检索结果-内蒙古大学图书馆

Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE), International Conference on

作者： S. Sudha Mercy S Madhavi Keerthika A Ch Prathima R T Prabhu Department of Computer Science & Design R.M.K Engineering College Chennai India Department of IT Vel tech Multi Tech Dr.Rangarajan Dr Sakunthala Engineering College Chennai India Department of ECE Aarupadai Veedu Institute of Technology Chennai India Department of Data Science School of Computing Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Tirupati India Department of ECE Saveetha School of Engineering SIMATS Chennai India

The mumps virus causes a very infectious sickness. The enlargement of the parotid salivary glands can be quite uncomfortable. Mumps treatment centers on symptom management. The illness must take its natural course. While most people experience very moderate symptoms, some develop severe consequences. The mumps virus can be avoided with the use of the MMR vaccination. In this research, we employ a convolutional neural network (CNN) technique to better automate mumps detection. In order to automate mumps detection, the authors of this research suggest a convolutional neural network (CNN) trained using XGBoost Classifier data. Incorporating machine learning (ML) technique comparisons. A mumps dataset consisting of 50×50 RGB picture patches served as the basis for all the models. Quantitative findings from each approach were put through validation testing based on their respective effectiveness metrics. To improve the efficiency of the model, the Mayfly Optimization Algorithm is implemented. Results show that the suggested method is effective, with 97% accuracy, suggesting that it might help decrease diagnostic errors caused by human error. And the suggested system we've developed is so precise that it outperforms the CNN model, which only gets around 92% of the time. Consequently, the suggested method is 5% more accurate than the CNN Model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Foundations of a computational science of game design: Abstractions and tradeoffs 16

Foundations of a computational science of game design: Abstr...

引用

16th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2020

作者： Cardona-Rivera, Rogelio E. Laboratory for Quantitative Experience Design School of Computing and the Entertainment Arts and Engineering Program University of Utah Salt Lake CityUT United States

ISBN: (纸本)9781577358497

This paper presents the foundations of a computational science of game design—a model of abstraction: the outcome of a situated design process that conceptualizes something in terms of something else for a specific purpose. The outcome of abstraction is modeled via an abstraction scheme, a step toward modeling the process of game design abstraction from a human-centered perspective. A scheme’s purpose is couched relative to a scheme’s properties, also defined herein;collectively, the properties represent the space of tradeoffs designers must navigate for engineering virtual worlds. This model’s analytical traction is evidenced by applying it to the design of pathfinding, a core behavior in artificial intelligence for games. More broadly, it is a foundation for shared progress because it affords directly comparing particular abstractions of concepts and phenomena across the gamut of research on intelligent systems in entertainment. Copyright © 2020, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Game design

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection: PyramidNet-ICNN Architecture With Modified BIRCH Segmentation

引用

Journal of Phytopathology 2025年第3期173卷

作者： Aarti P. Pimpalkar Arvind M. Jagtap Department of Computer Science and Engineering School of Computing MIT Art Design and Technology University Loni Kalbhor Pune Maharashtra India

Agriculture stands as the primary occupation in India, yet it faces a substantial annual loss of 35% in crop productivity due to plant diseases. These diseases pose a significant task in the sector of agriculture, emphasising the critical need for their automatic identification to efficiently monitor plant health. The conventional technique of analysis by specialists in laboratories is costly and time-consuming, even though the signs of the majority of diseases appear in plant leaves. Recognising the vital importance of early issue identification, this research proposes a novel hybrid Architecture, a hybrid of PyramidNet and ICNN models (Py-ICNN) for plant disease detection and classification with an Improved BIRCH (I-BIRCH) segmentation model, which uses an image as input. This framework follows a systematic approach, comprising preprocessing, segmentation, extraction of features and detection and classification of diseases. Using median and Contrast Limited Adaptive Histogram Equalisation (CLAHE) filtering, the input image first undergoes enhanced preprocessing. The preprocessed outcome is then subjected to I-Balanced Iterative Reducing and Clustering Using Hierarchies (BIRCH) segmentation. Then, features including IPHOG, multi-texton features and MBP-based features are extracted from the segmented image. These extracted features are then individually processed using PyramidNet and improved convolutional neural network (ICNN) to detect and classify the plant disease. Furthermore, the proposed Py-ICNN model is evaluated and compared with traditional methods. The findings demonstrate that the Py-ICNN framework obtained an accuracy of 93.70% and a specificity of 95.82%. These results demonstrate how well the Py-ICNN approach detects and classifies plant diseases.

关键词： I-BIRCH ICNN improved preprocessing IPHOG plant disease detection and classification

来源：评论

学校读者我要写书评

暂无评论

Towards Communication-efficient Federated Learning via Sparse and Aligned Adaptive Optimization

arXiv

引用

arXiv 2024年

作者： Deng, Xiumei Li, Jun Wei, Kang Shi, Long Xiong, Zeihui Ding, Ming Chen, Wen Jin, Shi Poor, H. Vincent School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing210094 China The Department of Computing Hong Kong Polytechnic University 999077 Hong Kong The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Data61 CSIRO SydneyNSW2015 Australia Department of Electronics Engineering Shanghai Jiao Tong University Shanghai200240 China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China Department of Electrical and Computer Engineering Princeton University NJ08544 United States

Adaptive moment estimation (Adam), as a Stochastic Gradient Descent (SGD) variant, has gained widespread popularity in federated learning (FL) due to its fast convergence. However, federated Adam (FedAdam) algorithms suffer from a threefold increase in uplink communication overhead compared to federated SGD (FedSGD) algorithms, which arises from the necessity to transmit both local model updates and first and second moment estimates from distributed devices to the centralized server for aggregation. Driven by this issue, we propose a novel sparse FedAdam algorithm called FedAdam-SSM, wherein distributed devices sparsify the updates of local model parameters and moment estimates and subsequently upload the sparse representations to the centralized server. To further reduce the communication overhead, the updates of local model parameters and moment estimates incorporate a shared sparse mask (SSM) into the sparsification process, eliminating the need for three separate sparse masks. Theoretically, we develop an upper bound on the divergence between the local model trained by FedAdam-SSM and the desired model trained by centralized Adam, which is related to sparsification error and imbalanced data distribution. By minimizing the divergence bound between the model trained by FedAdam-SSM and centralized Adam, we optimize the SSM to mitigate the learning performance degradation caused by sparsification error. Additionally, we provide convergence bounds for FedAdam-SSM in both convex and non-convex objective function settings, and investigate the impact of local epoch, learning rate and sparsification ratio on the convergence rate of FedAdam-SSM. Experimental results show that FedAdam-SSM outperforms baselines in terms of convergence rate (over 1.1× faster than the sparse FedAdam baselines) and test accuracy (over 14.5% ahead of the quantized FedAdam baselines). Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A review on additive/subtractive hybrid manufacturing of directed energy deposition(DED)process

Advanced Powder Materials

引用

Advanced Powder Materials 2022年第4期1卷 39-58页

作者： Mohammadreza Lalegani Dezaki Ahmad Serjouei Ali Zolfagharian Mohammad Fotouhi Mahmoud Moradi M.K.A.Ariffin Mahdi Bodaghi Department of Engineering School of Science and TechnologyNottingham Trent UniversityNottinghamNG118NSUK School of Engineering Deakin UniversityGeelong3216Australia Department of Materials MechanicsManagement and Design(3MD)Delft University of TechnologyDelftthe Netherlands School of Mechanical Aerospace and Automotive EngineeringFaculty of EngineeringEnvironment and ComputingCoventry UniversityCoventryCV12JHUK Department of Mechanical and Manufacturing Engineering Faculty of EngineeringUniversiti Putra MalaysiaSerdang43400Malaysia

Additive manufacturing(AM)processes are reliable techniques to build highly complex metallic *** energy deposition(DED)is one of the most common technologies to 3D print metal *** a wide range of literature that has discussed the ability of DED in metal printing,weak binding,poor accuracy,and rough surface still exist in final ***,limitations in 3D printing of metal powder and wire indicate post-processing techniques required to achieve high quality in both mechanical properties and surface ***,hybrid manufacturing(HM),specifically additive/subtractive hybrid manufacturing(ASHM)of DED has been proposed to enhance product *** is a capable process that combines two technologies with 3-axis or multi-axis *** methods have been suggested to increase the accuracy of machines to find better quality and *** contrast,drawbacks in ASHM still exist such as limitations in existing reliable materials and poor accuracy in machine coordination to avoid collision in the multi-axes *** should be noted that there is no review work with focuses on both DED and hybridization of DED ***,in this review work,a unique study of DED in comparison to ASHM as well as novel techniques are discussed with the objective of showing the capabilities of each process and the benefits of using them for different ***,new gaps are discussed in ASHM to enhance the layer bonding and surface quality with the processes'effects on microstructures and performance.

关键词： Additive manufacturing Additive/subtractive hybrid manufacturing 3D printing Hybrid manufacturing Metal alloysDirect energy deposition Machining

来源：评论

学校读者我要写书评

暂无评论

Study on Soft Robotic Pinniped Locomotion

arXiv

引用

arXiv 2023年

作者： Arachchige, Dimuthu D.K. Varshney, Tanmay Huzaifa, Umer Kanj, Iyad Nanayakkara, Thrishantha Chen, Yue Gilbert, Hunter B. Godage, Isuru S. School of Computing Jarvis College of Computing and Digital Media DePaul University ChicagoIL60604 United States College of Engineering Ohio State University ColumbusOH43210 United States Dyson School of Design Engineering Faculty of Engineering Imperial College London SW7 2BX United Kingdom Department of Biomedical Engineering Georgia Institute of Technology AtlantaGA30332 United States Department of Mechanical and Industrial Engineering Louisiana State University Baton RougeLA70803 United States Department of Engineering Technology and Industrial Distribution Texas A&M University College StationTX77843 United States

Legged locomotion is a highly promising but under-researched subfield within the field of soft robotics. The compliant limbs of soft-limbed robots offer numerous benefits, including the ability to regulate impacts, tolerate falls, and navigate through tight spaces. These robots have the potential to be used for various applications, such as search and rescue, inspection, surveillance, and more. The state-of-the-art still faces many challenges, including limited degrees of freedom, a lack of diversity in gait trajectories, insufficient limb dexterity, and limited payload capabilities. To address these challenges, we develop a modular soft-limbed robot that can mimic the locomotion of pinnipeds. By using a modular design approach, we aim to create a robot that has improved degrees of freedom, gait trajectory diversity, limb dexterity, and payload capabilities. We derive a complete floating-base kinematic model of the proposed robot and use it to generate and experimentally validate a variety of locomotion gaits. Results show that the proposed robot is capable of replicating these gaits effectively. We compare the locomotion trajectories under different gait parameters against our modeling results to demonstrate the validity of our proposed gait models. © 2023, CC BY-NC-SA.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Mathematical modelling and optimization of parameters for Al-Si-Fe aluminum alloy reinforced by Al 2 O 3 and graphite particles using Taguchi method

引用

Materials Today: Proceedings 2021年 44卷 979-986页

作者： Robale Dinsa Daba Devendra Kumar Sinha Habtamu Beri Satyam Shivam Gautam Gulam Mohammed Sayeed Ahmed Ram Sewak Singh Program of Mechanical Design and Manufacturing Engineering School of Mechanical Chemical and Materials Engineering ASTU ADAMA Ethiopia Department of Mechanical Engineering North Eastern Regional Institute of Science and Technology Itanagar India Department of Electronics and Communication School of Electrical Engineering and Computing ASTU ADAMA Ethiopia

In the present scenario the aluminum and its alloys are preferred due to requirement of lightweight high strength material. The present research article interrogates experimentally the study of actual density and porosity using powder metallurgy method. The experimental design is done using Taguchi L 16 orthogonal array. Actual density and porosity has been analyzed based on ‘smaller is best’ basis. Actual density and porosity are calculated using Archimedes principle. The leverage of four levels and five process parameters such as weight percentage of Al 2 O 3 , weight percentage of graphite, compaction pressure, compaction time and milling time are considered. Results reveal that Al 2 O 3 weight percentage has the highest leverage on density followed by compaction time and graphite weight percentage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rethinking Client Drift in Federated Learning: A Logit Perspective

arXiv

引用

arXiv 2023年

作者： Yan, Yunlu Feng, Chun-Mei Ye, Mang Zuo, Wangmeng Li, Ping Goh, Rick Siow Mong Zhu, Lei Chen, C.L. Philip Guangzhou Nansha511400 China The Institute of High Performance Computing A*STAR Singapore138632 Singapore The Hubei Luojia Laboratory National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China The School of Computer Science and Technology Harbin Institute of Technology Harbin130407 China The Hong Kong University of Science and Technology Hong Kong The Department of Computing the School of Design The Hong Kong Polytechnic University Hong Kong The School of Computer Science and Engineering South China University of Technology Guangzhou510006 China The Pazhou Lab Guangzhou510335 China

Federated Learning (FL) enables multiple clients to collaboratively learn in a distributed way, allowing for privacy protection. However, the real-world non-IID data will lead to client drift which degrades the performance of FL. Interestingly, we find that the difference in logits between the local and global models increases as the model is continuously updated, thus seriously deteriorating FL performance. This is mainly due to catastrophic forgetting caused by data heterogeneity between clients. To alleviate this problem, we propose a new algorithm, named FedCSD, a Class prototype Similarity Distillation in a federated framework to align the local and global models. FedCSD does not simply transfer global knowledge to local clients, as an undertrained global model cannot provide reliable knowledge, i.e., class similarity information, and its wrong soft labels will mislead the optimization of local models. Concretely, FedCSD introduces a class prototype similarity distillation to align the local logits with the refined global logits that are weighted by the similarity between local logits and the global prototype. To enhance the quality of global logits, FedCSD adopts an adaptive mask to filter out the terrible soft labels of the global models, thereby preventing them to mislead local optimization. Extensive experiments demonstrate the superiority of our method over the state-of-the-art federated learning approaches in various heterogeneous settings. The source code will be released. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Evaluation of KNN-NMF Algorithm for Recommendation Systems in E-Commerce

Evaluation of KNN-NMF Algorithm for Recommendation Systems i...

引用

IEEE Conference on Systems, Process & Control (ICSPC)

作者： Hew Sok Yen Samuel-Soma M. Ajibade Muhammed Basheer Jasser Bayan Issa Yoke Leng Yong Faizah Mohammed Bashir Emmanuel Falude Yakubu Aminu Dodo Department of Computing and Information Systems School of Engineering and Technology Sunway University Bandar Sunway Selangor Darul Ehsan Malaysia Research Centre for Nanomaterials and Energy Technology (RCNMET) School of Engineering and Technology Sunway University Petaling Jaya Selangor Malaysia Faculty of Informatics Engineering University of Aleppo Syria School of Information and Communication Technology HELP University Persiaran Cakerawala Subang Bestari Seksyen Shah Alam Malaysia Department of Decoration and Interior Design Engineering College of Engineering University of Hail Hail Kingdom of Saudi Arabia Malaysia-Japan International Institute of Technology (MJIIT) Universiti Teknologi Malaysia Jalan Sultan Yahya Petra Kuala Lumpur Malaysia Architectural Engineering Department College of Engineering Najran University Najran Kingdom of Saudi Arabia

ISBN: (数字)9798350391398

ISBN: (纸本)9798350391404

Due to growth in e-commerce, recommender systems have gained importance in providing recommendations to the user to help him or her make a choice. These systems not only assist the users in searching through the extensive product list but also increase businesses’ productivity by recommending products. The aim of this project is to suggest a hybrid recommender system which combines the aspects of collaborative and content-based filtering so as to enhance the efficiency of the recommendation system in e-commerce. In addition, it is to evaluate the performance of this model with the individual collaborative and content-based models. The study involved creating the CF and CBF models with the various algorithms like the Matrix Factorization, KNN, SVD, and the TF-IDF vectorization. The best models from CF and CBF were then combined with a Hybrid Filtering (HF) model by using weighted and switching combination to enhance the model’s effectiveness. The performance of the CF, CBF and the HF models was compared, in order to check if the proposed hybrid approach is better than the existing models. The results of the experiment show that the hybrid switching model provided better results than the CF and CBF models on their own. The hybrid filtering model had also managed to reduce the RMSE to $\mathbf{1. 0 6 5}$ and improved precision to 83.2%. This demonstrates the advantage of the proposed model over the traditional CF and CBF approaches. Our study validates that the hybrid filtering recommender system, especially the switching combination strategy, outperformed the traditional standalone models by integrating the benefits of both collaborative and content-based filtering. This provides a good starting point for future work and there are many directions in which the research can be expanded.

关键词： Productivity Machine learning algorithms Filtering Collaboration Switches Hafnium Nearest neighbor methods Electronic commerce User preference Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Immersive Technologies to Height Safety: Training Evaluation and Insights

Immersive Technologies to Height Safety: Training Evaluation...

引用

IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)

作者： André Cordeiro Regina Leite Lucas Gregory Márcio Catapan Alexandre Siqueira Tiago Silva Matheus Brandão Paulo Ambrosio Pedro Reis Ingrid Winkler Pharmaceutical Technology Institute Oswaldo Cruz Foundation Rio de Janeiro Brazil Civil Construction Department Bahia Federal Institute Salvador Brazil PPG-Design Paraná Federal University Curitiba Brazil College of Engineering University of Florida Gainesville USA Dept. of Mech. and Ind. Engineering NOVA School of Sci. and Technology Caparica Portugal Dept. of Engineering and Computing Santa Cruz State University Ilhéus Brazil School of Engineering and Technology Lusiada University Vila Nova Famalicão Portugal INCITE INDUSTRIA 4.0 SENAI CIMATEC Salvador Brazil

ISBN: (数字)9798331521578

ISBN: (纸本)9798331521585

Falls from height remain a leading cause of workplace fatalities worldwide, emphasizing the need for effective training. This study examines virtual reality as an immersive tool for safety training evaluation, focusing on working at height. Using the design Science Research approach, we developed an immersive environment simulating a 33-meter-high scenario, then tested with ten participants performing tasks. Data from observations, error reports, interviews, and Presence Questionnaire showed high engagement, immersion, and effective identification of unsafe behaviors. These findings highlight virtual reality's potential to enhance safety training and inform future improvements in sensory realism and scalability.

关键词： Training Solid modeling Scalability Employment Dynamics Virtual reality Particle measurements Reliability Interviews Testing

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：