检索结果-内蒙古大学图书馆

7th International Conference on Digital Medicine and Image processing, DMIP 2024

作者： Li, Mengqi Qi, Senrong Zhu, Xuemei Niu, Kai Han, Jianhui Li, Ying He, Zhiqiang Key Laboratory of Universal Wireless Communications Ministry of Education Beijing University of Posts and Telecommunications Beijing China Beijing Stomatological Hospital & School of Stomatology Capital Medical University Beijing China Beijing University of Posts and Telecommunications Hospital Beijing China

ISBN: (纸本)9798400709586

Landmark detection is an essential foundation of cephalometric analysis, playing a crucial role in clinical diagnosis and treatment of orthodontic and orthognathic conditions. This paper proposes a novel framework that enables targeted learning and extraction of structural and medical features based on neural network. Specifically, our framework's key components comprise Contour Sharpener, Coupling Transformer, and Progressively Targeted Feature Extraction Networks (PT-FENet). The Contour Sharpener intensifies contour features informed by the prior distributions of landmarks, enabling the network to learn anatomical structural features. The Coupling Transformer couples and transforms associated landmarks based on the similarity of features around medically related landmarks and the invariant structure of geometrically constrained landmarks to enhance the learning of anatomical structures and medical correlations among them. PT-FENet fully extracts multi-scale features and progressively targets the refinement of anatomical structural and medical features grounded in prior knowledge, thereby augmenting the attention towards detection information. Experimental results demonstrate that our method outperforms existing state-of-the-art methods on public dataset. Our method enables rapid batch processing of images for precise landmark detection, thus possessing significant value in clinical cephalometric analysis and orthodontic applications. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of batch file intelligent summary assistant based on AIGC+RPA 24

Design and implementation of batch file intelligent summary ...

引用

8th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2024

作者： Lin, Meirong Information Engineering College Hainan Vocational University of Science and Technology Hainan Haikou China

ISBN: (纸本)9798400710094

This paper presents the design and implementation of a batch file intelligent summary assistant based on AIGC and RPA. This system aims to solve the problem of large human resource consumption and low efficiency in batch document processing. By combining the ability of text summary generation of AIGC technology and efficient document processing ability of RPA technology, it can realize the rapid and accurate summary of a large number of documents. This project describes in detail the overall process design of the system, the specific implementation methods of AIGC module and RPA module, summarizes the research results, and puts forward the future research direction. This study provides new ideas and technical support for improving the efficiency of batch file processing. © 2024 Copyright held by the owner/author(s).

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

Eco-Friendly Fabrication of Suspended 1D Nanoheaters for Ultralow Power TCD-Type Gas Sensors 38

Eco-Friendly Fabrication of Suspended 1D Nanoheaters for Ult...

引用

38th IEEE International Conference on Micro Electro Mechanical Systems, MEMS 2025

作者： Cho, Wootaek Yoo, Jihyeon Kwak, Jong-Hyun Shin, Heungjoo Korea Republic of

ISBN: (纸本)9798331508890

We developed a simple and eco-friendly fabrication method of a suspended 1D nanoheater for ultralow power thermal conductivity detector (TCD)-type gas sensors. The nanoheater was fabricated through selective metal deposition on the unique suspended carbon nanogrid, which acted as a shadow mask during the metal deposition process. Consequently, the nanoheaters can be fabricated using only a simple four-step microscale batch process (photolithography-pyrolysis-photolithography-metallization) without using any harmful etching. Due to the high surface-to-volume ratio and small size of the nanoheater, the nanoheater-based TCD-type gas sensor enabled ultrafast gas detection, facilitating pulse-width modulation-based sensor operation at 300 nW. © 2025 IEEE.

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-batch Pipeline 25

Klotski: Efficient Mixture-of-Expert Inference via Expert-Aw...

引用

30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2025

作者： Fang, Zhiyuan Huang, Yuegui Hong, Zicong Lyu, Yufeng Chen, Wuhui Yu, Yue Yu, Fan Zheng, Zibin Sun Yat-sen University Zhuhai China Sun Yat-sen University Guangzhou China Hong Kong University of Science and Technology Hong Kong Huawei Technologies Co. Ltd Shenzhen China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9798400710797

Mixture of Experts (MoE), with its distinctive sparse structure, enables the scaling of language models up to trillions of parameters without significantly increasing computational costs. However, the substantial parameter size presents a challenge for inference, as the expansion in GPU memory cannot keep pace with the growth in parameters. Although offloading techniques utilise memory from the CPU and disk and parallelise the I/O and computation for efficiency, the computation for each expert in MoE models is often less than the I/O, resulting in numerous bubbles in the pipeline. Therefore, we propose Klotski, an efficient MoE inference engine that significantly reduces pipeline bubbles through a novel expert-aware multi-batch pipeline paradigm. The proposed paradigm uses batch processing to extend the computation time of the current layer to overlap with the loading time of the next layer. Although this idea has been effectively applied to dense models, more batches may activate more experts in the MoE, leading to longer loading times and more bubbles. Thus, unlike traditional approaches, we balance computation and I/O time and minimise bubbles by orchestrating their inference orders based on their heterogeneous computation and I/O requirements and activation patterns under different batch numbers. Moreover, to adapt to different hardware environments and models, we design a constraint-sensitive I/O-compute planner and a correlation-aware expert prefetcher for a schedule that minimises pipeline bubbles. Experimental results demonstrate that Klotski achieves a superior throughput-latency trade-off compared to state-of-the-art techniques, with throughput improvements of up to 85.12x. © 2025 ACM.

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

Fair-Sharing Simulator for batch Computing Systems 15th

Fair-Sharing Simulator for Batch Computing Systems

引用

15th International Conference on Parallel processing and Applied Mathematics, PPAM 2024

作者： Klusáček, Dalibor CESNET Prague Czech Republic

ISBN: (纸本)9783031856990

Scientific computing centers or private (in-house) cloud data centers do not rely on the standard pay-as-you-go business model which is common in commercial clouds to allocate resources. Instead, the system is typically shared by a set of selected users, and the administrator’s job is to ensure that resources are shared fairly given the existing policies of that organization. One common approach, especially in batch systems, is to deploy a fairshare-based prioritization in the scheduler, where a prioritization mechanism balances resource consumption so that individual users get the right shares of resources over time. In this paper, we present a tool developed to simulate the fairshare setting in a batch system. Using a set of experiments, we demonstrate the utility of this tool in tuning fairshare settings in a standard HPC/HTC scheduler and present the impact of often-overlooked additional options for modifying the basic fairshare settings. All the findings in this paper are based on our real-world experience of running and optimizing a distributed national computing infrastructure in the Czech Republic. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

Event-Driven Architectures for Real-Time Analytics in Big data Systems 1

Event-Driven Architectures for Real-Time Analytics in Big Da...

引用

1st International Conference on Advances in Computer Science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Singh, Khushmeet Kumar, Naresh Desai, Piyush Bipinkumar Katyayan, Shashank Shekhar Changalreddy, Vybhav Reddy Kammireddy Jain, Arpit Dr. A.P.J. Abdul Kalam Technical University Uttar Pradesh Lucknow226031 India Greater Noida201306 India Tamil Nadu Vellore632014 India Eli Broad College of Business Michigan State University East LansingMI United States Bowling Green State University Bowling GreenOH43403 United States Koneru Lakshmaiah Education Foundation Department of CSE A.P. Vedeshwaram India

ISBN: (纸本)9798331518578

The buzzword in big data processing is Event-Driven Architecture (EDA), which is proving to be an effective alternative to processing data in real-time. As we know, the traditional batch processing methods are not enough to meet the demand for real-time analytics owing to the exponential growth of Big data. Event-driven architecture provides a loosely coupled and scalable implementation, as it decouples the components of a system, where data flows between them asynchronously in response to events. We have built upon the principles of EDA and its applications in the domain of real-time analytics for Big data. There are three moving parts to an EDA: an event producer, an event broker, and an event consumer. On the event producer, you will create events according to when the data changes in data or drive an event based on the user acting;it gets saved into the event broker. The consumer then consumes this data, processes events and produces insights in real-time. EDA has several benefits for big data systems. It is able to process large amounts of data simultaneously in real-time to facilitate timely decision-making for organizations. It has fault tolerance and horizontal scalability so that it can handle spikes well. It also offers greater ease of processing events and improved integration with diverse data sources. Pervasive phenomenon of Big data: with, EDA is emerging as a viable contender in real-time analytics processing. © 2025 IEEE.

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding 24

ProPD: Dynamic Token Tree Pruning and Generation for LLM Par...

引用

43rd International Conference on Computer-Aided Design, ICCAD 2024

作者： Zhong, Shuzhang Yang, Zebin Gong, Ruihao Wang, Runsheng Huang, Ru Li, Meng Institute for Artificial Intelligence Peking University Beijing China School of Integrated Circuits Peking University Beijing China Sensetime Research Beijing China Institute of Electronic Design Automation Peking University Wuxi China Beijing Advanced Innovation Center for Integrated Circuits Beijing China

ISBN: (纸本)9798400710773

Recent advancements in generative large language models (LLMs) have significantly boosted the performance in natural language processing tasks. However, their efficiency is constrained by the inherent limitations in autoregressive token generation. While parallel decoding with token tree verification, e.g., Medusa, has been proposed to improve decoding parallelism and efficiency, it often struggles with maintaining contextual relationships due to its independent token prediction approach and incurs significant verification overhead, especially with large tree sizes and batch processing. In this paper, we propose ProPD, an efficient LLM parallel decoding framework based on dynamic token tree pruning and generation. ProPD features an advanced early pruning mechanism to efficiently eliminate unpromising token sequences to improve verification efficiency. Additionally, it introduces a dynamic token tree generation algorithm to balance the computation and parallelism of the verification phase in real-time and maximize the overall efficiency across different batch sizes, sequence lengths, and tasks, etc. We verify ProPD across a diverse set of datasets, LLMs, and batch sizes and demonstrate ProPD consistently outperforms existing decoding algorithms by 1.1-3.2 ×. © 2024 Copyright is held by the owner/author(s).

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

Automated Precision in Food Packaging: A Cost-Effective Solution for Emerging Companies 4th

Automated Precision in Food Packaging: A Cost-Effective Sol...

引用

4th International Conference on Advanced Research in Technologies, Information, Innovation and Sustainability 2024, ARTIIS 2024

作者： Terneus, Juan Diego Moya, Viviana Abedrabbo, Faruk Vásconez, Juan Pablo Moya, Marcelo Facultad de Ciencias Técnicas Universidad Internacional Del Ecuador UIDE Quito170411 Ecuador Energy Transformation Center Faculty of Engineering Universidad Andres Bello Santiago7500971 Chile

ISBN: (纸本)9783031832093

This study aims to automate the packaging process efficiently and enhance production in emerging companies. A prototype that integrates mechanical, electronic, and control design was developed to achieve mass-controlled filling with precise measurements and efficient batch processing. The system features a screw conveyor mechanism and a rotary drum mechanism, employing a cascade control strategy with a Proportional-Integral (PI) controller to accurately regulate motor speed. Extensive testing of the filling machine demonstrated its capability to fill 100 g containers with an error margin of ±5 g and an average filling time of 1.08 min per container. These results highlighted the system’s exceptional accuracy and efficiency. A cost analysis of implementing this machine in the Ecuadorian Tervide Company was also provided. The proposed methodology shows significant potential to enhance efficiency and accuracy in filling food products for emerging companies, establishing a precedent for sustainable production improvements globally. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

Tiny Deep Ensemble: Uncertainty Estimation in Edge AI Accelerators via Ensembling Normalization Layers with Shared Weights 24

Tiny Deep Ensemble: Uncertainty Estimation in Edge AI Accele...

引用

43rd International Conference on Computer-Aided Design, ICCAD 2024

作者： Ahmed, Soyed Tuhin Hefenbrock, Michael Tahoori, Mehdi B. Karlsruhe Institute of Technology RevoAI GmbH Germany

ISBN: (纸本)9798400710773

The applications of artificial intelligence (AI) are rapidly evolving, and they are also commonly used in safety-critical domains, such as autonomous driving and medical diagnosis, where functional safety is paramount. In AI-driven systems, uncertainty estimation allows the user to avoid overconfidence predictions and achieve functional safety. Therefore, the robustness and reliability of model predictions can be improved. However, conventional uncertainty estimation methods, such as the deep ensemble method, impose high computation and accordingly hardware (latency and energy) overhead because they require the storage and processing of multiple models. Alternatively, Monte Carlo dropout (MC-dropout) methods, although having low memory overhead, necessitate numerous (~ 100) forward passes, leading to high computational overhead and latency. Thus, these approaches are not suitable for battery-powered edge devices with limited computing and memory resources. In this paper, we propose the Tiny-Deep Ensemble approach, a low-cost approach for uncertainty estimation on edge devices. In our approach, only normalization layers are ensembled M times, with all ensemble members sharing common weights and biases, leading to a significant decrease in storage requirements and latency. Moreover, our approach requires only one forward pass in a hardware architecture that allows batch processing for inference and uncertainty estimation. Furthermore, it has approximately the same memory overhead compared to a single model. Therefore, latency and memory overhead are reduced by a factor of up to ~ M×. Nevertheless, our method does not compromise accuracy, with an increase in inference accuracy of up to ~ 1% and a reduction in RMSE of 17.17% in various benchmark datasets, tasks, and state-of-the-art architectures. © 2024 Copyright is held by the owner/author(s).

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

batch process quality prediction based on TFCMixer modeling

SSRN

引用

SSRN 2025年

作者： Zhao, Xiaoqiang Liu, Yongyong Hui, Yonyong Liu, Kai Yao, Qinglei College of Electrical and Information Engineering Lanzhou University of Technology Lanzhou730050 China Gansu Key Laboratory Advanced Control for Industrial Processes Lanzhou University of Technology Lanzhou730050 China National Experimental Teaching Center of Electrical and Control Engineering Lanzhou University of Technology Lanzhou730050 China

Deep learning models are now widely used for the prediction of quality variables in batch processes. However, the dynamics and nonlinearities of batch processes, and long training time of deep learning models are unfavorable for quality prediction. To address these issues, an batch process quality prediction method based on the Temporal Feature Convolutional Mixer (TFCMixer) model is proposed. First, the maximum information coefficient (MIC) method is utilized to filter out the process variables that are more relevant to the quality variables to reduce the model training time. Second, a temporal feature convolution processor is designed to extract key information from the time series. On the one hand, the pro cessor processes the data in time dimension through convolution operation to learn the dynamic changes of the data in time, and utilizes double convolution operation to process the feature dimension in the data, so that the model can learn the interaction information between the features, which helps to deeply understand the complex relationship between the features and improve the prediction accuracy of the model;on the other hand, it incorporates a residual scale block to regulate the model's training time. Scale is incorporated to regulate the effect of residual signals in the final output, so as to adjust the performance of the model according to different tasks and data characteristics, and the Hard Swish activation function with continuous differentiability is introduced to stabilize the training of the model. Then, the temporal projection is combined with a temporal feature convolution processor to perform the conversion between time steps. Finally, experiments are conducted using data from the penicillin fermentation process and semiconductor wafer etching process. The results demonstrate the accuracy and effectiveness of the proposed model, which requires fewer iterations for training to achieve excellent prediction results. © 2025, The Authors. All ri

关键词： batch data processing

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：