检索结果-内蒙古大学图书馆

Visual-semantic network: a visual and semantic enhanced model for gesture recognition

Visual Intelligence 2023年第1期1卷 71-83页

作者： Yizhe Wang Congqi Cao Yanning Zhang National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer ScienceNorthwestern Polytechnical UniversityXi’an710129China

Gesture recognition has attracted considerable attention and made encouraging progress in recent years due to its great potential in ***,the spatial and temporal modeling in gesture recognition is still a problem to be ***,existing works lack efficient temporal modeling and effective spatial attention *** efficiently model temporal information,wefirst propose a long-and short-term temporal shift module(LS-TSM)that models the long-term and short-term temporal information ***,we propose a spatial attention module(SAM)that focuses on where the change primarily occurs to obtain effective spatial attention *** addition,the semantic relationship among gestures is helpful in gesture ***,this is usually neglected by previous ***,we propose a label relation module(LRM)that takes full advantage of the relationship among classes based on their labels’semantic *** explore the best form of LRM,we design four different semantic reconstruction methods to incorporate the semantic relationship information into the class label’s semantic *** perform extensive ablation studies to analyze the best settings of each *** best form of LRM is utilized to build our visual-semantic network(VS Network),which achieves the state-of-the-art performance on two gesture datasets,i.e.,EgoGesture and NVGesture.

关键词： Gesture recognition Temporal modeling Spatial attention Semantic relationship

来源：评论

学校读者我要写书评

暂无评论

Clustering-based Image-Text Graph Matching for Domain Generalization 27th

Clustering-based Image-Text Graph Matching for Domain Genera...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Park, Nokyung Chae, Daewon Shim, Jeongyong Kim, Sangpil Kim, Eun-Sol Kim, Jinkyu Department of Computer Science and Engineering Korea University Seoul Korea Republic of Department of Artificial Intelligence Korea University Seoul Korea Republic of Department of Artificial Intelligence Application Hanyang University Seoul Korea Republic of Department of Computer Science Hanyang University Seoul Korea Republic of

ISBN: (纸本)9783031781919

Learning domain-invariant visual representations is important to train a model that can generalize well to unseen target task domains. Recent works demonstrate that text descriptions contain high-level class-discriminative information and such auxiliary semantic cues can be used as effective pivot embedding for domain generalization problems. However, they use pivot embedding in a global manner (i.e., aligning an image embedding with sentence-level text embedding), which does not fully utilize the semantic cues of given text description. In this work, we advocate for the use of local alignment between image regions and corresponding textual descriptions to get domain-invariant features. To this end, we first represent image and text inputs as graphs. We then cluster nodes within these graphs and match the graph-based image node features to the nodes of textual graphs. This matching process is conducted both globally and locally, tightly aligning visual and textual semantic sub-structures. We experiment with large-scale public datasets, such as CUB-DG and DomainBed, and our model achieves matched or better state-of-the-art performance on these datasets. The code is available at: https://***/noparkee/Graph-Clustering-based-DG. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Secure Management of Digital Academic Certificates Using Blockchain Technology 3rd

Secure Management of Digital Academic Certificates Using Blo...

引用

3rd International Conference on Machine Learning, Image Processing, Network Security and Data sciences, MIND 2021

作者： Biswas, Anindya Kumar Dasgupta, Mou Ray, Sangram Department of Computer Application National Institute of Technology Raipur Raipur492010 India Department of Computer Science and Engineering National Institute of Technology Sikkim Ravangla Sikkim737139 India

ISBN: (纸本)9789811958670

The education sector is striving/needed to bring innovation in its different activities and the blockchain technology (BT), which is proposed for Bitcoin cryptocurrency, has promising property in securely decentralizing many applications including the ledger for banking systems. In this paper, we employ blockchain in academics for secure storage and easy retrieval/online verification of the hard-earned certificates to be used in diverse areas namely jobs, higher educations, forgery-detection, etc. Note that the academic certificates are indispensable for everyone’s lives, and it is the time to keep such important property in non-destructible manner but with easy accessibility to all concerned. The basic idea is that an educational institution while publishing the results of examinations, in addition to the distribution of certificates/marksheets to the students must incorporate the same in blockchain as smart certificates and make them available in peer-to-peer (P2P) network. This avoids the maintenance of registers for results kept by colleges, universities, education sectors, etc.;however, it supports for proofs of degrees claimed by students and online quick verification for any issue including fake certificate submission. An institution based on the departments, disciplines and various programs run creates multiple blockchains corresponding to the registers maintained, though the first block called the genesis block contained institute’s identity, would be the common for all. For conceptualization, a prototype design for management of blockchain-based smart certificates with various uses is presented. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

DnnARs: An Artificial Intelligence Technique for Prediction of Antimicrobial Resistant Strains in E. coli Bacteria Causing Urine Tract Infection

引用

SN computer science 2024年第8期5卷 1-16页

作者： Nayak, Debasish Swapnesh Kumar Priyadarshini, Arpita Mahanta, Pabani Das, Tejaswini Sahoo, Santanu Kumar Swarnkar, Tripti Department of Computer Science and Engineering FET-ITER Siksha ‘O’ Anusandhan (Deemed to Be) University Bhubaneswar India Department of Computer Science and Engineering SOET Centurion University of Technology and Management Odisha Bhubaneswar India Department of Statistics Utkal University Bhubaneswar India Department of Electronics and Communication Engineering FET-ITER Siksha ‘O’ Anusandhan (Deemed to Be) University Bhubaneswar India Department of Computer Application National Institute of Technology Raipur India

The rise of antimicrobial resistance (AMR) in bacteria that cause infectious diseases poses a significant global health challenge, necessitating advanced prediction technology for effective management and response. This study aims to evaluate the predictive capabilities of several machine learning (ML) and deep learning (DL) models in identifying patterns of antibiotic resistance. We have proposed a comprehensive experimental framework that combines multiple machine learning algorithms and deep learning architectures to evaluate their efficacy and accuracy in predicting antibiotic resistance. We have developed DnnARs, an artificial intelligence pipeline designed to identify antibiotic-resistant strains of E. coli bacteria, which are mostly responsible for urinary tract infections (UTIs). DnnARs utilizes Synthetic Minority Over-sampling Technique (SMOTE) and applies feature engineering using principal component analysis (PCA) and t-distributed Stochastic neighbor embedding (t-SNE) on our dataset to evaluate the effectiveness of various AI models. Our model comparison demonstrates that DL models outperform ML models when the dataset is fine-tuned using SMOTE and feature engineering. Our DnnARs achieve a classification accuracy of 97%, a specificity of 91%, and a remarkable sensitivity of 100%. The DL models that were examined exhibit an average classification accuracy that is 3.66% higher than that of the ML models. The findings demonstrate the capability of deep learning methodology to enhance predictive analytics for antimicrobial resistance, offering a robust and efficient alternative to traditional machine learning techniques. This research aims to enhance diagnostic tools and medications, improve the management of infectious diseases, reduce antibiotic resistance, and integrate deep learning models into clinical workflows to enable immediate decision-making. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Antimicrobial resistance Artificial intelligence Deep learning Infectious disease Machine learning Urine tract infections

来源：评论

学校读者我要写书评

暂无评论

Exploring Spectrum Sharing Algorithms for 6G Cellular Communication Networks 15

Exploring Spectrum Sharing Algorithms for 6G Cellular Commun...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Pattanaik, Ashutosh Shweta Ahmed, Zahid School of Engineering and Technology Department of Mechanical Engineering Karnataka Bangalore India Arka Jain University Department of Pharmacy Jharkhand Jamshedpur India Vivekananda Global University Department of Computer Science & Application Jaipur India

ISBN: (纸本)9798350370249

6G cell verbal exchange networks might be the successor to 5G networks, and their success relies heavily upon optimization measures that are enabled through the exploration of spectrum-sharing algorithms (SSAs). SSAs are hard and fast techniques implemented to maximize machine assets, performance metrics, and operational performance. That is performed by way of lowering interference, permitting spectrum contextualization, and improving the sharing of underutilized and congested spectrum. For 6G verbal exchange networks, a heightened attention on advanced database storage, distributed computing, and interference avoidance techniques must be taken a good way to ensure the maximum green use of be had spectrum. This paper explores a spread of SSAs for 6G mobile communication networks, consisting of dynamic spectrum get admission to, non-orthogonal more than one get right of entry to, and direct tool-enabled opportunistic spectrum usage. We evaluate current research that has been implemented to the improvement of SSAs and offer insight into future demanding situations and programs inside the subject. Furthermore, we talk about the significance of massive records and systems getting to know in the creation of SSA algorithms, providing capability enhancements to the ever-changing 6G communique networks. Standard, the usage of SSAs in 6G verbal exchange networks can make certain the most effective and green usage of be had spectrum, at the same time as additionally imparting extraordinary stages of aid flexibility © 2024 IEEE.

关键词： Cellular Contextualization Machine Learning Non-Orthogonal Spectrum-Sharing Successor

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation and Deep Neuro-fuzzy Network for Student Performance Prediction with MapReduce Framework

引用

International Journal of Automation and computing 2021年第6期18卷 981-992页

作者： Amlan Jyoti Baruah Siddhartha Baruah Department of Computer Science and Engineering Assam Kaziranga UniversityJorhat 785006India Department of Computer Application Jorhat Engineering CollegeJorhat 785007India

The main aim of an educational institute is to offer high-quality education to students. The system to achieve better quality in the educational system is to find the knowledge from educational data and to discover the attributes that manipulate the performance of students. Student performance prediction is a major issue in education and training, specifically in the educational data mining system. This research presents the student performance prediction approach with the MapReduce framework based on the proposed fractional competitive multi-verse optimization-based deep neuro-fuzzy network. The proposed fractional competitive multi-verse optimization-based deep neuro-fuzzy network is derived by integrating fractional calculus with competitive multi-verse optimization. The MapReduce framework is designed with the mapper and the reducer phase to perform the student performance prediction mechanism with the deep learning classifier. The input data is partitioned at the mapper phase to perform the data transformation process, and thereby the features are selected using the distance measure. The selected unique features are employed for the data segmentation process, and thereafter the prediction strategy is accomplished at the reducer phase by the deep neuro-fuzzy network classifier. The proposed method obtained the performance in terms of mean square error, root mean square error and mean absolute error with the values of 0.338 3, 0.581 7, and 0.391 5, respectively.

关键词： Educational data mining(EDA) MapReduce framework deep neuro-fuzzy network student performance data augmentation

来源：评论

学校读者我要写书评

暂无评论

Assessing the Robustness of Machine Learning Algorithms against Emerging Privacy and Security Threats in Medical applications 15

Assessing the Robustness of Machine Learning Algorithms agai...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Rao, Srikrishna Baskar Goswami, Sarbojeet Goyal, Manish Kumar School of Engineering and Technology Department of Aerospace Engineering Karnataka Bangalore India ARKA JAIN University Department of optometry Jharkhand Jamshedpur India Vivekananda Global University Department of Computer Science & Application Jaipur India

ISBN: (纸本)9798350370249

Using gadgets to realize algorithms in medical packages can provide new insights and talents, including new approaches to diagnose illnesses or reveal treatments. Rising privacy and security threats pose potential dangers to those structures that can restrict their efficacy and average performance. To make sure tool mastering algorithms are resilient to those threats, it is critical to assess their robustness. This summary offers an assessment of techniques to evaluate the robustness of tool-getting-to-know algorithms against emerging privacy and protection threats in medical programs. First, we check the kinds of threats and discuss how they'll affect the general performance of machine studying algorithms. Secondly, we compare a selection of strategies for measuring the robustness of gadgets and gaining knowledge of algorithms, which include static, dynamic, and adverse check strategies. Ultimately, we speak about techniques for mitigating threats in scientific packages, which provides for incorporating relaxed layout thoughts in tool studying structures and utilizing smoke assessments and strain tests. Through this assessment, we aim to provide more facts on the techniques for assessing the robustness of gadget-studying algorithms against rising privacy and security threats in scientific programs. © 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

FedDGA: Federated Multitask Learning Based on Dynamic Guided Attention

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 268-280页

作者： Sun, Haoyun Zhao, Hongwei Xu, Liang Zhang, Weishan Guan, Hongqing Yang, Su China University of Petroleum Qingdao266580 China Shandong Data Open Innovative Application Laboratory Qingdao266580 China WINDAKA Technology Company Ltd. Qingdao266580 China Beijing University of Science and Technology Beijing100083 China Swansea University Department of Computer Science Faculty of Science and Engineering SwanseaSA2 8PP United Kingdom

The proliferation of privacy-sensitive data has spurred the development of federated learning (FL), which is an important technology for state-of-the-art machine learning and responsible AI. However, most existing FL methods are constrained in their applicability and generalizability due to their narrow focus on specific tasks. This article presents a novel federated multitask learning (FMTL) framework that is capable of acquiring knowledge across multiple tasks. To address the challenges posed by non-IID data and task imbalance in FMTL, this study proposes a federated fusion strategy based on dynamic guided attention (FedDGA), which adaptively fine-tunes local models for multiple tasks with personalized attention. In addition, this article designed dynamic batch weight (DBW) to balance the task losses and improve the convergence speed. Extensive experiments were conducted on various datasets, tasks, and settings, and the proposed method was compared with state-of-the-art methods such as FedAvg, FedProx, and SCAFFOLD. The results show that our method achieves significant performance gains, with up to 11.1% increase in accuracy over the baselines. © 2020 IEEE.

关键词： Scaffolds

来源：评论

学校读者我要写书评

暂无评论

Applying Deep Neural Networks to Sentiment Analysis in Social Media 3

Applying Deep Neural Networks to Sentiment Analysis in Socia...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Meena, Y.R. Shrivastav, Amit Kumar Kharbas, Vikas Kumar School of Engineering and Technology Department of Civil Engineering Karnataka Bangalore India Arka Jain University Office of Registrar Jharkhand Jamshedpur India Vivekananda Global University Department of Computer Science & Application Jaipur India

ISBN: (纸本)9798350381931

Deep Neural Networks (DNNs) have currently been applied to sentiment evaluation responsibilities in social media, attaining advanced overall performance compared to conventional machine mastering techniques. That is due to the truth that DNNs are capable of analyzing representations via non-linear function maps, permitting them to seize the complex semantic relationships in textual content correctly. DNNs are also perfect for natural language processing (NLP) obligations because they can generalize from sparse records and use distributed representations in huge-scale datasets. The maximum commonly used DNN architectures for sentiment evaluation in social media are recurrent neural networks (RNNs) and convolutional neural networks (CNNs). RNNs are especially nicely applicable to this project due to the fact that they are able to capture temporal and contextual data and capture the dynamics of language use. RNNs are also extra sturdy to noisy or unstructured entry, which is commonplace in social media information. Alternatively, CNNs are nicely suited to seize neighborhood patterns in textual content, consequently permitting them to study neighborhoods, which means from phrases or phrases. In order to observe DNNs to sentiment analysis in social media, these networks ought to be taught with relevant and correct labels. It requires the development of an excessively satisfactory categorized dataset for training and validation purposes, which can be quite exertion-intensive. Additionally, DNNs are required to enter statistics in a form that is suitable for education and can frequently be non-trivial to extract from social media resources. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Fast Crop Pest Detection Using Lightweight Feature Extraction and Knowledge Distillation

Fast Crop Pest Detection Using Lightweight Feature Extractio...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Yang, Ze Jiang, Xianliang Jin, Guang Huang, Junkai Bai, Jie Yu, Dingxin Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China Zhejiang Key Laboratory of Mobile Network Application Technology Ningbo China

ISBN: (纸本)9798350337020

Pest detection is critical for achieving effective pest control. However, the current deep learning-based pest detection algorithm is unsuitable for deployment on resource-limited edge devices due to its extensive computation and long inference time. Although lightweight models have been widely used for practical detection, their insufficient feature extraction capability leads to a decline in detection accuracy. This paper proposes a fast algorithm for crop pest detection based on lightweight feature extraction and knowledge distillation. Firstly, we introduce partial convolution and propose a lightweight feature extraction module, C3Faster, which reduces the model's computation and speeds up model inference while ensuring effective feature extraction. Secondly, we use knowledge distillation to improve the model's detection accuracy by using teacher networks to assist in training. Finally, we created a dataset, CropPest6, consisting of six crop pest categories and conducted experiments. The experimental results demonstrate that our method reduces the detection time, number of parameters, and computation by 17%, 38%, and 44%, respectively, compared to the baseline model. Furthermore, our method achieves 93.9% Precision, 93.6% Recall, and 97.5% mean Average Precision (mAP), demonstrating its practical suitability for fast crop pest detection. © 2023 IEEE.

关键词： crop pests deep learning object detection pest detection

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：