检索结果-内蒙古大学图书馆

2022 Findings of the Association for Computational Linguistics: NAACL 2022

作者： Wu, Han Tan, Haochen Xu, Kun Liu, Shuqi Wu, Lianwei Song, Linqi City University of Hong Kong Shenzhen Research Institute Hong Kong Department of Computer Science City University of Hong Kong Hong Kong Huawei China Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University China

ISBN: (纸本)9781955917766

While conversational semantic role labeling (CSRL) has shown its usefulness on Chinese conversational tasks, it is still under-explored in non-Chinese languages due to the lack of multilingual CSRL annotations for the parser training. To avoid expensive data collection and error-propagation of translation-based methods, we present a simple but effective approach to perform zero-shot cross-lingual CSRL. Our model implicitly learns language-agnostic, conversational structure-aware and semantically rich representations with the hierarchical encoders and elaborately designed pre-training objectives. Experimental results show that our model outperforms all baselines by large margins on two newly collected English CSRL test sets. More importantly, we confirm the usefulness of CSRL to non-Chinese conversational tasks such as the question-in-context rewriting task in English and the multi-turn dialogue response generation tasks in English, German and Japanese by incorporating the CSRL information into the downstream conversation-based models. We believe this finding is significant and will facilitate the research of non-Chinese dialogue tasks which suffer the problems of ellipsis and anaphora. © Findings of the Association for Computational Linguistics: NAACL 2022 - Findings.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Real-Time Data Streams: The Future of Predictive Maintenance in Manufacturing

Real-Time Data Streams: The Future of Predictive Maintenance...

引用

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： Manish Kumar Goyal Haripriya Akhilendra Pratap Singh Department of Computer Science & Application Vivekananda Global University Jaipur India Department of Computer Science and Information Technology Jain (Deemed to be University) Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

Dynamic Predictive Modeling is a method that has brought about a revolutionary change in the field of preventive maintenance in the industrial sector. Using the benefits of real-time data streams and flexible algorithms, this cutting-edge technology enhances predictive maintenance processes. In this investigation, we evaluate the efficacy of Dynamic Predictive Modeling to that of numerous more conventional methods, including vibration analysis, acoustic emission analysis, thermography, oil analysis, ultrasonic testing, and data analytics. Accuracy, resource optimization, adaptability, downtime reduction, cost-effectiveness, and preventative maintenance are just a few of the criteria we use to evaluate the methods. The findings indicate that Dynamic Predictive Modeling outperforms its predecessors across a range of performance metrics. It can better adapt to the ever-changing industrial environment, allowing for more precise and timely breakdown forecasts. The allocation of resources and the economy of operation are both enhanced by the fact that maintenance procedures may be adjusted according to the actual condition of the equipment. Predictive maintenance is the most effective method for minimizing unscheduled downtime and increasing output in heavy industry. In a comparison of several approaches to predictive maintenance, Dynamic Predictive Modeling comes out on top with the highest aggregate score. A study reveals how an unconventional approach might improve the effectiveness and reliability of industrial operations. Increased equipment reliability, decreased maintenance costs, and a potential advantage in the manufacturing industry might arise from the use of dynamic predictive modeling.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Effect of Viewpoint Change Strategies on Multi-View Video and Audio Transmission QoE Over ICN/CCN

The Effect of Viewpoint Change Strategies on Multi-View Vide...

引用

IEEE Region 10 International Conference TENCON

作者： Toshiro Nunome Yoshiyuki Takada Department of En-gineering Computer Science Program Graduate School of Engineering Nagoya Institute of Technology Nagoya Japan Department of Engineering Computer Science Program Graduate School of Engineering Nagoya Institute of Technol-ogy Nagoya Japan

In this paper, we exploit caches on intermediate nodes for QoE enhancement of multi-view video and audio transmission over ICN/CCN by controlling the content request start timing of consumers. We assume the selected single viewpoint transmission method; a consumer receives video and audio streams of a requested viewpoint. We perform a simple experiment with two consumers. When the consumers play video and audio with the time difference, we assess the effect of cached content by the former consumer's request on the output quality of the latter consumer. We deal with two types of viewpoint change strategies for the former consumer, which affect the efficiency of cache utilization. From the assessment results, we see that cache utilization has an important factor in enhancing QoE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Symphony of Style: An Extensive Examination of Determination Mechanisms in Deep Learning-Inspired Outfit Suggestions

The Symphony of Style: An Extensive Examination of Determina...

引用

Computational Intelligence, Communication technology and Networking (CICTN), International Conference on

作者： Guru Prasad M S Ravatappa A Bhosagi Madhusudhana K Prithviraj Chandrappa S Vikash Kumar Department of Computer Science and Engineering Graphic Era (Deemed to be University) Dehradun India School of Computing and Information Technology Reva University Bengaluru India Dept. of Electronics & Communication Engineering SDM Institute of Technology Ujire India Department of Computer Science and Engineering Nitte (Deemed to be University) NMAMIT Mangalore India Department of Computer Science and Engineering Jain (Deemed-to-be University) Bengaluru India Department of Computer Application Graphic Era Deemed University Dehradun India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

In the field of the fashion industry, the introduction of deep learning technology has taken an innovative revolution by providing assistance in the construction of intellectual systems that are intelligent to deliver personalized ensemble recommendations. In this research work, an innovative ensemble recommendation structure called Deep Learning VGG16 (Visual Geometry Group 16) recommender is presented. The proposed method allows a deep learning model VGG16 to understand complex patterns and developments resulting from a vast group of fashion images. In order to increase the user experience and greater participation in the well-established fashion industry, the system offers personalized ensemble ideas. The important, core and fundamental component of the system is VGG16, consisting of 13 convolutional layers and 3 fully connected layers, which is used to support the analysis of fashion images. A cutting-edge convolutional neural network (CNN) model is improved over a large and diverse collection of fashion images. Model will extract advanced high-level information and statistics with the capability to distinguish particulars in colour patterns, clothing combinations, and stylistic elements. Using this process of development, the system becomes better at identifying user preferences and fashion trends.

关键词： Deep learning Adaptation models Visualization Virtual assistants Clothing Market research Clothing industry User experience Convolutional neural networks Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Optimizing Cloud Security with CNN and XGBoost Models for Intrusion Detection Systems

Optimizing Cloud Security with CNN and XGBoost Models for In...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Amit Karbhari Mogal V. Anitha Preeti Nitin Bhatt Kriti Srivasatava S. Rukmani Devi Anvesh Perada Department of Computer Science and Application MVP Samaj's CMCS College Nashik India Department of Computer Science and Engineering School of Engineering and Technology Dhanalakshmi Srinivasan University Trichy India Department of Electronics & Communication Engineering IIMT College of Engineering Greater Noida India Department of Computer Science and Engineering (Data Science) Dwarkadas J Sanghvi College of Engineering Vile Parle India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai India Department of Electrical and Computer Engineering Drexel University Philadelphia United States of America

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Cloud computing and Internet growth have simplified certain formerly difficult activities. This advancement has also revealed many security weaknesses. Due to cyberattacks, organizations need Intrusion Detection Systems (IDS) to protect their data and networks. Preprocessing, feature selection, and model training comprise the suggested strategy. Preprocessing includes data cleansing, standardization, and labeling. Information gain, chi-square, and PSO are used to choose features. CNN-XGBoost trains the model. The CNN-XGBoost model outperforms solo CNN and XGBoost with an average accuracy of 92.08%. This accuracy proves the hybrid method's cloud computing breach detection usefulness. The study underlines the importance of enhanced IDS models in cyber risk reduction. CNN's feature extraction and XGBoost's classification power provide a powerful, efficient, and reliable cloud intrusion detection model. Modern organizations benefit from this network security method.

关键词： Training Cloud computing Accuracy Computational modeling Standards organizations Intrusion detection Standardization Feature extraction Reliability Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Mortality Risk Prediction in Patients After Cardiac Surgery Using Machine Learning

Mortality Risk Prediction in Patients After Cardiac Surgery ...

引用

computer, Electronics & Electrical Engineering & their applications (IC2E3), International Conference on

作者： Shahnawaz Khan Gopal Kumar Thakur Shridhar Kulkarni Madan Mohan Tito Ayyalasomayajula Pundru Chandra Shaker Reddy Master of Computer Application Bundelkhand University Jhansi Utter Pradesh India Department of Data Sciences Harrisburg University of Science & Technology Pennsylvania USA School of Business & Technology Aspen University Phoenix Arizona USA School of Computer Science and Artificial Intelligence SR University Warangal Telangana India

ISBN: (数字)9798350388534

ISBN: (纸本)9798350388541

Norwood surgery restores systemic flow in neonates with solitary ventricle inherited heart abnormalities, but it is complicated and deadly. We created machinelearning(ML) strategies to anticipate cardiac surgery mortality using preoperative and intraoperative risk indicators. Mortality after surgery was the main consequence. Sensitivity, specificity, accuracy, and AUC were used to estimate model performance. The visualization algorithm used Shapley's additive explanations. Random-forest, neural-network, SVM, and gradient-boosting had AUC-values of 0.87, 0.79, 0.81, and 0.82 for anticipating cardiac surgery operative mortality, while EuroSCORE I and II, STS, and LR had 0.70, 0.73, 0.71, and 0.74. Shapley's additive explanations study of RF identified the top-20 predictors and individual-level explanations. ML strategies based on clinical data may anticpate heart surgery postoperative mortality better than clinical grading methods. Explanatory models can account for affecting factors to provide tailored risk profiles. These machine learning-driven models need more prospective multicenter studies to prove their therapeutic efficacy.

关键词： Heart Support vector machines Radio frequency Additives Sensitivity Surgery Mortality Machine learning Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Data Mining for Predictive Modeling of Stroke Risk and Post-Stroke Care Management

Machine Learning and Data Mining for Predictive Modeling of ...

引用

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： Gobi N B.P. Singh Surendra Yadav Department of Computer Science and Information Technology Jain (Deemed to be University) Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science & Application Vivekananda Global University Jaipur India

The research investigates the efficacy of a comprehensive machine learning and data mining approach in predictive modeling of stroke risk and post-stroke care management. A holistic methodology is proposed, integrating diverse datasets and advanced algorithms, including Logistic Regression, Random Forest, and Long Short-Term Memory (LSTM) networks. Data preprocessing, feature extraction, and personalized care plan generation are key components. Performance evaluation using accuracy, sensitivity, specificity, precision, F1 Score, AUC, and MAE demonstrates the superior predictive capabilities and efficiency of the proposed method compared to traditional approaches. The study highlights the potential for revolutionizing stroke care, emphasizing personalized risk assessment and post-stroke management for improved patient outcomes and healthcare delivery.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Bone Metastatic Cancer Origin Prediction Using Deep Learning on Digital Pathological

A Bone Metastatic Cancer Origin Prediction Using Deep Learni...

引用

computer, Electronics & Electrical Engineering & their applications (IC2E3), International Conference on

作者： Gopal Kumar Thakur Shridhar Kulkarni Shahnawaz Khan Madan Mohan Tito Ayyalasomayajula Pundru Chandra Shaker Reddy Department of Data Sciences Harrisburg University of Science & Technology Pennsylvania USA Master of Computer Application Bundelkhand University Jhansi Utter Pradesh India School of Business & Technology Aspen University Phoenix Arizona USA School of Computer Science and Artificial Intelligence SR University Warangal Telangana India

ISBN: (数字)9798350388534

ISBN: (纸本)9798350388541

The key to effective treatment for bone cancers is a precise imaging diagnosis. The diagnosis process might be improved with the introduction of AI and machine-learning(ML) techniques for characterizing and evaluating bone tumors on different imaging modalities. When it comes to clinical treatments, knowing where bone metastasis cancer (OBMC) originated is crucial. With little clinical data and bone biopsy, OBMC determination is difficult for pathologists. In order to forecast the OBMC from hematoxylineosin (H&E) stained slides alone, we developed a regional multiple-instance learning algorithms. We trained the model with data from 1041 instances across 8 institutions and 26,431 areas of interest that were tagged. External validation and ten-fold cross validation were used to evaluate the model's performance. Using top3 predictions as a guide, we ran an IHC test on 175cases with unclear origins to see how well the model's predictions matched up with the results shown by the markers. We also used the model to determine if a tumor was present in a specific area and to differentiate between neuroendocrine tumors, squamous cell carcinoma, and adenocarcinoma. With a 98.98% success rate in tumor detection and a 93.85% success rate in differentiating between three cancer kinds, the suggested model was a clear winner. Our model showed promise in assisting pathologists in accurately diagnosing the OBMC and performed well when used to predict the OBMC from standard histology.

关键词： Squamous cell carcinoma Histopathology Predictive models Bones Data models Software Standards Medical diagnostic imaging Cancer Tumors

来源：评论

学校读者我要写书评

暂无评论

FedBCD: Federated Ultrasound Video and Image Joint Learning for Breast Cancer Diagnosis

引用

IEEE Transactions on Medical Imaging 2025年第6期44卷 2395-2407页

作者： Deng, Tianpeng Huang, Chunwang Cai, Ming Liu, Yu Liu, Min Lin, Jiatai Shi, Zhenwei Zhao, Bingchao Huang, Jingqi Liang, Changhong Han, Guoqiang Liu, Zaiyi Wang, Ying Han, Chu South China University of Technology School of Computer Science and Engineering Guangdong Guangzhou510006 China Department of Ultrasound Guangzhou510080 China Department of Radiology Guangzhou510080 China Guangdong Prov. Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China Sun Yat-sen University Cancer Center Collaborative Innovation Center for Cancer Medicine Department of Ultrasound State Key Laboratory of Oncology in South China Guangzhou China The First Affiliated Hospital of Guangzhou Medical University Department of Medical Ultrasonics Guangzhou China

Ultrasonography plays an essential role in breast cancer diagnosis. Current deep learning based studies train the models on either images or videos in a centralized learning manner, lacking consideration of joint benefits between two different modality models or the privacy issue of data centralization. In this study, we propose the first decentralized learning solution for joint learning with breast ultrasound video and image, called FedBCD. To enable the model to learn from images and videos simultaneously and seamlessly in client-level local training, we propose a Joint Ultrasound Video and Image Learning (JUVIL) model to bridge the dimension gap between video and image data by incorporating temporal and spatial adapters. The parameter-efficient design of JUVIL with trainable adapters and frozen backbone further reduces the computational cost and communication burden of federated learning, finally improving the overall efficiency. Moreover, considering conventional model-wise aggregation may lead to unstable federated training due to different modalities, data capacities in different clients, and different functionalities across layers. We further propose a Fisher information matrix (FIM) guided Layer-wise Aggregation method named FILA. By measuring layer-wise sensitivity with FIM, FILA assigns higher contributions to the clients with lower sensitivity, improving personalized performance during federated training. Extensive experiments on three image clients and one video client demonstrate the benefits of joint learning architecture, especially for the ones with small-scale data. FedBCD significantly outperforms nine federated learning methods on both video-based and image-based diagnoses, demonstrating the superiority and potential for clinical practice. Code is released at https://***/tianpeng-deng/FedBCD. © 1982-2012 IEEE.

关键词： Fisher information matrix

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Aided Intelligent Framework for Condition Monitoring of Electrical Machinery 5

A Deep Learning Aided Intelligent Framework for Condition Mo...

引用

5th International Conference on Devices for Integrated Circuit, DevIC 2023

作者： Ganguly, Biswarup Ray, Radha Kumari Chatterjee, Arunava Paul, Subho Meghnad Saha Institute of Technology Electrical Engineering Department Kolkata India Application Development Associate Accenture Kolkata India Raghunathpur Govt. Polytechnic Electrical Engineering Department Purulia India Washington State University School of Electrical Engineering and Computer Science PullmanWA United States

ISBN: (纸本)9798350347265

Single-phase induction motors (SPIM) are fairly efficiently employed in household devices and possess wide applications in the industrial system. Typically, current signature-Analysis (CSA) based methods have been used for fault diagnosis, but not always been an efficient solution, especially for fractional kW SPIMs that may be replaced entirely iffaulty. This paper presents a deep learning (DL) based fault detection scheme of a SPIM which is in-service in household devices. The fault detection is done employing a wavelet based deep dense convolutional neural network (W-D2CNN), where several wavelets are used as convolutional filters for convolution operation. The convoluted feature maps are further passed through a proposed nonlinearity, i.e., SLReLU, for richer feature extraction. The uniqueness of the proposed method lies in the feature learning ability, where upper-And lower-layer features of the dense block fuse via concatenation operation. Also, the SL-ReLU has been designed to combine logarithmic function, softsign, and ReLU operation. The designed SL-ReLU minimizes the probability of convoluted output and gradient explosion, due to which training has been improved along with feature learning ability. Comprehensive results reveal the efficacy of the proposed work in terms of performance metrics with state-of-The-Art DL frameworks using the same dataset. The proposed work can also be extendable to multiphase-induction machines or any other electrical device working in any environment for fault identification. © 2023 IEEE.

关键词： Failure analysis

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：