria maps are integrated into suitability maps for various wellness tourism products under different scenarios, ranging from very pessimistic to very optimistic, using the Ordered Weighted Averaging (OWA) operator. Then, to identify areas of consensus, scenario-based maps for water, climate, and kinetic therapies are combined. In the very pessimistic (optimistic) scenario, climate-only therapy accounts for 0.91% (2.23%), water-only therapy for 1.07% (8.44%), and kinetic-only therapy for 3.5% (5.81%) of the area. The most significant expansion is observed in areas integrating all three therapies—climate, water, and kinetic—which increase from 3.23% in the very pessimistic scenario to 14.5% in the very optimistic scenario. The findings have substantial insights for policymakers, tourism planners, and investors in developing and promoting unique eco-wellness experiences that benefit tourists. The methodical approach and choice of data and parameters in the study can be inspirational and adjustable for relevant studies