检索结果-内蒙古大学图书馆

35th IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2024

作者： Zhang, Shenglin Xiong, Xiao Li, Mengyao Sun, Yongqian Zhao, Yongxin Chen, Xia Deng, Bowen Pei, Dan Nankai University China Haihe Laboratory of Information Technology Application Innovation China Tianjin Key Laboratory of Software Experience and Human Computer Interaction China Huawei Cloud Tsinghua University Beijing National Research Center for Information Science and Technology China

ISBN: (纸本)9798350367041

Conducting stress testing is essential to ensure the stability and performance of software systems post-launch. Among its various aspects, the real-time identification of the "Smooth Load Area"(SLA) is crucial for establishing performance benchmarks, identifying bottlenecks, guiding optimization strategies, and strategically allocating resources. However, existing methods are incapable of real-time inflection point detection or require manual intervention. This paper proposes Auto-PIP, an automated identification framework for performance inflection points based on key performance indicators (KPIs) during performance stress tests. Auto-PIP integrates trend testing algorithms with unsupervised anomaly detection algorithms to identify optimal operating points and estimate maximum capacity. Auto-PIP has been deployed in Huawei Cloud, and the evaluation results show that Auto-PIP demonstrated 100% accuracy in optimal inflection point detection, a 41.7% leap over baselines, and 83.9% accuracy in maximum point identification, a 10.7% gain. Additionally, we have released the dataset to the public to promote ongoing research. © 2024 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

InterLink: Linking Text with Code and Output in Computational Notebooks 25

InterLink: Linking Text with Code and Output in Computationa...

引用

2025 CHI Conference on human Factors in Computing Systems, CHI 2025

作者： Lin, Yanna Yang, Leni Li, Haotian Qu, Huamin Moritz, Dominik Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong Human-Computer Interaction Institute Carnegie Mellon University Pittsburgh PA United States Microsoft Research Asia Beijing China

ISBN: (纸本)9798400713941

Computational notebooks, widely used for ad-hoc analysis and often shared with others, can be difficult to understand because the standard linear layout is not optimized for reading. In particular, related text, code, and outputs may be spread across the UI making it difficult to draw connections. In response, we introduce InterLink, a plugin designed to present the relationships between text, code, and outputs, thereby making notebooks easier to understand. In a formative study, we identify pain points and derive design requirements for identifying and navigating relationships among various pieces of information within notebooks. Based on these requirements, InterLink features a new layout that separates text from code and outputs into two columns. It uses visual links to signal relationships between text and associated code and outputs and offers interactions for navigating related pieces of information. In a user study with 12 participants, those using InterLink were 13.6% more accurate at finding and integrating information from complex analyses in computational notebooks. These results show the potential of notebook layouts that make them easier to understand. © 2025 Copyright held by the owner/author(s).

关键词： Computational Notebook Interactive Computational Notebook Text-Code/Output Linking User Comprehension

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time Series Anomaly Detection based on Pre-trained Models with Dual-Attention Mechanism 35

Multivariate Time Series Anomaly Detection based on Pre-trai...

引用

35th IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2024

作者： Sun, Yongqian Guo, Yang Liang, Minghan Wen, Xidao Kuang, Junhua Zhang, Shenglin Li, Hongbo Xia, Kaixu Pei, Dan Nankai University China Tianjin Key Laboratory of Software Experience and Human Computer Interaction China BizSeer Haihe Laboratory of Information Technology Application Innovation China Tencent Tsinghua University Beijing National Research Center for Information Science and Technology China

ISBN: (纸本)9798350367041

In major tech companies, monitoring server performance data with anomaly detection algorithms is crucial for assessing operational status. Existing models often require separate training or fine-tuning for each server due to generalization limitations, leading to increased storage, memory, and training costs. As the number of servers grows, this approach becomes impractical. To address this, we propose using pretrained language models for time series anomaly detection, leveraging their strong generalization capabilities. Specifically, we employ two pre-trained GPT-2 models as backbones and implement a two-stage fine-tuning strategy to retain learned knowledge while adapting to specific business data characteristics. Our experiments on multiple anomaly detection datasets demonstrate that our method achieves the best average F1-Score, outperforming the leading baseline by 7%. © 2024 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

How are ML-Based Online Content Moderation Systems Actually Used? Studying Community Size, Local Activity, and Disparate Treatment 22

How are ML-Based Online Content Moderation Systems Actually ...

引用

5th ACM Conference on Fairness, Accountability, and Transparency, FAccT 2022

作者： Wang, Leijie Zhu, Haiyi Department of Computer Science and Technology Tsinghua University Beijing China Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States

ISBN: (纸本)9781450393522

Machine learning-based predictive systems are increasingly used to assist online groups and communities in various content moderation tasks. However, there are limited quantitative understandings of whether and how different groups and communities use such predictive systems differently according to their community characteristics. In this research, we conducted a field evaluation of how content moderation systems are used in 17 Wikipedia language communities. We found that 1) larger communities tend to use predictive systems to identify the most damaging edits, while smaller communities tend to use them to identify any edit that could be damaging;2) predictive systems are used less in content areas where there are more local editing activities;3) predictive systems have mixed effects on reducing disparate treatment between anonymous and registered editors across communities of different characteristics. Finally, we discuss the theoretical and practical implications for future human-centered moderation algorithms. © 2022 Owner/Author.

关键词： Online systems

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Feasibility of Predicting Information Relevance During Sensemaking with Eye Gaze Data

Evaluating the Feasibility of Predicting Information Relevan...

引用

International Symposium on Mixed and Augmented Reality (ISMAR)

作者： Ibrahim A. Tahmid Lee Lisle Kylie Davidson Kirsten Whitley Chris North Doug A. Bowman Department of Computer Science Center for Human-Computer Interaction Virginia Tech US Department of Defense

Eye gaze patterns vary based on reading purpose and complexity, and can provide insights into a reader’s perception of the content. We hypothesize that during a complex sensemaking task with many text-based documents, we will be able to use eye-tracking data to predict the importance of documents and words, which could be the basis for intelligent suggestions made by the system to an analyst. We introduce a novel eye-gaze metric called ‘GazeScore’ that predicts an analyst’s perception of the relevance of each document and word when they perform a sensemaking task. We conducted a user study to assess the effectiveness of this metric and found strong evidence that documents and words with high GazeScores are perceived as more relevant, while those with low GazeScores were considered less relevant. We explore potential real-time applications of this metric to facilitate immersive sensemaking tasks by offering relevant suggestions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition from Eye Movements Using Multi-way Autoregressive Model

Emotion Recognition from Eye Movements Using Multi-way Autor...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Ma, Tian-Fang Liu, Xuan-Hao Zheng, Wei-Long Lu, Bao-Liang Shanghai Jiao Tong University Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai China

ISBN: (纸本)9798350386226

The application of physiological signals in emotion recognition is a popular research topic in human-computer interactions. Eye movement, as an important physiological signal, plays an essential role in medicine, psychology, cognitive science, and other scientific research fields. Previous studies have successfully identified human emotions by combining various eye-related measurements, selecting features, and utilizing machine learning techniques. However, the exploration of eye movement signals in emotion recognition remains insufficient. In this study, we utilize eye tracking heatmap and eye movement trajectory data for emotion recognition for the first time. Based on the two types of eye movement data, we develop a multi-way autoregressive model capable of processing multi-view eye movement data. Compared to traditional deep learning baseline models, our model better adapts to the structure of eye movement data and significantly improves the classification performance. Furthermore, we integrate heatmap and trajectory data with commonly used eye-related measurement features, which further enhance the performance of emotion recognition beyond previous methods. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Tonic and Event-Related Phasic Transcutaneous Auricular Vagus Nerve Stimulation Alters Pupil Responses in the Change-Detection Task

引用

Neuromodulation 2025年第4期28卷 652-662页

作者： Chen, Jingxin Ke, Yufeng Ni, Guangjian Liu, Shuang Ming, Dong Academy of Medical Engineering and Translational Medicine Tianjin International Joint Research Centre for Neural Engineering Tianjin Key Laboratory of Brain Science and Neural Engineering Tianjin University Tianjin China Department of Biomedical Engineering College of Precision Instrument and Optoelectronics Engineering Tianjin University Tianjin China Haihe Laboratory of Brain-computer Interaction and Human-machine Integration Tianjin China

Background: Transcutaneous auricular vagus nerve stimulation (taVNS) has emerged as a potential modulator of cognitive behavior that activates the locus coeruleus-noradrenaline (LC-NA) system. Previous studies explored both phasic and tonic taVNS by investigating their impact on LC-NA markers such as pupil dilation and heart rate variability (HRV). Objective: Inconsistencies persist in the identification of reliable markers for assessing the effects of taVNS on noradrenergic activity. Furthermore, it remains unclear whether the effects of taVNS extend beyond pure vagal nerve responses, particularly in specific cognitive domains such as working memory. In the present study, we investigated the effects of taVNS on working memory capacity and LC-NA markers using a change-detection task. Materials and Methods: Twenty-two healthy, right-handed university students participated in a sham-controlled, randomized cross-over experiment with four sessions. We applied two types of phasic and event-related stimulation (Pre-event and Event-synchronous), tonic stimulation (Pre-task), and sham stimulation across different sessions. Pupil size and electrocardiogram data were recorded during the tasks. Results: taVNS did not significantly modulate behavioral performance on the change-detection task, specifically working memory capacity. However, both tonic and event-related phasic taVNS significantly influenced the pupillary response during the task. In addition, the Pre-task condition of the taVNS affected the low-frequency parameter of HRV. Conclusions: Our findings suggest that tonic and event-related phasic taVNS may modulate noradrenergic activity, as evidenced by pupil responses and HRV changes during the change-detection task. This study provides new evidence regarding the impact of taVNS on cognitive tasks, thus supporting the development of noninvasive neuromodulation interventions. © 2025 International Neuromodulation Society

关键词： Heart rate variability (HRV) LC-NA pupil response pupillometry taVNS

来源：评论

学校读者我要写书评

暂无评论

Opportunities for Serious Game Technologies to Engage Children with Autism in a Pakistani Sociocultural and Institutional Context: An investigation of the design space for serious game technologies to enhance engagement of children with autism and to facilitate external support provided 34

Opportunities for Serious Game Technologies to Engage Childr...

引用

34th Australian computer-human interaction Conference: Connected Creativity, OzCHI 2022

作者： Muneeb, Sara Sitbon, Laurianne Ahmad, Faizan Research Center for Human Computer Interaction Comsats University Islamabad Lahore Campus Pakistan Department of Computer Science Queensland University of Technology Australia Department of Computer Science School of Technologies Cardiff Metropolitan University United Kingdom

ISBN: (纸本)9798400700248

Usability and design of serious game technologies have been widely investigated as academic interventions tools for children with autism. However, besides the technology, the sociocultural and institutional context also impacts the gameplay activities of children with autism as well as the external support provided by instructors. Therefore, this paper investigates i) the impact of sociocultural and institutional context over the engagement of children with autism with serious game technologies, ii) the types of external support children with autism are offered or require during gameplay session, and iii) the type of rewards and encouragers that can act as unbiased support to increase the engagement of the children with autism during gameplay. This paper investigates these factors with an inductive analysis of educational gameplay activities of 23 children with autism in Lahore, Pakistan. Our study found that sociocultural and institutional context has substantial impact over the gameplay activities of children with autism. Children required both physical and verbal support during the gameplay activities, and institutional context influences the behavior of instructors as well. Finally, dynamic animations, rewards and encouragers can keep the children engaged for longer in the gameplay. © 2022 ACM.

关键词： Serious games

来源：评论

学校读者我要写书评

暂无评论

Spaces to Think: A Comparison of Small, Large, and Immersive Displays for the Sensemaking Process

Spaces to Think: A Comparison of Small, Large, and Immersive...

引用

International Symposium on Mixed and Augmented Reality (ISMAR)

作者： Lee Lisle Kylie Davidson Leonardo Pavanatto Ibrahim A. Tahmid Chris North Doug A. Bowman Department of Computer Science Center for Human-Computer Interaction Virginia Tech Department of Computer Science Sanghani Center Virginia Tech

Analysts need to process large amounts of data in order to extract concepts, themes, and plans of action based upon their findings. Different display technologies offer varying levels of space and interaction methods that change the way users can process data using them. In a comparative study, we investigated how the use of single traditional monitor, a large, high-resolution two-dimensional monitor, and immersive three-dimensional space using the Immersive Space to Think approach impact the sensemaking process. We found that user satisfaction grows and frustration decreases as available space increases. We observed specific strategies users employ in the various conditions to assist with the processing of datasets. We also found an increased usage of spatial memory as space increased, which increases performance in artifact position recall tasks. In future systems supporting sensemaking, we recommend using display technologies that provide users with large amounts of space to organize information and analysis artifacts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving the Interpretability through Maximizing Mutual Information for EEG Emotion Recognition

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 744-757页

作者： Yang, Hua Philip Chen, C.L. Chen, Bianna Zhang, Tong North Carolina State University Department of Computer Science United States South China University of Technology Guangdong Provincial Key Laboratory of AI Large Model and Intelligent Cognition The School of Computer Science and Engineering Guangzhou510006 China Pazhou Lab Guangzhou510335 China Engineering Research Center The Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangzhou China

Trustworthy Graph Neural Networks (GNNs) for EEG emotion recognition should identify emotions accurately and elucidate corresponding rationales. Current GNNs have achieved notable performance by dynamically modeling emotional connections between EEG channels. However, these GNNs lack interpretability due to the absence of explicit rationale behind their predictions. This paper conducts a comprehensive identification of important EEG channels to enhance the interpretability of EEG emotion recognition from the perspective of mutual information. Specifically, an Adjacency-Explainable Graph Neural Network (AEG) for ante-hoc interpretability is proposed to capture genuine EEG emotional connections, which gives a theoretical guarantee to remove spurious connections. Moreover, a Channel-wise Adaptive Class Activation Mapping Explainer (CACA) for post-hoc interpretability is developed to locate the EEG channels that contribute most to predictions. Experimental results on three datasets, i.e., SEED, SEED-IV, and DREAMER, prove that imbuing training processes with enhanced interpretability ensures significant performance improvements in emotion recognition. Quantitative comparisons of post-hoc interpretability also demonstrate the superiority of CACA. Furthermore, this paper illustrates two potential applications of the proposed methodologies, showing their broader utility and significance. © 2010-2012 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：