Pub Date : 2023-03-09DOI: 10.4000/books.irasec.3635
Gabriel Camară
{"title":"L’Asie du Sud-Est 2019 : bilan, enjeux et perspectives","authors":"Gabriel Camară","doi":"10.4000/books.irasec.3635","DOIUrl":"https://doi.org/10.4000/books.irasec.3635","url":null,"abstract":"","PeriodicalId":47420,"journal":{"name":"Journal of Contemporary Asia","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43317470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-06DOI: 10.1080/00472336.2023.2182228
Hasan H. Karrar
{"title":"Highways to the End of the World. Roads, Roadmen and Power in South Asia","authors":"Hasan H. Karrar","doi":"10.1080/00472336.2023.2182228","DOIUrl":"https://doi.org/10.1080/00472336.2023.2182228","url":null,"abstract":"","PeriodicalId":47420,"journal":{"name":"Journal of Contemporary Asia","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49448000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1080/00472336.2023.2176782
Taehwan Kim, S. Lee
{"title":"Double Poverty: Class, Employment Type, Gender and Time Poor Precarious Workers in the South Korean Service Economy","authors":"Taehwan Kim, S. Lee","doi":"10.1080/00472336.2023.2176782","DOIUrl":"https://doi.org/10.1080/00472336.2023.2176782","url":null,"abstract":"","PeriodicalId":47420,"journal":{"name":"Journal of Contemporary Asia","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49451123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01Epub Date: 2023-03-28DOI: 10.1145/3580804
Jeya Vikranth Jeyakumar, Ankur Sarker, Luis Antonio Garcia, Mani Srivastava
End-to-end deep learning models are increasingly applied to safety-critical human activity recognition (HAR) applications, e.g., healthcare monitoring and smart home control, to reduce developer burden and increase the performance and robustness of prediction models. However, integrating HAR models in safety-critical applications requires trust, and recent approaches have aimed to balance the performance of deep learning models with explainable decision-making for complex activity recognition. Prior works have exploited the compositionality of complex HAR (i.e., higher-level activities composed of lower-level activities) to form models with symbolic interfaces, such as concept-bottleneck architectures, that facilitate inherently interpretable models. However, feature engineering for symbolic concepts-as well as the relationship between the concepts-requires precise annotation of lower-level activities by domain experts, usually with fixed time windows, all of which induce a heavy and error-prone workload on the domain expert. In this paper, we introduce X-CHAR , an eXplainable Complex Human Activity Recognition model that doesn't require precise annotation of low-level activities, offers explanations in the form of human-understandable, high-level concepts, while maintaining the robust performance of end-to-end deep learning models for time series data. X-CHAR learns to model complex activity recognition in the form of a sequence of concepts. For each classification, X-CHAR outputs a sequence of concepts and a counterfactual example as the explanation. We show that the sequence information of the concepts can be modeled using Connectionist Temporal Classification (CTC) loss without having accurate start and end times of low-level annotations in the training dataset-significantly reducing developer burden. We evaluate our model on several complex activity datasets and demonstrate that our model offers explanations without compromising the prediction accuracy in comparison to baseline models. Finally, we conducted a mechanical Turk study to show that the explanations provided by our model are more understandable than the explanations from existing methods for complex activity recognition.
端到端深度学习模型越来越多地应用于安全关键型人类活动识别（HAR）应用中，例如医疗保健监测和智能家居控制，以减轻开发人员的负担，提高预测模型的性能和鲁棒性。然而，将 HAR 模型集成到安全关键型应用中需要信任，最近的方法旨在平衡深度学习模型的性能与复杂活动识别的可解释决策。之前的研究利用了复杂 HAR 的组成性（即由低级活动组成的高级活动），形成了具有符号接口的模型，如概念瓶颈架构，从而促进了模型的内在可解释性。然而，符号概念的特征工程--以及概念之间的关系--需要领域专家对低层活动进行精确标注，通常需要固定的时间窗口，所有这些都给领域专家带来了繁重且容易出错的工作量。本文介绍的 X-CHAR 是一种可解释的复杂人类活动识别模型，它不需要对低层次活动进行精确标注，而是以人类可理解的高层次概念形式提供解释，同时保持端到端深度学习模型对时间序列数据的稳健性能。X-CHAR 以概念序列的形式学习复杂活动识别建模。对于每个分类，X-CHAR 都会输出一个概念序列和一个反事实例子作为解释。我们的研究表明，概念的序列信息可以使用连接时序分类（CTC）损失来建模，而无需在训练数据集中有准确的低级注释的开始和结束时间--这大大减轻了开发人员的负担。我们在多个复杂活动数据集上评估了我们的模型，结果表明，与基线模型相比，我们的模型在不影响预测准确性的情况下提供了解释。最后，我们进行了一项机械 Turk 研究，证明我们的模型提供的解释比现有复杂活动识别方法提供的解释更容易理解。
{"title":"X-CHAR: A Concept-based Explainable Complex Human Activity Recognition Model.","authors":"Jeya Vikranth Jeyakumar, Ankur Sarker, Luis Antonio Garcia, Mani Srivastava","doi":"10.1145/3580804","DOIUrl":"10.1145/3580804","url":null,"abstract":"<p><p>End-to-end deep learning models are increasingly applied to safety-critical human activity recognition (HAR) applications, e.g., healthcare monitoring and smart home control, to reduce developer burden and increase the performance and robustness of prediction models. However, integrating HAR models in safety-critical applications requires trust, and recent approaches have aimed to balance the performance of deep learning models with explainable decision-making for complex activity recognition. Prior works have exploited the compositionality of complex HAR (i.e., higher-level activities composed of lower-level activities) to form models with symbolic interfaces, such as concept-bottleneck architectures, that facilitate inherently interpretable models. However, feature engineering for symbolic concepts-as well as the relationship between the concepts-requires precise annotation of lower-level activities by domain experts, usually with fixed time windows, all of which induce a heavy and error-prone workload on the domain expert. In this paper, we introduce <i>X-CHAR</i> , an eXplainable Complex Human Activity Recognition model that doesn't require precise annotation of low-level activities, offers explanations in the form of human-understandable, high-level concepts, while maintaining the robust performance of end-to-end deep learning models for time series data. <i>X-CHAR</i> learns to model complex activity recognition in the form of a sequence of concepts. For each classification, <i>X-CHAR</i> outputs a sequence of concepts and a counterfactual example as the explanation. We show that the sequence information of the concepts can be modeled using Connectionist Temporal Classification (CTC) loss without having accurate start and end times of low-level annotations in the training dataset-significantly reducing developer burden. We evaluate our model on several complex activity datasets and demonstrate that our model offers explanations without compromising the prediction accuracy in comparison to baseline models. Finally, we conducted a mechanical Turk study to show that the explanations provided by our model are more understandable than the explanations from existing methods for complex activity recognition.</p>","PeriodicalId":47420,"journal":{"name":"Journal of Contemporary Asia","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10961595/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80887756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1080/00472336.2023.2181204
P. Prime
{"title":"The China-led Belt and Road Initiative and its Reflections: The Crisis of Hegemony and Changing Global Orders","authors":"P. Prime","doi":"10.1080/00472336.2023.2181204","DOIUrl":"https://doi.org/10.1080/00472336.2023.2181204","url":null,"abstract":"","PeriodicalId":47420,"journal":{"name":"Journal of Contemporary Asia","volume":"53 1","pages":"902 - 904"},"PeriodicalIF":2.2,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41757389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-28DOI: 10.1080/00472336.2023.2174167
Szu-Yun Hsu
{"title":"Populism in Taiwan: Rethinking the Neo-liberalism–Populism Nexus","authors":"Szu-Yun Hsu","doi":"10.1080/00472336.2023.2174167","DOIUrl":"https://doi.org/10.1080/00472336.2023.2174167","url":null,"abstract":"","PeriodicalId":47420,"journal":{"name":"Journal of Contemporary Asia","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44721578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-06DOI: 10.1080/00472336.2023.2170265
S. Macwilliam
{"title":"Pacific Islands Guestworkers in Australia. The New Blackbirds?","authors":"S. Macwilliam","doi":"10.1080/00472336.2023.2170265","DOIUrl":"https://doi.org/10.1080/00472336.2023.2170265","url":null,"abstract":"","PeriodicalId":47420,"journal":{"name":"Journal of Contemporary Asia","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45553653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-01DOI: 10.1080/00472336.2023.2168207
T. Fleckenstein, Soohyung Lee, Jaehyoung Park
{"title":"Skills and Training in Hierarchical Capitalism: The Rise and Fall of Vocational Training in South Korea","authors":"T. Fleckenstein, Soohyung Lee, Jaehyoung Park","doi":"10.1080/00472336.2023.2168207","DOIUrl":"https://doi.org/10.1080/00472336.2023.2168207","url":null,"abstract":"","PeriodicalId":47420,"journal":{"name":"Journal of Contemporary Asia","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48928537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号