This paper examines how business users can leverage machine learning and data analytics through dashboards to optimize their decision making in demand-side supply chain management. We present a case study of an Austri...
详细信息
data narration is the activity of crafting narratives supported by facts extracted from dataexploration and analysis, using interactive visualizations. While data narration has recently attracted much attention, the ...
详细信息
ISBN:
(纸本)9783031157400;9783031157394
data narration is the activity of crafting narratives supported by facts extracted from dataexploration and analysis, using interactive visualizations. While data narration has recently attracted much attention, the process of crafting data narratives is loosely documented and has not yet been formally described. In this article, we propose a comprehensive and well-founded process to fill this need. It aims at (i) supporting the complete cycle of data narration, from the exploration of data to the visual rendering of the narrative, (ii) being flexible enough to cover a wide range of crafting practices, and (iii) being well founded upon with a conceptual model of the domain.
There are various types of available data, with different data structures, dimensions, and intervals. Conventional big data algorithms can lead to poor interpretability. In this study, novel methods are proposed based...
详细信息
ISBN:
(纸本)9781959025498
There are various types of available data, with different data structures, dimensions, and intervals. Conventional big data algorithms can lead to poor interpretability. In this study, novel methods are proposed based on big dataanalysis and machine learning. First, the data are categorized into 4 pairs to build parameter analysis model: pump static data, pump dynamic data, production static data, and production dynamic data. Combining static and dynamic data to establish parameter analysis modeling and different data pairs adopt different modeling methods: current and voltage data adopt picture recognition algorithm, vibration data adopt time domain analysis, and production data adopt random forest algorithm. Then, a deep neural network is developed to couple four models to diagnose ESPs production status. All the models have high accuracy through optimization. In the end, a management platform had been established for ESP wells including datavisualization, production analysis, fault diagnose and warning. visual production dynamic tracking management can improve the management efficiency of ESP wells and reduce the cost of future workover and relocation. Copyright 2024, Society of Petroleum Engineers.
The paper aims to delineate a workflow that demonstrates how the application of a digital process can facilitate a comprehensive comprehension of the current crisis state of overturning masonries applied to a case stu...
详细信息
Real-world reinforcement learning (RL) environments, whether in robotics or industrial settings, often involve non-visual observations and require not only efficient but also reliable and thus interpretable and flexib...
详细信息
ISBN:
(纸本)9783031539657;9783031539664
Real-world reinforcement learning (RL) environments, whether in robotics or industrial settings, often involve non-visual observations and require not only efficient but also reliable and thus interpretable and flexible RL approaches. To improve efficiency, agents that perform state representation learning with auxiliary tasks have been widely studied in visual observation contexts. However, for real-world problems, dedicated representation learning modules that are decoupled from RL agents are more suited to meet requirements. This study compares common auxiliary tasks based on, to the best of our knowledge, the only decoupled representation learning method for low-dimensional non-visual observations. We evaluate potential improvements in sample efficiency and returns for environments ranging from a simple pendulum to a complex simulated robotics task. Our findings show that representation learning with auxiliary tasks only provides performance gains in sufficiently complex environments and that learning environment dynamics is preferable to predicting rewards. These insights can inform future development of interpretable representation learning approaches for non-visual observations and advance the use of RL solutions in real-world scenarios.
With the development of the times, the use of 3D image virtual reconstruction (IVR) systems is increasing. The 3D IVR system can solve the problems of poor user experience quality and low human-machine interaction eff...
详细信息
The proceedings contain 66 papers. The topics discussed include: bringing data into the conversation: adapting content from business intelligence dashboards for threaded collaboration platforms;AEye: a visualization t...
ISBN:
(纸本)9798350354850
The proceedings contain 66 papers. The topics discussed include: bringing data into the conversation: adapting content from business intelligence dashboards for threaded collaboration platforms;AEye: a visualization tool for image datasets;feature clock: high-dimensional effects in two-dimensional plots;curve segment neighborhood-based vector field exploration;micro visualizations on a smartwatch: assessing reading performance while walking;guided statistical workflows with interactive explanations and assumption checking;opening the black box of 3D reconstruction error analysis with VECTOR;and an Overview+Detail layout for visualizing compound graphs.
Information visualization is a field of visualdataanalysis that focuses on working with abstract information. It also incorporates interactions that make it easier for users to assimilate and understand the informat...
详细信息
With the increasing number of Chinese students in Thailand, the demand for insurance services from these students has gradually shown diversity and personalized characteristics. However, the current research on the in...
详细信息
In order to solve the current shortcomings in the teaching of VR-integrated art majors, the creator teaching method is to apply virtual reality technology to the design and practical teaching of art courses. The innov...
详细信息
ISBN:
(纸本)9798400717819
In order to solve the current shortcomings in the teaching of VR-integrated art majors, the creator teaching method is to apply virtual reality technology to the design and practical teaching of art courses. The innovation of this study is reflected in three aspects. Firstly, virtual reality technology is organically combined with traditional ancient architecture in experimental teaching and applied to art teaching courses. In this way, the subjective initiative and leading role of students in teaching can be given full play. This method can play a positive role in promoting students' practical ability and innovation ability. Secondly, the model approach of VR simulation experiments to fully demonstrate traditional architecture is proposed. This paper discusses how to successfully embed art visuals and place VR at the forefront of a progressive curriculum. This study conducted in a Chinese context used Fine Art students (62) as respondents to apply VR technology to their subject area. Part of the raw data was collected by completing a questionnaire, followed by a visual regression (rs = 2.67, p < .0001). The basic dataanalysis showed that VR allows students to absorb information quickly compared to the usual teaching methods. This method can play an effective role in scientifically evaluating the effectiveness of teaching and targeting improvements. In conclusion, the digital humanities creator pedagogy has been fully applied in the design and practice teaching of art students.
暂无评论