检索结果-内蒙古大学图书馆

BERD+: A Generic Sequential Recommendation Framework by Eliminating Unreliable Data with Item- and Attribute-level Signals

引用

ACM Transactions on Information Systems 2023年第2期42卷 1-33页

作者： Sun, Yatong Yang, Xiaochun Sun, Zhu Wang, Bin School of Computer Science and Engineering Northeastern University School of Computing Macquarie University China Australia Institute of High Performance Computing Centre for Frontier AI Research A*STAR Singapore School of Computer Science and Engineering Northeastern University China National Frontiers Science Center for Industrial Intelligence and Systems Optimization China Key Laboratory of Data Analytics and Optimization for Smart Industry [Northeastern University Ministry of Education China

A preliminary work of our study was published at IJCAI’21 [47], which is substantially extended in the following aspects: (1) In Section 1, we analyze the necessity of introducing item attributes for detecting unreliable instances, together with the problems and challenges that attributes may bring in. (2) In Section 2, we add discussions about the limitations of existing attribute-aware recommender systems (Section 2.2) and denoising methods (Section 2.3) in the context of detecting unreliable instances. (3) In Section 4.2, we further conduct an in-depth analysis at the attribute level to demonstrate the capability of attributes for rectifying instance loss and uncertainty, as well as the disturbance caused by attributes. (4) We generalize BERD to a generic framework BERD+ in Section 5.1, equipped with novel modules, i.e., HU-GCN (Section 5.2) and EPE (Section 5.4), which properly incorporate item attributes while reducing their disturbance for rectifying instance uncer tainty (Section 5.5) and loss (Section 5.6). The generic BERD+ can be flexibly plugged into existing SRSs for performance enhanced recommendation via eliminating unreliable data. (5) In Section 6.2, we apply our BERD+ framework to seven state-of-the-art SRSs on five real-world datasets to illustrate its superiority. (6) To avoid unfair comparison caused by item attributes, we build and compare with the baseline that combines the original BERD and an advanced attribute-aware recommender system, KSR [19]. (7) For more comprehensive comparison, in Section 6.2.2, we compare BRED+ with two state-of-the-art denoising approaches;in Section 6.2.3, to examine the efficacy of HU-GCN and EPE, we compare HU-GCN with various attribute embedding techniques, i.e., variants of graph neural networks, and compare EPE with different attribute fusing methods, i.e., adding, concatenation, and weighted sum. (8) In Section 6.2.4, a detailed ablation study is conducted to verify the effectiveness of each module of BERD+. (

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A VMD Filtering Algorithm for Electromagnetic Wave Interference Signals of GIS Equipment

A VMD Filtering Algorithm for Electromagnetic Wave Interfere...

引用

第35届中国过程控制会议

作者： Chengcheng Xu Aimin An Jinhu Niu Bo Yu Chanyun Shao College of Electrical Technology and Information Engineering Lanzhou University of Technology Key Laboratory of Gansu Advanced Control for Industrial Processes

In the ultra-high voltage(UHV) network, the operational status of gas-insulated switchgear(GIS) equipment is closely related to the stable, reliable and safe operation of the entire UHV substation. Aiming at the problem that it is difficult to realize accurate and reliable partial discharge detection of GIS equipment due to the high voltage level and strong interference involved in GIS equipment, the study proposes a filtering algorithm based on VMD for electromagnetic wave interference signal of GIS equipment. Firstly, the local discharge signal is collected, secondly, the electromagnetic wave interference signal is superimposed to the discharge signal, and finally, the Variable Difference Modal Decomposition(VMD) signal filtering process is implemented on the MATLAB platform, and the validity of the VMD algorithm is verified by comparing it with the second-order Butterworth high-pass filtering method.

关键词： gis partial discharge detection electromagnetic wave interference signal filtering vmd algorithm

来源：评论

学校读者我要写书评

暂无评论

An Improved Road Target Detection Approach Based on YOLO-v8

An Improved Road Target Detection Approach Based on YOLO-v8

引用

Chinese Automation Congress (CAC)

作者： Hongyi Hou Wenyan Ci Lu Tian Yangxun Ge Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems School of Engineering Huzhou University Huzhou China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

To address the challenges of high equipment demands, low detection accuracy, and high miss rates for overlapping and small targets in traditional road target detection models, we propose an improved detection method named YOLOv8-GPT. The C2f module in the backbone network is restructured with the inclusion of a lightweight attention mechanism, Triplet Attention, improving the model's feature extraction capabilities. Additionally, a new lightweight convolution accumulation technique, GSConv, is integrated into the Neck, reducing model burden while preserving accuracy and enhancing computational cost efficiency. Then, to better detect small vehicles in crowded traffic, a dedicated small target detection head has been added, aiming to capture detailed features and contextual cues effectively. Ultimately, the Wise-IoU, capable of adaptively adjusting weight coefficients, is employed as the loss function for the refined model, boosting the regression performance of bounding boxes and overall detection robustness. Experiments on the KITTI dataset show that the YOLOv8-GPT model significantly excels beyond the original, with a 3.5 percentage point increase in $m$ AP, a reduction of 1.3 million parameters, and superior performance in both volume and accuracy compared to other classic detection models, highlighting its strong practical applicability.

关键词： Adaptation models Solid modeling Accuracy Attention mechanisms Convolution Roads Computational modeling Object detection Feature extraction Neck

来源：评论

学校读者我要写书评

暂无评论

Search Enhancement Generation for Fine-Tuning Large Language Models

Search Enhancement Generation for Fine-Tuning Large Language...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Yonghao Xing Shuxin Du Yi Qiu Xiaorui Guo Hongyi Xu Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems School of Engineering Huzhou University Huzhou China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

Large Language models (LLMS) have demonstrated remarkable linguistic capabilities, which has prompted people to try to apply them to a wide range of fields. Retrieval Enhanced Generation (RAG) has become an important framework for building LLM-based, and while building RAG is relatively simple, we have combined the use of RAG with a fine-tuned open source LLM in order to gain a deeper understanding of the domain and generate more precise answers. Our evaluation shows that this combination is better than what can be achieved with simple RAG or fine-tuning.

关键词： Databases Computational modeling Large language models Heuristic algorithms Buildings Linguistics Noise measurement Tuning Optimization Context modeling

来源：评论

学校读者我要写书评

暂无评论

Light focusing in linear arranged symmetric nanoparticle trimer on metal film system

引用

Chinese Physics B 2022年第1期31卷 540-546页

作者： Yuxia Tang Shuxia Wang Yingzhou Huang Yurui Fang State Key Laboratory of Coal Mine Disaster Dynamics and Control and Chongqing Key Laboratory of Soft Condensed Matter Physics and Smart Materials College of PhysicsChongqing UniversityChongqing 400044China Applied Physics School of Computer Science and Information EngineeringChongqing Technology and Business UniversityChongqing 400067China Key Laboratory of Materials Modification by Laser Electronand Ion Beams(Ministry of Education)School of PhysicsDalian University of TechnologyDalian 116024China

Benefiting from the induced image charge on film surface,the nanoparticle aggregating on metal exhibits interesting optical *** this work,a linear metal nanoparticle trimer on metal film system has been investigated to explore the novel optical *** the electric field and surface charge distributions demonstrate the light is focused on film greatly by the nanoparticles at two sides,which could be strongly modulated by the wavelength of incident *** the influence of nanoparticle in middle on this light focusing ability has also been studied here,which is explained by the plasmon hybridization *** finding about light focusing in nanoparticle aggregating on metal film not only enlarges the novel phenomenon of surface plasmon but also has great application prospect in the field of surface-enhanced spectra,surface catalysis,solar cells,water splitting,etc.

关键词： electric field enhancement light focusing nanoparticle trimer on metal film system plasmonic hybridization

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning Based Decision-Making Models on the Aero-Engine Bearing Fault Diagnosis

Ensemble Learning Based Decision-Making Models on the Aero-E...

引用

International Conference on Guidance, Navigation and control, ICGNC 2020

作者： Zhang, Shuo Li, Longqi Zhou, Heyang Liu, Haifeng Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian China School of Control Engineering Dalian University of Technology Dalian116024 China

ISBN: (纸本)9789811581540

The aero-engine is an extremely complex and precise mechanical system. Due to the changing working conditions, there are many factors that cause structural vibrations. The normal operation of each component is related to the stability and safety of the entire system. Failure of components can cause huge disasters. This paper analyzes the aero-engine bearing vibration failure caused by the low-pressure rotor imbalance, and finds that the main difficulty in constructing a fault diagnosis model of aero-engine lies in the processing of imbalance data and the extraction of multidimensional feature data. To solve these problems, a fault diagnosis method is proposed. This method first uses the border-line smote method to balance the data, and then proposes a weight-based Gini coefficient feature extraction method for feature extraction. Finally, the extracted features are used to construct an aero-engine fault diagnosis model. The principle of the fault diagnosis model is to build classifiers to distinguish between normal classes and fault classes. This paper mainly studies the classification effect of the three algorithms xgboost, GDBT and adaboost, and discusses the superiority of different algorithms. And using the bench data of a research institute for testing, it is found that the fault diagnosis model constructed by using the xgboost algorithm has a better fault diagnosis accuracy. It shows that this method has a good application in aero-engine fault diagnosis. © 2022, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Design of Intentional Eye-blink Signal Acquisition and control System Based on Pressure Sensor 7

Design of Intentional Eye-blink Signal Acquisition and Contr...

引用

7th International Conference on Intelligent Computing and Signal Processing, ICSP 2022

作者： Shao, Xueqi Ning, Haonan Yang, Wenjun Niu, Yafeng Southeast University School of Mechanical Engineering Department of Industrial Design Nanjing China National Key Laboratory of Science and Technology on Aircraft Control Xi'an China

ISBN: (纸本)9781665478571

Eye-blink control means that users blink intentionally to realize human-computer interaction. An intentional eye-blink signal acquisition and control system based on flexible pressure sensor is designed, which aims to control the object through simple eye movements such as blinking and winking. The system uses two pressure sensors to collect the blink signals at the orbicularis oculi muscles of the left and right eyes respectively. The software part realizes the acquisition and recognition of six intentional eye-blink signals, and transmits blink-control instruction signals through Bluetooth, so as to realize the control of the remote-controlled vehicle. The advantage of this system is that it is not affected by illumination and does not need GUI interface for control. The availability of the system is qualified after system test. © 2022 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Monascus vinegar alleviates high-fat-diet-induced inflammation in rats by regulating the NF-κB and PI3K/AKT/mTOR pathways

引用

Food Science and Human Wellness 2022年第4期11卷 943-953页

作者： Huanmei Meng Jia Song Bingqian Fan Yingqi Li Jiaojiao Zhang Jinping Yu Yu Zheng Min Wang State Key Laboratory of Food Nutrition and Safety Key Laboratory of Industrial Fermentation MicrobiologyTianjin Engineering Research Centre of Microbial Metabolism and Fermentation Process ControlCollege of BiotechnologyTianjin University of Science&TechnologyTianjin 300457China Shandong Engineering Research Centre of Condiment Fermentation Technology Shandong Yutu Co.LtdZibo 255300China

Monascus vinegar(MV) is a typical fermented food with various health-promoting effects. This study aimed to evaluate the role of MV in alleviating high-fat-diet-induced inflammation in rats with hyperlipidemia and elucidate the possible regulatory mechanisms. In the study, serum lipid profiles, liver pathology and liver inflammatory cytokines were analyzed in hyperlipidemia rats with MV(0.5 mL/kg mb, 2 mL/kg mb). Results showed that the administration of MV alleviated dyslipidemia by decreasing the serum and liver levels of triglyceride and total cholesterol. Increase in hepatic lipase and carnitine palmitoyl transferase 1(CPT-1)levels and decrease in hepatocyte steatosis, nephritis, and intestinal tissue injury in the HD group showed that high-dose MV can significantly suppress hepatic lipid accumulation and steatosis. In addition, compared with the model(MOD) group, the HD group showed significantly down-regulated the level of serum or hepatic alanine aminotransferase(ALT), aspartate aminotransferase(AST), CPT-1, interleukin(IL)-2, IL-6, IL-12,and tumor necrosis factor α(TNF-α). Moreover, the HD group showed repressed hepatic nuclear factor κB(NF-κB) pathway and inactivated phosphatidylinositol 3-kinase(PI3K)/protein kinase B(Akt)/mammalian target of rapamycin(mTOR) pathway mitigated liver inflammation. Similar results were obtained from cell experiments. Collectively, these findings revealed that MV might attenuate high-fat-diet-induced inflammation by inhibiting the NF-κB and PI3K/Akt/mTOR pathways.

关键词： Monascus vinegar Hyperlipidemia Inflammation NF-κB PI3K/AKT/mTOR

来源：评论

学校读者我要写书评

暂无评论

Operation State Monitoring of Wastewater Treatment Process Based on LSTM Network of Fusion Attention Mechanism

Operation State Monitoring of Wastewater Treatment Process B...

引用

IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS)

作者： Yonghao Xing Shuxin Du Yi Qiu Hongyi Xu Xiaorui Guo Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems School of Engineering Huzhou University Huzhou China

ISBN: (数字)9798350374315

ISBN: (纸本)9798350374322

In this paper, an LSTM neural network model based on fusion attention mechanism is proposed to classify the operational state of wastewater treatment process. The model combines the attention mechanism to effectively capture the changes and effects of key parameters in the wastewater treatment process. Through deep learning method, the model is built in Python language, and the actual test data is used for verification and comparative analysis, which verifies the accuracy and effectiveness of the model. The experimental results show that the model has significant advantages in improving the prediction classification accuracy and monitoring the running state of the sewage treatment process, and provides an effective method for the intelligent monitoring and management of the sewage treatment process.

关键词： Process monitoring Analytical models Attention mechanisms Accuracy Sewage treatment Discharges (electric) Data models Wastewater treatment Monitoring Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Fault Tolerant control for the Vibration Displacement System of a Continuous Casting Mold Based on a Fault Detection Observer

Fault Tolerant Control for the Vibration Displacement System...

引用

第43届中国控制会议

作者： Wenqi Hao Yiming Fang Le Liu Xiaonan Liu Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Engineering Research Center of the Education Ministry for Intelligent Control System and Intelligent Equipment Yanshan University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

In this paper,a fault detection observer and an adaptive sliding mode fault-tolerant controller are designed for the vibration displacement system of a continuous casting mold with actuator faults and load torque ***,a mathematical model of a continuous casting mold vibration displacement system driven by a servo motor with actuator faults and load disturbance uncertainties are ***,a fault detection observer is designed to obtain information on actuator faults,load disturbances,and system state ***,based on the information from the fault detection observer,an adaptive sliding mode fault-tolerant controller is designed,and the stability of the designed system is proved using Lyapunov stability ***,the effectiveness of the designed adaptive sliding mode fault-tolerant controller based on fault observer is verified through simulation.

关键词： Continuous casting mold Fault detection observer Fault tolerant control Actuator fault Vibration displacement system Driven by a servo motor

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：