The evolution of data architecture has seen the rise of data lakes, aiming to solve the bottlenecks of data management and promote intelligent decision-making. However, this centralized architecture is limited by the ...
详细信息
Travel time estimation is a crucial component of intelligent transportation systems, affecting various applications such as navigation, ride-hailing, and route planning. Traditional methods for travel time estimation ...
详细信息
ISBN:
(纸本)9798350399462
Travel time estimation is a crucial component of intelligent transportation systems, affecting various applications such as navigation, ride-hailing, and route planning. Traditional methods for travel time estimation rely on subjective judgments, limited data sources, and straightforward modeling techniques. Owing to recent advances in data mining and machine learning, numerous data-driven methods are adopted to address the problem that occurred in traditional schemes, which demonstrate exceptional performance. In this paper, we present a comprehensive survey of data-driven methods for travel time estimation, encompassing application scenarios, spatial-temporal modeling approaches, and data representation learning techniques. To support and promote further research in this field, we provide a valuable list of open data sources and source codes, offering researchers a solid foundation for their future endeavors. Furthermore, this survey discusses emerging trends and key challenges faced by the research community, such as the integration of real-time data streams and the use of uncertainty estimation. We also explore the potential impact of these advancements on transportation systems, highlighting opportunities for improvement and innovation. To the best of our knowledge, this work is among the first to offer a comprehensive, in-depth review of data-driven methods for travel time estimation, providing researchers and practitioners with a valuable reference in the field.
Scheduling and processing decisions in multiplatform datasystems can lead to efficient execution of workflow tasks across available platforms. In this work, we discuss how to create a cross-platform system for data S...
详细信息
Seismic data/images are critical to understand the structure of subsurfaces. However, for accurate structural analysis, seismic images need to be converted into velocity images that can recognize the depth and thickne...
详细信息
ISBN:
(纸本)9798350304060;9798350304053
Seismic data/images are critical to understand the structure of subsurfaces. However, for accurate structural analysis, seismic images need to be converted into velocity images that can recognize the depth and thickness of subsurface layers, and this conversion is usually achieved by using seismic full-waveform inversion (FWI). Various Deep neural networks (DNNs) have recently been proposed to replace FWI, and well-trained DNNs typically have lower computational costs but generate similar velocity images as compared to FWI. Yet, training a DNN model is non-trivial, which requires transmitting seismic data that are sensed by seismic receivers in the field to a centralized data center, leading to data privacy and security issues. Seismic field tests are normally conducted in rural areas, where data centers and Internet infrastructures are not available. Hence, it is impossible to train a DNN and achieve seismic inversion in real-time. In this paper, we propose the Asynchronous Federated Learning for Seismic Inversion (AsyncFedInv) framework, which applies multiple IoT devices in terms of edge computing boards to collaboratively train a compact UNet model in real-time based on a novel asynchronous federated learning, where 1) a staleness function is applied to mitigate model staleness, and 2) clients that generate similar local models would suspend its training, thus reducing the communication costs and energy consumption. Simulation results demonstrate that AsyncFedInv achieves a similar convergence rate but lower training loss and better testing performance as compared to a baseline algorithm FedAvg.
With the increase in the scale of power systems, the development of measurement technology, and the decrease in costs, the amount of data in power systems is showing a rapid growth trend, gradually acquiring the chara...
详细信息
With the rapid development of data technology, artificial intelligence big data technology has demonstrated unprecedented importance and effectiveness in supporting decision systems. This paper focuses on how artifici...
详细信息
Enhancing agricultural productivity while maintaining ecological balance amidst climate change is a looming challenge. The future of resilient farming and food security will depend upon the effectiveness of collecting...
详细信息
ISBN:
(纸本)9798400706226
Enhancing agricultural productivity while maintaining ecological balance amidst climate change is a looming challenge. The future of resilient farming and food security will depend upon the effectiveness of collecting, interpreting, and acting on data. An agricultural digital twin (DT) can provide a feedback loop which improves both farm management and the computer system which informs it through integrating right-time sensor data, process-based models (PBMs), data-driven models (DDMs), and hybrid approaches. Three demonstrator DTs for farm ecosystems are currently under development, utilizing extensive datasets from three instrumented research farms at the North Wyke Farm Platform in Devon, UK to drive and evaluate the accuracy of models in simulating key agroecosystem processes, such as soil nutrient cycling, water balance, and crop performance. The implementation process involves data collection, processing, model integration, and visualization. Key measurements are gathered up to every 15 minutes. PBMs along with DDMs and hybrid models will be utilized in an ensemble to enhance predictive accuracy and robustness. The DT architecture consists of three tiers. A client tier focuses on creating a user-friendly web frontend and API. An analysis and retrieval tier will facilitate the orchestration of services by a container registry and Kubernetes master node. A simulation tier will handle intensivedata processing and model simulations with Apache Spark and high-performance computing nodes. We expect the DTs to improve decision-making, enhance system resilience against biotic and abiotic stresses, and pave the way for sustainable agricultural innovation.
In recent years, as the resource consumption of computation-intensive recommendation systems (RS) significantly increased, and the supply of large-scale resources encountered bottleneck, computation resource allocatio...
详细信息
Multiple preferences between robots and tasks have been largely overlooked in previous research on Multi-Robot Task Allocation (MRTA) problems. In this paper, we propose a preference-driven approach based on hedonic g...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
Multiple preferences between robots and tasks have been largely overlooked in previous research on Multi-Robot Task Allocation (MRTA) problems. In this paper, we propose a preference-driven approach based on hedonic game to address the task allocation problem of muti-robot systems in emergency rescue scenarios. We present a distributed framework considering various preferences between robots and tasks to determine the division of coalitions in such problems and evaluate the scalability and adaptability of our algorithm through relevant experiments. Furthermore, considering the strict communication limitations in emergency rescue scenarios, we have verified that our algorithm can efficiently converge to a Nash-stable coalition partition even in conditions of insufficient communication distance.
Medication errors associated with the Medication Use Process present significant risks and require effective management. However, current practices do not address these risks. There is a lack of awareness that medicat...
详细信息
ISBN:
(纸本)9798350319439
Medication errors associated with the Medication Use Process present significant risks and require effective management. However, current practices do not address these risks. There is a lack of awareness that medication errors are unintended risks, and a lack of dedicated systems to manage them. To overcome these limitations, a digital system exploiting massive medical data (big data) is proposed. By integrating various data sources, this system aims to provide adaptable medication errors' management and continuous improvement. This article presents an overview of the system requirements and highlights the potential of data Mining in healthcare. Implementing this system could revolutionize medication error management and improve patient safety.
暂无评论