检索结果-内蒙古大学图书馆

Highly Differentiated Target Detection under Extremely Low-Light Conditions Based on Improved YOLOX Model

computer Modeling in Engineering & sciences 2024年第8期140卷 1507-1537页

作者： Haijian Shao Suqin Lei Chenxu Yan Xing Deng Yunsong Qi School of Computer Jiangsu University of Science and TechnologyZhenjiang212003China Department of Electrical and Computer Engineering University of NevadaLas VegasNV89154USA Zhejiang Geely Automobile Research Institute Ningbo315336China

This paper expounds upon a novel target detection methodology distinguished by its elevated discriminatory efficacy,specifically tailored for environments characterized by markedly low luminance *** methodologies struggle with the challenges posed by luminosity fluctuations,especially in settings characterized by diminished radiance,further exacerbated by the utilization of suboptimal imaging *** envisioned approach mandates a departure from the conventional YOLOX model,which exhibits inadequacies in mitigating these *** enhance the efficacy of this approach in low-light conditions,the dehazing algorithm undergoes refinement,effecting a discerning regulation of the transmission rate at the pixel level,reducing it to values below 0.5,thereby resulting in an augmentation of image ***,the coiflet wavelet transform is employed to discern and isolate high-discriminatory attributes by dismantling low-frequency image attributes and extracting high-frequency attributes across divergent *** utilization of CycleGAN serves to elevate the features of low-light imagery across an array of stylistic *** computational methodologies are then employed to amalgamate and conflate intricate attributes originating from images characterized by distinct stylistic orientations,thereby augmenting the model’s erudition *** validation conducted on the PASCAL VOC and MS COCO 2017 datasets substantiates pronounced *** refined low-light enhancement algorithm yields a discernible 5.9%augmentation in the target detection evaluation index when compared to the original *** Average Precision(mAP)undergoes enhancements of 9.45%and 0.052%in low-light visual renditions relative to conventional YOLOX *** envisaged approach presents a myriad of advantages over prevailing benchmark methodologies in the realm of target detection within environments marked by an acute scarcity of lumi

关键词： Target detection extremely low-light wavelet transformation highly differentiated features YOLOX

来源：评论

学校读者我要写书评

暂无评论

Boost diagnostic performance in retinal disease classification utilizing deep ensemble classifiers based on OCT

引用

Multimedia Tools and Applications 2024年 1-21页

作者： Khan, Umer Sadiq Khan, Saif Ur Rehman School of Computer and Information Science Hubei Engineering University Xiaogan432000 China School of Computer Science and Information Engineering Hubei University Wuhan430062 China Institute for AI Industrial Technology Research Hubei Engineering University Xiaogan432000 China School of Computer Science and Engineering Central South University Yuelu District 932 Lushan S Rd Changsha Hunan China

Damage to the retinal blood vessels is critical in diabetic retinopathy, a progressively emerging health concern that often advances quietly without explicit symptoms. Optical coherence tomography-OCT has emerged as a favored noninvasive imaging technique for diagnosing diabetic retinopathy promptly and accurately. However, timely and precise diagnoses from OCT images are essential in prevention of blindness. Moreover, accurate interpretation of OCT images is challenging. Single model learning debilitates in managing diverse data types and structures, constraining its adaptability to varied environments. Its limitations become apparent in tasks requiring expertise from multiple domains, delaying overall performance. Moreover, learning may exhibit susceptibility to overfitting with large and heterogeneous datasets, resulting in compromised generalization capabilities. In this study, we propose a hybrid learning model for the classification of four distinct classes of retinal diseases in OCT images with improved generalization capabilities. Our hybrid model is constructed upon the well-established architectural foundations of ResNet50 and EfficientNetB0. By pre-training the hybrid model on extensive datasets like ImageNet and then fine-tuning it on publicly available OCT image datasets, we capitalize on the strengths of both architectures. This empowers the hybrid model to excel in discerning intricate image patterns while efficiently extracting hierarchical prediction from various regions within the images. To enhance classification accuracy and mitigate overfitting, we eliminate the fully connected layer from the base model and introduce a concatenate layer to combine two objective learning prediction. A dataset comprising 84,452 OCT images, each expertly graded for illnesses. we conducted training and evaluation of our proposed model, which demonstrated superior performance compared to existing methods, achieving an impressive overall classification accuracy of 97.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Recognition of mortar pumpability via computer vision and deep learning

引用

Journal of Electronic science and Technology 2023年第3期21卷 73-81页

作者： Hao-Zhe Feng Hong-Yang Yu Wen-Yong Wang Wen-Xuan Wang Ming-Qian Du Research Institute Electronic Science and Technology University of Electronic Science and Technology of ChinaChengdu611731China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China The Second Research Institute of Civil Aviation Administration of China Chengdu610041China

The mortar pumpability is essential in the construction industry,which requires much labor to estimate manually and always causes material *** paper proposes an effective method by combining a 3-dimensional convolutional neural network(3D CNN)with a 2-dimensional convolutional long short-term memory network(ConvLSTM2D)to automatically classify the mortar *** results show that the proposed model has an accuracy rate of 100%with a fast convergence speed,based on the dataset organized by collecting the corresponding mortar image *** work demonstrates the feasibility of using computer vision and deep learning for mortar pumpability classification.

关键词： Classification computer vision Deep learning Pumpability 2-dimensional convolutional long short-term memory network (ConvLSTM2D) 3-dimensional convolutional neural network(3D CNN)

来源：评论

学校读者我要写书评

暂无评论

Design of Low-Power Turbo Encoder and Decoder for NB-IoT

引用

Chinese Journal of Electronics 2024年第2期33卷 403-414页

作者： Chong ZHANG Yuhang LIN Deming WANG Jianguo HU School of Microelectronics Science and Technology Sun Yat-sen University School of Physics and Telecommunication Engineering South China Normal University School of Electronics and Information Engineering South China Normal University Development Research Institute of Guangzhou Smart City Shenzhen Research Institute of Sun Yat-sen University

Turbo code is an error correction coding scheme close to the Shannon limit, usually used in wireless data transmission. Based on the parallel Turbo code algorithm, a parallel Turbo code circuit design scheme is *** the encoder, the recursive systematic convolutional encoder is multiplexed. The decoder is divided into branch metric, recursive, maximum likelihood ratio, and external information calculation modules. The decoding algorithm is based on Max-Log-MAP, controlling the component decoder in parallel. And the state metric calculation in the decoding circuit is combined to reduce the overall power consumption effectively, enabling the encoder and decoder to be used in narrowband Internet of things(NB-IoT). Finally, the hardware scheme of the main functional modules of Turbo code encoding and decoding is designed and implemented. The results show that the dynamic power consumption is less than 50 m W. The overall on-chip power consumption is reduced by 40% at the frequency of 125 MHz compared with previous jobs.

关键词： Turbo encoder and decoder Narrowband Internet of things Power dissipation

来源：评论

学校读者我要写书评

暂无评论

Microstructural Evolution during Tensile Deformation in TRC-ZA21 Magnesium Alloy with Different Loading Directions and Strain Rates

引用

Acta Metallurgica Sinica(English Letters) 2023年第2期36卷 192-214页

作者： Yun Zhang Chen Jiang Shaoheng Sun Wei Xu Quan Yang Yongjun Zhang Shiwei Tian Xiaoge Duan Zhe Xu Haitao Jiang Institute of Engineering Technology University of Science and Technology BeijingBeijing100083China China Electric Power Research Institute Beijing100055China Shunde Graduate School of University of Science and Technology Beijing Foshan528399China China Ship Research and Development Academy Beijing100081China

The variation of texture characteristics and activation of deformation mechanism in magnesium alloys can be achieved by addition of RE and Ca elements and subsequently affect the microstructure evolution during deformation *** this manuscript,the effects of loading direction and strain rate on mechanical properties,microstructural characteristics,texture evolution and deformation mechanism in TRC-ZA21 magnesium alloy sheet were ***,orientation dependence and strain rate sensitivity of deformation mechanism were also *** results showed that evident difference in mechanical properties in TRC-ZA21 alloy exhibited by the changes in loading direction and strain *** variations in grain orientation and basal texture characteristic were attributed to the grain rotation behavior during the plastic deformation,dominated by deformation *** slip,extension twinning and prismatic slip played different contributions to plastic deformation behavior and presented orientation dependence and strain rate *** activities of prismatic slip and extension twinning both enhance with increasing strain *** phenomenon of weakened effect of twinning and promoted role of prismatic slip was presented to coordinate strain compatibility during plastic deformation.

关键词： Magnesium alloys Mechanical property Orientation behavior Deformation mechanism Microstructural evolution

来源：评论

学校读者我要写书评

暂无评论

Transaction transmission model for blockchain channels based on non-cooperative games

引用

science China(Information sciences) 2023年第1期66卷 97-114页

作者： Peiyun ZHANG Chenxi LI Mengchu ZHOU Wenjun HUANG Abdullah ABUSORRAH Omaimah O.BAMASAG Engineering Research Center of Digital Forensics of Ministry of Education School of Computer and SoftwareNanjing University of Information Science and Technology School of Computer and Information Anhui Normal University Department of Electrical and Computer Engineering New Jersey Institute of Technology Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer Engineering Faculty of Engineering and K.A.CARE Energy Research and Innovation CenterKing Abdulaziz University Department of Computer Science Faculty of Computing and Information Technology Center of Excellence in Smart Environment Research King Abdulaziz University

In blockchain networks, transactions can be transmitted through channels. The existing transmission methods depend on their routing information. If a node randomly chooses a channel to transmit a transaction, the transmission may be aborted due to insufficient funds(also called balance) or a low transmission rate. To increase the success rate and reduce transmission delay across all transactions, this work proposes a transaction transmission model for blockchain channels based on non-cooperative game *** balance, channel states, and transmission probability are fully considered. This work then presents an optimized channel transaction transmission algorithm. First, channel balances are analyzed and suitable channels are selected if their balance is sufficient. Second, a Nash equilibrium point is found by using an iterative sub-gradient method and its related channels are then used to transmit transactions. The proposed method is compared with two state-of-the-art approaches: Silent Whispers and Speedy Murmurs. Experimental results show that the proposed method improves transmission success rate, reduces transmission delay,and effectively decreases transmission overhead in comparison with its two competitive peers.

关键词： Blockchain channel transaction transmission channel balance channel state channel transmission probability non-cooperative game

来源：评论

学校读者我要写书评

暂无评论

Revisiting the Self-Consistency Challenges in Multi-Choice Question Formats for Large Language Model Evaluation 30

Revisiting the Self-Consistency Challenges in Multi-Choice Q...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhou, Wenjie Wang, Qiang Xu, Mingzhou Duan, Xiangyu School of Computer Science and Technology Soochow University China Hithink RoyalFlush AI Research Institute

ISBN: (纸本)9782493814104

Multi-choice questions (MCQ) are a common method for assessing the world knowledge of large language models (LLMs), demonstrated by benchmarks such as MMLU and C-Eval. However, recent findings indicate that even top-tier LLMs, such as ChatGPT and GPT4, might display inconsistencies when faced with slightly varied inputs. This raises concerns about the credibility of MCQ-based evaluations. To address this issue, we introduced three knowledge-equivalent question variants: option position shuffle, option label replacement, and conversion to a True/False format. We rigorously tested a range of LLMs, varying in model size (from 6B to 70B) and types-pretrained language model (PLM), supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF). Our findings from MMLU and C-Eval revealed that accuracy for individual questions lacks robustness, particularly in smaller models ( © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Proactive Caching at the Wireless Edge:A Novel Predictive User Popularity-Aware Approach

引用

computer Modeling in Engineering & sciences 2024年第8期140卷 1997-2017页

作者： Yunye Wan Peng Chen Yunni Xia Yong Ma Dongge Zhu Xu Wang Hui Liu Weiling Li Xianhua Niu Lei Xu Yumin Dong College of Computer Science Chongqing UniversityChongqing400044China School of Computer and Software Engineering Xihua UniversityChengdu610039China School of Computer and Information Engineering Jiangxi Normal UniversityNanchang330022China Electric Power Research Institute of State Grid Ningxia Electric Power Co. Ltd.Yinchuan750002China College of Mechanical and Vehicle Engineering Chongqing UniversityChongqing400030China School of Computer Science and Technology Beijing Institute of TechnologyBeijing100083China School of Computer Science and Technology Dongguan University of TechnologyDongguan523808China School of Emergency Management Xihua UniversityChengdu610039China College of Computer and Information Science Chongqing Normal UniversityChongqing401331China

Mobile Edge Computing(MEC)is a promising technology that provides on-demand computing and efficient storage services as close to end users as *** an MEC environment,servers are deployed closer to mobile terminals to exploit storage infrastructure,improve content delivery efficiency,and enhance user ***,due to the limited capacity of edge servers,it remains a significant challenge to meet the changing,time-varying,and customized needs for highly diversified content of ***,techniques for caching content at the edge are becoming popular for addressing the above *** is capable of filling the communication gap between the users and content providers while relieving pressure on remote cloud ***,existing static caching strategies are still inefficient in handling the dynamics of the time-varying popularity of content and meeting users’demands for highly diversified entity *** address this challenge,we introduce a novel method for content caching over MEC,i.e.,*** synthesizes a content popularity prediction model,which takes users’stay time and their request traces as inputs,and a deep reinforcement learning model for yielding dynamic caching *** results demonstrate that PRIME,when tested upon the MovieLens 1M dataset for user request patterns and the Shanghai Telecom dataset for user mobility,outperforms its peers in terms of cache hit rates,transmission latency,and system cost.

关键词： Mobile edge computing content caching system average cost deep reinforcement learning collaborative mechanism

来源：评论

学校读者我要写书评

暂无评论

Track correlation algorithm based on CNN-LSTM for swarm targets

引用

Journal of Systems Engineering and Electronics 2024年第2期35卷 417-429页

作者： CHEN Jinyang WANG Xuhua CHEN Xian Research Institute for National Defense Engineering Academy of Military SciencesLuoyang 471023China Information Engineering University Zhengzhou 450001China School of Computer Science and Technology Xidian UniversityXi’an 710071China

The rapid development of unmanned aerial vehicle(UAV) swarm, a new type of aerial threat target, has brought great pressure to the air defense early warning system. At present, most of the track correlation algorithms only use part of the target location, speed, and other information for *** this paper, the artificial neural network method is used to establish the corresponding intelligent track correlation model and method according to the characteristics of swarm ***, a route correlation method based on convolutional neural networks (CNN) and long short-term memory (LSTM)Neural network is designed. In this model, the CNN is used to extract the formation characteristics of UAV swarm and the spatial position characteristics of single UAV track in the formation,while the LSTM is used to extract the time characteristics of UAV swarm. Experimental results show that compared with the traditional algorithms, the algorithm based on CNN-LSTM neural network can make full use of multiple feature information of the target, and has better robustness and accuracy for swarm targets.

关键词： track correlation correlation accuracy rate swarm target convolutional neural network(CNN) long short-term memory(LSTM)neural network

来源：评论

学校读者我要写书评

暂无评论

Adaptive Cost Aggregation in Iterative Depth Estimation for Efficient Multi-view Stereo 12th

Adaptive Cost Aggregation in Iterative Depth Estimation for...

引用

12th International Conference on Image and Graphics, ICIG 2023

作者： Wang, Xiang Bai, Xiao Wang, Chen School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University Beijing China

ISBN: (纸本)9783031463075

The deep multi-view stereo (MVS) approaches generally construct 3D cost volumes to regularize and regress the depth map. These methods are limited with high-resolution outputs since the memory and time costs grow cubically as the volume resolution increases. In this paper, we presented an multi-stage iterative depth map estimation method for MVS. In our network, the cost volume is iteratively processed by lightweight 2D convolution based GRU modules, and the multi-stage coarse-to-fine structure is adopted to speed up the depth estimation process. To further improve the 3D reconstruction quality, we make improvements from two different perspectives of adaptive cost aggregation: a view-adaptive weighting module is proposed to account for the occlusion problem in cost volume fusion, and a spatial-adaptive deformable geometric feature encoding module is introduced to the cost volume feature encoding before feeding into GRUs for stronger modeling capability. Experiments on the DTU dataset demonstrated the effectiveness of the proposed network in accuracy with remarkable efficiency performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Iterative methods

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：