检索结果-内蒙古大学图书馆

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Gopal, Vidhya Surendar, U. Bajulunisha, A. Tamilselvi, M. Sathiyapriya, V. Saranya, N. Sona College of Technology Department of Computer Science and Engineering Salem India Srm institute of Science and Technology Department of Electronics and Communication Engineering Chennai India Chennai Institute of Technology Department of Computer Science and Engineering Kundrathur India Roever Engineering College Department of Computer Science and Engineering Perambalur India Knowledge Institute of Technology Department of Computer Science and Engineering Salem India Karpagam College of Engineering Department of Artificial Intelligence and Data Science Coimbatore India

ISBN: (纸本)9798331508456

The difficulty with dynamic and heterogeneous natured edge computing environments is resource provisioning. Reinforcement Learning (RL) can be promising to solve the problems of resource allocation under conditions of dynamics and complexity. This research work presents a novel DDPG-based (Deep Deterministic Policy Gradient) approach for optimizing the dynamics of resource allocation in edge computing environments by exploiting the CRAWDAD KAIST-WIBRO dataset for the proposed model. This approach implements a neural network that learns the optimal policies of allocations with dynamism towards new changes in workloads and resource availabilities. In order to test the performance of this method, conducted several simulations over real-world workload and resource data, mapping the parameters like rewards and variation in episodes. The simulation results indicate that proposed approach performs superior compared to traditional heuristic-based approaches as well as other RL algorithms for resource usage, response time, and energy efficiency. This proposed approach permits optimized resource utilization along with quality of service, of paramount importance in executing complex and demanding applications at the edge computing environment. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Optimization of fracture reduction robot controller based on improved sparrow algorithm

引用

Biomimetic intelligence & Robotics 2023年第4期3卷 16-28页

作者： Baichuan An Jianwen Chen Hao Sun Minghuan Yin Zicheng Song Chao Zhuang Cheng Chang Minghe Liu School of Artificial Intelligence and Data Science Hebei University of TechnologyTianjin 300401China Limb Deformity Correction and Function Reconstruction Department Southern University of Science and Technology HospitalShenzhen 518000China Engineering Research Center of Intelligent Rehabilitation Device and Detection Technology Ministry of EducationTianjin 300401China

The accuracy of a fracture reduction robot(FRR)is critical for ensuring the safety of *** the repositioning accuracy of a FRR,reducing the error,and realizing a safer and more stable folding motion is *** achieve this,a sparrow search algorithm(SSA)based on the Levy flight operator was proposed in this study for self-tuning the robot controller *** inverse kinematic analysis of the FRR was also *** robot dynamics model was established using Simulink,and the inverse dynamics controller for the fracture reduction mechanism was designed using the computed torque control *** simulation and physical experiments were also *** actual motion trajectory of the actuator drive rod and its error with a desired trajectory was obtained through *** optimized Levy-sparrow search algorithm(Levy-SSA)crack reduction robot controller demonstrated an overall reduction of two orders of magnitude in the reduction error,with an average error reduction of 98.74%compared with the traditional unoptimized *** Levy-SSA increased the convergence of the crack reduction robot control system to the optimal solution,improved the accuracy of the motion trajectory,and exhibited important implications for robot controller optimization.

关键词： Fracture reduction robot The sparrow search algorithm Levy flight Reduction accuracy

来源：评论

学校读者我要写书评

暂无评论

Analysis and Design of Surgical Instrument Localization Algorithm

引用

Computer Modeling in engineering & sciences 2023年第10期137卷 669-685页

作者： Siyu Lu Jun Yang Bo Yang Zhengtong Yin Mingzhe Liu Lirong Yin Wenfeng Zheng School of Automation University of Electronic Science and Technology of ChinaChengdu610054China College of Resource and Environment Engineering Guizhou UniversityGuiyang550025China School of Data Science and Artificial Intelligence Wenzhou University of TechnologyWenzhou325000China Department of Geography and Anthropology Louisiana State UniversityBaton Rouge70803USA

With the help of surgical navigation system,doctors can operate on patients more intuitively and *** positioning accuracy and real-time performance of surgical instruments are very important to the whole *** this paper,we analyze and design the detection algorithm of surgical instrument location mark,and estimate the posture of surgical *** addition,we optimized the pose by ***,the algorithm of location mark detection proposed in this paper and the posture analysis data of surgical instruments are verified and analyzed through *** final result shows a high accuracy.

关键词： Surgical navigation system surgical instruments positioning positioning mark detection algorithm matching algorithm posture analysis

来源：评论

学校读者我要写书评

暂无评论

Text Extraction with Optimal Bi-LSTM

引用

Computers, Materials & Continua 2023年第9期76卷 3549-3567页

作者： Bahera H.Nayef Siti Norul Huda Sheikh Abdullah Rossilawati Sulaiman Ashwaq Mukred Saeed Computer Techniques Engineering Department Ibn Khaldun University CollegeBaghdad10011Iraq Faculty of Information Science and Technology Universiti Kebangsaan MalaysiaBangiSelangor43600Malaysia School of Electrical Engineering and Artificial Intelligence Xiamen University MalaysiaSepang43900Malaysia

Text extraction from images using the traditional techniques of image collecting,and pattern recognition using machine learning consume time due to the amount of extracted features from the *** Neural Networks introduce effective solutions to extract text features from images using a few techniques and the ability to train large datasets of images with significant *** study proposes using Dual Maxpooling and concatenating convolution Neural Networks(CNN)layers with the activation functions Relu and the Optimized Leaky Relu(OLRelu).The proposed method works by dividing the word image into slices that contain *** pass them to deep learning layers to extract feature maps and reform the predicted *** Short Memory(BiLSTM)layers extractmore compelling features and link the time sequence fromforward and backward directions during the training *** Connectionist Temporal Classification(CTC)function calcifies the training and validation loss *** addition to decoding the extracted feature to reform characters again and linking them according to their time *** proposed model performance is evaluated using training and validation loss errors on the Mjsynth and Integrated Argument Mining Tasks(IAM)*** result of IAM was 2.09%for the average loss errors with the proposed dualMaxpooling and *** the Mjsynth dataset,the best validation loss rate shrunk to 2.2%by applying concatenating CNN layers,and Relu.

关键词： Deep neural network text features dual max-pooling concatenating convolution neural networks bidirectional long short memory text connector characteristics

来源：评论

学校读者我要写书评

暂无评论

Machine learning-based classification study of rice blast disease 5

Machine learning-based classification study of rice blast di...

引用

5th International Conference on Computer Vision and data Mining, ICCVDM 2024

作者： Yang, Xu Liu, Fangyuan Song, Shaozhong An, Xiaofeng Wu, Yonghao School of Electronic Information Engineering Changchun University of Science and Technology Changchun China School of Data Science and Artificial Intelligence JiLin Engineering Normal University Changchun China Education Quality Monitoring Center JiLin Engineering Normal University Changchun China

ISBN: (纸本)9781510682863

Begin Rice, as the largest food crop grown in China, has shown a high incidence of rice blast disease, which seriously threatens the sustainability of rice production. A UAV multispectral remote sensing platform is used to realize the identification and monitoring of the incidence of rice blast disease and early warning at the field level, which assists variable fertilizer and drug application by plant protection UAVs. This research is based on a rice blast experiment in a large field in Wanchang Town, Yongji County, Jilin City, based on a malefactor, using a UAV multispectral remote sensing platform to obtain images of two fertility stages, namely, the nodulation stage(NS) and the spike stage(SS) of rice, and using six different vegetation index parameters as inputs to establish a DBO-XGBoost classification model, with an accuracy rate of more than 90% for both fertility stages. © 2024 SPIE.

关键词： Vegetation

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Deep Learning Technique for Crack Identification in Composite Materials

An Enhanced Deep Learning Technique for Crack Identificatio...

引用

International Conference on Advances in data-driven Computing and Intelligent Systems, ADCIS 2022

作者： Ramanathan, Saveeth Sankareswaran, Uma Maheswari Mohanraj, Prabhavathy Department of Computer Science Engineering Coimbatore Institute of Technology Coimbatore India Department of Electronics and Communication Engineering Coimbatore Institute of Technology Coimbatore India Department of Artificial Intelligence and Data Science Coimbatore Institute of Technology Coimbatore India

ISBN: (纸本)9789819909803

Composite material consists of more than one substance, which inherit the superior properties of the constituent’s elements for light weight and tensile strength. The identification of cracks in composite material at an earlier stage reduces the cost and effort. Deep learning is a complex model in machine learning to extract significant features from a large dataset. The suitable construction of convolutional neural network topology for the application will give better results. Our proposed model uses Bayesian optimization for hyper-parameter tuning which updates the hyper-parameter value for each iteration to improvise the accuracy. In this work real time, composite material images were taken as dataset captured by Silicon Electron Microscope and Evolution VF camera. Applied proposed model on Silicon Electron Microscope dataset, obtained accuracy over 88% and on Evolution VF dataset obtained accuracy over 91%. The integration of optimization techniques with CNN reduces the computational time. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Electron microscopes

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Coordination of Autonomous Vehicles for Smart Logistics in Industrial Environments 13

Multi-Agent Coordination of Autonomous Vehicles for Smart Lo...

引用

13th International Conference on System Modeling and Advancement in Research Trends, SMART 2024

作者： Kirubhakaran Karthikeswaran, D. Arun, M. Chakravarthy, R. Arun Akshya, J. Sundarrajan, M. Choudhry, Mani Deepak Surya Engineering College Department of Computer Science and Engineering Erode India Nehru Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India KGiSL Institute of Technology Department of Electronics and Communication Engineering Coimbatore India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Networking and Communications Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798350380583

Dynamic effects in industrial logistics demand more creative solutions towards the pursuit of efficiency and agility in evolving environments. Though static path-planning and taskallocation algorithms have provided the basis for how autonomous vehicles are guided within structured environments, those approaches usually fail to contend with indeterminacy outside of their modelled world, where there is dynamic obstacle appearance and changing task requirements, thus raising inefficiencies and costs of operations. To address these issues, the paper introduces a new multi-agent coordination system that uses a hybrid A∗ algorithm, integrating path planning with sophisticated detection methods for dynamic obstacles and improving superior task allocation. The system is supposed to provide improvements in real-time coordination in industries of autonomous vehicles to achieve efficient management of tasks and paths in changing environments. We integrate the latest in machine learning techniques for improved and real-time updates within the changes of the vehicle routing process based on both immediate sensory input and environmental interactions. Simulations show that our system performs the task much faster than classic systems: up to 30% improvement in completing tasks compared with classic models, and an average improvement of 25% in allround energy efficiency. It intelligently integrates machine learning techniques with real-time data processing. With the ability to scale up or down, or to adapt itself, this system addresses the chief challenges existing methods face and could revolutionize logistics operations within any industry. © 2024 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Bridging Machine Learning and Formal Concept Analysis for Effective Crowd Detection 25

Bridging Machine Learning and Formal Concept Analysis for Ef...

引用

25th International Arab Conference on Information technology, ACIT 2024

作者： Al-Oraiqat, Anas M. Drieiev, Oleksandr Samara, Ghassan Almatarneh, Sattam Al-Oraiqat, Karim A. Alrawashdeh, Hazim Drieieva, Hanna Elrashidi, Ali Hasan, Yassin M. Y. Zarqa University Faculty of Information Technology Department of Computer Science Jordan Central Ukrainian National Technical University Department of Cybersecurity and Software Kropyvnytskyi Ukraine Zarqa University Faculty of Information Technology Department of Data Science and Artificial Intelligence Jordan Zarqa University Faculty of Information Technology Department of Software Engineering Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia Assiut University Electrical Engineering Department Egypt

ISBN: (纸本)9798331540012

Crowd detection and prevention systems have become essential for managing densely populated areas. Modern systems leverage the combined power of machine learning, data mining, and image processing to extract and analyse features from crowded zones, enabling the identification of behavioural patterns and anomalies. However, most current solutions primarily focus on detection and lack robust decision-making and recommendation mechanisms for selecting appropriate crowd-prevention strategies. To address this gap, we integrate the predictive capabilities of machine learning models with the analytical and clustering strengths of Fuzzy Formal Concept Analysis (fuzzy FCA). Machine learning is employed to extract valuable insights from images of the area, with a neural network used to identify human figures, track individuals' positions, and predict crowd levels. This data is fed into an FFCA-based decision system, where crowd information is structured and clustered using lattice theory. This latter helped exclude low-crowd zones and cluster the rest of the monitored areas based on their crowd features. Additionally, we define bottom-up parsing algorithms to recommend suitable crowd-prevention plans based on crowd density levels within fuzzy formal concepts. Experiments confirmed not only the ability of fuzzy FCA to "exclude"low-crowd zones thanks to a used crowd threshold but also the efficient "feature-based clustering"of crowded zones into hierarchical formal concepts and these latter's "bottom-up parsing"to finally identify the dense zones. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Classification Techniques on Detecting Diabetic Retinopathy dataset 7

Deep Learning Classification Techniques on Detecting Diabeti...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Revathi, B. Usharani, C. Kezial Elizabeth, S.K. Nagaraj, P. Nithya, D. Ramco Institute of Technology Department of Artificial Intelligence And Data Science Virudhunagar India Mangayarkarasi College of Engineering Department of Computer Science And Engineering Madurai India Kalasalingam Academy of Research And Education Department of Computer Science And Engineering Virudhunagar Krishnankoil India Theni Kammavar Sangam College of Technology Department of Computer Science And Engineering Theni India

ISBN: (纸本)9798350359299

Deep learning algorithms can summarize images to understand how to carry out necessary tasks. The purpose of this study is to compare several deep learning methods. Both experience-based and explanation-based learning are possible in deep learning. The most widely utilized algorithms, such as Convolutional Neural Networks (CNN), Multilayer Perceptron (MLP), Generative Adversarial Networks (GAN), Radial Basis Function Networks (RBFN), and Deep Belief Networks (DBN), and the Diabetic Retinopathy dataset is utilized in this study to evaluate the effectiveness of the algorithms. A comparative study of the classifiers reveals that CNN performs more accurately than the other approaches. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Gloss-Free Sign Language Translation using Sign2gpt-Next Technique

Gloss-Free Sign Language Translation using Sign2gpt-Next Tec...

引用

2024 International Conference on Computing and Intelligent Reality Technologies, ICCIRT 2024

作者： Babisha, A. Umarani Srikanth, G. Angel Kiruba, D.R. Sundar, R. Department of Artificial Intelligence and Data Science Panimalar Engineering College Chennai India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Computer Science and Engineering DMI College of Engineering Chennai India Department of Computer Science and Engineering School of Computing Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9798331510299

This work proposes a new approach to convert the data from sign language to spoken language without exposing the data to a gloss layer. Whenever gloss annotations are used which frequently are incomplete and act as an intermediate representation, it is usually found to be a bottleneck in translating sign language videos. In order to avoid this, the authors use a combination of modern machine learning algorithms to arrive at the conclusion. They use Dino-V2 Vision Transformer to implement the function of extracting the spatial features of the input sign language video frames. This model is particularly suitable for learning and visual patterns in general and particularly for capturing fine details of these patterns. Further, a spatio-temporal transformer layer is added to automate the temporal processing of the Sign-Language which helps in the arrangement of the body gestures and limb movements needed at a specific temporal frame. It is then translated into the desired spoken language using a multilingual Generative Pre-trained Transformer (GPT) model. The approach can be said to be a big leap forward in sign language transliteration especially for such situations where few Gloss annotations are available, and making way for better and improved tools for the Deaf and the hard-of-hearing. © 2024 IEEE.

关键词： Audition

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：