检索结果-内蒙古大学图书馆

Spatial Correlation Module for Classification of Multi-Label Ocular Diseases Using Color Fundus Images

Computers, Materials & Continua 2023年第7期76卷 133-150页

作者： Ali Haider Khan Hassaan Malik Wajeeha Khalil Sayyid Kamran Hussain Tayyaba Anees Muzammil Hussain Department of Software Engineering Faculty of Computer SciencesLahore Garrison UniversityLahorePakistan Department of Computer Science School of Systems and TechnologyUniversity of Management and TechnologyLahore54000Pakistan Department of Computer Science&Information Technology University of Engineering and Technology(UET)PeshawarPakistan Department of Computer Science TIMES InstituteMultan60000Pakistan Department of Software Engineering School of Systems and TechnologyUniversity of Management and TechnologyLahore54000Pakistan

To prevent irreversible damage to one’s eyesight,ocular diseases(ODs)need to be recognized and treated *** fundus imaging(CFI)is a screening technology that is both effective and *** to CFIs,the early stages of the disease are characterized by a paucity of observable symptoms,which necessitates the prompt creation of automated and robust diagnostic *** traditional research focuses on image-level diagnostics that attend to the left and right eyes in isolation without making use of pertinent correlation data between the two sets of *** addition,they usually only target one or a few different kinds of eye diseases at the same *** this study,we design a patient-level multi-label OD(PLML_ODs)classification model that is based on a spatial correlation network(SCNet).This model takes into consideration the relevance of patient-level diagnosis combining bilateral eyes and multi-label ODs ***_ODs is made up of three parts:a backbone convolutional neural network(CNN)for feature extraction i.e.,DenseNet-169,a SCNet for feature correlation,and a classifier for the development of classification *** DenseNet-169 is responsible for retrieving two separate sets of attributes,one from each of the left and right *** then,the SCNet will record the correlations between the two feature sets on a pixel-by-pixel *** the attributes have been analyzed,they are integrated to provide a representation at the patient *** the whole process of ODs categorization,the patient-level representation will be *** efficacy of the PLML_ODs is examined using a soft margin loss on a dataset that is readily accessible to the public,and the results reveal that the classification performance is significantly improved when compared to several baseline approaches.

关键词： Ocular disease multi-label spatial correlation CNN eye disease

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance of Turkish Automatic Speech Recognition Using the Generative AI-Based Whisper Model 9

Evaluating the Performance of Turkish Automatic Speech Recog...

引用

9th International Conference on Computer Science and engineering, UBMK 2024

作者： Gokcimen, Tunahan Das, Bihter Das, Resul Firat University Technology Faculty Department of Software Engineering Elazig Turkey

ISBN: (纸本)9798350365887

Automatic speech recognition (ASR) for the Turkish language faces significant challenges due to its agglutinative structure and diverse phonetic variations. In this study, we evaluate the performance of OpenAI's Whisper models of varying sizes-tiny, base, small, and medium-on Turkish ASR tasks. The experiments were designed to measure each model's training loss, validation loss, word error rate (WER), and training time. Our findings indicate that larger models, specifically the whisper-medium, achieve superior performance with the lowest validation loss and WER, albeit at the cost of longer training times. The results demonstrate a substantial improvement in Turkish ASR capabilities compared to existing models, filling a significant gap in the literature. This study not only advances the state of ASR for the Turkish language but also provides valuable insights into the trade-offs between model complexity and performance, guiding future research and applications in the field. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Adversarial Graph Convolutional Network for Skeleton-Based Early Action Prediction

引用

Journal of Computer Science & technology 2024年第6期39卷 1269-1280页

作者： Xian-Shan Li Neng Zhang Bin-Quan Cai Jing-Wen Kang Feng-Da Zhao School of Information Science and Engineering Yanshan UniversityQinhuangdao 066004China School of Information Science and Engineering Xinjiang University of Science and TechnologyKorla 841000China Key Laboratory for Software Engineering of Hebei Province Yanshan UniversityQinhuangdao 066004China

This paper proposes a novel method for early action prediction based on 3D skeleton data. Our method combines the advantages of graph convolutional networks (GCNs) and adversarial learning to avoid the problems of insufficient spatio-temporal feature extraction and difficulty in predicting actions in the early execution stage of actions. In our method, GCNs, which have outstanding performance in the field of action recognition, are used to extract the spatio-temporal features of the skeleton. The model learns how to optimize the feature distribution of partial videos from the features of full videos through adversarial learning. Experiments on two challenging action prediction datasets show that our method performs well on skeleton-based early action prediction. State-of-the-art performance is reported in some observation ratios.

关键词： graph convolutional network adversarial learning skeleton-based action prediction

来源：评论

学校读者我要写书评

暂无评论

EfficientNetB0 Ensemble Model for Unified Deepfakes Detection 17

EfficientNetB0 Ensemble Model for Unified Deepfakes Detectio...

引用

17th International Conference on Open Source Systems and Technologies, ICOSST 2023

作者： Minhas, Samiya Afzal Mushtaq, Saad Javed, Ali University of Engineering and Technology Software Engineering Department Taxila Pakistan

ISBN: (纸本)9798350381320

In recent years, we have witnessed the generation of exceptional authentic deepfake images and videos due to the availability of cutting-edge Artificial Intelligence and deep learning techniques. Deepfakes represent synthetic multimedia content used to propagate disinformation for defamation, political unrest, manipulating elections, committing crimes, etc. In this paper, we present a novel ReLU-Swish EfficientNet (RSE-Net) for deepfakes detection. Our proposed RSE-Net is capable of reliably detecting deepfakes videos that are generated using different techniques. Our model leverages an ensemble of EfficientNet architectures, which are combined using a fusion technique to enhance the model's performance in detecting deepfakes. We suggested the ReLU activation in conv2D layers in place of regular Swish activation in EfficientNetB0 first variant as ReLU is computationally more efficient and reduces the risk of overfitting. We evaluated our model on two large-scale challenging deepfake datasets: FaceForensics ++ and CelebDF. Our RSE-Net attained an average accuracy of 99.7% on the FaceForensics++ dataset, and 96.09% on the CelebDF dataset. Furthermore, our model generalizes well and effectively detects deepfake videos in realworld scenarios. Thus, it is a valuable tool for analyzing and detecting potentially manipulated content. © 2023 IEEE.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-robot Path Planning Based on Optimal Energy Consumption 5

Research on Multi-robot Path Planning Based on Optimal Energ...

引用

5th International Conference on Big Data and Artificial Intelligence and software engineering, ICBASE 2024

作者： Wang, Yang Kang, Jinchuan Liu, Yuqi Tang, Qi Chengdu University of Information Technology School of Software Engineering Chengdu China

ISBN: (纸本)9798331506612

Aiming at the problem of energy consumption optimization in multi-robot path planning, this paper presents a multi-robot path planning algorithm based on optimal energy consumption. First, we improve the traditional A∗ algorithm to improve the efficiency and stability of multi-robot task execution through a three-step strategy, including queue priority, conflict avoidance and parking scheduling. Then, puts forward a new OECA∗ (Optimal Energy Consumption A∗) algorithm, the algorithm integrates the multiple factors combination model of energy consumption, in order to more accurately estimate the energy consumption in the process of robot path planning in. Then, this paper verifies the performance of the improved A∗ algorithm and OECA∗ algorithm through comparative experiments, and the results show that OECA∗ algorithm has a good advantage in energy consumption. The research in this paper provides an efficient solution to the path planning and scheduling problem of multi-robot systems. © 2024 IEEE.

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

An improved depth reconstruction method for unstable illumination environments in endoscopic surgeries 12

An improved depth reconstruction method for unstable illumin...

引用

SPIE 12th International Symposium on Multispectral Image Processing and Pattern Recognition, MIPPR 2023

作者： Peng, Shaowu Li, Zeqi Schoole of Software Engineering South China University of Technology Guangzhou China

ISBN: (数字)9781510674981

ISBN: (纸本)9781510674974

In the MIS (minimally invasive surgery), precise measurement and mastery of human organs is very important, even a slight wobble of instrument can cause a great deal of error. Digital 3D reconstruction technology can help doctor to confirm the real distance. Considering depth data is difficult to acquire and annotate on a large scale, especially in the human body scene, so many researches focus on self-supervised network. Most of them are based on a widely adopted hypothesis that Image brightness remains constant in adjacent frames, which cannot be satisfied in the body sense, with unstable lighting conditions in the narrow scale and complicated senses. To solve this problem, this paper proposes a high-precision depth reconstruction method for endoscopic surgical scenarios based on AFNet. Firstly, to overcome the limitations of the constant illumination assumption, we extract local features with illumination invariance and introduce quantization calculations for illumination-invariant feature descriptors in the loss function, to reduce the impact of illumination changes during the supervised process. Secondly, leveraging the synchronous movement of the light source and lens in the endoscope, we establish an association model between the brightness variation and depth prediction. This helps the network grasp the image context and smooth the depth better. Experiments show that our method improves the accuracy of depth estimation in endoscopic environments compared to baseline methods. The reconstruction effects on the ENDOVIS datasets of laparoscopic endoscopy and the ENDOSLAM datasets of gastrointestinal endoscopy are significantly improved. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Internal Model based SMC for FJRs using Singular Perturbation Approach 50

Internal Model based SMC for FJRs using Singular Perturbatio...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Khan, Raja Fawad Afsar Rsetam, Kamal Cao, Zhenwei Man, Zhihong School of Software and Electrical Engineering Swinburne University of Technology Melbourne Australia

ISBN: (纸本)9781665464543

The trajectory tracking performance of flexible joint robots (FJRs) is adversely affected in the presence of measurement noise, unmodelled system dynamics, external disturbances, and parametric variations. This paper proposes singular perturbation (SP) based continuous sliding mode controller (CSMC) schemes for the FJRs system to attain superior tracking accuracy. Firstly, the SP is applied to split the high-order FJRs system into two second-order quasi-steady-state and boundary layer models, which relaxes the requirements of high derivatives of system states in the control design. Secondly, two state-differentiators are developed for both subsystems to estimate unavailable velocity and acceleration signals. Then, based on estimated signals, the two CSMC schemes are constructed for both subsystems to attain the asymptotic convergence of tracking errors and fast variables, reduce chattering, and ensure robustness against external disturbance, measurement noise, and system uncertainties. Furthermore, the internal model method is applied to ease the tuning process of the sliding surface gains in the CSMC for both models. More importantly, the bandwidth of a fast control is chosen based on a slow subsystem bandwidth using Ruth Hurwitz stability criteria. Thus, the hectic gains tuning process is hugely simplified by applying an internal model based tuning on both subsystems. Finally, the provided simulation results verify the effectiveness of our proposed control in terms of measurement noise suppression, less chattering, robustness, and high tracking accuracy comparatively. © 2024 IEEE.

关键词： Stability criteria

来源：评论

学校读者我要写书评

暂无评论

Advanced DAG-Based Ranking(ADR)Protocol for Blockchain Scalability

引用

Computers, Materials & Continua 2023年第5期75卷 2593-2613页

作者： Tayyaba Noreen Qiufen Xia Muhammad Zeeshan Haider International School of Information Science and Engineering Dalian University of TechnologyDalian116620China School of Software Dalian University of TechnologyDalian116620China

In the past decade,blockchain has evolved as a promising solution to develop secure distributed ledgers and has gained massive ***,current blockchain systems face the problems of limited throughput,poor scalability,and high *** to the failure of consensus algorithms in managing nodes’identities,blockchain technology is considered inappropriate for many applications,e.g.,in IoT environments,because of poor *** paper proposes a blockchain consensus mechanism called the Advanced DAG-based Ranking(ADR)protocol to improve blockchain scalability and *** ADR protocol uses the directed acyclic graph ledger,where nodes are placed according to their ranking positions in the *** allows honest nodes to use theDirect Acyclic Graph(DAG)topology to write blocks and verify transactions instead of a chain of *** using a three-step strategy,this protocol ensures that the system is secured against doublespending attacks and allows for higher throughput and *** first step involves the safe entry of nodes into the system by verifying their private and public *** next step involves developing an advanced DAG ledger so nodes can start block production and verify *** the third step,a ranking algorithm is developed to separate the nodes created by *** eliminating attacker nodes,the nodes are ranked according to their performance in the system,and true nodes are arranged in blocks in topological *** a result,the ADR protocol is suitable for applications in the Internet of Things(IoT).We evaluated ADR on EC2 clusters with more than 100 nodes and achieved better transaction throughput and liveness of the network while adding malicious *** on the simulation results,this research determined that the transaction’s performance was significantly improved over blockchains like Internet of Things Applications(IOTA)and ByteBall.

关键词： Blockchain scalability directed acyclic graph advanced DAG-based ranking protocol

来源：评论

学校读者我要写书评

暂无评论

SlowFast Behavior Recognition Algorithm Based on Residual Frame 4

SlowFast Behavior Recognition Algorithm Based on Residual Fr...

引用

4th International Conference on Electronic Information engineering and Computer Science, EIECS 2024

作者： Yang, Deguo Hai, Wenwen School of Software Engineering Shenyang University of Technology Liaoning Shenyang China

ISBN: (纸本)9798331531409

In behavior recognition, the accuracy of recognition results is deeply affected by input video processing, which is crucial. Therefore, in order to improve the efficiency and accuracy of SlowFast behavior recognition model, we optimize the fast channel of the model, mainly in the fast channel, first apply residual frames to the video sequence to extract key frame changes, and then conduct behavior recognition based on these processed video data. This improvement aims to reduce computational redundancy, focus on more prominent motion features in the video, and improve the overall recognition efficiency and performance. Finally, the experimental results show that the proposed method improves the recognition accuracy compared with existing methods. © 2024 IEEE.

关键词： Behavior Recognition Residual Frame SlowFast

来源：评论

学校读者我要写书评

暂无评论

Event-Driven Attention Network:A Cross-Modal Framework for Efficient Image-Text Retrieval in Mass Gathering Events

引用

Computers, Materials & Continua 2025年第5期83卷 3277-3301页

作者： Kamil Yasen Heyan Jin Sijie Yang Li Zhan Xuyang Zhang Ke Qin Ye Li School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China School of Information and Software Engineering University of Electronic Science and Technology ofChinaChengdu611731China Kashi Institute of Electronics and Information Industry Kashi844508China

Research on mass gathering events is critical for ensuring public security and maintaining social ***,most of the existing works focus on crowd behavior analysis areas such as anomaly detection and crowd counting,and there is a relative lack of research on mass gathering *** believe real-time detection and monitoring of mass gathering behaviors are essential formigrating potential security risks and ***,it is imperative to develop a method capable of accurately identifying and localizing mass gatherings before disasters occur,enabling prompt and effective *** address this problem,we propose an innovative Event-Driven Attention Network(EDAN),which achieves image-text matching in the scenario of mass gathering events with good results for the first *** image-text retrieval methods based on global alignment are difficult to capture the local details within complex scenes,limiting retrieval *** local alignment-based methods aremore effective at extracting detailed features,they frequently process raw textual features directly,which often contain ambiguities and redundant information that can diminish retrieval efficiency and degrade model *** overcome these challenges,EDAN introduces an Event-Driven AttentionModule that adaptively focuses attention on image regions or textual words relevant to the event *** calculating the semantic distance between event labels and textual content,this module effectively significantly reduces computational complexity and enhances retrieval *** validate the effectiveness of EDAN,we construct a dedicated multimodal dataset tailored for the analysis of mass gathering events,providing a reliable foundation for subsequent *** conduct comparative experiments with other methods on our dataset,the experimental results demonstrate the effectiveness of *** the image-to-text retrieval task,EDAN achieved the best performance on the R@5 metric,w

关键词： Mass gathering events image-text retrieval attention mechanism

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：