With the growing popularity of electric vehicles (EVs), maintaining power grid stability has become a significant challenge. To address this issue, EV charging control strategies have been developed to manage the swit...
详细信息
In recent years, many crowdsourcing platforms have emerged, using the resources of recruited workers to perform diverse outsourcing tasks, where the video analytics attracts much attention due to its practical implica...
详细信息
ISBN:
(数字)9798350317152
ISBN:
(纸本)9798350317169
In recent years, many crowdsourcing platforms have emerged, using the resources of recruited workers to perform diverse outsourcing tasks, where the video analytics attracts much attention due to its practical implications. For maximum profits, platforms carefully choose the workers and determine the video analytics configurations to ensure accuracy; meanwhile, workers possess the flexibility to tailor the configurations for their indivi-dual gains, which makes it hard for platforms to optimize their profits considering the platform-worker conflicts. In this paper, we design an incentive mechanism for Multi-leader game-based video Analytics upon CROwdsourcing, named MACRO, to over-come the above situation. Under that mechanism, we first formu-late the utility optimization problems for platforms and workers, respectively. We then propose a dual ascent-based method to op-timally determine the video analytics configurations for a multi-platform game, ensuring Pareto efficiency. Moreover, in the context of a multi-leader game involving platform-worker conflicts, we design an incentive function with its incentive factor update strategy and propose an ADMM-based approach for maximizing incentives that motivate workers to contribute to the platforms' profits. Rigorous proofs demonstrate the linear convergence of the MACRO to the multi-leader Stackelberg equilibrium. Trace-driven experiments show that MACRO improves the Pareto efficiency by 26.3%, outperforming other approaches.
Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative task...
详细信息
Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely...
Federated learning (FL) is a promising learning paradigm that can tackle the increasingly prominent isolated data islands problem while keeping users' data locally with privacy and security guarantees. However, FL...
详细信息
Sarcasm, sentiment, and emotion are three typical kinds of spontaneous affective responses of humans to external events and they are tightly intertwined with each other. Such events may be expressed in multiple modali...
详细信息
With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that p...
详细信息
Prediction of developers' programming behaviors is an effective way to improve their development efficiency and optimize the organization of project modules and files. However, little research exists investigating...
详细信息
ISBN:
(数字)9781728191461
ISBN:
(纸本)9781728191478
Prediction of developers' programming behaviors is an effective way to improve their development efficiency and optimize the organization of project modules and files. However, little research exists investigating on this direction. In order to address this knowledge gap, we proposed a NLP-based approach to predict the programming behaviors in OSS (Open Source Software) communities. The proposed approach i) embeds the historical programming behavior data of a project into a multi-dimensional vector space to capture the potential laws in the data, ii) forms an eigenvector matrix reflecting the semantic relationship of the development behavior data, and iii) predicts the next programming behavior of a specific developer based on the eigenvector matrix. Our experiments on five OSS projects show that the prediction accuracy rate of the proposed prediction approach can reach up to about 50%, indicating that it can summarize the development behavior data law and effectively predict the programming behavior of developers. Our work can provide valuable assistance for developers' programming and projects' maintenance in practice.
The development and deployment of machine learning (ML) applications differ significantly from traditional applications in many ways, which have led to an increasing need for efficient and reliable production of ML ap...
详细信息
ISBN:
(数字)9781728191461
ISBN:
(纸本)9781728191478
The development and deployment of machine learning (ML) applications differ significantly from traditional applications in many ways, which have led to an increasing need for efficient and reliable production of ML applications and supported infrastructures. Though platforms such as TensorFlow Extended (TFX), ModelOps, and Kubeflow have provided end-to-end lifecycle management for ML applications by orchestrating its phases into multistep ML pipelines, their performance is still uncertain. To address this, we built a functional ML platform with DevOps capability from existing continuous integration (CI) or continuous delivery (CD) tools and Kubeflow, constructed and ran ML pipelines to train models with different layers and hyperparameters while time and computing resources consumed were recorded. On this basis, we analyzed the time and resource consumption of each step in the ML pipeline, explored the consumption concerning the ML platform and computational models, and proposed potential performance bottlenecks such as GPU utilization. Our work provides a valuable reference for ML pipeline platform construction in practice.
Grip force prediction plays an important role in biomechanical research, sports medicine, and clinical rehabilitation. Most of the current studies in this area only focuses on the characteristic input of surface Elect...
详细信息
ISBN:
(数字)9781665423403
ISBN:
(纸本)9781665423410
Grip force prediction plays an important role in biomechanical research, sports medicine, and clinical rehabilitation. Most of the current studies in this area only focuses on the characteristic input of surface Electromyography (sEMG) signals, but the acquisition and processing of sEMG are complicated and vulnerable to electromagnetic interference. The impedance signal has the advantages of easy acquisition and processing, strong anti-interference, non-invasive detection, and are widely used in the treatment of neuromuscular diseases. In this paper, impedance technique is introduced into grip force prediction. A single-frequency, low-intensity alternating current (AC) signal is injected into the brachioradialis muscle, and the change in muscle impedance is detected through the electrical effect of the electromagnetic field on biological tissue. Then, the correlation between impedance parameters and grip force changes is discussed, and the Long Short-Term Memory (LSTM) grip force prediction model is established with resistance (R) and phase (P) as feature inputs. The results show that the $r^{2}\_score$ of the grip force prediction model is greater than 0.94 and the mean square error (MSE) is lower than 0.7. This paper restores the actual grip force based on the LSTM prediction model and provides a new implementation idea for grip force prediction.
暂无评论