The U.S. Cyber Trust Mark is intended to empower consumers and enable security by demand. But is there such a demand? To explore this, we recruited 599 participants and asked them to select their desired smart device ...
详细信息
Brain dynamics big data is of increasing promise for many applications like epilepsy detection and cognitive understanding, with the advancements of consumer technology. However, the deep-source brain measurement is d...
详细信息
Navigating safely in dynamic and uncertain environments is challenging due to uncertainties in perception and motion. This letter presents the Chance-Constrained Unscented Model Predictive Path Integral (C2U-MPPI) fra...
详细信息
Little is known about the differences between trolling by influencers and followers, the difference between proactive and reactive trolling, and the relationship between them. Based on a content analysis of 1,386 comm...
详细信息
Little is known about the differences between trolling by influencers and followers, the difference between proactive and reactive trolling, and the relationship between them. Based on a content analysis of 1,386 comments on 160 posts of 19 influencers during a Sina Weibo trolling event, we found that influencers troll more frequently than their followers and they troll proactively more often than reactively, while followers troll reactively more often than proactively. Influencers generated less but more impactful content compared with their followers. In both proactive and reactive trolling, influencers derailed the discussion while followers provoked through their proactive trolling and insulted through their reactive trolling. These findings extend the research scope of trolling asymmetry and establish theoretical connections between social media roles and proactive-reactive trolling. 87 Annual Meeting of the Association for Information Science & Technology | Oct. 25 – 29, 2024 | Calgary, AB, Canada.
Alzheimer’s Disease and related dementia (ADRD) is prevalent in one in nine individuals age 65 or above, and it has a 65% higher risk of incidence for African American/Black adults. With an aging population in the Un...
详细信息
Software engineering workflows use version control systems to track changes and handle merge cases from multiple contributors. This has introduced challenges to testing because it is impractical to test whole codebase...
详细信息
Software engineering workflows use version control systems to track changes and handle merge cases from multiple contributors. This has introduced challenges to testing because it is impractical to test whole codebases to ensure each change is defect-free, and it is not enough to test changed files alone. Just-in-time software defect prediction (JIT-SDP) systems have been proposed to solve this by predicting the likelihood that a code change is defective. Numerous techniques have been studied to build such JIT software defect prediction models, but the power of pre-trained code transformer language models in this task has been underexplored. These models have achieved human-level performance in code understanding and software engineering tasks. Inspired by that, we modeled the problem of change defect prediction as a text classification task utilizing these pre-trained models. We have investigated this idea on a recently published dataset, ApacheJIT, consisting of 44k commits. We concatenated the changed lines in each commit as one string and augmented it with the commit message and static code metrics. Parameter-efficient fine-tuning was performed for 4 chosen pre-trained models, JavaBERT, CodeBERT, CodeT5, and CodeReviewer, with either partially frozen layers or low-rank adaptation (LoRA). Additionally, experiments with the Local, Sparse, and Global (LSG) attention variants were conducted to handle long commits efficiently, which reduces memory consumption. As far as the authors are aware, this is the first investigation into the abilities of pre-trained code models to detect defective changes in the ApacheJIT dataset. Our results show that proper fine-tuning improves the defect prediction performance of the chosen models in the F1 scores. CodeBERT and CodeReviewer achieved a 10% and 12% increase in the F1 score over the best baseline models, JITGNN and JITLine, when commit messages and code metrics are included. Our approach sheds more light on the abilities of l
The rapid growth of data generated by Internet of Things (IoT) devices necessitates the development of advanced computational frameworks that can efficiently handle real-time data processing. Traditional cloud and edg...
详细信息
The gradual guarantee is an important litmus test for gradually typed languages, that is, languages that enable a mixture of static and dynamic typing. The gradual guarantee states that changing the precision of a typ...
详细信息
Current quantum generative adversarial networks (QGANs) still struggle with practical-sized data. First, many QGANs use principal component analysis (PCA) for dimension reduction, which, as our studies reveal, can dim...
详细信息
Accurately predicting the Remaining Useful Life(RUL)of lithium-ion batteries is crucial for battery management *** learning-based methods have been shown to be effective in predicting RUL by leveraging battery capacit...
详细信息
Accurately predicting the Remaining Useful Life(RUL)of lithium-ion batteries is crucial for battery management *** learning-based methods have been shown to be effective in predicting RUL by leveraging battery capacity time series ***,the representation learning of features such as long-distance sequence dependencies and mutations in capacity time series still needs to be *** address this challenge,this paper proposes a novel deep learning model,the MLP-Mixer and Mixture of Expert(MMMe)model,for RUL *** MMMe model leverages the Gated Recurrent Unit and Multi-Head Attention mechanism to encode the sequential data of battery capacity to capture the temporal features and a re-zero MLP-Mixer model to capture the high-level ***,we devise an ensemble predictor based on a Mixture-of-Experts(MoE)architecture to generate reliable RUL *** experimental results on public datasets demonstrate that our proposed model significantly outperforms other existing methods,providing more reliable and precise RUL predictions while also accurately tracking the capacity degradation *** code and dataset are available at the website of github.
暂无评论