检索结果-内蒙古大学图书馆

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 2125-2138页

作者： Zhengtao Yu Jinlei Xu Xiang Huang Zhongfen Deng Yonghua Wen Li Sun Yuxin Huang Hao Peng Philip S. Yu Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Yunnan Province Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming China School of Cyber Science and Technology Beihang University Beijing China Department of Computer Science University of Illinois Chicago IL USA School of Control and Computer Engineering North China Electric Power University Beijing China

Multilingual Neural Machine Translation (NMT) excels in sharing knowledge across languages and transferring insights from high-resource languages to improve performance in low-resource languages. However, its performance lags in specific domains such as legal and medical. Previous works have focused on adding language-specific and domain-specific adapters to achieve domain adaptation. Although effective, these adapter-based methods only use domain data to train additional parameters, limiting the performance of multilingual NMT. In this paper, we propose CDSTX, a novel approach that achieves robust multilingual domain adaptation without relying on adapters, solely leveraging multilingual models. Specifically, we utilize the pretrained model XLM-R and frozen embeddings to preserve its robust multilingual capabilities and design a two-stage training strategy for domain adaptation. This includes separate training for the decoder and fine-tuning of the entire model, ensuring that the model effectively acquires domain knowledge and correctly represents domain-specific text. Moreover, to better utilize the domain information conveyed implicitly by the training data, we devise special domain tokens at the beginning of the source and target sentences called Source&Target Domain Tags. In addition, back translation is employed to enhance the cross-lingual transfer ability of our approach. Our proposed method is evaluated on two datasets across three translation tasks: Single-domain Multilingual NMT, Multi-domain bilingual NMT, and Multilingual Multi-domain NMT. Notably, in the single-domain multilingual NMT task, CDSTX significantly enhances zero-shot domain translation performance, achieving improvements of up to +30 BLEU points through the utilization of back-translation techniques. Even in the bilingual multi-domain NMT task where specific domain data for the target translation direction is unavailable, our method consistently outperforms all SOTA methods. Moreover, in the

关键词： Training Adaptation models Translation Limiting Law Large language models Training data Neural machine translation Multilingual Speech processing

来源：评论

学校读者我要写书评

暂无评论

Research on object detection for service robots based on image feature 5

Research on object detection for service robots based on ima...

引用

5th IEEE Advanced Information Management, Communicates, Electronic and automation control Conference, IMCEC 2022

作者： Wu, Jiabao Zhang, Yunxi Zhang, Yijing Jiang, Hetong Hou, Linlin Liu, Jia Tianjin University of Technology and Education School of Automation and Electrical Engineering Tianjin China Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing and Intelligent Control Tianjin China Qufu Normal University School of Information Science and Engineering Rizhao China

ISBN: (纸本)9781665479677

Object recognition and location capture is one of the important functions of the service robot, and the accurate detection of the target is of great significance for the subsequent function expansion. This paper studies the three kinds of HSV, ORB, SIFT algorithm based on color features, shape features and gradient. According to different scenarios of target objects, the image features are extracted and object detection is carried out through different algorithms. Compared with the detection results, it is concluded that the selection of appropriate algorithms based on different features for object detection is more efficient, which lays a foundation for subsequent service robots to complete accurate grasping of target objects in complex indoor environments. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

controller Dynamic Linearization Based Data-Driven Adaptive control for a Vapor-Compression Refrigeration System

Controller Dynamic Linearization Based Data-Driven Adaptive ...

引用

Data Driven control and Learning Systems (DDCLS)

作者： Jingyu Fang Xian Yu Shuangshuang Xiong College of Mechatronics and Control Engineering Shenzhen University Shenzhen School of Automation Beijing Information Science and Technology University Beijing P. R. China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

This paper applies a data-driven adaptive control method to a benchmark of vapor compression refrigeration system based on the controller dynamic linearization method. Two controllers, namely, a single-input single-output controller and an extended multiple-input multiple-output controller, are designed to track the exit temperature of the evaporator secondary flux and the refrigerant superheat at the evaporator exit, by controlling the valve opening of the evaporator, and the compressor speed. Both the controllers entirely rely on input-output data of the controlled system in the controller design. Comparative results between the applied data-driven adaptive control and the default PID control provided by the benchmark demonstrate the effectiveness of the two designed controllers.

关键词： Learning systems PI control Benchmark testing Valves Temperature control Refrigeration PD control

来源：评论

学校读者我要写书评

暂无评论

Process Monitoring of Operational Cost for Wastewater Treatment Processes Using Variants of ARMA Models Based Soft-sensors 11

Process Monitoring of Operational Cost for Wastewater Treatm...

引用

11th IEEE Data Driven control and Learning Systems Conference, DDCLS 2022

作者： Lu, Yu Liu, Yiqi Li, Dong Key Laboratory of Autonomous Systems and Networked Control Ministry of Education School of Automation Science and Engineering South China University of Technology Guangzhou510640 China Technical University of Denmark Department of Chemical and Biochemical Engineering Lyngby Denmark

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

Process monitoring of operation cost index (OCI) is of great importance for wastewater treatment plants (WWTPs), which is not only able to support financial budget, but also to optimize local operation. This paper proposed four variants of auto-regressive and moving average (ARMA), based on recursive least squares algorithm (RLS), ARMA based on recursive extended least squares algorithm (RELS), nonlinear auto-regressive neural network (NARNN), and nonlinear auto-regressive neural network with external input (NARXNN) respectively, to predict the operating cost in WWTPs. The proposed methods were validated in the simulation platform, Benchmark Simulation Model No.2-P (BSM2-P). On account of the strong nonlinearity of the wastewater treatment process, the nonlinear model, like NARXNN, achieved better performance in terms of mean square error (MSE) and correlation coefficient (R). © 2022 IEEE.

关键词： Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

Spectrum Sensing for Cognitive Radio Based on Feature Extraction and Deep Learning 11

Spectrum Sensing for Cognitive Radio Based on Feature Extrac...

引用

2022 11th International Conference on Information and Electronics engineering, ICIEE 2022

作者： Geng, Yue Huang, Jingyi Yang, Jianxin Zhang, Sen School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen518061 China School of Mechanical Engineering & Automation Beihang University Beijing100191 China School of Measurement-Control and Communication Engineering Harbin University of Science and Technology Harbin150080 China

In cognitive radio, spectrum sensing is used to determine whether the primary user is using the spectrum based on the signal received on a specific frequency band, thereby determining whether the secondary user can use the spectrum. The main problem faced by spectrum sensing is how to identify the existence of the primary signal under the condition of low signal-to-noise ratio (SNR). Compared with traditional technologies, deep learning methods can identify the features of input data more efficiently and accurately. Based on convolutional neural network (CNN), This paper regard spectrum sensing as a binary classification problem. In the method we proposed, different features of received are extracted, and a dataset of feature matrices obtained under different SNRs is constructed for the training of the CNN network. Experiment results show that under the condition of low signal-to-noise ratio, the performance of our method is improved compared with the traditional method, and the combination of different features can improve the sensing accuracy. © Published under licence by IOP Publishing Ltd.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

Semi-Global Robust Practical Output Voltage Tracking for Single-Phase UPS Inverters via Sampled-Data control

Semi-Global Robust Practical Output Voltage Tracking for Sin...

引用

第42届中国控制会议

作者： Kaiji Zeng Wei Liu Weijie Sun Weidong Liu Key Laboratory of Autonomous Systems and Networked Control Ministry of EducationSchool of Automation Science and EngineeringSouth China University of Technology

This paper deals with the sampled-data semi-global robust practical output voltage tracking problem for single-phase voltage source uninterruptible power supply *** construct an aperiodic sampled-data state feedback control law in an internal model principle *** analysis shows that as long as the upper bound of the sampling time interval of the controller is less than an explicitly computable threshold,our problem can be handled by the proposed sampled-data control *** the tracking error is guaranteed to approach a given neighborhood of the origin asympotically.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Output Voltage Practical Tracking control for Uninterruptible Power Supply Systems

Event-Triggered Output Voltage Practical Tracking Control fo...

引用

第35届中国控制与决策会议

作者： Ben Wu Wei Liu Weijie Sun Key Laboratory of Autonomous Systems and Networked Control Ministry of EducationSchool of Automation Science and EngineeringSouth China University of Technology

In this paper,by using the output regulation theory,we research the output voltage practical tracking problem for uninterruptible power supply systems under event-triggered control *** configuring the desired poles for a controllable pair and solving the regulator equations,a state feedback gain and a feedforward gain can be obtained for designing the control ***,under event-triggered mechanism,a control law that can be applied to a digital platform directly is designed to solve our ***,it can be verified that the voltage tracking error can converge to a pre-specified neighborhood of the origin.

关键词： Uninterruptible power supply output regulation event-triggered control

来源：评论

学校读者我要写书评

暂无评论

ADRC Combined with IMC for Non-Minimum Phase Systems

ADRC Combined with IMC for Non-Minimum Phase Systems

引用

第42届中国控制会议

作者： Xiangyang Li Xindi Deng Senping Tian Wei Ai Key Laboratory of Autonomous Systems and Network Control Ministry of EducationSchool of Automation Science and EngineeringSouth China University of Technology

The integrated control method,active disturbance rejection control(ADRC) combined with internal model control(IMC),is proposed for non-minimum phase *** ADRC combined with IMC is to reduce the influence of zeros on right half plant(RHP),system uncertainty and outer *** improved IMC is put in the inner loop and ADRC is adopted in the outer *** order to enhance the system's stability,an approximate zero phase error model of controlled plant(ZPEM) is used as the internal model in the IMC control loop where the feedback of the inner loop is the dynamic weighted filter sum of the real output and the ZPEM *** theoretical analysis and simulations verify effectiveness of the proposed method for non-minimum phase systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Designing a Secure Smart Remote Patient Monitoring and Warning System using Big Data and Internet of Things Ecosystems 10

Designing a Secure Smart Remote Patient Monitoring and Warni...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Ramesh, S.P. Abdulwahid, Ali Hadi Anjum, Afsana Venkatesh, N. Singh, Rajesh Chakravarthi, M. Kalyan Amet University Department of Computer Science and Engineering Tamil Nadu Kanathur India Southern Technical University Engineering Technical College Department of Control and Automation Basra Iraq Jazan University Department of Information Technology and Security Jazan Saudi Arabia School of Computer Science and Artificial Intelligence Sr University Telangana Warangal India Uttaranchal Institute of Technology Uttaranchal University India School of Electronics Engineering VIT-AP University Amaravathi India

ISBN: (纸本)9789380544472

The demand on healthcare is growing as a result of the expanding global population, rising demands for successful treatment, and an underlying improvement in life quality. Consequently, healthcare remains one of the most significant social and economic problems in the world, necessitating the development of new and more sophisticated scientific and technological treatments.E-health services are provided via personalised healthcare systems to meet the medical and support needs of the ageing population. An important development in the Big Data age is the Internet of Things, which facilitates several real-time engineering solutions through improved services. Healthcare systems are now using analytics over IoT data streams as a stream of user data to find new information, forecast rapid recognition, and make decisions on life-threatening situations. In this study, researchers have carried out a thorough review of the hottest recent revolutionary technologies in bespoke healthcare systems, with a focus on hypervisor, cloud infrastructure, big data analytic, the Web of Things, and smartphone apps. In order to make early disease detection and diagnosis possible, it is important to develop a better healthcare system. We have examined these problems and suggested potential solutions while offering secure e-health services. The purpose of this study is to design a smart and secure remote monitoring and warning system using the latest emerging technologies in 21stcentury such as big data analytics and Internet of Things (IoT) ecosystems. In this study the researchers discussed a detailed research methodology to meet the outcomes of the reerach. All the relevant findings and analysis are explained in descriptive manner. Moreover, this study highlights the constantly expanding requirements for better medical systems in the present and offers potential directions for future research. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Triggered Mechanism for Strict Feedback Systems Under Unknown control Directions

Triggered Mechanism for Strict Feedback Systems Under Unknow...

引用

Asian control Conference

作者： Guilong Liu Hongda Wu Yongliang Yang Wei Xie Weidong Zhang School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

This paper presents an event-based asymptotic tracking control scheme designed for strict feedback systems with unknown control directions. The control directions directly determine how the controller acts on the system, thus impacting the system's stability and convergence speed. When the control directions are unknown, it presents a significant challenge in controller design. To tackle this issue, the Nussbaum-type gains are introduced. However, this method increases communication overhead. Hence, an event-triggered mechanism is introduced to alleviate this burden. Additionally, to achieve and maintain desired target states, satisfying control requirements and performance demands, this paper improves the event-triggered mechanism to achieve asymptotic tracking. Finally, the feasibility and effectiveness of the proposed design are validated through a simulation example.

关键词： Asymptotic stability Target tracking Stability criteria control systems Optimization Convergence

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：