![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Chapter and Conference Paper
Fourier-Based Instance Selective Whitening for Domain Generalized Lane Detection
Lane detection represents a fundamental task within autonomous driving. While deep learning has made remarkable advancements in the source domain, its ability to generalize to unseen target domains still poses...
-
Chapter and Conference Paper
Research on New Technology of Elastic Cushion Layer for Static Load Testing of Composite Foundations
To address the limitation of conventional static load tests on composite foundations, this study presents an enhanced static load testing approach for composite foundations by incorporating an elastic cushion ...
-
Chapter and Conference Paper
Effect of Graphene on Properties of Hydrogenated Nitrile Butadiene Rubber at High Temperature and Drilling Fluid
Hydrogenated nitrile butadiene rubber (HNBR) is widely used in oil drilling field because of its high temperature and oil resistance, but its heat oxygen aging resistance and high temperature drilling fluid re...
-
Chapter and Conference Paper
Design and Efficiency Optimization of Asymmetric Magnetic Coupled Resonant Wireless Power Transfer System
The two-coil magnetic coupling resonant wireless power transfer (MCR-WPT) system has the disadvantages of short transmission distance, and low transmission efficiency when distance between the two coils is lon...
-
Chapter and Conference Paper
Towards Cost-Efficient Federated Multi-agent RL with Learnable Aggregation
Multi-agent reinforcement learning (MARL) often adopts centralized training with a decentralized execution (CTDE) framework to facilitate cooperation among agents. When it comes to deploying MARL algorithms in...
-
Chapter and Conference Paper
No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling
Vision Transformers (ViTs) have demonstrated outstanding performance in computer vision tasks, yet their high computational complexity prevents their deployment in computing resource-constrained environments. ...
-
Chapter and Conference Paper
Application of Deep Shear Wave Imaging in Evaluation of Near Borehole Hidden Reservoir
Carbonate rock of Tarim basin in western China is rich in petroleum resources, most of the target formation is buried as superdeep as 6500 m, and characterized by fracture and cavity reservoirs, and high heter...
-
Chapter and Conference Paper
Automatic Generation and Incremental Update Method of Single Line Diagram of Distribution Network
The single-line diagram of the distribution network is an electrical wiring diagram with a single feeder as the unit. It realizes the visual expression of the topological connection relationship of the distrib...
-
Chapter and Conference Paper
Research on Mass Image Data Storage Method for Data Center
With the advancement of technology and the development of the electric power business, power enterprises have generated a large amount of image data, which contains rich potential information, and it is urgent...
-
Chapter and Conference Paper
Research and Application of Interactive Power Distribution Topology Technology for Distributed New Energy
This paper analyzes the requirements of new energy interactive power distribution topology editing, studies the graph database technology for distributed new energy, designs the power topology function scheme,...
-
Chapter and Conference Paper
Design of Conversational Components to Facilitate Human-Agent Negotiation
With burgeoning interest in the industry and among citizens about the potential of human-AI partnerships [10], academic researchers have been pushing the frontier of new modalities of peer-level and ad-hoc human-...
-
Chapter and Conference Paper
Analysis Method of Fragmented Storage and Dynamic Loading of Distribution Network Topology Data
Due to the huge amount of data in the distribution network, the topology analysis method directly based on database query has low performance problems. To meet the performance requirements of various business ...
-
Chapter and Conference Paper
Exploration and Practice of Integrated Re-fracturing Technology for Horizontal Wells in Ultra-low Permeability Reservoirs in Huaqing Oilfield
The Huaqing Chang 6 reservoir in the Ordos Basin is a typical ultra-low permeability reservoir, in the early stage, horizontal well staged fracturing and water injection was used to supplement energy developme...
-
Chapter
On-Demand Accelerating Deep Neural Network Inference via Edge Computing
In this chapter, we study how to accelerate DNN inference under device-edge synergy, by jointly applying the two knobs of DNN model partitioning and right-sizing.
-
Chapter
Introduction to Edge Intelligence
We are living during an unprecedented era of artificial intelligence (AI) expansion. Driven by the recent advancements of algorithms, computing power, and big data, deep learning [Lecun et al., 2015]—the most ...
-
Chapter
Hierarchical Mobile-Edge-Cloud Model Training with Hybrid Parallelism
In this chapter, we present an execution paradigm of hybrid parallelism to accelerate the DNN model training process under the hierarchical mobile-edge-cloud architecture.
-
Chapter
Applications, Marketplaces, and Future Directions of Edge Intelligence
Having presented a review of existing efforts (with bias toward our own research) on edge intelligence (which is still in its infancy stage), we next share our view of its applications, marketplaces, and futur...
-
Chapter
Edge Intelligence via Model Training
In this chapter, we focus on distributed training of DNN at the edge, including the architectures, key performance indicators, enabling techniques, and existing systems and frameworks.
-
Chapter
Edge Intelligence via Model Inference
Chapters 2–5 focus on efficient training of EI models. Needless to say, real-time inference at the edge can be equally critical for enabling high-quality edge intelligence service deployment. In this chapter, ...
-
Chapter
Edge Intelligence via Federated Meta-Learning
As noted before, it is anticipated that a high percentage of IoT data will be stored and processed locally. However, because many AI applications typically require high computational power that greatly outweig...