检索结果-内蒙古大学图书馆

43rd Chinese Control Conference, CCC 2024

作者： Liang, Rongkai Li, Chuandong Su, Youxun Liang, Weiwei Chen, Menggang Luo, Zhen Southwest University College of Electronic and Information Engineering Chongqing400715 China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing China

ISBN: (纸本)9789887581581

In order to enhance the adaptability of wireless devices across diverse applications, it becomes imperative for an antenna to embody a multitude of functionalities, including the capacity to dynamically reconfigure the operating frequency, polarization mode, and radiation pattern. This paper introduces a frequency-reconfigurable antenna that incorporates an L-U shaped slot band with a Split-Ring Resonator (SRR). Fabricated on a 1.2 mm low-cost FR4 substrate using a partially grounded design approach, which measures 40 × 35 mm2. By manipulating the bias states of the two PIN diodes, the radiation element current and field distributions can be altered, resulting in reconfigurable bands spanning 2.45 GHz, 3.3 GHz, 4.5 GHz, 7.4 GHz, and 9.4 GHz, with an expansive Ultra-Wide Bandwidth (UWB) of 4230 MHz. This antenna design caters to a range of wireless applications, including WLAN (Wireless Local Area Network), WiMAX (Worldwide Interoperability for Microwave Access), Remote Radio, and X-band Satellite Communication. Through meticulous simulation optimization, four reconfiguration scenarios are thoroughly examined by presenting and analyzing the simulation results. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

Non-intrusive Load Monitoring Based Data-Free Incremental Electrical Appliance Identification 8th

Non-intrusive Load Monitoring Based Data-Free Incremental El...

引用

8th International Conference on Energy and Environmental Science, ICEES 2024

作者： Zhou, Rui Fang, Xiaohan The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei230601 China

ISBN: (纸本)9783031639005

In the realm of modern energy management systems, Non-Intrusive Load Monitoring (NILM) technology provides an innovative solution for power suppliers. It allows for remote monitoring and analysis of users’ electricity consumption patterns without requiring direct access to each device. This technology works by collecting comprehensive energy data at the user’s meter entry point and using algorithms to differentiate and identify the energy consumption characteristics of each device. However, with the increasing number of smart devices used by residential and commercial users, traditional NILM methods face the challenge of dealing with more complex and diverse electricity usage patterns. To address these challenges, we propose a novel incremental NILM framework. This framework has the ability to independently learn new load categories without load data, which is crucial for adapting in real-time to the changing variety of load devices, while also effectively addressing user privacy concerns. We introduce a VI-SCRM for extracting V-I trajectory features, incorporating a reconstruction convolution module. This method reduces the redundancy of V-I trajectory features and eliminates insignificant features, thereby improving algorithm efficiency. Additionally, this approach streamlines the model training process and prevents the model from ‘forgetting’ previously acquired knowledge. By implementing this framework in NILM, the system can continually adjust to new types of devices. Our experimental results confirm the effectiveness of this approach and highlight its potential advantages in practical applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Visual Prompt Flexible-Modal Face Anti-Spoofing

引用

IEEE Transactions on Dependable and Secure computing 2025年第3期22卷 2597-2606页

作者： Yu, Zitong Cai, Rizhao Cui, Yawen Liu, Ajian Chen, Changsheng Great Bay University School of Computing and Information Technology Dongguan523000 China Nanyang Technological University ROSE Lab School of EEE 639798 Singapore Hong Kong Polytechnic University Kowloon Hong Kong Chinese Academy of Sciences University of Chinese Academy of Sciences National Laboratory of Pattern Recognition Institute of Automation Beijing100190 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security College of Electronics and Information Engineering Shenzhen518060 China

Recently, vision transformer based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, multimodal face data collected from the real world is often imperfect due to missing modalities from various imaging sensors. Recently, flexible-modal FAS (Yu et al. 2023) has attracted more attention, which aims to develop a unified multimodal FAS model using complete multimodal face data but is insensitive to test-time missing modalities. In this paper, we tackle one main challenge in flexible-modal FAS, i.e., when missing modality occurs either during training or testing in real-world situations. Inspired by the recent success of the prompt learning in language models, we propose Visual Prompt flexible-modal FAS (VP-FAS), which learns the modal-relevant prompts to adapt the frozen pre-trained foundation model to downstream flexible-modal FAS task. Specifically, both vanilla visual prompts and residual contextual prompts are plugged into multimodal transformers to handle general missing-modality cases, while only requiring less than 4% learnable parameters compared to training the entire model. Furthermore, missing-modality regularization is proposed to force models to learn consistent multimodal feature embeddings when missing partial modalities. Extensive experiments conducted on two multimodal FAS benchmark datasets demonstrate the effectiveness of our VP-FAS framework that improves the performance under various missing-modality cases while alleviating the requirement of heavy model re-training. © 2004-2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

A Novel Unsupervised Feature Selection based on Correlation Measure between Heterogeneous Features 6

A Novel Unsupervised Feature Selection based on Correlation ...

引用

6th IEEE International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2023

作者： Cai, Jia-Ming Jia, Hong Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen China

ISBN: (纸本)9798350325485

Most existing feature selection algorithms only focus on a certain type of data, either numerical or categorical. In this paper, we present an unsupervised heterogeneous feature selection method based on a novel feature correlation measurement. Firstly, a unified correlation measuring framework is designed to quantify the correlations between any two features, including features with the same type and different types. Then, a filter-based feature selection algorithm is proposed to remove redundant features and obtain a best feature subset. Various experiments have been conducted on different mixed data sets and the results indicate that the proposed method can obtain better clustering performance with a smaller heterogeneous feature subset. © 2023 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

A Fusion Shallow and Deep Features Network for Facial StO2 Stress Classification 6

A Fusion Shallow and Deep Features Network for Facial StO2 S...

引用

6th IEEE information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2023

作者： Xia, Haolin Sun, Sirui Liu, Xinyu Zhou, Ju Wang, Hanpu Chen, Tong School of Electronic and Information Engineering Southwest University Chongqing China Key Laboratory of Non-Linear Circuit and Intelligent Information Processing of Chongqing Chongqing China Institute of Legal Psychology and Intelligent Computing Chongqing China

ISBN: (纸本)9781665460033

Stress is an emotional state that affects our lives, so it is vital to detect it accurately. Numerous studies have shown that tissue oxygen saturation (StO2) is an effective physiological signal for identifying different stress states. However, previous StO2 feature extraction methods relied too heavily on baselines to be realized in practice. In this paper, a two-stream network combining shallow and deep features, called CRNet, is proposed for baseline-independent StO2 stress classification. In CRNet, shallow features are extracted using a CNN network and deep features are extracted using a ResNet network. For the extracted high-dimensional deep features, MLP module is employed for dimensionality reduction, which can effectively combine the two levels of features and improve the feature extraction capability of the network. Experimental results show that CRNet can significantly improve the performance of StO2 stress classification to the state-of-the-art (SOTA) even when using only raw imbalanced data. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Fine Segmentation Method for the Outer Boundary of Tire Image Steel Belt Based on Adaptive Thresholding Under Local Histogram Statistical Features

A Fine Segmentation Method for the Outer Boundary of Tire Im...

引用

International Conference on Image, Vision and intelligent Systems, ICIVIS 2023

作者： Liu, Hua Li, Nan Hao, Jinyi Xia, Yingjie Li, Jinping School of Information Science and Engineering University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network-Based Intelligent Computing University of Jinan Jinan250022 China Shandong College and University Key Laboratory of Information Processing and Cognitive Computing in 13th Five-Year Jinan250022 China

ISBN: (纸本)9789819708543

The accuracy of defect detection in various locations is directly affected by the influence of precise segmentation of radial tire images. As the need for high-quality tires has grown, so has interest in the steel belt region. This region contains a diversity of textures and is impacted by shadows, and only a rough segmentation of this region has been achieved in the available literature, but this is interfered with by other areas, resulting in unsatisfactory defect detection in this region. As a result, we present a fine segmentation method for boundary mutation that takes advantage of the projection property of the local narrow window. First, the histogram adhesion change detection algorithm is designed;next, the narrow sliding window’s histogram peak width change algorithm is designed;finally, a wide sliding window is used for vertical projection, and the absolute value of the histogram change rate at the boundary is designed to maximize the algorithm. To calculate the outside boundary of the steel belt, the difference between the three sets of coordinates is kept within a specific error range. The detection was performed on 1,000 self-constructed data sets, with an accuracy rate of 94% and a detection speed of 0.1 s The experiments show that the algorithm can segment the steel belt’s outer boundary more finely and robustly, and it has a strong segmentation effect for images with a near texture angle and tire sidewall cord angle. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Retrieval Augmented Recipe Generation

Retrieval Augmented Recipe Generation

引用

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Liu, Guoshan Yin, Hailong Zhu, Bin Chen, Jingjing Ngo, Chong-Wah Jiang, Yu-Gang School of Computer Science Fudan University Shanghai Key Lab of Intelligent Information Processing China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Singapore Management University Singapore

ISBN: (纸本)9798331510831

The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method - first predicting ingredients from a food image and then generating instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light on generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallu-cinations during recipe generation, leading to suboptimal performance. To tackle this issue, we propose a retrieval augmented large multimodal model for recipe generation. We first introduce Stochastic Diversified Retrieval Augmentation (SDRA) to retrieve recipes semantically related to the image from an existing datastore as a supplement, integrating them into the prompt to add diverse and rich context to the input image. Additionally, Self-Consistency Ensemble Voting mechanism is proposed to determine the most confident prediction recipes as the final output. It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation. Extensive experiments validate the effectiveness of our proposed method, which demonstrates state-of-the-art (SOTA) performance in recipe generation on the Recipe1M dataset. © 2025 IEEE.

关键词： Food ingredients

来源：评论

学校读者我要写书评

暂无评论

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration 38

Speculative Decoding with CTC-based Draft Model for LLM Infe...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lightweight-Based Defect Detection for Small Target Insulators

Lightweight-Based Defect Detection for Small Target Insulato...

引用

TEPEN International Workshop on Fault Diagnostics and Prognostics, TEPEN-IWFDP 2024

作者： Liu, Shuxin Zhang, Lei Shi, Chengcheng Qin, Shuhan Ji, Guanjun Wang, Xiaodi School of Electrical Engineering Shanghai Dianji University Shanghai201306 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Fujian354300 China

ISBN: (纸本)9783031694820

Identifying defects in insulators, especially in small targets, remains a significant challenge due to the diverse types of insulators and complex transmission line backgrounds. This paper aims to enhance the accuracy of defect detection in insulators while minimizing the model’s parameter count for stable power system operation. To achieve this, we propose improvements to the feature fusion mechanism in the YOLOv8 network. These enhancements focus on better integrating multi-scale feature information, particularly emphasizing the detection sensitivity towards small targets. Additionally, these modifications lead to a reduction in the model’s parameter count while improving the detection accuracy of small targets. Furthermore, we introduce the SIOU loss function to the improved model, further enhancing its accuracy. Through experiments, our improved model achieves a mean average precision (mAP) of 89.2%, surpassing YOLOv8n by 2.7%. Remarkably, the model’s parameter count is significantly reduced to 2,796,249, demonstrating a balance between higher model accuracy and fewer parameters. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Insulating materials

来源：评论

学校读者我要写书评

暂无评论

Edge computing based multi-objective equilibrium task unloading of Internet of Vehicles 2

Edge computing based multi-objective equilibrium task unload...

引用

2nd International Conference on Electronic information Technology, EIT 2023

作者： Wang, Lingjiao Tang, Chen Guo, Hua Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Xiang Tan University 411105 China School of Automation and Electronic Information Xiang Tan University 411105 China

ISBN: (数字)9781510666627

ISBN: (纸本)9781510666610

The requirements of the Internet of Vehicles on the quality of service (QoS) of computing task offloading are constantly improving. The processing mode of edge computing, which deploys computing, bandwidth and storage resources near the user side, effectively improves the user experience. However, the computing capacity of edge servers is limited. Task offloading requests are overloaded and inefficient due to uneven server loads. Traditional cloud computing consumes a lot of energy and time. To solve the above problem, a KDQN based edge computing balanced task unloading mechanism is proposed: Q learning and convolutional neural network are used to obtain the optimal unloading strategy according to the returns of each step and continuous iterative updates, which reduces the convergence time of task unloading;K-means clustering is used to distribute part of the load of the overloaded server to the server with the closest European distance to achieve server load balancing. The experimental results show that compared to the existing offload mechanism, the new mechanism can reduce the average server energy consumption by 12.8%, the average service delay by 8.2%, and the average overload rate by 29.8%. © 2023 SPIE.

关键词： Quality of service

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：