Association for Computing Machinery

摘要： 压力信号是参与挖掘机电液比例控制的重要参数。目前，压力信号的获取依赖于压力传感器，但在恶劣的工作条件下，传感器容易出现故障，导致挖掘机控制失效。因此，提出一种基于长短时记忆(Long-short term memory, LSTM)网络的压力软测量模型。先分析SY375IDS挖掘机的液压系统原理，然后利用互信息法(Mutual information, MI)，确定了模型的输入。为了解决LSTM网络超参数选择困难的问题，利用贝叶斯优化(Bayesian optimization, BO)算法进行调优。最后，使用挖掘机90°甩方作业的实测压力数据验证了该模型的有效性。试验结果表明，与其他模型相比较，基于BO-LSTM的压力软测量模型具有更高的准确性和稳定性。考虑到多个传感器同时失效的情况，进行了进一步研究，构建基于BO-LSTM的多输出传统预测(Multi-output traditional prediction, MOTP)模型和多输出循环预测(Multi-output cyclic prediction, MOCP)模型。通过试验比较，MOCP模型表现出更优异的性能。

This research addresses the challenges associated with brain tumor classification by proposing a novel hybrid approach that combines feature selection and machine learning techniques. A median filter is employed to remove noise from MRI images, followed by feature extraction using the Grey Level Co-Occurrence Matrix (GLCM). To enhance classification accuracy, a hybrid Ant Colony Optimization with Crow Search Optimization Algorithm (HACCSA) is introduced for feature selection, identifying the most relevant features from the extracted set. The selected features are then used to train various machine learning classifiers, including Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and K-Nearest Neighbor (KNN). The classification performance is evaluated using k-fold cross-validation, demonstrating a significant improvement of $\mathbf{9 7 \%}$ compared to existing methods. This research contributes to the advancement of brain tumor classification by providing an effective and efficient approach that leverages feature selection and machine learning techniques.

Over the years, traditional tracing garbage collectors have accumulated assumptions that may not hold in new language designs.For instance, we usually assume that run-time objects do not hold addressable sub-parts and have a size of at least one pointer.These fail in systems striving to eliminate pointers and represent data in a dense, serialized form, such as the Gibbon compiler.We propose a new memory management strategy for language runtimes with mostly serialized heaps.It uses a hybrid, generational collector, where regions are bump-allocated into the young generation and objects are bump-allocated within those regions.Minor collections copy data into larger regions in the old generation, compacting it further.The old generation uses region-level reference counting.The resulting system maintains high performance for data traversal programs, while signicantly improving performance on other kinds of allocation patterns.

<p class="first" dir="auto" id="d1267377e82">Since 2017, SSP’s Mentorship Program has helped hundreds of publishing professionals to navigate the complexities, opportunities, and challenges of the scholarly publishing industry. For our mentees, the program offers a golden opportunity to discuss their workplace challenges and career goals in a safe environment uncomplicated by workplace dynamics. For our mentors, there is real value in giving back to the community by sharing their hard-earned publishing wisdom while also learning from their mentees. Feedback from our participants has generally been very positive, but we continue to look for improvements in our process. Our poster will highlight the key features of our approach and our successful track record, while emphasizing the need for continuing engagement from the SSP community. In this way, we hope to encourage new mentees to participate and to recruit more volunteer mentors to the program.

On behalf of ACM SIGCSE and the highly regarded RESPECT (Research on Equity and Sustained Participation in Engineering, Computing, and Technology) community, we are happy to announce that the RESPECT conference will now be integrated as one of the flagship conferences under the ACM SIGCSE umbrella. The Conference, recognized for its dedication to explore and promote diversity, equity, and inclusion in the fields of engineering, computing, and technology, aligns seamlessly with ACM SIGCSE's mission to foster innovation and excellence in computer science education worldwide.

Over the past ten years, many different approaches have been proposed for different aspects of the problem of resources management for long running, dynamic and diverse workloads such as processing query streams or distributed deep learning. ...

The 2023 ACM SIGIR Annual Business Meeting took place as a hybrid event during the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval in Taipei on July 26, 2023. The business meeting was led by the chair of the SIGIR Executive Committee (EC), Vanessa Murdock.

The COVID-19 pandemic led to a sudden shift to virtual work and events, with the last two years enabling an appropriated and rather simulated togetherness—the hybrid mode. As we return to in-person events, it is important to reflect on not only what we learned about technologies and social justice, but about the types of events we desire, and how to re-design them accordingly. This SIG aims to reflect on hybrid events and their execution: scaling them across sectors, communities, and industries; considering trade-offs when choosing technologies; studying best practices and defining measures of “success” for hybrid events; and finally, identifying and charting the wider social, ethical, and legal implications of hybrid formats. This SIG will consolidate these topics by inviting participants to collaboratively reflect on previous hybrid experiences and what can be learned from them.

research-article Free Access Share on ACM Publications Finances for 2021 Authors: Wendy Hall ACM Publications Board ACM Publications BoardSearch about this author , Divesh Srivastava ACM Publications Board ACM Publications BoardSearch about this author , Scott E. Delman ACM Director of Publications ACM Director of PublicationsSearch about this author Authors Info & Claims Communications of the ACMVolume 66Issue 4April 2023 pp 18–19https://doi.org/10.1145/3586184Published:23 March 2023Publication History 0citation0DownloadsMetricsTotal Citations0Total Downloads0Last 12 Months0Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteView all FormatsPDF

Context, as referred to situational factors related to the object of interest, can help infer the object's states or properties in visual recognition. As such contextual features are too diverse (across instances) to be annotated, existing attempts simply exploit image labels as supervision to learn them, resulting in various contextual tricks, such as features pyramid, context attention, etc. However, without carefully modeling the context's properties, especially its relation to the object, their estimated context can suffer from large inaccuracy. To amend this problem, we propose a novel Contextual Latent Generative Model (Context-LGM), which considers the object-context relation and models it in a hierarchical manner. Specifically, we firstly introduce a latent generative model with a pair of correlated latent variables to respectively model the object and context, and embed their correlation via the generative process. Then, to infer contextual features, we reformulate the objective function of Variational Auto-Encoder (VAE), where contextual features are learned as a posterior distribution conditioned on the object. Finally, to implement this contextual posterior, we introduce a Transformer that takes the object's information as a reference and locates correlated contextual factors. The effectiveness of our method is verified by state-of-the-art performance on two context-aware object recognition tasks, i.e. lung cancer prediction and emotion recognition.