In recent years, a wide variety of automated machine learning (AutoML) methods have been proposed to generate end-to-end ML pipelines. While these techniques facilitate the creation of models, given their black-box na...
详细信息
In recent years, a wide variety of automated machine learning (AutoML) methods have been proposed to generate end-to-end ML pipelines. While these techniques facilitate the creation of models, given their black-box nature, the complexity of the underlying algorithms, and the large number of pipelines they derive, they are difficult for developers to debug. It is also challenging for machine learning experts to select an AutoML system that is well suited for a given problem. In this paper, we present the pipeline Profiler, an interactive visualization tool that allows the exploration and comparison of the solution space of machine learning (ML) pipelines produced by AutoML systems. pipelineProfiler is integrated with Jupyter Notebook and can be combined with common data science tools to enable a rich set of analyses of the ML pipelines, providing users a better understanding of the algorithms that generated them as well as insights into how they can be improved. We demonstrate the utility of our tool through use cases where pipelineProfiler is used to better understand and improve a real-world AutoML system. Furthermore, we validate our approach by presenting a detailed analysis of a think-aloud experiment with six data scientists who develop and evaluate AutoML tools.
pipeline flow visualization of cemented tailings backfill slurry (CTBS) improves the safety and stability of transportation. High turbidity and low resolution make it difficult for conventional methods to monitor the ...
详细信息
pipeline flow visualization of cemented tailings backfill slurry (CTBS) improves the safety and stability of transportation. High turbidity and low resolution make it difficult for conventional methods to monitor the particle distribution state of CTBS in a short period of time. Particle tracking technology (PTT) is used to simulate and investigate the flow characteristics of CTBS pipeline, combine with theoretical analysis to construct a CTBS pipeline visualization model, elaborate the particle distribution state when CTBS flows in the pipeline, and explore the effects of pipe diameter (PD), flow velocity (FV) and tailings gradation (TG) on the particle distribution. The results show that particle tracking technology is better applied to investigate the particle transport distribution characteristics of CTBS tailings. Three concepts of particle accumulated gravity G(a), static friction angle theta and diameter dividing line are defined, and the transport pipe is divided into light wear zone, medium wear zone and heavy wear zone. The increase in pipe diameter increases the content of fine particles at the pipe wall and the thickness of the lubrication layer becomes larger, which improves the safety and stability of CTBS transport. The increased flow velocity reduces the settling phenomenon of large size particles and improves the transport efficiency, which increases the pipeline transport resistance. Under good tailings grading conditions, a wide range of tailings grading is more suitable as backfill material. The results of the study illustrate the flow characteristics of the backfill slurry in the pipeline from the particle perspective and provide a theoretical basis for pipeline transportation research.
In order to solve the problems of difficult early warning, difficult investigation, and large investment of human and material resources in the prevention and control of third-party damage to the China-Myanmar pipelin...
详细信息
In order to solve the problems of difficult early warning, difficult investigation, and large investment of human and material resources in the prevention and control of third-party damage to the China-Myanmar pipeline, and to realize the visualization of pipeline lines caused by third-party damage to the pipeline, intelligent pipeline inspection, and controllable hidden dangers of external damage are the key issues. Inevitable trend; in order to solve such third-party prevention and control problems, this paper proposes a multi-directional intelligent monitoring system based on intelligent high-definition cameras, builds a visualization network of China-Myanmar oil and gas pipelines, applies an intelligent line inspection system, and promotes the intelligence of user information management and control platforms. Change the mode of pipeline prevention and control, realize the transformation of China-Myanmar oil and gas pipeline safety prevention and control from ＂manual defense＂ to ＂technical defense＂, substantially improve the effect of pipeline prevention and control, and improve the patrol efficiency of oil and gas pipelines, so as to realize the safety management and control of China-Myanmar oil and gas pipelines The goal of efficient and intelligent management.
The development1of a high-speed multifrequency continuous scan sonar at Sonar Research and Development has resulted in the acquisition of extremely accurate, high-resolution bathymetric data. This rich underwater data...
详细信息
The development1of a high-speed multifrequency continuous scan sonar at Sonar Research and Development has resulted in the acquisition of extremely accurate, high-resolution bathymetric data. This rich underwater data provides new challenges and possibilities within the field of seabed visualization. This article introduces seabed visualization by describing three example case studies, which use the Seabed visualization System developed at SRD. All three case studies -- harbor wall, shipwreck, and pipeline visualization -- were implemented using real survey data. The high resolution of the data obtained makes slight changes in the seabed topography easily distinguishable. Annual survey inspections enable comparisons between the data sets, making the visualization system an important tool for management and planning.
暂无评论