检索结果-内蒙古大学图书馆

Preparation of Rich Lists of Research Gaps in the Specific Sentiment Analysis Tasks of Code-mixed Indian Languages

SN computer science 2024年第1期5卷 117页

作者： Saini, Jatinderkumar R. Roy, Saikat Symbiosis Institute of Computer Studies and Research Symbiosis International (Deemed University) Pune India Faculty of Computational Science Department of Computer Science National Defence Academy Pune India

Sentiment Analysis (SA) task for code-mixed Romanized text is an emerging area of research in Natural Language Processing (NLP). Since informal expression of sentiments in Romanized code-mixed Indian Languages (ILs) with emojis and/or emoticons is very common in social media, SA tasks for code-mixed posts/comments on ILs are being paid much attention by researchers. In the present survey, we have studied the evolution of language models over time, dataset details, research gaps, challenges towards building advanced models, possible recommendations to overcome those challenges, and determining the best-performing language models only for SA task on eight code-mixed ILs, namely Bengali–English, Hind–English, Kannada–English, Malayalam–English, Marathi–English, Punjabi–English, Telugu–English, and Tamil–English. Though many researchers have already explored the state-of-art text representation models for the SA task of resource-rich English language, contextual understanding and semantic feature extraction from non-standard code-mixed Romanized text of under-resourced ILs are yet to be explored to a large extent due to resource scarcity. We have focused on an exhaustive and comprehensive survey of very specific 70 research papers on SA tasks to list open research areas on code-mixed ILs. The present work will benefit researchers by providing a clear direction for future research scope in SA task in code-mixed IL pairs. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Attention-based models Deep learning-based model Lexicon-based models Machine learning (ML)

来源：评论

学校读者我要写书评

暂无评论

A Logic Programming Approach to VM Placement 14

A Logic Programming Approach to VM Placement

引用

14th International Conference on Cloud Computing and Services science, CLOSER 2024

作者： Andreoli, Remo Forti, Stefano Pannocchi, Luigi Cucinotta, Tommaso Brogi, Antonio Sant’Anna School of Advanced Studies Pisa Italy Department of Computer Science University of Pisa Pisa Italy

ISBN: (纸本)9789897587016

Placing virtual machines so to minimize the number of used physical hosts is an utterly important problem in cloud computing and next-generation virtualized networks. This article proposes a declarative reasoning methodology, and its open-source prototype, including four heuristic strategies to tackle this problem. Our proposal is extensively assessed over real data from an industrial case study and compared to state-of-the-art approaches, both in terms of execution times and solution optimality. As a result, our declarative approach determines placements that are only 6% far from optimal, outperforming a state-of-the-art genetic algorithm in terms of execution times, and a first-fit search for optimality of found placements. Last, its pipelining with a mathematical programming solution improves execution times of the latter by one order of magnitude on average, compared to using a genetic algorithm as a primer. © 2024 by SCITEPRESS – science and Technology Publications, Lda.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 528-538页

作者： Xiaorui Li Xiaojuan Ban Haoran Qiao Zhaolin Yuan Hong-Ning Dai Chao Yao Yu Guo Mohammad S.Obaidat George Q.Huang the School of Intelligence Science and Technology University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering the Key Laboratory of Intelligent Bionic Unmanned Systems and the Institute of Materials Intelligent Technology Liaoning Academy of Materials IEEE the Department of Computer Science Hong Kong Baptist University the School of Computer and Communication Engineering Key Laboratory of Advanced Materials and Devices for Post-Moore Chips Ministry of Education University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing the School of Computer and Communication Engineering University of Science and Technology Beijing the King Abdullah Ⅱ School of Information Technology The University of Jordan the Department of Computational Intelligence the School of Computing SRM University the School of Engineering The Amity University The Hong Kong Polytechnic University

In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network(MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with75% middle localization F1 score.

关键词： Eddy current testing nondestructive testing semantic segmentation time series analysis

来源：评论

学校读者我要写书评

暂无评论

Protection of Hazardous Places in Industries using Machine Learning 5

Protection of Hazardous Places in Industries using Machine L...

引用

5th International Conference on Emerging Smart Computing and Informatics, ESCI 2023

作者： Sankarasubramanian, Praveen Vels Institute of Science Technology and Advanced Studies Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9781665475242

Extreme precautions must be observed to handle toxic wastes, radioactive substances, chemical raw materials, chemical wastes, and bio-products in different industries. Any malfunction in a dangerous traffic network can lead to serious accidents, deaths and / or serious damage. Direct monitoring and analysis, and preventive measures to prevent the spread of failures, can significantly reduce the recurrence of adverse effects. Current research suggests that detailed publicity and information on the latest developments in pipeline monitoring and research may help modernize the oil industry in the future. We also propose a framework to detect timely leakage in pipelines, especially in oil and gas sector. © 2023 IEEE.

关键词： Toxic materials

来源：评论

学校读者我要写书评

暂无评论

A Music Recommender System to Identify the Emotional State of a Person Using Machine Learning Algorithms 4

A Music Recommender System to Identify the Emotional State o...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Muruganantham, A. Malarvizhi, C. Divya Vahini, S. Saranya, D. Uthiramoorthy, A. Karnataka Bengaluru India Psg Institute of Advanced Studies Department of Computer Science Coimbatore India Dr.Mahalingam College of Engineering and Technology Department of Computer Applications Tamil Nadu Pollachi India Sri Eshwar College of Engineering Department of Information Technology Coimbatore India Rathinam College of Arts and Science Department of Computer Science India

ISBN: (纸本)9798331523923

In today's digital world, customized recommendation algorithms can improve user experiences in many different areas. Within the sphere of intelligent human-technology interaction, this paper specifically examines a music recommender system driven by machine learning algorithms. It figures out what mood users are in and can provide an appropriate response in real time. The system being propounded in this essay uses advanced technology in facial expression recognition. With the help of a webcam, it aims to accurately detect user emotions, including joy, sadness, and anger. Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN) and Support Vector Machines (SVM) have been employed to effectively classify people's mood and recommend an appropriate song. Our extensive tests and examinations show that CNN, RNN, and SVM models are all very good at guessing users' moods - with high precision, recall, F1-score, and accuracy percentages. Furthermore, in-depth analyses like confusion matrixes illuminate how well each model serves as an emotion recognizer. This study's findings are representative of future prospects in affective computing around the globe with major implications for intelligent recommendation systems to which it's important that the models are sensitive. In conclusion, the suggested Music Recommender System is something new for taking a more personal view: We can be as deeply entertained as the web allows us to be - make tailored entertainment paths in the digital era. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Transformative Transfer Learning for MRI Brain Tumor Precision: Innovative Insights

引用

IEEE Access 2025年 13卷 31749-31761页

作者： Anwar, Raja Waseem Abrar, Mohammad Ullah, Faizan German University of Technology in Oman Department of Computer Science Muscat130 Oman Arab Open University Faculty of Computer Studies Muscat122 Oman Institute of Neuroscience and Medicine Forschungszentrum Jülich Jülich52428 Germany

Accurate brain tumor detection is essential for effective treatment and improved patient outcomes, yet conventional MRI classification methods often struggle with complex and variable imaging data. This study introduces the Transformative Transfer Learning (TTL) model, leveraging pre-trained deep neural networks fine-tuned for MRI brain tumor classification, using datasets from Nickparvar and Cheng. High-quality inputs were achieved through preprocessing, including resizing, normalization, noise reduction, and data augmentation. The TTL model, employing architectures such as VGG16, ResNet-50, InceptionV3, and DenseNet-121, demonstrated a substantial improvement over traditional methods, achieving an accuracy of 94.5%, sensitivity of 92.8%, and specificity of 93.1%. Additionally, the model yielded a precision of 93.2%, recall of 92.8%, F1-score of 93.0%, and true positive and true negative rates of 92.8% and 93.1%, respectively. Training and validation loss values of 0.15 and 0.18 confirm effective model convergence. These metrics underscore the model’s potential as a robust tool in clinical diagnostics, providing a pathway to more accurate and efficient MRI-based brain tumor detection. © 2025 The Authors.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

14-Bit SAR ADC with on-Chip Digital Bubble Sorting Calibration Technology

引用

Chinese Journal of Electronics 2025年第1期34卷 125-136页

作者： Hua Fan Zhuorui Chen Tongrui Xu Franco Maloberti Qi Wei Quanyuan Feng School of Integrated Circuit Science and Engineering(Exemplary School of Microelectronics) University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Chongqing Institute of Microelectronics Industry Technology University of Electronic Science and Technology of China Department of Electrical Computer and Biomedical Engineering University of Pavia Department of Precision Instrument Tsinghua University Institute of Microelectronics Southwest Jiaotong University

This article designs a 14-bit successive approximation register analog-to-digital converter（SAR ADC）.A novel digital bubble sorting calibration method is proposed and applied to eliminate the effect of capacitor mismatch on the linearity of the SAR ADC. To reduce the number of capacitors, a hybrid architecture of a high 8-bit binary-weighted capacitor array and a low 6-bit resistor array is adopted by the digital-to-analog（DAC）. The common-mode voltage VCM-based switching scheme is chosen to reduce the switching energy and area of the DAC. The time-domain comparator is employed to obtain lower power consumption. Sampling is performed through a gate voltage bootstrapped switch to reduce the nonlinear errors introduced when sampling the input signal. Moreover, the SAR logic and the whole calibration is totally implemented on-chip through digital integrated circuit（IC） tools such as design compiler, IC compiler, etc. Finally, a prototype is designed and implemented using 0.18 μm bipolar-complementary metal oxide semiconductor（CMOS）-double-diffused MOS 1.8 V CMOS technology. The measurement results show that the SAR ADC with on-chip bubble sorting calibration method achieves the signal-to-noise-and-distortion ratio of 69.75 dB and the spurious-free dynamic range of 83.77 dB.

关键词： Semiconductor device measurement Capacitors Linearity Switches Calibration System-on-chip Frequency measurement Time-domain analysis Sorting Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Revisiting SATZilla Features in 2024 27

Revisiting SATZilla Features in 2024

引用

27th International Conference on Theory and Applications of Satisfiability Testing, SAT 2024

作者： Shavit, Hadar Hoos, Holger H. RWTH Aachen University Germany Leiden Institute of Advanced Computer Science Leiden University Netherlands Department of Computer Science University of British Columbia Vancouver Canada

ISBN: (纸本)9783959773348

Boolean satisfiability (SAT) is an NP-complete problem with important applications, notably in hardware and software verification. Characterising a SAT instance by a set of features has shown great potential for various tasks, ranging from algorithm selection to benchmark generation. In this work, we revisit the widely used SATZilla features and introduce a new version of the tool used to compute them. In particular, we utilise a new preprocessor and SAT solvers, adjust the code to accommodate larger formulas, and determine better settings of the feature extraction time limits. We evaluate the extracted features on three downstream tasks: satisfiability prediction, running time prediction, and algorithm selection. We observe that our new tool is able to extract features from a broader range of instances than before. We show that the new version of the feature extractor produces features that achieve up to 26% lower RMSE for running time prediction, up to 3% higher accuracy for satisfiability prediction, and up to 15 times higher closed gap for algorithm selection on benchmarks from recent SAT competitions. © Hadar Shavit and Holger H. Hoos.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Meteorological Downscaling Based on Dual Learning and Subgrid-scale Auxiliary Information

引用

Advances in Atmospheric sciences 2025年第1期42卷 53-66页

作者： Jing HU Jialing MU Xiaomeng HUANG Xi WU Department of Computer Science Chengdu University of Information TechnologyChengdu 610225China Department of Earth System Science Ministry of Education Key Laboratory for Earth System ModelingInstitute for Global Change StudiesTsinghua UniversityBeijing 100084China

Climate downscaling is used to transform large-scale meteorological data into small-scale data with enhanced detail,which finds wide applications in climate modeling,numerical weather forecasting,and renewable *** deeplearning-based downscaling methods effectively capture the complex nonlinear mapping between meteorological data of varying scales,the supervised deep-learning-based downscaling methods suffer from insufficient high-resolution data in practice,and unsupervised methods struggle with accurately inferring small-scale specifics from limited large-scale inputs due to small-scale *** article presents DualDS,a dual-learning framework utilizing a Generative Adversarial Network–based neural network and subgrid-scale auxiliary information for climate *** a learning method is unified in a two-stream framework through up-and downsamplers,where the downsampler is used to simulate the information loss process during the upscaling,and the upsampler is used to reconstruct lost details and correct errors incurred during the *** dual learning strategy can eliminate the dependence on high-resolution ground truth data in the training process and refine the downscaling results by constraining the mapping *** findings demonstrate that DualDS is comparable to several state-of-the-art deep learning downscaling approaches,both qualitatively and ***,for a single surface-temperature data downscaling task,our method is comparable with other unsupervised algorithms with the same dataset,and we can achieve a 0.469 dB higher peak signal-to-noise ratio,0.017 higher structural similarity,0.08 lower RMSE,and the best correlation *** summary,this paper presents a novel approach to addressing small-scale uncertainty issues in unsupervised downscaling processes.

关键词： downscaling unsupervised deep learning dual learning auxiliary information

来源：评论

学校读者我要写书评

暂无评论

A Robotic Arm Vehicle using Voice Recognition for Physically Challenged People 2

A Robotic Arm Vehicle using Voice Recognition for Physically...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Nannda, Jia Dora, Lokareddy Venkanna Gupta, Tanvi Chouhan, Aryan Verma, Anmol Department of Computer Science and Engineering Manav Rachna International Institute of Research and Studies India Department of Computer Science and Engineering Manav Rachna International Institute of Research and Studies Faridabad India Department of electrical and electronics engineering Manav Rachna International Institute of Research and Studies India

ISBN: (纸本)9798331541217

In Today's world, all the work is automated by robots. The Robots have become a significant part of today's world, improving many people's lives, especially those who are physically challenged. This research paper presents a unique method for helping people with physical disabilities: A robotic arm vehicle using voice recognition for physically challenged people. Two remarkable features of the robot are its design and its adaptability in handling objects accurately. The comparative research demonstrates improved performance, such as faster job completion and increased grasping efficiency, when compared to older methods. Additionally, by integrating AI, the robotic arm gains the flexibility needed to operate in real-world environments. This finding might lead to more autonomous and effective assistive technology for personal support and healthcare applications. © 2024 IEEE.

关键词： Robotic arms

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：