检索结果-内蒙古大学图书馆

2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023

作者： Wang, Lanfang Yu, Zhenyang Yu, Yongtao Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huaian China

ISBN: (纸本)9798350306293

As a unique identity reflecting the manufacturer of the vehicle, the vehicle logo information plays an important role in many transportation-related applications. However, due to the challenges of size variations, shape and form diversities, deformations, occlusions, and complex scenarios, it is still not an easy task to realize highly accurate vehicle logo recognition from images. This paper proposes a novel semi-anchoring guided high-resolution capsule network (SAGHR-CapsNet) for vehicle logo recognition. First, constructed with a multibranch high-resolution capsule network architecture functioned with repeated multiresolution feature fusion for feature extraction, the SAGHR-CapsNet can extract semantically strong and spatially accurate feature representations at each scale. Second, designed with a capsule-based efficient self-attention mechanism for feature semantic promotion, the SAGHRCapsNet functions excellently to attend to channel-wise informative features and target-oriented spatial features. Finally, adopted with a semi-anchoring guided strategy for vehicle logo recognition, the SAGHR-CapsNet performs promisingly to simultaneously improve the processing efficiency and guarantee the recognition accuracy. Intensive quantitative evaluations and comparative analyses on two large-scale data sets demonstrated the applicability and superiority of the SAGHR-CapsNet in vehicle logo recognition tasks. © 2023 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

A routing method with the approach of reducing energy consumption in WSNs with the Jellyfish Search (JS) optimizer algorithm and unequal clustering 13

A routing method with the approach of reducing energy consum...

引用

13th International Conference on computer and Knowledge engineering, ICCKE 2023

作者： Gholami, Ehsan Hamidzadeh, Javad Sadjad University Faculty of Computer Engineering and Information Technology Mashhad Iran

ISBN: (纸本)9798350330151

Wireless sensor networks are among the most common communication tools used in military and civilian fields. These networks consist of many tiny devices called sensor nodes. Each node has processing capability and different types of memory, transmitter, radio frequency receiver, and power supply. In addition, nodes house sensors and actuators. Batteries usually power sensor nodes and need to operate longer without their presence. In most cases, changing or recharging the battery for sensor nodes is very difficult or even impossible. Designing routing protocols in wireless sensor networks is challenging due to network limitations, with an emphasis on energy efficiency. The proposed method uses a hierarchical routing mechanism to optimize routing using asymmetric clustering. The sensor nodes are asymmetrically clustered in the proposed method, and the cluster heads are selected using the Jellyfish Search (JS) optimizer algorithm. The problem of optimal clustering is an optimization problem, so in this research, the Jellyfish Search algorithm is used to provide the most optimal clusters in routing. Due to the utilization of a search mechanism based on chaos theory in the Jellyfish Search optimization, the proposed method exhibits high accuracy in clustering and optimal routing within wireless sensor networks. Evaluations indicate that the proposed method achieves lower energy consumption and longer network lifetime compared to GWO, MO-PSO, WGWO, and HMBCR algorithms. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

A Surface Defect Detection Method Based on Attention Mechanism for Workpieces

A Surface Defect Detection Method Based on Attention Mechani...

引用

2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023

作者： Qiu, Junlin Shen, Yongshan Feng, Wanli Zhang, Haodong Sun, Keke Qin, Yuxin Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huai'an China

ISBN: (纸本)9798350306293

With the rapid development of image processing technology in recent years, faced with the issues of low detection accuracy and missed detections in the process of surface defect detection on workpieces, we propose a workpiece surface defect detection method based on attention mechanism. The model uses EfficientDet-d0 as the baseline network, mixes the Fused-MBConv structure and MBConv structure in EfficientNetv2 network as part of the feature extraction network, and uses the convolutional attention module CBAM to focus on the information of space and channel direction at the same time, and the Hardmish activation function is used in the structure. Introducing a fast spatial pyramid pooling module (SPPF) at the top of the feature extraction network increases the network's depth and enhances its expressive power. The extracted features are fed into the Improved-BiFPN (Bidirectional Feature Pyramid Network) for feature enhancement, improving the model's ability to detect defects of different sizes. Experimental results demonstrate that our proposed surface defect detection method for workpieces outperforms other advanced detectors. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Thermal ProPerTies of PolyProPylene fibrillaTed fibre reinforced lighTweighT foamed concreTe

引用

Archives of Metallurgy and Materials 2024年第4期69卷 1519-1527页

作者： Mydin, A.O. Al Bakri Abdullah, M.M. Majeed, S.S. Omar, R. Ahmad, R. Garus, S. UNIVERSITI SAINS MALAYSIA SCHOOL OF HOUSING BUILDING AND PLANNING PENANG11800 Malaysia PERLIS Malaysia NAWROZ UNIVERSITY COLLEGE OF ENGINEERING DEPARTMENT OF CIVIL ENGINEERING KURDISTAN REGION Iraq FACULTY OF TECHNOLOGY MANAGEMENT AND BUSINESS DEPARTMENT OF CONSTRUCTION MANAGEMENTPARIT RAJA BATU PAHAT JOHOR86400 Malaysia FACULTY OF MECHANICAL ENGINEERING & TECHNOLOGY UNIVERSITI MALAYSIA PERLIS PERLIS01000 Malaysia CZESTOCHOWA UNIVERSITY OF TECHNOLOGY FACULTY OF MECHANICAL ENGINEERING AND COMPUTER SCIENCE CZESTOCHOWA42-201 Poland

The global demand for energy has experienced a significant rise. The thermal performance of conventional concrete has been extensively studied, but there is still a significant amount of research needed to understand the effects of synthetic fibres on the thermal properties of lightweight foamed concrete (LFC). LFC popularity in the construction industry has increased rapidly due to the many benefits it offers over conventional concrete. Therefore, the goal of this study is to investigate the feasibility of incorporating polypropylene fibrillated fibre (PFF) into LFC to improve its thermal properties. The PFF was integrated into the LFC in diverse weight fractions, between 1% to 4%. Density of 1080 kg/m3 was made and evaluated. Spreadability, permeable porosity, conductivity, diffusivity and specific heat capacity were determined. The findings demonstrate that spreadability of fresh mix decreased when the weight fractions of PFF were increased from 0% (250 mm) to 4% (239 mm). The incorporation of 3% PFF to LFC greatly improves its conductivity and diffusivity. Specifically, the thermal conductivity decreases from 0.3307 W/mK (in the control) to 0.2643 W/mK, and the diffusivity decreases from 0.4426 m2/s (in the control) to 0.3843 m2/s. Compared to the control specimen, LFC’s porosity increased slightly from 43.6% to 44.9% when 3% PFF was added. The findings revealed that the PFF possesses significant underlying potential for utilisation in cementitious materials, potentially serving a pivotal function in either reducing the thermal-inducing property or improving the heat transfer of the concrete. The utilisation of LFC-PFF composites may also result in significant energy savings. © 2024. The Author(s).

关键词： Light weight concrete

来源：评论

学校读者我要写书评

暂无评论

Dual-Mode Resonant Sectorial Monopole Antenna with Stable Backfire Gain

引用

Chinese Journal of Electronics 2024年第6期33卷 1478-1486页

作者： Feiyan JI Heng ZHANG Xiuqiong XING Wenjun LU Lei ZHU Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and Telecommunications Key Laboratory of Wireless Sensor Network & Communication Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau

A novel design approach to wideband, dual-mode resonant monopole antenna with stable, enhanced backfire gain is advanced. The sectorial monopole evolves from a linear, 0.75-wavelength electric prototype monopole under wideband dual-mode resonant operation. As theoretically predicted by the two resonant modes TE3/5,1and TE9/5,1within a 150° radiator, the operation principle is revealed at first. As have been numerically demonstrated and experimentally validated at 2.4-GHz band, the designed antenna exhibits a wide impedance bandwidth over 90.1%（i.e., 2.06–5.44 GHz）, in which the stable gain bandwidth in the backfire,-x-direction（θ = 90°, φ = 180°） with peak value of 3.2 dBi and fluctuation less than 3 dB is up to 45.3%（i.e., 3.74–5.44 GHz）. It is concluded that the stable wideband backfire gain frequency response should be owing to the high-order resonant mode in the unique sectorial monopole antennas.

关键词： Fluctuations Azimuth Prototypes Metals Resonance Frequency measurement Broadband antennas Impedance Gain Wideband

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Heart Sound Denoising Using Adaptive Line Enhancer with LMF Algorithm 12

A Comparative Study of Heart Sound Denoising Using Adaptive ...

引用

12th International Electrical engineering Congress, iEECON 2024

作者： Pongyart, Witthawas Ongcunaruck, Wisute Faculty Of Engineering King Mongkut's University Of Technology North Bangkok Electrical And Computer Engineering Department Bangkok Thailand

ISBN: (纸本)9798350383591

This paper presents a comparative study of heart sound denoising techniques by employing the Adaptive Line Enhancer (ALE) with the Least Mean Fourth (LMF) algorithm. Three variations of the ALE using LMF are developed and evaluated. The first approach replaces the conventional Least Mean Square (LMS) algorithm with LMF in the ALE structure. The second approach adopts a transform domain framework, and a Hadamard domain LMF is developed and used for ALE. Since the transform domain LMF requires the FIR filter order to match the dimension of the transformation, a novel structure of the transform domain ALE is developed, allowing the FIR filter order to be independent of the transform dimension. The study evaluates the performance of the ALE with LMF algorithm in both domains, alongside the proposed new structure. Simulated tests, focusing on steady-state behavior as the key performance index, demonstrate the superior performance of the newly developed transform domain ALE, surpassing both the time domain ALE with LMS and LMF algorithm and the conventional transform domain approach. © 2024 IEEE.

关键词： Time domain analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Chemical Accident News Classification Based on CNN and BiLSTM-Self-Attention

Research on Chemical Accident News Classification Based on C...

引用

2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023

作者： Zong, Hui Zhao, Yun Zhou, Heng Zhang, Le Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huaian China

ISBN: (纸本)9798350306293

Chemical accident news data encompasses essential information such as news headlines, news content, and news sources, with the context of news content playing a crucial role. To enhance the accuracy of text feature extraction and improve the efficiency of chemical accident news classification, this paper introduces a feature fusion-based classification approach. The proposed model employs a multi-layer convolutional neural network (CNN) to extract local features from the text of chemical accident news. Additionally, a Bidirectional Long Short-Term Memory (BiLSTM) network is utilized to capture global features, supplemented by the integration of a Self-Attention mechanism behind the BiLSTM network to assign weights to the features and reduce noise. The local and global features are then fused to enrich the semantic information. Furthermore, the feature fusion information undergoes maximum pooling and average pooling to reduce dimensionality and enhance the training speed. Finally, the information is fed into a Softmax layer for classification. Experimental results demonstrate that the proposed neural network model, namely ABLSACNN (Add-CNN-BiLSTM-Self-Attention), outperforms the CNN-Self-Attention model. The ABLSACNN model exhibits an improvement of1.59% in accuracy, 2.46% in recall rate, and 1.93% in F1 score on the chemical accident news dataset, thereby showcasing its superiority. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Mutual character dialogue generation with semi-supervised multitask learners and awareness

引用

International Journal of Information technology (Singapore) 2024年第3期16卷 1357-1363页

作者： Ahrari Khalaf, Ayesheh Hassan Abdalla Hashim, Aisha Olowolayemo, Akeem Department of Electrical and Computer Engineering Faculty of Engineering International Islamic University Malaysia (IIUM) Kuala Lumpur Malaysia Department of Computer Science Faculty of Information and Communication Technology International Islamic University Malaysia (IIUM) Kuala Lumpur Malaysia

Consistent efforts have been ongoing to improve the friendliness and reliability of informal dialogue systems. However, most research focuses solely on mimicking human-like answers. Therefore, the interlocutors’ awareness features of the dialogue system are left unexplored. Meanwhile, cognitive science research reveals that awareness is a crucial indicator of an effective, high-quality informal conversation. This research aims to boost the quality of the conversational generation system by factoring in awareness of the interlocutors in the design and training of the dialogue system model. The Generative Pre-Trained Transformer-2 (GPT-2) model was implemented into the Persona Perception (P²) Bot to achieve the objectives of this study. This was to precisely develop model's understanding, P² Bot was implemented using a transmitter–receiver-based structure. The P² Bot leverages mutual persona awareness to improve the quality of customized dialogue generation. GPT-2 is a 1.5B parameter transformer model that produces state-of-the-art accuracy in a zero-shot setting on seven of the eight evaluated language modeling datasets. The observations of the proposed model on a sizable open-source dataset, PERSONA-CHAT, proved successful, with improvement above the state-of-the-art baselines in both automatic measures and human assessments. The model has achieved 82.2% accuracy on Hits@1 performance metrics in the original data and 68.8% on the revised data. On the human evaluation, the model scored an average of 2.66, pointing out that the responses provided were coherent and informative. A dialogue generation model with character and awareness which can communicate like an informative human expert was introduced. This study presents the submerging of GPT-2 model on a mutual persona perception dialogue generating model. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Cognitive science Conversational agent Dialogue generation Generative Pre-trained Transformer 2 (GPT-2) Natural language understanding (NLU)

来源：评论

学校读者我要写书评

暂无评论

Survey and Tutorial on Hybrid Human-Artificial Intelligence

引用

Tsinghua Science and technology 2023年第3期28卷 486-499页

作者： Feifei Shi Fang Zhou Hong Liu Liming Chen Huansheng Ning School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China School of Computer Science and Software Engineering East China Normal UniversityShanghai 200062China Faculty of Computing Ulster UniversityNewtownabbey BT370QBUK

The growing computing power,easy acquisition of large-scale data,and constantly improved algorithms have led to a new wave of artificial intelligence(AI)applications,which change the ways we live,manufacture,and do *** with this development,a rising concern is the relationship between AI and human intelligence,namely,whether AI systems may one day overtake,manipulate,or replace *** this paper,we introduce a novel concept named hybrid human-artificial intelligence(H-AI),which fuses human abilities and AI capabilities into a unified *** presents a challenging yet promising research direction that prompts secure and trusted AI innovations while keeping humans in the loop for effective *** scientifically define the concept of H-AI and propose an evolution road map for the development of AI toward *** then examine the key underpinning techniques of H-AI,such as user profile modeling,cognitive computing,and human-in-the-loop machine ***,we discuss H-AI’s potential applications in the area of smart homes,intelligent medicine,smart transportation,and smart ***,we conduct a critical analysis of current challenges and open gaps in H-AI,upon which we elaborate on future research issues and directions.

关键词： hybrid human-artificial intelligence(H-AI) Internet of Things(IoT) artificial intelligence(AI)

来源：评论

学校读者我要写书评

暂无评论

Rank Reversal Avoiding Algorithm for Modern Cooperative Spectrum Sensing 21

Rank Reversal Avoiding Algorithm for Modern Cooperative Spec...

引用

21st International System-on-Chip Design Conference, ISOCC 2024

作者： Lee, Wilaiporn Srisomboon, Kanabadee King Mongkut's University of Technology North Bangkok Faculty of Engineering Department of Electrical and Computer Engineering Bangkok Thailand

ISBN: (纸本)9798350377088

To achieve high reliable of the licensed user detection of cognitive radio, the cooperative spectrum sensing requires a high reliable licensed user detection results from the unlicensed users to perform the cooperative spectrum sensing. Lately, modern cooperative spectrum sensing methods exploit AHP with machine learning models for determining the quality of unlicensed users and the fusion center gathers the local sensing results from only reliable unlicensed users. However, the rank reversal, which is the major issue of AHP that cost a rank reverse, cannot be avoided and addressed. In this paper, we propose a rank reversal avoiding algorithm for the modern cooperative spectrum sensing method by exploiting the epsilon-greedy algorithm for addressing the duplicate information of the local sensing results. From the simulation results, when applying our proposed algorithm to the cooperative spectrum sensing methods, the rank reversal issue can be avoided completely since the value of each duplicated information is expand using epsilon-greedy algorithm under the detected boundary. Moreover, the error of licensed user detection can be reduced once only the local sensing results are only gathered from the reliable unlicensed users. Then, cooperative spectrum sensing performance can be improved by addressing the rank reversal issue. © 2024 IEEE.

关键词： Contrastive Learning

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：